- Linux-stable-mirror - lists.linaro.org

Patch "dmaengine: dmatest: fix container_of member in dmatest_callback" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled dmaengine: dmatest: fix container_of member in dmatest_callback to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: dmaengine-dmatest-fix-container_of-member-in-dmatest_callback.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 66b3bd2356e0a1531c71a3dcf96944621e25c17c Mon Sep 17 00:00:00 2001 From: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> Date: Mon, 29 Jan 2018 14:40:11 +0800 Subject: dmaengine: dmatest: fix container_of member in dmatest_callback From: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> commit 66b3bd2356e0a1531c71a3dcf96944621e25c17c upstream. The type of arg passed to dmatest_callback is struct dmatest_done. It refers to test_done in struct dmatest_thread, not done_wait. Fixes: 6f6a23a213be ("dmaengine: dmatest: move callback wait ...") Signed-off-by: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> Acked-by: Adam Wallis <awallis(a)codeaurora.org> Signed-off-by: Vinod Koul <vinod.koul(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/dma/dmatest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -339,7 +339,7 @@ static void dmatest_callback(void *arg) { struct dmatest_done *done = arg; struct dmatest_thread *thread = - container_of(arg, struct dmatest_thread, done_wait); + container_of(done, struct dmatest_thread, test_done); if (!thread->done) { done->done = true; wake_up_all(done->wait); Patches currently in stable-queue which might be from shunyong.yang(a)hxt-semitech.com are queue-4.9/dmaengine-dmatest-fix-container_of-member-in-dmatest_callback.patch

7 years, 4 months

1
0
0 0

Patch "CIFS: zero sensitive data when freeing" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled CIFS: zero sensitive data when freeing to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-zero-sensitive-data-when-freeing.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 97f4b7276b829a8927ac903a119bef2f963ccc58 Mon Sep 17 00:00:00 2001 From: Aurelien Aptel <aaptel(a)suse.com> Date: Thu, 25 Jan 2018 15:59:39 +0100 Subject: CIFS: zero sensitive data when freeing From: Aurelien Aptel <aaptel(a)suse.com> commit 97f4b7276b829a8927ac903a119bef2f963ccc58 upstream. also replaces memset()+kfree() by kzfree(). Signed-off-by: Aurelien Aptel <aaptel(a)suse.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Reviewed-by: Pavel Shilovsky <pshilov(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/cifsencrypt.c | 3 +-- fs/cifs/connect.c | 6 +++--- fs/cifs/misc.c | 14 ++++---------- 3 files changed, 8 insertions(+), 15 deletions(-) --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -318,9 +318,8 @@ int calc_lanman_hash(const char *passwor { int i; int rc; - char password_with_pad[CIFS_ENCPWD_SIZE]; + char password_with_pad[CIFS_ENCPWD_SIZE] = {0}; - memset(password_with_pad, 0, CIFS_ENCPWD_SIZE); if (password) strncpy(password_with_pad, password, CIFS_ENCPWD_SIZE); --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1667,7 +1667,7 @@ cifs_parse_mount_options(const char *mou tmp_end++; if (!(tmp_end < end && tmp_end[1] == delim)) { /* No it is not. Set the password to NULL */ - kfree(vol->password); + kzfree(vol->password); vol->password = NULL; break; } @@ -1705,7 +1705,7 @@ cifs_parse_mount_options(const char *mou options = end; } - kfree(vol->password); + kzfree(vol->password); /* Now build new password string */ temp_len = strlen(value); vol->password = kzalloc(temp_len+1, GFP_KERNEL); @@ -4159,7 +4159,7 @@ cifs_construct_tcon(struct cifs_sb_info reset_cifs_unix_caps(0, tcon, NULL, vol_info); out: kfree(vol_info->username); - kfree(vol_info->password); + kzfree(vol_info->password); kfree(vol_info); return tcon; --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -99,14 +99,11 @@ sesInfoFree(struct cifs_ses *buf_to_free kfree(buf_to_free->serverOS); kfree(buf_to_free->serverDomain); kfree(buf_to_free->serverNOS); - if (buf_to_free->password) { - memset(buf_to_free->password, 0, strlen(buf_to_free->password)); - kfree(buf_to_free->password); - } + kzfree(buf_to_free->password); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); - kfree(buf_to_free->auth_key.response); - kfree(buf_to_free); + kzfree(buf_to_free->auth_key.response); + kzfree(buf_to_free); } struct cifs_tcon * @@ -137,10 +134,7 @@ tconInfoFree(struct cifs_tcon *buf_to_fr } atomic_dec(&tconInfoAllocCount); kfree(buf_to_free->nativeFileSystem); - if (buf_to_free->password) { - memset(buf_to_free->password, 0, strlen(buf_to_free->password)); - kfree(buf_to_free->password); - } + kzfree(buf_to_free->password); kfree(buf_to_free); } Patches currently in stable-queue which might be from aaptel(a)suse.com are queue-4.9/cifs-zero-sensitive-data-when-freeing.patch

7 years, 4 months

1
0
0 0

Patch "dccp: CVE-2017-8824: use-after-free in DCCP code" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled dccp: CVE-2017-8824: use-after-free in DCCP code to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: dccp-cve-2017-8824-use-after-free-in-dccp-code.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 69c64866ce072dea1d1e59a0d61e0f66c0dffb76 Mon Sep 17 00:00:00 2001 From: Mohamed Ghannam <simo.ghannam(a)gmail.com> Date: Tue, 5 Dec 2017 20:58:35 +0000 Subject: dccp: CVE-2017-8824: use-after-free in DCCP code From: Mohamed Ghannam <simo.ghannam(a)gmail.com> commit 69c64866ce072dea1d1e59a0d61e0f66c0dffb76 upstream. Whenever the sock object is in DCCP_CLOSED state, dccp_disconnect() must free dccps_hc_tx_ccid and dccps_hc_rx_ccid and set to NULL. Signed-off-by: Mohamed Ghannam <simo.ghannam(a)gmail.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/dccp/proto.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -259,6 +259,7 @@ int dccp_disconnect(struct sock *sk, int { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); int err = 0; const int old_state = sk->sk_state; @@ -278,6 +279,10 @@ int dccp_disconnect(struct sock *sk, int sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = NULL; + dp->dccps_hc_tx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); Patches currently in stable-queue which might be from simo.ghannam(a)gmail.com are queue-4.9/dccp-cve-2017-8824-use-after-free-in-dccp-code.patch

7 years, 4 months

1
0
0 0

Patch "cifs: Fix missing put_xid in cifs_file_strict_mmap" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled cifs: Fix missing put_xid in cifs_file_strict_mmap to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-fix-missing-put_xid-in-cifs_file_strict_mmap.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From f04a703c3d613845ae3141bfaf223489de8ab3eb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox <mawilcox(a)microsoft.com> Date: Fri, 15 Dec 2017 12:48:32 -0800 Subject: cifs: Fix missing put_xid in cifs_file_strict_mmap From: Matthew Wilcox <mawilcox(a)microsoft.com> commit f04a703c3d613845ae3141bfaf223489de8ab3eb upstream. If cifs_zap_mapping() returned an error, we would return without putting the xid that we got earlier. Restructure cifs_file_strict_mmap() and cifs_file_mmap() to be more similar to each other and have a single point of return that always puts the xid. Signed-off-by: Matthew Wilcox <mawilcox(a)microsoft.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/file.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3285,20 +3285,18 @@ static const struct vm_operations_struct int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) { - int rc, xid; + int xid, rc = 0; struct inode *inode = file_inode(file); xid = get_xid(); - if (!CIFS_CACHE_READ(CIFS_I(inode))) { + if (!CIFS_CACHE_READ(CIFS_I(inode))) rc = cifs_zap_mapping(inode); - if (rc) - return rc; - } - - rc = generic_file_mmap(file, vma); - if (rc == 0) + if (!rc) + rc = generic_file_mmap(file, vma); + if (!rc) vma->vm_ops = &cifs_file_vm_ops; + free_xid(xid); return rc; } @@ -3308,16 +3306,16 @@ int cifs_file_mmap(struct file *file, st int rc, xid; xid = get_xid(); + rc = cifs_revalidate_file(file); - if (rc) { + if (rc) cifs_dbg(FYI, "Validation prior to mmap failed, error=%d\n", rc); - free_xid(xid); - return rc; - } - rc = generic_file_mmap(file, vma); - if (rc == 0) + if (!rc) + rc = generic_file_mmap(file, vma); + if (!rc) vma->vm_ops = &cifs_file_vm_ops; + free_xid(xid); return rc; } Patches currently in stable-queue which might be from mawilcox(a)microsoft.com are queue-4.9/cifs-fix-missing-put_xid-in-cifs_file_strict_mmap.patch

7 years, 4 months

1
0
0 0

Patch "cifs: Fix autonegotiate security settings mismatch" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled cifs: Fix autonegotiate security settings mismatch to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-fix-autonegotiate-security-settings-mismatch.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 9aca7e454415f7878b28524e76bebe1170911a88 Mon Sep 17 00:00:00 2001 From: Daniel N Pettersson <danielnp(a)axis.com> Date: Thu, 11 Jan 2018 16:00:12 +0100 Subject: cifs: Fix autonegotiate security settings mismatch From: Daniel N Pettersson <danielnp(a)axis.com> commit 9aca7e454415f7878b28524e76bebe1170911a88 upstream. Autonegotiation gives a security settings mismatch error if the SMB server selects an SMBv3 dialect that isn't SMB3.02. The exact error is "protocol revalidation - security settings mismatch". This can be tested using Samba v4.2 or by setting the global Samba setting max protocol = SMB3_00. The check that fails in smb3_validate_negotiate is the dialect verification of the negotiate info response. This is because it tries to verify against the protocol_id in the global smbdefault_values. The protocol_id in smbdefault_values is SMB3.02. In SMB2_negotiate the protocol_id in smbdefault_values isn't updated, it is global so it probably shouldn't be, but server->dialect is. This patch changes the check in smb3_validate_negotiate to use server->dialect instead of server->vals->protocol_id. The patch works with autonegotiate and when using a specific version in the vers mount option. Signed-off-by: Daniel N Pettersson <danielnp(a)axis.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/smb2pdu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -585,8 +585,7 @@ int smb3_validate_negotiate(const unsign } /* check validate negotiate info response matches what we got earlier */ - if (pneg_rsp->Dialect != - cpu_to_le16(tcon->ses->server->vals->protocol_id)) + if (pneg_rsp->Dialect != cpu_to_le16(tcon->ses->server->dialect)) goto vneg_out; if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode)) Patches currently in stable-queue which might be from danielnp(a)axis.com are queue-4.9/cifs-fix-autonegotiate-security-settings-mismatch.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [stable] Security fixes

by Ben Hutchings

Please queue up the following fixes for stable: [all] 3d932ee27e85 media: dvb-usb-v2: lmedm04: Improve logic checking of warm start 7bf7a7116ed3 media: dvb-usb-v2: lmedm04: move ts2020 attach to dm04_lme2510_tuner [4.9 4.14 4.15] c0f71bbb8102 media: hdpvr: Fix an error handling path in hdpvr_probe() [4.4 4.9 4.14] ae6650163c66 loop: fix concurrent lo_open/lo_release Ben. -- Ben Hutchings Software Developer, Codethink Ltd.

7 years, 4 months

2
3
0 0

[Linux-stable-mirror] sched/wait: Fix add_wait_queue() behavioral change

by Tetsuo Handa

Recently, we are seeing I/O hungup reports. I don't know whether a regression introduced by commit 50816c48997af857 ("sched/wait: Standardize internal naming of wait-queue entries") is relevant. But shouldn't we backport commit c6b9d9a330290144 ("sched/wait: Fix add_wait_queue() behavioral change") to 4.13+ kernels anyway?

7 years, 4 months

5
5
0 0

Patch "watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: watchdog-gpio_wdt-set-wdog_hw_running-in-gpio_wdt_stop.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From bc137dfdbec27c0ec5731a89002daded4a4aa1ea Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes <rasmus.villemoes(a)prevas.dk> Date: Thu, 9 Nov 2017 14:39:55 +0100 Subject: watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop From: Rasmus Villemoes <rasmus.villemoes(a)prevas.dk> commit bc137dfdbec27c0ec5731a89002daded4a4aa1ea upstream. The first patch above (https://patchwork.kernel.org/patch/9970181/) makes the oops go away, but it just papers over the problem. The real problem is that the watchdog core clears WDOG_HW_RUNNING in watchdog_stop, and the gpio driver fails to set it in its stop function when it doesn't actually stop it. This means that the core doesn't know that it now has responsibility for petting the device, in turn causing the device to reset the system (I hadn't noticed this because the board I'm working on has that reset logic disabled). How about this (other drivers may of course have the same problem, I haven't checked). One might say that ->stop should return an error when the device can't be stopped, but OTOH this brings parity between a device without a ->stop method and a GPIO wd that has always-running set. IOW, I think ->stop should only return an error when an actual attempt to stop the hardware failed. From: Rasmus Villemoes <rasmus.villemoes(a)prevas.dk> The watchdog framework clears WDOG_HW_RUNNING before calling ->stop. If the driver is unable to stop the device, it is supposed to set that bit again so that the watchdog core takes care of sending heart-beats while the device is not open from user-space. Update the gpio_wdt driver to honour that contract (and get rid of the redundant clearing of WDOG_HW_RUNNING). Fixes: 3c10bbde10 ("watchdog: core: Clear WDOG_HW_RUNNING before calling the stop function") Signed-off-by: Rasmus Villemoes <rasmus.villemoes(a)prevas.dk> Reviewed-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Wim Van Sebroeck <wim(a)iguana.be> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/watchdog/gpio_wdt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/drivers/watchdog/gpio_wdt.c +++ b/drivers/watchdog/gpio_wdt.c @@ -80,7 +80,8 @@ static int gpio_wdt_stop(struct watchdog if (!priv->always_running) { gpio_wdt_disable(priv); - clear_bit(WDOG_HW_RUNNING, &wdd->status); + } else { + set_bit(WDOG_HW_RUNNING, &wdd->status); } return 0; Patches currently in stable-queue which might be from rasmus.villemoes(a)prevas.dk are queue-4.14/watchdog-gpio_wdt-set-wdog_hw_running-in-gpio_wdt_stop.patch

7 years, 4 months

1
0
0 0

Patch "sched/wait: Fix add_wait_queue() behavioral change" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled sched/wait: Fix add_wait_queue() behavioral change to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: sched-wait-fix-add_wait_queue-behavioral-change.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From c6b9d9a33029014446bd9ed84c1688f6d3d4eab9 Mon Sep 17 00:00:00 2001 From: Omar Sandoval <osandov(a)fb.com> Date: Tue, 5 Dec 2017 23:15:31 -0800 Subject: sched/wait: Fix add_wait_queue() behavioral change From: Omar Sandoval <osandov(a)fb.com> commit c6b9d9a33029014446bd9ed84c1688f6d3d4eab9 upstream. The following cleanup commit: 50816c48997a ("sched/wait: Standardize internal naming of wait-queue entries") ... unintentionally changed the behavior of add_wait_queue() from inserting the wait entry at the head of the wait queue to the tail of the wait queue. Beyond a negative performance impact this change in behavior theoretically also breaks wait queues which mix exclusive and non-exclusive waiters, as non-exclusive waiters will not be woken up if they are queued behind enough exclusive waiters. Signed-off-by: Omar Sandoval <osandov(a)fb.com> Reviewed-by: Jens Axboe <axboe(a)kernel.dk> Acked-by: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: kernel-team(a)fb.com Fixes: ("sched/wait: Standardize internal naming of wait-queue entries") Link: http://lkml.kernel.org/r/a16c8ccffd39bd08fdaa45a5192294c784b803a7.151254432… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- kernel/sched/wait.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -27,7 +27,7 @@ void add_wait_queue(struct wait_queue_he wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - __add_wait_queue_entry_tail(wq_head, wq_entry); + __add_wait_queue(wq_head, wq_entry); spin_unlock_irqrestore(&wq_head->lock, flags); } EXPORT_SYMBOL(add_wait_queue); Patches currently in stable-queue which might be from osandov(a)fb.com are queue-4.14/sched-wait-fix-add_wait_queue-behavioral-change.patch

7 years, 4 months

1
0
0 0

Patch "sched/rt: Use container_of() to get root domain in rto_push_irq_work_func()" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled sched/rt: Use container_of() to get root domain in rto_push_irq_work_func() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: sched-rt-use-container_of-to-get-root-domain-in-rto_push_irq_work_func.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From ad0f1d9d65938aec72a698116cd73a980916895e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> Date: Tue, 23 Jan 2018 20:45:37 -0500 Subject: sched/rt: Use container_of() to get root domain in rto_push_irq_work_func() From: Steven Rostedt (VMware) <rostedt(a)goodmis.org> commit ad0f1d9d65938aec72a698116cd73a980916895e upstream. When the rto_push_irq_work_func() is called, it looks at the RT overloaded bitmask in the root domain via the runqueue (rq->rd). The problem is that during CPU up and down, nothing here stops rq->rd from changing between taking the rq->rd->rto_lock and releasing it. That means the lock that is released is not the same lock that was taken. Instead of using this_rq()->rd to get the root domain, as the irq work is part of the root domain, we can simply get the root domain from the irq work that is passed to the routine: container_of(work, struct root_domain, rto_push_work) This keeps the root domain consistent. Reported-by: Pavan Kondeti <pkondeti(a)codeaurora.org> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mike Galbraith <efault(a)gmx.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Fixes: 4bdced5c9a292 ("sched/rt: Simplify the IPI based RT balancing logic") Link: http://lkml.kernel.org/r/CAEU1=PkiHO35Dzna8EQqNSKW1fr1y1zRQ5y66X117MG06sQtN… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- kernel/sched/rt.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1907,9 +1907,8 @@ static void push_rt_tasks(struct rq *rq) * the rt_loop_next will cause the iterator to perform another scan. * */ -static int rto_next_cpu(struct rq *rq) +static int rto_next_cpu(struct root_domain *rd) { - struct root_domain *rd = rq->rd; int next; int cpu; @@ -1985,7 +1984,7 @@ static void tell_cpu_to_push(struct rq * * Otherwise it is finishing up and an ipi needs to be sent. */ if (rq->rd->rto_cpu < 0) - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rq->rd); raw_spin_unlock(&rq->rd->rto_lock); @@ -1998,6 +1997,8 @@ static void tell_cpu_to_push(struct rq * /* Called from hardirq context */ void rto_push_irq_work_func(struct irq_work *work) { + struct root_domain *rd = + container_of(work, struct root_domain, rto_push_work); struct rq *rq; int cpu; @@ -2013,18 +2014,18 @@ void rto_push_irq_work_func(struct irq_w raw_spin_unlock(&rq->lock); } - raw_spin_lock(&rq->rd->rto_lock); + raw_spin_lock(&rd->rto_lock); /* Pass the IPI to the next rt overloaded queue */ - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rd); - raw_spin_unlock(&rq->rd->rto_lock); + raw_spin_unlock(&rd->rto_lock); if (cpu < 0) return; /* Try the next RT overloaded CPU */ - irq_work_queue_on(&rq->rd->rto_push_work, cpu); + irq_work_queue_on(&rd->rto_push_work, cpu); } #endif /* HAVE_RT_PUSH_IPI */ Patches currently in stable-queue which might be from rostedt(a)goodmis.org are queue-4.14/sched-rt-use-container_of-to-get-root-domain-in-rto_push_irq_work_func.patch queue-4.14/sched-rt-up-the-root-domain-ref-count-when-passing-it-around-via-ipis.patch

7 years, 4 months

1
0
0 0

Patch "sched/rt: Up the root domain ref count when passing it around via IPIs" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled sched/rt: Up the root domain ref count when passing it around via IPIs to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: sched-rt-up-the-root-domain-ref-count-when-passing-it-around-via-ipis.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 364f56653708ba8bcdefd4f0da2a42904baa8eeb Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> Date: Tue, 23 Jan 2018 20:45:38 -0500 Subject: sched/rt: Up the root domain ref count when passing it around via IPIs From: Steven Rostedt (VMware) <rostedt(a)goodmis.org> commit 364f56653708ba8bcdefd4f0da2a42904baa8eeb upstream. When issuing an IPI RT push, where an IPI is sent to each CPU that has more than one RT task scheduled on it, it references the root domain's rto_mask, that contains all the CPUs within the root domain that has more than one RT task in the runable state. The problem is, after the IPIs are initiated, the rq->lock is released. This means that the root domain that is associated to the run queue could be freed while the IPIs are going around. Add a sched_get_rd() and a sched_put_rd() that will increment and decrement the root domain's ref count respectively. This way when initiating the IPIs, the scheduler will up the root domain's ref count before releasing the rq->lock, ensuring that the root domain does not go away until the IPI round is complete. Reported-by: Pavan Kondeti <pkondeti(a)codeaurora.org> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mike Galbraith <efault(a)gmx.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Fixes: 4bdced5c9a292 ("sched/rt: Simplify the IPI based RT balancing logic") Link: http://lkml.kernel.org/r/CAEU1=PkiHO35Dzna8EQqNSKW1fr1y1zRQ5y66X117MG06sQtN… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- kernel/sched/rt.c | 9 +++++++-- kernel/sched/sched.h | 2 ++ kernel/sched/topology.c | 13 +++++++++++++ 3 files changed, 22 insertions(+), 2 deletions(-) --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1990,8 +1990,11 @@ static void tell_cpu_to_push(struct rq * rto_start_unlock(&rq->rd->rto_loop_start); - if (cpu >= 0) + if (cpu >= 0) { + /* Make sure the rd does not get freed while pushing */ + sched_get_rd(rq->rd); irq_work_queue_on(&rq->rd->rto_push_work, cpu); + } } /* Called from hardirq context */ @@ -2021,8 +2024,10 @@ void rto_push_irq_work_func(struct irq_w raw_spin_unlock(&rd->rto_lock); - if (cpu < 0) + if (cpu < 0) { + sched_put_rd(rd); return; + } /* Try the next RT overloaded CPU */ irq_work_queue_on(&rd->rto_push_work, cpu); --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -661,6 +661,8 @@ extern struct mutex sched_domains_mutex; extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); +extern void sched_get_rd(struct root_domain *rd); +extern void sched_put_rd(struct root_domain *rd); #ifdef HAVE_RT_PUSH_IPI extern void rto_push_irq_work_func(struct irq_work *work); --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -258,6 +258,19 @@ void rq_attach_root(struct rq *rq, struc call_rcu_sched(&old_rd->rcu, free_rootdomain); } +void sched_get_rd(struct root_domain *rd) +{ + atomic_inc(&rd->refcount); +} + +void sched_put_rd(struct root_domain *rd) +{ + if (!atomic_dec_and_test(&rd->refcount)) + return; + + call_rcu_sched(&rd->rcu, free_rootdomain); +} + static int init_rootdomain(struct root_domain *rd) { if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) Patches currently in stable-queue which might be from rostedt(a)goodmis.org are queue-4.14/sched-rt-use-container_of-to-get-root-domain-in-rto_push_irq_work_func.patch queue-4.14/sched-rt-up-the-root-domain-ref-count-when-passing-it-around-via-ipis.patch

7 years, 4 months

1
0
0 0

Patch "powerpc/pseries: include linux/types.h in asm/hvcall.h" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled powerpc/pseries: include linux/types.h in asm/hvcall.h to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: powerpc-pseries-include-linux-types.h-in-asm-hvcall.h.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 1b689a95ce7427075f9ac9fb4aea1af530742b7f Mon Sep 17 00:00:00 2001 From: Michal Suchanek <msuchanek(a)suse.de> Date: Mon, 15 Jan 2018 14:30:03 +0100 Subject: powerpc/pseries: include linux/types.h in asm/hvcall.h From: Michal Suchanek <msuchanek(a)suse.de> commit 1b689a95ce7427075f9ac9fb4aea1af530742b7f upstream. Commit 6e032b350cd1 ("powerpc/powernv: Check device-tree for RFI flush settings") uses u64 in asm/hvcall.h without including linux/types.h This breaks hvcall.h users that do not include the header themselves. Fixes: 6e032b350cd1 ("powerpc/powernv: Check device-tree for RFI flush settings") Signed-off-by: Michal Suchanek <msuchanek(a)suse.de> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/powerpc/include/asm/hvcall.h | 1 + 1 file changed, 1 insertion(+) --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -353,6 +353,7 @@ #define PROC_TABLE_GTSE 0x01 #ifndef __ASSEMBLY__ +#include <linux/types.h> /** * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments Patches currently in stable-queue which might be from msuchanek(a)suse.de are queue-4.14/powerpc-pseries-include-linux-types.h-in-asm-hvcall.h.patch

7 years, 4 months

1
0
0 0

Patch "KVM MMU: check pending exception before injecting APF" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KVM MMU: check pending exception before injecting APF to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: kvm-mmu-check-pending-exception-before-injecting-apf.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 2a266f23550be997d783f27e704b9b40c4010292 Mon Sep 17 00:00:00 2001 From: Haozhong Zhang <haozhong.zhang(a)intel.com> Date: Wed, 10 Jan 2018 21:44:42 +0800 Subject: KVM MMU: check pending exception before injecting APF From: Haozhong Zhang <haozhong.zhang(a)intel.com> commit 2a266f23550be997d783f27e704b9b40c4010292 upstream. For example, when two APF's for page ready happen after one exit and the first one becomes pending, the second one will result in #DF. Instead, just handle the second page fault synchronously. Reported-by: Ross Zwisler <zwisler(a)gmail.com> Message-ID: <CAOxpaSUBf8QoOZQ1p4KfUp0jq76OKfGY4Uxs-Gg8ngReD99xww(a)mail.gmail.com> Reported-by: Alec Blayne <ab(a)tevsa.net> Signed-off-by: Haozhong Zhang <haozhong.zhang(a)intel.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kvm/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3784,7 +3784,8 @@ static int kvm_arch_setup_async_pf(struc bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || - kvm_event_needs_reinjection(vcpu))) + kvm_event_needs_reinjection(vcpu) || + vcpu->arch.exception.pending)) return false; if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) Patches currently in stable-queue which might be from haozhong.zhang(a)intel.com are queue-4.14/kvm-mmu-check-pending-exception-before-injecting-apf.patch

7 years, 4 months

1
0
0 0

Patch "drm/i915: Redo plane sanitation during readout" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled drm/i915: Redo plane sanitation during readout to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: drm-i915-redo-plane-sanitation-during-readout.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 23ac12732825901b3fc6ac720958d8bff9a0d6ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Fri, 17 Nov 2017 21:19:09 +0200 Subject: drm/i915: Redo plane sanitation during readout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> commit 23ac12732825901b3fc6ac720958d8bff9a0d6ec upstream. Unify the plane disabling during state readout by pulling the code into a new helper intel_plane_disable_noatomic(). We'll also read out the state of all planes, so that we know which planes really need to be diabled. Additonally we change the plane<->pipe mapping sanitation to work by simply disabling the offending planes instead of entire pipes. And we do it before we otherwise sanitize the crtcs, which means we don't have to worry about misassigned planes during crtc sanitation anymore. v2: Reoder patches to not depend on enum old_plane_id v3: s/for_each_pipe/for_each_intel_crtc/ Cc: Thierry Reding <thierry.reding(a)gmail.com> Cc: Alex Villacís Lasso <alexvillacislasso(a)hotmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103223 Reviewed-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Tested-by: Thierry Reding <thierry.reding(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171117191917.11506-3-ville.… Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> (cherry picked from commit b1e01595a66dc206a2c75401ec4c285740537f3f) Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/i915/intel_display.c | 114 +++++++++++++++++++---------------- 1 file changed, 65 insertions(+), 49 deletions(-) --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2756,6 +2756,23 @@ intel_set_plane_visible(struct intel_crt crtc_state->active_planes); } +static void intel_plane_disable_noatomic(struct intel_crtc *crtc, + struct intel_plane *plane) +{ + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + + intel_set_plane_visible(crtc_state, plane_state, false); + + if (plane->id == PLANE_PRIMARY) + intel_pre_disable_primary_noatomic(&crtc->base); + + trace_intel_disable_plane(&plane->base, crtc); + plane->disable_plane(plane, crtc); +} + static void intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, struct intel_initial_plane_config *plane_config) @@ -2813,12 +2830,7 @@ intel_find_initial_plane_obj(struct inte * simplest solution is to just disable the primary plane now and * pretend the BIOS never had it enabled. */ - intel_set_plane_visible(to_intel_crtc_state(crtc_state), - to_intel_plane_state(plane_state), - false); - intel_pre_disable_primary_noatomic(&intel_crtc->base); - trace_intel_disable_plane(primary, intel_crtc); - intel_plane->disable_plane(intel_plane, intel_crtc); + intel_plane_disable_noatomic(intel_crtc, intel_plane); return; @@ -5954,6 +5966,7 @@ static void intel_crtc_disable_noatomic( struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_i915_private *dev_priv = to_i915(crtc->dev); enum intel_display_power_domain domain; + struct intel_plane *plane; u64 domains; struct drm_atomic_state *state; struct intel_crtc_state *crtc_state; @@ -5962,11 +5975,12 @@ static void intel_crtc_disable_noatomic( if (!intel_crtc->active) return; - if (crtc->primary->state->visible) { - intel_pre_disable_primary_noatomic(crtc); + for_each_intel_plane_on_crtc(&dev_priv->drm, intel_crtc, plane) { + const struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); - intel_crtc_disable_planes(crtc, 1 << drm_plane_index(crtc->primary)); - crtc->primary->state->visible = false; + if (plane_state->base.visible) + intel_plane_disable_noatomic(intel_crtc, plane); } state = drm_atomic_state_alloc(crtc->dev); @@ -14715,22 +14729,36 @@ void i830_disable_pipe(struct drm_i915_p POSTING_READ(DPLL(pipe)); } -static bool -intel_check_plane_mapping(struct intel_crtc *crtc) +static bool intel_plane_mapping_ok(struct intel_crtc *crtc, + struct intel_plane *primary) { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 val; + enum plane plane = primary->plane; + u32 val = I915_READ(DSPCNTR(plane)); - if (INTEL_INFO(dev_priv)->num_pipes == 1) - return true; + return (val & DISPLAY_PLANE_ENABLE) == 0 || + (val & DISPPLANE_SEL_PIPE_MASK) == DISPPLANE_SEL_PIPE(crtc->pipe); +} - val = I915_READ(DSPCNTR(!crtc->plane)); +static void +intel_sanitize_plane_mapping(struct drm_i915_private *dev_priv) +{ + struct intel_crtc *crtc; - if ((val & DISPLAY_PLANE_ENABLE) && - (!!(val & DISPPLANE_SEL_PIPE_MASK) == crtc->pipe)) - return false; + if (INTEL_GEN(dev_priv) >= 4) + return; - return true; + for_each_intel_crtc(&dev_priv->drm, crtc) { + struct intel_plane *plane = + to_intel_plane(crtc->base.primary); + + if (intel_plane_mapping_ok(crtc, plane)) + continue; + + DRM_DEBUG_KMS("%s attached to the wrong pipe, disabling plane\n", + plane->base.name); + intel_plane_disable_noatomic(crtc, plane); + } } static bool intel_crtc_has_encoders(struct intel_crtc *crtc) @@ -14786,33 +14814,15 @@ static void intel_sanitize_crtc(struct i /* Disable everything but the primary plane */ for_each_intel_plane_on_crtc(dev, crtc, plane) { - if (plane->base.type == DRM_PLANE_TYPE_PRIMARY) - continue; + const struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); - trace_intel_disable_plane(&plane->base, crtc); - plane->disable_plane(plane, crtc); + if (plane_state->base.visible && + plane->base.type != DRM_PLANE_TYPE_PRIMARY) + intel_plane_disable_noatomic(crtc, plane); } } - /* We need to sanitize the plane -> pipe mapping first because this will - * disable the crtc (and hence change the state) if it is wrong. Note - * that gen4+ has a fixed plane -> pipe mapping. */ - if (INTEL_GEN(dev_priv) < 4 && !intel_check_plane_mapping(crtc)) { - bool plane; - - DRM_DEBUG_KMS("[CRTC:%d:%s] wrong plane connection detected!\n", - crtc->base.base.id, crtc->base.name); - - /* Pipe has the wrong plane attached and the plane is active. - * Temporarily change the plane mapping and disable everything - * ... */ - plane = crtc->plane; - crtc->base.primary->state->visible = true; - crtc->plane = !plane; - intel_crtc_disable_noatomic(&crtc->base, ctx); - crtc->plane = plane; - } - /* Adjust the state of the output pipe according to whether we * have active connectors/encoders. */ if (crtc->active && !intel_crtc_has_encoders(crtc)) @@ -14920,14 +14930,18 @@ void i915_redisable_vga(struct drm_i915_ /* FIXME read out full plane state for all planes */ static void readout_plane_state(struct intel_crtc *crtc) { - struct intel_plane *primary = to_intel_plane(crtc->base.primary); - bool visible; + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + struct intel_plane *plane; - visible = crtc->active && primary->get_hw_state(primary); + for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + bool visible = plane->get_hw_state(plane); - intel_set_plane_visible(to_intel_crtc_state(crtc->base.state), - to_intel_plane_state(primary->base.state), - visible); + intel_set_plane_visible(crtc_state, plane_state, visible); + } } static void intel_modeset_readout_hw_state(struct drm_device *dev) @@ -15129,6 +15143,8 @@ intel_modeset_setup_hw_state(struct drm_ /* HW state is read out, now we need to sanitize this mess. */ get_encoder_power_domains(dev_priv); + intel_sanitize_plane_mapping(dev_priv); + for_each_intel_encoder(dev, encoder) { intel_sanitize_encoder(encoder); } Patches currently in stable-queue which might be from ville.syrjala(a)linux.intel.com are queue-4.14/drm-i915-redo-plane-sanitation-during-readout.patch queue-4.14/drm-i915-add-.get_hw_state-method-for-planes.patch queue-4.14/drm-i915-fix-deadlock-in-i830_disable_pipe.patch

7 years, 4 months

1
0
0 0

Patch "drm/i915: Fix deadlock in i830_disable_pipe()" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled drm/i915: Fix deadlock in i830_disable_pipe() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: drm-i915-fix-deadlock-in-i830_disable_pipe.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 4488496d58200c7511842e049a4cc891d928da56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Wed, 29 Nov 2017 14:54:11 +0200 Subject: drm/i915: Fix deadlock in i830_disable_pipe() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> commit 4488496d58200c7511842e049a4cc891d928da56 upstream. i830_disable_pipe() gets called from the power well code, and thus we're already holding the power domain mutex. That means we can't call plane->get_hw_state() as it will also try to grab the same mutex and will thus deadlock. Replace the assert_plane() calls (which calls ->get_hw_state()) with just raw register reads in i830_disable_pipe(). As a bonus we can now get a warning if plane C is enabled even though we don't even expose it as a drm plane. v2: Do a separate WARN_ON() for each plane (Chris) Cc: Chris Wilson <chris(a)chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris(a)chris-wilson.co.uk> Fixes: d87ce7640295 ("drm/i915: Add .get_hw_state() method for planes") Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171129125411.29055-1-ville.… (cherry picked from commit 5816d9cbc0a0fbf232fe297cefcb85361a3cde90) Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/i915/intel_display.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -14717,8 +14717,11 @@ void i830_disable_pipe(struct drm_i915_p DRM_DEBUG_KMS("disabling pipe %c due to force quirk\n", pipe_name(pipe)); - assert_planes_disabled(intel_get_crtc_for_pipe(dev_priv, PIPE_A)); - assert_planes_disabled(intel_get_crtc_for_pipe(dev_priv, PIPE_B)); + WARN_ON(I915_READ(DSPCNTR(PLANE_A)) & DISPLAY_PLANE_ENABLE); + WARN_ON(I915_READ(DSPCNTR(PLANE_B)) & DISPLAY_PLANE_ENABLE); + WARN_ON(I915_READ(DSPCNTR(PLANE_C)) & DISPLAY_PLANE_ENABLE); + WARN_ON(I915_READ(CURCNTR(PIPE_A)) & CURSOR_MODE); + WARN_ON(I915_READ(CURCNTR(PIPE_B)) & CURSOR_MODE); I915_WRITE(PIPECONF(pipe), 0); POSTING_READ(PIPECONF(pipe)); Patches currently in stable-queue which might be from ville.syrjala(a)linux.intel.com are queue-4.14/drm-i915-redo-plane-sanitation-during-readout.patch queue-4.14/drm-i915-add-.get_hw_state-method-for-planes.patch queue-4.14/drm-i915-fix-deadlock-in-i830_disable_pipe.patch

7 years, 4 months

1
0
0 0

Patch "drm/i915: Add .get_hw_state() method for planes" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled drm/i915: Add .get_hw_state() method for planes to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: drm-i915-add-.get_hw_state-method-for-planes.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From d87ce76402950b8e4d5117276d44465658e886a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Fri, 17 Nov 2017 21:19:08 +0200 Subject: drm/i915: Add .get_hw_state() method for planes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> commit d87ce76402950b8e4d5117276d44465658e886a4 upstream. Add a .get_hw_state() method for planes, returning true or false depending on whether the plane is enabled. Use it to rewrite the plane enabled/disabled asserts in platform agnostic fashion. We do lose the pre-gen4 plane<->pipe mapping checks, but since we're supposed sanitize that anyway it doesn't really matter. v2: Reoder patches to not depend on enum old_plane_id Just call assert_plane_disabled() from assert_planes_disabled() v3: Deal with disabled power wells in .get_hw_state() v4: Rebase due skl primary plane code removal Cc: Thierry Reding <thierry.reding(a)gmail.com> Cc: Alex Villacís Lasso <alexvillacislasso(a)hotmail.com> Reviewed-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> #v2 Tested-by: Thierry Reding <thierry.reding(a)gmail.com> #v2 Link: https://patchwork.freedesktop.org/patch/msgid/20171117191917.11506-2-ville.… Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> (cherry picked from commit 51f5a096398433a881e845d3685a2c1dac756019) Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/i915/intel_display.c | 188 ++++++++++++++++------------------- drivers/gpu/drm/i915/intel_drv.h | 2 drivers/gpu/drm/i915/intel_sprite.c | 83 +++++++++++++++ 3 files changed, 175 insertions(+), 98 deletions(-) --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1211,23 +1211,6 @@ void assert_panel_unlocked(struct drm_i9 pipe_name(pipe)); } -static void assert_cursor(struct drm_i915_private *dev_priv, - enum pipe pipe, bool state) -{ - bool cur_state; - - if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) - cur_state = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; - else - cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; - - I915_STATE_WARN(cur_state != state, - "cursor on pipe %c assertion failure (expected %s, current %s)\n", - pipe_name(pipe), onoff(state), onoff(cur_state)); -} -#define assert_cursor_enabled(d, p) assert_cursor(d, p, true) -#define assert_cursor_disabled(d, p) assert_cursor(d, p, false) - void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state) { @@ -1255,77 +1238,25 @@ void assert_pipe(struct drm_i915_private pipe_name(pipe), onoff(state), onoff(cur_state)); } -static void assert_plane(struct drm_i915_private *dev_priv, - enum plane plane, bool state) +static void assert_plane(struct intel_plane *plane, bool state) { - u32 val; - bool cur_state; + bool cur_state = plane->get_hw_state(plane); - val = I915_READ(DSPCNTR(plane)); - cur_state = !!(val & DISPLAY_PLANE_ENABLE); I915_STATE_WARN(cur_state != state, - "plane %c assertion failure (expected %s, current %s)\n", - plane_name(plane), onoff(state), onoff(cur_state)); + "%s assertion failure (expected %s, current %s)\n", + plane->base.name, onoff(state), onoff(cur_state)); } -#define assert_plane_enabled(d, p) assert_plane(d, p, true) -#define assert_plane_disabled(d, p) assert_plane(d, p, false) - -static void assert_planes_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - int i; - - /* Primary planes are fixed to pipes on gen4+ */ - if (INTEL_GEN(dev_priv) >= 4) { - u32 val = I915_READ(DSPCNTR(pipe)); - I915_STATE_WARN(val & DISPLAY_PLANE_ENABLE, - "plane %c assertion failure, should be disabled but not\n", - plane_name(pipe)); - return; - } - - /* Need to check both planes against the pipe */ - for_each_pipe(dev_priv, i) { - u32 val = I915_READ(DSPCNTR(i)); - enum pipe cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >> - DISPPLANE_SEL_PIPE_SHIFT; - I915_STATE_WARN((val & DISPLAY_PLANE_ENABLE) && pipe == cur_pipe, - "plane %c assertion failure, should be off on pipe %c but is still active\n", - plane_name(i), pipe_name(pipe)); - } -} +#define assert_plane_enabled(p) assert_plane(p, true) +#define assert_plane_disabled(p) assert_plane(p, false) -static void assert_sprites_disabled(struct drm_i915_private *dev_priv, - enum pipe pipe) +static void assert_planes_disabled(struct intel_crtc *crtc) { - int sprite; + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_plane *plane; - if (INTEL_GEN(dev_priv) >= 9) { - for_each_sprite(dev_priv, pipe, sprite) { - u32 val = I915_READ(PLANE_CTL(pipe, sprite)); - I915_STATE_WARN(val & PLANE_CTL_ENABLE, - "plane %d assertion failure, should be off on pipe %c but is still active\n", - sprite, pipe_name(pipe)); - } - } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - for_each_sprite(dev_priv, pipe, sprite) { - u32 val = I915_READ(SPCNTR(pipe, PLANE_SPRITE0 + sprite)); - I915_STATE_WARN(val & SP_ENABLE, - "sprite %c assertion failure, should be off on pipe %c but is still active\n", - sprite_name(pipe, sprite), pipe_name(pipe)); - } - } else if (INTEL_GEN(dev_priv) >= 7) { - u32 val = I915_READ(SPRCTL(pipe)); - I915_STATE_WARN(val & SPRITE_ENABLE, - "sprite %c assertion failure, should be off on pipe %c but is still active\n", - plane_name(pipe), pipe_name(pipe)); - } else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { - u32 val = I915_READ(DVSCNTR(pipe)); - I915_STATE_WARN(val & DVS_ENABLE, - "sprite %c assertion failure, should be off on pipe %c but is still active\n", - plane_name(pipe), pipe_name(pipe)); - } + for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) + assert_plane_disabled(plane); } static void assert_vblank_disabled(struct drm_crtc *crtc) @@ -1926,9 +1857,7 @@ static void intel_enable_pipe(struct int DRM_DEBUG_KMS("enabling pipe %c\n", pipe_name(pipe)); - assert_planes_disabled(dev_priv, pipe); - assert_cursor_disabled(dev_priv, pipe); - assert_sprites_disabled(dev_priv, pipe); + assert_planes_disabled(crtc); /* * A pipe without a PLL won't actually be able to drive bits from @@ -1997,9 +1926,7 @@ static void intel_disable_pipe(struct in * Make sure planes won't keep trying to pump pixels to us, * or we might hang the display. */ - assert_planes_disabled(dev_priv, pipe); - assert_cursor_disabled(dev_priv, pipe); - assert_sprites_disabled(dev_priv, pipe); + assert_planes_disabled(crtc); reg = PIPECONF(cpu_transcoder); val = I915_READ(reg); @@ -3397,6 +3324,31 @@ static void i9xx_disable_primary_plane(s spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } +static bool i9xx_plane_get_hw_state(struct intel_plane *primary) +{ + + struct drm_i915_private *dev_priv = to_i915(primary->base.dev); + enum intel_display_power_domain power_domain; + enum plane plane = primary->plane; + enum pipe pipe = primary->pipe; + bool ret; + + /* + * Not 100% correct for planes that can move between pipes, + * but that's only the case for gen2-4 which don't have any + * display power wells. + */ + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(DSPCNTR(plane)) & DISPLAY_PLANE_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static u32 intel_fb_stride_alignment(const struct drm_framebuffer *fb, int plane) { @@ -4973,7 +4925,8 @@ void hsw_enable_ips(struct intel_crtc *c * a vblank wait. */ - assert_plane_enabled(dev_priv, crtc->plane); + assert_plane_enabled(to_intel_plane(crtc->base.primary)); + if (IS_BROADWELL(dev_priv)) { mutex_lock(&dev_priv->rps.hw_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0xc0000000)); @@ -5005,7 +4958,8 @@ void hsw_disable_ips(struct intel_crtc * if (!crtc->config->ips_enabled) return; - assert_plane_enabled(dev_priv, crtc->plane); + assert_plane_enabled(to_intel_plane(crtc->base.primary)); + if (IS_BROADWELL(dev_priv)) { mutex_lock(&dev_priv->rps.hw_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0)); @@ -9577,6 +9531,23 @@ static void i845_disable_cursor(struct i i845_update_cursor(plane, NULL, NULL); } +static bool i845_cursor_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + bool ret; + + power_domain = POWER_DOMAIN_PIPE(PIPE_A); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -9770,6 +9741,28 @@ static void i9xx_disable_cursor(struct i i9xx_update_cursor(plane, NULL, NULL); } +static bool i9xx_cursor_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + enum pipe pipe = plane->pipe; + bool ret; + + /* + * Not 100% correct for planes that can move between pipes, + * but that's only the case for gen2-3 which don't have any + * display power wells. + */ + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} /* VESA 640x480x72Hz mode to set on the pipe */ static struct drm_display_mode load_detect_mode = { @@ -13240,6 +13233,7 @@ intel_primary_plane_create(struct drm_i9 primary->update_plane = skylake_update_primary_plane; primary->disable_plane = skylake_disable_primary_plane; + primary->get_hw_state = skl_plane_get_hw_state; } else if (INTEL_GEN(dev_priv) >= 9) { intel_primary_formats = skl_primary_formats; num_formats = ARRAY_SIZE(skl_primary_formats); @@ -13250,6 +13244,7 @@ intel_primary_plane_create(struct drm_i9 primary->update_plane = skylake_update_primary_plane; primary->disable_plane = skylake_disable_primary_plane; + primary->get_hw_state = skl_plane_get_hw_state; } else if (INTEL_GEN(dev_priv) >= 4) { intel_primary_formats = i965_primary_formats; num_formats = ARRAY_SIZE(i965_primary_formats); @@ -13257,6 +13252,7 @@ intel_primary_plane_create(struct drm_i9 primary->update_plane = i9xx_update_primary_plane; primary->disable_plane = i9xx_disable_primary_plane; + primary->get_hw_state = i9xx_plane_get_hw_state; } else { intel_primary_formats = i8xx_primary_formats; num_formats = ARRAY_SIZE(i8xx_primary_formats); @@ -13264,6 +13260,7 @@ intel_primary_plane_create(struct drm_i9 primary->update_plane = i9xx_update_primary_plane; primary->disable_plane = i9xx_disable_primary_plane; + primary->get_hw_state = i9xx_plane_get_hw_state; } if (INTEL_GEN(dev_priv) >= 9) @@ -13353,10 +13350,12 @@ intel_cursor_plane_create(struct drm_i91 if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) { cursor->update_plane = i845_update_cursor; cursor->disable_plane = i845_disable_cursor; + cursor->get_hw_state = i845_cursor_get_hw_state; cursor->check_plane = i845_check_cursor; } else { cursor->update_plane = i9xx_update_cursor; cursor->disable_plane = i9xx_disable_cursor; + cursor->get_hw_state = i9xx_cursor_get_hw_state; cursor->check_plane = i9xx_check_cursor; } @@ -14704,8 +14703,8 @@ void i830_disable_pipe(struct drm_i915_p DRM_DEBUG_KMS("disabling pipe %c due to force quirk\n", pipe_name(pipe)); - assert_plane_disabled(dev_priv, PLANE_A); - assert_plane_disabled(dev_priv, PLANE_B); + assert_planes_disabled(intel_get_crtc_for_pipe(dev_priv, PIPE_A)); + assert_planes_disabled(intel_get_crtc_for_pipe(dev_priv, PIPE_B)); I915_WRITE(PIPECONF(pipe), 0); POSTING_READ(PIPECONF(pipe)); @@ -14918,20 +14917,13 @@ void i915_redisable_vga(struct drm_i915_ intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); } -static bool primary_get_hw_state(struct intel_plane *plane) -{ - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - - return I915_READ(DSPCNTR(plane->plane)) & DISPLAY_PLANE_ENABLE; -} - /* FIXME read out full plane state for all planes */ static void readout_plane_state(struct intel_crtc *crtc) { struct intel_plane *primary = to_intel_plane(crtc->base.primary); bool visible; - visible = crtc->active && primary_get_hw_state(primary); + visible = crtc->active && primary->get_hw_state(primary); intel_set_plane_visible(to_intel_crtc_state(crtc->base.state), to_intel_plane_state(primary->base.state), --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -863,6 +863,7 @@ struct intel_plane { const struct intel_plane_state *plane_state); void (*disable_plane)(struct intel_plane *plane, struct intel_crtc *crtc); + bool (*get_hw_state)(struct intel_plane *plane); int (*check_plane)(struct intel_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state); @@ -1885,6 +1886,7 @@ int intel_sprite_set_colorkey(struct drm struct drm_file *file_priv); void intel_pipe_update_start(struct intel_crtc *crtc); void intel_pipe_update_end(struct intel_crtc *crtc); +bool skl_plane_get_hw_state(struct intel_plane *plane); /* intel_tv.c */ void intel_tv_init(struct drm_i915_private *dev_priv); --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -324,6 +324,26 @@ skl_disable_plane(struct intel_plane *pl spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } +bool +skl_plane_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + bool ret; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(PLANE_CTL(pipe, plane_id)) & PLANE_CTL_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static void chv_update_csc(struct intel_plane *plane, uint32_t format) { @@ -501,6 +521,26 @@ vlv_disable_plane(struct intel_plane *pl spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } +static bool +vlv_plane_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + bool ret; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(SPCNTR(pipe, plane_id)) & SP_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -641,6 +681,25 @@ ivb_disable_plane(struct intel_plane *pl spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } +static bool +ivb_plane_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + enum pipe pipe = plane->pipe; + bool ret; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(SPRCTL(pipe)) & SPRITE_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { @@ -772,6 +831,25 @@ g4x_disable_plane(struct intel_plane *pl spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } +static bool +g4x_plane_get_hw_state(struct intel_plane *plane) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum intel_display_power_domain power_domain; + enum pipe pipe = plane->pipe; + bool ret; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return false; + + ret = I915_READ(DVSCNTR(pipe)) & DVS_ENABLE; + + intel_display_power_put(dev_priv, power_domain); + + return ret; +} + static int intel_check_sprite_plane(struct intel_plane *plane, struct intel_crtc_state *crtc_state, @@ -1227,6 +1305,7 @@ intel_sprite_plane_create(struct drm_i91 intel_plane->update_plane = skl_update_plane; intel_plane->disable_plane = skl_disable_plane; + intel_plane->get_hw_state = skl_plane_get_hw_state; plane_formats = skl_plane_formats; num_plane_formats = ARRAY_SIZE(skl_plane_formats); @@ -1237,6 +1316,7 @@ intel_sprite_plane_create(struct drm_i91 intel_plane->update_plane = skl_update_plane; intel_plane->disable_plane = skl_disable_plane; + intel_plane->get_hw_state = skl_plane_get_hw_state; plane_formats = skl_plane_formats; num_plane_formats = ARRAY_SIZE(skl_plane_formats); @@ -1247,6 +1327,7 @@ intel_sprite_plane_create(struct drm_i91 intel_plane->update_plane = vlv_update_plane; intel_plane->disable_plane = vlv_disable_plane; + intel_plane->get_hw_state = vlv_plane_get_hw_state; plane_formats = vlv_plane_formats; num_plane_formats = ARRAY_SIZE(vlv_plane_formats); @@ -1262,6 +1343,7 @@ intel_sprite_plane_create(struct drm_i91 intel_plane->update_plane = ivb_update_plane; intel_plane->disable_plane = ivb_disable_plane; + intel_plane->get_hw_state = ivb_plane_get_hw_state; plane_formats = snb_plane_formats; num_plane_formats = ARRAY_SIZE(snb_plane_formats); @@ -1272,6 +1354,7 @@ intel_sprite_plane_create(struct drm_i91 intel_plane->update_plane = g4x_update_plane; intel_plane->disable_plane = g4x_disable_plane; + intel_plane->get_hw_state = g4x_plane_get_hw_state; modifiers = i9xx_plane_format_modifiers; if (IS_GEN6(dev_priv)) { Patches currently in stable-queue which might be from ville.syrjala(a)linux.intel.com are queue-4.14/drm-i915-redo-plane-sanitation-during-readout.patch queue-4.14/drm-i915-add-.get_hw_state-method-for-planes.patch queue-4.14/drm-i915-fix-deadlock-in-i830_disable_pipe.patch

7 years, 4 months

1
0
0 0

Patch "dmaengine: dmatest: fix container_of member in dmatest_callback" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled dmaengine: dmatest: fix container_of member in dmatest_callback to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: dmaengine-dmatest-fix-container_of-member-in-dmatest_callback.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 66b3bd2356e0a1531c71a3dcf96944621e25c17c Mon Sep 17 00:00:00 2001 From: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> Date: Mon, 29 Jan 2018 14:40:11 +0800 Subject: dmaengine: dmatest: fix container_of member in dmatest_callback From: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> commit 66b3bd2356e0a1531c71a3dcf96944621e25c17c upstream. The type of arg passed to dmatest_callback is struct dmatest_done. It refers to test_done in struct dmatest_thread, not done_wait. Fixes: 6f6a23a213be ("dmaengine: dmatest: move callback wait ...") Signed-off-by: Yang Shunyong <shunyong.yang(a)hxt-semitech.com> Acked-by: Adam Wallis <awallis(a)codeaurora.org> Signed-off-by: Vinod Koul <vinod.koul(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/dma/dmatest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -355,7 +355,7 @@ static void dmatest_callback(void *arg) { struct dmatest_done *done = arg; struct dmatest_thread *thread = - container_of(arg, struct dmatest_thread, done_wait); + container_of(done, struct dmatest_thread, test_done); if (!thread->done) { done->done = true; wake_up_all(done->wait); Patches currently in stable-queue which might be from shunyong.yang(a)hxt-semitech.com are queue-4.14/dmaengine-dmatest-fix-container_of-member-in-dmatest_callback.patch

7 years, 4 months

1
0
0 0

Patch "dccp: CVE-2017-8824: use-after-free in DCCP code" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled dccp: CVE-2017-8824: use-after-free in DCCP code to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: dccp-cve-2017-8824-use-after-free-in-dccp-code.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 69c64866ce072dea1d1e59a0d61e0f66c0dffb76 Mon Sep 17 00:00:00 2001 From: Mohamed Ghannam <simo.ghannam(a)gmail.com> Date: Tue, 5 Dec 2017 20:58:35 +0000 Subject: dccp: CVE-2017-8824: use-after-free in DCCP code From: Mohamed Ghannam <simo.ghannam(a)gmail.com> commit 69c64866ce072dea1d1e59a0d61e0f66c0dffb76 upstream. Whenever the sock object is in DCCP_CLOSED state, dccp_disconnect() must free dccps_hc_tx_ccid and dccps_hc_rx_ccid and set to NULL. Signed-off-by: Mohamed Ghannam <simo.ghannam(a)gmail.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/dccp/proto.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -259,6 +259,7 @@ int dccp_disconnect(struct sock *sk, int { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); int err = 0; const int old_state = sk->sk_state; @@ -278,6 +279,10 @@ int dccp_disconnect(struct sock *sk, int sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = NULL; + dp->dccps_hc_tx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); Patches currently in stable-queue which might be from simo.ghannam(a)gmail.com are queue-4.14/dccp-cve-2017-8824-use-after-free-in-dccp-code.patch

7 years, 4 months

1
0
0 0

Patch "cpufreq: mediatek: add mediatek related projects into blacklist" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled cpufreq: mediatek: add mediatek related projects into blacklist to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cpufreq-mediatek-add-mediatek-related-projects-into-blacklist.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 6066998cbd2b1012a8d5bc9a2957cfd0ad53150e Mon Sep 17 00:00:00 2001 From: Andrew-sh Cheng <andrew-sh.cheng(a)mediatek.com> Date: Fri, 8 Dec 2017 14:07:56 +0800 Subject: cpufreq: mediatek: add mediatek related projects into blacklist From: Andrew-sh Cheng <andrew-sh.cheng(a)mediatek.com> commit 6066998cbd2b1012a8d5bc9a2957cfd0ad53150e upstream. mediatek projects will use mediate-cpufreq.c as cpufreq driver, instead of using cpufreq_dt.c Add mediatek related projects into cpufreq-dt blacklist Signed-off-by: Andrew-sh Cheng <andrew-sh.cheng(a)mediatek.com> Acked-by: Viresh Kumar <viresh.kumar(a)linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Sean Wang <sean.wang(a)mediatek.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/cpufreq/cpufreq-dt-platdev.c | 8 ++++++++ 1 file changed, 8 insertions(+) --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -111,6 +111,14 @@ static const struct of_device_id blackli { .compatible = "marvell,armadaxp", }, + { .compatible = "mediatek,mt2701", }, + { .compatible = "mediatek,mt2712", }, + { .compatible = "mediatek,mt7622", }, + { .compatible = "mediatek,mt7623", }, + { .compatible = "mediatek,mt817x", }, + { .compatible = "mediatek,mt8173", }, + { .compatible = "mediatek,mt8176", }, + { .compatible = "nvidia,tegra124", }, { .compatible = "st,stih407", }, Patches currently in stable-queue which might be from andrew-sh.cheng(a)mediatek.com are queue-4.14/cpufreq-mediatek-add-mediatek-related-projects-into-blacklist.patch

7 years, 4 months

1
0
0 0

Patch "CIFS: zero sensitive data when freeing" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled CIFS: zero sensitive data when freeing to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-zero-sensitive-data-when-freeing.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 97f4b7276b829a8927ac903a119bef2f963ccc58 Mon Sep 17 00:00:00 2001 From: Aurelien Aptel <aaptel(a)suse.com> Date: Thu, 25 Jan 2018 15:59:39 +0100 Subject: CIFS: zero sensitive data when freeing From: Aurelien Aptel <aaptel(a)suse.com> commit 97f4b7276b829a8927ac903a119bef2f963ccc58 upstream. also replaces memset()+kfree() by kzfree(). Signed-off-by: Aurelien Aptel <aaptel(a)suse.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Reviewed-by: Pavel Shilovsky <pshilov(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/cifsencrypt.c | 3 +-- fs/cifs/connect.c | 6 +++--- fs/cifs/misc.c | 14 ++++---------- 3 files changed, 8 insertions(+), 15 deletions(-) --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -325,9 +325,8 @@ int calc_lanman_hash(const char *passwor { int i; int rc; - char password_with_pad[CIFS_ENCPWD_SIZE]; + char password_with_pad[CIFS_ENCPWD_SIZE] = {0}; - memset(password_with_pad, 0, CIFS_ENCPWD_SIZE); if (password) strncpy(password_with_pad, password, CIFS_ENCPWD_SIZE); --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1707,7 +1707,7 @@ cifs_parse_mount_options(const char *mou tmp_end++; if (!(tmp_end < end && tmp_end[1] == delim)) { /* No it is not. Set the password to NULL */ - kfree(vol->password); + kzfree(vol->password); vol->password = NULL; break; } @@ -1745,7 +1745,7 @@ cifs_parse_mount_options(const char *mou options = end; } - kfree(vol->password); + kzfree(vol->password); /* Now build new password string */ temp_len = strlen(value); vol->password = kzalloc(temp_len+1, GFP_KERNEL); @@ -4235,7 +4235,7 @@ cifs_construct_tcon(struct cifs_sb_info reset_cifs_unix_caps(0, tcon, NULL, vol_info); out: kfree(vol_info->username); - kfree(vol_info->password); + kzfree(vol_info->password); kfree(vol_info); return tcon; --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -98,14 +98,11 @@ sesInfoFree(struct cifs_ses *buf_to_free kfree(buf_to_free->serverOS); kfree(buf_to_free->serverDomain); kfree(buf_to_free->serverNOS); - if (buf_to_free->password) { - memset(buf_to_free->password, 0, strlen(buf_to_free->password)); - kfree(buf_to_free->password); - } + kzfree(buf_to_free->password); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); - kfree(buf_to_free->auth_key.response); - kfree(buf_to_free); + kzfree(buf_to_free->auth_key.response); + kzfree(buf_to_free); } struct cifs_tcon * @@ -136,10 +133,7 @@ tconInfoFree(struct cifs_tcon *buf_to_fr } atomic_dec(&tconInfoAllocCount); kfree(buf_to_free->nativeFileSystem); - if (buf_to_free->password) { - memset(buf_to_free->password, 0, strlen(buf_to_free->password)); - kfree(buf_to_free->password); - } + kzfree(buf_to_free->password); kfree(buf_to_free); } Patches currently in stable-queue which might be from aaptel(a)suse.com are queue-4.14/cifs-zero-sensitive-data-when-freeing.patch

7 years, 4 months

1
0
0 0

Patch "cifs: Fix autonegotiate security settings mismatch" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled cifs: Fix autonegotiate security settings mismatch to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-fix-autonegotiate-security-settings-mismatch.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 9aca7e454415f7878b28524e76bebe1170911a88 Mon Sep 17 00:00:00 2001 From: Daniel N Pettersson <danielnp(a)axis.com> Date: Thu, 11 Jan 2018 16:00:12 +0100 Subject: cifs: Fix autonegotiate security settings mismatch From: Daniel N Pettersson <danielnp(a)axis.com> commit 9aca7e454415f7878b28524e76bebe1170911a88 upstream. Autonegotiation gives a security settings mismatch error if the SMB server selects an SMBv3 dialect that isn't SMB3.02. The exact error is "protocol revalidation - security settings mismatch". This can be tested using Samba v4.2 or by setting the global Samba setting max protocol = SMB3_00. The check that fails in smb3_validate_negotiate is the dialect verification of the negotiate info response. This is because it tries to verify against the protocol_id in the global smbdefault_values. The protocol_id in smbdefault_values is SMB3.02. In SMB2_negotiate the protocol_id in smbdefault_values isn't updated, it is global so it probably shouldn't be, but server->dialect is. This patch changes the check in smb3_validate_negotiate to use server->dialect instead of server->vals->protocol_id. The patch works with autonegotiate and when using a specific version in the vers mount option. Signed-off-by: Daniel N Pettersson <danielnp(a)axis.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/smb2pdu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -733,8 +733,7 @@ int smb3_validate_negotiate(const unsign } /* check validate negotiate info response matches what we got earlier */ - if (pneg_rsp->Dialect != - cpu_to_le16(tcon->ses->server->vals->protocol_id)) + if (pneg_rsp->Dialect != cpu_to_le16(tcon->ses->server->dialect)) goto vneg_out; if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode)) Patches currently in stable-queue which might be from danielnp(a)axis.com are queue-4.14/cifs-fix-autonegotiate-security-settings-mismatch.patch

7 years, 4 months

1
0
0 0

Patch "cifs: Fix missing put_xid in cifs_file_strict_mmap" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled cifs: Fix missing put_xid in cifs_file_strict_mmap to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: cifs-fix-missing-put_xid-in-cifs_file_strict_mmap.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From f04a703c3d613845ae3141bfaf223489de8ab3eb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox <mawilcox(a)microsoft.com> Date: Fri, 15 Dec 2017 12:48:32 -0800 Subject: cifs: Fix missing put_xid in cifs_file_strict_mmap From: Matthew Wilcox <mawilcox(a)microsoft.com> commit f04a703c3d613845ae3141bfaf223489de8ab3eb upstream. If cifs_zap_mapping() returned an error, we would return without putting the xid that we got earlier. Restructure cifs_file_strict_mmap() and cifs_file_mmap() to be more similar to each other and have a single point of return that always puts the xid. Signed-off-by: Matthew Wilcox <mawilcox(a)microsoft.com> Signed-off-by: Steve French <smfrench(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/cifs/file.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3488,20 +3488,18 @@ static const struct vm_operations_struct int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) { - int rc, xid; + int xid, rc = 0; struct inode *inode = file_inode(file); xid = get_xid(); - if (!CIFS_CACHE_READ(CIFS_I(inode))) { + if (!CIFS_CACHE_READ(CIFS_I(inode))) rc = cifs_zap_mapping(inode); - if (rc) - return rc; - } - - rc = generic_file_mmap(file, vma); - if (rc == 0) + if (!rc) + rc = generic_file_mmap(file, vma); + if (!rc) vma->vm_ops = &cifs_file_vm_ops; + free_xid(xid); return rc; } @@ -3511,16 +3509,16 @@ int cifs_file_mmap(struct file *file, st int rc, xid; xid = get_xid(); + rc = cifs_revalidate_file(file); - if (rc) { + if (rc) cifs_dbg(FYI, "Validation prior to mmap failed, error=%d\n", rc); - free_xid(xid); - return rc; - } - rc = generic_file_mmap(file, vma); - if (rc == 0) + if (!rc) + rc = generic_file_mmap(file, vma); + if (!rc) vma->vm_ops = &cifs_file_vm_ops; + free_xid(xid); return rc; } Patches currently in stable-queue which might be from mawilcox(a)microsoft.com are queue-4.14/cifs-fix-missing-put_xid-in-cifs_file_strict_mmap.patch

7 years, 4 months

1
0
0 0

Patch "arm64: Define cputype macros for Falkor CPU" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled arm64: Define cputype macros for Falkor CPU to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: arm64-define-cputype-macros-for-falkor-cpu.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From c622cc013cece073722592cff1ac6643a33b1622 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni <shankerd(a)codeaurora.org> Date: Mon, 11 Dec 2017 16:42:31 -0600 Subject: arm64: Define cputype macros for Falkor CPU From: Shanker Donthineni <shankerd(a)codeaurora.org> commit c622cc013cece073722592cff1ac6643a33b1622 upstream. Add cputype definition macros for Qualcomm Datacenter Technologies Falkor CPU in cputype.h. It's unfortunate that the first revision of the Falkor CPU used the wrong part number 0x800, got fixed in v2 chip with part number 0xC00, and would be used the same value for future revisions. Signed-off-by: Shanker Donthineni <shankerd(a)codeaurora.org> Signed-off-by: Will Deacon <will.deacon(a)arm.com> Cc: Timur Tabi <timur(a)codeaurora.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+) --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -91,6 +91,7 @@ #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 +#define QCOM_CPU_PART_FALKOR 0xC00 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -99,6 +100,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) +#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #ifndef __ASSEMBLY__ Patches currently in stable-queue which might be from shankerd(a)codeaurora.org are queue-4.14/arm64-add-software-workaround-for-falkor-erratum-1041.patch queue-4.14/arm64-define-cputype-macros-for-falkor-cpu.patch

7 years, 4 months

1
0
0 0

Patch "arm64: Add software workaround for Falkor erratum 1041" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled arm64: Add software workaround for Falkor erratum 1041 to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: arm64-add-software-workaround-for-falkor-erratum-1041.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 932b50c7c1c65e6f23002e075b97ee083c4a9e71 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni <shankerd(a)codeaurora.org> Date: Mon, 11 Dec 2017 16:42:32 -0600 Subject: arm64: Add software workaround for Falkor erratum 1041 From: Shanker Donthineni <shankerd(a)codeaurora.org> commit 932b50c7c1c65e6f23002e075b97ee083c4a9e71 upstream. The ARM architecture defines the memory locations that are permitted to be accessed as the result of a speculative instruction fetch from an exception level for which all stages of translation are disabled. Specifically, the core is permitted to speculatively fetch from the 4KB region containing the current program counter 4K and next 4K. When translation is changed from enabled to disabled for the running exception level (SCTLR_ELn[M] changed from a value of 1 to 0), the Falkor core may errantly speculatively access memory locations outside of the 4KB region permitted by the architecture. The errant memory access may lead to one of the following unexpected behaviors. 1) A System Error Interrupt (SEI) being raised by the Falkor core due to the errant memory access attempting to access a region of memory that is protected by a slave-side memory protection unit. 2) Unpredictable device behavior due to a speculative read from device memory. This behavior may only occur if the instruction cache is disabled prior to or coincident with translation being changed from enabled to disabled. The conditions leading to this erratum will not occur when either of the following occur: 1) A higher exception level disables translation of a lower exception level (e.g. EL2 changing SCTLR_EL1[M] from a value of 1 to 0). 2) An exception level disabling its stage-1 translation if its stage-2 translation is enabled (e.g. EL1 changing SCTLR_EL1[M] from a value of 1 to 0 when HCR_EL2[VM] has a value of 1). To avoid the errant behavior, software must execute an ISB immediately prior to executing the MSR that will change SCTLR_ELn[M] from 1 to 0. Signed-off-by: Shanker Donthineni <shankerd(a)codeaurora.org> Signed-off-by: Will Deacon <will.deacon(a)arm.com> Cc: Timur Tabi <timur(a)codeaurora.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- Documentation/arm64/silicon-errata.txt | 1 + arch/arm64/Kconfig | 10 ++++++++++ arch/arm64/include/asm/assembler.h | 10 ++++++++++ arch/arm64/kernel/cpu-reset.S | 1 + arch/arm64/kernel/efi-entry.S | 2 ++ arch/arm64/kernel/head.S | 1 + arch/arm64/kernel/relocate_kernel.S | 1 + arch/arm64/kvm/hyp-init.S | 1 + 8 files changed, 27 insertions(+) --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -74,3 +74,4 @@ stable kernels. | Qualcomm Tech. | Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | | Qualcomm Tech. | QDF2400 ITS | E0065 | QCOM_QDF2400_ERRATUM_0065 | +| Qualcomm Tech. | Falkor v{1,2} | E1041 | QCOM_FALKOR_ERRATUM_1041 | --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -539,6 +539,16 @@ config QCOM_QDF2400_ERRATUM_0065 If unsure, say Y. +config QCOM_FALKOR_ERRATUM_E1041 + bool "Falkor E1041: Speculative instruction fetches might cause errant memory access" + default y + help + Falkor CPU may speculatively fetch instructions from an improper + memory location when MMU translation is changed from SCTLR_ELn[M]=1 + to SCTLR_ELn[M]=0. Prefix an ISB instruction to fix the problem. + + If unsure, say Y. + endmenu --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -499,4 +499,14 @@ alternative_else_nop_endif #endif .endm +/** + * Errata workaround prior to disable MMU. Insert an ISB immediately prior + * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. + */ + .macro pre_disable_mmu_workaround +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041 + isb +#endif + .endm + #endif /* __ASM_ASSEMBLER_H */ --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -37,6 +37,7 @@ ENTRY(__cpu_soft_restart) mrs x12, sctlr_el1 ldr x13, =SCTLR_ELx_FLAGS bic x12, x12, x13 + pre_disable_mmu_workaround msr sctlr_el1, x12 isb --- a/arch/arm64/kernel/efi-entry.S +++ b/arch/arm64/kernel/efi-entry.S @@ -96,6 +96,7 @@ ENTRY(entry) mrs x0, sctlr_el2 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el2, x0 isb b 2f @@ -103,6 +104,7 @@ ENTRY(entry) mrs x0, sctlr_el1 bic x0, x0, #1 << 0 // clear SCTLR.M bic x0, x0, #1 << 2 // clear SCTLR.C + pre_disable_mmu_workaround msr sctlr_el1, x0 isb 2: --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -732,6 +732,7 @@ __primary_switch: * to take into account by discarding the current kernel mapping and * creating a new one. */ + pre_disable_mmu_workaround msr sctlr_el1, x20 // disable the MMU isb bl __create_page_tables // recreate kernel mapping --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -45,6 +45,7 @@ ENTRY(arm64_relocate_new_kernel) mrs x0, sctlr_el2 ldr x1, =SCTLR_ELx_FLAGS bic x0, x0, x1 + pre_disable_mmu_workaround msr sctlr_el2, x0 isb 1: --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -151,6 +151,7 @@ reset: mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc + pre_disable_mmu_workaround msr sctlr_el2, x5 isb Patches currently in stable-queue which might be from shankerd(a)codeaurora.org are queue-4.14/arm64-add-software-workaround-for-falkor-erratum-1041.patch queue-4.14/arm64-define-cputype-macros-for-falkor-cpu.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH stable-4.14 0/3] drm/i915: Fix plane regression

by Ville Syrjala

From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> These backports fix a plane related regression causing a corrupted screen and bunch of WARNs from the kernel on some pre-i965 era hardware. Cc: <stable(a)vger.kernel.org> # 4.14 Ville Syrjälä (3): drm/i915: Add .get_hw_state() method for planes drm/i915: Redo plane sanitation during readout drm/i915: Fix deadlock in i830_disable_pipe() drivers/gpu/drm/i915/intel_display.c | 303 ++++++++++++++++++----------------- drivers/gpu/drm/i915/intel_drv.h | 2 + drivers/gpu/drm/i915/intel_sprite.c | 83 ++++++++++ 3 files changed, 242 insertions(+), 146 deletions(-) -- 2.13.6

7 years, 4 months

2
4
0 0

[Linux-stable-mirror] [PATCH 3.18 0/9] Backports for security and critical bug fixes

by Shuah Khan

As I started backporting security fixes, found a few problems that prevent tools to build on newer gcc releases, deadlock bug, and another bug that prevents client from being able to use imported devices. This patch series consists of security fixes and fixes to critical bugs. Andrew Goodbody (1): usb: usbip: Fix possible deadlocks reported by lockdep Shuah Khan (8): usbip: fix stub_rx: get_pipe() to validate endpoint number usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input usbip: prevent vhci_hcd driver from leaking a socket pointer address usbip: Fix potential format overflow in userspace tools usbip: vhci_hcd: clear just the USB_PORT_STAT_POWER bit usbip: prevent leaking socket pointer address in messages usbip: stub: stop printing kernel pointer addresses in messages usbip: vhci: stop printing kernel pointer addresses in messages drivers/usb/usbip/stub_dev.c | 3 +- drivers/usb/usbip/stub_main.c | 5 +- drivers/usb/usbip/stub_rx.c | 53 +++++++++++---- drivers/usb/usbip/stub_tx.c | 4 +- drivers/usb/usbip/usbip_common.c | 15 ++--- drivers/usb/usbip/usbip_common.h | 1 + drivers/usb/usbip/usbip_event.c | 5 +- drivers/usb/usbip/vhci_hcd.c | 102 +++++++++++++++-------------- drivers/usb/usbip/vhci_rx.c | 53 ++++++++------- drivers/usb/usbip/vhci_sysfs.c | 45 +++++++------ drivers/usb/usbip/vhci_tx.c | 17 +++-- tools/usb/usbip/libsrc/usbip_common.c | 9 ++- tools/usb/usbip/libsrc/usbip_host_driver.c | 27 ++++++-- tools/usb/usbip/libsrc/vhci_driver.c | 8 +-- 14 files changed, 205 insertions(+), 142 deletions(-) -- 2.14.1

7 years, 4 months

2
10
0 0

[Linux-stable-mirror] [PATCH 0/2][for 4.14] Add work-around for Falkor erratum E1041

by Timur Tabi

These two patches (back-ported from 4.15) implement a work-around for a rare but serious erratum in Qualcomm Datacenter Technologies Falkor cores. One small merge conflict in arch/arm64/Kconfig was resolved when back-porting patch #2. P.S. I couldn't find any good examples of submitting a back-ported patch with resolved merge conflicts to stable(a)vger.kernel.org, so I hope I'm not forgetting anything. Shanker Donthineni (2): [for 4.14] arm64: Define cputype macros for Falkor CPU [for 4.14] arm64: Add software workaround for Falkor erratum 1041 Documentation/arm64/silicon-errata.txt | 1 + arch/arm64/Kconfig | 10 ++++++++++ arch/arm64/include/asm/assembler.h | 10 ++++++++++ arch/arm64/include/asm/cputype.h | 2 ++ arch/arm64/kernel/cpu-reset.S | 1 + arch/arm64/kernel/efi-entry.S | 2 ++ arch/arm64/kernel/head.S | 1 + arch/arm64/kernel/relocate_kernel.S | 1 + arch/arm64/kvm/hyp-init.S | 1 + 9 files changed, 29 insertions(+) -- Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.

7 years, 4 months

2
3
0 0

[Linux-stable-mirror] [PATCH -stable] posix-timer: Properly check sigevent->sigev_notify

by Eric Biggers

From: Thomas Gleixner <tglx(a)linutronix.de> commit cef31d9af908243421258f1df35a4a644604efbe upstream. Please apply to 4.9-stable, 4.4-stable, and 3.18-stable. timer_create() specifies via sigevent->sigev_notify the signal delivery for the new timer. The valid modes are SIGEV_NONE, SIGEV_SIGNAL, SIGEV_THREAD and (SIGEV_SIGNAL | SIGEV_THREAD_ID). The sanity check in good_sigevent() is only checking the valid combination for the SIGEV_THREAD_ID bit, i.e. SIGEV_SIGNAL, but if SIGEV_THREAD_ID is not set it accepts any random value. This has no real effects on the posix timer and signal delivery code, but it affects show_timer() which handles the output of /proc/$PID/timers. That function uses a string array to pretty print sigev_notify. The access to that array has no bound checks, so random sigev_notify cause access beyond the array bounds. Add proper checks for the valid notify modes and remove the SIGEV_THREAD_ID masking from various code pathes as SIGEV_NONE can never be set in combination with SIGEV_THREAD_ID. Reported-by: Eric Biggers <ebiggers3(a)gmail.com> Reported-by: Dmitry Vyukov <dvyukov(a)google.com> Reported-by: Alexey Dobriyan <adobriyan(a)gmail.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: John Stultz <john.stultz(a)linaro.org> Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- kernel/time/posix-timers.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index f2826c35e918..fc7c37ad90a0 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -507,17 +507,22 @@ static struct pid *good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; - if ((event->sigev_notify & SIGEV_THREAD_ID ) && - (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || - !same_thread_group(rtn, current) || - (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL)) + switch (event->sigev_notify) { + case SIGEV_SIGNAL | SIGEV_THREAD_ID: + rtn = find_task_by_vpid(event->sigev_notify_thread_id); + if (!rtn || !same_thread_group(rtn, current)) + return NULL; + /* FALLTHRU */ + case SIGEV_SIGNAL: + case SIGEV_THREAD: + if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX) + return NULL; + /* FALLTHRU */ + case SIGEV_NONE: + return task_pid(rtn); + default: return NULL; - - if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && - ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) - return NULL; - - return task_pid(rtn); + } } void posix_timers_register_clock(const clockid_t clock_id, @@ -745,8 +750,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) /* interval timer ? */ if (iv.tv64) cur_setting->it_interval = ktime_to_timespec(iv); - else if (!hrtimer_active(timer) && - (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) + else if (!hrtimer_active(timer) && timr->it_sigev_notify != SIGEV_NONE) return; now = timer->base->get_time(); @@ -757,7 +761,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) * expiry is > now. */ if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING || - (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) + timr->it_sigev_notify == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); remaining = __hrtimer_expires_remaining_adjusted(timer, now); @@ -767,7 +771,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) * A single shot SIGEV_NONE timer must return 0, when * it is expired ! */ - if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) + if (timr->it_sigev_notify != SIGEV_NONE) cur_setting->it_value.tv_nsec = 1; } else cur_setting->it_value = ktime_to_timespec(remaining); @@ -865,7 +869,7 @@ common_timer_set(struct k_itimer *timr, int flags, timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); /* SIGEV_NONE timers are not queued ! See common_timer_get */ - if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { + if (timr->it_sigev_notify == SIGEV_NONE) { /* Setup correct expiry time for relative timers */ if (mode == HRTIMER_MODE_REL) { hrtimer_add_expires(timer, timer->base->get_time()); -- 2.16.0.rc1.238.g530d649a79-goog

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] Apply "netfilter: nf_queue: Make the queue_handler pernet" to 4.4-stable

by Eric Biggers

Hi Greg, can you please apply commit dc3ee32e96d7 ("netfilter: nf_queue: Make the queue_handler pernet") to 4.4-stable? syzbot is hitting the crash in nfqnl_nf_hook_drop() by interrupting thread creation in pg_net_init(). An OOM condition is not required, contrary to what is suggested by the original commit message. Thanks, Eric

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] Commit bc137dfdbec2 (watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop)

by Rasmus Villemoes

Hi stable maintainers Can I get you to consider including bc137dfdbec2 watchdog: gpio_wdt: set WDOG_HW_RUNNING in gpio_wdt_stop in -stable? Without that, any (always-running) gpio watchdog effectively fails to honour the magic close feature, causing an unexpected reset shortly after userspace gracefully closes the device. Anything containing 3c10bbde10 ("watchdog: core: Clear WDOG_HW_RUNNING before calling the stop function") probably needs it (i.e. 4.8+), but at the very least 4.14 and 4.15. Rasmus

7 years, 4 months

2
1
0 0

Re: [Linux-stable-mirror] [stable-4.4.y] compile error with KAISER and no vsyscall emulation

by Hugh Dickins

On Sat, 10 Feb 2018, Tobias Jakobi wrote: > Hello, > > I noticed a compile error with a recent version (4.4.115) of the 4.4.y branch: > arch/x86/mm/kaiser.c: In function ‘kaiser_init’: > arch/x86/mm/kaiser.c:348:8: error: ‘vsyscall_pgprot’ undeclared (first use in > this function) > > It seems like my combination of kernel options doesn't work for KAISER. > X86_VSYSCALL_EMULATION is not set on my system, while LEGACY_VSYSCALL is set to > NONE (LEGACY_VSYSCALL_NONE=y). I have managed to get things compiling again, by > moving the 'extern unsigned long vsyscall_pgprot' outside of the preprocessor > statement. This works for me, I guess because the code in question is never > called during runtime anyway (vsyscall_enabled() always returns false). > > With best wishes, > Tobias Yes, sorry about that, thanks Tobias. Same error on 4.9 too. Here's the patch that you correctly suggest, and it's good for both: [PATCH 4.4 and 4.9] kaiser: fix compile error without vsyscall Tobias noticed a compile error on 4.4.115, and it's the same on 4.9.80: arch/x86/mm/kaiser.c: In function ‘kaiser_init’: arch/x86/mm/kaiser.c:348:8: error: ‘vsyscall_pgprot’ undeclared (first use in this function) It seems like his combination of kernel options doesn't work for KAISER. X86_VSYSCALL_EMULATION is not set on his system, while LEGACY_VSYSCALL is set to NONE (LEGACY_VSYSCALL_NONE=y). He managed to get things compiling again, by moving the 'extern unsigned long vsyscall_pgprot' outside of the preprocessor statement. This works because the optimizer removes that code (vsyscall_enabled() is always false) - and that's how it was done in some older backports. Reported-by: Tobias Jakobi <tjakobi(a)math.uni-bielefeld.de> Signed-off-by: Hugh Dickins <hughd(a)google.com> --- arch/x86/include/asm/vsyscall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -13,7 +13,6 @@ extern void map_vsyscall(void); */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); extern bool vsyscall_enabled(void); -extern unsigned long vsyscall_pgprot; #else static inline void map_vsyscall(void) {} static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) @@ -22,5 +21,6 @@ static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } static inline bool vsyscall_enabled(void) { return false; } #endif +extern unsigned long vsyscall_pgprot; #endif /* _ASM_X86_VSYSCALL_H */

7 years, 4 months

2
1
0 0

Re: B43 driver no longer works in Linux 4.15 (bisected)

by Greg Kroah-Hartman

On Mon, Feb 12, 2018 at 03:22:32PM +0000, James Hogan wrote: > On Mon, Feb 12, 2018 at 05:08:10PM +0200, Kalle Valo wrote: > > James Hogan <jhogan(a)kernel.org> writes: > > > On Mon, Feb 05, 2018 at 01:23:31PM -0500, Adric Blake wrote: > > >> I bisected to this "first bad commit:" > > >> > > >> commit 58eae1416b804d900014d84feadda7195007cc30 > > >> Author: James Hogan <jhogan(a)kernel.org> > > >> Date: Mon Jan 15 21:17:14 2018 +0000 > > >> > > >> ssb: Disable PCI host for PCI_DRIVERS_GENERIC > > > > > > Yes, really sorry about that and thanks for going to the effort of > > > bisecting. There is a patch here: > > > https://patchwork.kernel.org/patch/10185397/ > > > > > > which is applied to linux-next as commit > > > a9e6d44ddeccd3522670e641f1ed9b068e746ff7, and is tagged for stable, > > > though I've just noticed the stable email address is incorrect... I'll > > > make sure it gets applied to the 4.15 stable branch though as soon as > > > I notice its merged. > > > > The commit is now in v4.16-rc1. > > Yes, thanks, > > Greg: Please can commit a9e6d44ddeccd3522670e641f1ed9b068e746ff7 ("ssb: > Do not disable PCI host on non-Mips") be applied to 4.15 stable (the > wrong stable email address was Cc'd in the commit message). Now applied, thanks. greg k-h

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] apply (dmaengine: dmatest: fix container_of member in dmatest_callback) to stable

by Adam Wallis

Please apply commit: 66b3bd2356e0a1531c71a3dcf96944621e25c17c (dmaengine: dmatest: fix container_of member in dmatest_callback) to stable This fixes a bug in dmatest that will cause the test to give a false negative. -- Adam Wallis Qualcomm Datacenter Technologies as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.

