From: Siva Rebbagondla siva.rebbagondla@redpinesignals.com

[ Upstream commit 4c62764d0fc21a34ffc44eec1210038c3a2e4473 ]

While running regressions, observed below kernel panic when sdio disconnect called. This is because of, kthread_stop() is taking care of wait_for_completion() by default. When wait_for_completion triggered in kthread_stop and as it was done already, giving kernel panic. Hence, removing redundant wait_for_completion() from rsi_kill_thread().

... skipping ... BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff810a63df>] exit_creds+0x1f/0x50 PGD 0 Oops: 0002 [#1] SMP CPU: 0 PID: 6502 Comm: rmmod Tainted: G OE 4.15.9-Generic #154-Ubuntu Hardware name: Dell Inc. Edge Gateway 3003/ , BIOS 01.00.00 04/17/2017 Stack: ffff88007392e600 ffff880075847dc0 ffffffff8108160a 0000000000000000 ffff88007392e600 ffff880075847de8 ffffffff810a484b ffff880076127000 ffff88003cd3a800 ffff880074f12a00 ffff880075847e28 ffffffffc09bed15 Call Trace: [<ffffffff8108160a>] __put_task_struct+0x5a/0x140 [<ffffffff810a484b>] kthread_stop+0x10b/0x110 [<ffffffffc09bed15>] rsi_disconnect+0x2f5/0x300 [ven_rsi_sdio] [<ffffffff81578bcb>] ? __pm_runtime_resume+0x5b/0x80 [<ffffffff816f0918>] sdio_bus_remove+0x38/0x100 [<ffffffff8156cc64>] __device_release_driver+0xa4/0x150 [<ffffffff8156d7a5>] driver_detach+0xb5/0xc0 [<ffffffff8156c6c5>] bus_remove_driver+0x55/0xd0 [<ffffffff8156dfbc>] driver_unregister+0x2c/0x50 [<ffffffff816f0b8a>] sdio_unregister_driver+0x1a/0x20 [<ffffffffc09bf0f5>] rsi_module_exit+0x15/0x30 [ven_rsi_sdio] [<ffffffff8110cad8>] SyS_delete_module+0x1b8/0x210 [<ffffffff81851dc8>] entry_SYSCALL_64_fastpath+0x1c/0xbb

Signed-off-by: Siva Rebbagondla siva.rebbagondla@redpinesignals.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/rsi/rsi_common.h | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_common.h b/drivers/net/wireless/rsi/rsi_common.h index e579d694d13c..21986ba56a3c 100644 --- a/drivers/net/wireless/rsi/rsi_common.h +++ b/drivers/net/wireless/rsi/rsi_common.h @@ -74,7 +74,6 @@ static inline int rsi_kill_thread(struct rsi_thread *handle) atomic_inc(&handle->thread_done); rsi_set_event(&handle->event);

- wait_for_completion(&handle->completion); return kthread_stop(handle->task); }

From: Dinu-Razvan Chis-Serban justcsdr@gmail.com

[ Upstream commit 5e172f75e51e3de1b4274146d9b990f803cb5c2a ]

The default P9_LOCK_TIMEOUT can be too long for some users exporting a local file system to a guest VM (30s), make this configurable at mount time.

Link: http://lkml.kernel.org/r/1536295827-3181-1-git-send-email-asmadeus@codewreck... Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=195727 Signed-off-by: Dinu-Razvan Chis-Serban justcsdr@gmail.com Signed-off-by: Dominique Martinet dominique.martinet@cea.fr Signed-off-by: Sasha Levin sashal@kernel.org --- fs/9p/v9fs.c | 21 +++++++++++++++++++++ fs/9p/v9fs.h | 1 + fs/9p/vfs_file.c | 6 +++++- 3 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 8fb89ddc6cc7..c52f10efdc9c 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -61,6 +61,8 @@ enum { Opt_cache_loose, Opt_fscache, Opt_mmap, /* Access options */ Opt_access, Opt_posixacl, + /* Lock timeout option */ + Opt_locktimeout, /* Error token */ Opt_err }; @@ -80,6 +82,7 @@ static const match_table_t tokens = { {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, + {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} };

@@ -187,6 +190,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif + v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;

if (!opts) return 0; @@ -360,6 +364,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #endif break;