7 years, 4 months

4
3
0 0

[Linux-stable-mirror] [PATCH stable] cifs: empty TargetInfo leads to crash on recovery

by Dan Aloni

commit cabfb3680f78 upstream. [ resend from Oct 20, 2014, see [1] ] A trivially patched Samba server (see [2] [3]) can cause a remote kernel crash (see [4]) in a client's CIFS kernel module upon session recovery, under kernels prior to v4.11. The server patch can made by a single source line modification - returning an empty TargetInfo in an NTLMSSP setup negotiation response. To reproduce at the client side, the CIFS client can be instructed to mount with SMB 2.0, on a share without user/password credentials, e.g: mount -t cifs //[host]/[share] -o vers=2.0,guest [mountpoint] (It may also reproduce with credentials, but I used a simpler configuration for the reproduction) An demo patch to Samba 4.7.4 is provided in the links provided. As for the client crash itself: When the session is recovered (after a server start/stop, for example), the following condition turns out to be true: ses->auth_key.len != 0 && ses->auth_key.response == NULL This will cause the following memcpy() in setup_ntlmv2_rsp() to GPF, because tiblob == NULL and tilen != 0 (these are the old auth_key values): memcpy(ses->auth_key.response + baselen, tiblob, tilen); By bisecting, upstream commit cabfb3680f78 ("CIFS: Enable encryption during session setup phase") from v4.11 have fixed this issue. According to my tests, LTS kernels versions 4.4.x and 4.9.x are affected. The patch below applies for 4.4.x however a similar patch can be applied to 4.9.x and older kernels. Signed-off-by: Dan Aloni <dan(a)kernelim.com> CC: Steve French <sfrench(a)samba.org> CC: stable(a)vger.kernel.org # 4.4.x CC: linux-cifs(a)vger.kernel.org CC: linux-kernel(a)vger.kernel.org [1] https://patchwork.kernel.org/patch/5106391/ [2] (temporary url) http://copr-dist-git.fedorainfracloud.org/cgit/alonid/samba-for-client-cras… [3] (temporary url) https://copr.fedorainfracloud.org/coprs/alonid/samba-for-client-crash-repro/ [4] [ 3414.518134] BUG: unable to handle kernel NULL pointer dereference at (null) [ 3414.518200] IP: memcpy_erms+0x6/0x10 [ 3414.518227] PGD 0 [ 3414.518252] Oops: 0000 [#1] SMP [ 3414.518272] Modules linked in: arc4 md4 cifs rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw ebtable_filter ebtables ip6table_filter ip6_tables snd_hda_codec_generic ppdev snd_hda_intel snd_hda_codec crct10dif_pclmul crc32_pclmul snd_hwdep snd_hda_core ghash_clmulni_intel snd_seq snd_seq_device snd_pcm joydev parport_pc tpm_tis parport tpm_tis_core tpm snd_timer snd soundcore qemu_fw_cfg virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c [ 3414.518708] virtio_blk virtio_console virtio_net qxl drm_kms_helper ttm crc32c_intel drm ata_generic nvme serio_raw nvme_core virtio_pci virtio_ring virtio pata_acpi [ 3414.518803] CPU: 3 PID: 1697 Comm: kworker/3:1 Not tainted 4.10.0-rc6-dan-00097-ge765a3d89ede #20 [ 3414.518852] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 [ 3414.518927] Workqueue: cifsiod smb2_reconnect_server [cifs] [ 3414.518960] task: ffff8cc6764a4000 task.stack: ffff9bc548808000 [ 3414.518997] RIP: 0010:memcpy_erms+0x6/0x10 [ 3414.519021] RSP: 0018:ffff9bc54880bbc8 EFLAGS: 00010296 [ 3414.519051] RAX: ffff8cc6ba00d8dc RBX: ffff8cc676190400 RCX: 0000000000000010 [ 3414.519091] RDX: 0000000000000010 RSI: 0000000000000000 RDI: ffff8cc6ba00d8dc [ 3414.519130] RBP: ffff9bc54880bc30 R08: ffff9bc54880bb58 R09: ffff9bc54880bb58 [ 3414.519170] R10: 000000004619520e R11: 00000000f46cd8cf R12: 0000000000000000 [ 3414.519209] R13: 0000000000000000 R14: ffff8cc6ba00d8a0 R15: 0000000000000010 [ 3414.519250] FS: 0000000000000000(0000) GS:ffff8cc6bfd80000(0000) knlGS:0000000000000000 [ 3414.519314] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3414.519347] CR2: 0000000000000000 CR3: 000000007992a000 CR4: 00000000003406e0 [ 3414.519392] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 3414.519431] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 3414.519470] Call Trace: [ 3414.519510] ? setup_ntlmv2_rsp+0x124/0xa10 [cifs] [ 3414.519553] build_ntlmssp_auth_blob+0x36/0x310 [cifs] [ 3414.519597] SMB2_sess_auth_rawntlmssp_authenticate+0xc7/0x300 [cifs] [ 3414.519646] SMB2_sess_setup+0x9a/0x140 [cifs] [ 3414.519685] cifs_setup_session+0x78/0x100 [cifs] [ 3414.519722] ? cifs_negotiate_protocol+0x84/0xd0 [cifs] [ 3414.519763] smb2_reconnect+0x308/0x3e0 [cifs] [ 3414.519793] ? __internal_add_timer+0x1f/0x60 [ 3414.519831] smb2_reconnect_server+0x187/0x260 [cifs] [ 3414.519863] process_one_work+0x19e/0x440 [ 3414.519887] worker_thread+0x4e/0x4a0 [ 3414.519910] ? process_one_work+0x440/0x440 [ 3414.519936] kthread+0x11e/0x140 [ 3414.520493] ? kthread_park+0x90/0x90 [ 3414.520989] ret_from_fork+0x2c/0x40 [ 3414.521450] Code: 78 ff ff ff 90 eb 1e 0f 1f 00 48 89 f8 48 89 d1 48 c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48 89 f8 48 89 d1 <f3> a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e 40 38 [ 3414.522488] RIP: memcpy_erms+0x6/0x10 RSP: ffff9bc54880bbc8 [ 3414.522964] CR2: 0000000000000000 [ 3414.526127] ---[ end trace bbe4aa1e45cc6c17 ]--- --- fs/cifs/smb2pdu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index f2ff60e58ec8..91c9e83df457 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -633,6 +633,7 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, */ kfree(ses->auth_key.response); ses->auth_key.response = NULL; + ses->auth_key.len = 0; /* * If memory allocation is successful, caller of this function @@ -837,6 +838,7 @@ ssetup_exit: rc = server->ops->generate_signingkey(ses); kfree(ses->auth_key.response); ses->auth_key.response = NULL; + ses->auth_key.len = 0; if (rc) { cifs_dbg(FYI, "SMB3 session key generation failed\n"); @@ -861,6 +863,7 @@ keygen_exit: if (!server->sign) { kfree(ses->auth_key.response); ses->auth_key.response = NULL; + ses->auth_key.len = 0; } if (spnego_key) { key_invalidate(spnego_key); -- 2.14.3

7 years, 4 months

2
3
0 0

Re: [PATCH v3] MIPS: fix incorrect mem=X@Y handling

by Mathieu Malaterre

Hi, On Tue, Feb 13, 2018 at 3:32 PM, James Hogan <jhogan(a)kernel.org> wrote: > On Tue, Feb 13, 2018 at 03:03:24PM +0100, Mathieu Malaterre wrote: >> James, >> >> On Tue, Feb 13, 2018 at 2:38 PM, James Hogan <jhogan(a)kernel.org> wrote: >> > On Tue, Feb 13, 2018 at 01:14:29PM +0100, Mathieu Malaterre wrote: >> >> Could you please review the patch v3 ? >> > >> > Yes, looks good to me, and Ralf had applied to his test branch so I >> > presume he's happy with it too. I'll apply for 4.16. >> >> Hum, just to be sure I understand the process. Which branch are you >> talking about: >> >> https://git.kernel.org/pub/scm/linux/kernel/git/ralf/linux.git > > I was referring to upstream-sfr.git branch=mips-next-test > https://git.linux-mips.org/cgit/ralf/upstream-sfr.git/log/?h=mips-next-test > > (The mips-next branch there is what Ralf puts into linux-next) > > I've applied the patch to my mips-fixes branch here: > git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/mips.git > > Sorry it seems a bit haphazard with multiple trees in use. I see it now, sorry for the noise. I was not looking at the right location. Anyway if that answer earlier question 4.11 should be correct, since I asked Greg to not backport the earlier patch: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1505915.html

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH] KVM: prevent overlap between user and private memslots

by Eric Biggers

From: Eric Biggers <ebiggers(a)google.com> Memslots must not overlap in guest physical memory, since otherwise some guest physical addresses will not uniquely map to a memslot. Yet, the overlap check in __kvm_set_memory_region() allows a memslot that overlaps one of the "private" memslots, e.g. the memslot reserved for the TSS on x86. This seems to be a very old bug that was introduced years ago when private memory slots were first added. It seems that later refactoring incorrectly assumed this bug was intentional and preserved it. Fix it by removing the loophole for private memslots, so we just check for overlap against all memslots. This bug was found by syzkaller, which used a memslot overlap to make pte_list_remove() be called for the wrong memslot, hitting a BUG(): pte_list_remove: 000000007185ed42 0->BUG kernel BUG at arch/x86/kvm/mmu.c:1209! [...] RIP: 0010:pte_list_remove+0x107/0x110 arch/x86/kvm/mmu.c:1208 [...] Call Trace: mmu_page_zap_pte+0x7e/0xd0 arch/x86/kvm/mmu.c:2499 kvm_mmu_page_unlink_children arch/x86/kvm/mmu.c:2521 [inline] kvm_mmu_prepare_zap_page+0x4f/0x340 arch/x86/kvm/mmu.c:2565 kvm_zap_obsolete_pages arch/x86/kvm/mmu.c:5348 [inline] kvm_mmu_invalidate_zap_all_pages+0xa6/0x100 arch/x86/kvm/mmu.c:5389 kvm_mmu_notifier_release+0x4f/0x80 arch/x86/kvm/../../../virt/kvm/kvm_main.c:468 __mmu_notifier_release+0x63/0x100 mm/mmu_notifier.c:75 mmu_notifier_release include/linux/mmu_notifier.h:244 [inline] exit_mmap+0x160/0x170 mm/mmap.c:3009 __mmput kernel/fork.c:966 [inline] mmput+0x44/0xd0 kernel/fork.c:987 exit_mm kernel/exit.c:544 [inline] do_exit+0x24a/0xb50 kernel/exit.c:856 do_group_exit+0x34/0xb0 kernel/exit.c:972 SYSC_exit_group kernel/exit.c:983 [inline] SyS_exit_group+0xb/0x10 kernel/exit.c:981 entry_SYSCALL_64_fastpath+0x1e/0x8b Reproducer: #include <fcntl.h> #include <linux/kvm.h> #include <sys/ioctl.h> int main() { static char buf[4096*3] __attribute__((aligned(4096))); int kvm, vm, cpu; struct kvm_mp_state mp_state = { KVM_MP_STATE_SIPI_RECEIVED }; struct kvm_userspace_memory_region memreg = { .memory_size = sizeof(buf), .userspace_addr = (__u64)buf, }; kvm = open("/dev/kvm", O_RDWR); vm = ioctl(kvm, KVM_CREATE_VM, 0); ioctl(vm, KVM_CREATE_IRQCHIP); cpu = ioctl(vm, KVM_CREATE_VCPU, 0); ioctl(cpu, KVM_SET_MP_STATE, &mp_state); ioctl(vm, KVM_SET_TSS_ADDR, 0); ioctl(cpu, KVM_RUN, 0); ioctl(vm, KVM_SET_USER_MEMORY_REGION, &memreg); } Reported-by: syzbot <syzkaller(a)googlegroups.com> Fixes: e0d62c7f4860 ("KVM: Add kernel-internal memory slots") Cc: <stable(a)vger.kernel.org> # v2.6.25+ Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- virt/kvm/kvm_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 210bf820385a..e536977e7b6d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -974,8 +974,7 @@ int __kvm_set_memory_region(struct kvm *kvm, /* Check for overlaps */ r = -EEXIST; kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { - if ((slot->id >= KVM_USER_MEM_SLOTS) || - (slot->id == id)) + if (slot->id == id) continue; if (!((base_gfn + npages <= slot->base_gfn) || (base_gfn >= slot->base_gfn + slot->npages))) -- 2.16.0

7 years, 4 months

3
6
0 0

Re: [PATCH v3] MIPS: fix incorrect mem=X@Y handling

by Mathieu Malaterre

James, On Tue, Feb 13, 2018 at 2:38 PM, James Hogan <jhogan(a)kernel.org> wrote: > On Tue, Feb 13, 2018 at 01:14:29PM +0100, Mathieu Malaterre wrote: >> On Thu, Feb 1, 2018 at 1:12 PM, Mathieu Malaterre <malat(a)debian.org> wrote: >> > On Thu, Feb 1, 2018 at 12:37 PM, Marcin Nowakowski >> > <marcin.nowakowski(a)mips.com> wrote: >> >> Commit 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") added a >> >> fix to ensure that the memory range between PHYS_OFFSET and low memory >> >> address specified by mem= cmdline argument is not later processed by >> >> free_all_bootmem. This change was incorrect for systems where the >> >> commandline specifies more than 1 mem argument, as it will cause all >> >> memory between PHYS_OFFSET and each of the memory offsets to be marked >> >> as reserved, which results in parts of the RAM marked as reserved >> >> (Creator CI20's u-boot has a default commandline argument 'mem=256M@0x0 >> >> mem=768M@0x30000000'). >> >> >> >> Change the behaviour to ensure that only the range between PHYS_OFFSET >> >> and the lowest start address of the memories is marked as protected. >> >> >> >> This change also ensures that the range is marked protected even if it's >> >> only defined through the devicetree and not only via commandline >> >> arguments. >> >> >> >> Reported-by: Mathieu Malaterre <mathieu.malaterre(a)gmail.com> >> >> Signed-off-by: Marcin Nowakowski <marcin.nowakowski(a)mips.com> >> >> Fixes: 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") >> >> Cc: <stable(a)vger.kernel.org> # v4.11+ >> >> --- >> >> v3: Update stable version, code cleanup as suggested by James Hogan >> >> v2: Use updated email adress, add tag for stable. >> >> --- >> >> arch/mips/kernel/setup.c | 16 ++++++++++++---- >> >> 1 file changed, 12 insertions(+), 4 deletions(-) >> >> >> >> diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c >> >> index 702c678de116..e4a1581ce822 100644 >> >> --- a/arch/mips/kernel/setup.c >> >> +++ b/arch/mips/kernel/setup.c >> >> @@ -375,6 +375,7 @@ static void __init bootmem_init(void) >> >> unsigned long reserved_end; >> >> unsigned long mapstart = ~0UL; >> >> unsigned long bootmap_size; >> >> + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; >> >> bool bootmap_valid = false; >> >> int i; >> >> >> >> @@ -395,7 +396,8 @@ static void __init bootmem_init(void) >> >> max_low_pfn = 0; >> >> >> >> /* >> >> - * Find the highest page frame number we have available. >> >> + * Find the highest page frame number we have available >> >> + * and the lowest used RAM address >> >> */ >> >> for (i = 0; i < boot_mem_map.nr_map; i++) { >> >> unsigned long start, end; >> >> @@ -407,6 +409,8 @@ static void __init bootmem_init(void) >> >> end = PFN_DOWN(boot_mem_map.map[i].addr >> >> + boot_mem_map.map[i].size); >> >> >> >> + ramstart = min(ramstart, boot_mem_map.map[i].addr); >> >> + >> >> #ifndef CONFIG_HIGHMEM >> >> /* >> >> * Skip highmem here so we get an accurate max_low_pfn if low >> >> @@ -436,6 +440,13 @@ static void __init bootmem_init(void) >> >> mapstart = max(reserved_end, start); >> >> } >> >> >> >> + /* >> >> + * Reserve any memory between the start of RAM and PHYS_OFFSET >> >> + */ >> >> + if (ramstart > PHYS_OFFSET) >> >> + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, >> >> + BOOT_MEM_RESERVED); >> >> + >> >> if (min_low_pfn >= max_low_pfn) >> >> panic("Incorrect memory mapping !!!"); >> >> if (min_low_pfn > ARCH_PFN_OFFSET) { >> >> @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) >> >> >> >> add_memory_region(start, size, BOOT_MEM_RAM); >> >> >> >> - if (start && start > PHYS_OFFSET) >> >> - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, >> >> - BOOT_MEM_RESERVED); >> >> return 0; >> >> } >> >> early_param("mem", early_parse_mem); >> >> -- >> >> 2.14.1 >> >> >> > >> > Looks good to me: >> > >> > $ cat /proc/cpuinfo >> > system type : JZ4780 >> > machine : Creator CI20 >> > processor : 0 >> > cpu model : Ingenic JZRISC V4.15 FPU V0.0 >> > BogoMIPS : 956.00 >> > wait instruction : yes >> > microsecond timers : no >> > tlb_entries : 32 >> > extra interrupt vector : yes >> > hardware watchpoint : yes, count: 1, address/irw mask: [0x0fff] >> > isa : mips1 mips2 mips32r1 mips32r2 >> > ASEs implemented : >> > shadow register sets : 1 >> > kscratch registers : 0 >> > package : 0 >> > core : 0 >> > VCED exceptions : not available >> > VCEI exceptions : not available >> > $ uname -a >> > Linux ci20 4.15.0+ #323 PREEMPT Thu Feb 1 13:08:11 CET 2018 mips GNU/Linux >> > >> > Tested-by: Mathieu Malaterre <malat(a)debian.org> >> > >> > Thanks >> >> Could you please review the patch v3 ? > > Yes, looks good to me, and Ralf had applied to his test branch so I > presume he's happy with it too. I'll apply for 4.16. Hum, just to be sure I understand the process. Which branch are you talking about: https://git.kernel.org/pub/scm/linux/kernel/git/ralf/linux.git > Commit 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") which > this fixes was evidently requested to be backported to stable (unsure > who by) and added to the 4.9 queue, but then this arose and it was > removed until this fix is merged (see > https://patchwork.linux-mips.org/patch/17268/). > > Anybody know how far back before 4.11 both of these patches should be > applied to stable? If not I'll just leave it at 4.11 and if its > important before then for kexec or whatever they can be requested again.

7 years, 4 months

1
0
0 0

v4.14.19 build: 0 failures 0 warnings (v4.14.19)

by Build bot for Mark Brown

Tree/Branch: v4.14.19 Git describe: v4.14.19 Commit: 1722fe3727 Linux 4.14.19 Build Time: 109 min 6 sec Passed: 10 / 10 (100.00 %) Failed: 0 / 10 ( 0.00 %) Errors: 0 Warnings: 0 Section Mismatches: 0 ------------------------------------------------------------------------------- defconfigs with issues (other than build errors): ------------------------------------------------------------------------------- =============================================================================== Detailed per-defconfig build reports below: ------------------------------------------------------------------------------- Passed with no errors, warnings or mismatches: arm64-allnoconfig arm64-allmodconfig arm-multi_v5_defconfig arm-multi_v7_defconfig x86_64-defconfig arm-allmodconfig arm-allnoconfig x86_64-allnoconfig arm-multi_v4t_defconfig arm64-defconfig close failed in file object destructor: sys.excepthook is missing lost sys.stderr

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH v3] MIPS: fix incorrect mem=X@Y handling

by Marcin Nowakowski

Commit 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") added a fix to ensure that the memory range between PHYS_OFFSET and low memory address specified by mem= cmdline argument is not later processed by free_all_bootmem. This change was incorrect for systems where the commandline specifies more than 1 mem argument, as it will cause all memory between PHYS_OFFSET and each of the memory offsets to be marked as reserved, which results in parts of the RAM marked as reserved (Creator CI20's u-boot has a default commandline argument 'mem=256M@0x0 mem=768M@0x30000000'). Change the behaviour to ensure that only the range between PHYS_OFFSET and the lowest start address of the memories is marked as protected. This change also ensures that the range is marked protected even if it's only defined through the devicetree and not only via commandline arguments. Reported-by: Mathieu Malaterre <mathieu.malaterre(a)gmail.com> Signed-off-by: Marcin Nowakowski <marcin.nowakowski(a)mips.com> Fixes: 73fbc1eba7ff ("MIPS: fix mem=X@Y commandline processing") Cc: <stable(a)vger.kernel.org> # v4.11+ --- v3: Update stable version, code cleanup as suggested by James Hogan v2: Use updated email adress, add tag for stable. --- arch/mips/kernel/setup.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 702c678de116..e4a1581ce822 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -375,6 +375,7 @@ static void __init bootmem_init(void) unsigned long reserved_end; unsigned long mapstart = ~0UL; unsigned long bootmap_size; + phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX; bool bootmap_valid = false; int i; @@ -395,7 +396,8 @@ static void __init bootmem_init(void) max_low_pfn = 0; /* - * Find the highest page frame number we have available. + * Find the highest page frame number we have available + * and the lowest used RAM address */ for (i = 0; i < boot_mem_map.nr_map; i++) { unsigned long start, end; @@ -407,6 +409,8 @@ static void __init bootmem_init(void) end = PFN_DOWN(boot_mem_map.map[i].addr + boot_mem_map.map[i].size); + ramstart = min(ramstart, boot_mem_map.map[i].addr); + #ifndef CONFIG_HIGHMEM /* * Skip highmem here so we get an accurate max_low_pfn if low @@ -436,6 +440,13 @@ static void __init bootmem_init(void) mapstart = max(reserved_end, start); } + /* + * Reserve any memory between the start of RAM and PHYS_OFFSET + */ + if (ramstart > PHYS_OFFSET) + add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET, + BOOT_MEM_RESERVED); + if (min_low_pfn >= max_low_pfn) panic("Incorrect memory mapping !!!"); if (min_low_pfn > ARCH_PFN_OFFSET) { @@ -664,9 +675,6 @@ static int __init early_parse_mem(char *p) add_memory_region(start, size, BOOT_MEM_RAM); - if (start && start > PHYS_OFFSET) - add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET, - BOOT_MEM_RESERVED); return 0; } early_param("mem", early_parse_mem); -- 2.14.1

7 years, 4 months

2
2
0 0

[tip:x86/urgent] x86/smpboot: Fix uncore_pci_remove() indexing bug when hot-removing a physical CPU

by tip-bot for Masayoshi Mizuma

Commit-ID: 295cc7eb314eb3321fb6d67ca6f7305f5c50d10f Gitweb: https://git.kernel.org/tip/295cc7eb314eb3321fb6d67ca6f7305f5c50d10f Author: Masayoshi Mizuma <m.mizuma(a)jp.fujitsu.com> AuthorDate: Thu, 8 Feb 2018 09:19:08 -0500 Committer: Ingo Molnar <mingo(a)kernel.org> CommitDate: Tue, 13 Feb 2018 12:47:28 +0100 x86/smpboot: Fix uncore_pci_remove() indexing bug when hot-removing a physical CPU When a physical CPU is hot-removed, the following warning messages are shown while the uncore device is removed in uncore_pci_remove(): WARNING: CPU: 120 PID: 5 at arch/x86/events/intel/uncore.c:988 uncore_pci_remove+0xf1/0x110 ... CPU: 120 PID: 5 Comm: kworker/u1024:0 Not tainted 4.15.0-rc8 #1 Workqueue: kacpi_hotplug acpi_hotplug_work_fn ... Call Trace: pci_device_remove+0x36/0xb0 device_release_driver_internal+0x145/0x210 pci_stop_bus_device+0x76/0xa0 pci_stop_root_bus+0x44/0x60 acpi_pci_root_remove+0x1f/0x80 acpi_bus_trim+0x54/0x90 acpi_bus_trim+0x2e/0x90 acpi_device_hotplug+0x2bc/0x4b0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 When uncore_pci_remove() runs, it tries to get the package ID to clear the value of uncore_extra_pci_dev[].dev[] by using topology_phys_to_logical_pkg(). The warning messesages are shown because topology_phys_to_logical_pkg() returns -1. arch/x86/events/intel/uncore.c: static void uncore_pci_remove(struct pci_dev *pdev) { ... phys_id = uncore_pcibus_to_physid(pdev->bus); ... pkg = topology_phys_to_logical_pkg(phys_id); // returns -1 for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { uncore_extra_pci_dev[pkg].dev[i] = NULL; break; } } WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); // <=========== HERE!! topology_phys_to_logical_pkg() tries to find cpuinfo_x86->phys_proc_id that matches the phys_pkg argument. arch/x86/kernel/smpboot.c: int topology_phys_to_logical_pkg(unsigned int phys_pkg) { int cpu; for_each_possible_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); if (c->initialized && c->phys_proc_id == phys_pkg) return c->logical_proc_id; } return -1; } However, the phys_proc_id was already set to 0 by remove_siblinginfo() when the CPU was offlined. So, topology_phys_to_logical_pkg() cannot find the correct logical_proc_id and always returns -1. As the result, uncore_pci_remove() calls WARN_ON_ONCE() and the warning messages are shown. What is worse is that the bogus 'pkg' index results in two bugs: - We dereference uncore_extra_pci_dev[] with a negative index - We fail to clean up a stale pointer in uncore_extra_pci_dev[][] To fix these bugs, remove the clearing of ->phys_proc_id from remove_siblinginfo(). This should not cause any problems, because ->phys_proc_id is not used after it is hot-removed and it is re-set while hot-adding. Signed-off-by: Masayoshi Mizuma <m.mizuma(a)jp.fujitsu.com> Acked-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: yasu.isimatu(a)gmail.com Cc: <stable(a)vger.kernel.org> Fixes: 30bb9811856f ("x86/topology: Avoid wasting 128k for package id array") Link: http://lkml.kernel.org/r/ed738d54-0f01-b38b-b794-c31dc118c207@gmail.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> --- arch/x86/kernel/smpboot.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27fac..cfc61e1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1430,7 +1430,6 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state();

7 years, 4 months

1
0
0 0

Re: Linux 4.9.81

by Greg KH

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4c2667aa4634..466c039c622b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2805,8 +2805,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space - noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops - noreplace-smp [X86-32,SMP] Don't replace SMP instructions with UP alternatives diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt new file mode 100644 index 000000000000..e9e6cbae2841 --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,90 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else + return array[index]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP <index>, #MAX_ARRAY_ELEMS + B.LT less + MOV <returnval>, #0 + RET + less: + LDR <returnval>, [<array>, <index>] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This +value will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may +result in sensitive information being leaked. Consider the following +code, building on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int index) + { + int val1, val2, + + val1 = load_array(arr1, index); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value +of an out-of-bounds address, while the second call will influence +microarchitectural state dependent on this value. This may provide an +arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are +respected even under speculation. Architectures which are affected by +speculation-based side-channels are expected to implement these +primitives. + +The array_index_nospec() helper in <linux/nospec.h> can be used to +prevent information from being leaked via side-channels. + +A call to array_index_nospec(index, size) returns a sanitized index +value that is bounded to [0, size) even under cpu speculation +conditions. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else { + index = array_index_nospec(index, MAX_ARRAY_ELEMS); + return array[index]; + } + } diff --git a/Makefile b/Makefile index 9550b6939076..4d5753f1c37b 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 80 +SUBLEVEL = 81 EXTRAVERSION = NAME = Roaring Lionus diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6eda5abbd719..0a6bb48854e3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -128,6 +128,7 @@ config PPC select ARCH_HAS_GCOV_PROFILE_ALL select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE + select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 select GENERIC_TIME_VSYSCALL_OLD select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index a703452d67b6..555e22d5e07f 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -209,5 +209,11 @@ exc_##label##_book3e: ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; +#define RFI_TO_KERNEL \ + rfi + +#define RFI_TO_USER \ + rfi + #endif /* _ASM_POWERPC_EXCEPTION_64E_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 9a3eee661297..cab6d2a46c41 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -51,6 +51,59 @@ #define EX_PPR 88 /* SMT thread status register (priority) */ #define EX_CTR 96 +/* + * Macros for annotating the expected destination of (h)rfid + * + * The nop instructions allow us to insert one or more instructions to flush the + * L1-D cache when returning to userspace or a guest. + */ +#define RFI_FLUSH_SLOT \ + RFI_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop + +#define RFI_TO_KERNEL \ + rfid + +#define RFI_TO_USER \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define HRFI_TO_KERNEL \ + hrfid + +#define HRFI_TO_USER \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_UNKNOWN \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + #ifdef CONFIG_RELOCATABLE #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index ddf54f5bbdd1..7b332342071c 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -189,4 +189,19 @@ void apply_feature_fixups(void); void setup_feature_keys(void); #endif +#define RFI_FLUSH_FIXUP_SECTION \ +951: \ + .pushsection __rfi_flush_fixup,"a"; \ + .align 2; \ +952: \ + FTR_ENTRY_OFFSET 951b-952b; \ + .popsection; + + +#ifndef __ASSEMBLY__ + +extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; + +#endif + #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 708edebcf147..0e12cb2437d1 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -240,6 +240,7 @@ #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC #define H_MANAGE_TRACE 0x1C0 +#define H_GET_CPU_CHARACTERISTICS 0x1C8 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4 #define H_QUERY_INT_STATE 0x1E4 #define H_POLL_PENDING 0x1D8 @@ -306,6 +307,17 @@ #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 +/* H_GET_CPU_CHARACTERISTICS return values */ +#define H_CPU_CHAR_SPEC_BAR_ORI31 (1ull << 63) // IBM bit 0 +#define H_CPU_CHAR_BCCTRL_SERIALISED (1ull << 62) // IBM bit 1 +#define H_CPU_CHAR_L1D_FLUSH_ORI30 (1ull << 61) // IBM bit 2 +#define H_CPU_CHAR_L1D_FLUSH_TRIG2 (1ull << 60) // IBM bit 3 +#define H_CPU_CHAR_L1D_THREAD_PRIV (1ull << 59) // IBM bit 4 + +#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 +#define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 +#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 + #ifndef __ASSEMBLY__ /** @@ -433,6 +445,11 @@ static inline unsigned long cmo_get_page_size(void) } #endif /* CONFIG_PPC_PSERIES */ +struct h_cpu_char_result { + u64 character; + u64 behaviour; +}; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6a6792bb39fb..ea43897183fd 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -205,6 +205,16 @@ struct paca_struct { struct sibling_subcore_state *sibling_subcore_state; #endif #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * rfi fallback flush must be in its own cacheline to prevent + * other paca data leaking into the L1d + */ + u64 exrfi[13] __aligned(0x80); + void *rfi_flush_fallback_area; + u64 l1d_flush_congruence; + u64 l1d_flush_sets; +#endif }; #ifdef CONFIG_PPC_BOOK3S diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 1b394247afc2..4e53b8570d1f 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -340,4 +340,18 @@ static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawr return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0); } +static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf); + if (rc == H_SUCCESS) { + p->character = retbuf[0]; + p->behaviour = retbuf[1]; + } + + return rc; +} + #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 654d64c9f3ac..6825a67cc3db 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -38,6 +38,19 @@ static inline void pseries_big_endian_exceptions(void) {} static inline void pseries_little_endian_exceptions(void) {} #endif /* CONFIG_PPC_PSERIES */ +void rfi_flush_enable(bool enable); + +/* These are bit flags */ +enum l1d_flush_type { + L1D_FLUSH_NONE = 0x1, + L1D_FLUSH_FALLBACK = 0x2, + L1D_FLUSH_ORI = 0x4, + L1D_FLUSH_MTTRIG = 0x8, +}; + +void __init setup_rfi_flush(enum l1d_flush_type, bool enable); +void do_rfi_flush_fixups(enum l1d_flush_type types); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c833d88c423d..64bcbd580495 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -240,6 +240,10 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S_64 DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp)); DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce)); + DEFINE(PACA_RFI_FLUSH_FALLBACK_AREA, offsetof(struct paca_struct, rfi_flush_fallback_area)); + DEFINE(PACA_EXRFI, offsetof(struct paca_struct, exrfi)); + DEFINE(PACA_L1D_FLUSH_CONGRUENCE, offsetof(struct paca_struct, l1d_flush_congruence)); + DEFINE(PACA_L1D_FLUSH_SETS, offsetof(struct paca_struct, l1d_flush_sets)); #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index caa659671599..c33b69d10919 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -251,13 +251,23 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ + ld r2,GPR2(r1) + ld r1,GPR1(r1) + mtlr r4 + mtcr r5 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + RFI_TO_USER + b . /* prevent speculative execution */ + + /* exit to kernel */ 1: ld r2,GPR2(r1) ld r1,GPR1(r1) mtlr r4 mtcr r5 mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - RFI + RFI_TO_KERNEL b . /* prevent speculative execution */ syscall_error: @@ -859,7 +869,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ACCOUNT_CPU_USER_EXIT(r13, r2, r4) REST_GPR(13, r1) -1: + mtspr SPRN_SRR1,r3 ld r2,_CCR(r1) @@ -872,8 +882,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r3,GPR3(r1) ld r4,GPR4(r1) ld r1,GPR1(r1) + RFI_TO_USER + b . /* prevent speculative execution */ - rfid +1: mtspr SPRN_SRR1,r3 + + ld r2,_CCR(r1) + mtcrf 0xFF,r2 + ld r2,_NIP(r1) + mtspr SPRN_SRR0,r2 + + ld r0,GPR0(r1) + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r1,GPR1(r1) + RFI_TO_KERNEL b . /* prevent speculative execution */ #endif /* CONFIG_PPC_BOOK3E */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index fd68e19b9ef7..96db6c3adebe 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -655,6 +655,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) andi. r10,r12,MSR_RI /* check for unrecoverable exception */ beq- 2f + andi. r10,r12,MSR_PR /* check for user mode (PR != 0) */ + bne 1f /* All done -- return from exception. */ @@ -671,7 +673,23 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) ld r11,PACA_EXSLB+EX_R11(r13) ld r12,PACA_EXSLB+EX_R12(r13) ld r13,PACA_EXSLB+EX_R13(r13) - rfid + RFI_TO_KERNEL + b . /* prevent speculative execution */ + +1: +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_PPR_PACA(PACA_EXSLB, r9) + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + RFI_TO_USER b . /* prevent speculative execution */ 2: mfspr r11,SPRN_SRR0 @@ -679,7 +697,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 8: mfspr r11,SPRN_SRR0 @@ -1576,6 +1594,92 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) bl kernel_bad_stack b 1b + .globl rfi_flush_fallback +rfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + rfid + + .globl hrfi_flush_fallback +hrfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + hrfid + /* * Called from arch_local_irq_enable when an interrupt needs * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a12be60181bf..7c30a91c1f86 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -37,6 +37,7 @@ #include <linux/memblock.h> #include <linux/memory.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <asm/io.h> #include <asm/kdump.h> @@ -678,4 +679,142 @@ static int __init disable_hardlockup_detector(void) return 0; } early_initcall(disable_hardlockup_detector); + +#ifdef CONFIG_PPC_BOOK3S_64 +static enum l1d_flush_type enabled_flush_types; +static void *l1d_flush_fallback_area; +static bool no_rfi_flush; +bool rfi_flush; + +static int __init handle_no_rfi_flush(char *p) +{ + pr_info("rfi-flush: disabled on command line."); + no_rfi_flush = true; + return 0; +} +early_param("no_rfi_flush", handle_no_rfi_flush); + +/* + * The RFI flush is not KPTI, but because users will see doco that says to use + * nopti we hijack that option here to also disable the RFI flush. + */ +static int __init handle_no_pti(char *p) +{ + pr_info("rfi-flush: disabling due to 'nopti' on command line.\n"); + handle_no_rfi_flush(NULL); + return 0; +} +early_param("nopti", handle_no_pti); + +static void do_nothing(void *unused) +{ + /* + * We don't need to do the flush explicitly, just enter+exit kernel is + * sufficient, the RFI exit handlers will do the right thing. + */ +} + +void rfi_flush_enable(bool enable) +{ + if (rfi_flush == enable) + return; + + if (enable) { + do_rfi_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else + do_rfi_flush_fixups(L1D_FLUSH_NONE); + + rfi_flush = enable; +} + +static void init_fallback_flush(void) +{ + u64 l1d_size, limit; + int cpu; + + l1d_size = ppc64_caches.dsize; + limit = min(safe_stack_limit(), ppc64_rma_size); + + /* + * Align to L1d size, and size it at 2x L1d size, to catch possible + * hardware prefetch runoff. We don't have a recipe for load patterns to + * reliably avoid the prefetcher. + */ + l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit)); + memset(l1d_flush_fallback_area, 0, l1d_size * 2); + + for_each_possible_cpu(cpu) { + /* + * The fallback flush is currently coded for 8-way + * associativity. Different associativity is possible, but it + * will be treated as 8-way and may not evict the lines as + * effectively. + * + * 128 byte lines are mandatory. + */ + u64 c = l1d_size / 8; + + paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; + paca[cpu].l1d_flush_congruence = c; + paca[cpu].l1d_flush_sets = c / 128; + } +} + +void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) +{ + if (types & L1D_FLUSH_FALLBACK) { + pr_info("rfi-flush: Using fallback displacement flush\n"); + init_fallback_flush(); + } + + if (types & L1D_FLUSH_ORI) + pr_info("rfi-flush: Using ori type flush\n"); + + if (types & L1D_FLUSH_MTTRIG) + pr_info("rfi-flush: Using mttrig type flush\n"); + + enabled_flush_types = types; + + if (!no_rfi_flush) + rfi_flush_enable(enable); +} + +#ifdef CONFIG_DEBUG_FS +static int rfi_flush_set(void *data, u64 val) +{ + if (val == 1) + rfi_flush_enable(true); + else if (val == 0) + rfi_flush_enable(false); + else + return -EINVAL; + + return 0; +} + +static int rfi_flush_get(void *data, u64 *val) +{ + *val = rfi_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); + +static __init int rfi_flush_debugfs_init(void) +{ + debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + return 0; +} +device_initcall(rfi_flush_debugfs_init); +#endif + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (rfi_flush) + return sprintf(buf, "Mitigation: RFI Flush\n"); + + return sprintf(buf, "Vulnerable\n"); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 7394b770ae1f..b61fb7902018 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,15 @@ SECTIONS /* Read-only data */ RODATA +#ifdef CONFIG_PPC64 + . = ALIGN(8); + __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) { + __start___rfi_flush_fixup = .; + *(__rfi_flush_fixup) + __stop___rfi_flush_fixup = .; + } +#endif + EXCEPTION_TABLE(0) NOTES :kernel :notes diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 043415f0bdb1..e86bfa111f3c 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -23,6 +23,7 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/firmware.h> +#include <asm/setup.h> struct fixup_entry { unsigned long mask; @@ -115,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +#ifdef CONFIG_PPC_BOOK3S_64 +void do_rfi_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___rfi_flush_fixup), + end = PTRRELOC(&__stop___rfi_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + if (types & L1D_FLUSH_FALLBACK) + /* b .+16 to fallback flush */ + instrs[0] = 0x48000010; + + i = 0; + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + patch_instruction(dest + 1, instrs[1]); + patch_instruction(dest + 2, instrs[2]); + } + + printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ + void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { long *start, *end; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index b33faa0015cc..6f8b4c19373a 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -35,13 +35,63 @@ #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> +#include <asm/tm.h> +#include <asm/setup.h> #include "powernv.h" +static void pnv_setup_rfi_flush(void) +{ + struct device_node *np, *fw_features; + enum l1d_flush_type type; + int enable; + + /* Default to fallback in case fw-features are not available */ + type = L1D_FLUSH_FALLBACK; + enable = 1; + + np = of_find_node_by_name(NULL, "ibm,opal"); + fw_features = of_get_child_by_name(np, "fw-features"); + of_node_put(np); + + if (fw_features) { + np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_MTTRIG; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_ORI; + + of_node_put(np); + + /* Enable unless firmware says NOT to */ + enable = 2; + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + of_node_put(fw_features); + } + + setup_rfi_flush(type, enable > 0); +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + pnv_setup_rfi_flush(); + /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 97aa3f332f24..1845fc611912 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -450,6 +450,39 @@ static void __init find_and_init_phbs(void) of_pci_check_probe_only(); } +static void pseries_setup_rfi_flush(void) +{ + struct h_cpu_char_result result; + enum l1d_flush_type types; + bool enable; + long rc; + + /* Enable by default */ + enable = true; + + rc = plpar_get_cpu_characteristics(&result); + if (rc == H_SUCCESS) { + types = L1D_FLUSH_NONE; + + if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2) + types |= L1D_FLUSH_MTTRIG; + if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30) + types |= L1D_FLUSH_ORI; + + /* Use fallback if nothing set in hcall */ + if (types == L1D_FLUSH_NONE) + types = L1D_FLUSH_FALLBACK; + + if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + enable = false; + } else { + /* Default to fallback if case hcall is not available */ + types = L1D_FLUSH_FALLBACK; + } + + setup_rfi_flush(types, enable); +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -467,6 +500,8 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); + pseries_setup_rfi_flush(); + /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index bdd9cc59d20f..b0cd306dc527 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -20,6 +20,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <asm/desc.h> @@ -201,7 +202,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -277,7 +278,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -299,7 +301,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -313,6 +315,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index a76dc738ec61..f5434b4670c1 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -237,7 +237,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %ebx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e729e1528584..db5009ce065a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -177,96 +177,17 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ -#ifdef CONFIG_RETPOLINE - movq sys_call_table(, %rax, 8), %rax - call __x86_indirect_thunk_rax -#else - call *sys_call_table(, %rax, 8) -#endif -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: - - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - RESTORE_C_REGS_EXCEPT_RCX_R11 - /* - * This opens a window where we have a user CR3, but are - * running in the kernel. This makes using the CS - * register useless for telling whether or not we need to - * switch CR3 in NMIs. Normal interrupts are OK because - * they are off here. - */ - SWITCH_USER_CR3 - movq RSP(%rsp), %rsp - USERGS_SYSRET64 - -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -339,6 +260,7 @@ return_from_SYSCALL_64: syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 + /* * This opens a window where we have a user CR3, but are * running in the kernel. This makes using the CS @@ -363,45 +285,6 @@ opportunistic_sysret_failed: jmp restore_c_regs_and_iret END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - popq %rax - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task @@ -435,7 +318,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %rbx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9dbc5abb6162..6705edda4ac3 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -6,14 +6,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 982c9e31daca..21298c173b0e 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -22,6 +22,7 @@ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/coredump.h> +#include <linux/kaiser.h> #include <asm-generic/sizes.h> #include <asm/perf_event.h> @@ -77,6 +78,23 @@ static size_t buf_size(struct page *page) return 1 << (PAGE_SHIFT + page_private(page)); } +static void bts_buffer_free_aux(void *data) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + struct bts_buffer *buf = data; + int nbuf; + + for (nbuf = 0; nbuf < buf->nr_bufs; nbuf++) { + struct page *page = buf->buf[nbuf].page; + void *kaddr = page_address(page); + size_t page_size = buf_size(page); + + kaiser_remove_mapping((unsigned long)kaddr, page_size); + } +#endif + kfree(data); +} + static void * bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) { @@ -113,29 +131,33 @@ bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) buf->real_size = size - size % BTS_RECORD_SIZE; for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) { - unsigned int __nr_pages; + void *kaddr = pages[pg]; + size_t page_size; + + page = virt_to_page(kaddr); + page_size = buf_size(page); + + if (kaiser_add_mapping((unsigned long)kaddr, + page_size, __PAGE_KERNEL) < 0) { + buf->nr_bufs = nbuf; + bts_buffer_free_aux(buf); + return NULL; + } - page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); - buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement; + buf->buf[nbuf].size = page_size - buf->buf[nbuf].displacement; pad = buf->buf[nbuf].size % BTS_RECORD_SIZE; buf->buf[nbuf].size -= pad; - pg += __nr_pages; - offset += __nr_pages << PAGE_SHIFT; + pg += page_size >> PAGE_SHIFT; + offset += page_size; } return buf; } -static void bts_buffer_free_aux(void *data) -{ - kfree(data); -} - static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx) { return buf->buf[idx].offset + buf->buf[idx].displacement; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index b15aa4083dfd..166654218329 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -37,5 +37,7 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -INDIRECT_THUNK(sp) +asmlinkage void __fill_rsb(void); +asmlinkage void __clear_rsb(void); + #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 00523524edbf..7bb29a416b77 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index bfb28caf97b1..857590390397 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -23,6 +23,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 9ea67a04ff4f..8c101579f535 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -28,6 +28,7 @@ enum cpuid_leafs CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, + CPUID_7_EDX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -78,8 +79,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -100,8 +102,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8537a21acd8b..8eb23f5cf7f4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -194,16 +194,16 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ @@ -260,6 +260,9 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ +#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -295,6 +298,13 @@ #define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 21c5ac15657b..1f8cca459c6c 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -59,6 +59,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 34a46dc076d3..75b748a1deb8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -12,6 +12,7 @@ */ #define INTEL_FAM6_CORE_YONAH 0x0E + #define INTEL_FAM6_CORE2_MEROM 0x0F #define INTEL_FAM6_CORE2_MEROM_L 0x16 #define INTEL_FAM6_CORE2_PENRYN 0x17 @@ -21,6 +22,7 @@ #define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_FAM6_NEHALEM_EX 0x2E + #define INTEL_FAM6_WESTMERE 0x25 #define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_FAM6_WESTMERE_EX 0x2F @@ -36,9 +38,9 @@ #define INTEL_FAM6_HASWELL_GT3E 0x46 #define INTEL_FAM6_BROADWELL_CORE 0x3D -#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_BROADWELL_GT3E 0x47 #define INTEL_FAM6_BROADWELL_X 0x4F +#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_SKYLAKE_MOBILE 0x4E #define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E @@ -57,9 +59,10 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ +#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A /* Xeon Phi */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b11c4c072df8..c768bc1550a1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -37,6 +37,13 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ + #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd @@ -50,6 +57,11 @@ #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) #define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index b5fee97813cd..ed35b915b5c9 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -188,8 +188,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4ad41087ce0e..300cc159b4a0 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -1,56 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NOSPEC_BRANCH_H__ -#define __NOSPEC_BRANCH_H__ +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * We define a CPP macro such that it can be used from both .S files and - * inline assembly. It's possible to do a .macro and then include that - * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. - */ - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -/* - * Google experimented with loop-unrolling and this turned out to be - * the optimal version — two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - call 772f; \ -773: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - call 774f; \ -775: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - dec reg; \ - jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; - #ifdef __ASSEMBLY__ /* @@ -121,17 +77,10 @@ #endif .endm - /* - * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP - * monstrosity above, manually. - */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +/* This clobbers the BX register */ +.macro FILL_RETURN_BUFFER nr:req ftr:req #ifdef CONFIG_RETPOLINE - ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE "jmp .Lskip_rsb_\@", \ - __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ - \ftr -.Lskip_rsb_\@: + ALTERNATIVE "", "call __clear_rsb", \ftr #endif .endm @@ -201,22 +150,30 @@ extern char __indirect_thunk_end[]; * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ATT *might* it be avoided. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); + alternative_input("", + "call __fill_rsb", + X86_FEATURE_RETPOLINE, + ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); #endif } +static inline void indirect_branch_prediction_barrier(void) +{ + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_USE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); +} + #endif /* __ASSEMBLY__ */ -#endif /* __NOSPEC_BRANCH_H__ */ +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 1178a51b77f3..b6d425999f99 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -27,17 +27,6 @@ static inline void paravirt_release_pud(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp; -#ifdef CONFIG_PAGE_TABLE_ISOLATION -/* - * Instead of one PGD, we acquire two PGDs. Being order-1, it is - * both 8k in size and 8k-aligned. That lets us just flip bit 12 - * in a pointer to swap between the two 4k halves. - */ -#define PGD_ALLOCATION_ORDER 1 -#else -#define PGD_ALLOCATION_ORDER 0 -#endif - /* * Allocate and free page tables. */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2536f90cd30c..5af0401ccff2 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -20,9 +20,15 @@ #ifdef CONFIG_PAGE_TABLE_ISOLATION extern int kaiser_enabled; +/* + * Instead of one PGD, we acquire two PGDs. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ #else #define kaiser_enabled 0 #endif +#define PGD_ALLOCATION_ORDER kaiser_enabled void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); void ptdump_walk_pgd_level_checkwx(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 353f038ec645..cb866ae1bc5d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -391,8 +391,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index fac9a5c0abe9..6847d85400a8 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -100,6 +100,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8e61c5..03eedc21246d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index bdf9c4c91572..89978b9c667a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -54,6 +54,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -213,7 +214,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index dead0f3921f3..a8d85a687cf4 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -123,6 +123,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -432,7 +437,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -474,6 +479,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -538,7 +547,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -573,7 +582,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 7d3bdd1ed697..d6d245088dd5 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -102,17 +102,17 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; @@ -130,17 +130,17 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 673059a109fe..6e5cc08134ba 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -59,31 +59,31 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -93,7 +93,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 10d5a3d6affc..03b6e5c6cf23 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -588,9 +577,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8cacf62ec458..957ad443b786 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/utsname.h> #include <linux/cpu.h> +#include <linux/module.h> #include <asm/nospec-branch.h> #include <asm/cmdline.h> @@ -89,20 +90,41 @@ static const char *spectre_v2_strings[] = { }; #undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static void __init spec2_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -117,42 +139,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt) return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { char arg[20]; - int ret; - - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); - if (ret > 0) { - if (match_option(arg, ret, "off")) { - goto disable; - } else if (match_option(arg, ret, "on")) { - spec2_print_if_secure("force enabled on command line."); - return SPECTRE_V2_CMD_FORCE; - } else if (match_option(arg, ret, "retpoline")) { - spec2_print_if_insecure("retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE; - } else if (match_option(arg, ret, "retpoline,amd")) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec2_print_if_insecure("AMD retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_AMD; - } else if (match_option(arg, ret, "retpoline,generic")) { - spec2_print_if_insecure("generic retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_GENERIC; - } else if (match_option(arg, ret, "auto")) { + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); return SPECTRE_V2_CMD_AUTO; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ @@ -190,10 +238,10 @@ static void __init spectre_v2_select_mitigation(void) return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; @@ -248,6 +296,12 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Filling RSB on context switch\n"); } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + pr_info("Enabling Indirect Branch Prediction Barrier\n"); + } } #undef pr_fmt @@ -268,7 +322,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, @@ -277,6 +331,8 @@ ssize_t cpu_show_spectre_v2(struct device *dev, if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d198ae02f2b7..08e89ed6aa87 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -44,6 +44,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -716,6 +718,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -737,6 +759,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ @@ -809,6 +832,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -837,6 +861,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -883,11 +942,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (c->x86_vendor != X86_VENDOR_AMD) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } fpu__init_system(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..4097b43cba2d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -61,6 +61,59 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-up… + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Updated in the 20180108 release; blacklist until we know otherwise */ + { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_mask == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -87,6 +140,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); } + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 5ce5155f0695..0afaf00b029b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -43,7 +43,7 @@ #define MICROCODE_VERSION "2.01" static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; /* * Synchronization. @@ -73,6 +73,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -85,8 +86,20 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -114,9 +127,7 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; - - if (check_loader_disabled_bsp()) - return; + bool intel = true; if (!have_cpuid_p()) return; @@ -126,16 +137,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) @@ -154,9 +176,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_cpuid_vendor(); family = x86_cpuid_family(); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b0dd9aec183d..afbb52532791 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,8 +31,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0887d2ae3797..dffe81d3c261 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -538,7 +538,7 @@ void set_personality_ia32(bool x32) current->personality &= ~READ_IMPLIES_EXEC; /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); @@ -546,7 +546,7 @@ void set_personality_ia32(bool x32) current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; } } EXPORT_SYMBOL_GPL(set_personality_ia32); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 0e63c0267f99..e497d374412a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -934,7 +934,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 763af1d0de64..b1a5d252d482 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -785,7 +785,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 8402907825b0..21454e254a4c 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -134,6 +134,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); pte_unmap(pte); + + /* + * PTI poisons low addresses in the kernel page tables in the + * name of making them unusable for userspace. To execute + * code at such a low address, the poison must be cleared. + * + * Note: 'pgd' actually gets set in pud_alloc(). + */ + pgd->pgd &= ~_PAGE_NX; + return 0; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 91af75e37306..93f924de06cf 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -355,6 +355,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); + /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -376,6 +380,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = F(PKU) | 0 /*OSPKE*/; + /* cpuid 7.0.edx*/ + const u32 kvm_cpuid_7_0_edx_x86_features = + F(SPEC_CTRL) | F(ARCH_CAPABILITIES); + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -458,12 +466,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; + entry->edx = 0; } entry->eax = 0; - entry->edx = 0; break; } case 9: @@ -607,7 +617,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 9368fecca3ee..d1beb7156704 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -160,6 +160,37 @@ static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) return best && (best->edx & bit(X86_FEATURE_RDTSCP)); } +static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBPB))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + +static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + +static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES)); +} + + /* * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6f5a3b076341..c8d573822e60 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" @@ -1012,8 +1013,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; call *%[fastop]" - : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + asm("push %[flags]; popf; " CALL_NOSPEC + : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } @@ -5306,15 +5307,14 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 24af898fb3a6..be644afab1bb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -183,6 +183,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -248,6 +250,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -510,6 +514,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -861,6 +866,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1535,6 +1559,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1644,11 +1670,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1677,6 +1709,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -3508,6 +3544,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3599,6 +3642,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4826,6 +4912,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -4918,6 +5013,27 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 178a344f55f8..d49da86e3099 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -109,6 +110,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -173,7 +182,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -191,6 +199,7 @@ struct loaded_vmcs { struct vmcs *shadow_vmcs; int cpu; int launched; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -207,7 +216,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -386,13 +395,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -419,15 +421,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -436,8 +438,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -538,6 +538,7 @@ struct vcpu_vmx { unsigned long host_rsp; u8 fail; bool nmi_known_unmasked; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -549,6 +550,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; /* @@ -856,21 +861,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - /* - * FIXME: Mitigation for CVE-2017-5753. To be replaced with a - * generic mechanism. - */ - asm("lfence"); - - if (vmcs_field_to_offset_table[field] == 0) + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) return -ENOENT; - - return vmcs_field_to_offset_table[field]; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -912,6 +914,9 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -931,12 +936,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; -static unsigned long *vmx_msr_bitmap_legacy; -static unsigned long *vmx_msr_bitmap_longmode; -static unsigned long *vmx_msr_bitmap_legacy_x2apic; -static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_legacy_x2apic_apicv_inactive; -static unsigned long *vmx_msr_bitmap_longmode_x2apic_apicv_inactive; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -1853,6 +1852,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2262,6 +2307,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2530,36 +2576,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv_inactive; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv_inactive; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2600,7 +2616,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -2989,6 +3005,19 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has_arch_capabilities(vcpu)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3093,6 +3122,68 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3532,11 +3623,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3552,9 +3638,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4561,10 +4676,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4598,8 +4711,8 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } -static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4633,6 +4746,15 @@ static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -4679,58 +4801,68 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); -} + u8 mode = 0; -static void vmx_enable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) -{ - if (apicv_active) { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_read_x2apic(u32 msr, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_R); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_R); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_R); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } -static void vmx_disable_intercept_msr_write_x2apic(u32 msr, bool apicv_active) +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, MSR_TYPE_W); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - msr, MSR_TYPE_W); - } + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; } static bool vmx_get_enable_apicv(void) @@ -4738,30 +4870,45 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; void *vapic_page; u16 status; - if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return; - if (max_irr == 256) - return 0; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return; + max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4772,7 +4919,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; + + nested_mark_vmcs12_pages_dirty(vcpu); } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4959,7 +5107,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5048,7 +5196,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5122,6 +5270,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5150,6 +5300,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->soft_vnmi_blocked = 0; @@ -6379,7 +6530,7 @@ static void wakeup_handler(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6394,41 +6545,13 @@ static __init int hardware_setup(void) if (!vmx_io_bitmap_b) goto out; - vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) - goto out1; - - vmx_msr_bitmap_legacy_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic) - goto out2; - - vmx_msr_bitmap_legacy_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy_x2apic_apicv_inactive) - goto out3; - - vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) - goto out4; - - vmx_msr_bitmap_longmode_x2apic = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic) - goto out5; - - vmx_msr_bitmap_longmode_x2apic_apicv_inactive = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode_x2apic_apicv_inactive) - goto out6; - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) - goto out7; + goto out1; vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmwrite_bitmap) - goto out8; + goto out2; memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); @@ -6437,12 +6560,9 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; - goto out9; + goto out3; } if (boot_cpu_has(X86_FEATURE_NX)) @@ -6499,47 +6619,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv_inactive, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv_inactive, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - /* - * enable_apicv && kvm_vcpu_apicv_active() - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - vmx_disable_intercept_msr_read_x2apic(msr, true); - - /* TMCCT */ - vmx_enable_intercept_msr_read_x2apic(0x839, true); - /* TPR */ - vmx_disable_intercept_msr_write_x2apic(0x808, true); - /* EOI */ - vmx_disable_intercept_msr_write_x2apic(0x80b, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_write_x2apic(0x83f, true); - - /* - * (enable_apicv && !kvm_vcpu_apicv_active()) || - * !enable_apicv - */ - /* TPR */ - vmx_disable_intercept_msr_read_x2apic(0x808, false); - vmx_disable_intercept_msr_write_x2apic(0x808, false); - if (enable_ept) { kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, @@ -6585,22 +6666,10 @@ static __init int hardware_setup(void) return alloc_kvm_area(); -out9: - free_page((unsigned long)vmx_vmwrite_bitmap); -out8: - free_page((unsigned long)vmx_vmread_bitmap); -out7: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); -out6: - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); -out5: - free_page((unsigned long)vmx_msr_bitmap_longmode); -out4: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); out3: - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); + free_page((unsigned long)vmx_vmwrite_bitmap); out2: - free_page((unsigned long)vmx_msr_bitmap_legacy); + free_page((unsigned long)vmx_vmread_bitmap); out1: free_page((unsigned long)vmx_io_bitmap_b); out: @@ -6611,12 +6680,6 @@ static __init int hardware_setup(void) static __exit void hardware_unsetup(void) { - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); - free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); - free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic_apicv_inactive); - free_page((unsigned long)vmx_msr_bitmap_legacy); - free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); @@ -6663,94 +6726,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } -/* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - /* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified @@ -7025,6 +7000,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + int r; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -7064,12 +7040,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7086,9 +7059,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7103,9 +7073,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7181,17 +7151,13 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmcs_clear(vmx->vmcs01.shadow_vmcs); free_vmcs(vmx->vmcs01.shadow_vmcs); vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7207,7 +7173,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7241,8 +7207,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; @@ -8029,6 +7993,19 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX); + /* + * The host physical addresses of some pages of guest memory + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false; @@ -8520,7 +8497,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -8676,14 +8653,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif "+r"(__sp) : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -8909,6 +8886,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -9027,6 +9013,27 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -9140,6 +9147,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9172,17 +9180,24 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) - goto free_msrs; if (!vmm_exclusive) kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id()))); - loaded_vmcs_init(vmx->loaded_vmcs); + err = alloc_loaded_vmcs(&vmx->vmcs01); if (!vmm_exclusive) kvm_cpu_vmxoff(); + if (err < 0) + goto free_msrs; + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -9576,21 +9591,31 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); if (!page) return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9617,6 +9642,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); nested_release_page_clean(page); @@ -10096,6 +10134,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10191,7 +10232,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); int cpu; - struct loaded_vmcs *vmcs02; bool ia32e; u32 msr_entry_idx; @@ -10331,17 +10371,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); cpu = get_cpu(); - vmx->loaded_vmcs = vmcs02; + vmx->loaded_vmcs = &vmx->nested.vmcs02; vmx_vcpu_put(vcpu); vmx_vcpu_load(vcpu, cpu); vcpu->cpu = cpu; @@ -10493,7 +10529,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10804,7 +10841,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -10855,10 +10892,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - load_vmcs12_host_state(vcpu, vmcs12); /* Update any VMCS fields that might have changed while L2 ran */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e023ef981feb..75f756eac979 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,6 +975,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6bf1898ddf49..4ad7c4dd311c 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -26,6 +26,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_RETPOLINE) += retpoline.o +OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 37b62d412148..b12b214713a6 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -39,6 +39,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -53,6 +55,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -67,6 +71,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -82,6 +88,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -93,6 +101,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index dfb2ba91b670..480edc3a5e03 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,6 +7,7 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -36,7 +37,6 @@ GENERATE_THUNK(_ASM_DX) GENERATE_THUNK(_ASM_SI) GENERATE_THUNK(_ASM_DI) GENERATE_THUNK(_ASM_BP) -GENERATE_THUNK(_ASM_SP) #ifdef CONFIG_64BIT GENERATE_THUNK(r8) GENERATE_THUNK(r9) @@ -47,3 +47,58 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 3bc7baf2a711..5c06dbffc52f 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -570,12 +570,12 @@ do { \ unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_to_user_ll); @@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index e3af318af2db..2a07341aca46 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -223,11 +223,13 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE], } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index 83f1439e57fd..6e8eaa7fe7a6 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -442,3 +442,7 @@ static struct platform_driver img_ascii_lcd_driver = { .remove = img_ascii_lcd_remove, }; module_platform_driver(img_ascii_lcd_driver); + +MODULE_DESCRIPTION("Imagination Technologies ASCII LCD Display"); +MODULE_AUTHOR("Paul Burton <paul.burton(a)mips.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index a2ec6d8796a0..3322b157106d 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -392,6 +392,31 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc) rcrtc->started = true; } +static void rcar_du_crtc_disable_planes(struct rcar_du_crtc *rcrtc) +{ + struct rcar_du_device *rcdu = rcrtc->group->dev; + struct drm_crtc *crtc = &rcrtc->crtc; + u32 status; + /* Make sure vblank interrupts are enabled. */ + drm_crtc_vblank_get(crtc); + /* + * Disable planes and calculate how many vertical blanking interrupts we + * have to wait for. If a vertical blanking interrupt has been triggered + * but not processed yet, we don't know whether it occurred before or + * after the planes got disabled. We thus have to wait for two vblank + * interrupts in that case. + */ + spin_lock_irq(&rcrtc->vblank_lock); + rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0); + status = rcar_du_crtc_read(rcrtc, DSSR); + rcrtc->vblank_count = status & DSSR_VBK ? 2 : 1; + spin_unlock_irq(&rcrtc->vblank_lock); + if (!wait_event_timeout(rcrtc->vblank_wait, rcrtc->vblank_count == 0, + msecs_to_jiffies(100))) + dev_warn(rcdu->dev, "vertical blanking timeout\n"); + drm_crtc_vblank_put(crtc); +} + static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc) { struct drm_crtc *crtc = &rcrtc->crtc; @@ -400,17 +425,16 @@ static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc) return; /* Disable all planes and wait for the change to take effect. This is - * required as the DSnPR registers are updated on vblank, and no vblank - * will occur once the CRTC is stopped. Disabling planes when starting - * the CRTC thus wouldn't be enough as it would start scanning out - * immediately from old frame buffers until the next vblank. + * required as the plane enable registers are updated on vblank, and no + * vblank will occur once the CRTC is stopped. Disabling planes when + * starting the CRTC thus wouldn't be enough as it would start scanning + * out immediately from old frame buffers until the next vblank. * * This increases the CRTC stop delay, especially when multiple CRTCs * are stopped in one operation as we now wait for one vblank per CRTC. * Whether this can be improved needs to be researched. */ - rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0); - drm_crtc_wait_one_vblank(crtc); + rcar_du_crtc_disable_planes(rcrtc); /* Disable vertical blanking interrupt reporting. We first need to wait * for page flip completion before stopping the CRTC as userspace @@ -548,10 +572,25 @@ static irqreturn_t rcar_du_crtc_irq(int irq, void *arg) irqreturn_t ret = IRQ_NONE; u32 status; + spin_lock(&rcrtc->vblank_lock); + status = rcar_du_crtc_read(rcrtc, DSSR); rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK); - if (status & DSSR_FRM) { + if (status & DSSR_VBK) { + /* + * Wake up the vblank wait if the counter reaches 0. This must + * be protected by the vblank_lock to avoid races in + * rcar_du_crtc_disable_planes(). + */ + if (rcrtc->vblank_count) { + if (--rcrtc->vblank_count == 0) + wake_up(&rcrtc->vblank_wait); + } + } + spin_unlock(&rcrtc->vblank_lock); + + if (status & DSSR_VBK) { drm_crtc_handle_vblank(&rcrtc->crtc); rcar_du_crtc_finish_page_flip(rcrtc); ret = IRQ_HANDLED; @@ -606,6 +645,8 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index) } init_waitqueue_head(&rcrtc->flip_wait); + init_waitqueue_head(&rcrtc->vblank_wait); + spin_lock_init(&rcrtc->vblank_lock); rcrtc->group = rgrp; rcrtc->mmio_offset = mmio_offsets[index]; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h index 6f08b7e7db06..48bef05b4c62 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h @@ -15,6 +15,7 @@ #define __RCAR_DU_CRTC_H__ #include <linux/mutex.h> +#include <linux/spinlock.h> #include <linux/wait.h> #include <drm/drmP.h> @@ -33,6 +34,9 @@ struct rcar_du_vsp; * @started: whether the CRTC has been started and is running * @event: event to post when the pending page flip completes * @flip_wait: wait queue used to signal page flip completion + * @vblank_lock: protects vblank_wait and vblank_count + * @vblank_wait: wait queue used to signal vertical blanking + * @vblank_count: number of vertical blanking interrupts to wait for * @outputs: bitmask of the outputs (enum rcar_du_output) driven by this CRTC * @group: CRTC group this CRTC belongs to */ @@ -48,6 +52,10 @@ struct rcar_du_crtc { struct drm_pending_vblank_event *event; wait_queue_head_t flip_wait; + spinlock_t vblank_lock; + wait_queue_head_t vblank_wait; + unsigned int vblank_count; + unsigned int outputs; struct rcar_du_group *group; diff --git a/drivers/media/platform/soc_camera/soc_scale_crop.c b/drivers/media/platform/soc_camera/soc_scale_crop.c index f77252d6ccd3..d29c24854c2c 100644 --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -418,3 +418,7 @@ void soc_camera_calc_client_output(struct soc_camera_device *icd, mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index bdbcd2b088a0..c3c28f0960e5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3849,7 +3849,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) struct list_head *head = &mbx->cmd_q; struct qlcnic_cmd_args *cmd = NULL; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); while (!list_empty(head)) { cmd = list_entry(head->next, struct qlcnic_cmd_args, list); @@ -3860,7 +3860,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) qlcnic_83xx_notify_cmd_completion(adapter, cmd); } - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); } static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter) @@ -3896,12 +3896,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter, { struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_del(&cmd->list); mbx->num_cmds--; - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); qlcnic_83xx_notify_cmd_completion(adapter, cmd); } @@ -3966,7 +3966,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, init_completion(&cmd->completion); cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_add_tail(&cmd->list, &mbx->cmd_q); mbx->num_cmds++; @@ -3974,7 +3974,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, *timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT; queue_work(mbx->work_q, &mbx->work); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return 0; } @@ -4070,15 +4070,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; spin_unlock_irqrestore(&mbx->aen_lock, flags); - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); if (list_empty(head)) { - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return; } cmd = list_entry(head->next, struct qlcnic_cmd_args, list); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); mbx_ops->encode_cmd(adapter, cmd); mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 298b74ebc1e9..18e68c91e651 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1387,7 +1387,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond) { void __iomem *ioaddr = tp->mmio_addr; - return RTL_R8(IBISR0) & 0x02; + return RTL_R8(IBISR0) & 0x20; } static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) @@ -1395,7 +1395,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) void __iomem *ioaddr = tp->mmio_addr; RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); - rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000); + rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index db65d9ad4488..e1e5e8438457 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -944,6 +944,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index 6e5d9095b195..a635fc6b1722 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -71,8 +71,18 @@ MODULE_FIRMWARE("b43/ucode11.fw"); MODULE_FIRMWARE("b43/ucode13.fw"); MODULE_FIRMWARE("b43/ucode14.fw"); MODULE_FIRMWARE("b43/ucode15.fw"); +MODULE_FIRMWARE("b43/ucode16_lp.fw"); MODULE_FIRMWARE("b43/ucode16_mimo.fw"); +MODULE_FIRMWARE("b43/ucode24_lcn.fw"); +MODULE_FIRMWARE("b43/ucode25_lcn.fw"); +MODULE_FIRMWARE("b43/ucode25_mimo.fw"); +MODULE_FIRMWARE("b43/ucode26_mimo.fw"); +MODULE_FIRMWARE("b43/ucode29_mimo.fw"); +MODULE_FIRMWARE("b43/ucode33_lcn40.fw"); +MODULE_FIRMWARE("b43/ucode30_mimo.fw"); MODULE_FIRMWARE("b43/ucode5.fw"); +MODULE_FIRMWARE("b43/ucode40.fw"); +MODULE_FIRMWARE("b43/ucode42.fw"); MODULE_FIRMWARE("b43/ucode9.fw"); static int modparam_bad_frames_preempt; diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c index 866aa3ce1ac9..6cf0006d4c8d 100644 --- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c +++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c @@ -436,3 +436,7 @@ int pxa2xx_pinctrl_exit(struct platform_device *pdev) return 0; } EXPORT_SYMBOL_GPL(pxa2xx_pinctrl_exit); + +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik(a)free.fr>"); +MODULE_DESCRIPTION("Marvell PXA2xx pinctrl driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index f2303f390345..23973a8124fc 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -965,6 +965,8 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, } } else { retval = uart_startup(tty, state, 1); + if (retval == 0) + tty_port_set_initialized(port, true); if (retval > 0) retval = 0; } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 96a0661011fd..e5b7652234fc 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1078,6 +1078,7 @@ static long vhost_net_reset_owner(struct vhost_net *n) } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); vhost_net_vq_reset(n); done: diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 6e84b2cae6ad..442b54a14cbc 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -9,6 +9,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> @@ -81,8 +82,10 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - if (fd < fdt->max_fds) + if (fd < fdt->max_fds) { + fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); + } return NULL; } diff --git a/include/linux/init.h b/include/linux/init.h index e30104ceb86d..8e346d1bd837 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -4,6 +4,13 @@ #include <linux/compiler.h> #include <linux/types.h> +/* Built-in __init functions needn't be compiled with retpoline */ +#if defined(RETPOLINE) && !defined(MODULE) +#define __noretpoline __attribute__((indirect_branch("keep"))) +#else +#define __noretpoline +#endif + /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -39,7 +46,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold notrace __latent_entropy +#define __init __section(.init.text) __cold notrace __latent_entropy __noretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/module.h b/include/linux/module.h index 0c3207d26ac0..d2224a09b4b5 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -791,6 +791,15 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef RETPOLINE +extern bool retpoline_module_ok(bool has_retpoline); +#else +static inline bool retpoline_module_ok(bool has_retpoline) +{ + return true; +} +#endif + #ifdef CONFIG_MODULE_SIG static inline bool module_sig_ok(struct module *module) { diff --git a/include/linux/nospec.h b/include/linux/nospec.h new file mode 100644 index 000000000000..b99bced39ac2 --- /dev/null +++ b/include/linux/nospec.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Linus Torvalds. All rights reserved. +// Copyright(c) 2018 Alexei Starovoitov. All rights reserved. +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#ifndef _LINUX_NOSPEC_H +#define _LINUX_NOSPEC_H + +/** + * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * When @index is out of bounds (@index >= @size), the sign bit will be + * set. Extend the sign bit to all bits and invert, giving a result of + * zero for an out of bounds index, or ~0 if within bounds [0, @size). + */ +#ifndef array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) + return 0; + + /* + * Always calculate and emit the mask even if the compiler + * thinks the mask is not needed. The compiler does not take + * into account the value of @index under speculation. + */ + OPTIMIZER_HIDE_VAR(index); + return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); +} +#endif + +/* + * array_index_nospec - sanitize an array index after a bounds check + * + * For a code sequence like: + * + * if (index < size) { + * index = array_index_nospec(index, size); + * val = array[index]; + * } + * + * ...if the CPU speculates past the bounds check then + * array_index_nospec() will clamp the index within the range of [0, + * size). + */ +#define array_index_nospec(index, size) \ +({ \ + typeof(index) _i = (index); \ + typeof(size) _s = (size); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ + \ + BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ + BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ + \ + _i &= _mask; \ + _i; \ +}) +#endif /* _LINUX_NOSPEC_H */ diff --git a/kernel/module.c b/kernel/module.c index 0e54d5bf0097..07bfb9971f2f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2817,6 +2817,15 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info) } #endif /* CONFIG_LIVEPATCH */ +static void check_modinfo_retpoline(struct module *mod, struct load_info *info) +{ + if (retpoline_module_ok(get_modinfo(info, "retpoline"))) + return; + + pr_warn("%s: loading module not compiled with retpoline compiler.\n", + mod->name); +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -2969,6 +2978,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); } + check_modinfo_retpoline(mod, info); + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); pr_warn("%s: module is from the staging directory, the quality " diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 77f396b679ce..5dce4291f0ed 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -93,6 +93,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) return more_reuse; } +static void reuseport_free_rcu(struct rcu_head *head) +{ + struct sock_reuseport *reuse; + + reuse = container_of(head, struct sock_reuseport, rcu); + if (reuse->prog) + bpf_prog_destroy(reuse->prog); + kfree(reuse); +} + /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. @@ -101,7 +111,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) */ int reuseport_add_sock(struct sock *sk, struct sock *sk2) { - struct sock_reuseport *reuse; + struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2); @@ -112,10 +122,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - "socket already in reuseport group"); + lockdep_is_held(&reuseport_lock)); + old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_socks != 1) { + spin_unlock_bh(&reuseport_lock); + return -EBUSY; + } if (reuse->num_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); @@ -133,19 +146,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_unlock_bh(&reuseport_lock); + if (old_reuse) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } -static void reuseport_free_rcu(struct rcu_head *head) -{ - struct sock_reuseport *reuse; - - reuse = container_of(head, struct sock_reuseport, rcu); - if (reuse->prog) - bpf_prog_destroy(reuse->prog); - kfree(reuse); -} - void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 9c7a4cea1628..7f5fe07d0b13 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; + + rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); + rcu_read_unlock(); + pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7efa6b062049..0d1a767db1bb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2316,6 +2316,12 @@ int tcp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index e86a34fd5484..8ec60532be2b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -452,7 +452,8 @@ static void bbr_advance_cycle_phase(struct sock *sk) bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; - bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; + bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT : + bbr_pacing_gain[bbr->cycle_idx]; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ @@ -461,8 +462,7 @@ static void bbr_update_cycle_phase(struct sock *sk, { struct bbr *bbr = inet_csk_ca(sk); - if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && - bbr_is_next_cycle_phase(sk, rs)) + if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs)) bbr_advance_cycle_phase(sk); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5cad76f87536..421379014995 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -274,6 +274,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; + bool saved_ipv6only; int addr_type = 0; int err = 0; @@ -378,19 +379,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; + saved_ipv6only = sk->sk_ipv6only; + if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED) + sk->sk_ipv6only = 1; + /* Make sure we are allowed to bind here. */ if ((snum || !inet->bind_address_no_port) && sk->sk_prot->get_port(sk, snum)) { + sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); err = -EADDRINUSE; goto out; } - if (addr_type != IPV6_ADDR_ANY) { + if (addr_type != IPV6_ADDR_ANY) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; - if (addr_type != IPV6_ADDR_MAPPED) - sk->sk_ipv6only = 1; - } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 117405dd07a3..a30e7e925c9b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -495,6 +495,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(-ENOENT); it->mrt = mrt; + it->cache = NULL; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ae83c3aec308..da574a16e7b3 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -496,6 +496,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags) { + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_u32_offload u32_offload = {0}; struct tc_to_netdev offload; @@ -520,7 +521,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, offload.cls_u32->knode.sel = &n->sel; offload.cls_u32->knode.exts = &n->exts; if (n->ht_down) - offload.cls_u32->knode.link_handle = n->ht_down->handle; + offload.cls_u32->knode.link_handle = ht->handle; err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &offload); @@ -788,8 +789,9 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, struct tc_u_knode *n) { - struct tc_u_knode *new; + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tc_u32_sel *s = &n->sel; + struct tc_u_knode *new; new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); @@ -807,11 +809,11 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, new->fshift = n->fshift; new->res = n->res; new->flags = n->flags; - RCU_INIT_POINTER(new->ht_down, n->ht_down); + RCU_INIT_POINTER(new->ht_down, ht); /* bump reference count as long as we hold pointer to structure */ - if (new->ht_down) - new->ht_down->refcnt++; + if (ht) + ht->refcnt++; #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c626f679e1c8..91722e97cdd5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16,6 +16,7 @@ #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/genetlink.h> @@ -2014,20 +2015,22 @@ static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { + u8 ac; + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); + ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); - if (txq_params->ac >= NL80211_NUM_ACS) + if (ac >= NL80211_NUM_ACS) return -EINVAL; - + txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS); return 0; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 845eb9b800f3..238db4ffd30c 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2130,6 +2130,14 @@ static void add_intree_flag(struct buffer *b, int is_intree) buf_printf(b, "\nMODULE_INFO(intree, \"Y\");\n"); } +/* Cannot check for assembler */ +static void add_retpoline(struct buffer *b) +{ + buf_printf(b, "\n#ifdef RETPOLINE\n"); + buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n"); + buf_printf(b, "#endif\n"); +} + static void add_staging_flag(struct buffer *b, const char *name) { static const char *staging_dir = "drivers/staging"; @@ -2474,6 +2482,7 @@ int main(int argc, char **argv) add_header(&buf, mod); add_intree_flag(&buf, !external_module); + add_retpoline(&buf); add_staging_flag(&buf, mod->name); err |= add_versions(&buf, mod); add_depends(&buf, mod, modules); diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index a871159bf03c..ead2fd60244d 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -141,23 +141,22 @@ static int valid_ecryptfs_desc(const char *ecryptfs_desc) */ static int valid_master_desc(const char *new_desc, const char *orig_desc) { - if (!memcmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_TRUSTED_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_TRUSTED_PREFIX_LEN)) - goto out; - } else if (!memcmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_USER_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_USER_PREFIX_LEN)) - goto out; - } else - goto out; + int prefix_len; + + if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) + prefix_len = KEY_TRUSTED_PREFIX_LEN; + else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) + prefix_len = KEY_USER_PREFIX_LEN; + else + return -EINVAL; + + if (!new_desc[prefix_len]) + return -EINVAL; + + if (orig_desc && strncmp(new_desc, orig_desc, prefix_len)) + return -EINVAL; + return 0; -out: - return -EINVAL; } /* diff --git a/sound/soc/codecs/pcm512x-spi.c b/sound/soc/codecs/pcm512x-spi.c index 712ed6598c48..ebdf9bd5a64c 100644 --- a/sound/soc/codecs/pcm512x-spi.c +++ b/sound/soc/codecs/pcm512x-spi.c @@ -70,3 +70,7 @@ static struct spi_driver pcm512x_spi_driver = { }; module_spi_driver(pcm512x_spi_driver); + +MODULE_DESCRIPTION("ASoC PCM512x codec driver - SPI"); +MODULE_AUTHOR("Mark Brown <broonie(a)kernel.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index f608f8d23f3d..dd88c2cb6470 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -232,13 +232,19 @@ static int asoc_simple_card_dai_link_of(struct device_node *node, snprintf(prop, sizeof(prop), "%scpu", prefix); cpu = of_get_child_by_name(node, prop); + if (!cpu) { + ret = -EINVAL; + dev_err(dev, "%s: Can't find %s DT node\n", __func__, prop); + goto dai_link_of_err; + } + snprintf(prop, sizeof(prop), "%splat", prefix); plat = of_get_child_by_name(node, prop); snprintf(prop, sizeof(prop), "%scodec", prefix); codec = of_get_child_by_name(node, prop); - if (!cpu || !codec) { + if (!codec) { ret = -EINVAL; dev_err(dev, "%s: Can't find %s DT node\n", __func__, prop); goto dai_link_of_err; diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 560cf4b51a99..a9a43acce30e 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -699,9 +699,14 @@ static int rsnd_ssi_dma_remove(struct rsnd_mod *mod, struct rsnd_priv *priv) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); + struct rsnd_mod *pure_ssi_mod = rsnd_io_to_mod_ssi(io); struct device *dev = rsnd_priv_to_dev(priv); int irq = ssi->irq; + /* Do nothing if non SSI (= SSI parent, multi SSI) mod */ + if (pure_ssi_mod != mod) + return 0; + /* PIO will request IRQ again */ devm_free_irq(dev, irq, mod);

7 years, 4 months

1
0
0 0

Patch "watchdog: indydog: Add dependency on SGI_HAS_INDYDOG" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled watchdog: indydog: Add dependency on SGI_HAS_INDYDOG to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: watchdog-indydog-add-dependency-on-sgi_has_indydog.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 24f8d233074badd4c18e4dafd2fb97d65838afed Mon Sep 17 00:00:00 2001 From: Matt Redfearn <matt.redfearn(a)mips.com> Date: Tue, 14 Nov 2017 10:52:54 +0000 Subject: watchdog: indydog: Add dependency on SGI_HAS_INDYDOG From: Matt Redfearn <matt.redfearn(a)mips.com> commit 24f8d233074badd4c18e4dafd2fb97d65838afed upstream. Commit da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") enabled building the Indy watchdog driver when COMPILE_TEST is enabled. However, the driver makes reference to symbols that are only defined for certain platforms are selected in the config. These platforms select SGI_HAS_INDYDOG. Without this, link time errors result, for example when building a MIPS allyesconfig. drivers/watchdog/indydog.o: In function `indydog_write': indydog.c:(.text+0x18): undefined reference to `sgimc' indydog.c:(.text+0x1c): undefined reference to `sgimc' drivers/watchdog/indydog.o: In function `indydog_start': indydog.c:(.text+0x54): undefined reference to `sgimc' indydog.c:(.text+0x58): undefined reference to `sgimc' drivers/watchdog/indydog.o: In function `indydog_stop': indydog.c:(.text+0xa4): undefined reference to `sgimc' drivers/watchdog/indydog.o:indydog.c:(.text+0xa8): more undefined references to `sgimc' follow make: *** [Makefile:1005: vmlinux] Error 1 Fix this by ensuring that CONFIG_INDIDOG can only be selected when the necessary dependent platform symbols are built in. Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") Signed-off-by: Matt Redfearn <matt.redfearn(a)mips.com> Signed-off-by: Ralf Baechle <ralf(a)linux-mips.org> Suggested-by: James Hogan <james.hogan(a)mips.com> Reviewed-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Wim Van Sebroeck <wim(a)iguana.be> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/watchdog/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1451,7 +1451,7 @@ config RC32434_WDT config INDYDOG tristate "Indy/I2 Hardware Watchdog" - depends on SGI_HAS_INDYDOG || (MIPS && COMPILE_TEST) + depends on SGI_HAS_INDYDOG help Hardware driver for the Indy's/I2's watchdog. This is a watchdog timer that will reboot the machine after a 60 second Patches currently in stable-queue which might be from matt.redfearn(a)mips.com are queue-4.14/watchdog-indydog-add-dependency-on-sgi_has_indydog.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH v4 2/5] x86/apic: Fix restoring boot irq mode in reboot and kexec/kdump

by Baoquan He

This is a regression fix. Before, to fix erratum AVR31, commit 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") moved lapic_shutdown() calling after disable_IO_APIC() in reboot and kexec/kdump code path. This introdued a regression. The root cause is that disable_IO_APIC() not only clears IO_APIC, also restore boot irq mode by setting LAPIC/APIC/IMCR, calling lapic_shutdown() after disable_IO_APIC() will disable LAPIC and ruin the possible virtual wire mode setting which the code has been trying to do all along. The consequence is, in KVM guest kernel always prints warning as below during kexec/kdump kernel boots up. That happened in setup_local_APIC() since 'do { xxx } while (queued && max_loops > 0)' loop does not function well any more if pending irq exists in APIC IRR after LAPIC is disabled. [ 0.001000] WARNING: CPU: 0 PID: 0 at arch/x86/kernel/apic/apic.c:1467 setup_local_APIC+0x228/0x330 [ 0.001000] Modules linked in: [ 0.001000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc5+ #3 [ 0.001000] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc26 04/01/2014 [ 0.001000] RIP: 0010:setup_local_APIC+0x228/0x330 [ 0.001000] RSP: 0000:ffffffffb6e03eb8 EFLAGS: 00010286 [ 0.001000] RAX: 0000009edb4c4d84 RBX: 0000000000000000 RCX: 00000000b099d800 [ 0.001000] RDX: 0000009e00000000 RSI: 0000000000000000 RDI: 0000000000000810 [ 0.001000] RBP: 0000000000000000 R08: ffffffffffffffff R09: 0000000000000001 [ 0.001000] R10: ffff98ce6a801c00 R11: 0761076d072f0776 R12: 0000000000000001 [ 0.001000] R13: 00000000000000f0 R14: 0000000000004000 R15: ffffffffffffc6ff [ 0.001000] FS: 0000000000000000(0000) GS:ffff98ce6bc00000(0000) knlGS:0000000000000000 [ 0.001000] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 0.001000] CR2: 00000000ffffffff CR3: 0000000022209000 CR4: 00000000000406b0 [ 0.001000] Call Trace: [ 0.001000] apic_bsp_setup+0x56/0x74 [ 0.001000] x86_late_time_init+0x11/0x16 [ 0.001000] start_kernel+0x3c9/0x486 [ 0.001000] secondary_startup_64+0xa5/0xb0 [ 0.001000] Code: 00 85 c9 74 2d 0f 31 c1 e1 0a 48 c1 e2 20 41 89 cf 4c 03 7c 24 08 48 09 d0 49 29 c7 4c 89 3c 24 48 83 3c 24 00 0f 8f 8f fe ff ff <0f> ff e9 10 ff ff ff 48 83 2c 24 01 eb e7 48 83 c4 18 5b 5d 41 [ 0.001000] ---[ end trace b88e71b9a6ebebdd ]--- [ 0.001000] masked ExtINT on CPU#0 To fix this, just break down disable_IO_APIC(), then call clear_IO_APIC() to stop IO_APIC where disable_IO_APIC() was called, and call restore_boot_irq_mode() to restore boot irq mode before reboot or kexec/kdump jump. As for KEXEC_JUMP, it's a little different then reboot and kexec/kdump. It doesn't call lapic_shutdown() before jump, so is not impacted by commit 522e66464467. Here in order to keep it the same as the old code, replace the old disable_IO_APIC() with clear_IO_APIC() and restore_boot_irq_mode(). Signed-off-by: Baoquan He <bhe(a)redhat.com> Fixes: commit 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") Cc: stable(a)vger.kernel.org --- v4->v3: Eric pointed out the change related to KEXEC_JUMP is not right. Correct it. Add Fixes tag and Cc to stable. arch/x86/include/asm/io_apic.h | 1 + arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/crash.c | 3 ++- arch/x86/kernel/machine_kexec_32.c | 3 ++- arch/x86/kernel/machine_kexec_64.c | 3 ++- arch/x86/kernel/reboot.c | 3 ++- 6 files changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 558d1a6a13ad..0fa95bfacb39 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -193,6 +193,7 @@ static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) extern void setup_IO_APIC(void); extern void enable_IO_APIC(void); extern void disable_IO_APIC(void); +extern void clear_IO_APIC(void); extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7b73b6b9b4b6..2d7cd2db77f5 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -587,7 +587,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) mpc_ioapic_id(apic), pin); } -static void clear_IO_APIC (void) +void clear_IO_APIC (void) { int apic, pin; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 10e74d4778a1..1f6680427ff0 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -199,9 +199,10 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); - disable_IO_APIC(); + clear_IO_APIC(); #endif lapic_shutdown(); + restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index edfede768688..4cd79d88a4ac 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -199,7 +199,8 @@ void machine_kexec(struct kimage *image) * one form or other. kexec jump path also need * one. */ - disable_IO_APIC(); + clear_IO_APIC(); + restore_boot_irq_mode(); #endif } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1f790cf9d38f..2ab14b9c1a89 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -297,7 +297,8 @@ void machine_kexec(struct kimage *image) * one form or other. kexec jump path also need * one. */ - disable_IO_APIC(); + clear_IO_APIC(); + restore_boot_irq_mode(); #endif } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2126b9d27c34..725624b6c0c0 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -666,7 +666,7 @@ void native_machine_shutdown(void) * Even without the erratum, it still makes sense to quiet IO APIC * before disabling Local APIC. */ - disable_IO_APIC(); + clear_IO_APIC(); #endif #ifdef CONFIG_SMP @@ -680,6 +680,7 @@ void native_machine_shutdown(void) #endif lapic_shutdown(); + restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); -- 2.13.6

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH] mpt3sas: Do not use 32-bit atomic request descriptor for Ventura controllers

by Shivasharan S

From: Suganath Prabu S <suganath-prabu.subramani(a)broadcom.com> Problem Statement: Sending I/O through 32 bit descriptors to Ventura series of controller results in IO timeout on certain conditions. This error only occurs on systems with high I/O activity on Ventura series controllers. Changes in this patch will prevent driver from using 32 bit descriptor and use 64 bit Descriptors. Cc: <stable(a)vger.kernel.org> Signed-off-by: Suganath Prabu S <suganath-prabu.subramani(a)broadcom.com> Signed-off-by: Shivasharan S <shivasharan.srikanteshwara(a)broadcom.com> --- drivers/scsi/mpt3sas/mpt3sas_base.c | 121 ------------------------------------ drivers/scsi/mpt3sas/mpt3sas_base.h | 1 - 2 files changed, 122 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 13d6e4e..6051469 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3108,116 +3108,6 @@ _base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid) } /** -* _base_put_smid_scsi_io_atomic - send SCSI_IO request to firmware using -* Atomic Request Descriptor -* @ioc: per adapter object -* @smid: system request message index -* @handle: device handle, unused in this function, for function type match -* -* Return nothing. -*/ -static void -_base_put_smid_scsi_io_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid, - u16 handle) -{ - Mpi26AtomicRequestDescriptor_t descriptor; - u32 *request = (u32 *)&descriptor; - - descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO; - descriptor.MSIxIndex = _base_get_msix_index(ioc); - descriptor.SMID = cpu_to_le16(smid); - - writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost); -} - -/** - * _base_put_smid_fast_path_atomic - send fast path request to firmware - * using Atomic Request Descriptor - * @ioc: per adapter object - * @smid: system request message index - * @handle: device handle, unused in this function, for function type match - * Return nothing - */ -static void -_base_put_smid_fast_path_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid, - u16 handle) -{ - Mpi26AtomicRequestDescriptor_t descriptor; - u32 *request = (u32 *)&descriptor; - - descriptor.RequestFlags = MPI25_REQ_DESCRIPT_FLAGS_FAST_PATH_SCSI_IO; - descriptor.MSIxIndex = _base_get_msix_index(ioc); - descriptor.SMID = cpu_to_le16(smid); - - writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost); -} - -/** - * _base_put_smid_hi_priority_atomic - send Task Management request to - * firmware using Atomic Request Descriptor - * @ioc: per adapter object - * @smid: system request message index - * @msix_task: msix_task will be same as msix of IO incase of task abort else 0 - * - * Return nothing. - */ -static void -_base_put_smid_hi_priority_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid, - u16 msix_task) -{ - Mpi26AtomicRequestDescriptor_t descriptor; - u32 *request = (u32 *)&descriptor; - - descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY; - descriptor.MSIxIndex = msix_task; - descriptor.SMID = cpu_to_le16(smid); - - writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost); -} - -/** - * _base_put_smid_nvme_encap_atomic - send NVMe encapsulated request to - * firmware using Atomic Request Descriptor - * @ioc: per adapter object - * @smid: system request message index - * - * Return nothing. - */ -static void -_base_put_smid_nvme_encap_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid) -{ - Mpi26AtomicRequestDescriptor_t descriptor; - u32 *request = (u32 *)&descriptor; - - descriptor.RequestFlags = MPI26_REQ_DESCRIPT_FLAGS_PCIE_ENCAPSULATED; - descriptor.MSIxIndex = _base_get_msix_index(ioc); - descriptor.SMID = cpu_to_le16(smid); - - writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost); -} - -/** - * _base_put_smid_default - Default, primarily used for config pages - * use Atomic Request Descriptor - * @ioc: per adapter object - * @smid: system request message index - * - * Return nothing. - */ -static void -_base_put_smid_default_atomic(struct MPT3SAS_ADAPTER *ioc, u16 smid) -{ - Mpi26AtomicRequestDescriptor_t descriptor; - u32 *request = (u32 *)&descriptor; - - descriptor.RequestFlags = MPI2_REQ_DESCRIPT_FLAGS_DEFAULT_TYPE; - descriptor.MSIxIndex = _base_get_msix_index(ioc); - descriptor.SMID = cpu_to_le16(smid); - - writel(cpu_to_le32(*request), &ioc->chip->AtomicRequestDescriptorPost); -} - -/** * _base_display_OEMs_branding - Display branding string * @ioc: per adapter object * @@ -5071,8 +4961,6 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc) if ((facts->IOCCapabilities & MPI2_IOCFACTS_CAPABILITY_RDPQ_ARRAY_CAPABLE) && (!reset_devices)) ioc->rdpq_array_capable = 1; - if (facts->IOCCapabilities & MPI26_IOCFACTS_CAPABILITY_ATOMIC_REQ) - ioc->atomic_desc_capable = 1; facts->FWVersion.Word = le32_to_cpu(mpi_reply.FWVersion.Word); facts->IOCRequestFrameSize = le16_to_cpu(mpi_reply.IOCRequestFrameSize); @@ -6006,20 +5894,11 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) break; } - if (ioc->atomic_desc_capable) { - ioc->put_smid_default = &_base_put_smid_default_atomic; - ioc->put_smid_scsi_io = &_base_put_smid_scsi_io_atomic; - ioc->put_smid_fast_path = &_base_put_smid_fast_path_atomic; - ioc->put_smid_hi_priority = &_base_put_smid_hi_priority_atomic; - ioc->put_smid_nvme_encap = &_base_put_smid_nvme_encap_atomic; - } else { ioc->put_smid_default = &_base_put_smid_default; ioc->put_smid_scsi_io = &_base_put_smid_scsi_io; ioc->put_smid_fast_path = &_base_put_smid_fast_path; ioc->put_smid_hi_priority = &_base_put_smid_hi_priority; ioc->put_smid_nvme_encap = &_base_put_smid_nvme_encap; - } - /* * These function pointers for other requests that don't diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 789bc42..3324392 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1348,7 +1348,6 @@ struct MPT3SAS_ADAPTER { void *device_remove_in_progress; u16 device_remove_in_progress_sz; u8 is_gen35_ioc; - u8 atomic_desc_capable; PUT_SMID_IO_FP_HIP put_smid_scsi_io; PUT_SMID_IO_FP_HIP put_smid_fast_path; PUT_SMID_IO_FP_HIP put_smid_hi_priority; -- 2.5.5

7 years, 4 months

2
1
0 0

Re: [Linux-stable-mirror] Linux 4.15.3

by Greg KH

diff --git a/Makefile b/Makefile index 54f1bc10b531..13566ad7863a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 15 -SUBLEVEL = 2 +SUBLEVEL = 3 EXTRAVERSION = NAME = Fearless Coyote diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 9267cbdb14d2..3ced1ba1fd11 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -198,11 +198,13 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE], } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index 016d7427ebfa..761d8279abca 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -505,4 +505,4 @@ module_platform_driver(uniphier_gpio_driver); MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro(a)socionext.com>"); MODULE_DESCRIPTION("UniPhier GPIO driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c index 46768c056193..0c28d0b995cc 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c @@ -115,3 +115,6 @@ struct mtk_vcodec_ctx *mtk_vcodec_get_curr_ctx(struct mtk_vcodec_dev *dev) return ctx; } EXPORT_SYMBOL(mtk_vcodec_get_curr_ctx); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Mediatek video codec driver"); diff --git a/drivers/media/platform/soc_camera/soc_scale_crop.c b/drivers/media/platform/soc_camera/soc_scale_crop.c index 270ec613c27c..6164102e6f9f 100644 --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -420,3 +420,7 @@ void soc_camera_calc_client_output(struct soc_camera_device *icd, mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/media/platform/tegra-cec/tegra_cec.c b/drivers/media/platform/tegra-cec/tegra_cec.c index 807c94c70049..92f93a880015 100644 --- a/drivers/media/platform/tegra-cec/tegra_cec.c +++ b/drivers/media/platform/tegra-cec/tegra_cec.c @@ -493,3 +493,8 @@ static struct platform_driver tegra_cec_driver = { }; module_platform_driver(tegra_cec_driver); + +MODULE_DESCRIPTION("Tegra HDMI CEC driver"); +MODULE_AUTHOR("NVIDIA CORPORATION"); +MODULE_AUTHOR("Cisco Systems, Inc. and/or its affiliates"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index f7080d0ab874..46b0372dd032 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3891,7 +3891,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) struct list_head *head = &mbx->cmd_q; struct qlcnic_cmd_args *cmd = NULL; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); while (!list_empty(head)) { cmd = list_entry(head->next, struct qlcnic_cmd_args, list); @@ -3902,7 +3902,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) qlcnic_83xx_notify_cmd_completion(adapter, cmd); } - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); } static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter) @@ -3938,12 +3938,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter, { struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_del(&cmd->list); mbx->num_cmds--; - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); qlcnic_83xx_notify_cmd_completion(adapter, cmd); } @@ -4008,7 +4008,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, init_completion(&cmd->completion); cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_add_tail(&cmd->list, &mbx->cmd_q); mbx->num_cmds++; @@ -4016,7 +4016,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, *timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT; queue_work(mbx->work_q, &mbx->work); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return 0; } @@ -4112,15 +4112,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; spin_unlock_irqrestore(&mbx->aen_lock, flags); - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); if (list_empty(head)) { - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return; } cmd = list_entry(head->next, struct qlcnic_cmd_args, list); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); mbx_ops->encode_cmd(adapter, cmd); mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 734286ebe5ef..dd713dff8d22 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1395,7 +1395,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond) { void __iomem *ioaddr = tp->mmio_addr; - return RTL_R8(IBISR0) & 0x02; + return RTL_R8(IBISR0) & 0x20; } static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) @@ -1403,7 +1403,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) void __iomem *ioaddr = tp->mmio_addr; RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); - rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000); + rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); } diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index fc8f8bdf6579..056cb6093630 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2902,6 +2902,12 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_alloc_ordered_workqueue; } + err = rocker_probe_ports(rocker); + if (err) { + dev_err(&pdev->dev, "failed to probe ports\n"); + goto err_probe_ports; + } + /* Only FIBs pointing to our own netdevs are programmed into * the device, so no need to pass a callback. */ @@ -2918,22 +2924,16 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) rocker->hw.id = rocker_read64(rocker, SWITCH_ID); - err = rocker_probe_ports(rocker); - if (err) { - dev_err(&pdev->dev, "failed to probe ports\n"); - goto err_probe_ports; - } - dev_info(&pdev->dev, "Rocker switch with id %*phN\n", (int)sizeof(rocker->hw.id), &rocker->hw.id); return 0; -err_probe_ports: - unregister_switchdev_notifier(&rocker_switchdev_notifier); err_register_switchdev_notifier: unregister_fib_notifier(&rocker->fib_nb); err_register_fib_notifier: + rocker_remove_ports(rocker); +err_probe_ports: destroy_workqueue(rocker->rocker_owq); err_alloc_ordered_workqueue: free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker); @@ -2961,9 +2961,9 @@ static void rocker_remove(struct pci_dev *pdev) { struct rocker *rocker = pci_get_drvdata(pdev); - rocker_remove_ports(rocker); unregister_switchdev_notifier(&rocker_switchdev_notifier); unregister_fib_notifier(&rocker->fib_nb); + rocker_remove_ports(rocker); rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET); destroy_workqueue(rocker->rocker_owq); free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 728819feab44..e7114c34fe4b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1245,6 +1245,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index c7bdeb655646..5636c7ca8eba 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1208,6 +1208,7 @@ static long vhost_net_reset_owner(struct vhost_net *n) } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); vhost_net_vq_reset(n); done: diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index becf86aa4ac6..d6ec5a5a6782 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -280,7 +280,6 @@ struct tcf_block { struct net *net; struct Qdisc *q; struct list_head cb_list; - struct work_struct work; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac2ffd5e02b9..0a78ce57872d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5828,6 +5828,20 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; + /* + * Socket cloning can throw us here with sk_memcg already + * filled. It won't however, necessarily happen from + * process context. So the test for root memcg given + * the current task's memcg won't help us in this case. + * + * Respecting the original socket's memcg is a better + * decision in this case. + */ + if (sk->sk_memcg) { + css_get(&sk->sk_memcg->css); + return; + } + rcu_read_lock(); memcg = mem_cgroup_from_task(current); if (memcg == root_mem_cgroup) diff --git a/net/core/sock.c b/net/core/sock.c index c0b5b2f17412..7571dabfc4cf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1675,16 +1675,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; - - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; - atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); + mem_cgroup_sk_alloc(newsk); cgroup_sk_alloc(&newsk->sk_cgrp_data); rcu_read_lock(); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5eeb1d20cc38..676092d7bd81 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -94,6 +94,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) return more_reuse; } +static void reuseport_free_rcu(struct rcu_head *head) +{ + struct sock_reuseport *reuse; + + reuse = container_of(head, struct sock_reuseport, rcu); + if (reuse->prog) + bpf_prog_destroy(reuse->prog); + kfree(reuse); +} + /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. @@ -102,7 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) */ int reuseport_add_sock(struct sock *sk, struct sock *sk2) { - struct sock_reuseport *reuse; + struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2); @@ -113,10 +123,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - "socket already in reuseport group"); + lockdep_is_held(&reuseport_lock)); + old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_socks != 1) { + spin_unlock_bh(&reuseport_lock); + return -EBUSY; + } if (reuse->num_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); @@ -134,19 +147,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_unlock_bh(&reuseport_lock); + if (old_reuse) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } -static void reuseport_free_rcu(struct rcu_head *head) -{ - struct sock_reuseport *reuse; - - reuse = container_of(head, struct sock_reuseport, rcu); - if (reuse->prog) - bpf_prog_destroy(reuse->prog); - kfree(reuse); -} - void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2d49717a7421..f0b1fc35dde1 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; + + rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); + rcu_read_unlock(); + pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4ca46dc08e63..3668c4182655 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -475,7 +475,6 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } - mem_cgroup_sk_alloc(newsk); out: release_sock(sk); if (req) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8e053ad7cae2..c821f5d68720 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2434,6 +2434,12 @@ int tcp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 8322f26e770e..25c5a0b60cfc 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -481,7 +481,8 @@ static void bbr_advance_cycle_phase(struct sock *sk) bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; - bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; + bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT : + bbr_pacing_gain[bbr->cycle_idx]; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ @@ -490,8 +491,7 @@ static void bbr_update_cycle_phase(struct sock *sk, { struct bbr *bbr = inet_csk_ca(sk); - if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && - bbr_is_next_cycle_phase(sk, rs)) + if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs)) bbr_advance_cycle_phase(sk); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f49bd7897e95..2547222589fe 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -186,7 +186,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); -static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id); +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, + bool send_na); static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(struct timer_list *t); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); @@ -3833,12 +3834,17 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { + bool send_na = false; + + if (ifp->flags & IFA_F_TENTATIVE && + !(ifp->flags & IFA_F_OPTIMISTIC)) + send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp, bump_id); + addrconf_dad_completed(ifp, bump_id, send_na); return; } @@ -3967,16 +3973,21 @@ static void addrconf_dad_work(struct work_struct *w) } if (ifp->dad_probes == 0) { + bool send_na = false; + /* * DAD was successful */ + if (ifp->flags & IFA_F_TENTATIVE && + !(ifp->flags & IFA_F_OPTIMISTIC)) + send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp, bump_id); + addrconf_dad_completed(ifp, bump_id, send_na); goto out; } @@ -4014,7 +4025,8 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) return true; } -static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, + bool send_na) { struct net_device *dev = ifp->idev->dev; struct in6_addr lladdr; @@ -4046,6 +4058,16 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) if (send_mld) ipv6_mc_dad_complete(ifp->idev); + /* send unsolicited NA if enabled */ + if (send_na && + (ifp->idev->cnf.ndisc_notify || + dev_net(dev)->ipv6.devconf_all->ndisc_notify)) { + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, + /*router=*/ !!ifp->idev->cnf.forwarding, + /*solicited=*/ false, /*override=*/ true, + /*inc_opt=*/ true); + } + if (send_rs) { /* * If a host as already performed a random delay @@ -4352,9 +4374,11 @@ static void addrconf_verify_rtnl(void) spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); + rcu_read_unlock_bh(); ipv6_create_tempaddr(ifpub, ifp, true); in6_ifa_put(ifpub); in6_ifa_put(ifp); + rcu_read_lock_bh(); goto restart; } } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c9441ca45399..416917719a6f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -284,6 +284,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; + bool saved_ipv6only; int addr_type = 0; int err = 0; @@ -389,19 +390,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; + saved_ipv6only = sk->sk_ipv6only; + if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED) + sk->sk_ipv6only = 1; + /* Make sure we are allowed to bind here. */ if ((snum || !inet->bind_address_no_port) && sk->sk_prot->get_port(sk, snum)) { + sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); err = -EADDRINUSE; goto out; } - if (addr_type != IPV6_ADDR_ANY) { + if (addr_type != IPV6_ADDR_ANY) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; - if (addr_type != IPV6_ADDR_MAPPED) - sk->sk_ipv6only = 1; - } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a2e1a864eb46..4fc566ec7e79 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -495,6 +495,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(-ENOENT); it->mrt = mrt; + it->cache = NULL; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b3cea200c85e..f61a5b613b52 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -566,6 +566,11 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { + /* skip tentative addresses until dad completes */ + if (ifa->flags & IFA_F_TENTATIVE && + !(ifa->flags & IFA_F_OPTIMISTIC)) + continue; + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0458b761f3c5..a560fb1d0230 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1586,12 +1586,19 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ - if (!(rt->rt6i_flags & RTF_EXPIRES) && - time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { - RT6_TRACE("aging clone %p\n", rt); + if (!(rt->rt6i_flags & RTF_EXPIRES)) { + if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + RT6_TRACE("aging clone %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + } else if (time_after(jiffies, rt->dst.expires)) { + RT6_TRACE("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; - } else if (rt->rt6i_flags & RTF_GATEWAY) { + } + + if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; __u8 neigh_flags = 0; @@ -1606,11 +1613,8 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, rt6_remove_exception(bucket, rt6_ex); return; } - } else if (__rt6_check_expired(rt)) { - RT6_TRACE("purging expired route %p\n", rt); - rt6_remove_exception(bucket, rt6_ex); - return; } + gc_args->more++; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b9d63d2246e6..e6b853f0ee4f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -217,8 +217,12 @@ static void tcf_chain_flush(struct tcf_chain *chain) static void tcf_chain_destroy(struct tcf_chain *chain) { + struct tcf_block *block = chain->block; + list_del(&chain->list); kfree(chain); + if (list_empty(&block->chain_list)) + kfree(block); } static void tcf_chain_hold(struct tcf_chain *chain) @@ -329,49 +333,34 @@ int tcf_block_get(struct tcf_block **p_block, } EXPORT_SYMBOL(tcf_block_get); -static void tcf_block_put_final(struct work_struct *work) -{ - struct tcf_block *block = container_of(work, struct tcf_block, work); - struct tcf_chain *chain, *tmp; - - rtnl_lock(); - - /* At this point, all the chains should have refcnt == 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_put(chain); - rtnl_unlock(); - kfree(block); -} - /* XXX: Standalone actions are not allowed to jump to any chain, and bound * actions should be all removed after flushing. */ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain; + struct tcf_chain *chain, *tmp; if (!block) return; - /* Hold a refcnt for all chains, except 0, so that they don't disappear + /* Hold a refcnt for all chains, so that they don't disappear * while we are iterating. */ list_for_each_entry(chain, &block->chain_list, list) - if (chain->index) - tcf_chain_hold(chain); + tcf_chain_hold(chain); list_for_each_entry(chain, &block->chain_list, list) tcf_chain_flush(chain); tcf_block_offload_unbind(block, q, ei); - INIT_WORK(&block->work, tcf_block_put_final); - /* Wait for existing RCU callbacks to cool down, make sure their works - * have been queued before this. We can not flush pending works here - * because we are holding the RTNL lock. - */ - rcu_barrier(); - tcf_queue_work(&block->work); + /* At this point, all the chains should have refcnt >= 1. */ + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_put(chain); + + /* Finally, put chain 0 and allow block to be freed. */ + chain = list_first_entry(&block->chain_list, struct tcf_chain, list); + tcf_chain_put(chain); } EXPORT_SYMBOL(tcf_block_put_ext); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 507859cdd1cb..33294b5b2c6a 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -544,6 +544,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags) { + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; bool skip_sw = tc_skip_sw(flags); @@ -563,7 +564,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, cls_u32.knode.sel = &n->sel; cls_u32.knode.exts = &n->exts; if (n->ht_down) - cls_u32.knode.link_handle = n->ht_down->handle; + cls_u32.knode.link_handle = ht->handle; err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); if (err < 0) { @@ -840,8 +841,9 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, struct tc_u_knode *n) { - struct tc_u_knode *new; + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); struct tc_u32_sel *s = &n->sel; + struct tc_u_knode *new; new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); @@ -859,11 +861,11 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, new->fshift = n->fshift; new->res = n->res; new->flags = n->flags; - RCU_INIT_POINTER(new->ht_down, n->ht_down); + RCU_INIT_POINTER(new->ht_down, ht); /* bump reference count as long as we hold pointer to structure */ - if (new->ht_down) - new->ht_down->refcnt++; + if (ht) + ht->refcnt++; #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] Linux 4.14.19

by Greg KH

diff --git a/.gitignore b/.gitignore index 0c39aa20b6ba..f6050b88e95b 100644 --- a/.gitignore +++ b/.gitignore @@ -7,38 +7,40 @@ # command after changing this file, to see if there are # any tracked files which get ignored after the change. # -# Normal rules +# Normal rules (sorted alphabetically) # .* +*.a +*.bin +*.bz2 +*.c.[012]*.* +*.dtb +*.dtb.S +*.dwo +*.elf +*.gcno +*.gz +*.i +*.ko +*.ll +*.lst +*.lz4 +*.lzma +*.lzo +*.mod.c *.o *.o.* -*.a +*.order +*.patch *.s -*.ko *.so *.so.dbg -*.mod.c -*.i -*.lst +*.su *.symtypes -*.order -*.elf -*.bin *.tar -*.gz -*.bz2 -*.lzma *.xz -*.lz4 -*.lzo -*.patch -*.gcno -*.ll -modules.builtin Module.symvers -*.dwo -*.su -*.c.[012]*.* +modules.builtin # # Top-level generic files @@ -53,6 +55,11 @@ Module.symvers /System.map /Module.markers +# +# RPM spec file (make rpm-pkg) +# +/*.spec + # # Debian directory (make deb-pkg) # diff --git a/Makefile b/Makefile index a69e5da9ed86..76a0b13623f4 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 18 +SUBLEVEL = 19 EXTRAVERSION = NAME = Petit Gorille diff --git a/arch/arc/boot/.gitignore b/arch/arc/boot/.gitignore index 5246969a20c5..c4c5fd529c25 100644 --- a/arch/arc/boot/.gitignore +++ b/arch/arc/boot/.gitignore @@ -1,2 +1 @@ -*.dtb* uImage diff --git a/arch/arm/boot/.gitignore b/arch/arm/boot/.gitignore index 3c79f85975aa..ce1c5ff746e7 100644 --- a/arch/arm/boot/.gitignore +++ b/arch/arm/boot/.gitignore @@ -3,4 +3,3 @@ zImage xipImage bootpImage uImage -*.dtb diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 0fcd82f01388..b8dc3b516f93 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -790,7 +790,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/arch/arm64/boot/dts/.gitignore b/arch/arm64/boot/dts/.gitignore deleted file mode 100644 index b60ed208c779..000000000000 --- a/arch/arm64/boot/dts/.gitignore +++ /dev/null @@ -1 +0,0 @@ -*.dtb diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index cb79fba79d43..b88a8dd14933 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -122,7 +122,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/arch/metag/boot/.gitignore b/arch/metag/boot/.gitignore index 2d6c0c160884..6c662ddb909a 100644 --- a/arch/metag/boot/.gitignore +++ b/arch/metag/boot/.gitignore @@ -1,4 +1,3 @@ vmlinux* uImage* ramdisk.* -*.dtb* diff --git a/arch/microblaze/boot/.gitignore b/arch/microblaze/boot/.gitignore index bf0459186027..679502d64a97 100644 --- a/arch/microblaze/boot/.gitignore +++ b/arch/microblaze/boot/.gitignore @@ -1,3 +1,2 @@ -*.dtb linux.bin* simpleImage.* diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore index d3962cd5ce0c..a73d6e2c4f64 100644 --- a/arch/mips/boot/.gitignore +++ b/arch/mips/boot/.gitignore @@ -5,4 +5,3 @@ zImage zImage.tmp calc_vmlinuz_load_addr uImage -*.dtb diff --git a/arch/nios2/boot/.gitignore b/arch/nios2/boot/.gitignore index 109279ca5a4d..64386a8dedd8 100644 --- a/arch/nios2/boot/.gitignore +++ b/arch/nios2/boot/.gitignore @@ -1,2 +1 @@ -*.dtb vmImage diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 84774ccba1c2..f92d0530ceb1 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -18,7 +18,6 @@ otheros.bld uImage cuImage.* dtbImage.* -*.dtb treeImage.* vmlinux.strip zImage diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c index 5f25b39f04d4..c4ac6043ebb0 100644 --- a/arch/unicore32/kernel/traps.c +++ b/arch/unicore32/kernel/traps.c @@ -298,7 +298,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 21be0193d9dc..b034826a0b3b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -287,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -344,7 +344,7 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins add_nops(instr + (a->instrlen - a->padlen), a->padlen); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -365,7 +365,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %px, -> %px", start, end); + DPRINTK("alt table %p -> %p", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -389,14 +389,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -422,7 +422,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } diff --git a/arch/xtensa/boot/.gitignore b/arch/xtensa/boot/.gitignore index be7655998b26..38177c7ebcab 100644 --- a/arch/xtensa/boot/.gitignore +++ b/arch/xtensa/boot/.gitignore @@ -1,3 +1,2 @@ uImage zImage.redboot -*.dtb diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index f5f58a6eee5d..e339960dcac7 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -221,11 +221,13 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE], } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c index 46768c056193..0c28d0b995cc 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c @@ -115,3 +115,6 @@ struct mtk_vcodec_ctx *mtk_vcodec_get_curr_ctx(struct mtk_vcodec_dev *dev) return ctx; } EXPORT_SYMBOL(mtk_vcodec_get_curr_ctx); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Mediatek video codec driver"); diff --git a/drivers/media/platform/soc_camera/soc_scale_crop.c b/drivers/media/platform/soc_camera/soc_scale_crop.c index 0116097c0c0f..092c73f24589 100644 --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -419,3 +419,7 @@ void soc_camera_calc_client_output(struct soc_camera_device *icd, mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index f7080d0ab874..46b0372dd032 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3891,7 +3891,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) struct list_head *head = &mbx->cmd_q; struct qlcnic_cmd_args *cmd = NULL; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); while (!list_empty(head)) { cmd = list_entry(head->next, struct qlcnic_cmd_args, list); @@ -3902,7 +3902,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) qlcnic_83xx_notify_cmd_completion(adapter, cmd); } - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); } static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter) @@ -3938,12 +3938,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter, { struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_del(&cmd->list); mbx->num_cmds--; - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); qlcnic_83xx_notify_cmd_completion(adapter, cmd); } @@ -4008,7 +4008,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, init_completion(&cmd->completion); cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_add_tail(&cmd->list, &mbx->cmd_q); mbx->num_cmds++; @@ -4016,7 +4016,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, *timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT; queue_work(mbx->work_q, &mbx->work); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return 0; } @@ -4112,15 +4112,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work) mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; spin_unlock_irqrestore(&mbx->aen_lock, flags); - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); if (list_empty(head)) { - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return; } cmd = list_entry(head->next, struct qlcnic_cmd_args, list); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); mbx_ops->encode_cmd(adapter, cmd); mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 958ff931e790..619a1b7281a0 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1388,7 +1388,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond) { void __iomem *ioaddr = tp->mmio_addr; - return RTL_R8(IBISR0) & 0x02; + return RTL_R8(IBISR0) & 0x20; } static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) @@ -1396,7 +1396,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) void __iomem *ioaddr = tp->mmio_addr; RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); - rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000); + rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); } diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index fc8f8bdf6579..056cb6093630 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2902,6 +2902,12 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_alloc_ordered_workqueue; } + err = rocker_probe_ports(rocker); + if (err) { + dev_err(&pdev->dev, "failed to probe ports\n"); + goto err_probe_ports; + } + /* Only FIBs pointing to our own netdevs are programmed into * the device, so no need to pass a callback. */ @@ -2918,22 +2924,16 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) rocker->hw.id = rocker_read64(rocker, SWITCH_ID); - err = rocker_probe_ports(rocker); - if (err) { - dev_err(&pdev->dev, "failed to probe ports\n"); - goto err_probe_ports; - } - dev_info(&pdev->dev, "Rocker switch with id %*phN\n", (int)sizeof(rocker->hw.id), &rocker->hw.id); return 0; -err_probe_ports: - unregister_switchdev_notifier(&rocker_switchdev_notifier); err_register_switchdev_notifier: unregister_fib_notifier(&rocker->fib_nb); err_register_fib_notifier: + rocker_remove_ports(rocker); +err_probe_ports: destroy_workqueue(rocker->rocker_owq); err_alloc_ordered_workqueue: free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker); @@ -2961,9 +2961,9 @@ static void rocker_remove(struct pci_dev *pdev) { struct rocker *rocker = pci_get_drvdata(pdev); - rocker_remove_ports(rocker); unregister_switchdev_notifier(&rocker_switchdev_notifier); unregister_fib_notifier(&rocker->fib_nb); + rocker_remove_ports(rocker); rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET); destroy_workqueue(rocker->rocker_owq); free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 2092febfcb42..8d9f02b7a71f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1243,6 +1243,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/of/unittest-data/.gitignore b/drivers/of/unittest-data/.gitignore deleted file mode 100644 index 4b3cf8b16de2..000000000000 --- a/drivers/of/unittest-data/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -testcases.dtb -testcases.dtb.S diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5e7200f05873..c17ccb913fde 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1826,8 +1826,10 @@ static int storvsc_probe(struct hv_device *device, fc_host_node_name(host) = stor_device->node_name; fc_host_port_name(host) = stor_device->port_name; stor_device->rport = fc_remote_port_add(host, 0, &ids); - if (!stor_device->rport) + if (!stor_device->rport) { + ret = -ENOMEM; goto err_out3; + } } #endif return 0; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bd15309ac5f1..082891dffd9d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1212,6 +1212,7 @@ static long vhost_net_reset_owner(struct vhost_net *n) } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, umem); vhost_net_vq_reset(n); done: diff --git a/kernel/exit.c b/kernel/exit.c index f6cad39f35df..e3a08761eb40 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1755,3 +1755,12 @@ COMPAT_SYSCALL_DEFINE5(waitid, return -EFAULT; } #endif + +__weak void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} +EXPORT_SYMBOL(abort); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53f7c919b916..66e7efabf0a1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5828,6 +5828,20 @@ void mem_cgroup_sk_alloc(struct sock *sk) if (!mem_cgroup_sockets_enabled) return; + /* + * Socket cloning can throw us here with sk_memcg already + * filled. It won't however, necessarily happen from + * process context. So the test for root memcg given + * the current task's memcg won't help us in this case. + * + * Respecting the original socket's memcg is a better + * decision in this case. + */ + if (sk->sk_memcg) { + css_get(&sk->sk_memcg->css); + return; + } + rcu_read_lock(); memcg = mem_cgroup_from_task(current); if (memcg == root_mem_cgroup) diff --git a/net/core/sock.c b/net/core/sock.c index 415f441c63b9..beb1e299fed3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1677,16 +1677,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; - - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; - atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); + mem_cgroup_sk_alloc(newsk); cgroup_sk_alloc(&newsk->sk_cgrp_data); rcu_read_lock(); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5eeb1d20cc38..676092d7bd81 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -94,6 +94,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) return more_reuse; } +static void reuseport_free_rcu(struct rcu_head *head) +{ + struct sock_reuseport *reuse; + + reuse = container_of(head, struct sock_reuseport, rcu); + if (reuse->prog) + bpf_prog_destroy(reuse->prog); + kfree(reuse); +} + /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. @@ -102,7 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) */ int reuseport_add_sock(struct sock *sk, struct sock *sk2) { - struct sock_reuseport *reuse; + struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2); @@ -113,10 +123,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)), - "socket already in reuseport group"); + lockdep_is_held(&reuseport_lock)); + old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_socks != 1) { + spin_unlock_bh(&reuseport_lock); + return -EBUSY; + } if (reuse->num_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); @@ -134,19 +147,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2) spin_unlock_bh(&reuseport_lock); + if (old_reuse) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } -static void reuseport_free_rcu(struct rcu_head *head) -{ - struct sock_reuseport *reuse; - - reuse = container_of(head, struct sock_reuseport, rcu); - if (reuse->prog) - bpf_prog_destroy(reuse->prog); - kfree(reuse); -} - void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 013fed55b610..fbeb35ad804b 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; + + rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); + rcu_read_unlock(); + pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b47a59cb3573..0cc08c512202 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -475,7 +475,6 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } - mem_cgroup_sk_alloc(newsk); out: release_sock(sk); if (req) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2a65d806b562..fe11128d7df4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2379,6 +2379,12 @@ int tcp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 8322f26e770e..25c5a0b60cfc 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -481,7 +481,8 @@ static void bbr_advance_cycle_phase(struct sock *sk) bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; - bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx]; + bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT : + bbr_pacing_gain[bbr->cycle_idx]; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ @@ -490,8 +491,7 @@ static void bbr_update_cycle_phase(struct sock *sk, { struct bbr *bbr = inet_csk_ca(sk); - if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw && - bbr_is_next_cycle_phase(sk, rs)) + if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs)) bbr_advance_cycle_phase(sk); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c5318f5f6a14..6a76e41e6d51 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -184,7 +184,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); -static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id); +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, + bool send_na); static void addrconf_dad_run(struct inet6_dev *idev); static void addrconf_rs_timer(unsigned long data); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); @@ -3825,12 +3826,17 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { + bool send_na = false; + + if (ifp->flags & IFA_F_TENTATIVE && + !(ifp->flags & IFA_F_OPTIMISTIC)) + send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp, bump_id); + addrconf_dad_completed(ifp, bump_id, send_na); return; } @@ -3959,16 +3965,21 @@ static void addrconf_dad_work(struct work_struct *w) } if (ifp->dad_probes == 0) { + bool send_na = false; + /* * DAD was successful */ + if (ifp->flags & IFA_F_TENTATIVE && + !(ifp->flags & IFA_F_OPTIMISTIC)) + send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); - addrconf_dad_completed(ifp, bump_id); + addrconf_dad_completed(ifp, bump_id, send_na); goto out; } @@ -4006,7 +4017,8 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) return true; } -static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) +static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, + bool send_na) { struct net_device *dev = ifp->idev->dev; struct in6_addr lladdr; @@ -4038,6 +4050,16 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id) if (send_mld) ipv6_mc_dad_complete(ifp->idev); + /* send unsolicited NA if enabled */ + if (send_na && + (ifp->idev->cnf.ndisc_notify || + dev_net(dev)->ipv6.devconf_all->ndisc_notify)) { + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, + /*router=*/ !!ifp->idev->cnf.forwarding, + /*solicited=*/ false, /*override=*/ true, + /*inc_opt=*/ true); + } + if (send_rs) { /* * If a host as already performed a random delay diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index bcbd5f3bf8bd..9ccbf74deb99 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -284,6 +284,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; + bool saved_ipv6only; int addr_type = 0; int err = 0; @@ -389,19 +390,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; + saved_ipv6only = sk->sk_ipv6only; + if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED) + sk->sk_ipv6only = 1; + /* Make sure we are allowed to bind here. */ if ((snum || !inet->bind_address_no_port) && sk->sk_prot->get_port(sk, snum)) { + sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); err = -EADDRINUSE; goto out; } - if (addr_type != IPV6_ADDR_ANY) { + if (addr_type != IPV6_ADDR_ANY) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; - if (addr_type != IPV6_ADDR_MAPPED) - sk->sk_ipv6only = 1; - } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f5500f5444e9..e1060f28410d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -496,6 +496,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(-ENOENT); it->mrt = mrt; + it->cache = NULL; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 266a530414d7..2a937c8d19e9 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -558,6 +558,11 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { + /* skip tentative addresses until dad completes */ + if (ifa->flags & IFA_F_TENTATIVE && + !(ifa->flags & IFA_F_OPTIMISTIC)) + continue; + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, diff --git a/scripts/package/Makefile b/scripts/package/Makefile index 34de8b953ecf..348af5b20618 100644 --- a/scripts/package/Makefile +++ b/scripts/package/Makefile @@ -50,7 +50,6 @@ rpm-pkg rpm: FORCE $(CONFIG_SHELL) $(MKSPEC) >$(objtree)/kernel.spec $(call cmd,src_tar,$(KERNELPATH),kernel.spec) +rpmbuild $(RPMOPTS) --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz - rm $(KERNELPATH).tar.gz kernel.spec # binrpm-pkg # --------------------------------------------------------------------------- @@ -59,7 +58,8 @@ binrpm-pkg: FORCE $(CONFIG_SHELL) $(MKSPEC) prebuilt > $(objtree)/binkernel.spec +rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \ $(UTS_MACHINE) -bb $(objtree)/binkernel.spec - rm binkernel.spec + +clean-files += $(objtree)/*.spec # Deb target # ---------------------------------------------------------------------------

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 4.14 00/22] 4.14.19-stable review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.14.19 release. There are 22 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Sun Feb 11 13:39:12 UTC 2018. Anything received after that time might be too late. The whole patch series can be found in one patch at: kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.19-rc1.gz or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 4.14.19-rc1 Dan Carpenter <dan.carpenter(a)oracle.com> scsi: storvsc: missing error code in storvsc_probe() Andrew Morton <akpm(a)linux-foundation.org> kernel/exit.c: export abort() to modules Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> arch: define weak abort() Robert Baronescu <robert.baronescu(a)nxp.com> crypto: tcrypt - fix S/G table for test_aead_speed() Jesse Chan <jc(a)linux.com> media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Jesse Chan <jc(a)linux.com> media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION Eric Dumazet <edumazet(a)google.com> soreuseport: fix mem leak in reuseport_add_sock() Martin KaFai Lau <kafai(a)fb.com> ipv6: Fix SO_REUSEPORT UDP socket with implicit sk_ipv6only Neal Cardwell <ncardwell(a)google.com> tcp_bbr: fix pacing_gain to always be unity when using lt_bw Jiri Pirko <jiri(a)mellanox.com> rocker: fix possible null pointer dereference in rocker_router_fib_event_work David Ahern <dsahern(a)gmail.com> net: ipv6: send unsolicited NA after DAD Roman Gushchin <guro(a)fb.com> Revert "defer call to mem_cgroup_sk_alloc()" Jason Wang <jasowang(a)redhat.com> vhost_net: stop device during reset owner Li RongQing <lirongqing(a)baidu.com> tcp: release sk_frag.page in tcp_disconnect Chunhao Lin <hau(a)realtek.com> r8169: fix RTL8168EP take too long to complete driver initialization. Kristian Evensen <kristian.evensen(a)gmail.com> qmi_wwan: Add support for Quectel EP06 Junxiao Bi <junxiao.bi(a)oracle.com> qlcnic: fix deadlock bug Eric Dumazet <edumazet(a)google.com> net: igmp: add a missing rcu locking section Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com> ip6mr: fix stale iterator Masahiro Yamada <yamada.masahiro(a)socionext.com> kbuild: rpm-pkg: keep spec file until make mrproper Masahiro Yamada <yamada.masahiro(a)socionext.com> .gitignore: move *.dtb and *.dtb.S patterns to the top-level .gitignore Masahiro Yamada <yamada.masahiro(a)socionext.com> .gitignore: sort normal pattern rules alphabetically ------------- Diffstat: .gitignore | 49 ++++++++++++---------- Makefile | 4 +- arch/arc/boot/.gitignore | 1 - arch/arm/boot/.gitignore | 1 - arch/arm/kernel/traps.c | 1 - arch/arm64/boot/dts/.gitignore | 1 - arch/m32r/kernel/traps.c | 1 - arch/metag/boot/.gitignore | 1 - arch/microblaze/boot/.gitignore | 1 - arch/mips/boot/.gitignore | 1 - arch/nios2/boot/.gitignore | 1 - arch/powerpc/boot/.gitignore | 1 - arch/unicore32/kernel/traps.c | 1 - arch/xtensa/boot/.gitignore | 1 - crypto/tcrypt.c | 6 ++- .../media/platform/mtk-vcodec/mtk_vcodec_util.c | 3 ++ drivers/media/platform/soc_camera/soc_scale_crop.c | 4 ++ .../net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 ++++---- drivers/net/ethernet/realtek/r8169.c | 4 +- drivers/net/ethernet/rocker/rocker_main.c | 18 ++++---- drivers/net/usb/qmi_wwan.c | 1 + drivers/of/unittest-data/.gitignore | 2 - drivers/scsi/storvsc_drv.c | 4 +- drivers/vhost/net.c | 1 + kernel/exit.c | 9 ++++ mm/memcontrol.c | 14 +++++++ net/core/sock.c | 5 +-- net/core/sock_reuseport.c | 35 +++++++++------- net/ipv4/igmp.c | 4 ++ net/ipv4/inet_connection_sock.c | 1 - net/ipv4/tcp.c | 6 +++ net/ipv4/tcp_bbr.c | 6 +-- net/ipv6/addrconf.c | 30 +++++++++++-- net/ipv6/af_inet6.c | 11 +++-- net/ipv6/ip6mr.c | 1 + net/ipv6/ndisc.c | 5 +++ scripts/package/Makefile | 4 +- 37 files changed, 164 insertions(+), 93 deletions(-)

7 years, 4 months

5
26
0 0

[Linux-stable-mirror] [PATCH 4.15 00/23] 4.15.3-stable review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.15.3 release. There are 23 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Sun Feb 11 13:39:20 UTC 2018. Anything received after that time might be too late. The whole patch series can be found in one patch at: kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.15.3-rc1.gz or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.15.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 4.15.3-rc1 Robert Baronescu <robert.baronescu(a)nxp.com> crypto: tcrypt - fix S/G table for test_aead_speed() Masahiro Yamada <yamada.masahiro(a)socionext.com> gpio: uniphier: fix mismatch between license text and MODULE_LICENSE Jesse Chan <jc(a)linux.com> media: tegra-cec: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Jesse Chan <jc(a)linux.com> media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Jesse Chan <jc(a)linux.com> media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION Jiri Pirko <jiri(a)mellanox.com> net: sched: fix use-after-free in tcf_block_put_ext Cong Wang <xiyou.wangcong(a)gmail.com> net_sched: get rid of rcu_barrier() in tcf_block_put_ext() Eric Dumazet <edumazet(a)google.com> soreuseport: fix mem leak in reuseport_add_sock() Martin KaFai Lau <kafai(a)fb.com> ipv6: Fix SO_REUSEPORT UDP socket with implicit sk_ipv6only Paolo Abeni <pabeni(a)redhat.com> cls_u32: add missing RCU annotation. Neal Cardwell <ncardwell(a)google.com> tcp_bbr: fix pacing_gain to always be unity when using lt_bw Jiri Pirko <jiri(a)mellanox.com> rocker: fix possible null pointer dereference in rocker_router_fib_event_work David Ahern <dsahern(a)gmail.com> net: ipv6: send unsolicited NA after DAD Roman Gushchin <guro(a)fb.com> Revert "defer call to mem_cgroup_sk_alloc()" Wei Wang <weiwan(a)google.com> ipv6: change route cache aging logic Eric Dumazet <edumazet(a)google.com> ipv6: addrconf: break critical section in addrconf_verify_rtnl() Jason Wang <jasowang(a)redhat.com> vhost_net: stop device during reset owner Li RongQing <lirongqing(a)baidu.com> tcp: release sk_frag.page in tcp_disconnect Chunhao Lin <hau(a)realtek.com> r8169: fix RTL8168EP take too long to complete driver initialization. Kristian Evensen <kristian.evensen(a)gmail.com> qmi_wwan: Add support for Quectel EP06 Junxiao Bi <junxiao.bi(a)oracle.com> qlcnic: fix deadlock bug Eric Dumazet <edumazet(a)google.com> net: igmp: add a missing rcu locking section Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com> ip6mr: fix stale iterator ------------- Diffstat: Makefile | 4 +-- crypto/tcrypt.c | 6 ++-- drivers/gpio/gpio-uniphier.c | 2 +- .../media/platform/mtk-vcodec/mtk_vcodec_util.c | 3 ++ drivers/media/platform/soc_camera/soc_scale_crop.c | 4 +++ drivers/media/platform/tegra-cec/tegra_cec.c | 5 +++ .../net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 +++++----- drivers/net/ethernet/realtek/r8169.c | 4 +-- drivers/net/ethernet/rocker/rocker_main.c | 18 +++++----- drivers/net/usb/qmi_wwan.c | 1 + drivers/vhost/net.c | 1 + include/net/sch_generic.h | 1 - mm/memcontrol.c | 14 ++++++++ net/core/sock.c | 5 +-- net/core/sock_reuseport.c | 35 ++++++++++--------- net/ipv4/igmp.c | 4 +++ net/ipv4/inet_connection_sock.c | 1 - net/ipv4/tcp.c | 6 ++++ net/ipv4/tcp_bbr.c | 6 ++-- net/ipv6/addrconf.c | 32 +++++++++++++++--- net/ipv6/af_inet6.c | 11 +++--- net/ipv6/ip6mr.c | 1 + net/ipv6/ndisc.c | 5 +++ net/ipv6/route.c | 20 ++++++----- net/sched/cls_api.c | 39 ++++++++-------------- net/sched/cls_u32.c | 12 ++++--- 26 files changed, 163 insertions(+), 95 deletions(-)

7 years, 4 months

4
26
0 0

[Linux-stable-mirror] Patch "watchdog: indydog: Add dependency on SGI_HAS_INDYDOG" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled watchdog: indydog: Add dependency on SGI_HAS_INDYDOG to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: watchdog-indydog-add-dependency-on-sgi_has_indydog.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 24f8d233074badd4c18e4dafd2fb97d65838afed Mon Sep 17 00:00:00 2001 From: Matt Redfearn <matt.redfearn(a)mips.com> Date: Tue, 14 Nov 2017 10:52:54 +0000 Subject: watchdog: indydog: Add dependency on SGI_HAS_INDYDOG From: Matt Redfearn <matt.redfearn(a)mips.com> commit 24f8d233074badd4c18e4dafd2fb97d65838afed upstream. Commit da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") enabled building the Indy watchdog driver when COMPILE_TEST is enabled. However, the driver makes reference to symbols that are only defined for certain platforms are selected in the config. These platforms select SGI_HAS_INDYDOG. Without this, link time errors result, for example when building a MIPS allyesconfig. drivers/watchdog/indydog.o: In function `indydog_write': indydog.c:(.text+0x18): undefined reference to `sgimc' indydog.c:(.text+0x1c): undefined reference to `sgimc' drivers/watchdog/indydog.o: In function `indydog_start': indydog.c:(.text+0x54): undefined reference to `sgimc' indydog.c:(.text+0x58): undefined reference to `sgimc' drivers/watchdog/indydog.o: In function `indydog_stop': indydog.c:(.text+0xa4): undefined reference to `sgimc' drivers/watchdog/indydog.o:indydog.c:(.text+0xa8): more undefined references to `sgimc' follow make: *** [Makefile:1005: vmlinux] Error 1 Fix this by ensuring that CONFIG_INDIDOG can only be selected when the necessary dependent platform symbols are built in. Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") Signed-off-by: Matt Redfearn <matt.redfearn(a)mips.com> Signed-off-by: Ralf Baechle <ralf(a)linux-mips.org> Suggested-by: James Hogan <james.hogan(a)mips.com> Reviewed-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Wim Van Sebroeck <wim(a)iguana.be> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/watchdog/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1451,7 +1451,7 @@ config RC32434_WDT config INDYDOG tristate "Indy/I2 Hardware Watchdog" - depends on SGI_HAS_INDYDOG || (MIPS && COMPILE_TEST) + depends on SGI_HAS_INDYDOG help Hardware driver for the Indy's/I2's watchdog. This is a watchdog timer that will reboot the machine after a 60 second Patches currently in stable-queue which might be from matt.redfearn(a)mips.com are queue-4.15/watchdog-indydog-add-dependency-on-sgi_has_indydog.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "[PATCH] Revert "x86/alternative: Print unadorned pointers"" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled [PATCH] Revert "x86/alternative: Print unadorned pointers" to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: revert-x86-alternative-print-unadorned-pointers.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From ddf5d08f6fa96dd9f3911931079264d6099c6a51 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Date: Tue, 13 Feb 2018 10:14:14 +0100 Subject: [PATCH] Revert "x86/alternative: Print unadorned pointers" This reverts commit 67eb59b8ecfb319438706cee2cb67a3045b54494. It's not needed in 4.14.y and only causes messy debugging messages, if anyone actually cares about these random debug messages in the first place (doubtful). Reported-by: Kees Cook <keescook(a)google.com> Acked-by: Borislav Petkov <bp(a)suse.de> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: riel(a)redhat.com Cc: ak(a)linux.intel.com Cc: peterz(a)infradead.org Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: jikos(a)kernel.org Cc: luto(a)amacapital.net Cc: dave.hansen(a)intel.com Cc: torvalds(a)linux-foundation.org Cc: keescook(a)google.com Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Cc: pjt(a)google.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/alternative.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -287,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 * tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -344,7 +344,7 @@ static void __init_or_module noinline op add_nops(instr + (a->instrlen - a->padlen), a->padlen); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -365,7 +365,7 @@ void __init_or_module noinline apply_alt u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %px, -> %px", start, end); + DPRINTK("alt table %p -> %p", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -389,14 +389,14 @@ void __init_or_module noinline apply_alt continue; } - DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -422,7 +422,7 @@ void __init_or_module noinline apply_alt a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } Patches currently in stable-queue which might be from gregkh(a)linuxfoundation.org are queue-4.14/crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch queue-4.14/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.14/r8169-fix-rtl8168ep-take-too-long-to-complete-driver-initialization.patch queue-4.14/tcp-release-sk_frag.page-in-tcp_disconnect.patch queue-4.14/gitignore-move-.dtb-and-.dtb.s-patterns-to-the-top-level-.gitignore.patch queue-4.14/net-igmp-add-a-missing-rcu-locking-section.patch queue-4.14/soreuseport-fix-mem-leak-in-reuseport_add_sock.patch queue-4.14/ipv6-fix-so_reuseport-udp-socket-with-implicit-sk_ipv6only.patch queue-4.14/kbuild-rpm-pkg-keep-spec-file-until-make-mrproper.patch queue-4.14/ip6mr-fix-stale-iterator.patch queue-4.14/media-mtk-vcodec-add-missing-module_license-description.patch queue-4.14/vhost_net-stop-device-during-reset-owner.patch queue-4.14/revert-defer-call-to-mem_cgroup_sk_alloc.patch queue-4.14/gitignore-sort-normal-pattern-rules-alphabetically.patch queue-4.14/rocker-fix-possible-null-pointer-dereference-in-rocker_router_fib_event_work.patch queue-4.14/revert-x86-alternative-print-unadorned-pointers.patch queue-4.14/net-ipv6-send-unsolicited-na-after-dad.patch queue-4.14/qlcnic-fix-deadlock-bug.patch queue-4.14/scsi-storvsc-missing-error-code-in-storvsc_probe.patch queue-4.14/qmi_wwan-add-support-for-quectel-ep06.patch queue-4.14/tcp_bbr-fix-pacing_gain-to-always-be-unity-when-using-lt_bw.patch queue-4.14/arch-define-weak-abort.patch queue-4.14/kernel-exit.c-export-abort-to-modules.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] + vmalloc-fix-__gfp_highmem-usage-for-vmalloc_32-on-32b-systems.patch added to -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: vmalloc: fix __GFP_HIGHMEM usage for vmalloc_32 on 32b systems has been added to the -mm tree. Its filename is vmalloc-fix-__gfp_highmem-usage-for-vmalloc_32-on-32b-systems.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/vmalloc-fix-__gfp_highmem-usage-fo… and later at http://ozlabs.org/~akpm/mmotm/broken-out/vmalloc-fix-__gfp_highmem-usage-fo… Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Michal Hocko <mhocko(a)suse.com> Subject: vmalloc: fix __GFP_HIGHMEM usage for vmalloc_32 on 32b systems Kai Heng Feng has noticed that BUG_ON(PageHighMem(pg)) triggers in drivers/media/common/saa7146/saa7146_core.c since 19809c2da28a ("mm, vmalloc: use __GFP_HIGHMEM implicitly"). saa7146_vmalloc_build_pgtable uses vmalloc_32 and it is reasonable to expect that the resulting page is not in highmem. The above commit aimed to add __GFP_HIGHMEM only for those requests which do not specify any zone modifier gfp flag. vmalloc_32 relies on GFP_VMALLOC32 which should do the right thing. Except it has been missed that GFP_VMALLOC32 is an alias for GFP_KERNEL on 32b architectures. Thanks to Matthew to notice this. Fix the problem by unconditionally setting GFP_DMA32 in GFP_VMALLOC32 for !64b arches (as a bailout). This should do the right thing and use ZONE_NORMAL which should be always below 4G on 32b systems. Debugged by Matthew Wilcox. Link: http://lkml.kernel.org/r/20180212095019.GX21609@dhcp22.suse.cz Fixes: 19809c2da28a ("mm, vmalloc: use __GFP_HIGHMEM implicitly”) Signed-off-by: Michal Hocko <mhocko(a)suse.com> Reported-by: Kai Heng Feng <kai.heng.feng(a)canonical.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Laura Abbott <labbott(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmalloc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff -puN mm/vmalloc.c~vmalloc-fix-__gfp_highmem-usage-for-vmalloc_32-on-32b-systems mm/vmalloc.c --- a/mm/vmalloc.c~vmalloc-fix-__gfp_highmem-usage-for-vmalloc_32-on-32b-systems +++ a/mm/vmalloc.c @@ -1947,7 +1947,11 @@ void *vmalloc_exec(unsigned long size) #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL #else -#define GFP_VMALLOC32 GFP_KERNEL +/* + * 64b systems should always have either DMA or DMA32 zones. For others + * GFP_DMA32 should do the right thing and use the normal zone. + */ +#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL #endif /** _ Patches currently in -mm which might be from mhocko(a)suse.com are vmalloc-fix-__gfp_highmem-usage-for-vmalloc_32-on-32b-systems.patch mm-oom-docs-describe-the-cgroup-aware-oom-killer-fix-2.patch mm-introduce-map_fixed_safe.patch fs-elf-drop-map_fixed-usage-from-elf_map.patch mm-numa-rework-do_pages_move.patch mm-migrate-remove-reason-argument-from-new_page_t.patch mm-unclutter-thp-migration.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH v3 3/3] extcon: int3496: process id-pin first so that we start with the right status

by Hans de Goede

Some other drivers may be waiting for our extcon to show-up (exiting their probe methods with -EPROBE_DEFER until we show up). These drivers will typically get the cable state directly after getting the extcon, this commit changes the int3496 code to process the id-pin before registering the extcon, so that other drivers see the correct state right away. Fixes: 2f556bdb9f2e ("extcon: int3496: Add Intel INT3496 ACPI ... driver") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> --- Changes in v2: -Add Fixes tag Changes in v3: -Fix oops on probe by scheduling the work too early --- drivers/extcon/extcon-intel-int3496.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c index c8691b5a9cb0..673bb26a9a2a 100644 --- a/drivers/extcon/extcon-intel-int3496.c +++ b/drivers/extcon/extcon-intel-int3496.c @@ -131,11 +131,15 @@ static int int3496_probe(struct platform_device *pdev) if (IS_ERR(data->gpio_usb_mux)) dev_info(dev, "can't request USB MUX GPIO\n"); - /* register extcon device */ data->edev = devm_extcon_dev_allocate(dev, int3496_cable); if (IS_ERR(data->edev)) return -ENOMEM; + /* process id-pin first so that we start with the right status */ + queue_delayed_work(system_wq, &data->work, 0); + flush_delayed_work(&data->work); + + /* register extcon device */ ret = devm_extcon_dev_register(dev, data->edev); if (ret < 0) { dev_err(dev, "can't register extcon device: %d\n", ret); @@ -153,9 +157,6 @@ static int int3496_probe(struct platform_device *pdev) return ret; } - /* queue initial processing of id-pin */ - queue_delayed_work(system_wq, &data->work, 0); - platform_set_drvdata(pdev, data); return 0; -- 2.14.3

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [PATCH] mtd: nand: vf610: set correct ooblayout

by Stefan Agner

With commit 3cf32d180227 ("mtd: nand: vf610: switch to mtd_ooblayout_ops") the driver started to use the NAND cores default large page ooblayout. However, shortly after commit 6a623e076944 ("mtd: nand: add ooblayout for old hamming layout") changed the default layout to the old hamming layout, which is not what vf610_nfc is using. Specify the default large page layout explicitly. Fixes: 6a623e076944 ("mtd: nand: add ooblayout for old hamming layout") Cc: <stable(a)vger.kernel.org> # v4.12+ Signed-off-by: Stefan Agner <stefan(a)agner.ch> --- drivers/mtd/nand/vf610_nfc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c index 80d31a58e558..f367144f3c6f 100644 --- a/drivers/mtd/nand/vf610_nfc.c +++ b/drivers/mtd/nand/vf610_nfc.c @@ -752,10 +752,8 @@ static int vf610_nfc_probe(struct platform_device *pdev) if (mtd->oobsize > 64) mtd->oobsize = 64; - /* - * mtd->ecclayout is not specified here because we're using the - * default large page ECC layout defined in NAND core. - */ + /* Use default large page ECC layout defined in NAND core */ + mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops); if (chip->ecc.strength == 32) { nfc->ecc_mode = ECC_60_BYTE; chip->ecc.bytes = 60; -- 2.16.1

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [PATCH] extcon: intel-int3496: Fix oops on probe

by Hans de Goede

Commit 41d600274fbf ("extcon: int3496: process id-pin first so that we start with the right status") starts the work on the workqueue before registration to make sure we've a valid cable state directly after registration. But that commit moves the queuing of the work to before we even alloc the extcon, causing a NULL pointer deref in the worker. This commit moves the queuing of the work to after we alloc the extcon, fixing the NULL pointer deref. Fixes: 41d600274fbf ("extcon: int3496: process id-pin first ...") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> --- drivers/extcon/extcon-intel-int3496.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c index b23ee9d993a3..673bb26a9a2a 100644 --- a/drivers/extcon/extcon-intel-int3496.c +++ b/drivers/extcon/extcon-intel-int3496.c @@ -131,15 +131,15 @@ static int int3496_probe(struct platform_device *pdev) if (IS_ERR(data->gpio_usb_mux)) dev_info(dev, "can't request USB MUX GPIO\n"); + data->edev = devm_extcon_dev_allocate(dev, int3496_cable); + if (IS_ERR(data->edev)) + return -ENOMEM; + /* process id-pin first so that we start with the right status */ queue_delayed_work(system_wq, &data->work, 0); flush_delayed_work(&data->work); /* register extcon device */ - data->edev = devm_extcon_dev_allocate(dev, int3496_cable); - if (IS_ERR(data->edev)) - return -ENOMEM; - ret = devm_extcon_dev_register(dev, data->edev); if (ret < 0) { dev_err(dev, "can't register extcon device: %d\n", ret); -- 2.14.3

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] [PATCH -mm -v2] mm, swap, frontswap: Fix THP swap if frontswap enabled

by Huang, Ying

From: Huang Ying <huang.ying.caritas(a)gmail.com> It was reported by Sergey Senozhatsky that if THP (Transparent Huge Page) and frontswap (via zswap) are both enabled, when memory goes low so that swap is triggered, segfault and memory corruption will occur in random user space applications as follow, kernel: urxvt[338]: segfault at 20 ip 00007fc08889ae0d sp 00007ffc73a7fc40 error 6 in libc-2.26.so[7fc08881a000+1ae000] #0 0x00007fc08889ae0d _int_malloc (libc.so.6) #1 0x00007fc08889c2f3 malloc (libc.so.6) #2 0x0000560e6004bff7 _Z14rxvt_wcstoutf8PKwi (urxvt) #3 0x0000560e6005e75c n/a (urxvt) #4 0x0000560e6007d9f1 _ZN16rxvt_perl_interp6invokeEP9rxvt_term9hook_typez (urxvt) #5 0x0000560e6003d988 _ZN9rxvt_term9cmd_parseEv (urxvt) #6 0x0000560e60042804 _ZN9rxvt_term6pty_cbERN2ev2ioEi (urxvt) #7 0x0000560e6005c10f _Z17ev_invoke_pendingv (urxvt) #8 0x0000560e6005cb55 ev_run (urxvt) #9 0x0000560e6003b9b9 main (urxvt) #10 0x00007fc08883af4a __libc_start_main (libc.so.6) #11 0x0000560e6003f9da _start (urxvt) After bisection, it was found the first bad commit is bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out"). The root cause is as follow. When the pages are written to swap device during swapping out in swap_writepage(), zswap (fontswap) is tried to compress the pages instead to improve the performance. But zswap (frontswap) will treat THP as normal page, so only the head page is saved. After swapping in, tail pages will not be restored to its original contents, so cause the memory corruption in the applications. This is fixed via splitting THP before writing the page to swap device if frontswap is enabled. To deal with the situation where frontswap is enabled at runtime, whether the page is THP is checked before using frontswap during swapping out too. Reported-and-tested-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Shaohua Li <shli(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: stable(a)vger.kernel.org # 4.14 Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Changelog: v2: - Move frontswap check into swapfile.c to avoid to make vmscan.c depends on frontswap. --- mm/page_io.c | 2 +- mm/swapfile.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/page_io.c b/mm/page_io.c index b41cf9644585..6dca817ae7a0 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -250,7 +250,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) unlock_page(page); goto out; } - if (frontswap_store(page) == 0) { + if (!PageTransHuge(page) && frontswap_store(page) == 0) { set_page_writeback(page); unlock_page(page); end_page_writeback(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 006047b16814..0b7c7883ce64 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -934,6 +934,9 @@ int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[]) /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && cluster); + /* Frontswap doesn't support THP */ + if (frontswap_enabled() && cluster) + goto noswap; avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages; if (avail_pgs <= 0) -- 2.15.1

7 years, 4 months

7
12
0 0

[Linux-stable-mirror] [PATCH v2] xenbus: track caller request id

by Joao Martins

Commit fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") optimized xenbus concurrent accesses but in doing so broke UABI of /dev/xen/xenbus. Through /dev/xen/xenbus applications are in charge of xenbus message exchange with the correct header and body. Now, after the mentioned commit the replies received by application will no longer have the header req_id echoed back as it was on request (see specification below for reference), because that particular field is being overwritten by kernel. struct xsd_sockmsg { uint32_t type; /* XS_??? */ uint32_t req_id;/* Request identifier, echoed in daemon's response. */ uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */ uint32_t len; /* Length of data following this. */ /* Generally followed by nul-terminated string(s). */ }; Before there was only one request at a time so req_id could simply be forwarded back and forth. To allow simultaneous requests we need a different req_id for each message thus kernel keeps a monotonic increasing counter for this field and is written on every request irrespective of userspace value. Forwarding again the req_id on userspace requests is not a solution because we would open the possibility of userspace-generated req_id colliding with kernel ones. So this patch instead takes another route which is to artificially keep user req_id while keeping the xenbus logic as is. We do that by saving the original req_id before xs_send(), use the private kernel counter as req_id and then once reply comes and was validated, we restore back the original req_id. Cc: <stable(a)vger.kernel.org> # 4.11 Fixes: fd8aa9095a ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") Reported-by: Bhavesh Davda <bhavesh.davda(a)oracle.com> Signed-off-by: Joao Martins <joao.m.martins(a)oracle.com> --- Here's a link to a unit test (https://pastebin.com/2q51j2sR) where req_id of reply and response are being asserted each request. Without this patch the assert will fail (e.g. try it with `./xswire_reqid_test name`). But on <= v4.10 or >= v4.11 with the fix above, it will print domain name 10 times. Changes since v1: * Adjust commit message (Comments from Juergen on IRC) * Unilateraly save/restore req_id and remove xs_request_is_user() * Initialize req_id for kernel callers --- drivers/xen/xenbus/xenbus.h | 1 + drivers/xen/xenbus/xenbus_comms.c | 1 + drivers/xen/xenbus/xenbus_xs.c | 3 +++ 3 files changed, 5 insertions(+) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 149c5e7efc89..092981171df1 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -76,6 +76,7 @@ struct xb_req_data { struct list_head list; wait_queue_head_t wq; struct xsd_sockmsg msg; + uint32_t caller_req_id; enum xsd_sockmsg_type type; char *body; const struct kvec *vec; diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 5b081a01779d..d239fc3c5e3d 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,6 +309,7 @@ static int process_msg(void) goto out; if (req->state == xb_req_state_wait_reply) { + req->msg.req_id = req->caller_req_id; req->msg.type = state.msg.type; req->msg.len = state.msg.len; req->body = state.body; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 3e59590c7254..3f3b29398ab8 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->state = xb_req_state_queued; init_waitqueue_head(&req->wq); + /* Save the caller req_id and restore it later in the reply */ + req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); mutex_lock(&xb_write_mutex); @@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; + msg.req_id = 0; msg.tx_id = t.id; msg.type = type; msg.len = 0; -- 2.11.0

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] [PATCH 6/6] xhci: fix xhci debugfs errors in xhci_stop

by Mathias Nyman

From: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> In function xhci_stop, xhci_debugfs_exit called before xhci_mem_cleanup. xhci_debugfs_exit removed the xhci debugfs root nodes, xhci_mem_cleanup called function xhci_free_virt_devices_depth_first which in turn called function xhci_debugfs_remove_slot. Function xhci_debugfs_remove_slot removed the nodes for devices, the nodes folders are sub folder of xhci debugfs. It is unreasonable to remove xhci debugfs root folder before xhci debugfs sub folder. Function xhci_mem_cleanup should be called before function xhci_debugfs_exit. Fixes: 02b6fdc2a153 ("usb: xhci: Add debugfs interface for xHCI driver") Cc: <stable(a)vger.kernel.org> # v4.15 Signed-off-by: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> --- drivers/usb/host/xhci.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 4adb6da..25d4b748 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -646,8 +646,6 @@ static void xhci_stop(struct usb_hcd *hcd) return; } - xhci_debugfs_exit(xhci); - xhci_dbc_exit(xhci); spin_lock_irq(&xhci->lock); @@ -680,6 +678,7 @@ static void xhci_stop(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "cleaning up memory"); xhci_mem_cleanup(xhci); + xhci_debugfs_exit(xhci); xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_stop completed - status = %x", readl(&xhci->op_regs->status)); -- 2.7.4

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 5/6] xhci: xhci debugfs device nodes weren't removed after device plugged out

by Mathias Nyman

From: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> There is a bug after plugged out USB device, the device and its ep00 nodes are still kept, we need to remove the nodes in xhci_free_dev when USB device is plugged out. Fixes: 052f71e25a7e ("xhci: Fix xhci debugfs NULL pointer dereference in resume from hibernate") Cc: <stable(a)vger.kernel.org> # v4.15 Signed-off-by: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> --- drivers/usb/host/xhci.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b01bd64..4adb6da 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3545,12 +3545,10 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) virt_dev->eps[i].ep_state &= ~EP_STOP_CMD_PENDING; del_timer_sync(&virt_dev->eps[i].stop_cmd_timer); } - + xhci_debugfs_remove_slot(xhci, udev->slot_id); ret = xhci_disable_slot(xhci, udev->slot_id); - if (ret) { - xhci_debugfs_remove_slot(xhci, udev->slot_id); + if (ret) xhci_free_virt_device(xhci, udev->slot_id); - } } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) -- 2.7.4

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 4/6] xhci: Fix xhci debugfs devices node disappearance after hibernation

by Mathias Nyman

From: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> During system resume from hibernation, xhci host is reset, all the nodes in devices folder are removed in xhci_mem_cleanup function. Later nodes in /sys/kernel/debug/usb/xhci/* are created again in function xhci_run, but the nodes already exist, so the nodes still keep the old ones, finally device nodes in xhci debugfs folder /sys/kernel/debug/usb/xhci/*/devices/* are disappeared. This fix removed xhci debugfs nodes before the nodes are re-created, so all the nodes in xhci debugfs can be re-created successfully. Fixes: 02b6fdc2a153 ("usb: xhci: Add debugfs interface for xHCI driver") Cc: <stable(a)vger.kernel.org> # v4.15 Signed-off-by: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> --- drivers/usb/host/xhci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 1eeb339..b01bd64 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1014,6 +1014,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) xhci_dbg(xhci, "cleaning up memory\n"); xhci_mem_cleanup(xhci); + xhci_debugfs_exit(xhci); xhci_dbg(xhci, "xhci_stop completed - status = %x\n", readl(&xhci->op_regs->status)); -- 2.7.4

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 3/6] xhci: Fix NULL pointer in xhci debugfs

by Mathias Nyman

From: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> Commit dde634057da7 ("xhci: Fix use-after-free in xhci debugfs") causes a null pointer dereference while fixing xhci-debugfs usage of ring pointers that were freed during hibernate. The fix passed addresses to ring pointers instead, but forgot to do this change for the xhci_ring_trb_show function. The address of the ring pointer passed to xhci-debugfs was of a temporary ring pointer "new_ring" instead of the actual ring "ring" pointer. The temporary new_ring pointer will be set to NULL later causing the NULL pointer dereference. This issue was seen when reading xhci related files in debugfs: cat /sys/kernel/debug/usb/xhci/*/devices/*/ep*/trbs [ 184.604861] BUG: unable to handle kernel NULL pointer dereference at (null) [ 184.613776] IP: xhci_ring_trb_show+0x3a/0x890 [ 184.618733] PGD 264193067 P4D 264193067 PUD 263238067 PMD 0 [ 184.625184] Oops: 0000 [#1] SMP [ 184.726410] RIP: 0010:xhci_ring_trb_show+0x3a/0x890 [ 184.731944] RSP: 0018:ffffba8243c0fd90 EFLAGS: 00010246 [ 184.737880] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000000295d6 [ 184.746020] RDX: 00000000000295d5 RSI: 0000000000000001 RDI: ffff971a6418d400 [ 184.754121] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 [ 184.762222] R10: ffff971a64c98a80 R11: ffff971a62a00e40 R12: ffff971a62a85500 [ 184.770325] R13: 0000000000020000 R14: ffff971a6418d400 R15: ffff971a6418d400 [ 184.778448] FS: 00007fe725a79700(0000) GS:ffff971a6ec00000(0000) knlGS:0000000000000000 [ 184.787644] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 184.794168] CR2: 0000000000000000 CR3: 000000025f365005 CR4: 00000000003606f0 [ 184.802318] Call Trace: [ 184.805094] ? seq_read+0x281/0x3b0 [ 184.809068] seq_read+0xeb/0x3b0 [ 184.812735] full_proxy_read+0x4d/0x70 [ 184.817007] __vfs_read+0x23/0x120 [ 184.820870] vfs_read+0x91/0x130 [ 184.824538] SyS_read+0x42/0x90 [ 184.828106] entry_SYSCALL_64_fastpath+0x1a/0x7d Fixes: dde634057da7 ("xhci: Fix use-after-free in xhci debugfs") Cc: <stable(a)vger.kernel.org> # v4.15 Signed-off-by: Zhengjun Xing <zhengjun.xing(a)linux.intel.com> Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> --- drivers/usb/host/xhci-debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index e26e685..5851052 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -211,7 +211,7 @@ static void xhci_ring_dump_segment(struct seq_file *s, static int xhci_ring_trb_show(struct seq_file *s, void *unused) { int i; - struct xhci_ring *ring = s->private; + struct xhci_ring *ring = *(struct xhci_ring **)s->private; struct xhci_segment *seg = ring->first_seg; for (i = 0; i < ring->num_segs; i++) { @@ -387,7 +387,7 @@ void xhci_debugfs_create_endpoint(struct xhci_hcd *xhci, snprintf(epriv->name, sizeof(epriv->name), "ep%02d", ep_index); epriv->root = xhci_debugfs_create_ring_dir(xhci, - &dev->eps[ep_index].new_ring, + &dev->eps[ep_index].ring, epriv->name, spriv->root); spriv->eps[ep_index] = epriv; -- 2.7.4

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] v4.15.3 build: 0 failures 0 warnings (v4.15.3)

by Build bot for Mark Brown

Tree/Branch: v4.15.3 Git describe: v4.15.3 Commit: e6e2d12fa4 Linux 4.15.3 Build Time: 112 min 12 sec Passed: 10 / 10 (100.00 %) Failed: 0 / 10 ( 0.00 %) Errors: 0 Warnings: 0 Section Mismatches: 0 ------------------------------------------------------------------------------- defconfigs with issues (other than build errors): ------------------------------------------------------------------------------- =============================================================================== Detailed per-defconfig build reports below: ------------------------------------------------------------------------------- Passed with no errors, warnings or mismatches: arm64-allnoconfig arm64-allmodconfig arm-multi_v5_defconfig arm-multi_v7_defconfig x86_64-defconfig arm-allmodconfig arm-allnoconfig x86_64-allnoconfig arm-multi_v4t_defconfig arm64-defconfig close failed in file object destructor: sys.excepthook is missing lost sys.stderr

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 1/2] xen: xenbus_dev_frontend: Fix XS_TRANSACTION_END handling

by Simon Gaiser

Commit fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") made a subtle change to the semantic of xenbus_dev_request_and_reply() and xenbus_transaction_end(). Before on an error response to XS_TRANSACTION_END xenbus_dev_request_and_reply() would not decrement the active transaction counter. But xenbus_transaction_end() has always counted the transaction as finished regardless of the response. The new behavior is that xenbus_dev_request_and_reply() and xenbus_transaction_end() will always count the transaction as finished regardless the response code (handled in xs_request_exit()). But xenbus_dev_frontend tries to end a transaction on closing of the device if the XS_TRANSACTION_END failed before. Trying to close the transaction twice corrupts the reference count. So fix this by also considering a transaction closed if we have sent XS_TRANSACTION_END once regardless of the return code. Cc: <stable(a)vger.kernel.org> # 4.11 Fixes: fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") Signed-off-by: Simon Gaiser <simon(a)invisiblethingslab.com> --- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index f3b089b7c0b6..d2edbc79384a 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -365,7 +365,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) if (WARN_ON(rc)) goto out; } - } else if (req->msg.type == XS_TRANSACTION_END) { + } else if (req->type == XS_TRANSACTION_END) { trans = xenbus_get_transaction(u, req->msg.tx_id); if (WARN_ON(!trans)) goto out; -- 2.15.1

7 years, 4 months

3
3
0 0

[Linux-stable-mirror] [PATCH 3.2 00/79] 3.2.99-rc1 review

by Ben Hutchings

This is the start of the stable review cycle for the 3.2.99 release. There are 79 patches in this series, which will be posted as responses to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Tue Feb 13 12:00:00 UTC 2018. Anything received after that time might be too late. All the patches have also been committed to the linux-3.2.y-rc branch of https://git.kernel.org/pub/scm/linux/kernel/git/bwh/linux-stable-rc.git . A shortlog and diffstat can be found below. Ben. ------------- Al Viro (2): autofs4: autofs4_wait() vs. autofs4_catatonic_mode() race [4041bcdc7bef06a2fb29c57394c713a74bd13b08] autofs4: catatonic_mode vs. notify_daemon race [8753333266be67ff3a984ac1f6566d31c260bee4] Alan (1): usbip: Fix sscanf handling [2d32927127f44d755780aa5fa88c8c34e72558f8] Alan Stern (1): USB: usbfs: compute urb->actual_length for isochronous [2ef47001b3ee3ded579b7532ebdcf8680e4d8c54] Alex Chen (1): ocfs2: should wait dio before inode lock in ocfs2_setattr() [28f5a8a7c033cbf3e32277f4cc9c6afd74f05300] Alexander Potapenko (1): sctp: fully initialize the IPv6 address in sctp_v6_to_addr() [15339e441ec46fbc3bf3486bb1ae4845b0f1bb8d] Alexander Steffen (1): tpm-dev-common: Reject too short writes [ee70bc1e7b63ac8023c9ff9475d8741e397316e7] Alexandre Belloni (1): rtc: set the alarm to the next expiring timer [74717b28cb32e1ad3c1042cafd76b264c8c0f68d] Andreas Rohner (1): nilfs2: fix race condition that causes file system corruption [31ccb1f7ba3cfe29631587d451cf5bb8ab593550] Arnd Bergmann (2): Input: adxl34x - do not treat FIFO_MODE() as boolean [1dbc080c9ef6bcfba652ef0d6ae919b8c7c85a1d] isofs: fix timestamps beyond 2027 [34be4dbf87fc3e474a842305394534216d428f5d] Bart Van Assche (1): IB/srp: Avoid that a cable pull can trigger a kernel crash [8a0d18c62121d3c554a83eb96e2752861d84d937] Bart Westgeest (1): staging: usbip: removed #if 0'd out code [34c09578179f5838e5958c45e8aed4edc9c6c3b8] Bernhard Rosenkraenzer (1): USB: Add delay-init quirk for Corsair K70 LUX keyboards [a0fea6027f19c62727315aba1a7fae75a9caa842] Brent Taylor (1): mtd: nand: Fix writing mtdoops to nand flash. [30863e38ebeb500a31cecee8096fb5002677dd9b] Chuck Lever (1): nfs: Fix ugly referral attributes [c05cefcc72416a37eba5a2b35f0704ed758a9145] Colin Ian King (1): rtc: interface: ignore expired timers when enqueuing new timers [2b2f5ff00f63847d95adad6289bd8b05f5983dd5] Dan Carpenter (2): eCryptfs: use after free in ecryptfs_release_messaging() [db86be3a12d0b6e5c5b51c2ab2a48f06329cb590] scsi: bfa: integer overflow in debugfs [3e351275655d3c84dc28abf170def9786db5176d] Eric Biggers (1): dm bufio: fix integer overflow when limiting maximum cache size [74d4108d9e681dbbe4a2940ed8fdff1f6868184c] Eric Dumazet (1): netfilter: xt_TCPMSS: add more sanity tests on tcph->doff [2638fd0f92d4397884fd991d8f4925cb3f081901] Eric W. Biederman (1): net/sctp: Always set scope_id in sctp_inet6_skb_msgname [7c8a61d9ee1df0fb4747879fa67a99614eb62fec] Felipe Balbi (1): usb: add helper to extract bits 12:11 of wMaxPacketSize [541b6fe63023f3059cf85d47ff2767a3e42a8e44] Gabriele Paoloni (1): PCI/AER: Report non-fatal errors only to the affected endpoint [86acc790717fb60fb51ea3095084e331d8711c74] Guenter Roeck (1): kaiser: Set _PAGE_NX only if supported [61e9b3671007a5da8127955a1a3bda7e0d5f42e8] Guillaume Nault (5): l2tp: don't register sessions in l2tp_session_create() [3953ae7b218df4d1e544b98a393666f9ae58a78c] l2tp: ensure sessions are freed after their PPPOL2TP socket [cdd10c9627496ad25c87ce6394e29752253c69d3] l2tp: initialise PPP sessions before registering them [f98be6c6359e7e4a61aaefb9964c1db31cb9ec0c] l2tp: initialise l2tp_eth sessions before registering them [ee28de6bbd78c2e18111a0aef43ea746f28d2073] l2tp: protect sock pointer of struct pppol2tp_session with RCU [ee40fb2e1eb5bc0ddd3f2f83c6e39a454ef5a741] Hou Tao (1): dm: fix race between dm_get_from_kobject() and __dm_destroy() [b9a41d21dceadf8104812626ef85dc56ee8a60ed] Jan Harkes (1): coda: fix 'kernel memory exposure attempt' in fsync [d337b66a4c52c7b04eec661d86c2ef6e168965a2] Jason Gunthorpe (1): sctp: Fixup v4mapped behaviour to comply with Sock API [299ee123e19889d511092347f5fc14db0f10e3a6] Jens Axboe (1): blktrace: fix unlocked access to init/start-stop/teardown [1f2cac107c591c24b60b115d6050adc213d10fc0] Johan Hovold (2): USB: serial: garmin_gps: fix I/O after failed probe and remove [19a565d9af6e0d828bd0d521d3bafd5017f4ce52] USB: serial: garmin_gps: fix memory leak on probe errors [74d471b598444b7f2d964930f7234779c80960a0] Ladi Prosek (1): KVM: nVMX: set IDTR and GDTR limits when loading L1 host state [21f2d551183847bc7fbe8d866151d00cdad18752] Ladislav Michl (1): video: udlfb: Fix read EDID timeout [c98769475575c8a585f5b3952f4b5f90266f699b] Lepton Wu (1): kaiser: Set _PAGE_NX only if supported [not upstream; specific to KAISER backport] Mark Bloch (1): IB/mlx4: Increase maximal message size under UD QP [5f22a1d87c5315a98981ecf93cd8de226cffe6ca] Markus Elfring (1): media: omap_vout: Fix a possible null pointer dereference in omap_vout_open() [bfba2b3e21b9426c0f9aca00f3cad8631b2da170] Masami Hiramatsu (1): x86/decoder: Add new TEST instruction pattern [12a78d43de767eaf8fb272facb7a7b6f2dc6a9df] Mauro Carvalho Chehab (1): [media] cx231xx: Fix the max number of interfaces [139d28826b8e2bc7a9232fde0d2f14812914f501] Michele Baldessari (1): media: Don't do DMA on stack for firmware upload in the AS102 driver [b3120d2cc447ee77b9d69bf4ad7b452c9adb4d39] Mike Snitzer (1): dm: discard support requires all targets in a table support discards [8a74d29d541cd86569139c6f3f44b2d210458071] Mohamed Ghannam (2): RDS: Heap OOB write in rds_message_alloc_sgs() [c095508770aebf1b9218e77026e48345d719b17c] RDS: null pointer dereference in rds_atomic_free_op [7d11f77f84b27cef452cee332f4e469503084737] Nadav Amit (1): KVM: vmx: Inject #GP on invalid PAT CR [4566654bb9be9e8864df417bb72ceee5136b6a6a] NeilBrown (2): autofs: don't fail mount for transient error [ecc0c469f27765ed1e2b967be0aa17cee1a60b76] autofs: fix careless error in recent commit [302ec300ef8a545a7fc7f667e5fd743b091c2eeb] Pablo Neira Ayuso (3): netfilter: xt_TCPMSS: fix handling of malformed TCP header and options [71ffe9c77dd7a2b62207953091efa8dafec958dd] netfilter: xt_TCPOPTSTRIP: don't use tcp_hdr() [ed82c437320c48a4032492f4a55a7e2c934158b6] netfilter: xt_TCPOPTSTRIP: fix possible mangling beyond packet boundary [bc6bcb59dd7c184d229f9e86d08aa56059938a4c] Paolo Bonzini (1): KVM: SVM: obey guest PAT [15038e14724799b8c205beb5f20f9e54896013c3] Phil Oester (2): netfilter: xt_TCPMSS: Fix missing fragmentation handling [b396966c4688522863572927cb30aa874b3ec504] netfilter: xt_TCPMSS: correct return value in tcpmss_mangle_packet [1205e1fa615805c9efa97303b552cf445965752a] Rusty Russell (1): x86/smp: Don't ever patch back to UP if we unplug cpus [816afe4ff98ee10b1d30fd66361be132a0a5cee6] Sean Young (1): media: rc: check for integer overflow [3e45067f94bbd61dec0619b1c32744eb0de480c8] Shuah Khan (4): usbip: fix stub_rx: get_pipe() to validate endpoint number [635f545a7e8be7596b9b2b6a43cab6bbd5a88e43] usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input [c6688ef9f29762e65bce325ef4acd6c675806366] usbip: fix stub_send_ret_submit() vulnerability to null transfer_buffer [be6123df1ea8f01ee2f896a16c2b7be3e4557a5a] usbip: prevent vhci_hcd driver from leaking a socket pointer address [2f2d0088eb93db5c649d2a5e34a3800a8a935fc5] Stanislaw Gruszka (1): rt2x00usb: mark device removed when get ENOENT usb error [bfa62a52cad93686bb8d8171ea5288813248a7c6] Takashi Iwai (6): ALSA: seq: Make ioctls race-free [b3defb791b26ea0683a93a4f49c77ec45ec96f10] ALSA: timer: Remove kernel warning at compat ioctl error paths [3d4e8303f2c747c8540a0a0126d0151514f6468b] ALSA: usb-audio: Add sanity checks in v2 clock parsers [0a62d6c966956d77397c32836a5bbfe3af786fc1] ALSA: usb-audio: Add sanity checks to FE parser [d937cd6790a2bef2d07b500487646bd794c039bb] ALSA: usb-audio: Fix potential out-of-bound access at parsing SU [f658f17b5e0e339935dca23e77e0f3cad591926b] ALSA: usb-audio: Fix potential zero-division at parsing FU [8428a8ebde2db1e988e41a58497a28beb7ce1705] Tom Parkin (3): l2tp: add session reorder queue purge function to core [48f72f92b31431c40279b0fba6c5588e07e67d95] l2tp: purge session reorder queue on delete [4c6e2fd35460208596fa099ee0750a4b0438aa5c] l2tp: push all ppp pseudowire shutdown through .release handler [cf2f5c886a209377daefd5d2ba0bcd49c3887813] Tuomas Tynkkynen (2): fs/9p: Compare qid.path in v9fs_test_inode [8ee031631546cf2f7859cc69593bd60bbdd70b46] net/9p: Switch to wait_event_killable() [9523feac272ccad2ad8186ba4fcc89103754de52] Vasily Gorbik (1): s390/disassembler: increase show_code buffer size [b192571d1ae375e0bbe0aa3ccfa1a3c3704454b9] Vijendar Mukunda (1): ALSA: hda: Add Raven PCI ID [9ceace3c9c18c67676e75141032a65a8e01f9a7a] Waiman Long (1): blktrace: Fix potential deadlock between delete & sysfs ops [5acb3cc2c2e9d3020a4fee43763c6463767f1572] Younger Liu (1): ocfs2: fix issue that ocfs2_setattr() does not deal with new_i_size==i_size [d62e74be1270c89fbaf7aada8218bfdf62d00a58] Zhou Chengming (1): kprobes, x86/alternatives: Use text_mutex to protect smp_alt_modules [e846d13958066828a9483d862cc8370a72fadbb6] Documentation/kernel-parameters.txt | 3 - Makefile | 4 +- arch/s390/kernel/dis.c | 4 +- arch/x86/include/asm/alternative.h | 4 +- arch/x86/kernel/alternative.c | 129 +++------- arch/x86/kernel/smpboot.c | 20 +- arch/x86/kvm/svm.c | 7 + arch/x86/kvm/vmx.c | 4 + arch/x86/kvm/x86.c | 5 +- arch/x86/kvm/x86.h | 2 + arch/x86/lib/x86-opcode-map.txt | 2 +- arch/x86/mm/kaiser.c | 5 +- arch/x86/xen/smp.c | 6 +- block/blk-core.c | 3 + drivers/char/tpm/tpm.c | 6 + drivers/infiniband/hw/mlx4/qp.c | 2 +- drivers/infiniband/ulp/srp/ib_srp.c | 23 +- drivers/input/misc/adxl34x.c | 2 +- drivers/md/dm-bufio.c | 15 +- drivers/md/dm-table.c | 32 ++- drivers/md/dm.c | 12 +- drivers/media/rc/ir-lirc-codec.c | 9 +- drivers/media/video/cx231xx/cx231xx-cards.c | 3 +- drivers/media/video/omap/omap_vout.c | 3 +- drivers/mtd/nand/nand_base.c | 9 +- drivers/net/wireless/rt2x00/rt2x00usb.c | 6 +- drivers/pci/pcie/aer/aerdrv_core.c | 9 +- drivers/rtc/interface.c | 16 +- drivers/scsi/bfa/bfad_debugfs.c | 5 +- drivers/staging/media/as102/as102_fw.c | 28 ++- drivers/staging/usbip/stub_rx.c | 58 +++-- drivers/staging/usbip/stub_tx.c | 7 + drivers/staging/usbip/usbip_common.h | 1 + .../staging/usbip/userspace/libsrc/usbip_common.c | 2 +- .../staging/usbip/userspace/libsrc/vhci_driver.c | 8 +- drivers/staging/usbip/vhci_hcd.c | 39 --- drivers/staging/usbip/vhci_sysfs.c | 20 +- drivers/usb/core/devio.c | 14 ++ drivers/usb/core/quirks.c | 3 + drivers/usb/serial/garmin_gps.c | 22 +- drivers/video/udlfb.c | 10 +- fs/9p/vfs_inode.c | 3 + fs/9p/vfs_inode_dotl.c | 3 + fs/autofs4/waitq.c | 45 +++- fs/coda/upcall.c | 3 +- fs/ecryptfs/messaging.c | 8 +- fs/isofs/isofs.h | 2 +- fs/isofs/rock.h | 2 +- fs/isofs/util.c | 2 +- fs/nfs/nfs4proc.c | 18 +- fs/nilfs2/segment.c | 6 +- fs/ocfs2/alloc.c | 2 +- fs/ocfs2/file.c | 18 +- include/linux/blkdev.h | 1 + include/linux/usb/ch9.h | 19 ++ include/net/sctp/sctp.h | 2 + include/net/sctp/structs.h | 8 +- kernel/cpu.c | 11 - kernel/extable.c | 2 + kernel/trace/blktrace.c | 76 ++++-- net/9p/client.c | 3 +- net/9p/trans_virtio.c | 13 +- net/l2tp/l2tp_core.c | 42 ++-- net/l2tp/l2tp_core.h | 3 + net/l2tp/l2tp_eth.c | 96 +++++-- net/l2tp/l2tp_ppp.c | 276 ++++++++++++--------- net/netfilter/xt_TCPMSS.c | 43 ++-- net/netfilter/xt_TCPOPTSTRIP.c | 19 +- net/rds/rdma.c | 4 + net/sctp/ipv6.c | 160 ++++++------ net/sctp/protocol.c | 12 +- net/sctp/socket.c | 33 ++- net/sctp/transport.c | 4 +- net/sctp/ulpevent.c | 2 +- sound/core/seq/seq_clientmgr.c | 10 +- sound/core/seq/seq_clientmgr.h | 1 + sound/core/timer_compat.c | 12 +- sound/pci/hda/hda_intel.c | 3 + sound/usb/clock.c | 9 +- sound/usb/mixer.c | 19 +- 80 files changed, 916 insertions(+), 641 deletions(-) -- Ben Hutchings Sturgeon's Law: Ninety percent of everything is crap.