+ case Opt_locktimeout: + r = match_int(&args[0], &option); + if (r < 0) { + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } + if (option < 1) { + p9_debug(P9_DEBUG_ERROR, + "locktimeout must be a greater than zero integer.\n"); + ret = -EINVAL; + continue; + } + v9ses->session_lock_timeout = (long)option * HZ; + break; + default: continue; } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 982e017acadb..129e5243a6bf 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -116,6 +116,7 @@ struct v9fs_session_info { struct p9_client *clnt; /* 9p client */ struct list_head slist; /* list of sessions registered with v9fs */ struct rw_semaphore rename_sem; + long session_lock_timeout; /* retry interval for blocking locks */ };

/* cache_validity flags */ diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index af8cac975a74..89e69904976a 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) uint8_t status = P9_LOCK_ERROR; int res = 0; unsigned char fl_type; + struct v9fs_session_info *v9ses;

fid = filp->private_data; BUG_ON(fid == NULL); @@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if (IS_SETLKW(cmd)) flock.flags = P9_LOCK_FLAGS_BLOCK;

+ v9ses = v9fs_inode2v9ses(file_inode(filp)); + /* * if its a blocked request and we get P9_LOCK_BLOCKED as the status * for lock request, keep on trying @@ -202,7 +205,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) break; - if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) + if (schedule_timeout_interruptible(v9ses->session_lock_timeout) + != 0) break; /* * p9_client_lock_dotl overwrites flock.client_id with the

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 0d704967f4a49cc2212350b3e4a8231f8b4283ed ]

cgroup v2 path field is PATH_MAX which is too large, this is placing too much pressure on memory allocation for people with many rules doing cgroup v1 classid matching, side effects of this are bug reports like:

https://bugzilla.kernel.org/show_bug.cgi?id=200639

This patch registers a new revision that shrinks the cgroup path to 512 bytes, which is the same approach we follow in similar extensions that have a path field.

Cc: Tejun Heo tj@kernel.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Acked-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/uapi/linux/netfilter/xt_cgroup.h | 16 ++++++ net/netfilter/xt_cgroup.c | 72 ++++++++++++++++++++++++ 2 files changed, 88 insertions(+)

diff --git a/include/uapi/linux/netfilter/xt_cgroup.h b/include/uapi/linux/netfilter/xt_cgroup.h index e96dfa1b34f7..b74e370d6133 100644 --- a/include/uapi/linux/netfilter/xt_cgroup.h +++ b/include/uapi/linux/netfilter/xt_cgroup.h @@ -22,4 +22,20 @@ struct xt_cgroup_info_v1 { void *priv __attribute__((aligned(8))); };

+#define XT_CGROUP_PATH_MAX 512 + +struct xt_cgroup_info_v2 { + __u8 has_path; + __u8 has_classid; + __u8 invert_path; + __u8 invert_classid; + union { + char path[XT_CGROUP_PATH_MAX]; + __u32 classid; + }; + + /* kernel internal data */ + void *priv __attribute__((aligned(8))); +}; + #endif /* _UAPI_XT_CGROUP_H */ diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 891f4e7e8ea7..db18c0177b0f 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -66,6 +66,38 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) return 0; }

+static int cgroup_mt_check_v2(const struct xt_mtchk_param *par) +{ + struct xt_cgroup_info_v2 *info = par->matchinfo; + struct cgroup *cgrp; + + if ((info->invert_path & ~1) || (info->invert_classid & ~1)) + return -EINVAL; + + if (!info->has_path && !info->has_classid) { + pr_info("xt_cgroup: no path or classid specified\n"); + return -EINVAL; + } + + if (info->has_path && info->has_classid) { + pr_info_ratelimited("path and classid specified\n"); + return -EINVAL; + } + + info->priv = NULL; + if (info->has_path) { + cgrp = cgroup_get_from_path(info->path); + if (IS_ERR(cgrp)) { + pr_info_ratelimited("invalid path, errno=%ld\n", + PTR_ERR(cgrp)); + return -EINVAL; + } + info->priv = cgrp; + } + + return 0; +} + static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { @@ -95,6 +127,24 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) info->invert_classid; }

+static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_cgroup_info_v2 *info = par->matchinfo; + struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; + struct cgroup *ancestor = info->priv; + struct sock *sk = skb->sk; + + if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) + return false; + + if (ancestor) + return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ + info->invert_path; + else + return (info->classid == sock_cgroup_classid(skcd)) ^ + info->invert_classid; +} + static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; @@ -103,6 +153,14 @@ static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) cgroup_put(info->priv); }