7 years, 4 months

4
82
0 0

[Linux-stable-mirror] [PATCH -mm -v3] mm, swap, frontswap: Fix THP swap if frontswap enabled

by Huang, Ying

From: Huang Ying <huang.ying.caritas(a)gmail.com> It was reported by Sergey Senozhatsky that if THP (Transparent Huge Page) and frontswap (via zswap) are both enabled, when memory goes low so that swap is triggered, segfault and memory corruption will occur in random user space applications as follow, kernel: urxvt[338]: segfault at 20 ip 00007fc08889ae0d sp 00007ffc73a7fc40 error 6 in libc-2.26.so[7fc08881a000+1ae000] #0 0x00007fc08889ae0d _int_malloc (libc.so.6) #1 0x00007fc08889c2f3 malloc (libc.so.6) #2 0x0000560e6004bff7 _Z14rxvt_wcstoutf8PKwi (urxvt) #3 0x0000560e6005e75c n/a (urxvt) #4 0x0000560e6007d9f1 _ZN16rxvt_perl_interp6invokeEP9rxvt_term9hook_typez (urxvt) #5 0x0000560e6003d988 _ZN9rxvt_term9cmd_parseEv (urxvt) #6 0x0000560e60042804 _ZN9rxvt_term6pty_cbERN2ev2ioEi (urxvt) #7 0x0000560e6005c10f _Z17ev_invoke_pendingv (urxvt) #8 0x0000560e6005cb55 ev_run (urxvt) #9 0x0000560e6003b9b9 main (urxvt) #10 0x00007fc08883af4a __libc_start_main (libc.so.6) #11 0x0000560e6003f9da _start (urxvt) After bisection, it was found the first bad commit is bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out"). The root cause is as follow. When the pages are written to swap device during swapping out in swap_writepage(), zswap (fontswap) is tried to compress the pages instead to improve the performance. But zswap (frontswap) will treat THP as normal page, so only the head page is saved. After swapping in, tail pages will not be restored to its original contents, so cause the memory corruption in the applications. This is fixed via rejecting to save page in frontswap store functions if the page is a THP. So that the THP will be swapped out to swap device. Another choice is to split THP if frontswap is enabled. But it is found that the frontswap enabling isn't flexible. For example, if CONFIG_ZSWAP=y (cannot be module), frontswap will be enabled even if zswap itself isn't enabled. Frontswap has multiple backends, to make it easy for one backend to enable THP support, the THP checking is put in backend frontswap store functions instead of the general interfaces. Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Reported-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Tested-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Suggested-by: Minchan Kim <minchan(a)kernel.org> # put THP checking in backend Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Shaohua Li <shli(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: stable(a)vger.kernel.org # 4.14 Changelog: v3: - Fix via checking THP in frontswap backend as suggested by Minchan. v2: - Move frontswap check into swapfile.c to avoid to make vmscan.c depends on frontswap as suggested by Minchan. --- drivers/xen/tmem.c | 4 ++++ mm/zswap.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index bf13d1ec51f3..04e7b3b29bac 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -284,6 +284,10 @@ static int tmem_frontswap_store(unsigned type, pgoff_t offset, int pool = tmem_frontswap_poolid; int ret; + /* THP isn't supported */ + if (PageTransHuge(page)) + return -1; + if (pool < 0) return -1; if (ind64 != ind) diff --git a/mm/zswap.c b/mm/zswap.c index c004aa4fd3f4..61a5c41972db 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1007,6 +1007,12 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, u8 *src, *dst; struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) }; + /* THP isn't supported */ + if (PageTransHuge(page)) { + ret = -EINVAL; + goto reject; + } + if (!zswap_enabled || !tree) { ret = -ENODEV; goto reject; -- 2.15.1

7 years, 4 months

3
2
0 0

[Linux-stable-mirror] [PATCH v2] extcon: int3496: process id-pin first so that we start with the right status

by Hans de Goede

Some other drivers may be waiting for our extcon to show-up (exiting their probe methods with -EPROBE_DEFER until we show up). These drivers will typically get the cable state directly after getting the extcon, this commit changes the int3496 code to process the id-pin before registering the extcon, so that other drivers see the correct state right away. Fixes: 2f556bdb9f2e ("extcon: int3496: Add Intel INT3496 ACPI ... driver") Cc: stable(a)vger.kernel.org Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> --- drivers/extcon/extcon-intel-int3496.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c index c8691b5a9cb0..b23ee9d993a3 100644 --- a/drivers/extcon/extcon-intel-int3496.c +++ b/drivers/extcon/extcon-intel-int3496.c @@ -131,6 +131,10 @@ static int int3496_probe(struct platform_device *pdev) if (IS_ERR(data->gpio_usb_mux)) dev_info(dev, "can't request USB MUX GPIO\n"); + /* process id-pin first so that we start with the right status */ + queue_delayed_work(system_wq, &data->work, 0); + flush_delayed_work(&data->work); + /* register extcon device */ data->edev = devm_extcon_dev_allocate(dev, int3496_cable); if (IS_ERR(data->edev)) @@ -153,9 +157,6 @@ static int int3496_probe(struct platform_device *pdev) return ret; } - /* queue initial processing of id-pin */ - queue_delayed_work(system_wq, &data->work, 0); - platform_set_drvdata(pdev, data); return 0; -- 2.14.3

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] [PATCH 3.16 000/136] 3.16.54-rc1 review

by Ben Hutchings

This is the start of the stable review cycle for the 3.16.54 release. There are 136 patches in this series, which will be posted as responses to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Tue Feb 13 12:00:00 UTC 2018. Anything received after that time might be too late. All the patches have also been committed to the linux-3.16.y-rc branch of https://git.kernel.org/pub/scm/linux/kernel/git/bwh/linux-stable-rc.git . A shortlog and diffstat can be found below. Ben. ------------- Alan Stern (1): USB: usbfs: compute urb->actual_length for isochronous [2ef47001b3ee3ded579b7532ebdcf8680e4d8c54] Alex Chen (1): ocfs2: should wait dio before inode lock in ocfs2_setattr() [28f5a8a7c033cbf3e32277f4cc9c6afd74f05300] Alexander Popov (1): usbip: fix NULL pointer dereference on errors [8c7003a3b4b4afd3734cdcc39217ef22d78a4a16] Alexander Potapenko (1): sctp: fully initialize the IPv6 address in sctp_v6_to_addr() [15339e441ec46fbc3bf3486bb1ae4845b0f1bb8d] Alexander Steffen (1): tpm-dev-common: Reject too short writes [ee70bc1e7b63ac8023c9ff9475d8741e397316e7] Alexandre Belloni (1): rtc: set the alarm to the next expiring timer [74717b28cb32e1ad3c1042cafd76b264c8c0f68d] Andreas Rohner (1): nilfs2: fix race condition that causes file system corruption [31ccb1f7ba3cfe29631587d451cf5bb8ab593550] Andrew F. Davis (1): ASoC: cs42l56: Fix reset GPIO name in example DT binding [8adc430603d67e76a0f8491df21654f691acda62] Andrey Konovalov (1): p54: don't unregister leds when they are not initialized [fc09785de0a364427a5df63d703bae9a306ed116] Andy Lutomirski (4): x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader [6b078f5de7fc0851af4102493c7b5bb07e49c4cb] x86, vdso: Move the vvar area before the vdso text [e6577a7ce99a506b587bcd1d2cd803cb45119557] x86/vdso: Get pvclock data from the vvar VMA instead of the fixmap [dac16fba6fc590fa7239676b35ed75dae4c4cd2b] x86/vdso: Remove pvclock fixmap machinery [cc1e24fdb064d3126a494716f22ad4fc39306742] Anna Schumaker (1): NFS: Avoid RCU usage in tracepoints [3944369db701f075092357b511fd9f5755771585] Arnd Bergmann (4): Input: adxl34x - do not treat FIFO_MODE() as boolean [1dbc080c9ef6bcfba652ef0d6ae919b8c7c85a1d] drm: gma500: fix logic error [67a3b63a54cbe18944191f43d644686731cf30c7] elf_fdpic: fix unused variable warning [11e3e8d6d9274bf630859b4c47bc4e4d76f289db] isofs: fix timestamps beyond 2027 [34be4dbf87fc3e474a842305394534216d428f5d] Bart Van Assche (3): IB/srp: Avoid that a cable pull can trigger a kernel crash [8a0d18c62121d3c554a83eb96e2752861d84d937] IB/srpt: Do not accept invalid initiator port names [c70ca38960399a63d5c048b7b700612ea321d17e] target/iscsi: Fix iSCSI task reassignment handling [59b6986dbfcdab96a971f9663221849de79a7556] Ben Hutchings (1): usbip: tools: Install all headers needed for libusbip development [c15562c0dcb2c7f26e891923b784cf1926b8c833] Ben Seri (1): Bluetooth: Prevent stack info leak from the EFS element. [06e7e776ca4d36547e503279aeff996cbb292c16] Bernhard Rosenkraenzer (1): USB: Add delay-init quirk for Corsair K70 LUX keyboards [a0fea6027f19c62727315aba1a7fae75a9caa842] Boshi Wang (1): ima: fix hash algorithm initialization [ebe7c0a7be92bbd34c6ff5b55810546a0ee05bee] Brent Taylor (1): mtd: nand: Fix writing mtdoops to nand flash. [30863e38ebeb500a31cecee8096fb5002677dd9b] Brian King (6): i40e: Use smp_rmb rather than read_barrier_depends [52c6912fde0133981ee50ba08808f257829c4c93] i40evf: Use smp_rmb rather than read_barrier_depends [f72271e2a0ae4277d53c4053f5eed8bb346ba38a] igb: Use smp_rmb rather than read_barrier_depends [c4cb99185b4cc96c0a1c70104dc21ae14d7e7f28] igbvf: Use smp_rmb rather than read_barrier_depends [1e1f9ca546556e508d021545861f6b5fc75a95fe] ixgbe: Fix skb list corruption on Power systems [0a9a17e3bb4564caf4bfe2a6783ae1287667d188] ixgbevf: Use smp_rmb rather than read_barrier_depends [ae0c585d93dfaf923d2c7eb44b2c3ab92854ea9b] Christian König (1): drm/ttm: once more fix ttm_buffer_object_transfer [4d98e5ee6084f6d7bc578c5d5f86de7156aaa4cb] Chuck Lever (1): nfs: Fix ugly referral attributes [c05cefcc72416a37eba5a2b35f0704ed758a9145] Colin Ian King (3): btrfs: avoid null pointer dereference on fs_info when calling btrfs_crit [3993b112dac968612b0b213ed59cb30f50b0015b] rtc: interface: ignore expired timers when enqueuing new timers [2b2f5ff00f63847d95adad6289bd8b05f5983dd5] staging: rtl8188eu: avoid a null dereference on pmlmepriv [123c0aab0050cd0e07ce18e453389fbbb0a5a425] Coly Li (2): bcache: check ca->alloc_thread initialized before wake up it [91af8300d9c1d7c6b6a2fd754109e08d4798b8d8] bcache: only permit to recovery read error when cache device is clean [d59b23795933678c9638fd20c942d2b4f3cd6185] Corey Minyard (1): ipmi: fix unsigned long underflow [392a17b10ec4320d3c0e96e2a23ebaad1123b989] Dan Carpenter (2): eCryptfs: use after free in ecryptfs_release_messaging() [db86be3a12d0b6e5c5b51c2ab2a48f06329cb590] scsi: bfa: integer overflow in debugfs [3e351275655d3c84dc28abf170def9786db5176d] Dongho Sim (1): f2fs: remove redundant lines in allocate_data_block [33be828ada7274ebcade2001f16e5b4e33a4636e] Doug Berger (1): net: bcmgenet: enable loopback during UniMAC sw_reset [28c2d1a7a0bfdf3617800d2beae1c67983c03d15] Douglas Fischer (1): USB: serial: qcserial: add pid/vid for Sierra Wireless EM7355 fw update [771394a54148f18926ca86414e51c69eda27d0cd] Eric Biggers (1): dm bufio: fix integer overflow when limiting maximum cache size [74d4108d9e681dbbe4a2940ed8fdff1f6868184c] Eric Dumazet (1): netfilter: xt_TCPMSS: add more sanity tests on tcph->doff [2638fd0f92d4397884fd991d8f4925cb3f081901] Eric W. Biederman (1): net/sctp: Always set scope_id in sctp_inet6_skb_msgname [7c8a61d9ee1df0fb4747879fa67a99614eb62fec] Gabriele Paoloni (1): PCI/AER: Report non-fatal errors only to the affected endpoint [86acc790717fb60fb51ea3095084e331d8711c74] Guenter Roeck (1): kaiser: Set _PAGE_NX only if supported [61e9b3671007a5da8127955a1a3bda7e0d5f42e8] Guillaume Nault (5): l2tp: don't register sessions in l2tp_session_create() [3953ae7b218df4d1e544b98a393666f9ae58a78c] l2tp: ensure sessions are freed after their PPPOL2TP socket [cdd10c9627496ad25c87ce6394e29752253c69d3] l2tp: initialise PPP sessions before registering them [f98be6c6359e7e4a61aaefb9964c1db31cb9ec0c] l2tp: initialise l2tp_eth sessions before registering them [ee28de6bbd78c2e18111a0aef43ea746f28d2073] l2tp: protect sock pointer of struct pppol2tp_session with RCU [ee40fb2e1eb5bc0ddd3f2f83c6e39a454ef5a741] Heiko Carstens (2): s390/runtime instrumention: fix possible memory corruption [d6e646ad7cfa7034d280459b2b2546288f247144] s390: fix transactional execution control register handling [a1c5befc1c24eb9c1ee83f711e0f21ee79cbb556] Hou Tao (1): dm: fix race between dm_get_from_kobject() and __dm_destroy() [b9a41d21dceadf8104812626ef85dc56ee8a60ed] Ingo Molnar (1): x86/platform/uv: Include clocksource.h for clocksource_touch_watchdog() [d51953b0873358d13b189996e6976dfa12a9b59d] Jaegeuk Kim (1): f2fs: expose some sectors to user in inline data or dentry case [5b4267d195dd887c4412e34b5a7365baa741b679] James Morse (2): ACPI / APEI: Remove ghes_ioremap_area [520e18a5080d2c444a03280d99c8a35cb667d321] ACPI / APEI: Replace ioremap_page_range() with fixmap [4f89fa286f6729312e227e7c2d764e8e7b9d340e] Jan Harkes (1): coda: fix 'kernel memory exposure attempt' in fsync [d337b66a4c52c7b04eec661d86c2ef6e168965a2] Jani Nikula (1): drm/i915/bios: parse DDI ports also for CHV for HDMI DDC pin and DP AUX channel [348e4058ebf53904e817eec7a1b25327143c2ed2] Jason Gunthorpe (1): sctp: Fixup v4mapped behaviour to comply with Sock API [299ee123e19889d511092347f5fc14db0f10e3a6] Jens Axboe (1): blktrace: fix unlocked access to init/start-stop/teardown [1f2cac107c591c24b60b115d6050adc213d10fc0] Joerg Roedel (1): iommu/vt-d: Don't register bus-notifier under dmar_global_lock [ec154bf56b276a0bb36079a5d22a267b5f417801] Johan Hovold (5): NFC: fix device-allocation error return [c45e3e4c5b134b081e8af362109905427967eb19] USB: serial: garmin_gps: fix I/O after failed probe and remove [19a565d9af6e0d828bd0d521d3bafd5017f4ce52] USB: serial: garmin_gps: fix memory leak on probe errors [74d471b598444b7f2d964930f7234779c80960a0] USB: serial: metro-usb: stop I/O after failed open [2339536d229df25c71c0900fc619289229bfecf6] clk: ti: dra7-atl-clock: fix child-node lookups [33ec6dbc5a02677509d97fe36cd2105753f0f0ea] Johannes Berg (1): nl80211: don't expose wdev->ssid for most interfaces [44905265bc155e0237c76c25bf5ddf740d85a8f2] John David Anglin (1): parisc: Fix validity check of pointer size argument in new CAS implementation [05f016d2ca7a4fab99d5d5472168506ddf95e74f] John Johansen (1): apparmor: ensure that undecidable profile attachments fail [844b8292b6311ecd30ae63db1471edb26e01d895] Joshua Watt (1): NFS: Fix typo in nomigration mount option [f02fee227e5f21981152850744a6084ff3fa94ee] Juerg Haefliger (1): Revert "x86: kvmclock: Disable use from vDSO if KPTI is enabled" [not upstream; reverts 3.16-specific change] Ladi Prosek (1): KVM: nVMX: set IDTR and GDTR limits when loading L1 host state [21f2d551183847bc7fbe8d866151d00cdad18752] Ladislav Michl (1): video: udlfb: Fix read EDID timeout [c98769475575c8a585f5b3952f4b5f90266f699b] Lepton Wu (1): kaiser: Set _PAGE_NX only if supported [not upstream; specific to KAISER backport] Maciej W. Rozycki (1): MIPS: Fix an n32 core file generation regset support regression [547da673173de51f73887377eb275304775064ad] Majd Dibbiny (1): IB/mlx5: Assign send CQ and recv CQ of UMR QP [31fde034a8bd964a5c7c1a5663fc87a913158db2] Manasi Navare (1): drm/i915/edp: Get the Panel Power Off timestamp after panel is off [cbacf02e7796fea02e5c6e46c90ed7cbe9e6f2c0] Mark Bloch (1): IB/mlx4: Increase maximal message size under UD QP [5f22a1d87c5315a98981ecf93cd8de226cffe6ca] Mark Rutland (1): arm64: vdso: fix clock_getres for 4GiB-aligned res [c80ed088a519da53f27b798a69748eaabc66aadf] Markus Elfring (2): media: omap_vout: Fix a possible null pointer dereference in omap_vout_open() [bfba2b3e21b9426c0f9aca00f3cad8631b2da170] platform/x86: sony-laptop: Fix error handling in sony_nc_setup_rfkill() [f6c8a317ab208aee223776327c06f23342492d54] Masami Hiramatsu (1): x86/decoder: Add new TEST instruction pattern [12a78d43de767eaf8fb272facb7a7b6f2dc6a9df] Mauro Carvalho Chehab (1): [media] cx231xx: Fix the max number of interfaces [139d28826b8e2bc7a9232fde0d2f14812914f501] Michał Mirosław (1): clk: tegra: Fix cclk_lp divisor register [54eff2264d3e9fd7e3987de1d7eba1d3581c631e] Mike Snitzer (1): dm: discard support requires all targets in a table support discards [8a74d29d541cd86569139c6f3f44b2d210458071] Mohamed Ghannam (2): RDS: Heap OOB write in rds_message_alloc_sgs() [c095508770aebf1b9218e77026e48345d719b17c] RDS: null pointer dereference in rds_atomic_free_op [7d11f77f84b27cef452cee332f4e469503084737] Nadav Amit (2): KVM: vmx: Inject #GP on invalid PAT CR [4566654bb9be9e8864df417bb72ceee5136b6a6a] staging: lustre: ptlrpc: kfree used instead of kvfree [c3eec59659cf25916647d2178c541302bb4822ad] Nathan Lynch (1): arm64: vdso: minor ABI fix for clock_getres [e1b6b6ce55a0a25c8aa8af019095253b2133a41a] NeilBrown (2): autofs: don't fail mount for transient error [ecc0c469f27765ed1e2b967be0aa17cee1a60b76] autofs: fix careless error in recent commit [302ec300ef8a545a7fc7f667e5fd743b091c2eeb] Nicholas Bellinger (3): iscsi-target: Fix non-immediate TMR reference leak [3fc9fb13a4b2576aeab86c62fd64eb29ab68659c] iscsi-target: Make TASK_REASSIGN use proper se_cmd->cmd_kref [ae072726f6109bb1c94841d6fb3a82dde298ea85] target: Avoid early CMD_T_PRE_EXECUTE failures during ABORT_TASK [1c21a48055a67ceb693e9c2587824a8de60a217c] Paolo Bonzini (2): KVM: SVM: obey guest PAT [15038e14724799b8c205beb5f20f9e54896013c3] x86: pvclock: Really remove the sched notifier for cross-cpu migrations [73459e2a1ada09a68c02cc5b73f3116fc8194b3d] Peter Ujfalusi (1): clk: ti: dra7-atl-clock: Fix of_node reference counting [660e1551939931657808d47838a3f443c0e83fd0] Peter Zijlstra (1): lib/int_sqrt: optimize small argument [3f3295709edea6268ff1609855f498035286af73] Philip Derrin (1): ARM: 8721/1: mm: dump: check hardware RO bit for LPAE [3b0c0c922ff4be275a8beb87ce5657d16f355b54] Radu Alexe (1): crypto: caam - fix incorrect define [cc2f8ab5334a736fa0e775cfccf06c1e268667f0] Roger Quadros (1): mtd: nand: omap2: Fix subpage write [739c64414f01748a36e7d82c8e0611dea94412bd] Roman Kapl (1): drm/radeon: fix atombios on big endian [4f626a4ac8f57ddabf06d03870adab91e463217f] Sean Young (1): media: rc: check for integer overflow [3e45067f94bbd61dec0619b1c32744eb0de480c8] Shriya (1): powerpc/powernv/cpufreq: Fix the frequency read by /proc/cpuinfo [cd77b5ce208c153260ed7882d8910f2395bfaabd] Shuah Khan (4): usbip: fix stub_rx: get_pipe() to validate endpoint number [635f545a7e8be7596b9b2b6a43cab6bbd5a88e43] usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input [c6688ef9f29762e65bce325ef4acd6c675806366] usbip: fix stub_send_ret_submit() vulnerability to null transfer_buffer [be6123df1ea8f01ee2f896a16c2b7be3e4557a5a] usbip: prevent vhci_hcd driver from leaking a socket pointer address [2f2d0088eb93db5c649d2a5e34a3800a8a935fc5] Stanislaw Gruszka (1): rt2x00usb: mark device removed when get ENOENT usb error [bfa62a52cad93686bb8d8171ea5288813248a7c6] Takashi Iwai (6): ALSA: seq: Make ioctls race-free [b3defb791b26ea0683a93a4f49c77ec45ec96f10] ALSA: timer: Remove kernel warning at compat ioctl error paths [3d4e8303f2c747c8540a0a0126d0151514f6468b] ALSA: usb-audio: Add sanity checks in v2 clock parsers [0a62d6c966956d77397c32836a5bbfe3af786fc1] ALSA: usb-audio: Add sanity checks to FE parser [d937cd6790a2bef2d07b500487646bd794c039bb] ALSA: usb-audio: Fix potential out-of-bound access at parsing SU [f658f17b5e0e339935dca23e77e0f3cad591926b] ALSA: usb-audio: Fix potential zero-division at parsing FU [8428a8ebde2db1e988e41a58497a28beb7ce1705] Theodore Ts'o (1): ext4: fix interaction between i_size, fallocate, and delalloc after a crash [51e3ae81ec58e95f10a98ef3dd6d7bce5d8e35a2] Tuomas Tynkkynen (2): fs/9p: Compare qid.path in v9fs_test_inode [8ee031631546cf2f7859cc69593bd60bbdd70b46] net/9p: Switch to wait_event_killable() [9523feac272ccad2ad8186ba4fcc89103754de52] Tyrel Datwyler (1): powerpc/pseries/vio: Dispose of virq mapping on vdevice unregister [b8f89fea599d91e674497aad572613eb63181f31] Vasily Gorbik (1): s390/disassembler: increase show_code buffer size [b192571d1ae375e0bbe0aa3ccfa1a3c3704454b9] Vijendar Mukunda (1): ALSA: hda: Add Raven PCI ID [9ceace3c9c18c67676e75141032a65a8e01f9a7a] Viktor Slavkovic (1): staging: android: ashmem: fix a race condition in ASHMEM_SET_SIZE ioctl [443064cb0b1fb4569fe0a71209da7625129fb760] Ville Syrjälä (1): drm/i915: Read timings from the correct transcoder in intel_crtc_mode_get() [e30a154b5262b967b133b06ac40777e651045898] Waiman Long (1): blktrace: Fix potential deadlock between delete & sysfs ops [5acb3cc2c2e9d3020a4fee43763c6463767f1572] William A. Kennington III (1): powerpc/opal: Fix EBUSY bug in acquiring tokens [71e24d7731a2903b1ae2bba2b2971c654d9c2aa6] Xin Long (2): route: also update fnhe_genid when updating a route cache [cebe84c6190d741045a322f5343f717139993c08] route: update fnhe_expires for redirect when the fnhe exists [e39d5246111399dbc6e11cd39fd8580191b86c47] Yunlong Song (1): Revert "f2fs: handle dirty segments inside refresh_sit_entry" [65f1b80b33378501ea552ef085e9c31739af356c] Zhou Chengming (1): kprobes, x86/alternatives: Use text_mutex to protect smp_alt_modules [e846d13958066828a9483d862cc8370a72fadbb6] .../devicetree/bindings/sound/cs42l56.txt | 2 +- Makefile | 4 +- arch/arm/mm/dump.c | 4 +- arch/arm64/kernel/vdso/gettimeofday.S | 3 +- arch/mips/kernel/ptrace.c | 17 ++ arch/parisc/kernel/syscall.S | 6 +- arch/powerpc/kernel/vio.c | 2 + arch/powerpc/platforms/powernv/opal-async.c | 6 +- arch/powerpc/platforms/powernv/setup.c | 2 +- arch/s390/include/asm/switch_to.h | 2 +- arch/s390/kernel/dis.c | 4 +- arch/s390/kernel/early.c | 4 +- arch/s390/kernel/process.c | 1 + arch/s390/kernel/runtime_instr.c | 4 +- arch/x86/include/asm/fixmap.h | 11 +- arch/x86/include/asm/pvclock.h | 15 +- arch/x86/include/asm/vdso.h | 19 +- arch/x86/kernel/alternative.c | 26 +- arch/x86/kernel/kvmclock.c | 16 +- arch/x86/kernel/pvclock.c | 68 ----- arch/x86/kvm/svm.c | 7 + arch/x86/kvm/vmx.c | 4 + arch/x86/kvm/x86.c | 5 +- arch/x86/kvm/x86.h | 2 + arch/x86/lib/x86-opcode-map.txt | 2 +- arch/x86/mm/kaiser.c | 7 +- arch/x86/platform/uv/uv_nmi.c | 1 + arch/x86/vdso/vclock_gettime.c | 103 ++++--- arch/x86/vdso/vdso-layout.lds.S | 45 ++- arch/x86/vdso/vdso2c.c | 15 +- arch/x86/vdso/vdso2c.h | 25 +- arch/x86/vdso/vma.c | 34 ++- block/blk-core.c | 3 + drivers/acpi/apei/ghes.c | 85 +----- drivers/char/ipmi/ipmi_msghandler.c | 10 +- drivers/char/tpm/tpm-dev.c | 6 + drivers/clk/tegra/clk-tegra30.c | 2 +- drivers/clk/ti/clk-dra7-atl.c | 3 +- drivers/crypto/caam/desc.h | 2 +- drivers/gpu/drm/gma500/mdfld_intel_display.c | 2 +- drivers/gpu/drm/i915/intel_bios.c | 2 +- drivers/gpu/drm/i915/intel_display.c | 14 +- drivers/gpu/drm/i915/intel_dp.c | 2 +- drivers/gpu/drm/radeon/atombios_dp.c | 38 ++- drivers/gpu/drm/ttm/ttm_bo_util.c | 1 + drivers/infiniband/hw/mlx4/qp.c | 2 +- drivers/infiniband/hw/mlx5/main.c | 2 + drivers/infiniband/ulp/srp/ib_srp.c | 23 +- drivers/infiniband/ulp/srpt/ib_srpt.c | 9 +- drivers/input/misc/adxl34x.c | 2 +- drivers/iommu/dmar.c | 7 +- drivers/iommu/intel-iommu.c | 10 + drivers/md/bcache/alloc.c | 3 +- drivers/md/bcache/request.c | 10 +- drivers/md/dm-bufio.c | 15 +- drivers/md/dm-table.c | 32 +- drivers/md/dm.c | 12 +- drivers/media/platform/omap/omap_vout.c | 3 +- drivers/media/rc/ir-lirc-codec.c | 9 +- drivers/media/usb/cx231xx/cx231xx-cards.c | 3 +- drivers/mtd/nand/nand_base.c | 9 +- drivers/mtd/nand/omap2.c | 340 ++++++++++++++------- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 56 +--- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igbvf/netdev.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/wireless/p54/main.c | 7 +- drivers/net/wireless/rt2x00/rt2x00usb.c | 6 +- drivers/pci/pcie/aer/aerdrv_core.c | 9 +- drivers/platform/x86/sony-laptop.c | 14 +- drivers/rtc/interface.c | 16 +- drivers/scsi/bfa/bfad_debugfs.c | 5 +- drivers/staging/android/ashmem.c | 2 + drivers/staging/lustre/lustre/ptlrpc/sec.c | 2 +- drivers/staging/rtl8188eu/core/rtw_mlme.c | 3 +- drivers/staging/usbip/stub.h | 1 - drivers/staging/usbip/stub_dev.c | 4 +- drivers/staging/usbip/stub_rx.c | 66 ++-- drivers/staging/usbip/stub_tx.c | 13 +- drivers/staging/usbip/usbip_common.h | 1 + drivers/staging/usbip/userspace/Makefile.am | 3 +- .../staging/usbip/userspace/libsrc/vhci_driver.c | 8 +- drivers/staging/usbip/vhci_sysfs.c | 20 +- drivers/target/iscsi/iscsi_target.c | 49 ++- drivers/target/target_core_tmr.c | 10 + drivers/target/target_core_transport.c | 2 + drivers/usb/core/devio.c | 14 + drivers/usb/core/quirks.c | 3 + drivers/usb/serial/garmin_gps.c | 22 +- drivers/usb/serial/metro-usb.c | 11 +- drivers/usb/serial/qcserial.c | 1 + drivers/video/fbdev/udlfb.c | 10 +- fs/9p/vfs_inode.c | 3 + fs/9p/vfs_inode_dotl.c | 3 + fs/autofs4/waitq.c | 16 +- fs/binfmt_elf_fdpic.c | 2 + fs/btrfs/super.c | 4 +- fs/coda/upcall.c | 3 +- fs/ecryptfs/messaging.c | 7 +- fs/ext4/extents.c | 6 +- fs/f2fs/file.c | 5 + fs/f2fs/segment.c | 20 +- fs/isofs/isofs.h | 2 +- fs/isofs/rock.h | 2 +- fs/isofs/util.c | 2 +- fs/nfs/nfs4proc.c | 18 +- fs/nfs/nfs4trace.h | 8 +- fs/nfs/super.c | 2 +- fs/nilfs2/segment.c | 6 +- fs/ocfs2/file.c | 9 +- include/linux/blkdev.h | 1 + include/linux/dmar.h | 1 + include/linux/sched.h | 8 - include/net/sctp/sctp.h | 2 + include/net/sctp/structs.h | 8 +- include/target/target_core_base.h | 2 + kernel/extable.c | 2 + kernel/sched/core.c | 15 - kernel/trace/blktrace.c | 76 ++++- lib/int_sqrt.c | 3 + net/9p/client.c | 3 +- net/9p/trans_virtio.c | 13 +- net/bluetooth/l2cap_core.c | 20 +- net/ipv4/route.c | 14 +- net/l2tp/l2tp_core.c | 21 +- net/l2tp/l2tp_core.h | 3 + net/l2tp/l2tp_eth.c | 101 ++++-- net/l2tp/l2tp_ppp.c | 236 ++++++++------ net/netfilter/xt_TCPMSS.c | 6 +- net/nfc/core.c | 2 +- net/rds/rdma.c | 4 + net/sctp/ipv6.c | 160 +++++----- net/sctp/protocol.c | 12 +- net/sctp/socket.c | 33 +- net/sctp/transport.c | 4 +- net/sctp/ulpevent.c | 2 +- net/wireless/nl80211.c | 26 +- security/apparmor/domain.c | 53 +++- security/integrity/ima/ima_main.c | 4 + sound/core/seq/seq_clientmgr.c | 10 +- sound/core/seq/seq_clientmgr.h | 1 + sound/core/timer_compat.c | 12 +- sound/pci/hda/hda_intel.c | 3 + sound/usb/clock.c | 9 +- sound/usb/mixer.c | 19 +- 149 files changed, 1480 insertions(+), 1026 deletions(-) -- Ben Hutchings Sturgeon's Law: Ninety percent of everything is crap.

7 years, 4 months

3
138
0 0

[Linux-stable-mirror] [PATCH] drm/i915/audio: do not set Maud/Naud values manually on KBL

by Jani Nikula

Apparently using the manual Maud/Naud mode does not work on KBL. The details on the failure mode are scarce, except that there's no audio, and there is obviously no idea on the root cause either. It is also unknown whether the failure can be reproduced on newer platforms in some scenarios. The problem was introduced when switching from automatic mode to manual mode in commit 6014ac122ed0 ("drm/i915/audio: set proper N/M in modeset"). Instead of reverting that, disable the feature on KBL as a workaround. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104093 Reported-by: Quanxian Wang <quanxian.wang(a)intel.com> Fixes: 6014ac122ed0 ("drm/i915/audio: set proper N/M in modeset") Cc: <stable(a)vger.kernel.org> # v4.10+ Cc: Keqiao Zhang <keqiao.zhang(a)intel.com> Cc: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Cc: Mengdong Lin <mengdong.lin(a)intel.com> Cc: Libin Yang <libin.yang(a)linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: Quanxian Wang <quanxian.wang(a)intel.com> Cc: Wang Zhijun <zhijunx.wang(a)intel.com> Cc: Cui Yueping <yuepingx.cui(a)intel.com> Cc: Alice Liu <alice.liu(a)intel.com> Cc: intel-gfx(a)lists.freedesktop.org Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> --- UNTESTED. Please provide Tested-by's on the affected KBLs, but *also* on CFL, CNL, etc. --- drivers/gpu/drm/i915/intel_audio.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 522d54fecb53..b7634cff12b6 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -294,12 +294,19 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); enum port port = encoder->port; enum pipe pipe = crtc->pipe; - const struct dp_aud_n_m *nm; + const struct dp_aud_n_m *nm = NULL; int rate; u32 tmp; rate = acomp ? acomp->aud_sample_rate[port] : 0; - nm = audio_config_dp_get_n_m(crtc_state, rate); + + /* + * FIXME: For reasons still unknown, there seem to be issues with the + * manual Maud/Naud mode on KBL. + */ + if (!IS_KABYLAKE(dev_priv)) + nm = audio_config_dp_get_n_m(crtc_state, rate); + if (nm) DRM_DEBUG_KMS("using Maud %u, Naud %u\n", nm->m, nm->n); else -- 2.11.0

7 years, 4 months

3
2
0 0

[Linux-stable-mirror] 4.14.x - KVM guests crashing

by Nikola Ciprich

Hi, not sure whether this is the best list to ask for that, but maybe somebody from -stable interested people has hit similar problem.. if it's not appropriate list to ask/report, please let me know since we started rolling to 4.14.x kernels, we've experienced multiple KVM guest panics (with 4.14 on hosts) We've first hit it with 4.14.12, yesterday I had similar problem with 4.14.16. backtraces can be observed here: http://nik.lbox.cz/download/guest-panic-host-4.14.12.png http://nik.lbox.cz/download/guest-panic-host-4.14.16.png sorry I don't have anything more complete they are a bit different, but there are some similarities (ie double_fault) also important to note, both are from different host systems. after reverting hosts to 4.4, crashes are gone. my question is, did anyone hit similar problem? Is this something know, maybe fixed in 4.14.17? (I'll give 4.14.17 try anyways I suppose) (or latest git?) could it be related to page table isolation enabled hosts? btw hosts are running x86_64 centos 7, guests are either centos 6 or centos 7 If I could provide any further info, let me know BR nik -- ------------------------------------- Ing. Nikola CIPRICH LinuxBox.cz, s.r.o. 28.rijna 168, 709 00 Ostrava tel.: +420 591 166 214 fax: +420 596 621 273 mobil: +420 777 093 799 www.linuxbox.cz mobil servis: +420 737 238 656 email servis: servis(a)linuxbox.cz -------------------------------------

7 years, 4 months

3
3
0 0

[Linux-stable-mirror] + mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3.patch added to -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm, swap, frontswap: fix THP swap if frontswap enabled has been added to the -mm tree. Its filename is mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-swap-frontswap-fix-thp-swap-if-… and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-swap-frontswap-fix-thp-swap-if-… Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm, swap, frontswap: fix THP swap if frontswap enabled It was reported by Sergey Senozhatsky that if THP (Transparent Huge Page) and frontswap (via zswap) are both enabled, when memory goes low so that swap is triggered, segfault and memory corruption will occur in random user space applications as follow, kernel: urxvt[338]: segfault at 20 ip 00007fc08889ae0d sp 00007ffc73a7fc40 error 6 in libc-2.26.so[7fc08881a000+1ae000] #0 0x00007fc08889ae0d _int_malloc (libc.so.6) #1 0x00007fc08889c2f3 malloc (libc.so.6) #2 0x0000560e6004bff7 _Z14rxvt_wcstoutf8PKwi (urxvt) #3 0x0000560e6005e75c n/a (urxvt) #4 0x0000560e6007d9f1 _ZN16rxvt_perl_interp6invokeEP9rxvt_term9hook_typez (urxvt) #5 0x0000560e6003d988 _ZN9rxvt_term9cmd_parseEv (urxvt) #6 0x0000560e60042804 _ZN9rxvt_term6pty_cbERN2ev2ioEi (urxvt) #7 0x0000560e6005c10f _Z17ev_invoke_pendingv (urxvt) #8 0x0000560e6005cb55 ev_run (urxvt) #9 0x0000560e6003b9b9 main (urxvt) #10 0x00007fc08883af4a __libc_start_main (libc.so.6) #11 0x0000560e6003f9da _start (urxvt) After bisection, it was found the first bad commit is bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out"). The root cause is as follows: When the pages are written to swap device during swapping out in swap_writepage(), zswap (fontswap) is tried to compress the pages to improve performance. But zswap (frontswap) will treat THP as a normal page, so only the head page is saved. After swapping in, tail pages will not be restored to their original contents, causing memory corruption in the applications. This is fixed by refusing to save page in the frontswap store functions if the page is a THP. So that the THP will be swapped out to swap device. Another choice is to split THP if frontswap is enabled. But it is found that the frontswap enabling isn't flexible. For example, if CONFIG_ZSWAP=y (cannot be module), frontswap will be enabled even if zswap itself isn't enabled. Frontswap has multiple backends, to make it easy for one backend to enable THP support, the THP checking is put in backend frontswap store functions instead of the general interfaces. Link: http://lkml.kernel.org/r/20180209084947.22749-1-ying.huang@intel.com Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Reported-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Suggested-by: Minchan Kim <minchan(a)kernel.org> [put THP checking in backend] Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Shaohua Li <shli(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: <stable(a)vger.kernel.org> [4.14] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- drivers/xen/tmem.c | 4 ++++ mm/zswap.c | 6 ++++++ 2 files changed, 10 insertions(+) diff -puN drivers/xen/tmem.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3 drivers/xen/tmem.c --- a/drivers/xen/tmem.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3 +++ a/drivers/xen/tmem.c @@ -284,6 +284,10 @@ static int tmem_frontswap_store(unsigned int pool = tmem_frontswap_poolid; int ret; + /* THP isn't supported */ + if (PageTransHuge(page)) + return -1; + if (pool < 0) return -1; if (ind64 != ind) diff -puN mm/zswap.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3 mm/zswap.c --- a/mm/zswap.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3 +++ a/mm/zswap.c @@ -1007,6 +1007,12 @@ static int zswap_frontswap_store(unsigne u8 *src, *dst; struct zswap_header zhdr = { .swpentry = swp_entry(type, offset) }; + /* THP isn't supported */ + if (PageTransHuge(page)) { + ret = -EINVAL; + goto reject; + } + if (!zswap_enabled || !tree) { ret = -ENODEV; goto reject; _ Patches currently in -mm which might be from huang.ying.caritas(a)gmail.com are mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [to-be-updated] mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm, swap, frontswap: Fix THP swap if frontswap enabled has been removed from the -mm tree. Its filename was mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm, swap, frontswap: Fix THP swap if frontswap enabled It was reported by Sergey Senozhatsky that if THP (Transparent Huge Page) and frontswap (via zswap) are both enabled, when memory goes low so that swap is triggered, segfault and memory corruption will occur in random user space applications as follow, kernel: urxvt[338]: segfault at 20 ip 00007fc08889ae0d sp 00007ffc73a7fc40 error 6 in libc-2.26.so[7fc08881a000+1ae000] #0 0x00007fc08889ae0d _int_malloc (libc.so.6) #1 0x00007fc08889c2f3 malloc (libc.so.6) #2 0x0000560e6004bff7 _Z14rxvt_wcstoutf8PKwi (urxvt) #3 0x0000560e6005e75c n/a (urxvt) #4 0x0000560e6007d9f1 _ZN16rxvt_perl_interp6invokeEP9rxvt_term9hook_typez (urxvt) #5 0x0000560e6003d988 _ZN9rxvt_term9cmd_parseEv (urxvt) #6 0x0000560e60042804 _ZN9rxvt_term6pty_cbERN2ev2ioEi (urxvt) #7 0x0000560e6005c10f _Z17ev_invoke_pendingv (urxvt) #8 0x0000560e6005cb55 ev_run (urxvt) #9 0x0000560e6003b9b9 main (urxvt) #10 0x00007fc08883af4a __libc_start_main (libc.so.6) #11 0x0000560e6003f9da _start (urxvt) After bisection, it was found the first bad commit is bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out"). The root cause is as follows: When the pages are written to swap device during swapping out in swap_writepage(), zswap (fontswap) is tried to compress the pages instead to improve the performance. But zswap (frontswap) will treat THP as normal page, so only the head page is saved. After swapping in, tail pages will not be restored to its original contents, so cause the memory corruption in the applications. This is fixed via splitting THP before writing the page to swap device if frontswap is enabled. To deal with the situation where frontswap is enabled at runtime, whether the page is THP is checked before using frontswap during swapping out too. Link: http://lkml.kernel.org/r/20180207070035.30302-1-ying.huang@intel.com Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Reported-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Tested-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Shaohua Li <shli(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: <stable(a)vger.kernel.org> [4.14+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_io.c | 2 +- mm/swapfile.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff -puN mm/page_io.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled mm/page_io.c --- a/mm/page_io.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled +++ a/mm/page_io.c @@ -250,7 +250,7 @@ int swap_writepage(struct page *page, st unlock_page(page); goto out; } - if (frontswap_store(page) == 0) { + if (!PageTransHuge(page) && frontswap_store(page) == 0) { set_page_writeback(page); unlock_page(page); end_page_writeback(page); diff -puN mm/swapfile.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled mm/swapfile.c --- a/mm/swapfile.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled +++ a/mm/swapfile.c @@ -934,6 +934,9 @@ int get_swap_pages(int n_goal, bool clus /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && cluster); + /* Frontswap doesn't support THP */ + if (frontswap_enabled() && cluster) + goto noswap; avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages; if (avail_pgs <= 0) _ Patches currently in -mm which might be from huang.ying.caritas(a)gmail.com are mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled-v3.patch

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] [PATCH 4.14 00/22] 4.14.19-stable review

by Kevin Hilman

On Fri, Feb 9, 2018 at 11:36 AM, kernelci.org bot <bot(a)kernelci.org> wrote: > stable-rc/linux-4.14.y boot: 111 boots: 2 failed, 109 passed (v4.14.18-23-g8d861f5b27b0) > > Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.14.y/kernel/v4.1… > Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.14.y/kernel/v4.14.18-23… > > Tree: stable-rc > Branch: linux-4.14.y > Git Describe: v4.14.18-23-g8d861f5b27b0 > Git Commit: 8d861f5b27b05466ce2a9d3c4108367555dccefe > Git URL: http://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git > Tested: 63 unique boards, 22 SoC families, 16 builds out of 185 TL;DR; All is well. > Boot Regressions Detected: > > arm64: > > defconfig: > bcm2837-rpi-3-b: > lab-baylibre: new failure (last pass: v4.14.18-19-g44b8fc264b98) > r8a7795-salvator-x: > lab-baylibre: new failure (last pass: v4.14.18-19-g44b8fc264b98) Both of these are a bootloader failure to TFTP a kernel image. Kevin

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 2/6] tracing: Fix parsing of globs with a wildcard at the beginning

by Steven Rostedt

From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> Al Viro reported: For substring - sure, but what about something like "*a*b" and "a*b"? AFAICS, filter_parse_regex() ends up with identical results in both cases - MATCH_GLOB and *search = "a*b". And no way for the caller to tell one from another. Testing this with the following: # cd /sys/kernel/tracing # echo '*raw*lock' > set_ftrace_filter bash: echo: write error: Invalid argument With this patch: # echo '*raw*lock' > set_ftrace_filter # cat set_ftrace_filter _raw_read_trylock _raw_write_trylock _raw_read_unlock _raw_spin_unlock _raw_write_unlock _raw_spin_trylock _raw_spin_lock _raw_write_lock _raw_read_lock Al recommended not setting the search buffer to skip the first '*' unless we know we are not using MATCH_GLOB. This implements his suggested logic. Link: http://lkml.kernel.org/r/20180127170748.GF13338@ZenIV.linux.org.uk Cc: stable(a)vger.kernel.org Fixes: 60f1d5e3bac44 ("ftrace: Support full glob matching") Reviewed-by: Masami Hiramatsu <mhiramat(a)kernel.org> Reported-by: Al Viro <viro(a)ZenIV.linux.org.uk> Suggsted-by: Al Viro <viro(a)ZenIV.linux.org.uk> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> --- kernel/trace/trace_events_filter.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 61e7f0678d33..a764aec3c9a1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -400,7 +400,6 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) for (i = 0; i < len; i++) { if (buff[i] == '*') { if (!i) { - *search = buff + 1; type = MATCH_END_ONLY; } else if (i == len - 1) { if (type == MATCH_END_ONLY) @@ -410,14 +409,14 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) buff[i] = 0; break; } else { /* pattern continues, use full glob */ - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } else if (strchr("[?\\", buff[i])) { - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } + if (buff[0] == '*') + *search = buff + 1; return type; } -- 2.15.1

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 1/6] ftrace: Remove incorrect setting of glob search field

by Steven Rostedt

From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> __unregister_ftrace_function_probe() will incorrectly parse the glob filter because it resets the search variable that was setup by filter_parse_regex(). Al Viro reported this: After that call of filter_parse_regex() we could have func_g.search not equal to glob only if glob started with '!' or '*'. In the former case we would've buggered off with -EINVAL (not = 1). In the latter we would've set func_g.search equal to glob + 1, calculated the length of that thing in func_g.len and proceeded to reset func_g.search back to glob. Suppose the glob is e.g. *foo*. We end up with func_g.type = MATCH_MIDDLE_ONLY; func_g.len = 3; func_g.search = "*foo"; Feeding that to ftrace_match_record() will not do anything sane - we will be looking for names containing "*foo" (->len is ignored for that one). Link: http://lkml.kernel.org/r/20180127031706.GE13338@ZenIV.linux.org.uk Cc: stable(a)vger.kernel.org Fixes: 3ba009297149f ("ftrace: Introduce ftrace_glob structure") Reviewed-by: Dmitry Safonov <0x7f454c46(a)gmail.com> Reviewed-by: Masami Hiramatsu <mhiramat(a)kernel.org> Reported-by: Al Viro <viro(a)ZenIV.linux.org.uk> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dabd9d167d42..eac9ce2c57a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4456,7 +4456,6 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, func_g.type = filter_parse_regex(glob, strlen(glob), &func_g.search, &not); func_g.len = strlen(func_g.search); - func_g.search = glob; /* we do not support '!' for function probes */ if (WARN_ON(not)) -- 2.15.1

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH] usb: gadget: uvc: Missing files for configfs interface

by Bin Liu

From: Petr Cvek <petr.cvek(a)tul.cz> commit c8cd751060b149997b9de53a494fb1490ded72c5 upstream. Commit 76e0da34c7ce ("usb-gadget/uvc: use per-attribute show and store methods") caused a stringification of an undefined macro argument "aname", so three UVC parameters (streaming_interval, streaming_maxpacket and streaming_maxburst) were named "aname". Add the definition of "aname" to the main macro and name the filenames as originaly intended. Signed-off-by: Petr Cvek <petr.cvek(a)tul.cz> Signed-off-by: Felipe Balbi <felipe.balbi(a)linux.intel.com> Signed-off-by: Bin Liu <b-liu(a)ti.com> --- drivers/usb/gadget/function/uvc_configfs.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index ad8c9b05572d..01656f1c6d65 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -2202,7 +2202,7 @@ static struct configfs_item_operations uvc_item_ops = { .release = uvc_attr_release, }; -#define UVCG_OPTS_ATTR(cname, conv, str2u, uxx, vnoc, limit) \ +#define UVCG_OPTS_ATTR(cname, aname, conv, str2u, uxx, vnoc, limit) \ static ssize_t f_uvc_opts_##cname##_show( \ struct config_item *item, char *page) \ { \ @@ -2245,16 +2245,16 @@ end: \ return ret; \ } \ \ -UVC_ATTR(f_uvc_opts_, cname, aname) +UVC_ATTR(f_uvc_opts_, cname, cname) #define identity_conv(x) (x) -UVCG_OPTS_ATTR(streaming_interval, identity_conv, kstrtou8, u8, identity_conv, - 16); -UVCG_OPTS_ATTR(streaming_maxpacket, le16_to_cpu, kstrtou16, u16, le16_to_cpu, - 3072); -UVCG_OPTS_ATTR(streaming_maxburst, identity_conv, kstrtou8, u8, identity_conv, - 15); +UVCG_OPTS_ATTR(streaming_interval, streaming_interval, identity_conv, + kstrtou8, u8, identity_conv, 16); +UVCG_OPTS_ATTR(streaming_maxpacket, streaming_maxpacket, le16_to_cpu, + kstrtou16, u16, le16_to_cpu, 3072); +UVCG_OPTS_ATTR(streaming_maxburst, streaming_maxburst, identity_conv, + kstrtou8, u8, identity_conv, 15); #undef identity_conv -- 1.9.1

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] [PATCH] KVM MMU: check pending exception before injecting APF

by Paolo Bonzini

From: Haozhong Zhang <haozhong.zhang(a)intel.com> [ upstream commit 2a266f23550be997d783f27e704b9b40c4010292 Mon Sep 17 00:00:00 2001 ] For example, when two APF's for page ready happen after one exit and the first one becomes pending, the second one will result in #DF. Instead, just handle the second page fault synchronously. Reported-by: Ross Zwisler <zwisler(a)gmail.com> Message-ID: <CAOxpaSUBf8QoOZQ1p4KfUp0jq76OKfGY4Uxs-Gg8ngReD99xww(a)mail.gmail.com> Reported-by: Alec Blayne <ab(a)tevsa.net> Signed-off-by: Haozhong Zhang <haozhong.zhang(a)intel.com> Fixes: 664f8e26b00c7673a8303b0d40853a0c24ca93e1 Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> --- arch/x86/kvm/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index c4deb1f34faa..e577bacd4bd0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3781,7 +3781,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || - kvm_event_needs_reinjection(vcpu))) + kvm_event_needs_reinjection(vcpu) || + vcpu->arch.exception.pending)) return false; if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) -- 1.8.3.1

7 years, 4 months

2
3
0 0

[Linux-stable-mirror] [PATCH] crypto: sha512-mb - initialize pending lengths correctly

by Eric Biggers

From: Eric Biggers <ebiggers(a)google.com> The SHA-512 multibuffer code keeps track of the number of blocks pending in each lane. The minimum of these values is used to identify the next lane that will be completed. Unused lanes are set to a large number (0xFFFFFFFF) so that they don't affect this calculation. However, it was forgotten to set the lengths to this value in the initial state, where all lanes are unused. As a result it was possible for sha512_mb_mgr_get_comp_job_avx2() to select an unused lane, causing a NULL pointer dereference. Specifically this could happen in the case where ->update() was passed fewer than SHA512_BLOCK_SIZE bytes of data, so it then called sha_complete_job() without having actually submitted any blocks to the multi-buffer code. This hit a NULL pointer dereference if another task happened to have submitted blocks concurrently to the same CPU and the flush timer had not yet expired. Fix this by initializing sha512_mb_mgr->lens correctly. As usual, this bug was found by syzkaller. Fixes: 45691e2d9b18 ("crypto: sha512-mb - submit/flush routines for AVX2") Reported-by: syzbot <syzkaller(a)googlegroups.com> Cc: <stable(a)vger.kernel.org> # v4.8+ Signed-off-by: Eric Biggers <ebiggers(a)google.com> --- arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; -- 2.16.0

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [PATCH] v4l: vsp1: Fix continuous mode for dual pipelines

by Kieran Bingham

From: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> To allow dual pipelines utilising two WPF entities when available, the VSP was updated to support header-mode display list in continuous pipelines. A small bug in the status check of the command register causes the second pipeline to be directly afflicted by the running of the first; appearing as a perceived performance issue with stuttering display. Fix the vsp1_dl_list_hw_update_pending() call to ensure that the read comparison corresponds to the correct pipeline. Fixes: eaf4bfad6ad8 ("v4l: vsp1: Add support for header display lists in continuous mode") Cc: "Stable v4.14+" <stable(a)vger.kernel.org> Signed-off-by: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> --- drivers/media/platform/vsp1/vsp1_dl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c index 8cd03ee45f79..34b5ed2592f8 100644 --- a/drivers/media/platform/vsp1/vsp1_dl.c +++ b/drivers/media/platform/vsp1/vsp1_dl.c @@ -509,7 +509,8 @@ static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm) return !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE) & VI6_DL_BODY_SIZE_UPD); else - return !!(vsp1_read(vsp1, VI6_CMD(dlm->index) & VI6_CMD_UPDHDR)); + return !!(vsp1_read(vsp1, VI6_CMD(dlm->index)) + & VI6_CMD_UPDHDR); } static bool vsp1_dl_hw_active(struct vsp1_dl_manager *dlm) -- 2.7.4

7 years, 4 months

3
2
0 0

[Linux-stable-mirror] [PATCH] v4l: vsp1: Fix header display list status check in continuous mode

by Kieran Bingham

From: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> To allow dual pipelines utilising two WPF entities when available, the VSP was updated to support header-mode display list in continuous pipelines. A small bug in the status check of the command register causes the second pipeline to be directly afflicted by the running of the first; appearing as a perceived performance issue with stuttering display. Fix the vsp1_dl_list_hw_update_pending() call to ensure that the read comparison corresponds to the correct pipeline. Fixes: eaf4bfad6ad8 ("v4l: vsp1: Add support for header display lists in continuous mode") Cc: "Stable v4.14+" <stable(a)vger.kernel.org> Reviewed-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Signed-off-by: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> --- drivers/media/platform/vsp1/vsp1_dl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c index 8cd03ee45f79..34b5ed2592f8 100644 --- a/drivers/media/platform/vsp1/vsp1_dl.c +++ b/drivers/media/platform/vsp1/vsp1_dl.c @@ -509,7 +509,8 @@ static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm) return !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE) & VI6_DL_BODY_SIZE_UPD); else - return !!(vsp1_read(vsp1, VI6_CMD(dlm->index) & VI6_CMD_UPDHDR)); + return !!(vsp1_read(vsp1, VI6_CMD(dlm->index)) + & VI6_CMD_UPDHDR); } static bool vsp1_dl_hw_active(struct vsp1_dl_manager *dlm) -- 2.7.4

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "scsi: storvsc: missing error code in storvsc_probe()" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled scsi: storvsc: missing error code in storvsc_probe() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: scsi-storvsc-missing-error-code-in-storvsc_probe.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From ca8dc694045e9aa248e9916e0f614deb0494cb3d Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Tue, 16 Jan 2018 13:40:22 +0300 Subject: scsi: storvsc: missing error code in storvsc_probe() From: Dan Carpenter <dan.carpenter(a)oracle.com> commit ca8dc694045e9aa248e9916e0f614deb0494cb3d upstream. We should set the error code if fc_remote_port_add() fails. Cc: <stable(a)vger.kernel.org> #v4.12+ Fixes: daf0cd445a21 ("scsi: storvsc: Add support for FC rport.") Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: Cathy Avery <cavery(a)redhat.com> Acked-by: K. Y. Srinivasan <kys(a)microsoft.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Long Li <longli(a)microsoft.com> --- drivers/scsi/storvsc_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1826,8 +1826,10 @@ static int storvsc_probe(struct hv_devic fc_host_node_name(host) = stor_device->node_name; fc_host_port_name(host) = stor_device->port_name; stor_device->rport = fc_remote_port_add(host, 0, &ids); - if (!stor_device->rport) + if (!stor_device->rport) { + ret = -ENOMEM; goto err_out3; + } } #endif return 0; Patches currently in stable-queue which might be from dan.carpenter(a)oracle.com are queue-4.14/scsi-storvsc-missing-error-code-in-storvsc_probe.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH] scsi: storvsc: missing error code in storvsc_probe()

by Long Li

From: Long Li <longli(a)microsoft.com> This patch backports upstream commit ca8dc694045e9aa248e9916e0f614deb0494cb3d for 4.14-stable. commit ca8dc694045e9aa248e9916e0f614deb0494cb3d: We should set the error code if fc_remote_port_add() fails. Cc: <stable(a)vger.kernel.org> #v4.12+ Fixes: daf0cd445a21 ("scsi: storvsc: Add support for FC rport.") Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Reviewed-by: Cathy Avery <cavery(a)redhat.com> Acked-by: K. Y. Srinivasan <kys(a)microsoft.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Long Li <longli(a)microsoft.com> --- drivers/scsi/storvsc_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5e7200f..c17ccb9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1826,8 +1826,10 @@ static int storvsc_probe(struct hv_device *device, fc_host_node_name(host) = stor_device->node_name; fc_host_port_name(host) = stor_device->port_name; stor_device->rport = fc_remote_port_add(host, 0, &ids); - if (!stor_device->rport) + if (!stor_device->rport) { + ret = -ENOMEM; goto err_out3; + } } #endif return 0; -- 2.7.4

7 years, 4 months

2
1
0 0

Re: [Linux-stable-mirror] [STABLE 4.9.y PATCH 0/9] Backport of KVM Speculation Control support

by Greg KH

On Tue, Feb 06, 2018 at 09:05:46PM +0000, Woodhouse, David wrote: > > > On Tue, 2018-02-06 at 19:01 +0100, Paolo Bonzini wrote: > > On 06/02/2018 18:29, David Woodhouse wrote: > > > I've put together a linux-4.9.y branch at > > > http://git.infradead.org/retpoline-stable.git/shortlog/refs/heads/linux-4.9… > > > > > > Most of it is fairly straightforward, apart from the IBPB on context > > > switch for which Tim has already posted a candidate. I wanted some more > > > review on my backports of the KVM bits though, including some extra > > > historical patches I pulled in. > > > > Looks good! Thanks for the work, > > > > Paolo > > Thanks. In that case, Greg, the full set is lined up in > http://git.infradead.org/retpoline-stable.git/shortlog/refs/heads/linux-4.9… > or git://git.infradead.org/retpoline-stable linux-4.9.y Many thanks for all of this work. I've now queued up all of these. greg k-h

7 years, 4 months

2
4
0 0

[Linux-stable-mirror] Patch "KVM: nVMX: kmap() can't fail" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KVM: nVMX: kmap() can't fail to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: kvm-nvmx-kmap-can-t-fail.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 42cf014d38d8822cce63703a467e00f65d000952 Mon Sep 17 00:00:00 2001 From: David Hildenbrand <david(a)redhat.com> Date: Wed, 25 Jan 2017 11:58:57 +0100 Subject: KVM: nVMX: kmap() can't fail From: David Hildenbrand <david(a)redhat.com> commit 42cf014d38d8822cce63703a467e00f65d000952 upstream. kmap() can't fail, therefore it will always return a valid pointer. Let's just get rid of the unnecessary checks. Signed-off-by: David Hildenbrand <david(a)redhat.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kvm/vmx.c | 9 --------- 1 file changed, 9 deletions(-) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4756,10 +4756,6 @@ static int vmx_complete_nested_posted_in return 0; vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -9584,11 +9580,6 @@ static inline bool nested_vmx_merge_msr_ if (!page) return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); Patches currently in stable-queue which might be from david(a)redhat.com are queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/kvm-nvmx-kmap-can-t-fail.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 4.14.y] crypto: tcrypt - fix S/G table for test_aead_speed()

by Horia Geantă

From: Robert Baronescu <robert.baronescu(a)nxp.com> commit 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 upstream. In case buffer length is a multiple of PAGE_SIZE, the S/G table is incorrectly generated. Fix this by handling buflen = k * PAGE_SIZE separately. Signed-off-by: Robert Baronescu <robert.baronescu(a)nxp.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Horia Geantă <horia.geanta(a)nxp.com> --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index f5f58a6eee5d..e339960dcac7 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -221,11 +221,13 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE], } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, -- 2.12.0.264.gd6db3f216544

7 years, 4 months

2
4
0 0

[Linux-stable-mirror] [PATCH] mpls, nospec: Sanitize array index in mpls_label_ok()

by Dan Williams

mpls_label_ok() validates that the 'platform_label' array index from a userspace netlink message payload is valid. Under speculation the mpls_label_ok() result may not resolve in the CPU pipeline until after the index is used to access an array element. Sanitize the index to zero to prevent userspace-controlled arbitrary out-of-bounds speculation, a precursor for a speculative execution side channel vulnerability. Cc: <stable(a)vger.kernel.org> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric W. Biederman <ebiederm(a)xmission.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> --- net/mpls/af_mpls.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 8ca9915befc8..aae3565c3a92 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -8,6 +8,7 @@ #include <linux/ipv6.h> #include <linux/mpls.h> #include <linux/netconf.h> +#include <linux/nospec.h> #include <linux/vmalloc.h> #include <linux/percpu.h> #include <net/ip.h> @@ -935,24 +936,27 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, return err; } -static bool mpls_label_ok(struct net *net, unsigned int index, +static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { + bool is_ok = true; + /* Reserved labels may not be set */ - if (index < MPLS_LABEL_FIRST_UNRESERVED) { + if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); - return false; + is_ok = false; } /* The full 20 bit range may not be supported. */ - if (index >= net->mpls.platform_labels) { + if (is_ok && *index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); - return false; + is_ok = false; } - return true; + *index = array_index_nospec(*index, net->mpls.platform_labels); + return is_ok; } static int mpls_route_add(struct mpls_route_config *cfg, @@ -975,7 +979,7 @@ static int mpls_route_add(struct mpls_route_config *cfg, index = find_free_label(net); } - if (!mpls_label_ok(net, index, extack)) + if (!mpls_label_ok(net, &index, extack)) goto errout; /* Append makes no sense with mpls */ @@ -1052,7 +1056,7 @@ static int mpls_route_del(struct mpls_route_config *cfg, index = cfg->rc_label; - if (!mpls_label_ok(net, index, extack)) + if (!mpls_label_ok(net, &index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); @@ -1810,7 +1814,7 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, - cfg->rc_label, extack)) + &cfg->rc_label, extack)) goto errout; break; } @@ -2137,7 +2141,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, goto errout; } - if (!mpls_label_ok(net, in_label, extack)) { + if (!mpls_label_ok(net, &in_label, extack)) { err = -EINVAL; goto errout; }

7 years, 4 months

2
1
0 0

Re: [Linux-stable-mirror] [PATCH 4/4] clk: bcm2835: Make sure the PLL is gated before changing its rate

by Boris Brezillon

On Thu, 08 Feb 2018 15:20:16 +0000 Eric Anholt <eric(a)anholt.net> wrote: > Boris Brezillon <boris.brezillon(a)bootlin.com> writes: > > > All bcm2835 PLLs should be gated before their rate can be changed. > > Setting CLK_SET_RATE_GATE will let the core enforce that, but this is > > not enough to make the code work in all situations. Indeed, the > > CLK_SET_RATE_GATE flag prevents a user from changing the rate while > > the clock is enabled, but this check only guarantees there's no Linux > > users. In our case, the clock might have been enabled by the > > bootloader/FW, and, because we have CLK_IGNORE_UNUSED set, Linux never > > disables the PLL. So we have to make sure the PLL is actually disabled > > before changing the rate. > > > > Fixes: 41691b8862e2 ("clk: bcm2835: Add support for programming the audio domain clocks") > > Cc: <stable(a)vger.kernel.org> > > Signed-off-by: Boris Brezillon <boris.brezillon(a)bootlin.com> > > --- > > drivers/clk/bcm/clk-bcm2835.c | 14 +++++++++++++- > > 1 file changed, 13 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c > > index 6c5d4a8e426c..051ce769c109 100644 > > --- a/drivers/clk/bcm/clk-bcm2835.c > > +++ b/drivers/clk/bcm/clk-bcm2835.c > > @@ -678,6 +678,18 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw, > > u32 ana[4]; > > int i; > > > > + /* > > + * Normally, the CLK_SET_RATE_GATE flag prevents a user from changing > > + * the rate while the clock is enabled, but this check only makes sure > > + * there's no Linux users. > > + * In our case, the clock might have been enabled by the bootloader/FW, > > + * and, since CLK_IGNORE_UNUSED flag is set, Linux never disables it. > > + * So we have to make sure the clk is actually disabled before changing > > + * the rate. > > + */ > > + if (bcm2835_pll_is_on(hw)) > > + bcm2835_pll_off(hw); > > + > > I'm not sure this improves the situation. If the PLL was on, then > presumably there's a divider using it and a CM clock using that, so > we'll probably end up driving some glitches on them. Hm, yes, but if someone is trying to change the rate of the PLL, and the core doesn't know other clks depend on this PLL (which is the case if we reach this point), we're already in big trouble. > > Does the common clk framework have a way to disable unused clocks from > the leaf clocks up to this root, before the general > disable-unused-clocks path happens late in the boot process? Not that I know of. What do you have in mind? -- Boris Brezillon, Bootlin (formerly Free Electrons) Embedded Linux and Kernel engineering http://bootlin.com

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] [PATCH 3/4] clk: bcm2835: De-assert/assert PLL reset signal when appropriate

by Boris Brezillon

On Thu, 08 Feb 2018 15:15:42 +0000 Eric Anholt <eric(a)anholt.net> wrote: > Boris Brezillon <boris.brezillon(a)bootlin.com> writes: > > > In order to enable a PLL, not only the PLL has to be powered up and > > locked, but you also have to de-assert the reset signal. The last part > > was missing. Add it so PLLs that were not enabled by the FW/bootloader > > can be enabled from Linux. > > > > Fixes: 41691b8862e2 ("clk: bcm2835: Add support for programming the audio domain clocks") > > Cc: <stable(a)vger.kernel.org> > > Signed-off-by: Boris Brezillon <boris.brezillon(a)bootlin.com> > > --- > > drivers/clk/bcm/clk-bcm2835.c | 7 +++++++ > > 1 file changed, 7 insertions(+) > > > > diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c > > index a07f6451694a..6c5d4a8e426c 100644 > > --- a/drivers/clk/bcm/clk-bcm2835.c > > +++ b/drivers/clk/bcm/clk-bcm2835.c > > @@ -602,6 +602,9 @@ static void bcm2835_pll_off(struct clk_hw *hw) > > const struct bcm2835_pll_data *data = pll->data; > > > > spin_lock(&cprman->regs_lock); > > + cprman_write(cprman, data->a2w_ctrl_reg, > > + cprman_read(cprman, data->a2w_ctrl_reg) & > > + ~A2W_PLL_CTRL_PRST_DISABLE); > > cprman_write(cprman, data->cm_ctrl_reg, > > cprman_read(cprman, data->cm_ctrl_reg) | > > CM_PLL_ANARST); > > For turning off, the FW just does the equivalent of: > > cprman_write(cprman, data->cm_ctrl_reg, CM_PLL_ANARST); > cprman_write(cprman, data->a2w_ctrl_reg, A2W_PLL_CTRL_PWRDN); > > How about we do that, instead? Agreed. > > > @@ -640,6 +643,10 @@ static int bcm2835_pll_on(struct clk_hw *hw) > > cpu_relax(); > > } > > > > + cprman_write(cprman, data->a2w_ctrl_reg, > > + cprman_read(cprman, data->a2w_ctrl_reg) | > > + A2W_PLL_CTRL_PRST_DISABLE); > > + > > return 0; > > } > > I agree with this hunk -- they drop PRST at the very end, after lock. -- Boris Brezillon, Bootlin (formerly Free Electrons) Embedded Linux and Kernel engineering http://bootlin.com

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 1/2] x86/microcode/AMD: Do not load when running on a hypervisor

by Rolf Neugebauer

From: Borislav Petkov <bp(a)suse.de> commit a15a753539eca8ba243d576f02e7ca9c4b7d7042 upstream with minor adjustments. Doing so is completely void of sense for multiple reasons so prevent it. Set dis_ucode_ldr to true and thus disable the microcode loader by default to address xen pv guests which execute the AP path but not the BSP path. By having it turned off by default, the APs won't run into the loader either. Also, check CPUID(1).ECX[31] which hypervisors set. Well almost, not the xen pv one. That one gets the aforementioned "fix". Also, improve the detection method by caching the final decision whether to continue loading in dis_ucode_ldr and do it once on the BSP. The APs then simply test that value. Signed-off-by: Borislav Petkov <bp(a)suse.de> Tested-by: Juergen Gross <jgross(a)suse.com> Tested-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Acked-by: Juergen Gross <jgross(a)suse.com> Link: http://lkml.kernel.org/r/20161218164414.9649-4-bp@alien8.de Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: <stable(a)vger.kernel.org> # 4.4.x Signed-off-by: Rolf Neugebauer <rolf.neugebauer(a)docker.com> --- arch/x86/kernel/cpu/microcode/core.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3e94ef461fd..1b3e0aa4c511 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -44,7 +44,7 @@ static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; static int __init disable_loader(char *str) { @@ -81,6 +81,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); const char *opt = "dis_ucode_ldr"; @@ -93,8 +94,23 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + if (!have_cpuid_p()) + return *res; + + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -126,9 +142,6 @@ void __init load_ucode_bsp(void) if (check_loader_disabled_bsp()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); @@ -162,9 +175,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); -- 2.16.0

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] Patch "x86/microcode: Do the family check first" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/microcode: Do the family check first to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-microcode-do-the-family-check-first.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 1f161f67a272cc4f29f27934dd3f74cb657eb5c4 Mon Sep 17 00:00:00 2001 From: Borislav Petkov <bp(a)suse.de> Date: Thu, 12 Oct 2017 13:23:16 +0200 Subject: x86/microcode: Do the family check first From: Borislav Petkov <bp(a)suse.de> commit 1f161f67a272cc4f29f27934dd3f74cb657eb5c4 upstream with adjustments. On CPUs like AMD's Geode, for example, we shouldn't even try to load microcode because they do not support the modern microcode loading interface. However, we do the family check *after* the other checks whether the loader has been disabled on the command line or whether we're running in a guest. So move the family checks first in order to exit early if we're being loaded on an unsupported family. Reported-and-tested-by: Sven Glodowski <glodi1(a)arcor.de> Signed-off-by: Borislav Petkov <bp(a)suse.de> Cc: <stable(a)vger.kernel.org> # 4.11.. Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://bugzilla.suse.com/show_bug.cgi?id=1061396 Link: http://lkml.kernel.org/r/20171012112316.977-1-bp@alien8.de Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rolf Neugebauer <rolf.neugebauer(a)docker.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/microcode/core.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -86,9 +86,6 @@ static bool __init check_loader_disabled bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - a = 1; c = 0; native_cpuid(&a, &b, &c, &d); @@ -130,8 +127,9 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; vendor = x86_cpuid_vendor(); @@ -139,16 +137,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-microcode-do-the-family-check-first.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/microcode: Do the family check first" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/microcode: Do the family check first to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-microcode-do-the-family-check-first.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 1f161f67a272cc4f29f27934dd3f74cb657eb5c4 Mon Sep 17 00:00:00 2001 From: Borislav Petkov <bp(a)suse.de> Date: Thu, 12 Oct 2017 13:23:16 +0200 Subject: x86/microcode: Do the family check first From: Borislav Petkov <bp(a)suse.de> commit 1f161f67a272cc4f29f27934dd3f74cb657eb5c4 upstream with adjustments. On CPUs like AMD's Geode, for example, we shouldn't even try to load microcode because they do not support the modern microcode loading interface. However, we do the family check *after* the other checks whether the loader has been disabled on the command line or whether we're running in a guest. So move the family checks first in order to exit early if we're being loaded on an unsupported family. Reported-and-tested-by: Sven Glodowski <glodi1(a)arcor.de> Signed-off-by: Borislav Petkov <bp(a)suse.de> Cc: <stable(a)vger.kernel.org> # 4.11.. Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://bugzilla.suse.com/show_bug.cgi?id=1061396 Link: http://lkml.kernel.org/r/20171012112316.977-1-bp@alien8.de Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Rolf Neugebauer <rolf.neugebauer(a)docker.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/microcode/core.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -94,9 +94,6 @@ static bool __init check_loader_disabled bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - a = 1; c = 0; native_cpuid(&a, &b, &c, &d); @@ -138,8 +135,9 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; vendor = x86_vendor(); @@ -147,16 +145,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.4/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.4/x86-microcode-do-the-family-check-first.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/microcode/AMD: Do not load when running on a hypervisor" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/microcode/AMD: Do not load when running on a hypervisor to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From a15a753539eca8ba243d576f02e7ca9c4b7d7042 Mon Sep 17 00:00:00 2001 From: Borislav Petkov <bp(a)suse.de> Date: Sun, 18 Dec 2016 17:44:13 +0100 Subject: x86/microcode/AMD: Do not load when running on a hypervisor From: Borislav Petkov <bp(a)suse.de> commit a15a753539eca8ba243d576f02e7ca9c4b7d7042 upstream with minor adjustments. Doing so is completely void of sense for multiple reasons so prevent it. Set dis_ucode_ldr to true and thus disable the microcode loader by default to address xen pv guests which execute the AP path but not the BSP path. By having it turned off by default, the APs won't run into the loader either. Also, check CPUID(1).ECX[31] which hypervisors set. Well almost, not the xen pv one. That one gets the aforementioned "fix". Also, improve the detection method by caching the final decision whether to continue loading in dis_ucode_ldr and do it once on the BSP. The APs then simply test that value. Signed-off-by: Borislav Petkov <bp(a)suse.de> Tested-by: Juergen Gross <jgross(a)suse.com> Tested-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Acked-by: Juergen Gross <jgross(a)suse.com> Link: http://lkml.kernel.org/r/20161218164414.9649-4-bp@alien8.de Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Rolf Neugebauer <rolf.neugebauer(a)docker.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/microcode/core.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -44,7 +44,7 @@ static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; static int __init disable_loader(char *str) { @@ -81,6 +81,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); const char *opt = "dis_ucode_ldr"; @@ -93,8 +94,23 @@ static bool __init check_loader_disabled bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + if (!have_cpuid_p()) + return *res; + + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -126,9 +142,6 @@ void __init load_ucode_bsp(void) if (check_loader_disabled_bsp()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); @@ -162,9 +175,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.4/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.4/x86-microcode-do-the-family-check-first.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "drm: rcar-du: Use the VBK interrupt for vblank events" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled drm: rcar-du: Use the VBK interrupt for vblank events to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: drm-rcar-du-use-the-vbk-interrupt-for-vblank-events.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From cbbb90b0c084d7dfb2ed8e3fecf8df200fbdd2a0 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> Date: Mon, 10 Jul 2017 23:46:39 +0300 Subject: drm: rcar-du: Use the VBK interrupt for vblank events From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> commit cbbb90b0c084d7dfb2ed8e3fecf8df200fbdd2a0 upstream. When implementing support for interlaced modes, the driver switched from reporting vblank events on the vertical blanking (VBK) interrupt to the frame end interrupt (FRM). This incorrectly divided the reported refresh rate by two. Fix it by moving back to the VBK interrupt. Fixes: 906eff7fcada ("drm: rcar-du: Implement support for interlaced modes") Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> Reviewed-by: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> Signed-off-by: thongsyho <thong.ho.px(a)rvc.renesas.com> Signed-off-by: Nhan Nguyen <nhan.nguyen.yb(a)renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/rcar-du/rcar_du_crtc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -551,7 +551,7 @@ static irqreturn_t rcar_du_crtc_irq(int status = rcar_du_crtc_read(rcrtc, DSSR); rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK); - if (status & DSSR_FRM) { + if (status & DSSR_VBK) { drm_crtc_handle_vblank(&rcrtc->crtc); rcar_du_crtc_finish_page_flip(rcrtc); ret = IRQ_HANDLED; Patches currently in stable-queue which might be from laurent.pinchart+renesas(a)ideasonboard.com are queue-4.9/drm-rcar-du-use-the-vbk-interrupt-for-vblank-events.patch queue-4.9/drm-rcar-du-fix-race-condition-when-disabling-planes-at-crtc-stop.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "drm: rcar-du: Fix race condition when disabling planes at CRTC stop" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled drm: rcar-du: Fix race condition when disabling planes at CRTC stop to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: drm-rcar-du-fix-race-condition-when-disabling-planes-at-crtc-stop.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 641307df71fe77d7b38a477067495ede05d47295 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> Date: Sat, 29 Jul 2017 02:31:33 +0300 Subject: drm: rcar-du: Fix race condition when disabling planes at CRTC stop From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> commit 641307df71fe77d7b38a477067495ede05d47295 upstream. When stopping the CRTC the driver must disable all planes and wait for the change to take effect at the next vblank. Merely calling drm_crtc_wait_one_vblank() is not enough, as the function doesn't include any mechanism to handle the race with vblank interrupts. Replace the drm_crtc_wait_one_vblank() call with a manual mechanism that handles the vblank interrupt race. Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> Reviewed-by: Kieran Bingham <kieran.bingham+renesas(a)ideasonboard.com> Signed-off-by: thongsyho <thong.ho.px(a)rvc.renesas.com> Signed-off-by: Nhan Nguyen <nhan.nguyen.yb(a)renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/rcar-du/rcar_du_crtc.c | 53 +++++++++++++++++++++++++++++---- drivers/gpu/drm/rcar-du/rcar_du_crtc.h | 8 ++++ 2 files changed, 55 insertions(+), 6 deletions(-) --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -392,6 +392,31 @@ static void rcar_du_crtc_start(struct rc rcrtc->started = true; } +static void rcar_du_crtc_disable_planes(struct rcar_du_crtc *rcrtc) +{ + struct rcar_du_device *rcdu = rcrtc->group->dev; + struct drm_crtc *crtc = &rcrtc->crtc; + u32 status; + /* Make sure vblank interrupts are enabled. */ + drm_crtc_vblank_get(crtc); + /* + * Disable planes and calculate how many vertical blanking interrupts we + * have to wait for. If a vertical blanking interrupt has been triggered + * but not processed yet, we don't know whether it occurred before or + * after the planes got disabled. We thus have to wait for two vblank + * interrupts in that case. + */ + spin_lock_irq(&rcrtc->vblank_lock); + rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0); + status = rcar_du_crtc_read(rcrtc, DSSR); + rcrtc->vblank_count = status & DSSR_VBK ? 2 : 1; + spin_unlock_irq(&rcrtc->vblank_lock); + if (!wait_event_timeout(rcrtc->vblank_wait, rcrtc->vblank_count == 0, + msecs_to_jiffies(100))) + dev_warn(rcdu->dev, "vertical blanking timeout\n"); + drm_crtc_vblank_put(crtc); +} + static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc) { struct drm_crtc *crtc = &rcrtc->crtc; @@ -400,17 +425,16 @@ static void rcar_du_crtc_stop(struct rca return; /* Disable all planes and wait for the change to take effect. This is - * required as the DSnPR registers are updated on vblank, and no vblank - * will occur once the CRTC is stopped. Disabling planes when starting - * the CRTC thus wouldn't be enough as it would start scanning out - * immediately from old frame buffers until the next vblank. + * required as the plane enable registers are updated on vblank, and no + * vblank will occur once the CRTC is stopped. Disabling planes when + * starting the CRTC thus wouldn't be enough as it would start scanning + * out immediately from old frame buffers until the next vblank. * * This increases the CRTC stop delay, especially when multiple CRTCs * are stopped in one operation as we now wait for one vblank per CRTC. * Whether this can be improved needs to be researched. */ - rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0); - drm_crtc_wait_one_vblank(crtc); + rcar_du_crtc_disable_planes(rcrtc); /* Disable vertical blanking interrupt reporting. We first need to wait * for page flip completion before stopping the CRTC as userspace @@ -548,10 +572,25 @@ static irqreturn_t rcar_du_crtc_irq(int irqreturn_t ret = IRQ_NONE; u32 status; + spin_lock(&rcrtc->vblank_lock); + status = rcar_du_crtc_read(rcrtc, DSSR); rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK); if (status & DSSR_VBK) { + /* + * Wake up the vblank wait if the counter reaches 0. This must + * be protected by the vblank_lock to avoid races in + * rcar_du_crtc_disable_planes(). + */ + if (rcrtc->vblank_count) { + if (--rcrtc->vblank_count == 0) + wake_up(&rcrtc->vblank_wait); + } + } + spin_unlock(&rcrtc->vblank_lock); + + if (status & DSSR_VBK) { drm_crtc_handle_vblank(&rcrtc->crtc); rcar_du_crtc_finish_page_flip(rcrtc); ret = IRQ_HANDLED; @@ -606,6 +645,8 @@ int rcar_du_crtc_create(struct rcar_du_g } init_waitqueue_head(&rcrtc->flip_wait); + init_waitqueue_head(&rcrtc->vblank_wait); + spin_lock_init(&rcrtc->vblank_lock); rcrtc->group = rgrp; rcrtc->mmio_offset = mmio_offsets[index]; --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h @@ -15,6 +15,7 @@ #define __RCAR_DU_CRTC_H__ #include <linux/mutex.h> +#include <linux/spinlock.h> #include <linux/wait.h> #include <drm/drmP.h> @@ -33,6 +34,9 @@ struct rcar_du_vsp; * @started: whether the CRTC has been started and is running * @event: event to post when the pending page flip completes * @flip_wait: wait queue used to signal page flip completion + * @vblank_lock: protects vblank_wait and vblank_count + * @vblank_wait: wait queue used to signal vertical blanking + * @vblank_count: number of vertical blanking interrupts to wait for * @outputs: bitmask of the outputs (enum rcar_du_output) driven by this CRTC * @group: CRTC group this CRTC belongs to */ @@ -48,6 +52,10 @@ struct rcar_du_crtc { struct drm_pending_vblank_event *event; wait_queue_head_t flip_wait; + spinlock_t vblank_lock; + wait_queue_head_t vblank_wait; + unsigned int vblank_count; + unsigned int outputs; struct rcar_du_group *group; Patches currently in stable-queue which might be from laurent.pinchart+renesas(a)ideasonboard.com are queue-4.9/drm-rcar-du-use-the-vbk-interrupt-for-vblank-events.patch queue-4.9/drm-rcar-du-fix-race-condition-when-disabling-planes-at-crtc-stop.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "crypto: tcrypt - fix S/G table for test_aead_speed()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled crypto: tcrypt - fix S/G table for test_aead_speed() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 Mon Sep 17 00:00:00 2001 From: Robert Baronescu <robert.baronescu(a)nxp.com> Date: Tue, 10 Oct 2017 13:21:59 +0300 Subject: crypto: tcrypt - fix S/G table for test_aead_speed() From: Robert Baronescu <robert.baronescu(a)nxp.com> commit 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 upstream. In case buffer length is a multiple of PAGE_SIZE, the S/G table is incorrectly generated. Fix this by handling buflen = k * PAGE_SIZE separately. Signed-off-by: Robert Baronescu <robert.baronescu(a)nxp.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Horia Geantă <horia.geanta(a)nxp.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -223,11 +223,13 @@ static void sg_init_aead(struct scatterl } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, Patches currently in stable-queue which might be from robert.baronescu(a)nxp.com are queue-4.9/crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ASoC: simple-card: Fix misleading error message" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ASoC: simple-card: Fix misleading error message to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: asoc-simple-card-fix-misleading-error-message.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 7ac45d1635a4cd2e99a4b11903d4a2815ca1b27b Mon Sep 17 00:00:00 2001 From: Julian Scheel <julian(a)jusst.de> Date: Wed, 24 May 2017 12:28:23 +0200 Subject: ASoC: simple-card: Fix misleading error message From: Julian Scheel <julian(a)jusst.de> commit 7ac45d1635a4cd2e99a4b11903d4a2815ca1b27b upstream. In case cpu could not be found the error message would always refer to /codec/ not being found in DT. Fix this by catching the cpu node not found case explicitly. Signed-off-by: Julian Scheel <julian(a)jusst.de> Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: thongsyho <thong.ho.px(a)rvc.renesas.com> Signed-off-by: Nhan Nguyen <nhan.nguyen.yb(a)renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- sound/soc/generic/simple-card.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -232,13 +232,19 @@ static int asoc_simple_card_dai_link_of( snprintf(prop, sizeof(prop), "%scpu", prefix); cpu = of_get_child_by_name(node, prop); + if (!cpu) { + ret = -EINVAL; + dev_err(dev, "%s: Can't find %s DT node\n", __func__, prop); + goto dai_link_of_err; + } + snprintf(prop, sizeof(prop), "%splat", prefix); plat = of_get_child_by_name(node, prop); snprintf(prop, sizeof(prop), "%scodec", prefix); codec = of_get_child_by_name(node, prop); - if (!cpu || !codec) { + if (!codec) { ret = -EINVAL; dev_err(dev, "%s: Can't find %s DT node\n", __func__, prop); goto dai_link_of_err; Patches currently in stable-queue which might be from julian(a)jusst.de are queue-4.9/asoc-simple-card-fix-misleading-error-message.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ASoC: rsnd: don't call free_irq() on Parent SSI" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ASoC: rsnd: don't call free_irq() on Parent SSI to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: asoc-rsnd-don-t-call-free_irq-on-parent-ssi.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 1f8754d4daea5f257370a52a30fcb22798c54516 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> Date: Tue, 16 May 2017 01:48:24 +0000 Subject: ASoC: rsnd: don't call free_irq() on Parent SSI From: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> commit 1f8754d4daea5f257370a52a30fcb22798c54516 upstream. If SSI uses shared pin, some SSI will be used as parent SSI. Then, normal SSI's remove and Parent SSI's remove (these are same SSI) will be called when unbind or remove timing. In this case, free_irq() will be called twice. This patch solve this issue. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> Tested-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx(a)renesas.com> Reported-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx(a)renesas.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: thongsyho <thong.ho.px(a)rvc.renesas.com> Signed-off-by: Nhan Nguyen <nhan.nguyen.yb(a)renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- sound/soc/sh/rcar/ssi.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -699,9 +699,14 @@ static int rsnd_ssi_dma_remove(struct rs struct rsnd_priv *priv) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); + struct rsnd_mod *ssi_parent_mod = rsnd_io_to_mod_ssip(io); struct device *dev = rsnd_priv_to_dev(priv); int irq = ssi->irq; + /* Do nothing for SSI parent mod */ + if (ssi_parent_mod == mod) + return 0; + /* PIO will request IRQ again */ devm_free_irq(dev, irq, mod); Patches currently in stable-queue which might be from kuninori.morimoto.gx(a)renesas.com are queue-4.9/asoc-rsnd-don-t-call-free_irq-on-parent-ssi.patch queue-4.9/asoc-rsnd-avoid-duplicate-free_irq.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ASoC: rsnd: avoid duplicate free_irq()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ASoC: rsnd: avoid duplicate free_irq() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: asoc-rsnd-avoid-duplicate-free_irq.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From e0936c3471a8411a5df327641fa3ffe12a2fb07b Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> Date: Wed, 9 Aug 2017 02:16:20 +0000 Subject: ASoC: rsnd: avoid duplicate free_irq() From: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> commit e0936c3471a8411a5df327641fa3ffe12a2fb07b upstream. commit 1f8754d4daea5f ("ASoC: rsnd: don't call free_irq() on Parent SSI") fixed Parent SSI duplicate free_irq(). But on Renesas Sound, not only Parent SSI but also Multi SSI have same issue. This patch avoid duplicate free_irq() if it was not pure SSI. Fixes: 1f8754d4daea5f ("ASoC: rsnd: don't call free_irq() on Parent SSI") Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx(a)renesas.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: thongsyho <thong.ho.px(a)rvc.renesas.com> Signed-off-by: Nhan Nguyen <nhan.nguyen.yb(a)renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- sound/soc/sh/rcar/ssi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -699,12 +699,12 @@ static int rsnd_ssi_dma_remove(struct rs struct rsnd_priv *priv) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); - struct rsnd_mod *ssi_parent_mod = rsnd_io_to_mod_ssip(io); + struct rsnd_mod *pure_ssi_mod = rsnd_io_to_mod_ssi(io); struct device *dev = rsnd_priv_to_dev(priv); int irq = ssi->irq; - /* Do nothing for SSI parent mod */ - if (ssi_parent_mod == mod) + /* Do nothing if non SSI (= SSI parent, multi SSI) mod */ + if (pure_ssi_mod != mod) return 0; /* PIO will request IRQ again */ Patches currently in stable-queue which might be from kuninori.morimoto.gx(a)renesas.com are queue-4.9/asoc-rsnd-don-t-call-free_irq-on-parent-ssi.patch queue-4.9/asoc-rsnd-avoid-duplicate-free_irq.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "crypto: tcrypt - fix S/G table for test_aead_speed()" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled crypto: tcrypt - fix S/G table for test_aead_speed() to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 Mon Sep 17 00:00:00 2001 From: Robert Baronescu <robert.baronescu(a)nxp.com> Date: Tue, 10 Oct 2017 13:21:59 +0300 Subject: crypto: tcrypt - fix S/G table for test_aead_speed() From: Robert Baronescu <robert.baronescu(a)nxp.com> commit 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 upstream. In case buffer length is a multiple of PAGE_SIZE, the S/G table is incorrectly generated. Fix this by handling buflen = k * PAGE_SIZE separately. Signed-off-by: Robert Baronescu <robert.baronescu(a)nxp.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Horia Geantă <horia.geanta(a)nxp.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -291,11 +291,13 @@ static void sg_init_aead(struct scatterl } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, Patches currently in stable-queue which might be from robert.baronescu(a)nxp.com are queue-4.4/crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "crypto: tcrypt - fix S/G table for test_aead_speed()" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled crypto: tcrypt - fix S/G table for test_aead_speed() to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 Mon Sep 17 00:00:00 2001 From: Robert Baronescu <robert.baronescu(a)nxp.com> Date: Tue, 10 Oct 2017 13:21:59 +0300 Subject: crypto: tcrypt - fix S/G table for test_aead_speed() From: Robert Baronescu <robert.baronescu(a)nxp.com> commit 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 upstream. In case buffer length is a multiple of PAGE_SIZE, the S/G table is incorrectly generated. Fix this by handling buflen = k * PAGE_SIZE separately. Signed-off-by: Robert Baronescu <robert.baronescu(a)nxp.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Horia Geantă <horia.geanta(a)nxp.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -198,11 +198,13 @@ static void sg_init_aead(struct scatterl } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, Patches currently in stable-queue which might be from robert.baronescu(a)nxp.com are queue-4.15/crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "kernel/exit.c: export abort() to modules" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled kernel/exit.c: export abort() to modules to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: kernel-exit.c-export-abort-to-modules.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From dc8635b78cd8669c37e230058d18c33af7451ab1 Mon Sep 17 00:00:00 2001 From: Andrew Morton <akpm(a)linux-foundation.org> Date: Thu, 4 Jan 2018 16:17:56 -0800 Subject: kernel/exit.c: export abort() to modules From: Andrew Morton <akpm(a)linux-foundation.org> commit dc8635b78cd8669c37e230058d18c33af7451ab1 upstream. gcc -fisolate-erroneous-paths-dereference can generate calls to abort() from modular code too. [arnd(a)arndb.de: drop duplicate exports of abort()] Link: http://lkml.kernel.org/r/20180102103311.706364-1-arnd@arndb.de Reported-by: Vineet Gupta <Vineet.Gupta1(a)synopsys.com> Cc: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Alexey Brodkin <Alexey.Brodkin(a)synopsys.com> Cc: Russell King <rmk+kernel(a)armlinux.org.uk> Cc: Jose Abreu <Jose.Abreu(a)synopsys.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Evgeniy Didin <Evgeniy.Didin(a)synopsys.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/arm/kernel/traps.c | 1 - arch/m32r/kernel/traps.c | 1 - arch/unicore32/kernel/traps.c | 1 - kernel/exit.c | 1 + 4 files changed, 1 insertion(+), 3 deletions(-) --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -790,7 +790,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -122,7 +122,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { --- a/arch/unicore32/kernel/traps.c +++ b/arch/unicore32/kernel/traps.c @@ -298,7 +298,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1763,3 +1763,4 @@ __weak void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } +EXPORT_SYMBOL(abort); Patches currently in stable-queue which might be from akpm(a)linux-foundation.org are queue-4.14/arch-define-weak-abort.patch queue-4.14/kernel-exit.c-export-abort-to-modules.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "crypto: tcrypt - fix S/G table for test_aead_speed()" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled crypto: tcrypt - fix S/G table for test_aead_speed() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 Mon Sep 17 00:00:00 2001 From: Robert Baronescu <robert.baronescu(a)nxp.com> Date: Tue, 10 Oct 2017 13:21:59 +0300 Subject: crypto: tcrypt - fix S/G table for test_aead_speed() From: Robert Baronescu <robert.baronescu(a)nxp.com> commit 5c6ac1d4f8fbdbed65dbeb8cf149d736409d16a1 upstream. In case buffer length is a multiple of PAGE_SIZE, the S/G table is incorrectly generated. Fix this by handling buflen = k * PAGE_SIZE separately. Signed-off-by: Robert Baronescu <robert.baronescu(a)nxp.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Horia Geantă <horia.geanta(a)nxp.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -221,11 +221,13 @@ static void sg_init_aead(struct scatterl } sg_init_table(sg, np + 1); - np--; + if (rem) + np--; for (k = 0; k < np; k++) sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE); - sg_set_buf(&sg[k + 1], xbuf[k], rem); + if (rem) + sg_set_buf(&sg[k + 1], xbuf[k], rem); } static void test_aead_speed(const char *algo, int enc, unsigned int secs, Patches currently in stable-queue which might be from robert.baronescu(a)nxp.com are queue-4.14/crypto-tcrypt-fix-s-g-table-for-test_aead_speed.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "arch: define weak abort()" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled arch: define weak abort() to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: arch-define-weak-abort.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 7c2c11b208be09c156573fc0076b7b3646e05219 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> Date: Thu, 14 Dec 2017 15:33:19 -0800 Subject: arch: define weak abort() From: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> commit 7c2c11b208be09c156573fc0076b7b3646e05219 upstream. gcc toggle -fisolate-erroneous-paths-dereference (default at -O2 onwards) isolates faulty code paths such as null pointer access, divide by zero etc. If gcc port doesnt implement __builtin_trap, an abort() is generated which causes kernel link error. In this case, gcc is generating abort due to 'divide by zero' in lib/mpi/mpih-div.c. Currently 'frv' and 'arc' are failing. Previously other arch was also broken like m32r was fixed by commit d22e3d69ee1a ("m32r: fix build failure"). Let's define this weak function which is common for all arch and fix the problem permanently. We can even remove the arch specific 'abort' after this is done. Link: http://lkml.kernel.org/r/1513118956-8718-1-git-send-email-sudipm.mukherjee@… Signed-off-by: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> Cc: Alexey Brodkin <Alexey.Brodkin(a)synopsys.com> Cc: Vineet Gupta <Vineet.Gupta1(a)synopsys.com> Cc: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Evgeniy Didin <Evgeniy.Didin(a)synopsys.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- kernel/exit.c | 8 ++++++++ 1 file changed, 8 insertions(+) --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1755,3 +1755,11 @@ Efault: return -EFAULT; } #endif + +__weak void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} Patches currently in stable-queue which might be from sudipm.mukherjee(a)gmail.com are queue-4.14/arch-define-weak-abort.patch queue-4.14/kernel-exit.c-export-abort-to-modules.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Add patch "kernel/exit.c: export abort() to modules" to 4.14-stable tree

by Evgeniy Didin

Patch subject: "kernel/exit.c: export abort() to modules" Commit ID: dc8635b78cd8 Reason: While building mpi.ko module with lastest stable Linux v4.14.17 an error occured: >ERROR: "abort" [lib/mpi/mpi.ko] undefined! Kernel version: 4.14.x

7 years, 4 months

3
3
0 0

[Linux-stable-mirror] Applied "regulator: stm32-vrefbuf: fix check on ready flag" to the regulator tree

by Mark Brown

The patch regulator: stm32-vrefbuf: fix check on ready flag has been applied to the regulator tree at https://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator.git All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark >From f63248fac563125fd5a2f0bc780ce7a299872cab Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier <fabrice.gasnier(a)st.com> Date: Thu, 8 Feb 2018 14:43:05 +0100 Subject: [PATCH] regulator: stm32-vrefbuf: fix check on ready flag stm32_vrefbuf_enable() wrongly checks VRR bit: 0 stands for not ready, 1 for ready. It currently checks the opposite. This makes enable routine to exit immediately without waiting for ready flag. Fixes: 0cdbf481e927 ("regulator: Add support for stm32-vrefbuf") Signed-off-by: Fabrice Gasnier <fabrice.gasnier(a)st.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- drivers/regulator/stm32-vrefbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c index 72c8b3e1022b..e0a9c445ed67 100644 --- a/drivers/regulator/stm32-vrefbuf.c +++ b/drivers/regulator/stm32-vrefbuf.c @@ -51,7 +51,7 @@ static int stm32_vrefbuf_enable(struct regulator_dev *rdev) * arbitrary timeout. */ ret = readl_poll_timeout(priv->base + STM32_VREFBUF_CSR, val, - !(val & STM32_VRR), 650, 10000); + val & STM32_VRR, 650, 10000); if (ret) { dev_err(&rdev->dev, "stm32 vrefbuf timed out!\n"); val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); -- 2.15.1

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Applied "regmap: Fix reversed bounds check in regmap_raw_write()" to the regmap tree

by Mark Brown

The patch regmap: Fix reversed bounds check in regmap_raw_write() has been applied to the regmap tree at https://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark >From f00e71091ab92eba52122332586c6ecaa9cd1a56 Mon Sep 17 00:00:00 2001 From: Dan Carpenter <dan.carpenter(a)oracle.com> Date: Thu, 8 Feb 2018 10:23:44 +0300 Subject: [PATCH] regmap: Fix reversed bounds check in regmap_raw_write() We're supposed to be checking that "val_len" is not too large but instead we check if it is smaller than the max. The only function affected would be regmap_i2c_smbus_i2c_write() in drivers/base/regmap/regmap-i2c.c. Strangely that function has its own limit check which returns an error if (count >= I2C_SMBUS_BLOCK_MAX) so it doesn't look like it has ever been able to do anything except return an error. Fixes: c335931ed9d2 ("regmap: Add raw_write/read checks for max_raw_write/read sizes") Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- drivers/base/regmap/regmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index ee302ccdfbc8..453116fd4362 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1831,7 +1831,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; - if (map->max_raw_write && map->max_raw_write > val_len) + if (map->max_raw_write && map->max_raw_write < val_len) return -E2BIG; map->lock(map->lock_arg); -- 2.15.1

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH v3] xenbus: track caller request id

by Joao Martins

Commit fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") optimized xenbus concurrent accesses but in doing so broke UABI of /dev/xen/xenbus. Through /dev/xen/xenbus applications are in charge of xenbus message exchange with the correct header and body. Now, after the mentioned commit the replies received by application will no longer have the header req_id echoed back as it was on request (see specification below for reference), because that particular field is being overwritten by kernel. struct xsd_sockmsg { uint32_t type; /* XS_??? */ uint32_t req_id;/* Request identifier, echoed in daemon's response. */ uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */ uint32_t len; /* Length of data following this. */ /* Generally followed by nul-terminated string(s). */ }; Before there was only one request at a time so req_id could simply be forwarded back and forth. To allow simultaneous requests we need a different req_id for each message thus kernel keeps a monotonic increasing counter for this field and is written on every request irrespective of userspace value. Forwarding again the req_id on userspace requests is not a solution because we would open the possibility of userspace-generated req_id colliding with kernel ones. So this patch instead takes another route which is to artificially keep user req_id while keeping the xenbus logic as is. We do that by saving the original req_id before xs_send(), use the private kernel counter as req_id and then once reply comes and was validated, we restore back the original req_id. Cc: <stable(a)vger.kernel.org> # 4.11 Fixes: fd8aa9095a ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") Reported-by: Bhavesh Davda <bhavesh.davda(a)oracle.com> Signed-off-by: Joao Martins <joao.m.martins(a)oracle.com> Reviewed-by: Juergen Gross <jgross(a)suse.com> --- Here's a link to a unit test (https://pastebin.com/N0kqNBnM) where req_id of reply and response are being asserted each request. Without this patch the assert will fail (e.g. try it with `./xswire_reqid_test name`). But on <= v4.10 or >= v4.11 with the fix above, it will print domain name 10 times. Changes since v2: * Add Juergen's Reviewed-by Changes since v1: * Adjust commit message (Comments from Juergen on IRC) * Unilateraly save/restore req_id and remove xs_request_is_user() * Initialize req_id for kernel callers --- drivers/xen/xenbus/xenbus.h | 1 + drivers/xen/xenbus/xenbus_comms.c | 1 + drivers/xen/xenbus/xenbus_xs.c | 3 +++ 3 files changed, 5 insertions(+) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 149c5e7efc89..092981171df1 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -76,6 +76,7 @@ struct xb_req_data { struct list_head list; wait_queue_head_t wq; struct xsd_sockmsg msg; + uint32_t caller_req_id; enum xsd_sockmsg_type type; char *body; const struct kvec *vec; diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index 5b081a01779d..d239fc3c5e3d 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,6 +309,7 @@ static int process_msg(void) goto out; if (req->state == xb_req_state_wait_reply) { + req->msg.req_id = req->caller_req_id; req->msg.type = state.msg.type; req->msg.len = state.msg.len; req->body = state.body; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 3e59590c7254..3f3b29398ab8 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -227,6 +227,8 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->state = xb_req_state_queued; init_waitqueue_head(&req->wq); + /* Save the caller req_id and restore it later in the reply */ + req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); mutex_lock(&xb_write_mutex); @@ -310,6 +312,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; + msg.req_id = 0; msg.tx_id = t.id; msg.type = type; msg.len = 0; -- 2.11.0

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [RFC][PATCH 2/6] tracing: Fix parsing of globs with a wildcard at the beginning

by Steven Rostedt

From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> Al Viro reported: For substring - sure, but what about something like "*a*b" and "a*b"? AFAICS, filter_parse_regex() ends up with identical results in both cases - MATCH_GLOB and *search = "a*b". And no way for the caller to tell one from another. Testing this with the following: # cd /sys/kernel/tracing # echo '*raw*lock' > set_ftrace_filter bash: echo: write error: Invalid argument With this patch: # echo '*raw*lock' > set_ftrace_filter # cat set_ftrace_filter _raw_read_trylock _raw_write_trylock _raw_read_unlock _raw_spin_unlock _raw_write_unlock _raw_spin_trylock _raw_spin_lock _raw_write_lock _raw_read_lock Al recommended not setting the search buffer to skip the first '*' unless we know we are not using MATCH_GLOB. This implements his suggested logic. Link: http://lkml.kernel.org/r/20180127170748.GF13338@ZenIV.linux.org.uk Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Fixes: 60f1d5e3bac44 ("ftrace: Support full glob matching") Reported-by: Al Viro <viro(a)ZenIV.linux.org.uk> Suggsted-by: Al Viro <viro(a)ZenIV.linux.org.uk> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> --- kernel/trace/trace_events_filter.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 61e7f0678d33..a764aec3c9a1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -400,7 +400,6 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) for (i = 0; i < len; i++) { if (buff[i] == '*') { if (!i) { - *search = buff + 1; type = MATCH_END_ONLY; } else if (i == len - 1) { if (type == MATCH_END_ONLY) @@ -410,14 +409,14 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) buff[i] = 0; break; } else { /* pattern continues, use full glob */ - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } else if (strchr("[?\\", buff[i])) { - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } + if (buff[0] == '*') + *search = buff + 1; return type; } -- 2.15.1

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [RFC][PATCH 1/6] ftrace: Remove incorrect setting of glob search field

by Steven Rostedt

From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> __unregister_ftrace_function_probe() will incorrectly parse the glob filter because it resets the search variable that was setup by filter_parse_regex(). Al Viro reported this: After that call of filter_parse_regex() we could have func_g.search not equal to glob only if glob started with '!' or '*'. In the former case we would've buggered off with -EINVAL (not = 1). In the latter we would've set func_g.search equal to glob + 1, calculated the length of that thing in func_g.len and proceeded to reset func_g.search back to glob. Suppose the glob is e.g. *foo*. We end up with func_g.type = MATCH_MIDDLE_ONLY; func_g.len = 3; func_g.search = "*foo"; Feeding that to ftrace_match_record() will not do anything sane - we will be looking for names containing "*foo" (->len is ignored for that one). Link: http://lkml.kernel.org/r/20180127031706.GE13338@ZenIV.linux.org.uk Cc: stable(a)vger.kernel.org Cc: Dmitry Safonov <0x7f454c46(a)gmail.com> Fixes: 3ba009297149f ("ftrace: Introduce ftrace_glob structure") Reported-by: Al Viro <viro(a)ZenIV.linux.org.uk> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> --- kernel/trace/ftrace.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dabd9d167d42..eac9ce2c57a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4456,7 +4456,6 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, func_g.type = filter_parse_regex(glob, strlen(glob), &func_g.search, &not); func_g.len = strlen(func_g.search); - func_g.search = glob; /* we do not support '!' for function probes */ if (WARN_ON(not)) -- 2.15.1

7 years, 4 months

3
2
0 0

[Linux-stable-mirror] [PATCH] xen: Fix {set, clear}_foreign_p2m_mapping on autotranslating guests

by Simon Gaiser

Commit 82616f9599a7 ("xen: remove tests for pvh mode in pure pv paths") removed the check for autotranslation from {set,clear}_foreign_p2m_mapping but those are called by grant-table.c also on PVH/HVM guests. Cc: <stable(a)vger.kernel.org> # 4.14 Fixes: 82616f9599a7 ("xen: remove tests for pvh mode in pure pv paths") Signed-off-by: Simon Gaiser <simon(a)invisiblethingslab.com> Reviewed-by: Juergen Gross <jgross(a)suse.com> --- arch/x86/xen/p2m.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 13b4f19b9131..159a897151d6 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -694,6 +694,9 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, int i, ret = 0; pte_t *pte; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + if (kmap_ops) { ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, kmap_ops, count); @@ -736,6 +739,9 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, { int i, ret = 0; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); -- 2.15.1

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [PATCH 1/7] media: v4l2-compat-ioctl32.c: make ctrl_is_pointer work for subdevs

by Hans Verkuil

From: Hans Verkuil <hansverk(a)cisco.com> If the device is of type VFL_TYPE_SUBDEV then vdev->ioctl_ops is NULL so the 'if (!ops->vidioc_query_ext_ctrl)' check would crash. Add a test for !ops to the condition. All sub-devices that have controls will use the control framework, so they do not have an equivalent to ops->vidioc_query_ext_ctrl. Returning false if ops is NULL is the correct thing to do here. Fixes: b8c601e8af ("v4l2-compat-ioctl32.c: fix ctrl_is_pointer") Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Acked-by: Sakari Ailus <sakari.ailus(a)linux.intel.com> Reported-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Reviewed-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Cc: <stable(a)vger.kernel.org> # for v4.15 and up Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> --- drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index bdb5c226d01c..5198c9eeb348 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -770,7 +770,7 @@ static inline bool ctrl_is_pointer(struct file *file, u32 id) return ctrl && ctrl->is_ptr; } - if (!ops->vidioc_query_ext_ctrl) + if (!ops || !ops->vidioc_query_ext_ctrl) return false; return !ops->vidioc_query_ext_ctrl(file, fh, &qec) && -- 2.15.1

7 years, 4 months

1
1
0 0

[Linux-stable-mirror] v4.15.2 build: 0 failures 0 warnings (v4.15.2)

by Build bot for Mark Brown

Tree/Branch: v4.15.2 Git describe: v4.15.2 Commit: db22ec452b Linux 4.15.2 Build Time: 112 min 8 sec Passed: 10 / 10 (100.00 %) Failed: 0 / 10 ( 0.00 %) Errors: 0 Warnings: 0 Section Mismatches: 0 ------------------------------------------------------------------------------- defconfigs with issues (other than build errors): ------------------------------------------------------------------------------- =============================================================================== Detailed per-defconfig build reports below: ------------------------------------------------------------------------------- Passed with no errors, warnings or mismatches: arm64-allnoconfig arm64-allmodconfig arm-multi_v5_defconfig arm-multi_v7_defconfig x86_64-defconfig arm-allmodconfig arm-allnoconfig x86_64-allnoconfig arm-multi_v4t_defconfig arm64-defconfig close failed in file object destructor: sys.excepthook is missing lost sys.stderr

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] v4.14.18 build: 0 failures 0 warnings (v4.14.18)

by Build bot for Mark Brown

Tree/Branch: v4.14.18 Git describe: v4.14.18 Commit: 81d0cc85ca Linux 4.14.18 Build Time: 108 min 51 sec Passed: 10 / 10 (100.00 %) Failed: 0 / 10 ( 0.00 %) Errors: 0 Warnings: 0 Section Mismatches: 0 ------------------------------------------------------------------------------- defconfigs with issues (other than build errors): ------------------------------------------------------------------------------- =============================================================================== Detailed per-defconfig build reports below: ------------------------------------------------------------------------------- Passed with no errors, warnings or mismatches: arm64-allnoconfig arm64-allmodconfig arm-multi_v5_defconfig arm-multi_v7_defconfig x86_64-defconfig arm-allmodconfig arm-allnoconfig x86_64-allnoconfig arm-multi_v4t_defconfig arm64-defconfig close failed in file object destructor: sys.excepthook is missing lost sys.stderr

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:49 -0800 Subject: x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit 304ec1b050310548db33063e567123fae8fd0301) Quoting Linus: I do think that it would be a good idea to very expressly document the fact that it's not that the user access itself is unsafe. I do agree that things like "get_user()" want to be protected, but not because of any direct bugs or problems with get_user() and friends, but simply because get_user() is an excellent source of a pointer that is obviously controlled from a potentially attacking user space. So it's a prime candidate for then finding _subsequent_ accesses that can then be used to perturb the cache. __uaccess_begin_nospec() covers __get_user() and copy_from_iter() where the limit check is far away from the user pointer de-reference. In those cases a barrier_nospec() prevents speculation with a potential pointer to privileged memory. uaccess_try_nospec covers get_user_try. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Suggested-by: Andi Kleen <ak(a)linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: Kees Cook <keescook(a)chromium.org> Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727416953.33451.10508284228526170604.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/uaccess.h | 6 +++--- arch/x86/include/asm/uaccess_32.h | 12 ++++++------ arch/x86/include/asm/uaccess_64.h | 12 ++++++------ arch/x86/lib/usercopy_32.c | 4 ++-- 4 files changed, 17 insertions(+), 17 deletions(-) --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -437,7 +437,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -547,7 +547,7 @@ struct __large_struct { unsigned long bu * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -582,7 +582,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -102,17 +102,17 @@ __copy_from_user(void *to, const void __ switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; @@ -130,17 +130,17 @@ static __always_inline unsigned long __c switch (n) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u8 *)to, from, 1, ret, 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u16 *)to, from, 2, ret, 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_size(*(u32 *)to, from, 4, ret, 4); __uaccess_end(); return ret; --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -59,31 +59,31 @@ int __copy_from_user_nocheck(void *dst, return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -93,7 +93,7 @@ int __copy_from_user_nocheck(void *dst, __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -570,7 +570,7 @@ do { \ unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n) { - __uaccess_begin(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else @@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - __uaccess_begin(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end}" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end} to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:44 -0800 Subject: x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end} From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit b5c4ae4f35325d520b230bab6eb3310613b72ac1) In preparation for converting some __uaccess_begin() instances to __uacess_begin_nospec(), make sure all 'from user' uaccess paths are using the _begin(), _end() helpers rather than open-coded stac() and clac(). No functional changes. Suggested-by: Ingo Molnar <mingo(a)redhat.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727416438.33451.17309465232057176966.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/lib/usercopy_32.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -570,12 +570,12 @@ do { \ unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_to_user_ll); @@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocach #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/syscall: Sanitize syscall table de-references under speculation" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/syscall: Sanitize syscall table de-references under speculation to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:59 -0800 Subject: x86/syscall: Sanitize syscall table de-references under speculation From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit 2fbd7af5af8665d18bcefae3e9700be07e22b681) The syscall table base is a user controlled function pointer in kernel space. Use array_index_nospec() to prevent any out of bounds speculation. While retpoline prevents speculating into a userspace directed target it does not stop the pointer de-reference, the concern is leaking memory relative to the syscall table base, by observing instruction cache behavior. Reported-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Andy Lutomirski <luto(a)kernel.org> Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727417984.33451.1216731042505722161.stgit@dwil… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/common.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -20,6 +20,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <asm/desc.h> @@ -277,7 +278,8 @@ __visible void do_syscall_64(struct pt_r * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -313,6 +315,7 @@ static __always_inline void do_syscall_3 } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:15 +0000 Subject: x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 20ffa1caecca4db8f79fe665acdeaa5af815a24d) Expose indirect_branch_prediction_barrier() for use in subsequent patches. [ tglx: Add IBPB status to spectre_v2 sysfs file ] Co-developed-by: KarimAllah Ahmed <karahmed(a)amazon.de> Signed-off-by: KarimAllah Ahmed <karahmed(a)amazon.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-8-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/cpufeatures.h | 2 ++ arch/x86/include/asm/nospec-branch.h | 13 +++++++++++++ arch/x86/kernel/cpu/bugs.c | 10 +++++++++- 3 files changed, 24 insertions(+), 1 deletion(-) --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -202,6 +202,8 @@ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ +#define X86_FEATURE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled*/ + /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -218,5 +218,18 @@ static inline void vmexit_fill_RSB(void) #endif } +static inline void indirect_branch_prediction_barrier(void) +{ + asm volatile(ALTERNATIVE("", + "movl %[msr], %%ecx\n\t" + "movl %[val], %%eax\n\t" + "movl $0, %%edx\n\t" + "wrmsr", + X86_FEATURE_IBPB) + : : [msr] "i" (MSR_IA32_PRED_CMD), + [val] "i" (PRED_CMD_IBPB) + : "eax", "ecx", "edx", "memory"); +} + #endif /* __ASSEMBLY__ */ #endif /* __NOSPEC_BRANCH_H__ */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -262,6 +262,13 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Filling RSB on context switch\n"); } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) || + boot_cpu_has(X86_FEATURE_AMD_PRED_CMD)) { + setup_force_cpu_cap(X86_FEATURE_IBPB); + pr_info("Enabling Indirect Branch Prediction Barrier\n"); + } } #undef pr_fmt @@ -291,7 +298,8 @@ ssize_t cpu_show_spectre_v2(struct devic if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_IBPB) ? ", IPBP" : "", spectre_v2_bad_module ? " - vulnerable module loaded" : ""); } #endif Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:33:09 CET 2018 From: Darren Kenny <darren.kenny(a)oracle.com> Date: Fri, 2 Feb 2018 19:12:20 +0000 Subject: x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL From: Darren Kenny <darren.kenny(a)oracle.com> (cherry picked from commit af189c95a371b59f493dbe0f50c0a09724868881) Fixes: 117cc7a908c83 ("x86/retpoline: Fill return stack buffer on vmexit") Signed-off-by: Darren Kenny <darren.kenny(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Link: https://lkml.kernel.org/r/20180202191220.blvgkgutojecxr3b@starbug-vm.ie.ora… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/nospec-branch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -150,7 +150,7 @@ extern char __indirect_thunk_end[]; * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ATT *might* it be avoided. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { Patches currently in stable-queue which might be from darren.kenny(a)oracle.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/spectre: Simplify spectre_v2 command line parsing" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/spectre: Simplify spectre_v2 command line parsing to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-spectre-simplify-spectre_v2-command-line-parsing.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: KarimAllah Ahmed <karahmed(a)amazon.de> Date: Thu, 1 Feb 2018 11:27:21 +0000 Subject: x86/spectre: Simplify spectre_v2 command line parsing From: KarimAllah Ahmed <karahmed(a)amazon.de> (cherry picked from commit 9005c6834c0ffdfe46afa76656bd9276cca864f6) [dwmw2: Use ARRAY_SIZE] Signed-off-by: KarimAllah Ahmed <karahmed(a)amazon.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Link: https://lkml.kernel.org/r/1517484441-1420-3-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 84 +++++++++++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 29 deletions(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -118,13 +118,13 @@ static inline const char *spectre_v2_mod static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static void __init spec2_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -139,42 +139,68 @@ static inline bool match_option(const ch return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { char arg[20]; - int ret; + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); - if (ret > 0) { - if (match_option(arg, ret, "off")) { - goto disable; - } else if (match_option(arg, ret, "on")) { - spec2_print_if_secure("force enabled on command line."); - return SPECTRE_V2_CMD_FORCE; - } else if (match_option(arg, ret, "retpoline")) { - spec2_print_if_insecure("retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE; - } else if (match_option(arg, ret, "retpoline,amd")) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec2_print_if_insecure("AMD retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_AMD; - } else if (match_option(arg, ret, "retpoline,generic")) { - spec2_print_if_insecure("generic retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_GENERIC; - } else if (match_option(arg, ret, "auto")) { + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ Patches currently in stable-queue which might be from karahmed(a)amazon.de are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/spectre: Report get_user mitigation for spectre_v1" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/spectre: Report get_user mitigation for spectre_v1 to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-spectre-report-get_user-mitigation-for-spectre_v1.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:03:21 -0800 Subject: x86/spectre: Report get_user mitigation for spectre_v1 From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit edfbae53dab8348fca778531be9f4855d2ca0360) Reflect the presence of get_user(), __get_user(), and 'syscall' protections in sysfs. The expectation is that new and better tooling will allow the kernel to grow more usages of array_index_nospec(), for now, only claim mitigation for __user pointer de-references. Reported-by: Jiri Slaby <jslaby(a)suse.cz> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727420158.33451.11658324346540434635.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -296,7 +296,7 @@ ssize_t cpu_show_spectre_v1(struct devic { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable"" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable" to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Colin Ian King <colin.king(a)canonical.com> Date: Tue, 30 Jan 2018 19:32:18 +0000 Subject: x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable" From: Colin Ian King <colin.king(a)canonical.com> (cherry picked from commit e698dcdfcda41efd0984de539767b4cddd235f1e) Trivial fix to spelling mistake in pr_err error message text. Signed-off-by: Colin Ian King <colin.king(a)canonical.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: kernel-janitors(a)vger.kernel.org Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)suse.de> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Link: https://lkml.kernel.org/r/20180130193218.9271-1-colin.king@canonical.com Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -102,7 +102,7 @@ bool retpoline_module_ok(bool has_retpol if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) return true; - pr_err("System may be vunerable to spectre v2\n"); + pr_err("System may be vulnerable to spectre v2\n"); spectre_v2_bad_module = true; return false; } Patches currently in stable-queue which might be from colin.king(a)canonical.com are queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/spectre: Check CONFIG_RETPOLINE in command line parser" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/spectre: Check CONFIG_RETPOLINE in command line parser to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-spectre-check-config_retpoline-in-command-line-parser.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Dou Liyang <douly.fnst(a)cn.fujitsu.com> Date: Tue, 30 Jan 2018 14:13:50 +0800 Subject: x86/spectre: Check CONFIG_RETPOLINE in command line parser From: Dou Liyang <douly.fnst(a)cn.fujitsu.com> (cherry picked from commit 9471eee9186a46893726e22ebb54cade3f9bc043) The spectre_v2 option 'auto' does not check whether CONFIG_RETPOLINE is enabled. As a consequence it fails to emit the appropriate warning and sets feature flags which have no effect at all. Add the missing IS_ENABLED() check. Fixes: da285121560e ("x86/spectre: Add boot time option to select Spectre v2 mitigation") Signed-off-by: Dou Liyang <douly.fnst(a)cn.fujitsu.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: ak(a)linux.intel.com Cc: peterz(a)infradead.org Cc: Tomohiro" <misono.tomohiro(a)jp.fujitsu.com> Cc: dave.hansen(a)intel.com Cc: bp(a)alien8.de Cc: arjan(a)linux.intel.com Cc: dwmw(a)amazon.co.uk Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/f5892721-7528-3647-08fb-f8d10e65ad87@cn.fujitsu.c… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -212,10 +212,10 @@ static void __init spectre_v2_select_mit return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; Patches currently in stable-queue which might be from douly.fnst(a)cn.fujitsu.com are queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline: Simplify vmexit_fill_RSB()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline: Simplify vmexit_fill_RSB() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-simplify-vmexit_fill_rsb.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Borislav Petkov <bp(a)alien8.de> Date: Sat, 27 Jan 2018 16:24:33 +0000 Subject: x86/retpoline: Simplify vmexit_fill_RSB() From: Borislav Petkov <bp(a)alien8.de> (cherry picked from commit 1dde7415e99933bb7293d6b2843752cbdb43ec11) Simplify it to call an asm-function instead of pasting 41 insn bytes at every call site. Also, add alignment to the macro as suggested here: https://support.google.com/faqs/answer/7625886 [dwmw2: Clean up comments, let it clobber %ebx and just tell the compiler] Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: ak(a)linux.intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1517070274-12128-3-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_32.S | 3 - arch/x86/entry/entry_64.S | 3 - arch/x86/include/asm/asm-prototypes.h | 3 + arch/x86/include/asm/nospec-branch.h | 70 +++------------------------------- arch/x86/lib/Makefile | 1 arch/x86/lib/retpoline.S | 56 +++++++++++++++++++++++++++ 6 files changed, 71 insertions(+), 65 deletions(-) --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -237,7 +237,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %ebx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -435,7 +435,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %rbx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -37,4 +37,7 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) +asmlinkage void __fill_rsb(void); +asmlinkage void __clear_rsb(void); + #endif /* CONFIG_RETPOLINE */ --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -7,50 +7,6 @@ #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * We define a CPP macro such that it can be used from both .S files and - * inline assembly. It's possible to do a .macro and then include that - * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. - */ - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -/* - * Google experimented with loop-unrolling and this turned out to be - * the optimal version — two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - call 772f; \ -773: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - call 774f; \ -775: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - dec reg; \ - jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; - #ifdef __ASSEMBLY__ /* @@ -121,17 +77,10 @@ #endif .endm - /* - * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP - * monstrosity above, manually. - */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +/* This clobbers the BX register */ +.macro FILL_RETURN_BUFFER nr:req ftr:req #ifdef CONFIG_RETPOLINE - ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE "jmp .Lskip_rsb_\@", \ - __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ - \ftr -.Lskip_rsb_\@: + ALTERNATIVE "", "call __clear_rsb", \ftr #endif .endm @@ -206,15 +155,10 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); + alternative_input("", + "call __fill_rsb", + X86_FEATURE_RETPOLINE, + ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); #endif } --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -26,6 +26,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_RETPOLINE) += retpoline.o +OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,6 +7,7 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -46,3 +47,58 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) Patches currently in stable-queue which might be from bp(a)alien8.de are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/retpoline: Avoid retpolines for built-in __init functions" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline: Avoid retpolines for built-in __init functions to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 1 Feb 2018 11:27:20 +0000 Subject: x86/retpoline: Avoid retpolines for built-in __init functions From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 66f793099a636862a71c59d4a6ba91387b155e0c) There's no point in building init code with retpolines, since it runs before any potentially hostile userspace does. And before the retpoline is actually ALTERNATIVEd into place, for much of it. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: karahmed(a)amazon.de Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Link: https://lkml.kernel.org/r/1517484441-1420-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- include/linux/init.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) --- a/include/linux/init.h +++ b/include/linux/init.h @@ -4,6 +4,13 @@ #include <linux/compiler.h> #include <linux/types.h> +/* Built-in __init functions needn't be compiled with retpoline */ +#if defined(RETPOLINE) && !defined(MODULE) +#define __noretpoline __attribute__((indirect_branch("keep"))) +#else +#define __noretpoline +#endif + /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -39,7 +46,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold notrace __latent_entropy +#define __init __section(.init.text) __cold notrace __latent_entropy __noretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/paravirt: Remove 'noreplace-paravirt' cmdline option" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/paravirt: Remove 'noreplace-paravirt' cmdline option to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Josh Poimboeuf <jpoimboe(a)redhat.com> Date: Tue, 30 Jan 2018 22:13:33 -0600 Subject: x86/paravirt: Remove 'noreplace-paravirt' cmdline option From: Josh Poimboeuf <jpoimboe(a)redhat.com> (cherry picked from commit 12c69f1e94c89d40696e83804dd2f0965b5250cd) The 'noreplace-paravirt' option disables paravirt patching, leaving the original pv indirect calls in place. That's highly incompatible with retpolines, unless we want to uglify paravirt even further and convert the paravirt calls to retpolines. As far as I can tell, the option doesn't seem to be useful for much other than introducing surprising corner cases and making the kernel vulnerable to Spectre v2. It was probably a debug option from the early paravirt days. So just remove it. Signed-off-by: Josh Poimboeuf <jpoimboe(a)redhat.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Juergen Gross <jgross(a)suse.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Ashok Raj <ashok.raj(a)intel.com> Cc: Greg KH <gregkh(a)linuxfoundation.org> Cc: Jun Nakajima <jun.nakajima(a)intel.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Rusty Russell <rusty(a)rustcorp.com.au> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Asit Mallick <asit.k.mallick(a)intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jason Baron <jbaron(a)akamai.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Alok Kataria <akataria(a)vmware.com> Cc: Arjan Van De Ven <arjan.van.de.ven(a)intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: Dan Williams <dan.j.williams(a)intel.com> Link: https://lkml.kernel.org/r/20180131041333.2x6blhxirc2kclrq@treble Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- Documentation/kernel-parameters.txt | 2 -- arch/x86/kernel/alternative.c | 14 -------------- 2 files changed, 16 deletions(-) --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2805,8 +2805,6 @@ bytes respectively. Such letter suffixes norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space - noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops - noreplace-smp [X86-32,SMP] Don't replace SMP instructions with UP alternatives --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(ch } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -588,9 +577,6 @@ void __init_or_module apply_paravirt(str struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; Patches currently in stable-queue which might be from jpoimboe(a)redhat.com are queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/pti: Mark constant arrays as __initconst" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/pti: Mark constant arrays as __initconst to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-pti-mark-constant-arrays-as-__initconst.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:33:09 CET 2018 From: Arnd Bergmann <arnd(a)arndb.de> Date: Fri, 2 Feb 2018 22:39:23 +0100 Subject: x86/pti: Mark constant arrays as __initconst From: Arnd Bergmann <arnd(a)arndb.de> (cherry picked from commit 4bf5d56d429cbc96c23d809a08f63cd29e1a702e) I'm seeing build failures from the two newly introduced arrays that are marked 'const' and '__initdata', which are mutually exclusive: arch/x86/kernel/cpu/common.c:882:43: error: 'cpu_no_speculation' causes a section type conflict with 'e820_table_firmware_init' arch/x86/kernel/cpu/common.c:895:43: error: 'cpu_no_meltdown' causes a section type conflict with 'e820_table_firmware_init' The correct annotation is __initconst. Fixes: fec9434a12f3 ("x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)suse.de> Cc: Thomas Garnier <thgarnie(a)google.com> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Link: https://lkml.kernel.org/r/20180202213959.611210-1-arnd@arndb.de Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -861,7 +861,7 @@ static void identify_cpu_without_cpuid(s #endif } -static const __initdata struct x86_cpu_id cpu_no_speculation[] = { +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, @@ -874,7 +874,7 @@ static const __initdata struct x86_cpu_i {} }; -static const __initdata struct x86_cpu_id cpu_no_meltdown[] = { +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { { X86_VENDOR_AMD }, {} }; Patches currently in stable-queue which might be from arnd(a)arndb.de are queue-4.9/auxdisplay-img-ascii-lcd-add-missing-module_description-author-license.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/nospec: Fix header guards names" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/nospec: Fix header guards names to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-nospec-fix-header-guards-names.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Borislav Petkov <bp(a)suse.de> Date: Fri, 26 Jan 2018 13:11:37 +0100 Subject: x86/nospec: Fix header guards names From: Borislav Petkov <bp(a)suse.de> (cherry picked from commit 7a32fc51ca938e67974cbb9db31e1a43f98345a9) ... to adhere to the _ASM_X86_ naming scheme. No functional change. Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: riel(a)redhat.com Cc: ak(a)linux.intel.com Cc: peterz(a)infradead.org Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: jikos(a)kernel.org Cc: luto(a)amacapital.net Cc: dave.hansen(a)intel.com Cc: torvalds(a)linux-foundation.org Cc: keescook(a)google.com Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Cc: pjt(a)google.com Link: https://lkml.kernel.org/r/20180126121139.31959-3-bp@alien8.de Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/nospec-branch.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NOSPEC_BRANCH_H__ -#define __NOSPEC_BRANCH_H__ +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ #include <asm/alternative.h> #include <asm/alternative-asm.h> @@ -232,4 +232,4 @@ static inline void indirect_branch_predi } #endif /* __ASSEMBLY__ */ -#endif /* __NOSPEC_BRANCH_H__ */ +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/kvm: Update spectre-v1 mitigation" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/kvm: Update spectre-v1 mitigation to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-kvm-update-spectre-v1-mitigation.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Wed, 31 Jan 2018 17:47:03 -0800 Subject: x86/kvm: Update spectre-v1 mitigation From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit 085331dfc6bbe3501fb936e657331ca943827600) Commit 75f139aaf896 "KVM: x86: Add memory barrier on vmcs field lookup" added a raw 'asm("lfence");' to prevent a bounds check bypass of 'vmcs_field_to_offset_table'. The lfence can be avoided in this path by using the array_index_nospec() helper designed for these types of fixes. Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Andrew Honig <ahonig(a)google.com> Cc: kvm(a)vger.kernel.org Cc: Jim Mattson <jmattson(a)google.com> Link: https://lkml.kernel.org/r/151744959670.6342.3001723920950249067.stgit@dwill… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kvm/vmx.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -856,21 +857,18 @@ static const unsigned short vmcs_field_t static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - /* - * FIXME: Mitigation for CVE-2017-5753. To be replaced with a - * generic mechanism. - */ - asm("lfence"); - - if (vmcs_field_to_offset_table[field] == 0) + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) return -ENOENT; - - return vmcs_field_to_offset_table[field]; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86: Introduce barrier_nospec" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86: Introduce barrier_nospec to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-introduce-barrier_nospec.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:33 -0800 Subject: x86: Introduce barrier_nospec From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit b3d7ad85b80bbc404635dca80f5b129f6242bc7a) Rename the open coded form of this instruction sequence from rdtsc_ordered() into a generic barrier primitive, barrier_nospec(). One of the mitigations for Spectre variant1 vulnerabilities is to fence speculative execution after successfully validating a bounds check. I.e. force the result of a bounds check to resolve in the instruction pipeline to ensure speculative execution honors that result before potentially operating on out-of-bounds data. No functional changes. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Suggested-by: Andi Kleen <ak(a)linux.intel.com> Suggested-by: Ingo Molnar <mingo(a)redhat.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727415361.33451.9049453007262764675.stgit@dwil… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/barrier.h | 4 ++++ arch/x86/include/asm/msr.h | 3 +-- 2 files changed, 5 insertions(+), 2 deletions(-) --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -47,6 +47,10 @@ static inline unsigned long array_index_ /* Override the default implementation from linux/nospec.h. */ #define array_index_mask_nospec array_index_mask_nospec +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -188,8 +188,7 @@ static __always_inline unsigned long lon * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:39 -0800 Subject: x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit b3bbfb3fb5d25776b8e3f361d2eedaabb0b496cd) For __get_user() paths, do not allow the kernel to speculate on the value of a user controlled pointer. In addition to the 'stac' instruction for Supervisor Mode Access Protection (SMAP), a barrier_nospec() causes the access_ok() result to resolve in the pipeline before the CPU might take any speculative action on the pointer value. Given the cost of 'stac' the speculation barrier is placed after 'stac' to hopefully overlap the cost of disabling SMAP with the cost of flushing the instruction pipeline. Since __get_user is a major kernel interface that deals with user controlled pointers, the __uaccess_begin_nospec() mechanism will prevent speculative execution past an access_ok() permission check. While speculative execution past access_ok() is not enough to lead to a kernel memory leak, it is a necessary precondition. To be clear, __uaccess_begin_nospec() is addressing a class of potential problems near __get_user() usages. Note, that while the barrier_nospec() in __uaccess_begin_nospec() is used to protect __get_user(), pointer masking similar to array_index_nospec() will be used for get_user() since it incorporates a bounds check near the usage. uaccess_try_nospec provides the same mechanism for get_user_try. No functional changes. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Suggested-by: Andi Kleen <ak(a)linux.intel.com> Suggested-by: Ingo Molnar <mingo(a)redhat.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727415922.33451.5796614273104346583.stgit@dwil… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/uaccess.h | 9 +++++++++ 1 file changed, 9 insertions(+) --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -123,6 +123,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -474,6 +479,10 @@ struct __large_struct { unsigned long bu __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86: Implement array_index_mask_nospec" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86: Implement array_index_mask_nospec to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-implement-array_index_mask_nospec.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:28 -0800 Subject: x86: Implement array_index_mask_nospec From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit babdde2698d482b6c0de1eab4f697cf5856c5859) array_index_nospec() uses a mask to sanitize user controllable array indexes, i.e. generate a 0 mask if 'index' >= 'size', and a ~0 mask otherwise. While the default array_index_mask_nospec() handles the carry-bit from the (index - size) result in software. The x86 array_index_mask_nospec() does the same, but the carry-bit is handled in the processor CF flag without conditional instructions in the control flow. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727414808.33451.1873237130672785331.stgit@dwil… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/barrier.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -23,6 +23,30 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/get_user: Use pointer masking to limit speculation" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/get_user: Use pointer masking to limit speculation to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-get_user-use-pointer-masking-to-limit-speculation.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:54 -0800 Subject: x86/get_user: Use pointer masking to limit speculation From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit c7f631cb07e7da06ac1d231ca178452339e32a94) Quoting Linus: I do think that it would be a good idea to very expressly document the fact that it's not that the user access itself is unsafe. I do agree that things like "get_user()" want to be protected, but not because of any direct bugs or problems with get_user() and friends, but simply because get_user() is an excellent source of a pointer that is obviously controlled from a potentially attacking user space. So it's a prime candidate for then finding _subsequent_ accesses that can then be used to perturb the cache. Unlike the __get_user() case get_user() includes the address limit check near the pointer de-reference. With that locality the speculation can be mitigated with pointer narrowing rather than a barrier, i.e. array_index_nospec(). Where the narrowing is performed by: cmp %limit, %ptr sbb %mask, %mask and %mask, %ptr With respect to speculation the value of %ptr is either less than %limit or NULL. Co-developed-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: Kees Cook <keescook(a)chromium.org> Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727417469.33451.11804043010080838495.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/lib/getuser.S | 10 ++++++++++ 1 file changed, 10 insertions(+) --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -39,6 +39,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -53,6 +55,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -67,6 +71,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -82,6 +88,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -93,6 +101,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/entry/64: Remove the SYSCALL64 fast path" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Remove the SYSCALL64 fast path to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-remove-the-syscall64-fast-path.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Andy Lutomirski <luto(a)kernel.org> Date: Sun, 28 Jan 2018 10:38:49 -0800 Subject: x86/entry/64: Remove the SYSCALL64 fast path From: Andy Lutomirski <luto(a)kernel.org> (cherry picked from commit 21d375b6b34ff511a507de27bf316b3dde6938d9) The SYCALLL64 fast path was a nice, if small, optimization back in the good old days when syscalls were actually reasonably fast. Now there is PTI to slow everything down, and indirect branches are verboten, making everything messier. The retpoline code in the fast path is particularly nasty. Just get rid of the fast path. The slow path is barely slower. [ tglx: Split out the 'push all extra regs' part ] Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Ingo Molnar <mingo(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Kernel Hardening <kernel-hardening(a)lists.openwall.com> Link: https://lkml.kernel.org/r/462dff8d4d64dfbfc851fbf3130641809d980ecd.15171644… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_64.S | 123 -------------------------------------------- arch/x86/entry/syscall_64.c | 7 -- 2 files changed, 3 insertions(+), 127 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -179,94 +179,11 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r11 /* pt_regs->r11 */ sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ -#ifdef CONFIG_RETPOLINE - movq sys_call_table(, %rax, 8), %rax - call __x86_indirect_thunk_rax -#else - call *sys_call_table(, %rax, 8) -#endif -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: - - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - RESTORE_C_REGS_EXCEPT_RCX_R11 - /* - * This opens a window where we have a user CR3, but are - * running in the kernel. This makes using the CS - * register useless for telling whether or not we need to - * switch CR3 in NMIs. Normal interrupts are OK because - * they are off here. - */ - SWITCH_USER_CR3 - movq RSP(%rsp), %rsp - USERGS_SYSRET64 - -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -339,6 +256,7 @@ return_from_SYSCALL_64: syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ RESTORE_C_REGS_EXCEPT_RCX_R11 + /* * This opens a window where we have a user CR3, but are * running in the kernel. This makes using the CS @@ -363,45 +281,6 @@ opportunistic_sysret_failed: jmp restore_c_regs_and_iret END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - popq %rax - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -6,14 +6,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); Patches currently in stable-queue which might be from luto(a)kernel.org are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/entry/64: Push extra regs right away" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/entry/64: Push extra regs right away to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-entry-64-push-extra-regs-right-away.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Andy Lutomirski <luto(a)kernel.org> Date: Sun, 28 Jan 2018 10:38:49 -0800 Subject: x86/entry/64: Push extra regs right away From: Andy Lutomirski <luto(a)kernel.org> (cherry picked from commit d1f7732009e0549eedf8ea1db948dc37be77fd46) With the fast path removed there is no point in splitting the push of the normal and the extra register set. Just push the extra regs right away. [ tglx: Split out from 'x86/entry/64: Remove the SYSCALL64 fast path' ] Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Ingo Molnar <mingo(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Kernel Hardening <kernel-hardening(a)lists.openwall.com> Link: https://lkml.kernel.org/r/462dff8d4d64dfbfc851fbf3130641809d980ecd.15171644… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/entry_64.S | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -177,10 +177,14 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ Patches currently in stable-queue which might be from luto(a)kernel.org are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Tue, 30 Jan 2018 14:30:23 +0000 Subject: x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 7fcae1118f5fd44a862aa5c3525248e35ee67c3b) Despite the fact that all the other code there seems to be doing it, just using set_cpu_cap() in early_intel_init() doesn't actually work. For CPUs with PKU support, setup_pku() calls get_cpu_cap() after c->c_init() has set those feature bits. That resets those bits back to what was queried from the hardware. Turning the bits off for bad microcode is easy to fix. That can just use setup_clear_cpu_cap() to force them off for all CPUs. I was less keen on forcing the feature bits *on* that way, just in case of inconsistencies. I appreciate that the kernel is going to get this utterly wrong if CPU features are not consistent, because it has already applied alternatives by the time secondary CPUs are brought up. But at least if setup_force_cpu_cap() isn't being used, we might have a chance of *detecting* the lack of the corresponding bit and either panicking or refusing to bring the offending CPU online. So ensure that the appropriate feature bits are set within get_cpu_cap() regardless of how many extra times it's called. Fixes: 2961298e ("x86/cpufeatures: Clean up Spectre v2 related CPUID flags") Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: karahmed(a)amazon.de Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Link: https://lkml.kernel.org/r/1517322623-15261-1-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/common.c | 21 +++++++++++++++++++++ arch/x86/kernel/cpu/intel.c | 27 ++++++++------------------- 2 files changed, 29 insertions(+), 19 deletions(-) --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -718,6 +718,26 @@ static void apply_forced_caps(struct cpu } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -812,6 +832,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -140,28 +140,17 @@ static void early_init_intel(struct cpui rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); } - /* - * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, - * and they also have a different bit for STIBP support. Also, - * a hypervisor might have set the individual AMD bits even on - * Intel CPUs, for finer-grained selection of what's available. - */ - if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { - set_cpu_cap(c, X86_FEATURE_IBRS); - set_cpu_cap(c, X86_FEATURE_IBPB); - } - if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) - set_cpu_cap(c, X86_FEATURE_STIBP); - /* Now if any of them are set, check the blacklist and clear the lot */ - if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); - clear_cpu_cap(c, X86_FEATURE_IBRS); - clear_cpu_cap(c, X86_FEATURE_IBPB); - clear_cpu_cap(c, X86_FEATURE_STIBP); - clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); - clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); } /* Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpu/bugs: Make retpoline module warning conditional" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpu/bugs: Make retpoline module warning conditional to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpu-bugs-make-retpoline-module-warning-conditional.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Sat, 27 Jan 2018 15:45:14 +0100 Subject: x86/cpu/bugs: Make retpoline module warning conditional From: Thomas Gleixner <tglx(a)linutronix.de> (cherry picked from commit e383095c7fe8d218e00ec0f83e4b95ed4e627b02) If sysfs is disabled and RETPOLINE not defined: arch/x86/kernel/cpu/bugs.c:97:13: warning: ‘spectre_v2_bad_module’ defined but not used [-Wunused-variable] static bool spectre_v2_bad_module; Hide it. Fixes: caf7501a1b4e ("module/retpoline: Warn about missing retpoline in module") Reported-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -93,9 +93,10 @@ static const char *spectre_v2_strings[] #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; -static bool spectre_v2_bad_module; #ifdef RETPOLINE +static bool spectre_v2_bad_module; + bool retpoline_module_ok(bool has_retpoline) { if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) @@ -105,6 +106,13 @@ bool retpoline_module_ok(bool has_retpol spectre_v2_bad_module = true; return false; } + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } #endif static void __init spec2_print_if_insecure(const char *reason) @@ -299,7 +307,7 @@ ssize_t cpu_show_spectre_v2(struct devic return sprintf(buf, "Not affected\n"); return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_IBPB) ? ", IPBP" : "", - spectre_v2_bad_module ? " - vulnerable module loaded" : ""); + boot_cpu_has(X86_FEATURE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); } #endif Patches currently in stable-queue which might be from tglx(a)linutronix.de are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/kaiser-fix-intel_bts-perf-crashes.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpufeatures: Clean up Spectre v2 related CPUID flags" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpufeatures: Clean up Spectre v2 related CPUID flags to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Sat, 27 Jan 2018 16:24:32 +0000 Subject: x86/cpufeatures: Clean up Spectre v2 related CPUID flags From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 2961298efe1ea1b6fc0d7ee8b76018fa6c0bcef2) We want to expose the hardware features simply in /proc/cpuinfo as "ibrs", "ibpb" and "stibp". Since AMD has separate CPUID bits for those, use them as the user-visible bits. When the Intel SPEC_CTRL bit is set which indicates both IBRS and IBPB capability, set those (AMD) bits accordingly. Likewise if the Intel STIBP bit is set, set the AMD STIBP that's used for the generic hardware capability. Hide the rest from /proc/cpuinfo by putting "" in the comments. Including RETPOLINE and RETPOLINE_AMD which shouldn't be visible there. There are patches to make the sysfs vulnerabilities information non-readable by non-root, and the same should apply to all information about which mitigations are actually in use. Those *shouldn't* appear in /proc/cpuinfo. The feature bit for whether IBPB is actually used, which is needed for ALTERNATIVEs, is renamed to X86_FEATURE_USE_IBPB. Originally-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: ak(a)linux.intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1517070274-12128-2-git-send-email-dwmw@amazon.co.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/cpufeatures.h | 18 +++++++++--------- arch/x86/include/asm/nospec-branch.h | 2 +- arch/x86/kernel/cpu/bugs.c | 7 +++---- arch/x86/kernel/cpu/intel.c | 31 +++++++++++++++++++++---------- 4 files changed, 34 insertions(+), 24 deletions(-) --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -194,15 +194,15 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ -#define X86_FEATURE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled*/ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -260,9 +260,9 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ -#define X86_FEATURE_AMD_PRED_CMD (13*32+12) /* Prediction Command MSR (AMD) */ -#define X86_FEATURE_AMD_SPEC_CTRL (13*32+14) /* Speculation Control MSR only (AMD) */ -#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors (AMD) */ +#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -301,8 +301,8 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ -#define X86_FEATURE_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ /* --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -225,7 +225,7 @@ static inline void indirect_branch_predi "movl %[val], %%eax\n\t" "movl $0, %%edx\n\t" "wrmsr", - X86_FEATURE_IBPB) + X86_FEATURE_USE_IBPB) : : [msr] "i" (MSR_IA32_PRED_CMD), [val] "i" (PRED_CMD_IBPB) : "eax", "ecx", "edx", "memory"); --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -272,9 +272,8 @@ retpoline_auto: } /* Initialize Indirect Branch Prediction Barrier if supported */ - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) || - boot_cpu_has(X86_FEATURE_AMD_PRED_CMD)) { - setup_force_cpu_cap(X86_FEATURE_IBPB); + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Enabling Indirect Branch Prediction Barrier\n"); } } @@ -307,7 +306,7 @@ ssize_t cpu_show_spectre_v2(struct devic return sprintf(buf, "Not affected\n"); return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", spectre_v2_module_string()); } #endif --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -140,17 +140,28 @@ static void early_init_intel(struct cpui rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); } - if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || - cpu_has(c, X86_FEATURE_STIBP) || - cpu_has(c, X86_FEATURE_AMD_SPEC_CTRL) || - cpu_has(c, X86_FEATURE_AMD_PRED_CMD) || - cpu_has(c, X86_FEATURE_AMD_STIBP)) && bad_spectre_microcode(c)) { - pr_warn("Intel Spectre v2 broken microcode detected; disabling SPEC_CTRL\n"); - clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); + + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + clear_cpu_cap(c, X86_FEATURE_IBRS); + clear_cpu_cap(c, X86_FEATURE_IBPB); clear_cpu_cap(c, X86_FEATURE_STIBP); - clear_cpu_cap(c, X86_FEATURE_AMD_SPEC_CTRL); - clear_cpu_cap(c, X86_FEATURE_AMD_PRED_CMD); - clear_cpu_cap(c, X86_FEATURE_AMD_STIBP); + clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); + clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP); } /* Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-retpoline-avoid-retpolines-for-built-in-__init-functions.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-cpu-bugs-make-retpoline-module-warning-conditional.patch queue-4.9/x86-spectre-check-config_retpoline-in-command-line-parser.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-cpuid-fix-up-virtual-ibrs-ibpb-stibp-feature-bits-on-intel.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-spectre-simplify-spectre_v2-command-line-parsing.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/x86-speculation-add-basic-ibpb-indirect-branch-prediction-barrier-support.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-speculation-fix-typo-ibrs_att-which-should-be-ibrs_all.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/asm: Move 'status' from thread_struct to thread_info" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/asm: Move 'status' from thread_struct to thread_info to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-asm-move-status-from-thread_struct-to-thread_info.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Andy Lutomirski <luto(a)kernel.org> Date: Sun, 28 Jan 2018 10:38:50 -0800 Subject: x86/asm: Move 'status' from thread_struct to thread_info From: Andy Lutomirski <luto(a)kernel.org> (cherry picked from commit 37a8f7c38339b22b69876d6f5a0ab851565284e3) The TS_COMPAT bit is very hot and is accessed from code paths that mostly also touch thread_info::flags. Move it into struct thread_info to improve cache locality. The only reason it was in thread_struct is that there was a brief period during which arch-specific fields were not allowed in struct thread_info. Linus suggested further changing: ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); to: if (unlikely(ti->status & (TS_COMPAT|TS_I386_REGS_POKED))) ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); on the theory that frequently dirtying the cacheline even in pure 64-bit code that never needs to modify status hurts performance. That could be a reasonable followup patch, but I suspect it matters less on top of this patch. Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Andy Lutomirski <luto(a)kernel.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Acked-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Kernel Hardening <kernel-hardening(a)lists.openwall.com> Link: https://lkml.kernel.org/r/03148bcc1b217100e6e8ecf6a5468c45cf4304b6.15171644… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/entry/common.c | 4 ++-- arch/x86/include/asm/processor.h | 2 -- arch/x86/include/asm/syscall.h | 6 +++--- arch/x86/include/asm/thread_info.h | 3 ++- arch/x86/kernel/process_64.c | 4 ++-- arch/x86/kernel/ptrace.c | 2 +- arch/x86/kernel/signal.c | 2 +- 7 files changed, 11 insertions(+), 12 deletions(-) --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -201,7 +201,7 @@ __visible inline void prepare_exit_to_us * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -299,7 +299,7 @@ static __always_inline void do_syscall_3 unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -391,8 +391,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(str * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -54,6 +54,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -213,7 +214,7 @@ static inline int arch_within_stack_fram #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -538,7 +538,7 @@ void set_personality_ia32(bool x32) current->personality &= ~READ_IMPLIES_EXEC; /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); @@ -546,7 +546,7 @@ void set_personality_ia32(bool x32) current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; } } EXPORT_SYMBOL_GPL(set_personality_ia32); --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -934,7 +934,7 @@ static int putreg32(struct task_struct * */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -785,7 +785,7 @@ static inline unsigned long get_nr_resta * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI Patches currently in stable-queue which might be from luto(a)kernel.org are queue-4.9/x86-entry-64-push-extra-regs-right-away.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/x86-asm-move-status-from-thread_struct-to-thread_info.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-entry-64-remove-the-syscall64-fast-path.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/bugs: Drop one "mitigation" from dmesg" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/bugs: Drop one "mitigation" from dmesg to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-bugs-drop-one-mitigation-from-dmesg.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Borislav Petkov <bp(a)suse.de> Date: Fri, 26 Jan 2018 13:11:39 +0100 Subject: x86/bugs: Drop one "mitigation" from dmesg From: Borislav Petkov <bp(a)suse.de> (cherry picked from commit 55fa19d3e51f33d9cd4056d25836d93abf9438db) Make [ 0.031118] Spectre V2 mitigation: Mitigation: Full generic retpoline into [ 0.031118] Spectre V2: Mitigation: Full generic retpoline to reduce the mitigation mitigations strings. Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: riel(a)redhat.com Cc: ak(a)linux.intel.com Cc: peterz(a)infradead.org Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: jikos(a)kernel.org Cc: luto(a)amacapital.net Cc: dave.hansen(a)intel.com Cc: torvalds(a)linux-foundation.org Cc: keescook(a)google.com Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: tim.c.chen(a)linux.intel.com Cc: pjt(a)google.com Link: https://lkml.kernel.org/r/20180126121139.31959-5-bp@alien8.de Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -90,7 +90,7 @@ static const char *spectre_v2_strings[] }; #undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; static bool spectre_v2_bad_module; Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/alternative: Print unadorned pointers" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/alternative: Print unadorned pointers to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-alternative-print-unadorned-pointers.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:30:27 CET 2018 From: Borislav Petkov <bp(a)suse.de> Date: Fri, 26 Jan 2018 13:11:36 +0100 Subject: x86/alternative: Print unadorned pointers From: Borislav Petkov <bp(a)suse.de> (cherry picked from commit 0e6c16c652cadaffd25a6bb326ec10da5bcec6b4) After commit ad67b74d2469 ("printk: hash addresses printed with %p") pointers are being hashed when printed. However, this makes the alternative debug output completely useless. Switch to %px in order to see the unadorned kernel pointers. Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: riel(a)redhat.com Cc: ak(a)linux.intel.com Cc: peterz(a)infradead.org Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: jikos(a)kernel.org Cc: luto(a)amacapital.net Cc: dave.hansen(a)intel.com Cc: torvalds(a)linux-foundation.org Cc: keescook(a)google.com Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Cc: pjt(a)google.com Link: https://lkml.kernel.org/r/20180126121139.31959-2-bp@alien8.de Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/alternative.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -298,7 +298,7 @@ recompute_jump(struct alt_instr *a, u8 * tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -352,7 +352,7 @@ static void __init_or_module optimize_no sync_core(); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -370,7 +370,7 @@ void __init_or_module apply_alternatives u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %p -> %p", start, end); + DPRINTK("alt table %px, -> %px", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -394,14 +394,14 @@ void __init_or_module apply_alternatives continue; } - DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -422,7 +422,7 @@ void __init_or_module apply_alternatives a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } Patches currently in stable-queue which might be from bp(a)suse.de are queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-retpoline-simplify-vmexit_fill_rsb.patch queue-4.9/x86-cpufeatures-clean-up-spectre-v2-related-cpuid-flags.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/x86-microcode-amd-do-not-load-when-running-on-a-hypervisor.patch queue-4.9/x86-nospec-fix-header-guards-names.patch queue-4.9/x86-alternative-print-unadorned-pointers.patch queue-4.9/x86-spectre-fix-spelling-mistake-vunerable-vulnerable.patch queue-4.9/x86-pti-mark-constant-arrays-as-__initconst.patch queue-4.9/x86-bugs-drop-one-mitigation-from-dmesg.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "nl80211: Sanitize array index in parse_txq_params" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled nl80211: Sanitize array index in parse_txq_params to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: nl80211-sanitize-array-index-in-parse_txq_params.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:03:15 -0800 Subject: nl80211: Sanitize array index in parse_txq_params From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit 259d8c1e984318497c84eef547bbb6b1d9f4eb05) Wireless drivers rely on parse_txq_params to validate that txq_params->ac is less than NL80211_NUM_ACS by the time the low-level driver's ->conf_tx() handler is called. Use a new helper, array_index_nospec(), to sanitize txq_params->ac with respect to speculation. I.e. ensure that any speculation into ->conf_tx() handlers is done with a value of txq_params->ac that is within the bounds of [0, NL80211_NUM_ACS). Reported-by: Christian Lamparter <chunkeey(a)gmail.com> Reported-by: Elena Reshetova <elena.reshetova(a)intel.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: Johannes Berg <johannes(a)sipsolutions.net> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: linux-wireless(a)vger.kernel.org Cc: torvalds(a)linux-foundation.org Cc: "David S. Miller" <davem(a)davemloft.net> Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727419584.33451.7700736761686184303.stgit@dwil… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/wireless/nl80211.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16,6 +16,7 @@ #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/genetlink.h> @@ -2014,20 +2015,22 @@ static const struct nla_policy txq_param static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { + u8 ac; + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); + ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); - if (txq_params->ac >= NL80211_NUM_ACS) + if (ac >= NL80211_NUM_ACS) return -EINVAL; - + txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS); return 0; } Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "vfs, fdtable: Prevent bounds-check bypass via speculative execution" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled vfs, fdtable: Prevent bounds-check bypass via speculative execution to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:03:05 -0800 Subject: vfs, fdtable: Prevent bounds-check bypass via speculative execution From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit 56c30ba7b348b90484969054d561f711ba196507) 'fd' is a user controlled value that is used as a data dependency to read from the 'fdt->fd' array. In order to avoid potential leaks of kernel memory values, block speculative execution of the instruction stream that could issue reads based on an invalid 'file *' returned from __fcheck_files. Co-developed-by: Elena Reshetova <elena.reshetova(a)intel.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: gregkh(a)linuxfoundation.org Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727418500.33451.17392199002892248656.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- include/linux/fdtable.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -9,6 +9,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> @@ -81,8 +82,10 @@ static inline struct file *__fcheck_file { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - if (fd < fdt->max_fds) + if (fd < fdt->max_fds) { + fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); + } return NULL; } Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "array_index_nospec: Sanitize speculative array de-references" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled array_index_nospec: Sanitize speculative array de-references to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: array_index_nospec-sanitize-speculative-array-de-references.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Dan Williams <dan.j.williams(a)intel.com> Date: Mon, 29 Jan 2018 17:02:22 -0800 Subject: array_index_nospec: Sanitize speculative array de-references From: Dan Williams <dan.j.williams(a)intel.com> (cherry picked from commit f3804203306e098dae9ca51540fcd5eb700d7f40) array_index_nospec() is proposed as a generic mechanism to mitigate against Spectre-variant-1 attacks, i.e. an attack that bypasses boundary checks via speculative execution. The array_index_nospec() implementation is expected to be safe for current generation CPUs across multiple architectures (ARM, x86). Based on an original implementation by Linus Torvalds, tweaked to remove speculative flows by Alexei Starovoitov, and tweaked again by Linus to introduce an x86 assembly implementation for the mask generation. Co-developed-by: Linus Torvalds <torvalds(a)linux-foundation.org> Co-developed-by: Alexei Starovoitov <ast(a)kernel.org> Suggested-by: Cyril Novikov <cnovikov(a)lynx.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: linux-arch(a)vger.kernel.org Cc: kernel-hardening(a)lists.openwall.com Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Russell King <linux(a)armlinux.org.uk> Cc: gregkh(a)linuxfoundation.org Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727414229.33451.18411580953862676575.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- include/linux/nospec.h | 72 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 include/linux/nospec.h --- /dev/null +++ b/include/linux/nospec.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Linus Torvalds. All rights reserved. +// Copyright(c) 2018 Alexei Starovoitov. All rights reserved. +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#ifndef _LINUX_NOSPEC_H +#define _LINUX_NOSPEC_H + +/** + * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * When @index is out of bounds (@index >= @size), the sign bit will be + * set. Extend the sign bit to all bits and invert, giving a result of + * zero for an out of bounds index, or ~0 if within bounds [0, @size). + */ +#ifndef array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) + return 0; + + /* + * Always calculate and emit the mask even if the compiler + * thinks the mask is not needed. The compiler does not take + * into account the value of @index under speculation. + */ + OPTIMIZER_HIDE_VAR(index); + return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); +} +#endif + +/* + * array_index_nospec - sanitize an array index after a bounds check + * + * For a code sequence like: + * + * if (index < size) { + * index = array_index_nospec(index, size); + * val = array[index]; + * } + * + * ...if the CPU speculates past the bounds check then + * array_index_nospec() will clamp the index within the range of [0, + * size). + */ +#define array_index_nospec(index, size) \ +({ \ + typeof(index) _i = (index); \ + typeof(size) _s = (size); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ + \ + BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ + BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ + \ + _i &= _mask; \ + _i; \ +}) +#endif /* _LINUX_NOSPEC_H */ Patches currently in stable-queue which might be from dan.j.williams(a)intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-paravirt-remove-noreplace-paravirt-cmdline-option.patch queue-4.9/documentation-document-array_index_nospec.patch queue-4.9/x86-usercopy-replace-open-coded-stac-clac-with-__uaccess_-begin-end.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/vfs-fdtable-prevent-bounds-check-bypass-via-speculative-execution.patch queue-4.9/x86-uaccess-use-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/x86-implement-array_index_mask_nospec.patch queue-4.9/array_index_nospec-sanitize-speculative-array-de-references.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-kvm-update-spectre-v1-mitigation.patch queue-4.9/x86-get_user-use-pointer-masking-to-limit-speculation.patch queue-4.9/x86-syscall-sanitize-syscall-table-de-references-under-speculation.patch queue-4.9/x86-spectre-report-get_user-mitigation-for-spectre_v1.patch queue-4.9/x86-introduce-barrier_nospec.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-introduce-__uaccess_begin_nospec-and-uaccess_try_nospec.patch queue-4.9/nl80211-sanitize-array-index-in-parse_txq_params.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "Documentation: Document array_index_nospec" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled Documentation: Document array_index_nospec to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: documentation-document-array_index_nospec.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Thu Feb 8 03:32:24 CET 2018 From: Mark Rutland <mark.rutland(a)arm.com> Date: Mon, 29 Jan 2018 17:02:16 -0800 Subject: Documentation: Document array_index_nospec From: Mark Rutland <mark.rutland(a)arm.com> (cherry picked from commit f84a56f73dddaeac1dba8045b007f742f61cd2da) Document the rationale and usage of the new array_index_nospec() helper. Signed-off-by: Mark Rutland <mark.rutland(a)arm.com> Signed-off-by: Will Deacon <will.deacon(a)arm.com> Signed-off-by: Dan Williams <dan.j.williams(a)intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Kees Cook <keescook(a)chromium.org> Cc: linux-arch(a)vger.kernel.org Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: gregkh(a)linuxfoundation.org Cc: kernel-hardening(a)lists.openwall.com Cc: torvalds(a)linux-foundation.org Cc: alan(a)linux.intel.com Link: https://lkml.kernel.org/r/151727413645.33451.15878817161436755393.stgit@dwi… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- Documentation/speculation.txt | 90 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 90 insertions(+) create mode 100644 Documentation/speculation.txt --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,90 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else + return array[index]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP <index>, #MAX_ARRAY_ELEMS + B.LT less + MOV <returnval>, #0 + RET + less: + LDR <returnval>, [<array>, <index>] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This +value will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may +result in sensitive information being leaked. Consider the following +code, building on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int index) + { + int val1, val2, + + val1 = load_array(arr1, index); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value +of an out-of-bounds address, while the second call will influence +microarchitectural state dependent on this value. This may provide an +arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are +respected even under speculation. Architectures which are affected by +speculation-based side-channels are expected to implement these +primitives. + +The array_index_nospec() helper in <linux/nospec.h> can be used to +prevent information from being leaked via side-channels. + +A call to array_index_nospec(index, size) returns a sanitized index +value that is bounded to [0, size) even under cpu speculation +conditions. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else { + index = array_index_nospec(index, MAX_ARRAY_ELEMS); + return array[index]; + } + } Patches currently in stable-queue which might be from mark.rutland(a)arm.com are queue-4.9/documentation-document-array_index_nospec.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCH 4.14 000/159] 4.14.9-stable review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 4.14.9 release. There are 159 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Sun Dec 24 08:45:36 UTC 2017. Anything received after that time might be too late. The whole patch series can be found in one patch at: kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.9-rc1.gz or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 4.14.9-rc1 Peter Hutterer <peter.hutterer(a)who-t.net> platform/x86: asus-wireless: send an EV_SYN/SYN_REPORT between state changes Daniel Lezcano <daniel.lezcano(a)linaro.org> thermal/drivers/hisi: Fix multiple alarm interrupts firing Daniel Lezcano <daniel.lezcano(a)linaro.org> thermal/drivers/hisi: Simplify the temperature/step computation Daniel Lezcano <daniel.lezcano(a)linaro.org> thermal/drivers/hisi: Fix kernel panic on alarm interrupt Daniel Lezcano <daniel.lezcano(a)linaro.org> thermal/drivers/hisi: Fix missing interrupt enablement Niranjana Vishwanathapura <niranjana.vishwanathapura(a)intel.com> IB/opa_vnic: Properly return the total MACs in UC MAC list Scott Franco <safranco(a)intel.com> IB/opa_vnic: Properly clear Mac Table Digest Eric Anholt <eric(a)anholt.net> drm/vc4: Avoid using vrefresh==0 mode in DSI htotal math. Nicholas Piggin <npiggin(a)gmail.com> cpuidle: fix broadcast control when broadcast can not be entered Alexandre Belloni <alexandre.belloni(a)free-electrons.com> rtc: set the alarm to the next expiring timer Hoang Tran <tranviethoang.vn(a)gmail.com> tcp: fix under-evaluated ssthresh in TCP Vegas Chen-Yu Tsai <wens(a)csie.org> clk: sunxi-ng: sun6i: Rename HDMI DDC clock to avoid name collision Arvind Yadav <arvind.yadav.cs(a)gmail.com> staging: greybus: light: Release memory obtained by kasprintf Wei Hu(Xavier) <xavier.huwei(a)huawei.com> RDMA/hns: Avoid NULL pointer exception Mike Manning <mmanning(a)brocade.com> net: ipv6: send NS for DAD when link operationally up Mick Tarsel <mjtarsel(a)linux.vnet.ibm.com> ibmvnic: Set state UP Jacob Keller <jacob.e.keller(a)intel.com> fm10k: ensure we process SM mbx when processing VF mbx Marek Szyprowski <m.szyprowski(a)samsung.com> ARM: exynos_defconfig: Enable UAS support for Odroid HC1 board Alex Williamson <alex.williamson(a)redhat.com> vfio/pci: Virtualize Maximum Payload Size Alan Brady <alan.brady(a)intel.com> i40e: fix client notify of VF reset Dick Kennedy <dick.kennedy(a)broadcom.com> scsi: lpfc: Fix warning messages when NVME_TARGET_FC not defined Dick Kennedy <dick.kennedy(a)broadcom.com> scsi: lpfc: PLOGI failures during NPIV testing Dick Kennedy <dick.kennedy(a)broadcom.com> scsi: lpfc: Fix secure firmware updates Jacob Keller <jacob.e.keller(a)intel.com> fm10k: fix mis-ordered parameters in declaration for .ndo_set_vf_bw Nicolas Dechesne <nicolas.dechesne(a)linaro.org> ASoC: codecs: msm8916-wcd-analog: fix module autoload Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> sctp: silence warns on sctp_stream_init allocations Nicholas Piggin <npiggin(a)gmail.com> powerpc/watchdog: Do not trigger SMP crash from touch_nmi_watchdog Nicholas Piggin <npiggin(a)gmail.com> powerpc/xmon: Avoid tripping SMP hardlockup watchdog Ed Blake <ed.blake(a)sondrel.com> ASoC: img-parallel-out: Add pm_runtime_get/put to set_fmt callback Jean-François Têtu <jean-francois.tetu(a)savoirfairelinux.com> ASoC: codecs: msm8916-wcd-analog: fix micbias level Tom Zanussi <tom.zanussi(a)linux.intel.com> tracing: Exclude 'generic fields' from histograms Gabriele Paoloni <gabriele.paoloni(a)huawei.com> PCI/AER: Report non-fatal errors only to the affected endpoint Jacob Keller <jacob.e.keller(a)intel.com> i40e/i40evf: spread CPU affinity hints across online CPUs only Hans de Goede <hdegoede(a)redhat.com> Bluetooth: hci_bcm: Fix setting of irq trigger type Hans de Goede <hdegoede(a)redhat.com> Bluetooth: hci_uart_set_flow_control: Fix NULL deref when using serdev Andrew Jeffery <andrew(a)aj.id.au> leds: pca955x: Don't invert requested value in pca955x_gpio_set_value() Wei Wang <weiwan(a)google.com> ipv6: grab rt->rt6i_ref before allocating pcpu rt William Tu <u9012063(a)gmail.com> ip_gre: check packet length and mtu correctly in erspan tx Guoqing Jiang <gqjiang(a)suse.com> md: always set THREAD_WAKEUP and wake up wqueue if thread existed Luca Miccio <lucmiccio(a)gmail.com> block,bfq: Disable writeback throttling Colin Ian King <colin.king(a)canonical.com> IB/rxe: check for allocation failure on elem Emil Tantilov <emil.s.tantilov(a)intel.com> ixgbe: fix use of uninitialized padding Lorenzo Bianconi <lorenzo.bianconi83(a)gmail.com> iio: st_sensors: add register mask for status register Lihong Yang <lihong.yang(a)intel.com> i40e: use the safe hash table iterator when deleting mac filters Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> igb: check memory allocation failure Fabio Estevam <fabio.estevam(a)nxp.com> PM / OPP: Move error message to debug level Stuart Hayes <stuart.w.hayes(a)gmail.com> PCI: Create SR-IOV virtfn/physfn links before attaching driver Sreekanth Reddy <sreekanth.reddy(a)broadcom.com> scsi: mpt3sas: Fix IO error occurs on pulling out a drive from RAID1 volume created on two SATA drive Varun Prakash <varun(a)chelsio.com> scsi: cxgb4i: fix Tx skb leak David Daney <david.daney(a)cavium.com> PCI: Avoid bus reset if bridge itself is broken Dan Murphy <dmurphy(a)ti.com> net: phy: at803x: Change error to EINVAL for invalid MAC Shakeel Butt <shakeelb(a)google.com> kvm, mm: account kvm related kmem slabs to kmemcg Russell King <rmk+kernel(a)armlinux.org.uk> rtc: pl031: make interrupt optional Christophe Jaillet <christophe.jaillet(a)wanadoo.fr> crypto: lrw - Fix an error handling path in 'create()' Christian Lamparter <chunkeey(a)gmail.com> crypto: crypto4xx - increase context and scatter ring buffer elements Chen-Yu Tsai <wens(a)csie.org> clk: sunxi-ng: sun5i: Fix bit offset of audio PLL post-divider Chen-Yu Tsai <wens(a)csie.org> clk: sunxi-ng: nm: Check if requested rate is supported by fractional clock Shashank Sharma <shashank.sharma(a)intel.com> drm: Add retries for lspcon mode detection Derek Basehore <dbasehore(a)chromium.org> backlight: pwm_bl: Fix overflow condition Jens Wiklander <jens.wiklander(a)linaro.org> optee: fix invalid of_node_put() in optee_driver_init() Thomas Gleixner <tglx(a)linutronix.de> x86/cpufeatures: Make CPU bugs sticky Thomas Gleixner <tglx(a)linutronix.de> x86/paravirt: Provide a way to check for hypervisors Thomas Gleixner <tglx(a)linutronix.de> x86/paravirt: Dont patch flush_tlb_single Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Make cpu_entry_area.tss read-only Andy Lutomirski <luto(a)kernel.org> x86/entry: Clean up the SYSENTER_stack code Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Remove the SYSENTER stack canary Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Move the IST stacks into struct cpu_entry_area Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Create a per-CPU SYSCALL entry trampoline Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Return to userspace from the trampoline stack Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Use a per-CPU trampoline stack for IDT entries Andy Lutomirski <luto(a)kernel.org> x86/espfix/64: Stop assuming that pt_regs is on the entry stack Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0 Andy Lutomirski <luto(a)kernel.org> x86/entry: Remap the TSS into the CPU entry area Andy Lutomirski <luto(a)kernel.org> x86/entry: Move SYSENTER_stack to the beginning of struct tss_struct Andy Lutomirski <luto(a)kernel.org> x86/dumpstack: Handle stack overflow on all stacks Andy Lutomirski <luto(a)kernel.org> x86/entry: Fix assumptions that the HW TSS is at the beginning of cpu_tss Andy Lutomirski <luto(a)kernel.org> x86/kasan/64: Teach KASAN about the cpu_entry_area Andy Lutomirski <luto(a)kernel.org> x86/mm/fixmap: Generalize the GDT fixmap mechanism, introduce struct cpu_entry_area Andy Lutomirski <luto(a)kernel.org> x86/entry/gdt: Put per-CPU GDT remaps in ascending order Andy Lutomirski <luto(a)kernel.org> x86/dumpstack: Add get_stack_info() support for the SYSENTER stack Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Allocate and enable the SYSENTER stack Andy Lutomirski <luto(a)kernel.org> x86/irq/64: Print the offending IP in the stack overflow warning Andy Lutomirski <luto(a)kernel.org> x86/irq: Remove an old outdated comment about context tracking races Josh Poimboeuf <jpoimboe(a)redhat.com> x86/unwinder: Handle stack overflows more gracefully Andy Lutomirski <luto(a)kernel.org> x86/unwinder/orc: Dont bail on stack overflow Boris Ostrovsky <boris.ostrovsky(a)oracle.com> x86/entry/64/paravirt: Use paravirt-safe macro to access eflags Andrey Ryabinin <aryabinin(a)virtuozzo.com> x86/mm/kasan: Don't use vmemmap_populate() to initialize shadow Will Deacon <will.deacon(a)arm.com> locking/barriers: Convert users of lockless_dereference() to READ_ONCE() Will Deacon <will.deacon(a)arm.com> locking/barriers: Add implicit smp_read_barrier_depends() to READ_ONCE() Daniel Borkmann <daniel(a)iogearbox.net> bpf: fix build issues on um due to mising bpf_perf_event.h Andi Kleen <ak(a)linux.intel.com> perf/x86: Enable free running PEBS for REGS_USER/INTR Rudolf Marek <r.marek(a)assembler.cz> x86: Make X86_BUG_FXSAVE_LEAK detectable in CPUID on AMD Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> x86/cpufeature: Add User-Mode Instruction Prevention definitions Ingo Molnar <mingo(a)kernel.org> drivers/misc/intel/pti: Rename the header file to free up the namespace Juergen Gross <jgross(a)suse.com> x86/virt: Add enum for hypervisors to replace x86_hyper Juergen Gross <jgross(a)suse.com> x86/virt, x86/platform: Merge 'struct x86_hyper' into 'struct x86_platform' and 'struct x86_init' James Morse <james.morse(a)arm.com> ACPI / APEI: Replace ioremap_page_range() with fixmap Andy Lutomirski <luto(a)kernel.org> selftests/x86/ldt_gdt: Run most existing LDT test cases against the GDT as well Andy Lutomirski <luto(a)kernel.org> selftests/x86/ldt_gdt: Add infrastructure to test set_thread_area() Ingo Molnar <mingo(a)kernel.org> x86/cpufeatures: Fix various details in the feature definitions Ingo Molnar <mingo(a)kernel.org> x86/cpufeatures: Re-tabulate the X86_FEATURE definitions Borislav Petkov <bp(a)suse.de> x86/mm: Define _PAGE_TABLE using _KERNPG_TABLE Thomas Gleixner <tglx(a)linutronix.de> bitops: Revert cbe96375025e ("bitops: Add clear/set_bit32() to linux/bitops.h") Thomas Gleixner <tglx(a)linutronix.de> x86/cpuid: Replace set/clear_bit32() Borislav Petkov <bp(a)suse.de> x86/entry/64: Shorten TEST instructions Andy Lutomirski <luto(a)kernel.org> x86/traps: Use a new on_thread_stack() helper to clean up an assertion Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Remove thread_struct::sp0 Andy Lutomirski <luto(a)kernel.org> x86/entry/32: Fix cpu_current_top_of_stack initialization at boot Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Remove all remaining direct thread_struct::sp0 reads Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Stop initializing TSS.sp0 at boot Andy Lutomirski <luto(a)kernel.org> x86/xen/64, x86/entry/64: Clean up SP code in cpu_initialize_context() Andy Lutomirski <luto(a)kernel.org> x86/entry: Add task_top_of_stack() to find the top of a task's stack Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Pass SP0 directly to load_sp0() Andy Lutomirski <luto(a)kernel.org> x86/entry/32: Pull the MSR_IA32_SYSENTER_CS update code out of native_load_sp0() Andy Lutomirski <luto(a)kernel.org> x86/entry/64: De-Xen-ify our NMI code Juergen Gross <jgross(a)suse.com> xen, x86/entry/64: Add xen NMI trap entry Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Remove the RESTORE_..._REGS infrastructure Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Use POP instead of MOV to restore regs on NMI return Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Merge the fast and slow SYSRET paths Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Use pop instead of movq in syscall_return_via_sysret Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Shrink paranoid_exit_restore and make labels local Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Simplify reg restore code in the standard IRET paths Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Move SWAPGS into the common IRET-to-usermode path Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Split the IRET-to-user and IRET-to-kernel paths Andy Lutomirski <luto(a)kernel.org> x86/entry/64: Remove the restore_c_regs_and_iret label Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> ptrace,x86: Make user_64bit_mode() available to 32-bit builds Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> x86/boot: Relocate definition of the initial state of CR0 Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> x86/mm: Relocate page fault error codes to traps.h Gayatri Kammela <gayatri.kammela(a)intel.com> x86/cpufeatures: Enable new SSE/AVX/AVX512 CPU features Baoquan He <bhe(a)redhat.com> x86/mm/64: Rename the register_page_bootmem_memmap() 'size' parameter to 'nr_pages' Masahiro Yamada <yamada.masahiro(a)socionext.com> x86/build: Beautify build log of syscall headers Josh Poimboeuf <jpoimboe(a)redhat.com> x86/asm: Don't use the confusing '.ifeq' directive Dongjiu Geng <gengdongjiu(a)huawei.com> ACPI / APEI: remove the unused dead-code for SEA/NMI notification type Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> x86/xen: Drop 5-level paging support code from the XEN_PV code Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> x86/xen: Provide pre-built page tables only for CONFIG_XEN_PV=y and CONFIG_XEN_PVH=y Andrey Ryabinin <aryabinin(a)virtuozzo.com> x86/kasan: Use the same shadow offset for 4- and 5-level paging Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y Thomas Gleixner <tglx(a)linutronix.de> x86/cpuid: Prevent out of bound access in do_clear_cpu_cap() Kamalesh Babulal <kamalesh(a)linux.vnet.ibm.com> objtool: Print top level commands on incorrect usage Kees Cook <keescook(a)chromium.org> x86/platform/UV: Convert timers to use timer_setup() Andi Kleen <ak(a)linux.intel.com> x86/fpu: Remove the explicit clearing of XSAVE dependent features Andi Kleen <ak(a)linux.intel.com> x86/fpu: Make XSAVE check the base CPUID features before enabling Andi Kleen <ak(a)linux.intel.com> x86/fpu: Parse clearcpuid= as early XSAVE argument Andi Kleen <ak(a)linux.intel.com> x86/cpuid: Add generic table for CPUID dependencies Andi Kleen <ak(a)linux.intel.com> bitops: Add clear/set_bit32() to linux/bitops.h Josh Poimboeuf <jpoimboe(a)redhat.com> x86/unwind: Make CONFIG_UNWINDER_ORC=y the default in kconfig for 64-bit Josh Poimboeuf <jpoimboe(a)redhat.com> x86/unwind: Rename unwinder config options to 'CONFIG_UNWINDER_*' Steven Rostedt (VMware) <rostedt(a)goodmis.org> x86/fpu/debug: Remove unused 'x86_fpu_state' and 'x86_fpu_deactivate_state' tracepoints Ingo Molnar <mingo(a)kernel.org> x86/unwinder: Make CONFIG_UNWINDER_ORC=y the default in the 64-bit defconfig Jan Beulich <JBeulich(a)suse.com> ACPI / APEI: adjust a local variable type in ghes_ioremap_pfn_irq() Josh Poimboeuf <jpoimboe(a)redhat.com> x86/head: Add unwind hint annotations Josh Poimboeuf <jpoimboe(a)redhat.com> x86/xen: Add unwind hint annotations Josh Poimboeuf <jpoimboe(a)redhat.com> x86/xen: Fix xen head ELF annotations Josh Poimboeuf <jpoimboe(a)redhat.com> x86/boot: Annotate verify_cpu() as a callable function Josh Poimboeuf <jpoimboe(a)redhat.com> x86/head: Fix head ELF function annotations Josh Poimboeuf <jpoimboe(a)redhat.com> x86/head: Remove unused 'bad_address' code Josh Poimboeuf <jpoimboe(a)redhat.com> x86/head: Remove confusing comment Josh Poimboeuf <jpoimboe(a)redhat.com> objtool: Don't report end of section error after an empty unwind hint Uros Bizjak <ubizjak(a)gmail.com> x86/asm: Remove unnecessary \n\t in front of CC_SET() from asm templates ------------- Diffstat: Documentation/x86/orc-unwinder.txt | 2 +- Documentation/x86/x86_64/mm.txt | 2 +- Makefile | 8 +- arch/arm/configs/exynos_defconfig | 2 +- arch/arm64/include/asm/fixmap.h | 7 + arch/powerpc/kernel/watchdog.c | 7 +- arch/powerpc/xmon/xmon.c | 17 +- arch/um/include/asm/Kbuild | 1 + arch/x86/Kconfig | 5 +- arch/x86/Kconfig.debug | 39 +- arch/x86/configs/tiny.config | 4 +- arch/x86/configs/x86_64_defconfig | 1 + arch/x86/entry/calling.h | 69 +-- arch/x86/entry/entry_32.S | 6 +- arch/x86/entry/entry_64.S | 322 +++++++++--- arch/x86/entry/entry_64_compat.S | 10 +- arch/x86/entry/syscalls/Makefile | 4 +- arch/x86/events/core.c | 2 +- arch/x86/events/intel/core.c | 4 + arch/x86/events/perf_event.h | 24 +- arch/x86/hyperv/hv_init.c | 2 +- arch/x86/include/asm/archrandom.h | 8 +- arch/x86/include/asm/bitops.h | 10 +- arch/x86/include/asm/compat.h | 1 + arch/x86/include/asm/cpufeature.h | 11 +- arch/x86/include/asm/cpufeatures.h | 538 +++++++++++---------- arch/x86/include/asm/desc.h | 11 +- arch/x86/include/asm/fixmap.h | 74 ++- arch/x86/include/asm/hypervisor.h | 53 +- arch/x86/include/asm/irqflags.h | 3 + arch/x86/include/asm/kdebug.h | 1 + arch/x86/include/asm/mmu_context.h | 4 +- arch/x86/include/asm/module.h | 2 +- arch/x86/include/asm/paravirt.h | 14 +- arch/x86/include/asm/paravirt_types.h | 2 +- arch/x86/include/asm/percpu.h | 2 +- arch/x86/include/asm/pgtable_types.h | 3 +- arch/x86/include/asm/processor.h | 109 +++-- arch/x86/include/asm/ptrace.h | 6 +- arch/x86/include/asm/rmwcc.h | 2 +- arch/x86/include/asm/stacktrace.h | 3 + arch/x86/include/asm/switch_to.h | 26 + arch/x86/include/asm/thread_info.h | 2 +- arch/x86/include/asm/trace/fpu.h | 10 - arch/x86/include/asm/traps.h | 21 +- arch/x86/include/asm/unwind.h | 15 +- arch/x86/include/asm/x86_init.h | 24 + arch/x86/include/uapi/asm/processor-flags.h | 3 + arch/x86/kernel/Makefile | 10 +- arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/apic/x2apic_uv_x.c | 5 +- arch/x86/kernel/asm-offsets.c | 6 + arch/x86/kernel/asm-offsets_32.c | 9 +- arch/x86/kernel/asm-offsets_64.c | 4 + arch/x86/kernel/cpu/Makefile | 1 + arch/x86/kernel/cpu/amd.c | 7 +- arch/x86/kernel/cpu/common.c | 195 +++++--- arch/x86/kernel/cpu/cpuid-deps.c | 121 +++++ arch/x86/kernel/cpu/hypervisor.c | 64 +-- arch/x86/kernel/cpu/mshyperv.c | 6 +- arch/x86/kernel/cpu/vmware.c | 8 +- arch/x86/kernel/doublefault.c | 36 +- arch/x86/kernel/dumpstack.c | 74 ++- arch/x86/kernel/dumpstack_32.c | 6 + arch/x86/kernel/dumpstack_64.c | 6 + arch/x86/kernel/fpu/init.c | 11 + arch/x86/kernel/fpu/xstate.c | 43 +- arch/x86/kernel/head_32.S | 5 +- arch/x86/kernel/head_64.S | 45 +- arch/x86/kernel/ioport.c | 2 +- arch/x86/kernel/irq.c | 12 - arch/x86/kernel/irq_64.c | 4 +- arch/x86/kernel/kvm.c | 6 +- arch/x86/kernel/ldt.c | 2 +- arch/x86/kernel/paravirt_patch_64.c | 2 - arch/x86/kernel/process.c | 27 +- arch/x86/kernel/process_32.c | 8 +- arch/x86/kernel/process_64.c | 19 +- arch/x86/kernel/smpboot.c | 3 +- arch/x86/kernel/traps.c | 72 +-- arch/x86/kernel/unwind_orc.c | 88 ++-- arch/x86/kernel/verify_cpu.S | 3 +- arch/x86/kernel/vm86_32.c | 20 +- arch/x86/kernel/vmlinux.lds.S | 9 + arch/x86/kernel/x86_init.c | 9 + arch/x86/kvm/mmu.c | 4 +- arch/x86/kvm/vmx.c | 2 +- arch/x86/lib/delay.c | 4 +- arch/x86/mm/fault.c | 88 ++-- arch/x86/mm/init.c | 2 +- arch/x86/mm/init_64.c | 10 +- arch/x86/mm/kasan_init_64.c | 262 ++++++++-- arch/x86/power/cpu.c | 16 +- arch/x86/xen/enlighten_hvm.c | 12 +- arch/x86/xen/enlighten_pv.c | 15 +- arch/x86/xen/mmu_pv.c | 161 +++--- arch/x86/xen/smp_pv.c | 17 +- arch/x86/xen/xen-asm_64.S | 2 +- arch/x86/xen/xen-head.S | 11 +- block/bfq-iosched.c | 3 +- block/blk-wbt.c | 2 +- crypto/lrw.c | 6 +- drivers/acpi/apei/ghes.c | 78 +-- drivers/base/power/opp/core.c | 2 +- drivers/bluetooth/hci_bcm.c | 23 +- drivers/bluetooth/hci_ldisc.c | 7 + drivers/clk/sunxi-ng/ccu-sun5i.c | 4 +- drivers/clk/sunxi-ng/ccu-sun6i-a31.c | 2 +- drivers/clk/sunxi-ng/ccu_nm.c | 3 + drivers/cpuidle/cpuidle.c | 1 + drivers/crypto/amcc/crypto4xx_core.h | 10 +- drivers/gpu/drm/drm_dp_dual_mode_helper.c | 16 +- drivers/gpu/drm/vc4/vc4_dsi.c | 3 +- drivers/hv/vmbus_drv.c | 2 +- drivers/iio/accel/st_accel_core.c | 35 +- drivers/iio/common/st_sensors/st_sensors_core.c | 2 +- drivers/iio/common/st_sensors/st_sensors_trigger.c | 16 +- drivers/iio/gyro/st_gyro_core.c | 15 +- drivers/iio/magnetometer/st_magn_core.c | 10 +- drivers/iio/pressure/st_pressure_core.c | 15 +- drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 5 + drivers/infiniband/sw/rxe/rxe_pool.c | 2 + drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c | 1 + .../infiniband/ulp/opa_vnic/opa_vnic_vema_iface.c | 8 +- drivers/input/mouse/vmmouse.c | 10 +- drivers/leds/leds-pca955x.c | 17 +- drivers/md/dm-mpath.c | 20 +- drivers/md/md.c | 4 +- drivers/misc/pti.c | 2 +- drivers/misc/vmw_balloon.c | 2 +- drivers/net/ethernet/ibm/ibmvnic.c | 2 + drivers/net/ethernet/intel/fm10k/fm10k.h | 4 +- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 12 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 16 +- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 7 +- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 9 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 + drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 4 +- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 2 + drivers/net/phy/at803x.c | 2 +- drivers/pci/iov.c | 3 +- drivers/pci/pci.c | 4 + drivers/pci/pcie/aer/aerdrv_core.c | 9 +- drivers/platform/x86/asus-wireless.c | 1 + drivers/rtc/interface.c | 2 +- drivers/rtc/rtc-pl031.c | 14 +- drivers/scsi/cxgbi/cxgb4i/cxgb4i.c | 1 + drivers/scsi/lpfc/lpfc_hbadisc.c | 3 +- drivers/scsi/lpfc/lpfc_hw4.h | 2 +- drivers/scsi/lpfc/lpfc_nvmet.c | 2 + drivers/scsi/mpt3sas/mpt3sas_scsih.c | 5 + drivers/staging/greybus/light.c | 2 + drivers/tee/optee/core.c | 1 - drivers/thermal/hisi_thermal.c | 74 ++- drivers/vfio/pci/vfio_pci_config.c | 6 +- drivers/video/backlight/pwm_bl.c | 7 +- fs/dcache.c | 4 +- fs/overlayfs/ovl_entry.h | 2 +- fs/overlayfs/readdir.c | 2 +- include/asm-generic/vmlinux.lds.h | 2 +- include/linux/compiler.h | 1 + include/linux/hypervisor.h | 8 +- include/linux/iio/common/st_sensors.h | 7 +- include/linux/{pti.h => intel-pti.h} | 6 +- include/linux/mm.h | 2 +- include/linux/mmzone.h | 6 +- include/linux/rculist.h | 4 +- include/linux/rcupdate.h | 4 +- kernel/events/core.c | 4 +- kernel/seccomp.c | 2 +- kernel/task_work.c | 2 +- kernel/trace/trace_events_hist.c | 4 +- lib/Kconfig.debug | 2 +- mm/page_alloc.c | 10 + mm/slab.h | 2 +- mm/sparse.c | 17 +- net/ipv4/ip_gre.c | 8 +- net/ipv4/tcp_vegas.c | 2 +- net/ipv6/addrconf.c | 12 +- net/ipv6/route.c | 58 +-- net/sctp/stream.c | 8 +- scripts/Makefile.build | 2 +- sound/soc/codecs/msm8916-wcd-analog.c | 9 +- sound/soc/img/img-parallel-out.c | 2 + tools/objtool/check.c | 7 +- tools/objtool/objtool.c | 6 +- tools/testing/selftests/x86/ldt_gdt.c | 61 ++- virt/kvm/kvm_main.c | 2 +- 188 files changed, 2414 insertions(+), 1428 deletions(-)