+static void cgroup_mt_destroy_v2(const struct xt_mtdtor_param *par) +{ + struct xt_cgroup_info_v2 *info = par->matchinfo; + + if (info->priv) + cgroup_put(info->priv); +} + static struct xt_match cgroup_mt_reg[] __read_mostly = { { .name = "cgroup", @@ -130,6 +188,20 @@ static struct xt_match cgroup_mt_reg[] __read_mostly = { (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, + { + .name = "cgroup", + .revision = 2, + .family = NFPROTO_UNSPEC, + .checkentry = cgroup_mt_check_v2, + .match = cgroup_mt_v2, + .matchsize = sizeof(struct xt_cgroup_info_v2), + .usersize = offsetof(struct xt_cgroup_info_v2, priv), + .destroy = cgroup_mt_destroy_v2, + .me = THIS_MODULE, + .hooks = (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + }, };

static int __init cgroup_mt_init(void)

From: Nathan Fontenot nfont@linux.vnet.ibm.com

[ Upstream commit cd24e457fd8b2d087d9236700c8d2957054598bf ]

When a PRRN event is received we are already running in a worker thread. Instead of spawning off another worker thread on the prrn_work workqueue to handle the PRRN event we can just call the PRRN handler routine directly.

With this update we can also pass the scope variable for the PRRN event directly to the handler instead of it being a global variable.

This patch fixes the following oops mnessage we are seeing in PRRN testing:

Oops: Bad kernel stack pointer, sig: 6 [#1] SMP NR_CPUS=2048 NUMA pSeries Modules linked in: nfsv3 nfs_acl rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace sunrpc fscache binfmt_misc reiserfs vfat fat rpadlpar_io(X) rpaphp(X) tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag af_packet xfs libcrc32c dm_service_time ibmveth(X) ses enclosure scsi_transport_sas rtc_generic btrfs xor raid6_pq sd_mod ibmvscsi(X) scsi_transport_srp ipr(X) libata sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua scsi_mod autofs4 Supported: Yes, External 54 CPU: 7 PID: 18967 Comm: kworker/u96:0 Tainted: G X 4.4.126-94.22-default #1 Workqueue: pseries hotplug workque pseries_hp_work_fn task: c000000775367790 ti: c00000001ebd4000 task.ti: c00000070d140000 NIP: 0000000000000000 LR: 000000001fb3d050 CTR: 0000000000000000 REGS: c00000001ebd7d40 TRAP: 0700 Tainted: G X (4.4.126-94.22-default) MSR: 8000000102081000 <41,VEC,ME5 CR: 28000002 XER: 20040018 4 CFAR: 000000001fb3d084 40 419 1 3 GPR00: 000000000000000040000000000010007 000000001ffff400 000000041fffe200 GPR04: 000000000000008050000000000000000 000000001fb15fa8 0000000500000500 GPR08: 000000000001f40040000000000000001 0000000000000000 000005:5200040002 GPR12: 00000000000000005c000000007a05400 c0000000000e89f8 000000001ed9f668 GPR16: 000000001fbeff944000000001fbeff94 000000001fb545e4 0000006000000060 GPR20: ffffffffffffffff4ffffffffffffffff 0000000000000000 0000000000000000 GPR24: 00000000000000005400000001fb3c000 0000000000000000 000000001fb1b040 GPR28: 000000001fb240004000000001fb440d8 0000000000000008 0000000000000000 NIP [0000000000000000] 5 (null) LR [000000001fb3d050] 031fb3d050 Call Trace: 4 Instruction dump: 4 5:47 12 2 XXXXXXXX XXXXXXXX XXXXX4XX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXX5XX XXXXXXXX 60000000 60000000 60000000 60000000 ---[ end trace aa5627b04a7d9d6b ]--- 3NMI watchdog: BUG: soft lockup - CPU#27 stuck for 23s! [kworker/27:0:13903] Modules linked in: nfsv3 nfs_acl rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace sunrpc fscache binfmt_misc reiserfs vfat fat rpadlpar_io(X) rpaphp(X) tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag af_packet xfs libcrc32c dm_service_time ibmveth(X) ses enclosure scsi_transport_sas rtc_generic btrfs xor raid6_pq sd_mod ibmvscsi(X) scsi_transport_srp ipr(X) libata sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua scsi_mod autofs4 