7 years, 4 months

19
229
0 0

[Linux-stable-mirror] Patch "x86/retpoline: Remove the esp/rsp thunk" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/retpoline: Remove the esp/rsp thunk to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-retpoline-remove-the-esp-rsp-thunk.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: Waiman Long <longman(a)redhat.com> Date: Mon, 22 Jan 2018 17:09:34 -0500 Subject: x86/retpoline: Remove the esp/rsp thunk From: Waiman Long <longman(a)redhat.com> (cherry picked from commit 1df37383a8aeabb9b418698f0bcdffea01f4b1b2) It doesn't make sense to have an indirect call thunk with esp/rsp as retpoline code won't work correctly with the stack pointer register. Removing it will help compiler writers to catch error in case such a thunk call is emitted incorrectly. Fixes: 76b043848fd2 ("x86/retpoline: Add initial retpoline support") Suggested-by: Jeff Law <law(a)redhat.com> Signed-off-by: Waiman Long <longman(a)redhat.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Kees Cook <keescook(a)google.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Jiri Kosina <jikos(a)kernel.org> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: Greg Kroah-Hartman <gregkh(a)linux-foundation.org> Cc: Paul Turner <pjt(a)google.com> Link: https://lkml.kernel.org/r/1516658974-27852-1-git-send-email-longman@redhat.… Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/asm-prototypes.h | 1 - arch/x86/lib/retpoline.S | 1 - 2 files changed, 2 deletions(-) --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -37,5 +37,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -INDIRECT_THUNK(sp) #endif /* CONFIG_RETPOLINE */ --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -36,7 +36,6 @@ GENERATE_THUNK(_ASM_DX) GENERATE_THUNK(_ASM_SI) GENERATE_THUNK(_ASM_DI) GENERATE_THUNK(_ASM_BP) -GENERATE_THUNK(_ASM_SP) #ifdef CONFIG_64BIT GENERATE_THUNK(r8) GENERATE_THUNK(r9) Patches currently in stable-queue which might be from longman(a)redhat.com are queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:13 +0000 Subject: x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit fec9434a12f38d3aeafeb75711b71d8a1fdef621) Also, for CPUs which don't speculate at all, don't report that they're vulnerable to the Spectre variants either. Leave the cpu_no_meltdown[] match table with just X86_VENDOR_AMD in it for now, even though that could be done with a simple comparison, on the assumption that we'll have more to add. Based on suggestions from Dave Hansen and Alan Cox. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Borislav Petkov <bp(a)suse.de> Acked-by: Dave Hansen <dave.hansen(a)intel.com> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-6-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/common.c | 48 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 43 insertions(+), 5 deletions(-) --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -44,6 +44,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -838,6 +840,41 @@ static void identify_cpu_without_cpuid(s #endif } +static const __initdata struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initdata struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -884,11 +921,12 @@ static void __init early_identify_cpu(st setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (c->x86_vendor != X86_VENDOR_AMD) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } fpu__init_system(c); Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/msr: Add definitions for new speculation control MSRs" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/msr: Add definitions for new speculation control MSRs to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-msr-add-definitions-for-new-speculation-control-msrs.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:12 +0000 Subject: x86/msr: Add definitions for new speculation control MSRs From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 1e340c60d0dd3ae07b5bedc16a0469c14b9f3410) Add MSR and bit definitions for SPEC_CTRL, PRED_CMD and ARCH_CAPABILITIES. See Intel's 336996-Speculative-Execution-Side-Channel-Mitigations.pdf Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-5-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/msr-index.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -37,6 +37,13 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ + #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd @@ -50,6 +57,11 @@ #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) #define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpufeatures: Add Intel feature bits for Speculation Control" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpufeatures: Add Intel feature bits for Speculation Control to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:10 +0000 Subject: x86/cpufeatures: Add Intel feature bits for Speculation Control From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit fc67dd70adb711a45d2ef34e12d1a8be75edde61) Add three feature bits exposed by new microcode on Intel CPUs for speculation control. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Borislav Petkov <bp(a)suse.de> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-3-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/cpufeatures.h | 3 +++ 1 file changed, 3 insertions(+) --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -296,6 +296,9 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ /* * BUG word(s) Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpufeatures: Add CPUID_7_EDX CPUID leaf" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpufeatures: Add CPUID_7_EDX CPUID leaf to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:09 +0000 Subject: x86/cpufeatures: Add CPUID_7_EDX CPUID leaf From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 95ca0ee8636059ea2800dfbac9ecac6212d6b38f) This is a pure feature bits leaf. There are two AVX512 feature bits in it already which were handled as scattered bits, and three more from this leaf are going to be added for speculation control features. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Borislav Petkov <bp(a)suse.de> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/cpufeature.h | 7 +++++-- arch/x86/include/asm/cpufeatures.h | 10 ++++++---- arch/x86/include/asm/disabled-features.h | 3 ++- arch/x86/include/asm/required-features.h | 3 ++- arch/x86/kernel/cpu/common.c | 1 + arch/x86/kernel/cpu/scattered.c | 2 -- 6 files changed, 16 insertions(+), 10 deletions(-) --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -28,6 +28,7 @@ enum cpuid_leafs CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, + CPUID_7_EDX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -78,8 +79,9 @@ extern const char * const x86_bug_flags[ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -100,8 +102,9 @@ extern const char * const x86_bug_flags[ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -197,9 +197,7 @@ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ @@ -295,6 +293,10 @@ #define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ + /* * BUG word(s) */ --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -59,6 +59,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -100,6 +100,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -737,6 +737,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,8 +31,6 @@ void init_scattered_cpuid_features(struc const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpufeatures: Add AMD feature bits for Speculation Control" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpufeatures: Add AMD feature bits for Speculation Control to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:11 +0000 Subject: x86/cpufeatures: Add AMD feature bits for Speculation Control From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit 5d10cbc91d9eb5537998b65608441b592eec65e7) AMD exposes the PRED_CMD/SPEC_CTRL MSRs slightly differently to Intel. See http://lkml.kernel.org/r/2b3e25cc-286d-8bd0-aeaf-9ac4aae39de8@amd.com Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/cpufeatures.h | 3 +++ 1 file changed, 3 insertions(+) --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -258,6 +258,9 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ +#define X86_FEATURE_AMD_PRED_CMD (13*32+12) /* Prediction Command MSR (AMD) */ +#define X86_FEATURE_AMD_SPEC_CTRL (13*32+14) /* Speculation Control MSR only (AMD) */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors (AMD) */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: David Woodhouse <dwmw(a)amazon.co.uk> Date: Thu, 25 Jan 2018 16:14:14 +0000 Subject: x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes From: David Woodhouse <dwmw(a)amazon.co.uk> (cherry picked from commit a5b2966364538a0e68c9fa29bc0a3a1651799035) This doesn't refuse to load the affected microcodes; it just refuses to use the Spectre v2 mitigation features if they're detected, by clearing the appropriate feature bits. The AMD CPUID bits are handled here too, because hypervisors *may* have been exposing those bits even on Intel chips, for fine-grained control of what's available. It is non-trivial to use x86_match_cpu() for this table because that doesn't handle steppings. And the approach taken in commit bd9240a18 almost made me lose my lunch. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: gnomes(a)lxorguk.ukuu.org.uk Cc: ak(a)linux.intel.com Cc: ashok.raj(a)intel.com Cc: dave.hansen(a)intel.com Cc: karahmed(a)amazon.de Cc: arjan(a)linux.intel.com Cc: torvalds(a)linux-foundation.org Cc: peterz(a)infradead.org Cc: bp(a)alien8.de Cc: pbonzini(a)redhat.com Cc: tim.c.chen(a)linux.intel.com Cc: gregkh(a)linux-foundation.org Link: https://lkml.kernel.org/r/1516896855-7642-7-git-send-email-dwmw@amazon.co.uk Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/include/asm/intel-family.h | 7 ++- arch/x86/kernel/cpu/intel.c | 66 ++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+), 2 deletions(-) --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -12,6 +12,7 @@ */ #define INTEL_FAM6_CORE_YONAH 0x0E + #define INTEL_FAM6_CORE2_MEROM 0x0F #define INTEL_FAM6_CORE2_MEROM_L 0x16 #define INTEL_FAM6_CORE2_PENRYN 0x17 @@ -21,6 +22,7 @@ #define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_FAM6_NEHALEM_EX 0x2E + #define INTEL_FAM6_WESTMERE 0x25 #define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_FAM6_WESTMERE_EX 0x2F @@ -36,9 +38,9 @@ #define INTEL_FAM6_HASWELL_GT3E 0x46 #define INTEL_FAM6_BROADWELL_CORE 0x3D -#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_BROADWELL_GT3E 0x47 #define INTEL_FAM6_BROADWELL_X 0x4F +#define INTEL_FAM6_BROADWELL_XEON_D 0x56 #define INTEL_FAM6_SKYLAKE_MOBILE 0x4E #define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E @@ -57,9 +59,10 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ +#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A /* Xeon Phi */ --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -61,6 +61,59 @@ void check_mpx_erratum(struct cpuinfo_x8 } } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-up… + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Updated in the 20180108 release; blacklist until we know otherwise */ + { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_mask == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -87,6 +140,19 @@ static void early_init_intel(struct cpui rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); } + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_STIBP) || + cpu_has(c, X86_FEATURE_AMD_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_AMD_PRED_CMD) || + cpu_has(c, X86_FEATURE_AMD_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling SPEC_CTRL\n"); + clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL); + clear_cpu_cap(c, X86_FEATURE_STIBP); + clear_cpu_cap(c, X86_FEATURE_AMD_SPEC_CTRL); + clear_cpu_cap(c, X86_FEATURE_AMD_PRED_CMD); + clear_cpu_cap(c, X86_FEATURE_AMD_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * Patches currently in stable-queue which might be from dwmw(a)amazon.co.uk are queue-4.9/kvm-vmx-introduce-alloc_loaded_vmcs.patch queue-4.9/kvm-nvmx-eliminate-vmcs02-pool.patch queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/kvm-nvmx-vmx_complete_nested_posted_interrupt-can-t-fail.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kvm-vmx-make-msr-bitmaps-per-vcpu.patch queue-4.9/kvm-nvmx-mark-vmcs12-pages-dirty-on-l2-exit.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "module/retpoline: Warn about missing retpoline in module" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled module/retpoline: Warn about missing retpoline in module to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: module-retpoline-warn-about-missing-retpoline-in-module.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: Andi Kleen <ak(a)linux.intel.com> Date: Thu, 25 Jan 2018 15:50:28 -0800 Subject: module/retpoline: Warn about missing retpoline in module From: Andi Kleen <ak(a)linux.intel.com> (cherry picked from commit caf7501a1b4ec964190f31f9c3f163de252273b8) There's a risk that a kernel which has full retpoline mitigations becomes vulnerable when a module gets loaded that hasn't been compiled with the right compiler or the right option. To enable detection of that mismatch at module load time, add a module info string "retpoline" at build time when the module was compiled with retpoline support. This only covers compiled C source, but assembler source or prebuilt object files are not checked. If a retpoline enabled kernel detects a non retpoline protected module at load time, print a warning and report it in the sysfs vulnerability file. [ tglx: Massaged changelog ] Signed-off-by: Andi Kleen <ak(a)linux.intel.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: gregkh(a)linuxfoundation.org Cc: torvalds(a)linux-foundation.org Cc: jeyu(a)kernel.org Cc: arjan(a)linux.intel.com Link: https://lkml.kernel.org/r/20180125235028.31211-1-andi@firstfloor.org Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kernel/cpu/bugs.c | 17 ++++++++++++++++- include/linux/module.h | 9 +++++++++ kernel/module.c | 11 +++++++++++ scripts/mod/modpost.c | 9 +++++++++ 4 files changed, 45 insertions(+), 1 deletion(-) --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/utsname.h> #include <linux/cpu.h> +#include <linux/module.h> #include <asm/nospec-branch.h> #include <asm/cmdline.h> @@ -92,6 +93,19 @@ static const char *spectre_v2_strings[] #define pr_fmt(fmt) "Spectre V2 mitigation: " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static bool spectre_v2_bad_module; + +#ifdef RETPOLINE +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vunerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} +#endif static void __init spec2_print_if_insecure(const char *reason) { @@ -277,6 +291,7 @@ ssize_t cpu_show_spectre_v2(struct devic if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); + return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled], + spectre_v2_bad_module ? " - vulnerable module loaded" : ""); } #endif --- a/include/linux/module.h +++ b/include/linux/module.h @@ -791,6 +791,15 @@ static inline void module_bug_finalize(c static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef RETPOLINE +extern bool retpoline_module_ok(bool has_retpoline); +#else +static inline bool retpoline_module_ok(bool has_retpoline) +{ + return true; +} +#endif + #ifdef CONFIG_MODULE_SIG static inline bool module_sig_ok(struct module *module) { --- a/kernel/module.c +++ b/kernel/module.c @@ -2817,6 +2817,15 @@ static int check_modinfo_livepatch(struc } #endif /* CONFIG_LIVEPATCH */ +static void check_modinfo_retpoline(struct module *mod, struct load_info *info) +{ + if (retpoline_module_ok(get_modinfo(info, "retpoline"))) + return; + + pr_warn("%s: loading module not compiled with retpoline compiler.\n", + mod->name); +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -2969,6 +2978,8 @@ static int check_modinfo(struct module * add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); } + check_modinfo_retpoline(mod, info); + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); pr_warn("%s: module is from the staging directory, the quality " --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2130,6 +2130,14 @@ static void add_intree_flag(struct buffe buf_printf(b, "\nMODULE_INFO(intree, \"Y\");\n"); } +/* Cannot check for assembler */ +static void add_retpoline(struct buffer *b) +{ + buf_printf(b, "\n#ifdef RETPOLINE\n"); + buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n"); + buf_printf(b, "#endif\n"); +} + static void add_staging_flag(struct buffer *b, const char *name) { static const char *staging_dir = "drivers/staging"; @@ -2474,6 +2482,7 @@ int main(int argc, char **argv) add_header(&buf, mod); add_intree_flag(&buf, !external_module); + add_retpoline(&buf); add_staging_flag(&buf, mod->name); err |= add_versions(&buf, mod); add_depends(&buf, mod, modules); Patches currently in stable-queue which might be from ak(a)linux.intel.com are queue-4.9/kvm-vmx-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/kvm-svm-allow-direct-access-to-msr_ia32_spec_ctrl.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/module-retpoline-warn-about-missing-retpoline-in-module.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/kvm-vmx-emulate-msr_ia32_arch_capabilities.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "KVM: x86: Make indirect calls in emulator speculation safe" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KVM: x86: Make indirect calls in emulator speculation safe to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: Peter Zijlstra <peterz(a)infradead.org> Date: Thu, 25 Jan 2018 10:58:13 +0100 Subject: KVM: x86: Make indirect calls in emulator speculation safe From: Peter Zijlstra <peterz(a)infradead.org> (cherry picked from commit 1a29b5b7f347a1a9230c1e0af5b37e3e571588ab) Replace the indirect calls with CALL_NOSPEC. Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Ashok Raj <ashok.raj(a)intel.com> Cc: Greg KH <gregkh(a)linuxfoundation.org> Cc: Jun Nakajima <jun.nakajima(a)intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: rga(a)amazon.de Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Asit Mallick <asit.k.mallick(a)intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Jason Baron <jbaron(a)akamai.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Arjan Van De Ven <arjan.van.de.ven(a)intel.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Link: https://lkml.kernel.org/r/20180125095843.595615683@infradead.org [dwmw2: Use ASM_CALL_CONSTRAINT like upstream, now we have it] Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kvm/emulate.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" @@ -1012,8 +1013,8 @@ static __always_inline u8 test_cc(unsign void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; call *%[fastop]" - : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + asm("push %[flags]; popf; " CALL_NOSPEC + : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } @@ -5306,15 +5307,14 @@ static void fetch_possible_mmx_operand(s static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); Patches currently in stable-queue which might be from peterz(a)infradead.org are queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kaiser-fix-intel_bts-perf-crashes.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "KVM: VMX: Make indirect call speculation safe" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KVM: VMX: Make indirect call speculation safe to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: kvm-vmx-make-indirect-call-speculation-safe.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 19:38:23 CST 2018 From: Peter Zijlstra <peterz(a)infradead.org> Date: Thu, 25 Jan 2018 10:58:14 +0100 Subject: KVM: VMX: Make indirect call speculation safe From: Peter Zijlstra <peterz(a)infradead.org> (cherry picked from commit c940a3fb1e2e9b7d03228ab28f375fb5a47ff699) Replace indirect call with CALL_NOSPEC. Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Ashok Raj <ashok.raj(a)intel.com> Cc: Greg KH <gregkh(a)linuxfoundation.org> Cc: Jun Nakajima <jun.nakajima(a)intel.com> Cc: David Woodhouse <dwmw2(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: rga(a)amazon.de Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Asit Mallick <asit.k.mallick(a)intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Jason Baron <jbaron(a)akamai.com> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: Arjan Van De Ven <arjan.van.de.ven(a)intel.com> Cc: Tim Chen <tim.c.chen(a)linux.intel.com> Link: https://lkml.kernel.org/r/20180125095843.645776917@infradead.org Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/x86/kvm/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8676,14 +8676,14 @@ static void vmx_handle_external_intr(str #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif "+r"(__sp) : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); Patches currently in stable-queue which might be from peterz(a)infradead.org are queue-4.9/kvm-x86-add-ibpb-support.patch queue-4.9/x86-cpufeatures-add-intel-feature-bits-for-speculation-control.patch queue-4.9/x86-cpufeatures-add-cpuid_7_edx-cpuid-leaf.patch queue-4.9/kvm-x86-make-indirect-calls-in-emulator-speculation-safe.patch queue-4.9/x86-cpufeature-blacklist-spec_ctrl-pred_cmd-on-early-spectre-v2-microcodes.patch queue-4.9/x86-asm-fix-inline-asm-call-constraints-for-gcc-4.4.patch queue-4.9/kvm-vmx-make-indirect-call-speculation-safe.patch queue-4.9/x86-cpufeatures-add-amd-feature-bits-for-speculation-control.patch queue-4.9/x86-msr-add-definitions-for-new-speculation-control-msrs.patch queue-4.9/x86-pti-make-unpoison-of-pgd-for-trusted-boot-work-for-real.patch queue-4.9/kaiser-fix-intel_bts-perf-crashes.patch queue-4.9/x86-retpoline-remove-the-esp-rsp-thunk.patch queue-4.9/x86-pti-do-not-enable-pti-on-cpus-which-are-not-vulnerable-to-meltdown.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] v3.18.94 build: 0 failures 1 warnings (v3.18.94)

by Build bot for Mark Brown

Tree/Branch: v3.18.94 Git describe: v3.18.94 Commit: cde3537bd1 Linux 3.18.94 Build Time: 50 min 14 sec Passed: 9 / 9 (100.00 %) Failed: 0 / 9 ( 0.00 %) Errors: 0 Warnings: 1 Section Mismatches: 0 ------------------------------------------------------------------------------- defconfigs with issues (other than build errors): 2 warnings 0 mismatches : x86_64-defconfig ------------------------------------------------------------------------------- Warnings Summary: 1 2 ../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address] =============================================================================== Detailed per-defconfig build reports below: ------------------------------------------------------------------------------- x86_64-defconfig : PASS, 0 errors, 2 warnings, 0 section mismatches Warnings: ../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address] ../include/linux/ftrace.h:632:36: warning: calling '__builtin_return_address' with a nonzero argument is unsafe [-Wframe-address] ------------------------------------------------------------------------------- Passed with no errors, warnings or mismatches: arm64-allnoconfig arm64-allmodconfig arm-multi_v5_defconfig arm-multi_v7_defconfig arm-allmodconfig arm-allnoconfig x86_64-allnoconfig arm64-defconfig

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] A question about commit 6c16fa backported in 3.18.93

by Wang Han

Hello, I am not familiar with Linux mailing, sorry for this. I am writing this mail because I am not sure about commit 6c16fa957e84c8b640dadc4e0264ff0d2dae7aa3 added in 3.18.93. That backport made the arp.h changes in struct __ipv4_neigh_lookup(), but compared with upstream commit, I think that 3 lines should be added in __ipv4_neigh_lookup_noref(), as I go through the context. Also the latter would be called unconditionally if former is called so it would cover more cases. Could you please check this and let me know? Though it would 90% be my derp. Thanks, Wang

7 years, 4 months

2
3
0 0

[Linux-stable-mirror] [PATCH for 3.18] ipv4: Map neigh lookup keys in __ipv4_neigh_lookup_noref()

by Wang Han

As discussed earlier, From: Wang Han <wanghan1995315(a)gmail.com> Date: Sat, 3 Feb 2018 03:28:35 +1400 Subject: [PATCH] ipv4: Map neigh lookup keys in __ipv4_neigh_lookup_noref() Commit 6c16fa957e84 is an incorrect backport as we map the keys in struct __ipv4_neigh_lookup(), but the correct place to add the code is struct __ipv4_neigh_lookup_noref(), compared to upstream. Fix it by moving the code, or fewer cases will be covered as __ipv4_neigh_lookup_noref() will be called unconditionally from __ipv4_neigh_lookup(), and it can be called from other places such as ip_output.c. Fixes: 6c16fa957e84 (ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY) Signed-off-by: Wang Han <wanghan1995315(a)gmail.com> --- include/net/arp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/net/arp.h b/include/net/arp.h index 174014585ade..5d8c7990582f 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -22,6 +22,9 @@ static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev struct neighbour *n; u32 hash_val; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; @@ -37,9 +40,6 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 { struct neighbour *n; - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - key = INADDR_ANY; - rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !atomic_inc_not_zero(&n->refcnt)) -- 2.14.1

7 years, 4 months

2
1
0 0

Re: [Linux-stable-mirror] [PATCH 3.18 00/36] 3.18.94-stable review

by Greg Kroah-Hartman

On Wed, Feb 07, 2018 at 03:19:07PM +0000, Harsh Shandilya wrote: > On Tue 6 Feb, 2018, 12:09 AM Greg Kroah-Hartman, <gregkh(a)linuxfoundation.org> > wrote: > > > This is the start of the stable review cycle for the 3.18.94 release. > > There are 36 patches in this series, all will be posted as a response > > to this one. If anyone has any issues with these being applied, please > > let me know. > > > > Responses should be made by Wed Feb 7 18:23:41 UTC 2018. > > Anything received after that time might be too late. > > > > Let's find out if I am too late. > > https://www.spinics.net/lists/stable/msg213160.html will have to be lined > up for 3.18.94, or to .95 if I'm late since it's fixing a erroneous > backport from 3.18.93 which went unnoticed until after release. The email > bringing it up and the subsequent patch were probably lost in the usual > stable noise. I have applied it to the CAF tree for the oneplus3 and > verified that it does not break compilation or userspace for arm64. It will be queued up for the next release, I missed it this time, sorry. greg k-h

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] [Bug 197863] Thinkpad X240 resume dramatically slower on kernels 4.13+

by Greg KH

On Sat, Feb 03, 2018 at 07:25:54PM +0100, Markus Demleitner wrote: > On Tue, Jan 30, 2018 at 07:32:04AM +0100, Greg KH wrote: > > On Mon, Jan 29, 2018 at 07:21:09PM +0100, Markus Demleitner wrote: > > > A while ago I opened bug #197863 in the kernel bugzilla: > > > > > > https://bugzilla.kernel.org/show_bug.cgi?id=197863 > > > > > > Essentially, xhci_hcd on a resume from RAM takes several seconds on a > > > Thinkpad X240 that is equipped with a Sierra LTE modem after an > > > upgrade to 4.13: > [...] > > > Now, interestingly, there are quick resumes in 4.15.0, too, now and > > > then. In that case, things look pretty much like on 4.12.2. Here's > > > a 4.15.0 fast resume example: > > > > > > [ 873.127570] usb 1-4: device firmware changed > > > [ 873.277351] usb 1-8: reset high-speed USB device number 4 using xhci_hcd > > > [ 873.515141] restoring control 00000000-0000-0000-0000-000000000101/0/2 > > > [ 873.583238] OOM killer enabled. > > > [ 873.583240] Restarting tasks ... > > > [ 873.583339] usb 1-4: USB disconnect, device number 10 > > > [ 873.586356] done. > > > [ 873.604420] PM: suspend exit > > > [ 873.737283] usb 1-4: new high-speed USB device number 11 using xhci_hcd > > > [ 880.867398] usb 1-4: device descriptor read/64, error -110 > > > [ 881.175558] usb 1-4: New USB device found, idVendor=1199, idProduct=a001 > > > [ 881.175563] usb 1-4: New USB device strings: Mfr=1, Product=2, SerialNumber=3 > > > [ 881.175566] usb 1-4: Product: Sierra Wireless EM7345 4G LTE > > > [ 881.175568] usb 1-4: Manufacturer: Sierra Wireless Inc. > > > [ 881.175570] usb 1-4: SerialNumber: 013937002544516 > > > > > > Any guess what might be behind this? > > > > Any chance you can run 'git bisect' to find the offending commit for > > this issue? > > It's 662591461c4b9a1e3b9b159dbf37648a585ebaae. To my eyes, it even > looks plausible that it's causing the problematic behaviour, but > since I can't say I understand what I'd be doing if I dabbled with > the change, I've refrained from guessing how to fix it. > > I'm happy to try patches, though. Ok, thanks. I've added the authors of this patch to the email here, perhaps they have an idea of what is going on? greg k-h

7 years, 4 months

4
5
0 0

Re: [Linux-stable-mirror] Linux 4.15.2

by Greg KH

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 46b26bfee27b..1e762c210f1b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2742,8 +2742,6 @@ norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space - noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops - noreplace-smp [X86-32,SMP] Don't replace SMP instructions with UP alternatives diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt new file mode 100644 index 000000000000..e9e6cbae2841 --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,90 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else + return array[index]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP <index>, #MAX_ARRAY_ELEMS + B.LT less + MOV <returnval>, #0 + RET + less: + LDR <returnval>, [<array>, <index>] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This +value will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may +result in sensitive information being leaked. Consider the following +code, building on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int index) + { + int val1, val2, + + val1 = load_array(arr1, index); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value +of an out-of-bounds address, while the second call will influence +microarchitectural state dependent on this value. This may provide an +arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are +respected even under speculation. Architectures which are affected by +speculation-based side-channels are expected to implement these +primitives. + +The array_index_nospec() helper in <linux/nospec.h> can be used to +prevent information from being leaked via side-channels. + +A call to array_index_nospec(index, size) returns a sanitized index +value that is bounded to [0, size) even under cpu speculation +conditions. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else { + index = array_index_nospec(index, MAX_ARRAY_ELEMS); + return array[index]; + } + } diff --git a/Makefile b/Makefile index af101b556ba0..54f1bc10b531 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 15 -SUBLEVEL = 1 +SUBLEVEL = 2 EXTRAVERSION = NAME = Fearless Coyote diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index d7d3cc24baf4..21dbdf0e476b 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <linux/livepatch.h> #include <linux/syscalls.h> @@ -206,7 +207,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -282,7 +283,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -304,7 +306,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -318,6 +320,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 60c4c342316c..2a35b1e0fb90 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,7 +252,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %ebx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ff6f8022612c..c752abe89d80 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -236,91 +236,20 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - UNWIND_HINT_REGS extra=0 - - TRACE_IRQS_OFF - - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ -#ifdef CONFIG_RETPOLINE - movq sys_call_table(, %rax, 8), %rax - call __x86_indirect_thunk_rax -#else - call *sys_call_table(, %rax, 8) -#endif -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - addq $6*8, %rsp /* skip extra regs -- they were preserved */ - UNWIND_HINT_EMPTY - jmp .Lpop_c_regs_except_rcx_r11_and_sysret -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: TRACE_IRQS_IRETQ /* we're about to change IF */ /* @@ -393,7 +322,6 @@ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY POP_EXTRA_REGS -.Lpop_c_regs_except_rcx_r11_and_sysret: popq %rsi /* skip r11 */ popq %r10 popq %r9 @@ -424,47 +352,6 @@ syscall_return_via_sysret: USERGS_SYSRET64 END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - popq %rax - UNWIND_HINT_REGS extra=0 - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - UNWIND_HINT_FUNC - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task @@ -499,7 +386,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %rbx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9c09775e589d..c176d2fab1da 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -7,14 +7,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 1908214b9125..4d111616524b 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,4 +38,7 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) +asmlinkage void __fill_rsb(void); +asmlinkage void __clear_rsb(void); + #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 7fb336210e1b..30d406146016 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -24,6 +24,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea9a7dde62e5..70eddb3922ff 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -29,6 +29,7 @@ enum cpuid_leafs CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, + CPUID_7_EDX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 25b9375c1484..73b5fff159a4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -203,14 +203,14 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ + +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -271,6 +271,9 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -319,6 +322,13 @@ #define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index b027633e7300..33833d1909af 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -77,6 +77,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 64c4a30e0d39..e203169931c7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -137,8 +137,10 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); -#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_TOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_TOT_START (FIXADDR_TOP - FIXADDR_TOT_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e7b983a35506..e520a1e6fc11 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -39,6 +39,13 @@ /* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ + #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -57,6 +64,11 @@ #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) #define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 07962f5f6fba..30df295f6d94 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4ad41087ce0e..4d57894635f2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -1,56 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NOSPEC_BRANCH_H__ -#define __NOSPEC_BRANCH_H__ +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * We define a CPP macro such that it can be used from both .S files and - * inline assembly. It's possible to do a .macro and then include that - * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. - */ - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -/* - * Google experimented with loop-unrolling and this turned out to be - * the optimal version — two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - call 772f; \ -773: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - call 774f; \ -775: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - dec reg; \ - jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; - #ifdef __ASSEMBLY__ /* @@ -121,17 +77,10 @@ #endif .endm - /* - * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP - * monstrosity above, manually. - */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +/* This clobbers the BX register */ +.macro FILL_RETURN_BUFFER nr:req ftr:req #ifdef CONFIG_RETPOLINE - ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE "jmp .Lskip_rsb_\@", \ - __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ - \ftr -.Lskip_rsb_\@: + ALTERNATIVE "", "call __clear_rsb", \ftr #endif .endm @@ -201,22 +150,25 @@ extern char __indirect_thunk_end[]; * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ATT *might* it be avoided. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); + alternative_input("", + "call __fill_rsb", + X86_FEATURE_RETPOLINE, + ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); #endif } +static inline void indirect_branch_prediction_barrier(void) +{ + alternative_input("", + "call __ibp_barrier", + X86_FEATURE_USE_IBPB, + ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); +} + #endif /* __ASSEMBLY__ */ -#endif /* __NOSPEC_BRANCH_H__ */ +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index ce245b0cdfca..0777e18a1d23 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,8 +44,9 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ */ #define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ + & PMD_MASK) #define PKMAP_BASE \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d3a67fba200a..513f9604c192 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -460,8 +460,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -971,4 +969,7 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); + +void __ibp_barrier(void); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d91ba04dd007..fb3a6de7440b 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -106,6 +106,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8e61c5..03eedc21246d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 00223333821a..eda3b6823ca4 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,6 +55,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -221,7 +222,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d33e4a26dc7e..2b8f18ca5874 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -174,6 +174,8 @@ struct tlb_state { struct mm_struct *loaded_mm; u16 loaded_mm_asid; u16 next_asid; + /* last user mm's ctx id */ + u64 last_ctx_id; /* * We can be in one of several states: diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 574dff4d2913..aae77eb8491c 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -124,6 +124,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -445,7 +450,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 72950401b223..ba2dc1930630 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)to, from, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)to, from, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)to, from, ret, "l", "k", "=r", 4); __uaccess_end(); diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f07ef3c575db..62546b3a398e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4817d743c263..a481763a3776 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -298,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -355,7 +344,7 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins add_nops(instr + (a->instrlen - a->padlen), a->padlen); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -376,7 +365,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %p -> %p", start, end); + DPRINTK("alt table %px, -> %px", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -400,14 +389,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -433,7 +422,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } @@ -599,9 +588,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 390b3dc3d438..71949bf2de5a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/utsname.h> #include <linux/cpu.h> +#include <linux/module.h> #include <asm/nospec-branch.h> #include <asm/cmdline.h> @@ -90,20 +91,41 @@ static const char *spectre_v2_strings[] = { }; #undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static void __init spec2_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -118,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt) return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { char arg[20]; - int ret; - - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); - if (ret > 0) { - if (match_option(arg, ret, "off")) { - goto disable; - } else if (match_option(arg, ret, "on")) { - spec2_print_if_secure("force enabled on command line."); - return SPECTRE_V2_CMD_FORCE; - } else if (match_option(arg, ret, "retpoline")) { - spec2_print_if_insecure("retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE; - } else if (match_option(arg, ret, "retpoline,amd")) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec2_print_if_insecure("AMD retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_AMD; - } else if (match_option(arg, ret, "retpoline,generic")) { - spec2_print_if_insecure("generic retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_GENERIC; - } else if (match_option(arg, ret, "auto")) { + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ @@ -191,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void) return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; @@ -249,6 +297,12 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Filling RSB on context switch\n"); } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + pr_info("Enabling Indirect Branch Prediction Barrier\n"); + } } #undef pr_fmt @@ -269,7 +323,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, @@ -278,6 +332,14 @@ ssize_t cpu_show_spectre_v2(struct device *dev, if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); } #endif + +void __ibp_barrier(void) +{ + __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); +} +EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ef29ad001991..d63f4b5706e4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -47,6 +47,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -748,6 +750,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -769,6 +791,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ @@ -841,6 +864,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); /* * Clear/Set all flags overridden by options, after probe. @@ -876,6 +900,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -923,11 +982,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (c->x86_vendor != X86_VENDOR_AMD) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } fpu__init_system(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b1af22073e28..319bf989fad1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-up… + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Updated in the 20180108 release; blacklist until we know otherwise */ + { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_mask == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -122,6 +175,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) c->microcode = intel_get_microcode_revision(); + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d0e69769abfd..df11f5d604be 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,8 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c75466232016..9eb448c7859d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -557,7 +557,7 @@ static void __set_personality_x32(void) * Pretend to come from a x32 execve. */ task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; #endif } @@ -571,7 +571,7 @@ static void __set_personality_ia32(void) current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; #endif } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f37d18124648..ed5c4cdf0a34 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -935,7 +935,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b9e00e8f1c9b..4cdc0b27ec82 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -787,7 +787,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0099e10eb045..13f5d4217e4f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -67,9 +67,7 @@ u64 kvm_supported_xcr0(void) #define F(x) bit(X86_FEATURE_##x) -/* These are scattered features in cpufeatures.h. */ -#define KVM_CPUID_BIT_AVX512_4VNNIW 2 -#define KVM_CPUID_BIT_AVX512_4FMAPS 3 +/* For scattered features from cpufeatures.h; we currently expose none */ #define KF(x) bit(KVM_CPUID_BIT_##x) int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -367,6 +365,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); + /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -392,7 +394,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS); + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -477,7 +480,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; - entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; @@ -627,7 +630,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c2cea6651279..9a327d5b6d1f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -54,6 +54,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX}, [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, + [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, }; static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b514b2b2845a..290ecf711aec 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" @@ -1021,8 +1022,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; call *%[fastop]" - : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + asm("push %[flags]; popf; " CALL_NOSPEC + : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } @@ -5335,9 +5336,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), ASM_CALL_CONSTRAINT + [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f40d0da1f1d3..4e3c79530526 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -184,6 +184,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -249,6 +251,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -529,6 +533,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -880,6 +885,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1582,6 +1606,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1703,11 +1729,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1736,6 +1768,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -3593,6 +3629,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3684,6 +3727,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4936,6 +5022,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -5028,6 +5123,27 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c829d89e2e63..bee4c49f6dd0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -34,6 +34,7 @@ #include <linux/tboot.h> #include <linux/hrtimer.h> #include <linux/frame.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -111,6 +112,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -185,7 +194,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -210,6 +218,7 @@ struct loaded_vmcs { int soft_vnmi_blocked; ktime_t entry_time; s64 vnmi_blocked_time; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -226,7 +235,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -409,13 +418,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -440,15 +442,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -457,8 +459,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -581,6 +581,7 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -592,6 +593,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; u32 secondary_exec_control; @@ -898,21 +903,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - /* - * FIXME: Mitigation for CVE-2017-5753. To be replaced with a - * generic mechanism. - */ - asm("lfence"); - - if (vmcs_field_to_offset_table[field] == 0) + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) return -ENOENT; - - return vmcs_field_to_offset_table[field]; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -935,6 +937,9 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -954,12 +959,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); enum { VMX_IO_BITMAP_A, VMX_IO_BITMAP_B, - VMX_MSR_BITMAP_LEGACY, - VMX_MSR_BITMAP_LONGMODE, - VMX_MSR_BITMAP_LEGACY_X2APIC_APICV, - VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV, - VMX_MSR_BITMAP_LEGACY_X2APIC, - VMX_MSR_BITMAP_LONGMODE_X2APIC, VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR @@ -969,12 +968,6 @@ static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; #define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A]) #define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B]) -#define vmx_msr_bitmap_legacy (vmx_bitmap[VMX_MSR_BITMAP_LEGACY]) -#define vmx_msr_bitmap_longmode (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE]) -#define vmx_msr_bitmap_legacy_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV]) -#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV]) -#define vmx_msr_bitmap_legacy_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC]) -#define vmx_msr_bitmap_longmode_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC]) #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) @@ -1918,6 +1911,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2296,6 +2335,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2572,36 +2612,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2642,7 +2652,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -3276,6 +3286,20 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3383,6 +3407,70 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3837,11 +3925,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3857,9 +3940,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4918,10 +5030,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4955,6 +5065,50 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) +{ + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + if (msr <= 0x1fff) { + if (type & MSR_TYPE_R) + /* read-low */ + __set_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __set_bit(msr, msr_bitmap + 0x800 / f); + + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + if (type & MSR_TYPE_R) + /* read-high */ + __set_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __set_bit(msr, msr_bitmap + 0xc00 / f); + + } +} + +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -5001,30 +5155,70 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); + u8 mode = 0; + + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; + } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv, - msr, type); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, type); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; +} + static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) { return enable_apicv; @@ -5274,7 +5468,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5461,7 +5655,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5539,6 +5733,8 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5567,6 +5763,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6744,7 +6941,7 @@ void vmx_enable_tdp(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6764,9 +6961,6 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out; @@ -6835,42 +7029,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - for (msr = 0x800; msr <= 0x8ff; msr++) { - if (msr == 0x839 /* TMCCT */) - continue; - vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true); - } - - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true); - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false); - - /* EOI */ - vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) vmx_enable_tdp(); else @@ -6973,94 +7133,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } -/* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - /* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified @@ -7241,13 +7313,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs *shadow_vmcs; + int r; - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7264,9 +7334,6 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7278,9 +7345,9 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7423,10 +7490,6 @@ static void free_nested(struct vcpu_vmx *vmx) free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -7434,7 +7497,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7450,7 +7513,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7493,8 +7556,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -8406,10 +8467,11 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) /* * The host physical addresses of some pages of guest memory - * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU - * may write to these pages via their host physical address while - * L2 is running, bypassing any address-translation-based dirty - * tracking (e.g. EPT write protection). + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. @@ -8943,7 +9005,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -9129,14 +9191,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif ASM_CALL_CONSTRAINT : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -9373,6 +9435,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -9491,6 +9562,27 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -9604,6 +9696,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9636,13 +9729,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) + err = alloc_loaded_vmcs(&vmx->vmcs01); + if (err < 0) goto free_msrs; - loaded_vmcs_init(vmx->loaded_vmcs); + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -10105,10 +10205,25 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap); @@ -10141,6 +10256,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); kvm_release_page_clean(page); @@ -10682,6 +10810,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10903,20 +11034,15 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct loaded_vmcs *vmcs02; u32 msr_entry_idx; u32 exit_qual; - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - vmx_switch_vmcs(vcpu, vmcs02); + vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { @@ -11485,7 +11611,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -11534,10 +11660,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c53298dfbf50..ac381437c291 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1009,6 +1009,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f23934bbaf4e..69a473919260 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -27,6 +27,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_RETPOLINE) += retpoline.o +OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index c97d935a29e8..49b167f73215 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -40,6 +40,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -54,6 +56,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -68,6 +72,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -83,6 +89,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -94,6 +102,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index c909961e678a..480edc3a5e03 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,6 +7,7 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -46,3 +47,58 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1b377f734e64..7add8ba06887 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -331,12 +331,12 @@ do { \ unsigned long __copy_user_ll(void *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_user_ll); @@ -344,7 +344,7 @@ EXPORT_SYMBOL(__copy_user_ll); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -353,7 +353,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5bfe61a5e8e3..012d02624848 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> /* * TLB flushing, formerly SMP-only @@ -247,6 +248,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } else { u16 new_asid; bool need_flush; + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -292,6 +314,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } @@ -369,6 +399,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index db040b378224..9180b9bd5821 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -441,3 +441,7 @@ static struct platform_driver img_ascii_lcd_driver = { .remove = img_ascii_lcd_remove, }; module_platform_driver(img_ascii_lcd_driver); + +MODULE_DESCRIPTION("Imagination Technologies ASCII LCD Display"); +MODULE_AUTHOR("Paul Burton <paul.burton(a)mips.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index d9ab7c75b14f..e0c73ceba2ed 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -147,6 +147,7 @@ static struct fpga_manager *fpga_region_get_manager(struct fpga_region *region) mgr_node = of_parse_phandle(np, "fpga-mgr", 0); if (mgr_node) { mgr = of_fpga_mgr_get(mgr_node); + of_node_put(mgr_node); of_node_put(np); return mgr; } @@ -192,10 +193,13 @@ static int fpga_region_get_bridges(struct fpga_region *region, parent_br = region_np->parent; /* If overlay has a list of bridges, use it. */ - if (of_parse_phandle(overlay, "fpga-bridges", 0)) + br = of_parse_phandle(overlay, "fpga-bridges", 0); + if (br) { + of_node_put(br); np = overlay; - else + } else { np = region_np; + } for (i = 0; ; i++) { br = of_parse_phandle(np, "fpga-bridges", i); @@ -203,12 +207,15 @@ static int fpga_region_get_bridges(struct fpga_region *region, break; /* If parent bridge is in list, skip it. */ - if (br == parent_br) + if (br == parent_br) { + of_node_put(br); continue; + } /* If node is a bridge, get it and add to list */ ret = fpga_bridge_get_to_list(br, region->info, &region->bridge_list); + of_node_put(br); /* If any of the bridges are in use, give up */ if (ret == -EBUSY) { diff --git a/drivers/iio/accel/kxsd9-i2c.c b/drivers/iio/accel/kxsd9-i2c.c index 98fbb628d5bd..38411e1c155b 100644 --- a/drivers/iio/accel/kxsd9-i2c.c +++ b/drivers/iio/accel/kxsd9-i2c.c @@ -63,3 +63,6 @@ static struct i2c_driver kxsd9_i2c_driver = { .id_table = kxsd9_i2c_id, }; module_i2c_driver(kxsd9_i2c_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("KXSD9 accelerometer I2C interface"); diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c index 47d24ae5462f..fe3d7826783c 100644 --- a/drivers/iio/adc/qcom-vadc-common.c +++ b/drivers/iio/adc/qcom-vadc-common.c @@ -5,6 +5,7 @@ #include <linux/math64.h> #include <linux/log2.h> #include <linux/err.h> +#include <linux/module.h> #include "qcom-vadc-common.h" @@ -229,3 +230,6 @@ int qcom_vadc_decimation_from_dt(u32 value) return __ffs64(value / VADC_DECIMATION_MIN); } EXPORT_SYMBOL(qcom_vadc_decimation_from_dt); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Qualcomm ADC common functionality"); diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c index 866aa3ce1ac9..6cf0006d4c8d 100644 --- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c +++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c @@ -436,3 +436,7 @@ int pxa2xx_pinctrl_exit(struct platform_device *pdev) return 0; } EXPORT_SYMBOL_GPL(pxa2xx_pinctrl_exit); + +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik(a)free.fr>"); +MODULE_DESCRIPTION("Marvell PXA2xx pinctrl driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 854995e1cae7..7e7e6eb95b0a 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -974,6 +974,8 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, } } else { retval = uart_startup(tty, state, 1); + if (retval == 0) + tty_port_set_initialized(port, true); if (retval > 0) retval = 0; } diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 1c65817673db..41615f38bcff 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> @@ -82,8 +83,10 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - if (fd < fdt->max_fds) + if (fd < fdt->max_fds) { + fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); + } return NULL; } diff --git a/include/linux/init.h b/include/linux/init.h index ea1b31101d9e..506a98151131 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -5,6 +5,13 @@ #include <linux/compiler.h> #include <linux/types.h> +/* Built-in __init functions needn't be compiled with retpoline */ +#if defined(RETPOLINE) && !defined(MODULE) +#define __noretpoline __attribute__((indirect_branch("keep"))) +#else +#define __noretpoline +#endif + /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -40,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy +#define __init __section(.init.text) __cold __latent_entropy __noretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/module.h b/include/linux/module.h index c69b49abe877..1d8f245967be 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -801,6 +801,15 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef RETPOLINE +extern bool retpoline_module_ok(bool has_retpoline); +#else +static inline bool retpoline_module_ok(bool has_retpoline) +{ + return true; +} +#endif + #ifdef CONFIG_MODULE_SIG static inline bool module_sig_ok(struct module *module) { diff --git a/include/linux/nospec.h b/include/linux/nospec.h new file mode 100644 index 000000000000..b99bced39ac2 --- /dev/null +++ b/include/linux/nospec.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Linus Torvalds. All rights reserved. +// Copyright(c) 2018 Alexei Starovoitov. All rights reserved. +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#ifndef _LINUX_NOSPEC_H +#define _LINUX_NOSPEC_H + +/** + * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * When @index is out of bounds (@index >= @size), the sign bit will be + * set. Extend the sign bit to all bits and invert, giving a result of + * zero for an out of bounds index, or ~0 if within bounds [0, @size). + */ +#ifndef array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) + return 0; + + /* + * Always calculate and emit the mask even if the compiler + * thinks the mask is not needed. The compiler does not take + * into account the value of @index under speculation. + */ + OPTIMIZER_HIDE_VAR(index); + return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); +} +#endif + +/* + * array_index_nospec - sanitize an array index after a bounds check + * + * For a code sequence like: + * + * if (index < size) { + * index = array_index_nospec(index, size); + * val = array[index]; + * } + * + * ...if the CPU speculates past the bounds check then + * array_index_nospec() will clamp the index within the range of [0, + * size). + */ +#define array_index_nospec(index, size) \ +({ \ + typeof(index) _i = (index); \ + typeof(size) _s = (size); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ + \ + BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ + BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ + \ + _i &= _mask; \ + _i; \ +}) +#endif /* _LINUX_NOSPEC_H */ diff --git a/kernel/module.c b/kernel/module.c index dea01ac9cb74..09e48eee4d55 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2863,6 +2863,15 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info) } #endif /* CONFIG_LIVEPATCH */ +static void check_modinfo_retpoline(struct module *mod, struct load_info *info) +{ + if (retpoline_module_ok(get_modinfo(info, "retpoline"))) + return; + + pr_warn("%s: loading module not compiled with retpoline compiler.\n", + mod->name); +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -3029,6 +3038,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); } + check_modinfo_retpoline(mod, info); + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); pr_warn("%s: module is from the staging directory, the quality " diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 542a4fc0a8d7..4bbcfc1e2d43 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16,6 +16,7 @@ #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/genetlink.h> @@ -2056,20 +2057,22 @@ static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { + u8 ac; + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); + ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); - if (txq_params->ac >= NL80211_NUM_ACS) + if (ac >= NL80211_NUM_ACS) return -EINVAL; - + txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS); return 0; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index f51cf977c65b..6510536c06df 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2165,6 +2165,14 @@ static void add_intree_flag(struct buffer *b, int is_intree) buf_printf(b, "\nMODULE_INFO(intree, \"Y\");\n"); } +/* Cannot check for assembler */ +static void add_retpoline(struct buffer *b) +{ + buf_printf(b, "\n#ifdef RETPOLINE\n"); + buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n"); + buf_printf(b, "#endif\n"); +} + static void add_staging_flag(struct buffer *b, const char *name) { static const char *staging_dir = "drivers/staging"; @@ -2506,6 +2514,7 @@ int main(int argc, char **argv) err |= check_modname_len(mod); add_header(&buf, mod); add_intree_flag(&buf, !external_module); + add_retpoline(&buf); add_staging_flag(&buf, mod->name); err |= add_versions(&buf, mod); add_depends(&buf, mod, modules); diff --git a/sound/soc/codecs/pcm512x-spi.c b/sound/soc/codecs/pcm512x-spi.c index 25c63510ae15..7cdd2dc4fd79 100644 --- a/sound/soc/codecs/pcm512x-spi.c +++ b/sound/soc/codecs/pcm512x-spi.c @@ -70,3 +70,7 @@ static struct spi_driver pcm512x_spi_driver = { }; module_spi_driver(pcm512x_spi_driver); + +MODULE_DESCRIPTION("ASoC PCM512x codec driver - SPI"); +MODULE_AUTHOR("Mark Brown <broonie(a)kernel.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f40d46e24bcc..9cd028aa1509 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -543,18 +543,14 @@ static int add_call_destinations(struct objtool_file *file) dest_off = insn->offset + insn->len + insn->immediate; insn->call_dest = find_symbol_by_offset(insn->sec, dest_off); - /* - * FIXME: Thanks to retpolines, it's now considered - * normal for a function to call within itself. So - * disable this warning for now. - */ -#if 0 - if (!insn->call_dest) { - WARN_FUNC("can't find call dest symbol at offset 0x%lx", - insn->sec, insn->offset, dest_off); + + if (!insn->call_dest && !insn->ignore) { + WARN_FUNC("unsupported intra-function call", + insn->sec, insn->offset); + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } -#endif + } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -598,7 +594,7 @@ static int handle_group_alt(struct objtool_file *file, struct instruction *orig_insn, struct instruction **new_insn) { - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; + struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump = NULL; unsigned long dest_off; last_orig_insn = NULL; @@ -614,28 +610,30 @@ static int handle_group_alt(struct objtool_file *file, last_orig_insn = insn; } - if (!next_insn_same_sec(file, last_orig_insn)) { - WARN("%s: don't know how to handle alternatives at end of section", - special_alt->orig_sec->name); - return -1; - } - - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; + if (next_insn_same_sec(file, last_orig_insn)) { + fake_jump = malloc(sizeof(*fake_jump)); + if (!fake_jump) { + WARN("malloc failed"); + return -1; + } + memset(fake_jump, 0, sizeof(*fake_jump)); + INIT_LIST_HEAD(&fake_jump->alts); + clear_insn_state(&fake_jump->state); + + fake_jump->sec = special_alt->new_sec; + fake_jump->offset = -1; + fake_jump->type = INSN_JUMP_UNCONDITIONAL; + fake_jump->jump_dest = list_next_entry(last_orig_insn, list); + fake_jump->ignore = true; } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - clear_insn_state(&fake_jump->state); - - fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - fake_jump->ignore = true; if (!special_alt->new_len) { + if (!fake_jump) { + WARN("%s: empty alternative at end of section", + special_alt->orig_sec->name); + return -1; + } + *new_insn = fake_jump; return 0; } @@ -648,6 +646,8 @@ static int handle_group_alt(struct objtool_file *file, last_new_insn = insn; + insn->ignore = orig_insn->ignore_alts; + if (insn->type != INSN_JUMP_CONDITIONAL && insn->type != INSN_JUMP_UNCONDITIONAL) continue; @@ -656,8 +656,14 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = insn->offset + insn->len + insn->immediate; - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { + if (!fake_jump) { + WARN("%s: alternative jump to end of section", + special_alt->orig_sec->name); + return -1; + } insn->jump_dest = fake_jump; + } if (!insn->jump_dest) { WARN_FUNC("can't find alternative jump destination", @@ -672,7 +678,8 @@ static int handle_group_alt(struct objtool_file *file, return -1; } - list_add(&fake_jump->list, &last_new_insn->list); + if (fake_jump) + list_add(&fake_jump->list, &last_new_insn->list); return 0; } @@ -729,10 +736,6 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } - /* Ignore retpoline alternatives. */ - if (orig_insn->ignore_alts) - continue; - new_insn = NULL; if (!special_alt->group || special_alt->new_len) { new_insn = find_insn(file, special_alt->new_sec, @@ -1089,11 +1092,11 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - ret = add_call_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_call_destinations(file); if (ret) return ret; @@ -1720,10 +1723,12 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, insn->visited = true; - list_for_each_entry(alt, &insn->alts, list) { - ret = validate_branch(file, alt->insn, state); - if (ret) - return 1; + if (!insn->ignore_alts) { + list_for_each_entry(alt, &insn->alts, list) { + ret = validate_branch(file, alt->insn, state); + if (ret) + return 1; + } } switch (insn->type) { diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e61fe703197b..18384d9be4e1 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -98,6 +98,11 @@ static int create_orc_entry(struct section *u_sec, struct section *ip_relasec, struct orc_entry *orc; struct rela *rela; + if (!insn_sec->sym) { + WARN("missing symbol for section %s", insn_sec->name); + return -1; + } + /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc));

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] Linux 4.14.18

by Greg KH

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8122b5f98ea1..c76afdcafbef 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2718,8 +2718,6 @@ norandmaps Don't use address space randomization. Equivalent to echo 0 > /proc/sys/kernel/randomize_va_space - noreplace-paravirt [X86,IA-64,PV_OPS] Don't patch paravirt_ops - noreplace-smp [X86-32,SMP] Don't replace SMP instructions with UP alternatives diff --git a/Documentation/speculation.txt b/Documentation/speculation.txt new file mode 100644 index 000000000000..e9e6cbae2841 --- /dev/null +++ b/Documentation/speculation.txt @@ -0,0 +1,90 @@ +This document explains potential effects of speculation, and how undesirable +effects can be mitigated portably using common APIs. + +=========== +Speculation +=========== + +To improve performance and minimize average latencies, many contemporary CPUs +employ speculative execution techniques such as branch prediction, performing +work which may be discarded at a later stage. + +Typically speculative execution cannot be observed from architectural state, +such as the contents of registers. However, in some cases it is possible to +observe its impact on microarchitectural state, such as the presence or +absence of data in caches. Such state may form side-channels which can be +observed to extract secret information. + +For example, in the presence of branch prediction, it is possible for bounds +checks to be ignored by code which is speculatively executed. Consider the +following code: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else + return array[index]; + } + +Which, on arm64, may be compiled to an assembly sequence such as: + + CMP <index>, #MAX_ARRAY_ELEMS + B.LT less + MOV <returnval>, #0 + RET + less: + LDR <returnval>, [<array>, <index>] + RET + +It is possible that a CPU mis-predicts the conditional branch, and +speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This +value will subsequently be discarded, but the speculated load may affect +microarchitectural state which can be subsequently measured. + +More complex sequences involving multiple dependent memory accesses may +result in sensitive information being leaked. Consider the following +code, building on the prior example: + + int load_dependent_arrays(int *arr1, int *arr2, int index) + { + int val1, val2, + + val1 = load_array(arr1, index); + val2 = load_array(arr2, val1); + + return val2; + } + +Under speculation, the first call to load_array() may return the value +of an out-of-bounds address, while the second call will influence +microarchitectural state dependent on this value. This may provide an +arbitrary read primitive. + +==================================== +Mitigating speculation side-channels +==================================== + +The kernel provides a generic API to ensure that bounds checks are +respected even under speculation. Architectures which are affected by +speculation-based side-channels are expected to implement these +primitives. + +The array_index_nospec() helper in <linux/nospec.h> can be used to +prevent information from being leaked via side-channels. + +A call to array_index_nospec(index, size) returns a sanitized index +value that is bounded to [0, size) even under cpu speculation +conditions. + +This can be used to protect the earlier load_array() example: + + int load_array(int *array, unsigned int index) + { + if (index >= MAX_ARRAY_ELEMS) + return 0; + else { + index = array_index_nospec(index, MAX_ARRAY_ELEMS); + return array[index]; + } + } diff --git a/Makefile b/Makefile index 7ed993896dd5..a69e5da9ed86 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 17 +SUBLEVEL = 18 EXTRAVERSION = NAME = Petit Gorille diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index cb782ac1c35d..fe418226df7f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,6 +164,7 @@ config PPC select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL select GENERIC_SMP_IDLE_THREAD diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 935059cb9e40..9527a4c6cbc2 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -38,6 +38,7 @@ #include <linux/memory.h> #include <linux/nmi.h> +#include <asm/debugfs.h> #include <asm/io.h> #include <asm/kdump.h> #include <asm/prom.h> @@ -884,4 +885,41 @@ void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) if (!no_rfi_flush) rfi_flush_enable(enable); } + +#ifdef CONFIG_DEBUG_FS +static int rfi_flush_set(void *data, u64 val) +{ + if (val == 1) + rfi_flush_enable(true); + else if (val == 0) + rfi_flush_enable(false); + else + return -EINVAL; + + return 0; +} + +static int rfi_flush_get(void *data, u64 *val) +{ + *val = rfi_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); + +static __init int rfi_flush_debugfs_init(void) +{ + debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + return 0; +} +device_initcall(rfi_flush_debugfs_init); +#endif + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (rfi_flush) + return sprintf(buf, "Mitigation: RFI Flush\n"); + + return sprintf(buf, "Vulnerable\n"); +} #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03505ffbe1b6..60e21ccfb6d6 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/context_tracking.h> #include <linux/user-return-notifier.h> +#include <linux/nospec.h> #include <linux/uprobes.h> #include <linux/livepatch.h> #include <linux/syscalls.h> @@ -208,7 +209,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -284,7 +285,8 @@ __visible void do_syscall_64(struct pt_regs *regs) * regs->orig_ax, which changes the behavior of some syscalls. */ if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) { - regs->ax = sys_call_table[nr & __SYSCALL_MASK]( + nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls); + regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); } @@ -306,7 +308,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - current->thread.status |= TS_COMPAT; + ti->status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { @@ -320,6 +322,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) } if (likely(nr < IA32_NR_syscalls)) { + nr = array_index_nospec(nr, IA32_NR_syscalls); /* * It's possible that a 32-bit syscall implementation * takes a 64-bit parameter but nonetheless assumes that diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 60c4c342316c..2a35b1e0fb90 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,7 +252,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %ebx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index be6b66464f6a..16e2d72e79a0 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -232,91 +232,20 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ pushq %r11 /* pt_regs->r11 */ - sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ - UNWIND_HINT_REGS extra=0 - - TRACE_IRQS_OFF - - /* - * If we need to do entry work or if we guess we'll need to do - * exit work, go straight to the slow path. - */ - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz entry_SYSCALL64_slow_path - -entry_SYSCALL_64_fastpath: - /* - * Easy case: enable interrupts and issue the syscall. If the syscall - * needs pt_regs, we'll call a stub that disables interrupts again - * and jumps to the slow path. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax -#else - andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10, %rcx - - /* - * This call instruction is handled specially in stub_ptregs_64. - * It might end up jumping to the slow path. If it jumps, RAX - * and all argument registers are clobbered. - */ -#ifdef CONFIG_RETPOLINE - movq sys_call_table(, %rax, 8), %rax - call __x86_indirect_thunk_rax -#else - call *sys_call_table(, %rax, 8) -#endif -.Lentry_SYSCALL_64_after_fastpath_call: - - movq %rax, RAX(%rsp) -1: + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS - /* - * If we get here, then we know that pt_regs is clean for SYSRET64. - * If we see that no exit work is required (which we are required - * to check with IRQs off), then we can go straight to SYSRET64. - */ - DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - movq PER_CPU_VAR(current_task), %r11 - testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) - jnz 1f - - LOCKDEP_SYS_EXIT - TRACE_IRQS_ON /* user mode is traced as IRQs on */ - movq RIP(%rsp), %rcx - movq EFLAGS(%rsp), %r11 - addq $6*8, %rsp /* skip extra regs -- they were preserved */ - UNWIND_HINT_EMPTY - jmp .Lpop_c_regs_except_rcx_r11_and_sysret -1: - /* - * The fast path looked good when we started, but something changed - * along the way and we need to switch to the slow path. Calling - * raise(3) will trigger this, for example. IRQs are off. - */ - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - SAVE_EXTRA_REGS - movq %rsp, %rdi - call syscall_return_slowpath /* returns with IRQs disabled */ - jmp return_from_SYSCALL_64 - -entry_SYSCALL64_slow_path: /* IRQs are off. */ - SAVE_EXTRA_REGS movq %rsp, %rdi call do_syscall_64 /* returns with IRQs disabled */ -return_from_SYSCALL_64: TRACE_IRQS_IRETQ /* we're about to change IF */ /* @@ -389,7 +318,6 @@ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY POP_EXTRA_REGS -.Lpop_c_regs_except_rcx_r11_and_sysret: popq %rsi /* skip r11 */ popq %r10 popq %r9 @@ -420,47 +348,6 @@ syscall_return_via_sysret: USERGS_SYSRET64 END(entry_SYSCALL_64) -ENTRY(stub_ptregs_64) - /* - * Syscalls marked as needing ptregs land here. - * If we are on the fast path, we need to save the extra regs, - * which we achieve by trying again on the slow path. If we are on - * the slow path, the extra regs are already saved. - * - * RAX stores a pointer to the C function implementing the syscall. - * IRQs are on. - */ - cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) - jne 1f - - /* - * Called from fast path -- disable IRQs again, pop return address - * and jump to slow path - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - popq %rax - UNWIND_HINT_REGS extra=0 - jmp entry_SYSCALL64_slow_path - -1: - JMP_NOSPEC %rax /* Called from C */ -END(stub_ptregs_64) - -.macro ptregs_stub func -ENTRY(ptregs_\func) - UNWIND_HINT_FUNC - leaq \func(%rip), %rax - jmp stub_ptregs_64 -END(ptregs_\func) -.endm - -/* Instantiate ptregs_stub for each ptregs-using syscall */ -#define __SYSCALL_64_QUAL_(sym) -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym -#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) -#include <asm/syscalls_64.h> - /* * %rdi: prev task * %rsi: next task @@ -495,7 +382,8 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + /* Clobbers %rbx */ + FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9c09775e589d..c176d2fab1da 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -7,14 +7,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_64_QUAL_(sym) sym -#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym - -#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), +#define __SYSCALL_64(nr, sym, qual) [nr] = sym, extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 0927cdc4f946..4d111616524b 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,5 +38,7 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -INDIRECT_THUNK(sp) +asmlinkage void __fill_rsb(void); +asmlinkage void __clear_rsb(void); + #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 01727dbc294a..1e7c955b6303 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -24,6 +24,34 @@ #define wmb() asm volatile("sfence" ::: "memory") #endif +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * Returns: + * 0 - (index < size) + */ +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + asm ("cmp %1,%2; sbb %0,%0;" + :"=r" (mask) + :"r"(size),"r" (index) + :"cc"); + return mask; +} + +/* Override the default implementation from linux/nospec.h. */ +#define array_index_mask_nospec array_index_mask_nospec + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ + "lfence", X86_FEATURE_LFENCE_RDTSC) + #ifdef CONFIG_X86_PPRO_FENCE #define dma_rmb() rmb() #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index ea9a7dde62e5..70eddb3922ff 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -29,6 +29,7 @@ enum cpuid_leafs CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, + CPUID_7_EDX, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 18)) + BUILD_BUG_ON_ZERO(NCAPINTS != 19)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 25b9375c1484..73b5fff159a4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -203,14 +203,14 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ + +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -271,6 +271,9 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -319,6 +322,13 @@ #define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index e428e16dd822..c6a3af198294 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -71,6 +71,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 64c4a30e0d39..e203169931c7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -137,8 +137,10 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); -#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_TOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_TOT_START (FIXADDR_TOP - FIXADDR_TOT_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fa11fb1fa570..eb83ff1bae8f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -39,6 +39,13 @@ /* Intel MSRs. Some also available on other CPUs */ +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ + #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -57,6 +64,11 @@ #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) #define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 07962f5f6fba..30df295f6d94 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void) * that some other imaginary CPU is updating continuously with a * time stamp. */ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); + barrier_nospec(); return rdtsc(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4ad41087ce0e..4d57894635f2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -1,56 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NOSPEC_BRANCH_H__ -#define __NOSPEC_BRANCH_H__ +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * We define a CPP macro such that it can be used from both .S files and - * inline assembly. It's possible to do a .macro and then include that - * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. - */ - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -/* - * Google experimented with loop-unrolling and this turned out to be - * the optimal version — two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -#define __FILL_RETURN_BUFFER(reg, nr, sp) \ - mov $(nr/2), reg; \ -771: \ - call 772f; \ -773: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 773b; \ -772: \ - call 774f; \ -775: /* speculation trap */ \ - pause; \ - lfence; \ - jmp 775b; \ -774: \ - dec reg; \ - jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; - #ifdef __ASSEMBLY__ /* @@ -121,17 +77,10 @@ #endif .endm - /* - * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP - * monstrosity above, manually. - */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +/* This clobbers the BX register */ +.macro FILL_RETURN_BUFFER nr:req ftr:req #ifdef CONFIG_RETPOLINE - ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE "jmp .Lskip_rsb_\@", \ - __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ - \ftr -.Lskip_rsb_\@: + ALTERNATIVE "", "call __clear_rsb", \ftr #endif .endm @@ -201,22 +150,25 @@ extern char __indirect_thunk_end[]; * On VMEXIT we must ensure that no RSB predictions learned in the guest * can be followed in the host, by overwriting the RSB completely. Both * retpoline and IBRS mitigations for Spectre v2 need this; only on future - * CPUs with IBRS_ATT *might* it be avoided. + * CPUs with IBRS_ALL *might* it be avoided. */ static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - unsigned long loops; - - asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE("jmp 910f", - __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), - X86_FEATURE_RETPOLINE) - "910:" - : "=r" (loops), ASM_CALL_CONSTRAINT - : : "memory" ); + alternative_input("", + "call __fill_rsb", + X86_FEATURE_RETPOLINE, + ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); #endif } +static inline void indirect_branch_prediction_barrier(void) +{ + alternative_input("", + "call __ibp_barrier", + X86_FEATURE_USE_IBPB, + ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); +} + #endif /* __ASSEMBLY__ */ -#endif /* __NOSPEC_BRANCH_H__ */ +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index ce245b0cdfca..0777e18a1d23 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -44,8 +44,9 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ */ #define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) \ + & PMD_MASK) #define PKMAP_BASE \ ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9c18da64daa9..c57c6e77c29f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -459,8 +459,6 @@ struct thread_struct { unsigned short gsindex; #endif - u32 status; /* thread synchronous flags */ - #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -970,4 +968,7 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); + +void __ibp_barrier(void); + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d91ba04dd007..fb3a6de7440b 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -106,6 +106,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index e3c95e8e61c5..03eedc21246d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread.status & TS_COMPAT) + if (task->thread_info.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 00223333821a..eda3b6823ca4 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,6 +55,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ }; #define INIT_THREAD_INFO(tsk) \ @@ -221,7 +222,7 @@ static inline int arch_within_stack_frames(const void * const stack, #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ - current->thread.status & TS_COMPAT) + current_thread_info()->status & TS_COMPAT) #endif /* diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 3effd3c994af..4405c4b308e8 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -174,6 +174,8 @@ struct tlb_state { struct mm_struct *loaded_mm; u16 loaded_mm_asid; u16 next_asid; + /* last user mm's ctx id */ + u64 last_ctx_id; /* * We can be in one of several states: diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 574dff4d2913..aae77eb8491c 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -124,6 +124,11 @@ extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) /* * This is a type: either unsigned long, if the argument fits into @@ -445,7 +450,7 @@ do { \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; }; __uaccess_begin(); \ barrier(); +#define uaccess_try_nospec do { \ + current->thread.uaccess_err = 0; \ + __uaccess_begin_nospec(); \ + #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ @@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; }; * get_user_ex(...); * } get_user_catch(err) */ -#define get_user_try uaccess_try +#define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ @@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __uaccess_begin(); \ + __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 72950401b223..ba2dc1930630 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)to, from, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)to, from, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: ret = 0; - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)to, from, ret, "l", "k", "=r", 4); __uaccess_end(); diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f07ef3c575db..62546b3a398e 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) return copy_user_generic(dst, (__force void *)src, size); switch (size) { case 1: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); __uaccess_end(); return ret; case 2: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); __uaccess_end(); return ret; case 4: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); __uaccess_end(); return ret; case 8: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); __uaccess_end(); return ret; case 10: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); if (likely(!ret)) @@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size) __uaccess_end(); return ret; case 16: - __uaccess_begin(); + __uaccess_begin_nospec(); __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); if (likely(!ret)) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index e0b97e4d1db5..21be0193d9dc 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -46,17 +46,6 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#ifdef CONFIG_PARAVIRT -static int __initdata_or_module noreplace_paravirt = 0; - -static int __init setup_noreplace_paravirt(char *str) -{ - noreplace_paravirt = 1; - return 1; -} -__setup("noreplace-paravirt", setup_noreplace_paravirt); -#endif - #define DPRINTK(fmt, args...) \ do { \ if (debug_alternative) \ @@ -298,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -355,7 +344,7 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins add_nops(instr + (a->instrlen - a->padlen), a->padlen); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -376,7 +365,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %p -> %p", start, end); + DPRINTK("alt table %px, -> %px", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -400,14 +389,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -433,7 +422,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } @@ -599,9 +588,6 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *p; char insnbuf[MAX_PATCH_LEN]; - if (noreplace_paravirt) - return; - for (p = start; p < end; p++) { unsigned int used; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 390b3dc3d438..71949bf2de5a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/utsname.h> #include <linux/cpu.h> +#include <linux/module.h> #include <asm/nospec-branch.h> #include <asm/cmdline.h> @@ -90,20 +91,41 @@ static const char *spectre_v2_strings[] = { }; #undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +#ifdef RETPOLINE +static bool spectre_v2_bad_module; + +bool retpoline_module_ok(bool has_retpoline) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) + return true; + + pr_err("System may be vulnerable to spectre v2\n"); + spectre_v2_bad_module = true; + return false; +} + +static inline const char *spectre_v2_module_string(void) +{ + return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; +} +#else +static inline const char *spectre_v2_module_string(void) { return ""; } +#endif + static void __init spec2_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static void __init spec2_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s\n", reason); + pr_info("%s selected on command line.\n", reason); } static inline bool retp_compiler(void) @@ -118,42 +140,68 @@ static inline bool match_option(const char *arg, int arglen, const char *opt) return len == arglen && !strncmp(arg, opt, len); } +static const struct { + const char *option; + enum spectre_v2_mitigation_cmd cmd; + bool secure; +} mitigation_options[] = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, +}; + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { char arg[20]; - int ret; - - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); - if (ret > 0) { - if (match_option(arg, ret, "off")) { - goto disable; - } else if (match_option(arg, ret, "on")) { - spec2_print_if_secure("force enabled on command line."); - return SPECTRE_V2_CMD_FORCE; - } else if (match_option(arg, ret, "retpoline")) { - spec2_print_if_insecure("retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE; - } else if (match_option(arg, ret, "retpoline,amd")) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); - return SPECTRE_V2_CMD_AUTO; - } - spec2_print_if_insecure("AMD retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_AMD; - } else if (match_option(arg, ret, "retpoline,generic")) { - spec2_print_if_insecure("generic retpoline selected on command line."); - return SPECTRE_V2_CMD_RETPOLINE_GENERIC; - } else if (match_option(arg, ret, "auto")) { + int ret, i; + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_NONE; + else { + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } } - if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if ((cmd == SPECTRE_V2_CMD_RETPOLINE || + cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + !IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; -disable: - spec2_print_if_insecure("disabled on command line."); - return SPECTRE_V2_CMD_NONE; + } + + if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + + if (mitigation_options[i].secure) + spec2_print_if_secure(mitigation_options[i].option); + else + spec2_print_if_insecure(mitigation_options[i].option); + + return cmd; } /* Check for Skylake-like CPUs (for RSB handling) */ @@ -191,10 +239,10 @@ static void __init spectre_v2_select_mitigation(void) return; case SPECTRE_V2_CMD_FORCE: - /* FALLTRHU */ case SPECTRE_V2_CMD_AUTO: - goto retpoline_auto; - + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; case SPECTRE_V2_CMD_RETPOLINE_AMD: if (IS_ENABLED(CONFIG_RETPOLINE)) goto retpoline_amd; @@ -249,6 +297,12 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Filling RSB on context switch\n"); } + + /* Initialize Indirect Branch Prediction Barrier if supported */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + pr_info("Enabling Indirect Branch Prediction Barrier\n"); + } } #undef pr_fmt @@ -269,7 +323,7 @@ ssize_t cpu_show_spectre_v1(struct device *dev, { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Vulnerable\n"); + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } ssize_t cpu_show_spectre_v2(struct device *dev, @@ -278,6 +332,14 @@ ssize_t cpu_show_spectre_v2(struct device *dev, if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); + return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + spectre_v2_module_string()); } #endif + +void __ibp_barrier(void) +{ + __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); +} +EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 372ba3fb400f..92b66e21bae5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -47,6 +47,8 @@ #include <asm/pat.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #ifdef CONFIG_X86_LOCAL_APIC #include <asm/uv/uv.h> @@ -724,6 +726,26 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) } } +static void init_speculation_control(struct cpuinfo_x86 *c) +{ + /* + * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support, + * and they also have a different bit for STIBP support. Also, + * a hypervisor might have set the individual AMD bits even on + * Intel CPUs, for finer-grained selection of what's available. + * + * We use the AMD bits in 0x8000_0008 EBX as the generic hardware + * features, which are visible in /proc/cpuinfo and used by the + * kernel. So set those accordingly from the Intel bits. + */ + if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_IBPB); + } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) + set_cpu_cap(c, X86_FEATURE_STIBP); +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -745,6 +767,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_7_ECX] = ecx; + c->x86_capability[CPUID_7_EDX] = edx; } /* Extended state features: level 0x0000000d */ @@ -817,6 +840,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + init_speculation_control(c); /* * Clear/Set all flags overridden by options, after probe. @@ -852,6 +876,41 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } +static const __initconst struct x86_cpu_id cpu_no_speculation[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_CENTAUR, 5 }, + { X86_VENDOR_INTEL, 5 }, + { X86_VENDOR_NSC, 5 }, + { X86_VENDOR_ANY, 4 }, + {} +}; + +static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { + { X86_VENDOR_AMD }, + {} +}; + +static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = 0; + + if (x86_match_cpu(cpu_no_meltdown)) + return false; + + if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + /* Rogue Data Cache Load? No! */ + if (ia32_cap & ARCH_CAP_RDCL_NO) + return false; + + return true; +} + /* * Do minimum CPU detection early. * Fields really needed: vendor, cpuid_level, family, model, mask, @@ -899,11 +958,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (c->x86_vendor != X86_VENDOR_AMD) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + if (!x86_match_cpu(cpu_no_speculation)) { + if (cpu_vulnerable_to_meltdown(c)) + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + } fpu__init_system(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b720dacac051..4cf4f8cbc69d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -102,6 +102,59 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; } +/* + * Early microcode releases for the Spectre v2 mitigation were broken. + * Information taken from; + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-up… + * - https://kb.vmware.com/s/article/52345 + * - Microcode revisions observed in the wild + * - Release note from 20180108 microcode release + */ +struct sku_microcode { + u8 model; + u8 stepping; + u32 microcode; +}; +static const struct sku_microcode spectre_bad_microcodes[] = { + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, + { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, + { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, + { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, + { INTEL_FAM6_BROADWELL_XEON_D, 0x03, 0x07000011 }, + { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_FAM6_HASWELL_ULT, 0x01, 0x21 }, + { INTEL_FAM6_HASWELL_GT3E, 0x01, 0x18 }, + { INTEL_FAM6_HASWELL_CORE, 0x03, 0x23 }, + { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, + { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, + { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + /* Updated in the 20180108 release; blacklist until we know otherwise */ + { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, + /* Observed in the wild */ + { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, +}; + +static bool bad_spectre_microcode(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { + if (c->x86_model == spectre_bad_microcodes[i].model && + c->x86_mask == spectre_bad_microcodes[i].stepping) + return (c->microcode <= spectre_bad_microcodes[i].microcode); + } + return false; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -122,6 +175,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) c->microcode = intel_get_microcode_revision(); + /* Now if any of them are set, check the blacklist and clear the lot */ + if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || + cpu_has(c, X86_FEATURE_INTEL_STIBP) || + cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) || + cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) { + pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n"); + setup_clear_cpu_cap(X86_FEATURE_IBRS); + setup_clear_cpu_cap(X86_FEATURE_IBPB); + setup_clear_cpu_cap(X86_FEATURE_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d0e69769abfd..df11f5d604be 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -21,8 +21,6 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, - { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 }, - { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 }, { X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 }, { X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 }, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c75466232016..9eb448c7859d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -557,7 +557,7 @@ static void __set_personality_x32(void) * Pretend to come from a x32 execve. */ task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; - current->thread.status &= ~TS_COMPAT; + current_thread_info()->status &= ~TS_COMPAT; #endif } @@ -571,7 +571,7 @@ static void __set_personality_ia32(void) current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; - current->thread.status |= TS_COMPAT; + current_thread_info()->status |= TS_COMPAT; #endif } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f37d18124648..ed5c4cdf0a34 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -935,7 +935,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - child->thread.status |= TS_I386_REGS_POKED; + child->thread_info.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b9e00e8f1c9b..4cdc0b27ec82 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -787,7 +787,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0099e10eb045..13f5d4217e4f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -67,9 +67,7 @@ u64 kvm_supported_xcr0(void) #define F(x) bit(X86_FEATURE_##x) -/* These are scattered features in cpufeatures.h. */ -#define KVM_CPUID_BIT_AVX512_4VNNIW 2 -#define KVM_CPUID_BIT_AVX512_4FMAPS 3 +/* For scattered features from cpufeatures.h; we currently expose none */ #define KF(x) bit(KVM_CPUID_BIT_##x) int kvm_update_cpuid(struct kvm_vcpu *vcpu) @@ -367,6 +365,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB) | F(IBRS); + /* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -392,7 +394,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - KF(AVX512_4VNNIW) | KF(AVX512_4FMAPS); + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -477,7 +480,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; - entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); + cpuid_mask(&entry->edx, CPUID_7_EDX); } else { entry->ebx = 0; entry->ecx = 0; @@ -627,7 +630,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c2cea6651279..9a327d5b6d1f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -54,6 +54,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX}, [CPUID_7_ECX] = { 7, 0, CPUID_ECX}, [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX}, + [CPUID_7_EDX] = { 7, 0, CPUID_EDX}, }; static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index eca6a89f2326..fab073b19528 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" @@ -1021,8 +1022,8 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; - asm("push %[flags]; popf; call *%[fastop]" - : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + asm("push %[flags]; popf; " CALL_NOSPEC + : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } @@ -5350,9 +5351,9 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; - asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), ASM_CALL_CONSTRAINT + [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6a8284f72328..e0bc3ad0f6cd 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -184,6 +184,8 @@ struct vcpu_svm { u64 gs_base; } host; + u64 spec_ctrl; + u32 *msrpm; ulong nmi_iret_rip; @@ -249,6 +251,8 @@ static const struct svm_direct_access_msrs { { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -529,6 +533,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc; struct page *save_area; + struct vmcb *current_vmcb; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -880,6 +885,25 @@ static bool valid_msr_intercept(u32 index) return false; } +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return !!test_bit(bit_write, &tmp); +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { @@ -1585,6 +1609,8 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + svm->spec_ctrl = 0; + if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; @@ -1706,11 +1732,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i; if (unlikely(cpu != vcpu->cpu)) { @@ -1739,6 +1771,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (static_cpu_has(X86_FEATURE_RDTSCP)) wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } avic_vcpu_load(vcpu, cpu); } @@ -3579,6 +3615,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_CR: msr_info->data = svm->nested.vm_cr_msr; break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + msr_info->data = svm->spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3670,6 +3713,49 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + svm->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4922,6 +5008,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + asm volatile ( "push %%" _ASM_BP "; \n\t" "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" @@ -5014,6 +5109,27 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + + if (svm->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a45063a9219c..0ae4b1a86168 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -34,6 +34,7 @@ #include <linux/tboot.h> #include <linux/hrtimer.h> #include <linux/frame.h> +#include <linux/nospec.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -108,6 +109,14 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define MSR_BITMAP_MODE_X2APIC 1 +#define MSR_BITMAP_MODE_X2APIC_APICV 2 +#define MSR_BITMAP_MODE_LM 4 + #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL /* Guest_tsc -> host_tsc conversion requires 64-bit division. */ @@ -182,7 +191,6 @@ module_param(ple_window_max, int, S_IRUGO); extern const ulong vmx_return; #define NR_AUTOLOAD_MSRS 8 -#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -207,6 +215,7 @@ struct loaded_vmcs { int soft_vnmi_blocked; ktime_t entry_time; s64 vnmi_blocked_time; + unsigned long *msr_bitmap; struct list_head loaded_vmcss_on_cpu_link; }; @@ -223,7 +232,7 @@ struct shared_msr_entry { * stored in guest memory specified by VMPTRLD, but is opaque to the guest, * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. * More than one of these structures may exist, if L1 runs multiple L2 guests. - * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * nested_vmx_run() will use the data here to build the vmcs02: a VMCS for the * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). @@ -406,13 +415,6 @@ struct __packed vmcs12 { */ #define VMCS12_SIZE 0x1000 -/* Used to remember the last vmcs02 used for some recently used vmcs12s */ -struct vmcs02_list { - struct list_head list; - gpa_t vmptr; - struct loaded_vmcs vmcs02; -}; - /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -437,15 +439,15 @@ struct nested_vmx { */ bool sync_shadow_vmcs; - /* vmcs02_list cache of VMCSs recently used to run L2 guests */ - struct list_head vmcs02_pool; - int vmcs02_num; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + + struct loaded_vmcs vmcs02; + /* - * Guest pages referred to in vmcs02 with host-physical pointers, so - * we must keep them pinned while L2 runs. + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. */ struct page *apic_access_page; struct page *virtual_apic_page; @@ -454,8 +456,6 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; - unsigned long *msr_bitmap; - struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -570,6 +570,7 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; + u8 msr_bitmap_mode; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -581,6 +582,10 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + + u64 arch_capabilities; + u64 spec_ctrl; + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; u32 secondary_exec_control; @@ -887,21 +892,18 @@ static const unsigned short vmcs_field_to_offset_table[] = { static inline short vmcs_field_to_offset(unsigned long field) { - BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); + const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); + unsigned short offset; - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + BUILD_BUG_ON(size > SHRT_MAX); + if (field >= size) return -ENOENT; - /* - * FIXME: Mitigation for CVE-2017-5753. To be replaced with a - * generic mechanism. - */ - asm("lfence"); - - if (vmcs_field_to_offset_table[field] == 0) + field = array_index_nospec(field, size); + offset = vmcs_field_to_offset_table[field]; + if (offset == 0) return -ENOENT; - - return vmcs_field_to_offset_table[field]; + return offset; } static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) @@ -927,6 +929,9 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -946,12 +951,6 @@ static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); enum { VMX_IO_BITMAP_A, VMX_IO_BITMAP_B, - VMX_MSR_BITMAP_LEGACY, - VMX_MSR_BITMAP_LONGMODE, - VMX_MSR_BITMAP_LEGACY_X2APIC_APICV, - VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV, - VMX_MSR_BITMAP_LEGACY_X2APIC, - VMX_MSR_BITMAP_LONGMODE_X2APIC, VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR @@ -961,12 +960,6 @@ static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; #define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A]) #define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B]) -#define vmx_msr_bitmap_legacy (vmx_bitmap[VMX_MSR_BITMAP_LEGACY]) -#define vmx_msr_bitmap_longmode (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE]) -#define vmx_msr_bitmap_legacy_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC_APICV]) -#define vmx_msr_bitmap_longmode_x2apic_apicv (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC_APICV]) -#define vmx_msr_bitmap_legacy_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LEGACY_X2APIC]) -#define vmx_msr_bitmap_longmode_x2apic (vmx_bitmap[VMX_MSR_BITMAP_LONGMODE_X2APIC]) #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) @@ -1913,6 +1906,52 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) vmcs_write32(EXCEPTION_BITMAP, eb); } +/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2291,6 +2330,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); } if (!already_loaded) { @@ -2567,36 +2607,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } -static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) -{ - unsigned long *msr_bitmap; - - if (is_guest_mode(vcpu)) - msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; - else if (cpu_has_secondary_exec_ctrls() && - (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic_apicv; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic_apicv; - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode_x2apic; - else - msr_bitmap = vmx_msr_bitmap_legacy_x2apic; - } - } else { - if (is_long_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - } - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); -} - /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -2637,7 +2647,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(&vmx->vcpu); + vmx_update_msr_bitmap(&vmx->vcpu); } /* @@ -3273,6 +3283,20 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = to_vmx(vcpu)->arch_capabilities; + break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -3380,6 +3404,70 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && + !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vmx->arch_capabilities = data; + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -3822,11 +3910,6 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) return vmcs; } -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3842,9 +3925,38 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + if (loaded_vmcs->msr_bitmap) + free_page((unsigned long)loaded_vmcs->msr_bitmap); WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } +static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs->shadow_vmcs = NULL; + loaded_vmcs_init(loaded_vmcs); + + if (cpu_has_vmx_msr_bitmap()) { + loaded_vmcs->msr_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); + if (!loaded_vmcs->msr_bitmap) + goto out_vmcs; + memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + } + return 0; + +out_vmcs: + free_loaded_vmcs(loaded_vmcs); + return -ENOMEM; +} + static void free_kvm_area(void) { int cpu; @@ -4917,10 +5029,8 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -4954,6 +5064,50 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, } } +static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) +{ + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + if (msr <= 0x1fff) { + if (type & MSR_TYPE_R) + /* read-low */ + __set_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __set_bit(msr, msr_bitmap + 0x800 / f); + + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + if (type & MSR_TYPE_R) + /* read-high */ + __set_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __set_bit(msr, msr_bitmap + 0xc00 / f); + + } +} + +static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type, bool value) +{ + if (value) + vmx_enable_intercept_for_msr(msr_bitmap, msr, type); + else + vmx_disable_intercept_for_msr(msr_bitmap, msr, type); +} + /* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. @@ -5000,30 +5154,70 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) +static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) { - if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, - msr, MSR_TYPE_R | MSR_TYPE_W); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, - msr, MSR_TYPE_R | MSR_TYPE_W); + u8 mode = 0; + + if (cpu_has_secondary_exec_ctrls() && + (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { + mode |= MSR_BITMAP_MODE_X2APIC; + if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) + mode |= MSR_BITMAP_MODE_X2APIC_APICV; + } + + if (is_long_mode(vcpu)) + mode |= MSR_BITMAP_MODE_LM; + + return mode; } -static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_active) +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, + u8 mode) { - if (apicv_active) { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic_apicv, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic_apicv, - msr, type); - } else { - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, - msr, type); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, - msr, type); + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } + + if (mode & MSR_BITMAP_MODE_X2APIC) { + /* + * TPR reads and writes can be virtualized even if virtual interrupt + * delivery is not in use. + */ + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { + vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); + vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + } } } +static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + u8 mode = vmx_msr_bitmap_mode(vcpu); + u8 changed = mode ^ vmx->msr_bitmap_mode; + + if (!changed) + return; + + vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, + !(mode & MSR_BITMAP_MODE_LM)); + + if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) + vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); + + vmx->msr_bitmap_mode = mode; +} + static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu) { return enable_apicv; @@ -5269,7 +5463,7 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static u32 vmx_exec_control(struct vcpu_vmx *vmx) @@ -5456,7 +5650,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); } if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_legacy)); + vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ @@ -5534,6 +5728,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl); @@ -5564,6 +5760,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u64 cr0; vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6739,7 +6936,7 @@ void vmx_enable_tdp(void) static __init int hardware_setup(void) { - int r = -ENOMEM, i, msr; + int r = -ENOMEM, i; rdmsrl_safe(MSR_EFER, &host_efer); @@ -6760,9 +6957,6 @@ static __init int hardware_setup(void) memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); - memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out; @@ -6825,42 +7019,8 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); - vmx_disable_intercept_for_msr(MSR_GS_BASE, false); - vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); - vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - - memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic_apicv, - vmx_msr_bitmap_longmode, PAGE_SIZE); - memcpy(vmx_msr_bitmap_legacy_x2apic, - vmx_msr_bitmap_legacy, PAGE_SIZE); - memcpy(vmx_msr_bitmap_longmode_x2apic, - vmx_msr_bitmap_longmode, PAGE_SIZE); - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - for (msr = 0x800; msr <= 0x8ff; msr++) { - if (msr == 0x839 /* TMCCT */) - continue; - vmx_disable_intercept_msr_x2apic(msr, MSR_TYPE_R, true); - } - - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_W, true); - vmx_disable_intercept_msr_x2apic(0x808, MSR_TYPE_R | MSR_TYPE_W, false); - - /* EOI */ - vmx_disable_intercept_msr_x2apic(0x80b, MSR_TYPE_W, true); - /* SELF-IPI */ - vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) vmx_enable_tdp(); else @@ -6963,94 +7123,6 @@ static int handle_monitor(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } -/* - * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. - * We could reuse a single VMCS for all the L2 guests, but we also want the - * option to allocate a separate vmcs02 for each separate loaded vmcs12 - this - * allows keeping them loaded on the processor, and in the future will allow - * optimizations where prepare_vmcs02 doesn't need to set all the fields on - * every entry if they never change. - * So we keep, in vmx->nested.vmcs02_pool, a cache of size VMCS02_POOL_SIZE - * (>=0) with a vmcs02 for each recently loaded vmcs12s, most recent first. - * - * The following functions allocate and free a vmcs02 in this pool. - */ - -/* Get a VMCS from the pool to use as vmcs02 for the current vmcs12. */ -static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmx->nested.current_vmptr) { - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { - /* Recycle the least recently used VMCS. */ - item = list_last_entry(&vmx->nested.vmcs02_pool, - struct vmcs02_list, list); - item->vmptr = vmx->nested.current_vmptr; - list_move(&item->list, &vmx->nested.vmcs02_pool); - return &item->vmcs02; - } - - /* Create a new VMCS */ - item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL); - if (!item) - return NULL; - item->vmcs02.vmcs = alloc_vmcs(); - item->vmcs02.shadow_vmcs = NULL; - if (!item->vmcs02.vmcs) { - kfree(item); - return NULL; - } - loaded_vmcs_init(&item->vmcs02); - item->vmptr = vmx->nested.current_vmptr; - list_add(&(item->list), &(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num++; - return &item->vmcs02; -} - -/* Free and remove from pool a vmcs02 saved for a vmcs12 (if there is one) */ -static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr) -{ - struct vmcs02_list *item; - list_for_each_entry(item, &vmx->nested.vmcs02_pool, list) - if (item->vmptr == vmptr) { - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - return; - } -} - -/* - * Free all VMCSs saved for this vcpu, except the one pointed by - * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs - * must be &vmx->vmcs01. - */ -static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) -{ - struct vmcs02_list *item, *n; - - WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01); - list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) { - /* - * Something will leak if the above WARN triggers. Better than - * a use-after-free. - */ - if (vmx->loaded_vmcs == &item->vmcs02) - continue; - - free_loaded_vmcs(&item->vmcs02); - list_del(&item->list); - kfree(item); - vmx->nested.vmcs02_num--; - } -} - /* * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), * set the success or error code of an emulated VMX instruction, as specified @@ -7231,13 +7303,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs *shadow_vmcs; + int r; - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) + goto out_vmcs02; vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) @@ -7254,9 +7324,6 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = shadow_vmcs; } - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; @@ -7268,9 +7335,9 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) kfree(vmx->nested.cached_vmcs12); out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); + free_loaded_vmcs(&vmx->nested.vmcs02); -out_msr_bitmap: +out_vmcs02: return -ENOMEM; } @@ -7412,10 +7479,6 @@ static void free_nested(struct vcpu_vmx *vmx) free_vpid(vmx->nested.vpid02); vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; - if (vmx->nested.msr_bitmap) { - free_page((unsigned long)vmx->nested.msr_bitmap); - vmx->nested.msr_bitmap = NULL; - } if (enable_shadow_vmcs) { vmx_disable_shadow_vmcs(vmx); vmcs_clear(vmx->vmcs01.shadow_vmcs); @@ -7423,7 +7486,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); - /* Unpin physical memory we referred to in current vmcs02 */ + /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); vmx->nested.apic_access_page = NULL; @@ -7439,7 +7502,7 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.pi_desc = NULL; } - nested_free_all_saved_vmcss(vmx); + free_loaded_vmcs(&vmx->nested.vmcs02); } /* Emulate the VMXOFF instruction */ @@ -7482,8 +7545,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - nested_free_vmcs02(vmx, vmptr); - nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -8395,10 +8456,11 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) /* * The host physical addresses of some pages of guest memory - * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU - * may write to these pages via their host physical address while - * L2 is running, bypassing any address-translation-based dirty - * tracking (e.g. EPT write protection). + * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC + * Page). The CPU may write to these pages via their host + * physical address while L2 is running, bypassing any + * address-translation-based dirty tracking (e.g. EPT write + * protection). * * Mark them dirty on every exit from L2 to prevent them from * getting out of sync with dirty tracking. @@ -8932,7 +8994,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); } static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) @@ -9118,14 +9180,14 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #endif "pushf\n\t" __ASM_SIZE(push) " $%c[cs]\n\t" - "call *%[entry]\n\t" + CALL_NOSPEC : #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif ASM_CALL_CONSTRAINT : - [entry]"r"(entry), + THUNK_TARGET(entry), [ss]"i"(__KERNEL_DS), [cs]"i"(__KERNEL_CS) ); @@ -9362,6 +9424,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_arm_hv_timer(vcpu); + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -9480,6 +9551,27 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -9594,6 +9686,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + unsigned long *msr_bitmap; int cpu; if (!vmx) @@ -9626,13 +9719,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx->guest_msrs) goto free_pml; - vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - vmx->loaded_vmcs->shadow_vmcs = NULL; - if (!vmx->loaded_vmcs->vmcs) + err = alloc_loaded_vmcs(&vmx->vmcs01); + if (err < 0) goto free_msrs; - loaded_vmcs_init(vmx->loaded_vmcs); + msr_bitmap = vmx->vmcs01.msr_bitmap; + vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + vmx->msr_bitmap_mode = 0; + + vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; @@ -10101,10 +10201,25 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, int msr; struct page *page; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd & spec_ctrl are trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); - /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd && !spec_ctrl) return false; page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap); @@ -10137,6 +10252,19 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, MSR_TYPE_W); } } + + if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); kvm_release_page_clean(page); @@ -10678,6 +10806,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); + if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10894,20 +11025,15 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct loaded_vmcs *vmcs02; u32 msr_entry_idx; u32 exit_qual; - vmcs02 = nested_get_current_vmcs02(vmx); - if (!vmcs02) - return -ENOMEM; - enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); - vmx_switch_vmcs(vcpu, vmcs02); + vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { @@ -11476,7 +11602,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_write64(GUEST_IA32_DEBUGCTL, 0); if (cpu_has_vmx_msr_bitmap()) - vmx_set_msr_bitmap(vcpu); + vmx_update_msr_bitmap(vcpu); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -11522,10 +11648,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vm_exit_controls_reset_shadow(vmx); vmx_segment_cache_clear(vmx); - /* if no vmcs02 cache requested, remove the one we used */ - if (VMCS02_POOL_SIZE == 0) - nested_free_vmcs02(vmx, vmx->nested.current_vmptr); - /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8c28023a43b1..f97358423f9c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1006,6 +1006,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES }; static unsigned num_msrs_to_save; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index d435c89875c1..d0a3170e6804 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -27,6 +27,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_RETPOLINE) += retpoline.o +OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index c97d935a29e8..49b167f73215 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -40,6 +40,8 @@ ENTRY(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -54,6 +56,8 @@ ENTRY(__get_user_2) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 2: movzwl -1(%_ASM_AX),%edx xor %eax,%eax @@ -68,6 +72,8 @@ ENTRY(__get_user_4) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 3: movl -3(%_ASM_AX),%edx xor %eax,%eax @@ -83,6 +89,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movq -7(%_ASM_AX),%rdx xor %eax,%eax @@ -94,6 +102,8 @@ ENTRY(__get_user_8) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user_8 + sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ + and %_ASM_DX, %_ASM_AX ASM_STAC 4: movl -7(%_ASM_AX),%edx 5: movl -3(%_ASM_AX),%ecx diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index dfb2ba91b670..480edc3a5e03 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,6 +7,7 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -36,7 +37,6 @@ GENERATE_THUNK(_ASM_DX) GENERATE_THUNK(_ASM_SI) GENERATE_THUNK(_ASM_DI) GENERATE_THUNK(_ASM_BP) -GENERATE_THUNK(_ASM_SP) #ifdef CONFIG_64BIT GENERATE_THUNK(r8) GENERATE_THUNK(r9) @@ -47,3 +47,58 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 1b377f734e64..7add8ba06887 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -331,12 +331,12 @@ do { \ unsigned long __copy_user_ll(void *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_user_ll); @@ -344,7 +344,7 @@ EXPORT_SYMBOL(__copy_user_ll); unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin_nospec(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && static_cpu_has(X86_FEATURE_XMM2)) n = __copy_user_intel_nocache(to, from, n); @@ -353,7 +353,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5bfe61a5e8e3..012d02624848 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/cpu.h> +#include <linux/debugfs.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> -#include <linux/debugfs.h> /* * TLB flushing, formerly SMP-only @@ -247,6 +248,27 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } else { u16 new_asid; bool need_flush; + u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); + + /* + * Avoid user/user BTB poisoning by flushing the branch + * predictor when switching between processes. This stops + * one process from doing Spectre-v2 attacks on another. + * + * As an optimization, flush indirect branches only when + * switching into processes that disable dumping. This + * protects high value processes like gpg, without having + * too high performance overhead. IBPB is *expensive*! + * + * This will not flush branches when switching into kernel + * threads. It will also not flush if we switch to idle + * thread and back to the same process. It will flush if we + * switch to a different non-dumpable process. + */ + if (tsk && tsk->mm && + tsk->mm->context.ctx_id != last_ctx_id && + get_dumpable(tsk->mm) != SUID_DUMP_USER) + indirect_branch_prediction_barrier(); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -292,6 +314,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } + /* + * Record last user mm's context id, so we can avoid + * flushing branch buffer with IBPB if we switch back + * to the same user. + */ + if (next != &init_mm) + this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } @@ -369,6 +399,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ + this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index a9020f82eea7..58403052514f 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -443,3 +443,7 @@ static struct platform_driver img_ascii_lcd_driver = { .remove = img_ascii_lcd_remove, }; module_platform_driver(img_ascii_lcd_driver); + +MODULE_DESCRIPTION("Imagination Technologies ASCII LCD Display"); +MODULE_AUTHOR("Paul Burton <paul.burton(a)mips.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index d9ab7c75b14f..e0c73ceba2ed 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -147,6 +147,7 @@ static struct fpga_manager *fpga_region_get_manager(struct fpga_region *region) mgr_node = of_parse_phandle(np, "fpga-mgr", 0); if (mgr_node) { mgr = of_fpga_mgr_get(mgr_node); + of_node_put(mgr_node); of_node_put(np); return mgr; } @@ -192,10 +193,13 @@ static int fpga_region_get_bridges(struct fpga_region *region, parent_br = region_np->parent; /* If overlay has a list of bridges, use it. */ - if (of_parse_phandle(overlay, "fpga-bridges", 0)) + br = of_parse_phandle(overlay, "fpga-bridges", 0); + if (br) { + of_node_put(br); np = overlay; - else + } else { np = region_np; + } for (i = 0; ; i++) { br = of_parse_phandle(np, "fpga-bridges", i); @@ -203,12 +207,15 @@ static int fpga_region_get_bridges(struct fpga_region *region, break; /* If parent bridge is in list, skip it. */ - if (br == parent_br) + if (br == parent_br) { + of_node_put(br); continue; + } /* If node is a bridge, get it and add to list */ ret = fpga_bridge_get_to_list(br, region->info, &region->bridge_list); + of_node_put(br); /* If any of the bridges are in use, give up */ if (ret == -EBUSY) { diff --git a/drivers/iio/accel/kxsd9-i2c.c b/drivers/iio/accel/kxsd9-i2c.c index 98fbb628d5bd..38411e1c155b 100644 --- a/drivers/iio/accel/kxsd9-i2c.c +++ b/drivers/iio/accel/kxsd9-i2c.c @@ -63,3 +63,6 @@ static struct i2c_driver kxsd9_i2c_driver = { .id_table = kxsd9_i2c_id, }; module_i2c_driver(kxsd9_i2c_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("KXSD9 accelerometer I2C interface"); diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c index 47d24ae5462f..fe3d7826783c 100644 --- a/drivers/iio/adc/qcom-vadc-common.c +++ b/drivers/iio/adc/qcom-vadc-common.c @@ -5,6 +5,7 @@ #include <linux/math64.h> #include <linux/log2.h> #include <linux/err.h> +#include <linux/module.h> #include "qcom-vadc-common.h" @@ -229,3 +230,6 @@ int qcom_vadc_decimation_from_dt(u32 value) return __ffs64(value / VADC_DECIMATION_MIN); } EXPORT_SYMBOL(qcom_vadc_decimation_from_dt); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Qualcomm ADC common functionality"); diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c index 866aa3ce1ac9..6cf0006d4c8d 100644 --- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c +++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c @@ -436,3 +436,7 @@ int pxa2xx_pinctrl_exit(struct platform_device *pdev) return 0; } EXPORT_SYMBOL_GPL(pxa2xx_pinctrl_exit); + +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik(a)free.fr>"); +MODULE_DESCRIPTION("Marvell PXA2xx pinctrl driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 3a14cccbd7ff..7948acf14601 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -987,6 +987,8 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, } } else { retval = uart_startup(tty, state, 1); + if (retval == 0) + tty_port_set_initialized(port, true); if (retval > 0) retval = 0; } diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 1c65817673db..41615f38bcff 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -10,6 +10,7 @@ #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> @@ -82,8 +83,10 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i { struct fdtable *fdt = rcu_dereference_raw(files->fdt); - if (fd < fdt->max_fds) + if (fd < fdt->max_fds) { + fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); + } return NULL; } diff --git a/include/linux/init.h b/include/linux/init.h index f38b993edacb..943139a563e3 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -5,6 +5,13 @@ #include <linux/compiler.h> #include <linux/types.h> +/* Built-in __init functions needn't be compiled with retpoline */ +#if defined(RETPOLINE) && !defined(MODULE) +#define __noretpoline __attribute__((indirect_branch("keep"))) +#else +#define __noretpoline +#endif + /* These macros are used to mark some functions or * initialized data (doesn't apply to uninitialized data) * as `initialization' functions. The kernel can take this @@ -40,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __inittrace __latent_entropy +#define __init __section(.init.text) __cold __inittrace __latent_entropy __noretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/module.h b/include/linux/module.h index fe5aa3736707..b1cc541f2ddf 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -794,6 +794,15 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ +#ifdef RETPOLINE +extern bool retpoline_module_ok(bool has_retpoline); +#else +static inline bool retpoline_module_ok(bool has_retpoline) +{ + return true; +} +#endif + #ifdef CONFIG_MODULE_SIG static inline bool module_sig_ok(struct module *module) { diff --git a/include/linux/nospec.h b/include/linux/nospec.h new file mode 100644 index 000000000000..b99bced39ac2 --- /dev/null +++ b/include/linux/nospec.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2018 Linus Torvalds. All rights reserved. +// Copyright(c) 2018 Alexei Starovoitov. All rights reserved. +// Copyright(c) 2018 Intel Corporation. All rights reserved. + +#ifndef _LINUX_NOSPEC_H +#define _LINUX_NOSPEC_H + +/** + * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise + * @index: array element index + * @size: number of elements in array + * + * When @index is out of bounds (@index >= @size), the sign bit will be + * set. Extend the sign bit to all bits and invert, giving a result of + * zero for an out of bounds index, or ~0 if within bounds [0, @size). + */ +#ifndef array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + /* + * Warn developers about inappropriate array_index_nospec() usage. + * + * Even if the CPU speculates past the WARN_ONCE branch, the + * sign bit of @index is taken into account when generating the + * mask. + * + * This warning is compiled out when the compiler can infer that + * @index and @size are less than LONG_MAX. + */ + if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, + "array_index_nospec() limited to range of [0, LONG_MAX]\n")) + return 0; + + /* + * Always calculate and emit the mask even if the compiler + * thinks the mask is not needed. The compiler does not take + * into account the value of @index under speculation. + */ + OPTIMIZER_HIDE_VAR(index); + return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1); +} +#endif + +/* + * array_index_nospec - sanitize an array index after a bounds check + * + * For a code sequence like: + * + * if (index < size) { + * index = array_index_nospec(index, size); + * val = array[index]; + * } + * + * ...if the CPU speculates past the bounds check then + * array_index_nospec() will clamp the index within the range of [0, + * size). + */ +#define array_index_nospec(index, size) \ +({ \ + typeof(index) _i = (index); \ + typeof(size) _s = (size); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ + \ + BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ + BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ + \ + _i &= _mask; \ + _i; \ +}) +#endif /* _LINUX_NOSPEC_H */ diff --git a/kernel/module.c b/kernel/module.c index de66ec825992..690c0651c40f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2855,6 +2855,15 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info) } #endif /* CONFIG_LIVEPATCH */ +static void check_modinfo_retpoline(struct module *mod, struct load_info *info) +{ + if (retpoline_module_ok(get_modinfo(info, "retpoline"))) + return; + + pr_warn("%s: loading module not compiled with retpoline compiler.\n", + mod->name); +} + /* Sets info->hdr and info->len. */ static int copy_module_from_user(const void __user *umod, unsigned long len, struct load_info *info) @@ -3021,6 +3030,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK); } + check_modinfo_retpoline(mod, info); + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); pr_warn("%s: module is from the staging directory, the quality " diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d396cb61a280..81bef0676e1d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16,6 +16,7 @@ #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/etherdevice.h> #include <net/net_namespace.h> #include <net/genetlink.h> @@ -2056,20 +2057,22 @@ static const struct nla_policy txq_params_policy[NL80211_TXQ_ATTR_MAX + 1] = { static int parse_txq_params(struct nlattr *tb[], struct ieee80211_txq_params *txq_params) { + u8 ac; + if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] || !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] || !tb[NL80211_TXQ_ATTR_AIFS]) return -EINVAL; - txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); + ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]); txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]); txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]); txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]); txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]); - if (txq_params->ac >= NL80211_NUM_ACS) + if (ac >= NL80211_NUM_ACS) return -EINVAL; - + txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS); return 0; } diff --git a/scripts/faddr2line b/scripts/faddr2line index 39e07d8574dd..7721d5b2b0c0 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -44,10 +44,10 @@ set -o errexit set -o nounset -READELF="${CROSS_COMPILE}readelf" -ADDR2LINE="${CROSS_COMPILE}addr2line" -SIZE="${CROSS_COMPILE}size" -NM="${CROSS_COMPILE}nm" +READELF="${CROSS_COMPILE:-}readelf" +ADDR2LINE="${CROSS_COMPILE:-}addr2line" +SIZE="${CROSS_COMPILE:-}size" +NM="${CROSS_COMPILE:-}nm" command -v awk >/dev/null 2>&1 || die "awk isn't installed" command -v ${READELF} >/dev/null 2>&1 || die "readelf isn't installed" diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 98314b400a95..54deaa1066cf 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -2165,6 +2165,14 @@ static void add_intree_flag(struct buffer *b, int is_intree) buf_printf(b, "\nMODULE_INFO(intree, \"Y\");\n"); } +/* Cannot check for assembler */ +static void add_retpoline(struct buffer *b) +{ + buf_printf(b, "\n#ifdef RETPOLINE\n"); + buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n"); + buf_printf(b, "#endif\n"); +} + static void add_staging_flag(struct buffer *b, const char *name) { static const char *staging_dir = "drivers/staging"; @@ -2506,6 +2514,7 @@ int main(int argc, char **argv) err |= check_modname_len(mod); add_header(&buf, mod); add_intree_flag(&buf, !external_module); + add_retpoline(&buf); add_staging_flag(&buf, mod->name); err |= add_versions(&buf, mod); add_depends(&buf, mod, modules); diff --git a/sound/soc/codecs/pcm512x-spi.c b/sound/soc/codecs/pcm512x-spi.c index 712ed6598c48..ebdf9bd5a64c 100644 --- a/sound/soc/codecs/pcm512x-spi.c +++ b/sound/soc/codecs/pcm512x-spi.c @@ -70,3 +70,7 @@ static struct spi_driver pcm512x_spi_driver = { }; module_spi_driver(pcm512x_spi_driver); + +MODULE_DESCRIPTION("ASoC PCM512x codec driver - SPI"); +MODULE_AUTHOR("Mark Brown <broonie(a)kernel.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f40d46e24bcc..9cd028aa1509 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -543,18 +543,14 @@ static int add_call_destinations(struct objtool_file *file) dest_off = insn->offset + insn->len + insn->immediate; insn->call_dest = find_symbol_by_offset(insn->sec, dest_off); - /* - * FIXME: Thanks to retpolines, it's now considered - * normal for a function to call within itself. So - * disable this warning for now. - */ -#if 0 - if (!insn->call_dest) { - WARN_FUNC("can't find call dest symbol at offset 0x%lx", - insn->sec, insn->offset, dest_off); + + if (!insn->call_dest && !insn->ignore) { + WARN_FUNC("unsupported intra-function call", + insn->sec, insn->offset); + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } -#endif + } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -598,7 +594,7 @@ static int handle_group_alt(struct objtool_file *file, struct instruction *orig_insn, struct instruction **new_insn) { - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump; + struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump = NULL; unsigned long dest_off; last_orig_insn = NULL; @@ -614,28 +610,30 @@ static int handle_group_alt(struct objtool_file *file, last_orig_insn = insn; } - if (!next_insn_same_sec(file, last_orig_insn)) { - WARN("%s: don't know how to handle alternatives at end of section", - special_alt->orig_sec->name); - return -1; - } - - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; + if (next_insn_same_sec(file, last_orig_insn)) { + fake_jump = malloc(sizeof(*fake_jump)); + if (!fake_jump) { + WARN("malloc failed"); + return -1; + } + memset(fake_jump, 0, sizeof(*fake_jump)); + INIT_LIST_HEAD(&fake_jump->alts); + clear_insn_state(&fake_jump->state); + + fake_jump->sec = special_alt->new_sec; + fake_jump->offset = -1; + fake_jump->type = INSN_JUMP_UNCONDITIONAL; + fake_jump->jump_dest = list_next_entry(last_orig_insn, list); + fake_jump->ignore = true; } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - clear_insn_state(&fake_jump->state); - - fake_jump->sec = special_alt->new_sec; - fake_jump->offset = -1; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - fake_jump->ignore = true; if (!special_alt->new_len) { + if (!fake_jump) { + WARN("%s: empty alternative at end of section", + special_alt->orig_sec->name); + return -1; + } + *new_insn = fake_jump; return 0; } @@ -648,6 +646,8 @@ static int handle_group_alt(struct objtool_file *file, last_new_insn = insn; + insn->ignore = orig_insn->ignore_alts; + if (insn->type != INSN_JUMP_CONDITIONAL && insn->type != INSN_JUMP_UNCONDITIONAL) continue; @@ -656,8 +656,14 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = insn->offset + insn->len + insn->immediate; - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { + if (!fake_jump) { + WARN("%s: alternative jump to end of section", + special_alt->orig_sec->name); + return -1; + } insn->jump_dest = fake_jump; + } if (!insn->jump_dest) { WARN_FUNC("can't find alternative jump destination", @@ -672,7 +678,8 @@ static int handle_group_alt(struct objtool_file *file, return -1; } - list_add(&fake_jump->list, &last_new_insn->list); + if (fake_jump) + list_add(&fake_jump->list, &last_new_insn->list); return 0; } @@ -729,10 +736,6 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } - /* Ignore retpoline alternatives. */ - if (orig_insn->ignore_alts) - continue; - new_insn = NULL; if (!special_alt->group || special_alt->new_len) { new_insn = find_insn(file, special_alt->new_sec, @@ -1089,11 +1092,11 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - ret = add_call_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_call_destinations(file); if (ret) return ret; @@ -1720,10 +1723,12 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, insn->visited = true; - list_for_each_entry(alt, &insn->alts, list) { - ret = validate_branch(file, alt->insn, state); - if (ret) - return 1; + if (!insn->ignore_alts) { + list_for_each_entry(alt, &insn->alts, list) { + ret = validate_branch(file, alt->insn, state); + if (ret) + return 1; + } } switch (insn->type) { diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e61fe703197b..18384d9be4e1 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -98,6 +98,11 @@ static int create_orc_entry(struct section *u_sec, struct section *ip_relasec, struct orc_entry *orc; struct rela *rela; + if (!insn_sec->sym) { + WARN("missing symbol for section %s", insn_sec->name); + return -1; + } + /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc));

7 years, 4 months

1
0
0 0

Re: [Linux-stable-mirror] Linux 3.18.94

by Greg KH

diff --git a/Makefile b/Makefile index 172d9e596d25..03a5b7e2076c 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 18 -SUBLEVEL = 93 +SUBLEVEL = 94 EXTRAVERSION = NAME = Diseased Newt diff --git a/arch/um/Makefile b/arch/um/Makefile index e4b1a9639c4d..d467ae58c934 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -68,9 +68,10 @@ KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ KBUILD_AFLAGS += $(ARCH_INCLUDE) -USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -D__KERNEL__,,\ - $(patsubst -I%,,$(KBUILD_CFLAGS)))) $(ARCH_INCLUDE) $(MODE_INCLUDE) \ - $(filter -I%,$(CFLAGS)) -D_FILE_OFFSET_BITS=64 -idirafter include +USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ + $(ARCH_INCLUDE) $(MODE_INCLUDE) $(filter -I%,$(CFLAGS)) \ + -D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \ + -idirafter $(obj)/include -D__KERNEL__ -D__UM_HOST__ #This will adjust *FLAGS accordingly to the platform. include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS) @@ -116,7 +117,7 @@ archheaders: archprepare: include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib +LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie) CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ $(call cc-option, -fno-stack-protector,) \ diff --git a/arch/um/drivers/mconsole.h b/arch/um/drivers/mconsole.h index 8b22535c62ce..44af7379ea19 100644 --- a/arch/um/drivers/mconsole.h +++ b/arch/um/drivers/mconsole.h @@ -7,7 +7,7 @@ #ifndef __MCONSOLE_H__ #define __MCONSOLE_H__ -#ifndef __KERNEL__ +#ifdef __UM_HOST__ #include <stdint.h> #define u32 uint32_t #endif diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h index b3906f860a87..233e2593eee0 100644 --- a/arch/um/include/shared/init.h +++ b/arch/um/include/shared/init.h @@ -40,28 +40,8 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -#ifndef __KERNEL__ -#ifndef __section -# define __section(S) __attribute__ ((__section__(#S))) -#endif - -#if __GNUC__ == 3 - -#if __GNUC_MINOR__ >= 3 -# define __used __attribute__((__used__)) -#else -# define __used __attribute__((__unused__)) -#endif - -#else -#if __GNUC__ == 4 -# define __used __attribute__((__used__)) -#endif -#endif - -#else #include <linux/compiler.h> -#endif + /* These are for everybody (although not all archs will actually discard it in modules) */ #define __init __section(.init.text) @@ -131,7 +111,7 @@ extern struct uml_param __uml_setup_start, __uml_setup_end; #define __uml_postsetup_call __used __section(.uml.postsetup.init) #define __uml_exit_call __used __section(.uml.exitcall.exit) -#ifndef __KERNEL__ +#ifdef __UM_HOST__ #define __define_initcall(level,fn) \ static initcall_t __initcall_##fn __used \ diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index cef068563336..4cff19f6207a 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -17,7 +17,7 @@ #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) /* This is to get size_t */ -#ifdef __KERNEL__ +#ifndef __UM_HOST__ #include <linux/types.h> #else #include <stddef.h> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 306d152336cd..bcae7051aba2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -849,7 +849,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, static inline int emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) { - return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); + return x86_emulate_instruction(vcpu, 0, + emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); } void kvm_enable_efer_bits(u64); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 852572c971c4..08751c554d35 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4385,6 +4385,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) bool op_prefix = false; bool has_seg_override = false; struct opcode opcode; + u16 dummy; + struct desc_struct desc; ctxt->memop.type = OP_NONE; ctxt->memopp = NULL; @@ -4403,6 +4405,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) switch (mode) { case X86EMUL_MODE_REAL: case X86EMUL_MODE_VM86: + def_op_bytes = def_ad_bytes = 2; + ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS); + if (desc.d) + def_op_bytes = def_ad_bytes = 4; + break; case X86EMUL_MODE_PROT16: def_op_bytes = def_ad_bytes = 2; break; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c1fd6d3d4394..9b02ba40fed0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4569,7 +4569,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_writel(GUEST_RFLAGS, 0x02); + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -5707,7 +5707,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) return 1; - err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); + err = emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0dcbe370374f..80a83113a1ce 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5109,7 +5109,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; - r = EMULATE_FAIL; + r = EMULATE_USER_EXIT; } kvm_queue_exception(vcpu, UD_VECTOR); diff --git a/arch/x86/um/shared/sysdep/tls.h b/arch/x86/um/shared/sysdep/tls.h index 27cce00c6b30..a682db13df23 100644 --- a/arch/x86/um/shared/sysdep/tls.h +++ b/arch/x86/um/shared/sysdep/tls.h @@ -1,7 +1,7 @@ #ifndef _SYSDEP_TLS_H #define _SYSDEP_TLS_H -# ifndef __KERNEL__ +#ifdef __UM_HOST__ /* Change name to avoid conflicts with the original one from <asm/ldt.h>, which * may be named user_desc (but in 2.4 and in header matching its API was named @@ -22,11 +22,11 @@ typedef struct um_dup_user_desc { #endif } user_desc_t; -# else /* __KERNEL__ */ +#else /* __UM_HOST__ */ typedef struct user_desc user_desc_t; -# endif /* __KERNEL__ */ +#endif /* __UM_HOST__ */ extern int os_set_thread_area(user_desc_t *info, int pid); extern int os_get_thread_area(user_desc_t *info, int pid); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6cb1beb47c25..94385b969f67 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1512,9 +1512,8 @@ out: return err; } -static void lo_release(struct gendisk *disk, fmode_t mode) +static void __lo_release(struct loop_device *lo) { - struct loop_device *lo = disk->private_data; int err; mutex_lock(&lo->lo_ctl_mutex); @@ -1542,6 +1541,13 @@ out: mutex_unlock(&lo->lo_ctl_mutex); } +static void lo_release(struct gendisk *disk, fmode_t mode) +{ + mutex_lock(&loop_index_mutex); + __lo_release(disk->private_data); + mutex_unlock(&loop_index_mutex); +} + static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, .open = lo_open, diff --git a/drivers/gpio/gpio-iop.c b/drivers/gpio/gpio-iop.c index 0a5e9d3f308c..2978aa5ae282 100644 --- a/drivers/gpio/gpio-iop.c +++ b/drivers/gpio/gpio-iop.c @@ -130,3 +130,7 @@ static int __init iop3xx_gpio_init(void) return platform_driver_register(&iop3xx_gpio_driver); } arch_initcall(iop3xx_gpio_init); + +MODULE_DESCRIPTION("GPIO handling for Intel IOP3xx processors"); +MODULE_AUTHOR("Lennert Buytenhek <buytenh(a)wantstofly.org>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 291d11fe93e7..6f3fabb5350f 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -20,6 +20,7 @@ */ #include <linux/kernel.h> +#include <linux/math64.h> #include <linux/module.h> #include <linux/init.h> #include <linux/err.h> @@ -443,8 +444,8 @@ static long pmbus_reg2data_linear(struct pmbus_data *data, static long pmbus_reg2data_direct(struct pmbus_data *data, struct pmbus_sensor *sensor) { - long val = (s16) sensor->data; - long m, b, R; + s64 b, val = (s16)sensor->data; + s32 m, R; m = data->info->m[sensor->class]; b = data->info->b[sensor->class]; @@ -472,11 +473,12 @@ static long pmbus_reg2data_direct(struct pmbus_data *data, R--; } while (R < 0) { - val = DIV_ROUND_CLOSEST(val, 10); + val = div_s64(val + 5LL, 10L); /* round closest */ R++; } - return (val - b) / m; + val = div_s64(val - b, m); + return clamp_val(val, LONG_MIN, LONG_MAX); } /* @@ -588,7 +590,8 @@ static u16 pmbus_data2reg_linear(struct pmbus_data *data, static u16 pmbus_data2reg_direct(struct pmbus_data *data, struct pmbus_sensor *sensor, long val) { - long m, b, R; + s64 b, val64 = val; + s32 m, R; m = data->info->m[sensor->class]; b = data->info->b[sensor->class]; @@ -605,18 +608,18 @@ static u16 pmbus_data2reg_direct(struct pmbus_data *data, R -= 3; /* Adjust R and b for data in milli-units */ b *= 1000; } - val = val * m + b; + val64 = val64 * m + b; while (R > 0) { - val *= 10; + val64 *= 10; R--; } while (R < 0) { - val = DIV_ROUND_CLOSEST(val, 10); + val64 = div_s64(val64 + 5LL, 10L); /* round closest */ R++; } - return val; + return (u16)clamp_val(val64, S16_MIN, S16_MAX); } static u16 pmbus_data2reg_vid(struct pmbus_data *data, diff --git a/drivers/input/input.c b/drivers/input/input.c index 0f175f55782b..34aae7e5498a 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -668,6 +668,7 @@ EXPORT_SYMBOL(input_close_device); */ static void input_dev_release_keys(struct input_dev *dev) { + bool need_sync = false; int code; if (is_event_supported(EV_KEY, dev->evbit, EV_MAX)) { @@ -675,9 +676,11 @@ static void input_dev_release_keys(struct input_dev *dev) if (is_event_supported(code, dev->keybit, KEY_MAX) && __test_and_clear_bit(code, dev->key)) { input_pass_event(dev, EV_KEY, code, 0); + need_sync = true; } } - input_pass_event(dev, EV_SYN, SYN_REPORT, 1); + if (need_sync) + input_pass_event(dev, EV_SYN, SYN_REPORT, 1); } } diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 43829d9493f7..e53ce5e2a28a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -808,7 +808,10 @@ int bch_btree_cache_alloc(struct cache_set *c) c->shrink.scan_objects = bch_mca_scan; c->shrink.seeks = 4; c->shrink.batch = c->btree_pages * 2; - register_shrinker(&c->shrink); + + if (register_shrinker(&c->shrink)) + pr_warn("bcache: %s: could not register shrinker", + __func__); return 0; } diff --git a/drivers/media/usb/usbtv/usbtv-core.c b/drivers/media/usb/usbtv/usbtv-core.c index 29428bef272c..3bbc77aa6a33 100644 --- a/drivers/media/usb/usbtv/usbtv-core.c +++ b/drivers/media/usb/usbtv/usbtv-core.c @@ -127,6 +127,7 @@ static void usbtv_disconnect(struct usb_interface *intf) static struct usb_device_id usbtv_id_table[] = { { USB_DEVICE(0x1b71, 0x3002) }, + { USB_DEVICE(0x1f71, 0x3301) }, {} }; MODULE_DEVICE_TABLE(usb, usbtv_id_table); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 3b3911e511ac..1ffad88e8a29 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3172,7 +3172,7 @@ static int __igb_close(struct net_device *netdev, bool suspending) static int igb_close(struct net_device *netdev) { - if (netif_device_present(netdev)) + if (netif_device_present(netdev) || netdev->dismantle) return __igb_close(netdev, false); return 0; } diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig index 7b90a5eba099..9d6c252c1911 100644 --- a/drivers/net/ethernet/xilinx/Kconfig +++ b/drivers/net/ethernet/xilinx/Kconfig @@ -36,6 +36,7 @@ config XILINX_AXI_EMAC config XILINX_LL_TEMAC tristate "Xilinx LL TEMAC (LocalLink Tri-mode Ethernet MAC) driver" depends on (PPC || MICROBLAZE) + depends on !64BIT || BROKEN select PHYLIB ---help--- This driver supports the Xilinx 10/100/1000 LocalLink TEMAC diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 8f45be1592ca..e76f46edee08 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -85,6 +85,8 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) +static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); + struct netfront_stats { u64 rx_packets; u64 tx_packets; @@ -2080,10 +2082,12 @@ static void netback_changed(struct xenbus_device *dev, break; case XenbusStateClosed: + wake_up_all(&module_unload_q); if (dev->state == XenbusStateClosed) break; /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: + wake_up_all(&module_unload_q); xenbus_frontend_closed(dev); break; } @@ -2305,6 +2309,20 @@ static int xennet_remove(struct xenbus_device *dev) dev_dbg(&dev->dev, "%s\n", dev->nodename); + if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { + xenbus_switch_state(dev, XenbusStateClosing); + wait_event(module_unload_q, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosing); + + xenbus_switch_state(dev, XenbusStateClosed); + wait_event(module_unload_q, + xenbus_read_driver_state(dev->otherend) == + XenbusStateClosed || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown); + } + xennet_disconnect_backend(info); xennet_sysfs_delif(info->netdev); diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 605ca60e8a10..64ee59685aac 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4287,12 +4287,15 @@ static int ufshcd_config_vreg(struct device *dev, struct ufs_vreg *vreg, bool on) { int ret = 0; - struct regulator *reg = vreg->reg; - const char *name = vreg->name; + struct regulator *reg; + const char *name; int min_uV, uA_load; BUG_ON(!vreg); + reg = vreg->reg; + name = vreg->name; + if (regulator_count_voltages(reg) > 0) { min_uV = on ? vreg->min_uV : 0; ret = regulator_set_voltage(reg, min_uV, vreg->max_uV); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index bf0effb86137..4c5e43f6f7f6 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1220,12 +1220,23 @@ static int spi_imx_remove(struct platform_device *pdev) { struct spi_master *master = platform_get_drvdata(pdev); struct spi_imx_data *spi_imx = spi_master_get_devdata(master); + int ret; spi_bitbang_stop(&spi_imx->bitbang); + ret = clk_enable(spi_imx->clk_per); + if (ret) + return ret; + + ret = clk_enable(spi_imx->clk_ipg); + if (ret) { + clk_disable(spi_imx->clk_per); + return ret; + } + writel(0, spi_imx->base + MXC_CSPICTRL); - clk_unprepare(spi_imx->clk_ipg); - clk_unprepare(spi_imx->clk_per); + clk_disable_unprepare(spi_imx->clk_ipg); + clk_disable_unprepare(spi_imx->clk_per); spi_imx_sdma_exit(spi_imx); spi_master_put(master); diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index d598fec4abbf..0bfb4fe8a86e 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -1396,19 +1396,13 @@ static int rtw_wx_get_essid(struct net_device *dev, if ((check_fwstate(pmlmepriv, _FW_LINKED)) || (check_fwstate(pmlmepriv, WIFI_ADHOC_MASTER_STATE))) { len = pcur_bss->Ssid.SsidLength; - - wrqu->essid.length = len; - memcpy(extra, pcur_bss->Ssid.Ssid, len); - - wrqu->essid.flags = 1; } else { - ret = -1; - goto exit; + len = 0; + *extra = 0; } - -exit: - + wrqu->essid.length = len; + wrqu->essid.flags = 1; return ret; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index a5e94b8fa2dc..e01d39509172 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -381,7 +381,7 @@ static int acm_submit_read_urb(struct acm *acm, int index, gfp_t mem_flags) res = usb_submit_urb(acm->read_urbs[index], mem_flags); if (res) { - if (res != -EPERM) { + if (res != -EPERM && res != -ENODEV) { dev_err(&acm->data->dev, "%s - usb_submit_urb failed: %d\n", __func__, res); @@ -1712,6 +1712,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0ace, 0x1611), /* ZyDAS 56K USB MODEM - new version */ .driver_info = SINGLE_RX_URB, /* firmware bug */ }, + { USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */ + .driver_info = SINGLE_RX_URB, + }, { USB_DEVICE(0x22b8, 0x7000), /* Motorola Q Phone */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index f24adf48b0cc..0056ca7e588c 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -103,7 +103,6 @@ int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep) { - struct usb_composite_dev *cdev = get_gadget_data(g); struct usb_endpoint_descriptor *chosen_desc = NULL; struct usb_descriptor_header **speed_desc = NULL; @@ -170,8 +169,12 @@ ep_found: _ep->maxburst = comp_desc->bMaxBurst + 1; break; default: - if (comp_desc->bMaxBurst != 0) + if (comp_desc->bMaxBurst != 0) { + struct usb_composite_dev *cdev; + + cdev = get_gadget_data(g); ERROR(cdev, "ep0 bMaxBurst must be 0\n"); + } _ep->maxburst = 1; break; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 2c46089ac423..88aa287f10ea 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3438,7 +3438,8 @@ static void ffs_closed(struct ffs_data *ffs) ci = opts->func_inst.group.cg_item.ci_parent->ci_parent; ffs_dev_unlock(); - unregister_gadget_item(ci); + if (test_bit(FFS_FL_BOUND, &ffs->flags)) + unregister_gadget_item(ci); return; done: ffs_dev_unlock(); diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index a69f7cd9d0bf..1594e811ab00 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -62,6 +62,7 @@ config USB_SERIAL_SIMPLE - Fundamental Software dongle. - HP4x calculators - a number of Motorola phones + - Motorola Tetra devices - Novatel Wireless GPS receivers - Siemens USB/MPI adapter. - ViVOtech ViVOpay USB device. diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c index f35befe3bccf..eef2cbb001ea 100644 --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -2219,7 +2219,6 @@ static int write_cmd_usb(struct edgeport_port *edge_port, /* something went wrong */ dev_err(dev, "%s - usb_submit_urb(write command) failed, status = %d\n", __func__, status); - usb_kill_urb(urb); usb_free_urb(urb); atomic_dec(&CmdUrbs); return status; diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 534c308c6b33..387dde4abb57 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -39,6 +39,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_RSAQ2) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_DCU11) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_RSAQ3) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_CHILITAG) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_PHAROS) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ALDIGA) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MMX) }, diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index e3b7af8adfb7..6184bd4d3777 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -17,6 +17,7 @@ #define PL2303_PRODUCT_ID_DCU11 0x1234 #define PL2303_PRODUCT_ID_PHAROS 0xaaa0 #define PL2303_PRODUCT_ID_RSAQ3 0xaaa2 +#define PL2303_PRODUCT_ID_CHILITAG 0xaaa8 #define PL2303_PRODUCT_ID_ALDIGA 0x0611 #define PL2303_PRODUCT_ID_MMX 0x0612 #define PL2303_PRODUCT_ID_GPRS 0x0609 diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index 40de275cddf4..35f6b121f9d8 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -72,6 +72,11 @@ DEVICE(vivopay, VIVOPAY_IDS); { USB_DEVICE(0x22b8, 0x2c64) } /* Motorola V950 phone */ DEVICE(moto_modem, MOTO_IDS); +/* Motorola Tetra driver */ +#define MOTOROLA_TETRA_IDS() \ + { USB_DEVICE(0x0cad, 0x9011) } /* Motorola Solutions TETRA PEI */ +DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS); + /* Novatel Wireless GPS driver */ #define NOVATEL_IDS() \ { USB_DEVICE(0x09d7, 0x0100) } /* NovAtel FlexPack GPS */ @@ -101,6 +106,7 @@ static struct usb_serial_driver * const serial_drivers[] = { &flashloader_device, &vivopay_device, &moto_modem_device, + &motorola_tetra_device, &novatel_gps_device, &hp4x_device, &suunto_device, @@ -115,6 +121,7 @@ static const struct usb_device_id id_table[] = { FLASHLOADER_IDS(), VIVOPAY_IDS(), MOTO_IDS(), + MOTOROLA_TETRA_IDS(), NOVATEL_IDS(), HP4X_IDS(), SUUNTO_IDS(), diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 017278ec4e03..7d535f1ddecc 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -1067,20 +1067,19 @@ static int uas_post_reset(struct usb_interface *intf) return 0; err = uas_configure_endpoints(devinfo); - if (err) { + if (err && err != ENODEV) shost_printk(KERN_ERR, shost, "%s: alloc streams error %d after reset", __func__, err); - return 1; - } + /* we must unblock the host in every case lest we deadlock */ spin_lock_irqsave(shost->host_lock, flags); scsi_report_bus_reset(shost, 0); spin_unlock_irqrestore(shost->host_lock, flags); scsi_unblock_requests(shost); - return 0; + return err ? 1 : 0; } static int uas_suspend(struct usb_interface *intf, pm_message_t message) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d59ce5a665d9..34b718c6ce53 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -62,12 +62,16 @@ static const stateid_t zero_stateid = { static const stateid_t currentstateid = { .si_generation = 1, }; +static const stateid_t close_stateid = { + .si_generation = 0xffffffffU, +}; static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t))) #define CURRENT_STATEID(stateid) (!memcmp((stateid), &currentstateid, sizeof(stateid_t))) +#define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t))) /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); @@ -4411,7 +4415,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) struct nfs4_stid *s; __be32 status = nfserr_bad_stateid; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || + CLOSE_STATEID(stateid)) return status; /* Client debugging aid. */ if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) { @@ -4469,7 +4474,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, else if (typemask & NFS4_DELEG_STID) typemask |= NFS4_REVOKED_DELEG_STID; - if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || + CLOSE_STATEID(stateid)) return nfserr_bad_stateid; status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { @@ -4901,6 +4907,11 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd4_close_open_stateid(stp); + /* See RFC5661 sectionm 18.2.4 */ + if (stp->st_stid.sc_client->cl_minorversion) + memcpy(&close->cl_stateid, &close_stateid, + sizeof(close->cl_stateid)); + /* put reference from nfs4_preprocess_seqid_op */ nfs4_put_stid(&stp->st_stid); out: diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 18aaccb290c2..a9b448e8f92d 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2730,7 +2730,8 @@ static int __init dquot_init(void) printk("Dquot-cache hash table entries: %ld (order %ld, %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - register_shrinker(&dqcache_shrinker); + if (register_shrinker(&dqcache_shrinker)) + panic("Cannot register dquot shrinker"); return 0; } diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 214e63b84e5c..4efc60236cdb 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -763,7 +763,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath; u8 ttl, flags, hopcount; const u8 *orig_addr; - u32 orig_sn, metric, metric_txsta, interval; + u32 orig_sn, new_metric, orig_metric, last_hop_metric, interval; bool root_is_gate; ttl = rann->rann_ttl; @@ -774,7 +774,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, interval = le32_to_cpu(rann->rann_interval); hopcount = rann->rann_hopcount; hopcount++; - metric = le32_to_cpu(rann->rann_metric); + orig_metric = le32_to_cpu(rann->rann_metric); /* Ignore our own RANNs */ if (ether_addr_equal(orig_addr, sdata->vif.addr)) @@ -791,7 +791,10 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, return; } - metric_txsta = airtime_link_metric_get(local, sta); + last_hop_metric = airtime_link_metric_get(local, sta); + new_metric = orig_metric + last_hop_metric; + if (new_metric < orig_metric) + new_metric = MAX_METRIC; mpath = mesh_path_lookup(sdata, orig_addr); if (!mpath) { @@ -804,7 +807,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } if (!(SN_LT(mpath->sn, orig_sn)) && - !(mpath->sn == orig_sn && metric < mpath->rann_metric)) { + !(mpath->sn == orig_sn && new_metric < mpath->rann_metric)) { rcu_read_unlock(); return; } @@ -822,7 +825,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, } mpath->sn = orig_sn; - mpath->rann_metric = metric + metric_txsta; + mpath->rann_metric = new_metric; mpath->is_root = true; /* Recording RANNs sender address to send individually * addressed PREQs destined for root mesh STA */ @@ -842,7 +845,7 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata, mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr, orig_sn, 0, NULL, 0, broadcast_addr, hopcount, ttl, interval, - metric + metric_txsta, 0, sdata); + new_metric, 0, sdata); } rcu_read_unlock(); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index be04b056c1bd..8223fe463fa3 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3969,6 +3969,8 @@ static int sock_has_perm(struct task_struct *task, struct sock *sk, u32 perms) struct lsm_network_audit net = {0,}; u32 tsid = task_sid(task); + if (!sksec) + return -EFAULT; if (sksec->sid == SECINITSID_KERNEL) return 0; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 0a52e377a617..83bf65ae8251 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -236,6 +236,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) rwlock_init(&client->ports_lock); mutex_init(&client->ports_mutex); INIT_LIST_HEAD(&client->ports_list_head); + mutex_init(&client->ioctl_mutex); /* find free slot in the client table */ spin_lock_irqsave(&clients_lock, flags); @@ -2200,6 +2201,7 @@ static int snd_seq_do_ioctl(struct snd_seq_client *client, unsigned int cmd, void __user *arg) { struct seq_ioctl_table *p; + int ret; switch (cmd) { case SNDRV_SEQ_IOCTL_PVERSION: @@ -2213,8 +2215,12 @@ static int snd_seq_do_ioctl(struct snd_seq_client *client, unsigned int cmd, if (! arg) return -EFAULT; for (p = ioctl_tables; p->cmd; p++) { - if (p->cmd == cmd) - return p->func(client, arg); + if (p->cmd == cmd) { + mutex_lock(&client->ioctl_mutex); + ret = p->func(client, arg); + mutex_unlock(&client->ioctl_mutex); + return ret; + } } pr_debug("ALSA: seq unknown ioctl() 0x%x (type='%c', number=0x%02x)\n", cmd, _IOC_TYPE(cmd), _IOC_NR(cmd)); diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index 20f0a725ec7d..91f8f165bfdc 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -59,6 +59,7 @@ struct snd_seq_client { struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; + struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ /* output pool */ diff --git a/sound/soc/codecs/pcm512x-spi.c b/sound/soc/codecs/pcm512x-spi.c index f297058c0038..3ace683f0aec 100644 --- a/sound/soc/codecs/pcm512x-spi.c +++ b/sound/soc/codecs/pcm512x-spi.c @@ -67,3 +67,7 @@ static struct spi_driver pcm512x_spi_driver = { }; module_spi_driver(pcm512x_spi_driver); + +MODULE_DESCRIPTION("ASoC PCM512x codec driver - SPI"); +MODULE_AUTHOR("Mark Brown <broonie(a)kernel.org>"); +MODULE_LICENSE("GPL v2"); diff --git a/tools/usb/usbip/src/usbip_bind.c b/tools/usb/usbip/src/usbip_bind.c index fa46141ae68b..e121cfb1746a 100644 --- a/tools/usb/usbip/src/usbip_bind.c +++ b/tools/usb/usbip/src/usbip_bind.c @@ -144,6 +144,7 @@ static int bind_device(char *busid) int rc; struct udev *udev; struct udev_device *dev; + const char *devpath; /* Check whether the device with this bus ID exists. */ udev = udev_new(); @@ -152,8 +153,16 @@ static int bind_device(char *busid) err("device with the specified bus ID does not exist"); return -1; } + devpath = udev_device_get_devpath(dev); udev_unref(udev); + /* If the device is already attached to vhci_hcd - bail out */ + if (strstr(devpath, USBIP_VHCI_DRV_NAME)) { + err("bind loop detected: device: %s is attached to %s\n", + devpath, USBIP_VHCI_DRV_NAME); + return -1; + } + rc = unbind_other(busid); if (rc == UNBIND_ST_FAILED) { err("could not unbind driver from device on busid %s", busid); diff --git a/tools/usb/usbip/src/usbip_list.c b/tools/usb/usbip/src/usbip_list.c index d5ce34a410e7..ac6081c3db82 100644 --- a/tools/usb/usbip/src/usbip_list.c +++ b/tools/usb/usbip/src/usbip_list.c @@ -180,6 +180,7 @@ static int list_devices(bool parsable) const char *busid; char product_name[128]; int ret = -1; + const char *devpath; /* Create libudev context. */ udev = udev_new(); @@ -202,6 +203,14 @@ static int list_devices(bool parsable) path = udev_list_entry_get_name(dev_list_entry); dev = udev_device_new_from_syspath(udev, path); + /* Ignore devices attached to vhci_hcd */ + devpath = udev_device_get_devpath(dev); + if (strstr(devpath, USBIP_VHCI_DRV_NAME)) { + dbg("Skip the device %s already attached to %s\n", + devpath, USBIP_VHCI_DRV_NAME); + continue; + } + /* Get device information. */ idVendor = udev_device_get_sysattr_value(dev, "idVendor"); idProduct = udev_device_get_sysattr_value(dev, "idProduct");

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] platform/x86: dell-laptop: Allocate buffer on heap rather than globally

by Mario.Limonciello＠dell.com

commit 9862b43624 upstream There has been a race condition identified with initialization of the dell-laptop driver due to changes in 4.15. This commit has been shown to resolve the race condition. I'd like to see this brought back to 4.15 stable. It doesn't apply to anything earlier. Thanks,

7 years, 4 months

2
2
0 0

[Linux-stable-mirror] [PATCH] Revert "usb: musb: host: don't start next rx urb if current one failed"

by Bin Liu

This reverts commit dbac5d07d13e330e6706813c9fde477140fb5d80. commit dbac5d07d13e ("usb: musb: host: don't start next rx urb if current one failed") along with commit b5801212229f ("usb: musb: host: clear rxcsr error bit if set") try to solve the issue described in [1], but the latter alone is sufficient, and the former causes the issue as in [2], so now revert it. [1] https://marc.info/?l=linux-usb&m=146173995117456&w=2 [2] https://marc.info/?l=linux-usb&m=151689238420622&w=2 Signed-off-by: Bin Liu <b-liu(a)ti.com> --- drivers/usb/musb/musb_host.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 394b4ac86161..45ed32c2cba9 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -391,13 +391,7 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, } } - /* - * The pipe must be broken if current urb->status is set, so don't - * start next urb. - * TODO: to minimize the risk of regression, only check urb->status - * for RX, until we have a test case to understand the behavior of TX. - */ - if ((!status || !is_in) && qh && qh->is_ready) { + if (qh != NULL && qh->is_ready) { musb_dbg(musb, "... next ep%d %cX urb %p", hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh)); musb_start_urb(musb, is_in, qh); -- 1.9.1

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [to-be-updated] fontswap-thp-fix.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm: fontswap: thp fix has been removed from the -mm tree. Its filename was fontswap-thp-fix.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm: fontswap: thp fix Link: http://lkml.kernel.org/r/87d11j4pdy.fsf@yhuang-dev.intel.com Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Reported-by: Sergey Senozhatsky <sergey.senozhatsky.work(a)gmail.com> Tested-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_io.c | 2 +- mm/vmscan.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 4 deletions(-) diff -puN mm/page_io.c~fontswap-thp-fix mm/page_io.c --- a/mm/page_io.c~fontswap-thp-fix +++ a/mm/page_io.c @@ -250,7 +250,7 @@ int swap_writepage(struct page *page, st unlock_page(page); goto out; } - if (frontswap_store(page) == 0) { + if (!PageTransHuge(page) && frontswap_store(page) == 0) { set_page_writeback(page); unlock_page(page); end_page_writeback(page); diff -puN mm/vmscan.c~fontswap-thp-fix mm/vmscan.c --- a/mm/vmscan.c~fontswap-thp-fix +++ a/mm/vmscan.c @@ -55,6 +55,7 @@ #include <linux/swapops.h> #include <linux/balloon_compaction.h> +#include <linux/frontswap.h> #include "internal.h" @@ -1121,13 +1122,22 @@ static unsigned long shrink_page_list(st if (!can_split_huge_page(page, NULL)) goto activate_locked; /* + * Split THP if frontswap enabled, + * because it cannot process THP + */ + if (frontswap_enabled()) { + if (split_huge_page_to_list( + page, page_list)) + goto activate_locked; + } + /* * Split pages without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ - if (!compound_mapcount(page) && - split_huge_page_to_list(page, - page_list)) + else if (!compound_mapcount(page) && + split_huge_page_to_list(page, + page_list)) goto activate_locked; } if (!add_to_swap(page)) { _ Patches currently in -mm which might be from huang.ying.caritas(a)gmail.com are mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] + mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch added to -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: mm, swap, frontswap: Fix THP swap if frontswap enabled has been added to the -mm tree. Its filename is mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-swap-frontswap-fix-thp-swap-if-… and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-swap-frontswap-fix-thp-swap-if-… Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Huang Ying <huang.ying.caritas(a)gmail.com> Subject: mm, swap, frontswap: Fix THP swap if frontswap enabled It was reported by Sergey Senozhatsky that if THP (Transparent Huge Page) and frontswap (via zswap) are both enabled, when memory goes low so that swap is triggered, segfault and memory corruption will occur in random user space applications as follow, kernel: urxvt[338]: segfault at 20 ip 00007fc08889ae0d sp 00007ffc73a7fc40 error 6 in libc-2.26.so[7fc08881a000+1ae000] #0 0x00007fc08889ae0d _int_malloc (libc.so.6) #1 0x00007fc08889c2f3 malloc (libc.so.6) #2 0x0000560e6004bff7 _Z14rxvt_wcstoutf8PKwi (urxvt) #3 0x0000560e6005e75c n/a (urxvt) #4 0x0000560e6007d9f1 _ZN16rxvt_perl_interp6invokeEP9rxvt_term9hook_typez (urxvt) #5 0x0000560e6003d988 _ZN9rxvt_term9cmd_parseEv (urxvt) #6 0x0000560e60042804 _ZN9rxvt_term6pty_cbERN2ev2ioEi (urxvt) #7 0x0000560e6005c10f _Z17ev_invoke_pendingv (urxvt) #8 0x0000560e6005cb55 ev_run (urxvt) #9 0x0000560e6003b9b9 main (urxvt) #10 0x00007fc08883af4a __libc_start_main (libc.so.6) #11 0x0000560e6003f9da _start (urxvt) After bisection, it was found the first bad commit is bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out"). The root cause is as follows: When the pages are written to swap device during swapping out in swap_writepage(), zswap (fontswap) is tried to compress the pages instead to improve the performance. But zswap (frontswap) will treat THP as normal page, so only the head page is saved. After swapping in, tail pages will not be restored to its original contents, so cause the memory corruption in the applications. This is fixed via splitting THP before writing the page to swap device if frontswap is enabled. To deal with the situation where frontswap is enabled at runtime, whether the page is THP is checked before using frontswap during swapping out too. Link: http://lkml.kernel.org/r/20180207070035.30302-1-ying.huang@intel.com Fixes: bd4c82c22c367e068 ("mm, THP, swap: delay splitting THP after swapped out") Signed-off-by: "Huang, Ying" <ying.huang(a)intel.com> Reported-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Tested-by: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Cc: Dan Streetman <ddstreet(a)ieee.org> Cc: Seth Jennings <sjenning(a)redhat.com> Cc: Minchan Kim <minchan(a)kernel.org> Cc: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Cc: Shaohua Li <shli(a)kernel.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Mel Gorman <mgorman(a)techsingularity.net> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: <stable(a)vger.kernel.org> [4.14+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_io.c | 2 +- mm/swapfile.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff -puN mm/page_io.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled mm/page_io.c --- a/mm/page_io.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled +++ a/mm/page_io.c @@ -250,7 +250,7 @@ int swap_writepage(struct page *page, st unlock_page(page); goto out; } - if (frontswap_store(page) == 0) { + if (!PageTransHuge(page) && frontswap_store(page) == 0) { set_page_writeback(page); unlock_page(page); end_page_writeback(page); diff -puN mm/swapfile.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled mm/swapfile.c --- a/mm/swapfile.c~mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled +++ a/mm/swapfile.c @@ -934,6 +934,9 @@ int get_swap_pages(int n_goal, bool clus /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && cluster); + /* Frontswap doesn't support THP */ + if (frontswap_enabled() && cluster) + goto noswap; avail_pgs = atomic_long_read(&nr_swap_pages) / nr_pages; if (avail_pgs <= 0) _ Patches currently in -mm which might be from huang.ying.caritas(a)gmail.com are mm-swap-frontswap-fix-thp-swap-if-frontswap-enabled.patch fontswap-thp-fix.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "KEYS: encrypted: fix buffer overread in valid_master_desc()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KEYS: encrypted: fix buffer overread in valid_master_desc() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 794b4bc292f5d31739d89c0202c54e7dc9bc3add Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)google.com> Date: Thu, 8 Jun 2017 14:48:18 +0100 Subject: KEYS: encrypted: fix buffer overread in valid_master_desc() From: Eric Biggers <ebiggers(a)google.com> commit 794b4bc292f5d31739d89c0202c54e7dc9bc3add upstream. With the 'encrypted' key type it was possible for userspace to provide a data blob ending with a master key description shorter than expected, e.g. 'keyctl add encrypted desc "new x" @s'. When validating such a master key description, validate_master_desc() could read beyond the end of the buffer. Fix this by using strncmp() instead of memcmp(). [Also clean up the code to deduplicate some logic.] Cc: Mimi Zohar <zohar(a)linux.vnet.ibm.com> Signed-off-by: Eric Biggers <ebiggers(a)google.com> Signed-off-by: David Howells <dhowells(a)redhat.com> Signed-off-by: James Morris <james.l.morris(a)oracle.com> Signed-off-by: Jin Qian <jinqian(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- security/keys/encrypted-keys/encrypted.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -141,23 +141,22 @@ static int valid_ecryptfs_desc(const cha */ static int valid_master_desc(const char *new_desc, const char *orig_desc) { - if (!memcmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_TRUSTED_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_TRUSTED_PREFIX_LEN)) - goto out; - } else if (!memcmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_USER_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_USER_PREFIX_LEN)) - goto out; - } else - goto out; + int prefix_len; + + if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) + prefix_len = KEY_TRUSTED_PREFIX_LEN; + else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) + prefix_len = KEY_USER_PREFIX_LEN; + else + return -EINVAL; + + if (!new_desc[prefix_len]) + return -EINVAL; + + if (orig_desc && strncmp(new_desc, orig_desc, prefix_len)) + return -EINVAL; + return 0; -out: - return -EINVAL; } /* Patches currently in stable-queue which might be from ebiggers(a)google.com are queue-4.9/keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5331aec1bf9c9da557668174e0a4bfcee39f1121 Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 15:56:28 -0500 Subject: media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE From: Jesse Chan <jc(a)linux.com> commit 5331aec1bf9c9da557668174e0a4bfcee39f1121 upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/soc_camera/soc_scale_crop.o see include/linux/module.h for more information This adds the license as "GPL", which matches the header of the file. MODULE_DESCRIPTION and MODULE_AUTHOR are also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/soc_camera/soc_scale_crop.c | 4 ++++ 1 file changed, 4 insertions(+) --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -418,3 +418,7 @@ void soc_camera_calc_client_output(struc mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.9/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.9/auxdisplay-img-ascii-lcd-add-missing-module_description-author-license.patch queue-4.9/asoc-pcm512x-add-missing-module_description-author-license.patch queue-4.9/pinctrl-pxa-pxa2xx-add-missing-module_description-author-license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "b43: Add missing MODULE_FIRMWARE()" has been added to the 4.9-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled b43: Add missing MODULE_FIRMWARE() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: b43-add-missing-module_firmware.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 3c89a72ad80c64bdbd5ff851ee9c328a191f7e01 Mon Sep 17 00:00:00 2001 From: Takashi Iwai <tiwai(a)suse.de> Date: Thu, 4 May 2017 11:27:52 +0200 Subject: b43: Add missing MODULE_FIRMWARE() From: Takashi Iwai <tiwai(a)suse.de> commit 3c89a72ad80c64bdbd5ff851ee9c328a191f7e01 upstream. Some firmware entries were forgotten to be added via MODULE_FIRMWARE(), which may result in the non-functional state when the driver is loaded in initrd. Link: http://bugzilla.opensuse.org/show_bug.cgi?id=1037344 Fixes: 15be8e89cdd9 ("b43: add more bcma cores") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/net/wireless/broadcom/b43/main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -71,8 +71,18 @@ MODULE_FIRMWARE("b43/ucode11.fw"); MODULE_FIRMWARE("b43/ucode13.fw"); MODULE_FIRMWARE("b43/ucode14.fw"); MODULE_FIRMWARE("b43/ucode15.fw"); +MODULE_FIRMWARE("b43/ucode16_lp.fw"); MODULE_FIRMWARE("b43/ucode16_mimo.fw"); +MODULE_FIRMWARE("b43/ucode24_lcn.fw"); +MODULE_FIRMWARE("b43/ucode25_lcn.fw"); +MODULE_FIRMWARE("b43/ucode25_mimo.fw"); +MODULE_FIRMWARE("b43/ucode26_mimo.fw"); +MODULE_FIRMWARE("b43/ucode29_mimo.fw"); +MODULE_FIRMWARE("b43/ucode33_lcn40.fw"); +MODULE_FIRMWARE("b43/ucode30_mimo.fw"); MODULE_FIRMWARE("b43/ucode5.fw"); +MODULE_FIRMWARE("b43/ucode40.fw"); +MODULE_FIRMWARE("b43/ucode42.fw"); MODULE_FIRMWARE("b43/ucode9.fw"); static int modparam_bad_frames_preempt; Patches currently in stable-queue which might be from tiwai(a)suse.de are queue-4.9/b43-add-missing-module_firmware.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5331aec1bf9c9da557668174e0a4bfcee39f1121 Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 15:56:28 -0500 Subject: media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE From: Jesse Chan <jc(a)linux.com> commit 5331aec1bf9c9da557668174e0a4bfcee39f1121 upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/soc_camera/soc_scale_crop.o see include/linux/module.h for more information This adds the license as "GPL", which matches the header of the file. MODULE_DESCRIPTION and MODULE_AUTHOR are also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/soc_camera/soc_scale_crop.c | 4 ++++ 1 file changed, 4 insertions(+) --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -405,3 +405,7 @@ void soc_camera_calc_client_output(struc mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.4/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.4/asoc-pcm512x-add-missing-module_description-author-license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "KEYS: encrypted: fix buffer overread in valid_master_desc()" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KEYS: encrypted: fix buffer overread in valid_master_desc() to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 794b4bc292f5d31739d89c0202c54e7dc9bc3add Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)google.com> Date: Thu, 8 Jun 2017 14:48:18 +0100 Subject: KEYS: encrypted: fix buffer overread in valid_master_desc() From: Eric Biggers <ebiggers(a)google.com> commit 794b4bc292f5d31739d89c0202c54e7dc9bc3add upstream. With the 'encrypted' key type it was possible for userspace to provide a data blob ending with a master key description shorter than expected, e.g. 'keyctl add encrypted desc "new x" @s'. When validating such a master key description, validate_master_desc() could read beyond the end of the buffer. Fix this by using strncmp() instead of memcmp(). [Also clean up the code to deduplicate some logic.] Cc: Mimi Zohar <zohar(a)linux.vnet.ibm.com> Signed-off-by: Eric Biggers <ebiggers(a)google.com> Signed-off-by: David Howells <dhowells(a)redhat.com> Signed-off-by: James Morris <james.l.morris(a)oracle.com> Signed-off-by: Jin Qian <jinqian(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- security/keys/encrypted-keys/encrypted.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -141,23 +141,22 @@ static int valid_ecryptfs_desc(const cha */ static int valid_master_desc(const char *new_desc, const char *orig_desc) { - if (!memcmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_TRUSTED_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_TRUSTED_PREFIX_LEN)) - goto out; - } else if (!memcmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_USER_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_USER_PREFIX_LEN)) - goto out; - } else - goto out; + int prefix_len; + + if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) + prefix_len = KEY_TRUSTED_PREFIX_LEN; + else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) + prefix_len = KEY_USER_PREFIX_LEN; + else + return -EINVAL; + + if (!new_desc[prefix_len]) + return -EINVAL; + + if (orig_desc && strncmp(new_desc, orig_desc, prefix_len)) + return -EINVAL; + return 0; -out: - return -EINVAL; } /* Patches currently in stable-queue which might be from ebiggers(a)google.com are queue-4.4/keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "don't put symlink bodies in pagecache into highmem" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled don't put symlink bodies in pagecache into highmem to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: don-t-put-symlink-bodies-in-pagecache-into-highmem.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 21fc61c73c3903c4c312d0802da01ec2b323d174 Mon Sep 17 00:00:00 2001 From: Al Viro <viro(a)zeniv.linux.org.uk> Date: Tue, 17 Nov 2015 01:07:57 -0500 Subject: don't put symlink bodies in pagecache into highmem From: Al Viro <viro(a)zeniv.linux.org.uk> commit 21fc61c73c3903c4c312d0802da01ec2b323d174 upstream. kmap() in page_follow_link_light() needed to go - allowing to hold an arbitrary number of kmaps for long is a great way to deadlocking the system. new helper (inode_nohighmem(inode)) needs to be used for pagecache symlinks inodes; done for all in-tree cases. page_follow_link_light() instrumented to yell about anything missed. Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Jin Qian <jinqian(a)google.com> Signed-off-by: Jin Qian <jinqian(a)android.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- fs/ext4/inode.c | 1 + fs/ext4/namei.c | 1 + fs/ext4/symlink.c | 10 +++------- fs/f2fs/inode.c | 1 + fs/f2fs/namei.c | 5 ++--- fs/inode.c | 6 ++++++ include/linux/fs.h | 1 + 7 files changed, 15 insertions(+), 10 deletions(-) --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4417,6 +4417,7 @@ struct inode *ext4_iget(struct super_blo inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } + inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3151,6 +3151,7 @@ static int ext4_symlink(struct inode *di if ((disk_link.len > EXT4_N_BLOCKS * 4)) { if (!encryption_required) inode->i_op = &ext4_symlink_inode_operations; + inode_nohighmem(inode); ext4_set_aops(inode); /* * We cannot call page_symlink() with transaction started --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -45,7 +45,7 @@ static const char *ext4_encrypted_follow cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; } @@ -75,16 +75,12 @@ static const char *ext4_encrypted_follow /* Null-terminate the name */ if (res <= plen) paddr[res] = '\0'; - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } return *cookie = paddr; errout: - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } kfree(paddr); return ERR_PTR(res); } --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -202,6 +202,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -351,6 +351,7 @@ static int f2fs_symlink(struct inode *di inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -942,7 +943,7 @@ static const char *f2fs_encrypted_follow cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; /* Symlink is encrypted */ @@ -982,13 +983,11 @@ static const char *f2fs_encrypted_follow /* Null-terminate the name */ paddr[res] = '\0'; - kunmap(cpage); page_cache_release(cpage); return *cookie = paddr; errout: kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); page_cache_release(cpage); return ERR_PTR(res); } --- a/fs/inode.c +++ b/fs/inode.c @@ -2028,3 +2028,9 @@ void inode_set_flags(struct inode *inode new_flags) != old_flags)); } EXPORT_SYMBOL(inode_set_flags); + +void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); +} +EXPORT_SYMBOL(inode_nohighmem); --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3066,5 +3066,6 @@ static inline bool dir_relax(struct inod } extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); #endif /* _LINUX_FS_H */ Patches currently in stable-queue which might be from viro(a)zeniv.linux.org.uk are queue-4.4/don-t-put-symlink-bodies-in-pagecache-into-highmem.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5331aec1bf9c9da557668174e0a4bfcee39f1121 Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 15:56:28 -0500 Subject: media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE From: Jesse Chan <jc(a)linux.com> commit 5331aec1bf9c9da557668174e0a4bfcee39f1121 upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/soc_camera/soc_scale_crop.o see include/linux/module.h for more information This adds the license as "GPL", which matches the header of the file. MODULE_DESCRIPTION and MODULE_AUTHOR are also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/soc_camera/soc_scale_crop.c | 4 ++++ 1 file changed, 4 insertions(+) --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -420,3 +420,7 @@ void soc_camera_calc_client_output(struc mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.15/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.15/media-mtk-vcodec-add-missing-module_license-description.patch queue-4.15/media-tegra-cec-add-missing-module_description-author-license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: tegra-cec: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: tegra-cec: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-tegra-cec-add-missing-module_description-author-license.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 20772c1a6f0e03d4231e2b539863987fa0c94e89 Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 15:56:52 -0500 Subject: media: tegra-cec: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE From: Jesse Chan <jc(a)linux.com> commit 20772c1a6f0e03d4231e2b539863987fa0c94e89 upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/tegra-cec/tegra_cec.o see include/linux/module.h for more information This adds the license as "GPL v2", which matches the header of the file. MODULE_DESCRIPTION and MODULE_AUTHOR are also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/tegra-cec/tegra_cec.c | 5 +++++ 1 file changed, 5 insertions(+) --- a/drivers/media/platform/tegra-cec/tegra_cec.c +++ b/drivers/media/platform/tegra-cec/tegra_cec.c @@ -493,3 +493,8 @@ static struct platform_driver tegra_cec_ }; module_platform_driver(tegra_cec_driver); + +MODULE_DESCRIPTION("Tegra HDMI CEC driver"); +MODULE_AUTHOR("NVIDIA CORPORATION"); +MODULE_AUTHOR("Cisco Systems, Inc. and/or its affiliates"); +MODULE_LICENSE("GPL v2"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.15/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.15/media-mtk-vcodec-add-missing-module_license-description.patch queue-4.15/media-tegra-cec-add-missing-module_description-author-license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-mtk-vcodec-add-missing-module_license-description.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From ccbc1e3876d5476fc23429690a683294ef0f755b Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 02:47:54 -0500 Subject: media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION From: Jesse Chan <jc(a)linux.com> commit ccbc1e3876d5476fc23429690a683294ef0f755b upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/mtk-vcodec/mtk-vcodec-common.o see include/linux/module.h for more information This adds the license as "GPL v2", which matches the header of the file. MODULE_DESCRIPTION is also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c | 3 +++ 1 file changed, 3 insertions(+) --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c @@ -115,3 +115,6 @@ struct mtk_vcodec_ctx *mtk_vcodec_get_cu return ctx; } EXPORT_SYMBOL(mtk_vcodec_get_curr_ctx); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Mediatek video codec driver"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.15/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.15/media-mtk-vcodec-add-missing-module_license-description.patch queue-4.15/media-tegra-cec-add-missing-module_description-author-license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "gpio: uniphier: fix mismatch between license text and MODULE_LICENSE" has been added to the 4.15-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled gpio: uniphier: fix mismatch between license text and MODULE_LICENSE to the 4.15-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: gpio-uniphier-fix-mismatch-between-license-text-and-module_license.patch and it can be found in the queue-4.15 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 13f9d59cef91a027bb338fc79b564fafa7680cd8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada <yamada.masahiro(a)socionext.com> Date: Thu, 23 Nov 2017 19:01:49 +0900 Subject: gpio: uniphier: fix mismatch between license text and MODULE_LICENSE From: Masahiro Yamada <yamada.masahiro(a)socionext.com> commit 13f9d59cef91a027bb338fc79b564fafa7680cd8 upstream. The comment block of this file indicates GPL-2.0 "only", while the MODULE_LICENSE is GPL-2.0 "or later", as include/linux/module.h describes as follows: "GPL" [GNU Public License v2 or later] "GPL v2" [GNU Public License v2] I am the author of this driver, and my intention is GPL-2.0 "only". Fixes: dbe776c2ca54 ("gpio: uniphier: add UniPhier GPIO controller driver") Signed-off-by: Masahiro Yamada <yamada.masahiro(a)socionext.com> Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpio/gpio-uniphier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -505,4 +505,4 @@ module_platform_driver(uniphier_gpio_dri MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro(a)socionext.com>"); MODULE_DESCRIPTION("UniPhier GPIO driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); Patches currently in stable-queue which might be from yamada.masahiro(a)socionext.com are queue-4.15/gpio-uniphier-fix-mismatch-between-license-text-and-module_license.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 5331aec1bf9c9da557668174e0a4bfcee39f1121 Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 15:56:28 -0500 Subject: media: soc_camera: soc_scale_crop: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE From: Jesse Chan <jc(a)linux.com> commit 5331aec1bf9c9da557668174e0a4bfcee39f1121 upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/soc_camera/soc_scale_crop.o see include/linux/module.h for more information This adds the license as "GPL", which matches the header of the file. MODULE_DESCRIPTION and MODULE_AUTHOR are also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/soc_camera/soc_scale_crop.c | 4 ++++ 1 file changed, 4 insertions(+) --- a/drivers/media/platform/soc_camera/soc_scale_crop.c +++ b/drivers/media/platform/soc_camera/soc_scale_crop.c @@ -419,3 +419,7 @@ void soc_camera_calc_client_output(struc mf->height = soc_camera_shift_scale(rect->height, shift, scale_v); } EXPORT_SYMBOL(soc_camera_calc_client_output); + +MODULE_DESCRIPTION("soc-camera scaling-cropping functions"); +MODULE_AUTHOR("Guennadi Liakhovetski <kernel(a)pengutronix.de>"); +MODULE_LICENSE("GPL"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.14/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.14/media-mtk-vcodec-add-missing-module_license-description.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION" has been added to the 4.14-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: media-mtk-vcodec-add-missing-module_license-description.patch and it can be found in the queue-4.14 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From ccbc1e3876d5476fc23429690a683294ef0f755b Mon Sep 17 00:00:00 2001 From: Jesse Chan <jc(a)linux.com> Date: Mon, 20 Nov 2017 02:47:54 -0500 Subject: media: mtk-vcodec: add missing MODULE_LICENSE/DESCRIPTION From: Jesse Chan <jc(a)linux.com> commit ccbc1e3876d5476fc23429690a683294ef0f755b upstream. This change resolves a new compile-time warning when built as a loadable module: WARNING: modpost: missing MODULE_LICENSE() in drivers/media/platform/mtk-vcodec/mtk-vcodec-common.o see include/linux/module.h for more information This adds the license as "GPL v2", which matches the header of the file. MODULE_DESCRIPTION is also added. Signed-off-by: Jesse Chan <jc(a)linux.com> Signed-off-by: Hans Verkuil <hans.verkuil(a)cisco.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)s-opensource.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c | 3 +++ 1 file changed, 3 insertions(+) --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_util.c @@ -115,3 +115,6 @@ struct mtk_vcodec_ctx *mtk_vcodec_get_cu return ctx; } EXPORT_SYMBOL(mtk_vcodec_get_curr_ctx); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Mediatek video codec driver"); Patches currently in stable-queue which might be from jc(a)linux.com are queue-4.14/media-soc_camera-soc_scale_crop-add-missing-module_description-author-license.patch queue-4.14/media-mtk-vcodec-add-missing-module_license-description.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ARM: exynos_defconfig: Enable options to mount a rootfs via NFS" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ARM: exynos_defconfig: Enable options to mount a rootfs via NFS to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: arm-exynos_defconfig-enable-options-to-mount-a-rootfs-via-nfs.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 19f79ccf6d77409cd138bce8db206cdac7fd5ea7 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas <javier.martinez(a)collabora.co.uk> Date: Fri, 27 Mar 2015 01:50:16 +0900 Subject: ARM: exynos_defconfig: Enable options to mount a rootfs via NFS From: Javier Martinez Canillas <javier.martinez(a)collabora.co.uk> commit 19f79ccf6d77409cd138bce8db206cdac7fd5ea7 upstream. This patch enables the options to mount a rootfs over NFS and also support for automatic configuration of IP addresses during boot as needed by NFS. Signed-off-by: Javier Martinez Canillas <javier.martinez(a)collabora.co.uk> Signed-off-by: Kukjin Kim <kgene(a)kernel.org> Signed-off-by: Guillaume Tucker <guillaume.tucker(a)collabora.com> Reviewed-by: Krzysztof Kozlowski <krzk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/arm/configs/exynos_defconfig | 6 ++++++ 1 file changed, 6 insertions(+) --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -33,6 +33,10 @@ CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_NET_KEY=y CONFIG_INET=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y CONFIG_RFKILL_REGULATOR=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y @@ -170,6 +174,8 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_CRAMFS=y CONFIG_ROMFS_FS=y +CONFIG_NFS_FS=y +CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y Patches currently in stable-queue which might be from javier.martinez(a)collabora.co.uk are queue-3.18/arm-exynos_defconfig-enable-options-to-mount-a-rootfs-via-nfs.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "KEYS: encrypted: fix buffer overread in valid_master_desc()" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled KEYS: encrypted: fix buffer overread in valid_master_desc() to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 794b4bc292f5d31739d89c0202c54e7dc9bc3add Mon Sep 17 00:00:00 2001 From: Eric Biggers <ebiggers(a)google.com> Date: Thu, 8 Jun 2017 14:48:18 +0100 Subject: KEYS: encrypted: fix buffer overread in valid_master_desc() From: Eric Biggers <ebiggers(a)google.com> commit 794b4bc292f5d31739d89c0202c54e7dc9bc3add upstream. With the 'encrypted' key type it was possible for userspace to provide a data blob ending with a master key description shorter than expected, e.g. 'keyctl add encrypted desc "new x" @s'. When validating such a master key description, validate_master_desc() could read beyond the end of the buffer. Fix this by using strncmp() instead of memcmp(). [Also clean up the code to deduplicate some logic.] Cc: Mimi Zohar <zohar(a)linux.vnet.ibm.com> Signed-off-by: Eric Biggers <ebiggers(a)google.com> Signed-off-by: David Howells <dhowells(a)redhat.com> Signed-off-by: James Morris <james.l.morris(a)oracle.com> Signed-off-by: Jin Qian <jinqian(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- security/keys/encrypted-keys/encrypted.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -141,23 +141,22 @@ static int valid_ecryptfs_desc(const cha */ static int valid_master_desc(const char *new_desc, const char *orig_desc) { - if (!memcmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_TRUSTED_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_TRUSTED_PREFIX_LEN)) - goto out; - } else if (!memcmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) { - if (strlen(new_desc) == KEY_USER_PREFIX_LEN) - goto out; - if (orig_desc) - if (memcmp(new_desc, orig_desc, KEY_USER_PREFIX_LEN)) - goto out; - } else - goto out; + int prefix_len; + + if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN)) + prefix_len = KEY_TRUSTED_PREFIX_LEN; + else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN)) + prefix_len = KEY_USER_PREFIX_LEN; + else + return -EINVAL; + + if (!new_desc[prefix_len]) + return -EINVAL; + + if (orig_desc && strncmp(new_desc, orig_desc, prefix_len)) + return -EINVAL; + return 0; -out: - return -EINVAL; } /* Patches currently in stable-queue which might be from ebiggers(a)google.com are queue-3.18/keys-encrypted-fix-buffer-overread-in-valid_master_desc.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ARM: exynos_defconfig: Enable NFSv4 client" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ARM: exynos_defconfig: Enable NFSv4 client to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: arm-exynos_defconfig-enable-nfsv4-client.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From 1c1fb9b0c89a2506e556114c813a606bc1508d49 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski <k.kozlowski(a)samsung.com> Date: Wed, 25 Nov 2015 13:09:43 +0900 Subject: ARM: exynos_defconfig: Enable NFSv4 client From: Krzysztof Kozlowski <k.kozlowski(a)samsung.com> commit 1c1fb9b0c89a2506e556114c813a606bc1508d49 upstream. NFS client is already enabled (NFS_FS) and by default it enables clients for version 2 and 3. Enable explicitly the version 4 client to utilize the newer protocol. The NFS client is especially useful for testing kernel in automated environments (network boot with network file system). Signed-off-by: Krzysztof Kozlowski <k.kozlowski(a)samsung.com> Reviewed-by: Javier Martinez Canillas <javier(a)osg.samsung.com> Signed-off-by: Guillaume Tucker <guillaume.tucker(a)collabora.com> Reviewed-by: Krzysztof Kozlowski <krzk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- arch/arm/configs/exynos_defconfig | 1 + 1 file changed, 1 insertion(+) --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -175,6 +175,7 @@ CONFIG_TMPFS_POSIX_ACL=y CONFIG_CRAMFS=y CONFIG_ROMFS_FS=y CONFIG_NFS_FS=y +CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y Patches currently in stable-queue which might be from k.kozlowski(a)samsung.com are queue-3.18/arm-exynos_defconfig-enable-nfsv4-client.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCHv2 1/1] ext4/f2fs: don't put symlink in pagecache into highmem

by Jin Qian

From: Jin Qian <jinqian(a)google.com> partial backport from 21fc61c73c3903c4c312d0802da01ec2b323d174 upstream to v4.4 to prevent virt_to_page on highmem. ext4_encrypted_follow_link uses kmap() for cpage caddr = kmap(cpage); _ext4_fname_disk_to_usr calls virt_to_page on the kmapped address. _ext4_fname_disk_to_usr() ext4_fname_decrypt() sg_init_one() sg_init_one(&src_sg, iname->name, iname->len); sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); Cc: linux-stable <stable(a)vger.kernel.org> # 4.4.y Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Jin Qian <jinqian(a)google.com> Signed-off-by: Jin Qian <jinqian(a)android.com> --- fs/ext4/inode.c | 1 + fs/ext4/namei.c | 1 + fs/ext4/symlink.c | 10 +++------- fs/f2fs/inode.c | 1 + fs/f2fs/namei.c | 5 ++--- fs/inode.c | 6 ++++++ include/linux/fs.h | 1 + 7 files changed, 15 insertions(+), 10 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4df1cb19a243..f0cabc8c96cb 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4417,6 +4417,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } + inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 4c36dca486cc..32960b3ecd4f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3151,6 +3151,7 @@ static int ext4_symlink(struct inode *dir, if ((disk_link.len > EXT4_N_BLOCKS * 4)) { if (!encryption_required) inode->i_op = &ext4_symlink_inode_operations; + inode_nohighmem(inode); ext4_set_aops(inode); /* * We cannot call page_symlink() with transaction started diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index e8e7af62ac95..287c3980fa0b 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -45,7 +45,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; } @@ -75,16 +75,12 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ if (res <= plen) paddr[res] = '\0'; - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } return *cookie = paddr; errout: - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } kfree(paddr); return ERR_PTR(res); } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 97e20decacb4..5528801a5baf 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -202,6 +202,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 2c32110f9fc0..484df6850747 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -351,6 +351,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -942,7 +943,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; /* Symlink is encrypted */ @@ -982,13 +983,11 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ paddr[res] = '\0'; - kunmap(cpage); page_cache_release(cpage); return *cookie = paddr; errout: kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); page_cache_release(cpage); return ERR_PTR(res); } diff --git a/fs/inode.c b/fs/inode.c index b0edef500590..b95615f3fc50 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2028,3 +2028,9 @@ void inode_set_flags(struct inode *inode, unsigned int flags, new_flags) != old_flags)); } EXPORT_SYMBOL(inode_set_flags); + +void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); +} +EXPORT_SYMBOL(inode_nohighmem); diff --git a/include/linux/fs.h b/include/linux/fs.h index c8decb7075d6..f746a59fcc88 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3066,5 +3066,6 @@ static inline bool dir_relax(struct inode *inode) } extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); #endif /* _LINUX_FS_H */ -- 2.16.0.rc1.238.g530d649a79-goog

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] [merged] locking-qrwlock-include-asm-byteorderh-as-needed.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: locking/qrwlock: include asm/byteorder.h as needed has been removed from the -mm tree. Its filename was locking-qrwlock-include-asm-byteorderh-as-needed.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Arnd Bergmann <arnd(a)arndb.de> Subject: locking/qrwlock: include asm/byteorder.h as needed Moving the qrwlock struct definition into a header file introduced a subtle bug on all little-endian machines, where some files in some configurations would see the fields in an incorrect order. This was found by building with an LTO enabled compiler that warns every time we try to link together files with incompatible data structures. A second patch changes linux/kconfig.h to always define the symbols, but this seems to be the root cause of most of the issues, so I'd suggest we do both. On a current linux-next kernel, I verified that this header is responsible for all type mismatches as a result from the endianess confusion. Link: http://lkml.kernel.org/r/20180202154104.1522809-1-arnd@arndb.de Fixes: e0d02285f16e ("locking/qrwlock: Use 'struct qrwlock' instead of 'struct __qrwlock'") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Nicolas Pitre <nico(a)linaro.org> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Babu Moger <babu.moger(a)amd.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Masahiro Yamada <yamada.masahiro(a)socionext.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/asm-generic/qrwlock_types.h | 1 + 1 file changed, 1 insertion(+) diff -puN include/asm-generic/qrwlock_types.h~locking-qrwlock-include-asm-byteorderh-as-needed include/asm-generic/qrwlock_types.h --- a/include/asm-generic/qrwlock_types.h~locking-qrwlock-include-asm-byteorderh-as-needed +++ a/include/asm-generic/qrwlock_types.h @@ -3,6 +3,7 @@ #define __ASM_GENERIC_QRWLOCK_TYPES_H #include <linux/types.h> +#include <asm/byteorder.h> #include <asm/spinlock_types.h> /* _ Patches currently in -mm which might be from arnd(a)arndb.de are kbuild-always-define-endianess-in-kconfigh.patch bugh-work-around-gcc-pr82365-in-bug.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] pipe-fix-off-by-one-error-when-checking-buffer-limits.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: pipe: fix off-by-one error when checking buffer limits has been removed from the -mm tree. Its filename was pipe-fix-off-by-one-error-when-checking-buffer-limits.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Eric Biggers <ebiggers(a)google.com> Subject: pipe: fix off-by-one error when checking buffer limits With pipe-user-pages-hard set to 'N', users were actually only allowed up to 'N - 1' buffers; and likewise for pipe-user-pages-soft. Fix this to allow up to 'N' buffers, as would be expected. Link: http://lkml.kernel.org/r/20180111052902.14409-5-ebiggers3@gmail.com Fixes: b0b91d18e2e9 ("pipe: fix limit checking in pipe_set_size()") Signed-off-by: Eric Biggers <ebiggers(a)google.com> Acked-by: Willy Tarreau <w(a)1wt.eu> Acked-by: Kees Cook <keescook(a)chromium.org> Acked-by: Joe Lawrence <joe.lawrence(a)redhat.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: "Luis R . Rodriguez" <mcgrof(a)kernel.org> Cc: Michael Kerrisk <mtk.manpages(a)gmail.com> Cc: Mikulas Patocka <mpatocka(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/pipe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff -puN fs/pipe.c~pipe-fix-off-by-one-error-when-checking-buffer-limits fs/pipe.c --- a/fs/pipe.c~pipe-fix-off-by-one-error-when-checking-buffer-limits +++ a/fs/pipe.c @@ -605,12 +605,12 @@ static unsigned long account_pipe_buffer static bool too_many_pipe_buffers_soft(unsigned long user_bufs) { - return pipe_user_pages_soft && user_bufs >= pipe_user_pages_soft; + return pipe_user_pages_soft && user_bufs > pipe_user_pages_soft; } static bool too_many_pipe_buffers_hard(unsigned long user_bufs) { - return pipe_user_pages_hard && user_bufs >= pipe_user_pages_hard; + return pipe_user_pages_hard && user_bufs > pipe_user_pages_hard; } static bool is_unprivileged_user(void) _ Patches currently in -mm which might be from ebiggers(a)google.com are

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] pipe-actually-allow-root-to-exceed-the-pipe-buffer-limits.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: pipe: actually allow root to exceed the pipe buffer limits has been removed from the -mm tree. Its filename was pipe-actually-allow-root-to-exceed-the-pipe-buffer-limits.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Eric Biggers <ebiggers(a)google.com> Subject: pipe: actually allow root to exceed the pipe buffer limits pipe-user-pages-hard and pipe-user-pages-soft are only supposed to apply to unprivileged users, as documented in both Documentation/sysctl/fs.txt and the pipe(7) man page. However, the capabilities are actually only checked when increasing a pipe's size using F_SETPIPE_SZ, not when creating a new pipe. Therefore, if pipe-user-pages-hard has been set, the root user can run into it and be unable to create pipes. Similarly, if pipe-user-pages-soft has been set, the root user can run into it and have their pipes limited to 1 page each. Fix this by allowing the privileged override in both cases. Link: http://lkml.kernel.org/r/20180111052902.14409-4-ebiggers3@gmail.com Fixes: 759c01142a5d ("pipe: limit the per-user amount of pages allocated in pipes") Signed-off-by: Eric Biggers <ebiggers(a)google.com> Acked-by: Kees Cook <keescook(a)chromium.org> Acked-by: Joe Lawrence <joe.lawrence(a)redhat.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: "Luis R . Rodriguez" <mcgrof(a)kernel.org> Cc: Michael Kerrisk <mtk.manpages(a)gmail.com> Cc: Mikulas Patocka <mpatocka(a)redhat.com> Cc: Willy Tarreau <w(a)1wt.eu> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/pipe.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff -puN fs/pipe.c~pipe-actually-allow-root-to-exceed-the-pipe-buffer-limits fs/pipe.c --- a/fs/pipe.c~pipe-actually-allow-root-to-exceed-the-pipe-buffer-limits +++ a/fs/pipe.c @@ -613,6 +613,11 @@ static bool too_many_pipe_buffers_hard(u return pipe_user_pages_hard && user_bufs >= pipe_user_pages_hard; } +static bool is_unprivileged_user(void) +{ + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); +} + struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; @@ -629,12 +634,12 @@ struct pipe_inode_info *alloc_pipe_info( user_bufs = account_pipe_buffers(user, 0, pipe_bufs); - if (too_many_pipe_buffers_soft(user_bufs)) { + if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, 1); pipe_bufs = 1; } - if (too_many_pipe_buffers_hard(user_bufs)) + if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), @@ -1065,7 +1070,7 @@ static long pipe_set_size(struct pipe_in if (nr_pages > pipe->buffers && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && - !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } _ Patches currently in -mm which might be from ebiggers(a)google.com are

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] kasan-rework-kconfig-settings.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: kasan: rework Kconfig settings has been removed from the -mm tree. Its filename was kasan-rework-kconfig-settings.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Arnd Bergmann <arnd(a)arndb.de> Subject: kasan: rework Kconfig settings We get a lot of very large stack frames using gcc-7.0.1 with the default -fsanitize-address-use-after-scope --param asan-stack=1 options, which can easily cause an overflow of the kernel stack, e.g. drivers/gpu/drm/i915/gvt/handlers.c:2434:1: warning: the frame size of 46176 bytes is larger than 3072 bytes drivers/net/wireless/ralink/rt2x00/rt2800lib.c:5650:1: warning: the frame size of 23632 bytes is larger than 3072 bytes lib/atomic64_test.c:250:1: warning: the frame size of 11200 bytes is larger than 3072 bytes drivers/gpu/drm/i915/gvt/handlers.c:2621:1: warning: the frame size of 9208 bytes is larger than 3072 bytes drivers/media/dvb-frontends/stv090x.c:3431:1: warning: the frame size of 6816 bytes is larger than 3072 bytes fs/fscache/stats.c:287:1: warning: the frame size of 6536 bytes is larger than 3072 bytes To reduce this risk, -fsanitize-address-use-after-scope is now split out into a separate CONFIG_KASAN_EXTRA Kconfig option, leading to stack frames that are smaller than 2 kilobytes most of the time on x86_64. An earlier version of this patch also prevented combining KASAN_EXTRA with KASAN_INLINE, but that is no longer necessary with gcc-7.0.1. All patches to get the frame size below 2048 bytes with CONFIG_KASAN=y and CONFIG_KASAN_EXTRA=n have been merged by maintainers now, so we can bring back that default now. KASAN_EXTRA=y still causes lots of warnings but now defaults to !COMPILE_TEST to disable it in allmodconfig, and it remains disabled in all other defconfigs since it is a new option. I arbitrarily raise the warning limit for KASAN_EXTRA to 3072 to reduce the noise, but an allmodconfig kernel still has around 50 warnings on gcc-7. I experimented a bit more with smaller stack frames and have another follow-up series that reduces the warning limit for 64-bit architectures to 1280 bytes (without CONFIG_KASAN). With earlier versions of this patch series, I also had patches to address the warnings we get with KASAN and/or KASAN_EXTRA, using a "noinline_if_stackbloat" annotation. That annotation now got replaced with a gcc-8 bugfix (see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715) and a workaround for older compilers, which means that KASAN_EXTRA is now just as bad as before and will lead to an instant stack overflow in a few extreme cases. This reverts parts of commit commit 3f181b4 ("lib/Kconfig.debug: disable -Wframe-larger-than warnings with KASAN=y"). Two patches in linux-next should be merged first to avoid introducing warnings in an allmodconfig build: 3cd890dbe2a4 ("media: dvb-frontends: fix i2c access helpers for KASAN") 16c3ada89cff ("media: r820t: fix r820t_write_reg for KASAN") Do we really need to backport this? I think we do: without this patch, enabling KASAN will lead to unavoidable kernel stack overflow in certain device drivers when built with gcc-7 or higher on linux-4.10+ or any version that contains a backport of commit c5caf21ab0cf8. Most people are probably still on older compilers, but it will get worse over time as they upgrade their distros. The warnings we get on kernels older than this should all be for code that uses dangerously large stack frames, though most of them do not cause an actual stack overflow by themselves.The asan-stack option was added in linux-4.0, and commit 3f181b4d8652 ("lib/Kconfig.debug: disable -Wframe-larger-than warnings with KASAN=y") effectively turned off the warning for allmodconfig kernels, so I would like to see this fix backported to any kernels later than 4.0. I have done dozens of fixes for individual functions with stack frames larger than 2048 bytes with asan-stack, and I plan to make sure that all those fixes make it into the stable kernels as well (most are already there). Part of the complication here is that asan-stack (from 4.0) was originally assumed to always require much larger stacks, but that turned out to be a combination of multiple gcc bugs that we have now worked around and fixed, but sanitize-address-use-after-scope (from v4.10) has a much higher inherent stack usage and also suffers from at least three other problems that we have analyzed but not yet fixed upstream, each of them makes the stack usage more severe than it should be. Link: http://lkml.kernel.org/r/20171221134744.2295529-1-arnd@arndb.de Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Acked-by: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Mauro Carvalho Chehab <mchehab(a)kernel.org> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/Kconfig.debug | 2 +- lib/Kconfig.kasan | 11 +++++++++++ scripts/Makefile.kasan | 2 ++ 3 files changed, 14 insertions(+), 1 deletion(-) diff -puN lib/Kconfig.debug~kasan-rework-kconfig-settings lib/Kconfig.debug --- a/lib/Kconfig.debug~kasan-rework-kconfig-settings +++ a/lib/Kconfig.debug @@ -217,7 +217,7 @@ config ENABLE_MUST_CHECK config FRAME_WARN int "Warn for stack frames larger than (needs gcc 4.4)" range 0 8192 - default 0 if KASAN + default 3072 if KASAN_EXTRA default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 1280 if (!64BIT && PARISC) default 1024 if (!64BIT && !PARISC) diff -puN lib/Kconfig.kasan~kasan-rework-kconfig-settings lib/Kconfig.kasan --- a/lib/Kconfig.kasan~kasan-rework-kconfig-settings +++ a/lib/Kconfig.kasan @@ -20,6 +20,17 @@ config KASAN Currently CONFIG_KASAN doesn't work with CONFIG_DEBUG_SLAB (the resulting kernel does not boot). +config KASAN_EXTRA + bool "KAsan: extra checks" + depends on KASAN && DEBUG_KERNEL && !COMPILE_TEST + help + This enables further checks in the kernel address sanitizer, for now + it only includes the address-use-after-scope check that can lead + to excessive kernel stack usage, frame size warnings and longer + compile time. + https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 has more + + choice prompt "Instrumentation type" depends on KASAN diff -puN scripts/Makefile.kasan~kasan-rework-kconfig-settings scripts/Makefile.kasan --- a/scripts/Makefile.kasan~kasan-rework-kconfig-settings +++ a/scripts/Makefile.kasan @@ -38,7 +38,9 @@ else endif +ifdef CONFIG_KASAN_EXTRA CFLAGS_KASAN += $(call cc-option, -fsanitize-address-use-after-scope) +endif CFLAGS_KASAN_NOSANITIZE := -fno-builtin _ Patches currently in -mm which might be from arnd(a)arndb.de are kbuild-always-define-endianess-in-kconfigh.patch bugh-work-around-gcc-pr82365-in-bug.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: lib/ubsan: add type mismatch handler for new GCC/Clang has been removed from the -mm tree. Its filename was lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Subject: lib/ubsan: add type mismatch handler for new GCC/Clang UBSAN=y fails to build with new GCC/clang: arch/x86/kernel/head64.o: In function `sanitize_boot_params': arch/x86/include/asm/bootparam_utils.h:37: undefined reference to `__ubsan_handle_type_mismatch_v1' because Clang and GCC 8 slightly changed ABI for 'type mismatch' errors. Compiler now uses new __ubsan_handle_type_mismatch_v1() function with slightly modified 'struct type_mismatch_data'. Let's add new 'struct type_mismatch_data_common' which is independent from compiler's layout of 'struct type_mismatch_data'. And make __ubsan_handle_type_mismatch[_v1]() functions transform compiler-dependent type mismatch data to our internal representation. This way, we can support both old and new compilers with minimal amount of change. Link: http://lkml.kernel.org/r/20180119152853.16806-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Reported-by: Sodagudi Prasad <psodagud(a)codeaurora.org> Cc: <stable(a)vger.kernel.org> [4.5+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/ubsan.c | 48 ++++++++++++++++++++++++++++++++++++++---------- lib/ubsan.h | 14 ++++++++++++++ 2 files changed, 52 insertions(+), 10 deletions(-) diff -puN lib/ubsan.c~lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang lib/ubsan.c --- a/lib/ubsan.c~lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang +++ a/lib/ubsan.c @@ -265,14 +265,14 @@ void __ubsan_handle_divrem_overflow(stru } EXPORT_SYMBOL(__ubsan_handle_divrem_overflow); -static void handle_null_ptr_deref(struct type_mismatch_data *data) +static void handle_null_ptr_deref(struct type_mismatch_data_common *data) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s null pointer of type %s\n", type_check_kinds[data->type_check_kind], @@ -281,15 +281,15 @@ static void handle_null_ptr_deref(struct ubsan_epilogue(&flags); } -static void handle_misaligned_access(struct type_mismatch_data *data, +static void handle_misaligned_access(struct type_mismatch_data_common *data, unsigned long ptr) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s misaligned address %p for type %s\n", type_check_kinds[data->type_check_kind], @@ -299,15 +299,15 @@ static void handle_misaligned_access(str ubsan_epilogue(&flags); } -static void handle_object_size_mismatch(struct type_mismatch_data *data, +static void handle_object_size_mismatch(struct type_mismatch_data_common *data, unsigned long ptr) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s address %p with insufficient space\n", type_check_kinds[data->type_check_kind], (void *) ptr); @@ -315,7 +315,7 @@ static void handle_object_size_mismatch( ubsan_epilogue(&flags); } -void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, +static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data, unsigned long ptr) { @@ -326,8 +326,36 @@ void __ubsan_handle_type_mismatch(struct else handle_object_size_mismatch(data, ptr); } + +void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, + unsigned long ptr) +{ + struct type_mismatch_data_common common_data = { + .location = &data->location, + .type = data->type, + .alignment = data->alignment, + .type_check_kind = data->type_check_kind + }; + + ubsan_type_mismatch_common(&common_data, ptr); +} EXPORT_SYMBOL(__ubsan_handle_type_mismatch); +void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data, + unsigned long ptr) +{ + + struct type_mismatch_data_common common_data = { + .location = &data->location, + .type = data->type, + .alignment = 1UL << data->log_alignment, + .type_check_kind = data->type_check_kind + }; + + ubsan_type_mismatch_common(&common_data, ptr); +} +EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1); + void __ubsan_handle_nonnull_return(struct nonnull_return_data *data) { unsigned long flags; diff -puN lib/ubsan.h~lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang lib/ubsan.h --- a/lib/ubsan.h~lib-ubsan-add-type-mismatch-handler-for-new-gcc-clang +++ a/lib/ubsan.h @@ -37,6 +37,20 @@ struct type_mismatch_data { unsigned char type_check_kind; }; +struct type_mismatch_data_v1 { + struct source_location location; + struct type_descriptor *type; + unsigned char log_alignment; + unsigned char type_check_kind; +}; + +struct type_mismatch_data_common { + struct source_location *location; + struct type_descriptor *type; + unsigned long alignment; + unsigned char type_check_kind; +}; + struct nonnull_arg_data { struct source_location location; struct source_location attr_location; _ Patches currently in -mm which might be from aryabinin(a)virtuozzo.com are mm-kasan-dont-vfree-nonexistent-vm_area.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] revert-kernel-relayc-fix-potential-memory-leak.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: kernel/relay.c: revert "kernel/relay.c: fix potential memory leak" has been removed from the -mm tree. Its filename was revert-kernel-relayc-fix-potential-memory-leak.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Eric Biggers <ebiggers(a)google.com> Subject: kernel/relay.c: revert "kernel/relay.c: fix potential memory leak" This reverts ba62bafe942b159a6 ("kernel/relay.c: fix potential memory leak"). This commit introduced a double free bug, because 'chan' is already freed by the line: kref_put(&chan->kref, relay_destroy_channel); This bug was found by syzkaller, using the BLKTRACESETUP ioctl. Link: http://lkml.kernel.org/r/20180127004759.101823-1-ebiggers3@gmail.com Fixes: ba62bafe942b ("kernel/relay.c: fix potential memory leak") Signed-off-by: Eric Biggers <ebiggers(a)google.com> Reported-by: syzbot <syzkaller(a)googlegroups.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Zhouyi Zhou <yizhouzhou(a)ict.ac.cn> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: <stable(a)vger.kernel.org> [4.7+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/relay.c | 1 - 1 file changed, 1 deletion(-) diff -puN kernel/relay.c~revert-kernel-relayc-fix-potential-memory-leak kernel/relay.c --- a/kernel/relay.c~revert-kernel-relayc-fix-potential-memory-leak +++ a/kernel/relay.c @@ -611,7 +611,6 @@ free_bufs: kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); - kfree(chan); return NULL; } EXPORT_SYMBOL_GPL(relay_open); _ Patches currently in -mm which might be from ebiggers(a)google.com are

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] revert-async-simplify-lowest_in_progress.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: kernel/async.c: revert "async: simplify lowest_in_progress()" has been removed from the -mm tree. Its filename was revert-async-simplify-lowest_in_progress.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Rasmus Villemoes <linux(a)rasmusvillemoes.dk> Subject: kernel/async.c: revert "async: simplify lowest_in_progress()" This reverts 92266d6ef60c2381 ("async: simplify lowest_in_progress()"), which was simply wrong: In the case where domain is NULL, we now use the wrong offsetof() in the list_first_entry macro, so we don't actually fetch the ->cookie value, but rather the eight bytes located sizeof(struct list_head) further into the struct async_entry. On 64 bit, that's the data member, while on 32 bit, that's a u64 built from func and data in some order. I think the bug happens to be harmless in practice: It obviously only affects callers which pass a NULL domain, and AFAICT the only such caller is async_synchronize_full() -> async_synchronize_full_domain(NULL) -> async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, NULL) and the ASYNC_COOKIE_MAX means that in practice we end up waiting for the async_global_pending list to be empty - but it would break if somebody happened to pass (void*)-1 as the data element to async_schedule, and of course also if somebody ever does a async_synchronize_cookie_domain(, NULL) with a "finite" cookie value. Maybe the "harmless in practice" means this isn't -stable material. But I'm not completely confident my quick git grep'ing is enough, and there might be affected code in one of the earlier kernels that has since been removed, so I'll leave the decision to the stable guys. Link: http://lkml.kernel.org/r/20171128104938.3921-1-linux@rasmusvillemoes.dk Fixes: 92266d6ef60c "async: simplify lowest_in_progress()" Signed-off-by: Rasmus Villemoes <linux(a)rasmusvillemoes.dk> Acked-by: Tejun Heo <tj(a)kernel.org> Cc: Arjan van de Ven <arjan(a)linux.intel.com> Cc: Adam Wallis <awallis(a)codeaurora.org> Cc: Lai Jiangshan <laijs(a)cn.fujitsu.com> Cc: <stable(a)vger.kernel.org> [3.10+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/async.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff -puN kernel/async.c~revert-async-simplify-lowest_in_progress kernel/async.c --- a/kernel/async.c~revert-async-simplify-lowest_in_progress +++ a/kernel/async.c @@ -84,20 +84,24 @@ static atomic_t entry_count; static async_cookie_t lowest_in_progress(struct async_domain *domain) { - struct list_head *pending; + struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); - if (domain) - pending = &domain->pending; - else - pending = &async_global_pending; + if (domain) { + if (!list_empty(&domain->pending)) + first = list_first_entry(&domain->pending, + struct async_entry, domain_list); + } else { + if (!list_empty(&async_global_pending)) + first = list_first_entry(&async_global_pending, + struct async_entry, global_list); + } - if (!list_empty(pending)) - ret = list_first_entry(pending, struct async_entry, - domain_list)->cookie; + if (first) + ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; _ Patches currently in -mm which might be from linux(a)rasmusvillemoes.dk are ida-do-zeroing-in-ida_pre_get.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] fs-proc-kcorec-use-probe_kernel_read-instead-of-memcpy.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: fs/proc/kcore.c: use probe_kernel_read() instead of memcpy() has been removed from the -mm tree. Its filename was fs-proc-kcorec-use-probe_kernel_read-instead-of-memcpy.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Heiko Carstens <heiko.carstens(a)de.ibm.com> Subject: fs/proc/kcore.c: use probe_kernel_read() instead of memcpy() df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data") added a bounce buffer to avoid hardened usercopy checks. Copying to the bounce buffer was implemented with a simple memcpy() assuming that it is always valid to read from kernel memory iff the kern_addr_valid() check passed. A simple, but pointless, test case like "dd if=/proc/kcore of=/dev/null" now can easily crash the kernel, since the former execption handling on invalid kernel addresses now doesn't work anymore. Also adding a kern_addr_valid() implementation wouldn't help here. Most architectures simply return 1 here, while a couple implemented a page table walk to figure out if something is mapped at the address in question. With DEBUG_PAGEALLOC active mappings are established and removed all the time, so that relying on the result of kern_addr_valid() before executing the memcpy() also doesn't work. Therefore simply use probe_kernel_read() to copy to the bounce buffer. This also allows to simplify read_kcore(). At least on s390 this fixes the observed crashes and doesn't introduce warnings that were removed with df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data"), even though the generic probe_kernel_read() implementation uses uaccess functions. While looking into this I'm also wondering if kern_addr_valid() could be completely removed...(?) Link: http://lkml.kernel.org/r/20171202132739.99971-1-heiko.carstens@de.ibm.com Fixes: df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data") Fixes: f5509cc18daa ("mm: Hardened usercopy") Signed-off-by: Heiko Carstens <heiko.carstens(a)de.ibm.com> Acked-by: Kees Cook <keescook(a)chromium.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Al Viro <viro(a)ZenIV.linux.org.uk> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/proc/kcore.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff -puN fs/proc/kcore.c~fs-proc-kcorec-use-probe_kernel_read-instead-of-memcpy fs/proc/kcore.c --- a/fs/proc/kcore.c~fs-proc-kcorec-use-probe_kernel_read-instead-of-memcpy +++ a/fs/proc/kcore.c @@ -512,23 +512,15 @@ read_kcore(struct file *file, char __use return -EFAULT; } else { if (kern_addr_valid(start)) { - unsigned long n; - /* * Using bounce buffer to bypass the * hardened user copy kernel text checks. */ - memcpy(buf, (char *) start, tsz); - n = copy_to_user(buffer, buf, tsz); - /* - * We cannot distinguish between fault on source - * and fault on destination. When this happens - * we clear too and hope it will trigger the - * EFAULT again. - */ - if (n) { - if (clear_user(buffer + tsz - n, - n)) + if (probe_kernel_read(buf, (void *) start, tsz)) { + if (clear_user(buffer, tsz)) + return -EFAULT; + } else { + if (copy_to_user(buffer, buf, tsz)) return -EFAULT; } } else { _ Patches currently in -mm which might be from heiko.carstens(a)de.ibm.com are

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [merged] kasan-dont-emit-builtin-calls-when-sanitization-is-off.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: kasan: don't emit builtin calls when sanitization is off has been removed from the -mm tree. Its filename was kasan-dont-emit-builtin-calls-when-sanitization-is-off.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Andrey Konovalov <andreyknvl(a)google.com> Subject: kasan: don't emit builtin calls when sanitization is off With KASAN enabled the kernel has two different memset() functions, one with KASAN checks (memset) and one without (__memset). KASAN uses some macro tricks to use the proper version where required. For example memset() calls in mm/slub.c are without KASAN checks, since they operate on poisoned slab object metadata. The issue is that clang emits memset() calls even when there is no memset() in the source code. They get linked with improper memset() implementation and the kernel fails to boot due to a huge amount of KASAN reports during early boot stages. The solution is to add -fno-builtin flag for files with KASAN_SANITIZE := n marker. Link: http://lkml.kernel.org/r/8ffecfffe04088c52c42b92739c2bd8a0bcb3f5e.151638459… Signed-off-by: Andrey Konovalov <andreyknvl(a)google.com> Acked-by: Nick Desaulniers <ndesaulniers(a)google.com> Cc: Masahiro Yamada <yamada.masahiro(a)socionext.com> Cc: Michal Marek <michal.lkml(a)markovi.net> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: Alexander Potapenko <glider(a)google.com> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- Makefile | 3 ++- scripts/Makefile.kasan | 3 +++ scripts/Makefile.lib | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) diff -puN Makefile~kasan-dont-emit-builtin-calls-when-sanitization-is-off Makefile --- a/Makefile~kasan-dont-emit-builtin-calls-when-sanitization-is-off +++ a/Makefile @@ -434,7 +434,8 @@ export MAKE LEX YACC AWK GENKSYMS INSTAL export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS -export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_KASAN CFLAGS_UBSAN +export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE +export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL diff -puN scripts/Makefile.kasan~kasan-dont-emit-builtin-calls-when-sanitization-is-off scripts/Makefile.kasan --- a/scripts/Makefile.kasan~kasan-dont-emit-builtin-calls-when-sanitization-is-off +++ a/scripts/Makefile.kasan @@ -31,4 +31,7 @@ else endif CFLAGS_KASAN += $(call cc-option, -fsanitize-address-use-after-scope) + +CFLAGS_KASAN_NOSANITIZE := -fno-builtin + endif diff -puN scripts/Makefile.lib~kasan-dont-emit-builtin-calls-when-sanitization-is-off scripts/Makefile.lib --- a/scripts/Makefile.lib~kasan-dont-emit-builtin-calls-when-sanitization-is-off +++ a/scripts/Makefile.lib @@ -121,7 +121,7 @@ endif ifeq ($(CONFIG_KASAN),y) _c_flags += $(if $(patsubst n%,, \ $(KASAN_SANITIZE_$(basetarget).o)$(KASAN_SANITIZE)y), \ - $(CFLAGS_KASAN)) + $(CFLAGS_KASAN), $(CFLAGS_KASAN_NOSANITIZE)) endif ifeq ($(CONFIG_UBSAN),y) _ Patches currently in -mm which might be from andreyknvl(a)google.com are

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] [PATCHES] Networking

by David Miller

Please queue up the following networking bug fixes for 4.9.x, 4.14.x, and 4.15.x -stable, respectively. Thanks!

7 years, 4 months

2
1
0 0

[Linux-stable-mirror] Patch "tcp: release sk_frag.page in tcp_disconnect" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled tcp: release sk_frag.page in tcp_disconnect to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: tcp-release-sk_frag.page-in-tcp_disconnect.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:38:15 PST 2018 From: Li RongQing <lirongqing(a)baidu.com> Date: Fri, 26 Jan 2018 16:40:41 +0800 Subject: tcp: release sk_frag.page in tcp_disconnect From: Li RongQing <lirongqing(a)baidu.com> [ Upstream commit 9b42d55a66d388e4dd5550107df051a9637564fc ] socket can be disconnected and gets transformed back to a listening socket, if sk_frag.page is not released, which will be cloned into a new socket by sk_clone_lock, but the reference count of this page is increased, lead to a use after free or double free issue Signed-off-by: Li RongQing <lirongqing(a)baidu.com> Cc: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/ipv4/tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2280,6 +2280,12 @@ int tcp_disconnect(struct sock *sk, int WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } Patches currently in stable-queue which might be from lirongqing(a)baidu.com are queue-3.18/tcp-release-sk_frag.page-in-tcp_disconnect.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "qlcnic: fix deadlock bug" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled qlcnic: fix deadlock bug to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: qlcnic-fix-deadlock-bug.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:38:15 PST 2018 From: Junxiao Bi <junxiao.bi(a)oracle.com> Date: Mon, 29 Jan 2018 17:53:42 +0800 Subject: qlcnic: fix deadlock bug From: Junxiao Bi <junxiao.bi(a)oracle.com> [ Upstream commit 233ac3891607f501f08879134d623b303838f478 ] The following soft lockup was caught. This is a deadlock caused by recusive locking. Process kworker/u40:1:28016 was holding spin lock "mbx->queue_lock" in qlcnic_83xx_mailbox_worker(), while a softirq came in and ask the same spin lock in qlcnic_83xx_enqueue_mbx_cmd(). This lock should be hold by disable bh.. [161846.962125] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/u40:1:28016] [161846.962367] Modules linked in: tun ocfs2 xen_netback xen_blkback xen_gntalloc xen_gntdev xen_evtchn xenfs xen_privcmd autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs bnx2fc fcoe libfcoe libfc sunrpc 8021q mrp garp bridge stp llc bonding dm_round_robin dm_multipath iTCO_wdt iTCO_vendor_support pcspkr sb_edac edac_core i2c_i801 shpchp lpc_ich mfd_core ioatdma ipmi_devintf ipmi_si ipmi_msghandler sg ext4 jbd2 mbcache2 sr_mod cdrom sd_mod igb i2c_algo_bit i2c_core ahci libahci megaraid_sas ixgbe dca ptp pps_core vxlan udp_tunnel ip6_udp_tunnel qla2xxx scsi_transport_fc qlcnic crc32c_intel be2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdio libiscsi_tcp qla4xxx iscsi_boot_sysfs libiscsi scsi_transport_iscsi dm_mirror dm_region_hash dm_log dm_mod [161846.962454] [161846.962460] CPU: 1 PID: 28016 Comm: kworker/u40:1 Not tainted 4.1.12-94.5.9.el6uek.x86_64 #2 [161846.962463] Hardware name: Oracle Corporation SUN SERVER X4-2L /ASSY,MB,X4-2L , BIOS 26050100 09/19/2017 [161846.962489] Workqueue: qlcnic_mailbox qlcnic_83xx_mailbox_worker [qlcnic] [161846.962493] task: ffff8801f2e34600 ti: ffff88004ca5c000 task.ti: ffff88004ca5c000 [161846.962496] RIP: e030:[<ffffffff810013aa>] [<ffffffff810013aa>] xen_hypercall_sched_op+0xa/0x20 [161846.962506] RSP: e02b:ffff880202e43388 EFLAGS: 00000206 [161846.962509] RAX: 0000000000000000 RBX: ffff8801f6996b70 RCX: ffffffff810013aa [161846.962511] RDX: ffff880202e433cc RSI: ffff880202e433b0 RDI: 0000000000000003 [161846.962513] RBP: ffff880202e433d0 R08: 0000000000000000 R09: ffff8801fe893200 [161846.962516] R10: ffff8801fe400538 R11: 0000000000000206 R12: ffff880202e4b000 [161846.962518] R13: 0000000000000050 R14: 0000000000000001 R15: 000000000000020d [161846.962528] FS: 0000000000000000(0000) GS:ffff880202e40000(0000) knlGS:ffff880202e40000 [161846.962531] CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 [161846.962533] CR2: 0000000002612640 CR3: 00000001bb796000 CR4: 0000000000042660 [161846.962536] Stack: [161846.962538] ffff880202e43608 0000000000000000 ffffffff813f0442 ffff880202e433b0 [161846.962543] 0000000000000000 ffff880202e433cc ffffffff00000001 0000000000000000 [161846.962547] 00000009813f03d6 ffff880202e433e0 ffffffff813f0460 ffff880202e43440 [161846.962552] Call Trace: [161846.962555] <IRQ> [161846.962565] [<ffffffff813f0442>] ? xen_poll_irq_timeout+0x42/0x50 [161846.962570] [<ffffffff813f0460>] xen_poll_irq+0x10/0x20 [161846.962578] [<ffffffff81014222>] xen_lock_spinning+0xe2/0x110 [161846.962583] [<ffffffff81013f01>] __raw_callee_save_xen_lock_spinning+0x11/0x20 [161846.962592] [<ffffffff816e5c57>] ? _raw_spin_lock+0x57/0x80 [161846.962609] [<ffffffffa028acfc>] qlcnic_83xx_enqueue_mbx_cmd+0x7c/0xe0 [qlcnic] [161846.962623] [<ffffffffa028e008>] qlcnic_83xx_issue_cmd+0x58/0x210 [qlcnic] [161846.962636] [<ffffffffa028caf2>] qlcnic_83xx_sre_macaddr_change+0x162/0x1d0 [qlcnic] [161846.962649] [<ffffffffa028cb8b>] qlcnic_83xx_change_l2_filter+0x2b/0x30 [qlcnic] [161846.962657] [<ffffffff8160248b>] ? __skb_flow_dissect+0x18b/0x650 [161846.962670] [<ffffffffa02856e5>] qlcnic_send_filter+0x205/0x250 [qlcnic] [161846.962682] [<ffffffffa0285c77>] qlcnic_xmit_frame+0x547/0x7b0 [qlcnic] [161846.962691] [<ffffffff8160ac22>] xmit_one+0x82/0x1a0 [161846.962696] [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0 [161846.962701] [<ffffffff81630112>] sch_direct_xmit+0x112/0x220 [161846.962706] [<ffffffff8160b80f>] __dev_queue_xmit+0x1df/0x5e0 [161846.962710] [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20 [161846.962721] [<ffffffffa0575bd5>] bond_dev_queue_xmit+0x35/0x80 [bonding] [161846.962729] [<ffffffffa05769fb>] __bond_start_xmit+0x1cb/0x210 [bonding] [161846.962736] [<ffffffffa0576a71>] bond_start_xmit+0x31/0x60 [bonding] [161846.962740] [<ffffffff8160ac22>] xmit_one+0x82/0x1a0 [161846.962745] [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0 [161846.962749] [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0 [161846.962754] [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20 [161846.962760] [<ffffffffa05cfa72>] vlan_dev_hard_start_xmit+0xb2/0x150 [8021q] [161846.962764] [<ffffffff8160ac22>] xmit_one+0x82/0x1a0 [161846.962769] [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0 [161846.962773] [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0 [161846.962777] [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20 [161846.962789] [<ffffffffa05adf74>] br_dev_queue_push_xmit+0x54/0xa0 [bridge] [161846.962797] [<ffffffffa05ae4ff>] br_forward_finish+0x2f/0x90 [bridge] [161846.962807] [<ffffffff810b0dad>] ? ttwu_do_wakeup+0x1d/0x100 [161846.962811] [<ffffffff815f929b>] ? __alloc_skb+0x8b/0x1f0 [161846.962818] [<ffffffffa05ae04d>] __br_forward+0x8d/0x120 [bridge] [161846.962822] [<ffffffff815f613b>] ? __kmalloc_reserve+0x3b/0xa0 [161846.962829] [<ffffffff810be55e>] ? update_rq_runnable_avg+0xee/0x230 [161846.962836] [<ffffffffa05ae176>] br_forward+0x96/0xb0 [bridge] [161846.962845] [<ffffffffa05af85e>] br_handle_frame_finish+0x1ae/0x420 [bridge] [161846.962853] [<ffffffffa05afc4f>] br_handle_frame+0x17f/0x260 [bridge] [161846.962862] [<ffffffffa05afad0>] ? br_handle_frame_finish+0x420/0x420 [bridge] [161846.962867] [<ffffffff8160d057>] __netif_receive_skb_core+0x1f7/0x870 [161846.962872] [<ffffffff8160d6f2>] __netif_receive_skb+0x22/0x70 [161846.962877] [<ffffffff8160d913>] netif_receive_skb_internal+0x23/0x90 [161846.962884] [<ffffffffa07512ea>] ? xenvif_idx_release+0xea/0x100 [xen_netback] [161846.962889] [<ffffffff816e5a10>] ? _raw_spin_unlock_irqrestore+0x20/0x50 [161846.962893] [<ffffffff8160e624>] netif_receive_skb_sk+0x24/0x90 [161846.962899] [<ffffffffa075269a>] xenvif_tx_submit+0x2ca/0x3f0 [xen_netback] [161846.962906] [<ffffffffa0753f0c>] xenvif_tx_action+0x9c/0xd0 [xen_netback] [161846.962915] [<ffffffffa07567f5>] xenvif_poll+0x35/0x70 [xen_netback] [161846.962920] [<ffffffff8160e01b>] napi_poll+0xcb/0x1e0 [161846.962925] [<ffffffff8160e1c0>] net_rx_action+0x90/0x1c0 [161846.962931] [<ffffffff8108aaba>] __do_softirq+0x10a/0x350 [161846.962938] [<ffffffff8108ae75>] irq_exit+0x125/0x130 [161846.962943] [<ffffffff813f03a9>] xen_evtchn_do_upcall+0x39/0x50 [161846.962950] [<ffffffff816e7ffe>] xen_do_hypervisor_callback+0x1e/0x40 [161846.962952] <EOI> [161846.962959] [<ffffffff816e5c4a>] ? _raw_spin_lock+0x4a/0x80 [161846.962964] [<ffffffff816e5b1e>] ? _raw_spin_lock_irqsave+0x1e/0xa0 [161846.962978] [<ffffffffa028e279>] ? qlcnic_83xx_mailbox_worker+0xb9/0x2a0 [qlcnic] [161846.962991] [<ffffffff810a14e1>] ? process_one_work+0x151/0x4b0 [161846.962995] [<ffffffff8100c3f2>] ? check_events+0x12/0x20 [161846.963001] [<ffffffff810a1960>] ? worker_thread+0x120/0x480 [161846.963005] [<ffffffff816e187b>] ? __schedule+0x30b/0x890 [161846.963010] [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0 [161846.963015] [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0 [161846.963021] [<ffffffff810a6b3e>] ? kthread+0xce/0xf0 [161846.963025] [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70 [161846.963031] [<ffffffff816e6522>] ? ret_from_fork+0x42/0x70 [161846.963035] [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70 [161846.963037] Code: cc 51 41 53 b8 1c 00 00 00 0f 05 41 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 51 41 53 b8 1d 00 00 00 0f 05 <41> 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc Signed-off-by: Junxiao Bi <junxiao.bi(a)oracle.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -3825,7 +3825,7 @@ static void qlcnic_83xx_flush_mbx_queue( struct list_head *head = &mbx->cmd_q; struct qlcnic_cmd_args *cmd = NULL; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); while (!list_empty(head)) { cmd = list_entry(head->next, struct qlcnic_cmd_args, list); @@ -3836,7 +3836,7 @@ static void qlcnic_83xx_flush_mbx_queue( qlcnic_83xx_notify_cmd_completion(adapter, cmd); } - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); } static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter) @@ -3872,12 +3872,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd( { struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_del(&cmd->list); mbx->num_cmds--; - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); qlcnic_83xx_notify_cmd_completion(adapter, cmd); } @@ -3942,7 +3942,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(s init_completion(&cmd->completion); cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN; - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); list_add_tail(&cmd->list, &mbx->cmd_q); mbx->num_cmds++; @@ -3950,7 +3950,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(s *timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT; queue_work(mbx->work_q, &mbx->work); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return 0; } @@ -4046,15 +4046,15 @@ static void qlcnic_83xx_mailbox_worker(s mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT; spin_unlock_irqrestore(&mbx->aen_lock, flags); - spin_lock(&mbx->queue_lock); + spin_lock_bh(&mbx->queue_lock); if (list_empty(head)) { - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); return; } cmd = list_entry(head->next, struct qlcnic_cmd_args, list); - spin_unlock(&mbx->queue_lock); + spin_unlock_bh(&mbx->queue_lock); mbx_ops->encode_cmd(adapter, cmd); mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST); Patches currently in stable-queue which might be from junxiao.bi(a)oracle.com are queue-3.18/qlcnic-fix-deadlock-bug.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "r8169: fix RTL8168EP take too long to complete driver initialization." has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled r8169: fix RTL8168EP take too long to complete driver initialization. to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: r8169-fix-rtl8168ep-take-too-long-to-complete-driver-initialization.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:38:15 PST 2018 From: Chunhao Lin <hau(a)realtek.com> Date: Wed, 31 Jan 2018 01:32:36 +0800 Subject: r8169: fix RTL8168EP take too long to complete driver initialization. From: Chunhao Lin <hau(a)realtek.com> [ Upstream commit 086ca23d03c0d2f4088f472386778d293e15c5f6 ] Driver check the wrong register bit in rtl_ocp_tx_cond() that keep driver waiting until timeout. Fix this by waiting for the right register bit. Signed-off-by: Chunhao Lin <hau(a)realtek.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/net/ethernet/realtek/r8169.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1375,7 +1375,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond) { void __iomem *ioaddr = tp->mmio_addr; - return RTL_R8(IBISR0) & 0x02; + return RTL_R8(IBISR0) & 0x20; } static void rtl8168dp_driver_start(struct rtl8169_private *tp) @@ -1421,7 +1421,7 @@ static void rtl8168ep_driver_stop(struct void __iomem *ioaddr = tp->mmio_addr; RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); - rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000); + rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP); Patches currently in stable-queue which might be from hau(a)realtek.com are queue-3.18/r8169-fix-rtl8168ep-take-too-long-to-complete-driver-initialization.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "net: igmp: add a missing rcu locking section" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled net: igmp: add a missing rcu locking section to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: net-igmp-add-a-missing-rcu-locking-section.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:38:15 PST 2018 From: Eric Dumazet <edumazet(a)google.com> Date: Thu, 1 Feb 2018 10:26:57 -0800 Subject: net: igmp: add a missing rcu locking section From: Eric Dumazet <edumazet(a)google.com> [ Upstream commit e7aadb27a5415e8125834b84a74477bfbee4eff5 ] Newly added igmpv3_get_srcaddr() needs to be called under rcu lock. Timer callbacks do not ensure this locking. ============================= WARNING: suspicious RCU usage 4.15.0+ #200 Not tainted ----------------------------- ./include/linux/inetdevice.h:216 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 3 locks held by syzkaller616973/4074: #0: (&mm->mmap_sem){++++}, at: [<00000000bfce669e>] __do_page_fault+0x32d/0xc90 arch/x86/mm/fault.c:1355 #1: ((&im->timer)){+.-.}, at: [<00000000619d2f71>] lockdep_copy_map include/linux/lockdep.h:178 [inline] #1: ((&im->timer)){+.-.}, at: [<00000000619d2f71>] call_timer_fn+0x1c6/0x820 kernel/time/timer.c:1316 #2: (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] spin_lock_bh include/linux/spinlock.h:315 [inline] #2: (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] igmpv3_send_report+0x98/0x5b0 net/ipv4/igmp.c:600 stack backtrace: CPU: 0 PID: 4074 Comm: syzkaller616973 Not tainted 4.15.0+ #200 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:53 lockdep_rcu_suspicious+0x123/0x170 kernel/locking/lockdep.c:4592 __in_dev_get_rcu include/linux/inetdevice.h:216 [inline] igmpv3_get_srcaddr net/ipv4/igmp.c:329 [inline] igmpv3_newpack+0xeef/0x12e0 net/ipv4/igmp.c:389 add_grhead.isra.27+0x235/0x300 net/ipv4/igmp.c:432 add_grec+0xbd3/0x1170 net/ipv4/igmp.c:565 igmpv3_send_report+0xd5/0x5b0 net/ipv4/igmp.c:605 igmp_send_report+0xc43/0x1050 net/ipv4/igmp.c:722 igmp_timer_expire+0x322/0x5c0 net/ipv4/igmp.c:831 call_timer_fn+0x228/0x820 kernel/time/timer.c:1326 expire_timers kernel/time/timer.c:1363 [inline] __run_timers+0x7ee/0xb70 kernel/time/timer.c:1666 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285 invoke_softirq kernel/softirq.c:365 [inline] irq_exit+0x1cc/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:541 [inline] smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052 apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:938 Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/ipv4/igmp.c | 4 ++++ 1 file changed, 4 insertions(+) --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -384,7 +384,11 @@ static struct sk_buff *igmpv3_newpack(st pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; + + rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); + rcu_read_unlock(); + pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(skb, NULL); Patches currently in stable-queue which might be from edumazet(a)google.com are queue-3.18/tcp-release-sk_frag.page-in-tcp_disconnect.patch queue-3.18/net-igmp-add-a-missing-rcu-locking-section.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "ip6mr: fix stale iterator" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled ip6mr: fix stale iterator to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: ip6mr-fix-stale-iterator.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:38:15 PST 2018 From: Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com> Date: Wed, 31 Jan 2018 16:29:30 +0200 Subject: ip6mr: fix stale iterator From: Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com> [ Upstream commit 4adfa79fc254efb7b0eb3cd58f62c2c3f805f1ba ] When we dump the ip6mr mfc entries via proc, we initialize an iterator with the table to dump but we don't clear the cache pointer which might be initialized from a prior read on the same descriptor that ended. This can result in lock imbalance (an unnecessary unlock) leading to other crashes and hangs. Clear the cache pointer like ipmr does to fix the issue. Thanks for the reliable reproducer. Here's syzbot's trace: WARNING: bad unlock balance detected! 4.15.0-rc3+ #128 Not tainted syzkaller971460/3195 is trying to release lock (mrt_lock) at: [<000000006898068d>] ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553 but there are no more locks to release! other info that might help us debug this: 1 lock held by syzkaller971460/3195: #0: (&p->lock){+.+.}, at: [<00000000744a6565>] seq_read+0xd5/0x13d0 fs/seq_file.c:165 stack backtrace: CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:53 print_unlock_imbalance_bug+0x12f/0x140 kernel/locking/lockdep.c:3561 __lock_release kernel/locking/lockdep.c:3775 [inline] lock_release+0x5f9/0xda0 kernel/locking/lockdep.c:4023 __raw_read_unlock include/linux/rwlock_api_smp.h:225 [inline] _raw_read_unlock+0x1a/0x30 kernel/locking/spinlock.c:255 ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553 traverse+0x3bc/0xa00 fs/seq_file.c:135 seq_read+0x96a/0x13d0 fs/seq_file.c:189 proc_reg_read+0xef/0x170 fs/proc/inode.c:217 do_loop_readv_writev fs/read_write.c:673 [inline] do_iter_read+0x3db/0x5b0 fs/read_write.c:897 compat_readv+0x1bf/0x270 fs/read_write.c:1140 do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189 C_SYSC_preadv fs/read_write.c:1209 [inline] compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203 do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline] do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389 entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125 RIP: 0023:0xf7f73c79 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 BUG: sleeping function called from invalid context at lib/usercopy.c:25 in_atomic(): 1, irqs_disabled(): 0, pid: 3195, name: syzkaller971460 INFO: lockdep is turned off. CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:53 ___might_sleep+0x2b2/0x470 kernel/sched/core.c:6060 __might_sleep+0x95/0x190 kernel/sched/core.c:6013 __might_fault+0xab/0x1d0 mm/memory.c:4525 _copy_to_user+0x2c/0xc0 lib/usercopy.c:25 copy_to_user include/linux/uaccess.h:155 [inline] seq_read+0xcb4/0x13d0 fs/seq_file.c:279 proc_reg_read+0xef/0x170 fs/proc/inode.c:217 do_loop_readv_writev fs/read_write.c:673 [inline] do_iter_read+0x3db/0x5b0 fs/read_write.c:897 compat_readv+0x1bf/0x270 fs/read_write.c:1140 do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189 C_SYSC_preadv fs/read_write.c:1209 [inline] compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203 do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline] do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389 entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125 RIP: 0023:0xf7f73c79 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 WARNING: CPU: 1 PID: 3195 at lib/usercopy.c:26 _copy_to_user+0xb5/0xc0 lib/usercopy.c:26 Reported-by: syzbot <bot+eceb3204562c41a438fa1f2335e0fe4f6886d669(a)syzkaller.appspotmail.com> Signed-off-by: Nikolay Aleksandrov <nikolay(a)cumulusnetworks.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/ipv6/ip6mr.c | 1 + 1 file changed, 1 insertion(+) --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -498,6 +498,7 @@ static void *ipmr_mfc_seq_start(struct s return ERR_PTR(-ENOENT); it->mrt = mrt; + it->cache = NULL; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } Patches currently in stable-queue which might be from nikolay(a)cumulusnetworks.com are queue-3.18/ip6mr-fix-stale-iterator.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "vhost_net: stop device during reset owner" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled vhost_net: stop device during reset owner to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: vhost_net-stop-device-during-reset-owner.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:22:35 PST 2018 From: Jason Wang <jasowang(a)redhat.com> Date: Thu, 25 Jan 2018 22:03:52 +0800 Subject: vhost_net: stop device during reset owner From: Jason Wang <jasowang(a)redhat.com> [ Upstream commit 4cd879515d686849eec5f718aeac62a70b067d82 ] We don't stop device before reset owner, this means we could try to serve any virtqueue kick before reset dev->worker. This will result a warn since the work was pending at llist during owner resetting. Fix this by stopping device during owner reset. Reported-by: syzbot+eb17c6162478cc50632c(a)syzkaller.appspotmail.com Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server") Signed-off-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/vhost/net.c | 1 + 1 file changed, 1 insertion(+) --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -981,6 +981,7 @@ static long vhost_net_reset_owner(struct } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, memory); vhost_net_vq_reset(n); done: Patches currently in stable-queue which might be from jasowang(a)redhat.com are queue-4.4/vhost_net-stop-device-during-reset-owner.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "vhost_net: stop device during reset owner" has been added to the 3.18-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled vhost_net: stop device during reset owner to the 3.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: vhost_net-stop-device-during-reset-owner.patch and it can be found in the queue-3.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:22:35 PST 2018 From: Jason Wang <jasowang(a)redhat.com> Date: Thu, 25 Jan 2018 22:03:52 +0800 Subject: vhost_net: stop device during reset owner From: Jason Wang <jasowang(a)redhat.com> [ Upstream commit 4cd879515d686849eec5f718aeac62a70b067d82 ] We don't stop device before reset owner, this means we could try to serve any virtqueue kick before reset dev->worker. This will result a warn since the work was pending at llist during owner resetting. Fix this by stopping device during owner reset. Reported-by: syzbot+eb17c6162478cc50632c(a)syzkaller.appspotmail.com Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server") Signed-off-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/vhost/net.c | 1 + 1 file changed, 1 insertion(+) --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1009,6 +1009,7 @@ static long vhost_net_reset_owner(struct } vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); + vhost_dev_stop(&n->dev); vhost_dev_reset_owner(&n->dev, memory); vhost_net_vq_reset(n); done: Patches currently in stable-queue which might be from jasowang(a)redhat.com are queue-3.18/vhost_net-stop-device-during-reset-owner.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "r8169: fix RTL8168EP take too long to complete driver initialization." has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled r8169: fix RTL8168EP take too long to complete driver initialization. to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: r8169-fix-rtl8168ep-take-too-long-to-complete-driver-initialization.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:22:35 PST 2018 From: Chunhao Lin <hau(a)realtek.com> Date: Wed, 31 Jan 2018 01:32:36 +0800 Subject: r8169: fix RTL8168EP take too long to complete driver initialization. From: Chunhao Lin <hau(a)realtek.com> [ Upstream commit 086ca23d03c0d2f4088f472386778d293e15c5f6 ] Driver check the wrong register bit in rtl_ocp_tx_cond() that keep driver waiting until timeout. Fix this by waiting for the right register bit. Signed-off-by: Chunhao Lin <hau(a)realtek.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/net/ethernet/realtek/r8169.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1387,7 +1387,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond) { void __iomem *ioaddr = tp->mmio_addr; - return RTL_R8(IBISR0) & 0x02; + return RTL_R8(IBISR0) & 0x20; } static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) @@ -1395,7 +1395,7 @@ static void rtl8168ep_stop_cmac(struct r void __iomem *ioaddr = tp->mmio_addr; RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01); - rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000); + rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000); RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20); RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01); } Patches currently in stable-queue which might be from hau(a)realtek.com are queue-4.4/r8169-fix-rtl8168ep-take-too-long-to-complete-driver-initialization.patch

7 years, 4 months

1
0
0 0

[Linux-stable-mirror] Patch "tcp: release sk_frag.page in tcp_disconnect" has been added to the 4.4-stable tree

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled tcp: release sk_frag.page in tcp_disconnect to the 4.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… The filename of the patch is: tcp-release-sk_frag.page-in-tcp_disconnect.patch and it can be found in the queue-4.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable(a)vger.kernel.org> know about it. >From foo@baz Wed Feb 7 11:22:35 PST 2018 From: Li RongQing <lirongqing(a)baidu.com> Date: Fri, 26 Jan 2018 16:40:41 +0800 Subject: tcp: release sk_frag.page in tcp_disconnect From: Li RongQing <lirongqing(a)baidu.com> [ Upstream commit 9b42d55a66d388e4dd5550107df051a9637564fc ] socket can be disconnected and gets transformed back to a listening socket, if sk_frag.page is not released, which will be cloned into a new socket by sk_clone_lock, but the reference count of this page is increased, lead to a use after free or double free issue Signed-off-by: Li RongQing <lirongqing(a)baidu.com> Cc: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- net/ipv4/tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2276,6 +2276,12 @@ int tcp_disconnect(struct sock *sk, int WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + } + sk->sk_error_report(sk); return err; } Patches currently in stable-queue which might be from lirongqing(a)baidu.com are queue-4.4/tcp-release-sk_frag.page-in-tcp_disconnect.patch

7 years, 4 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror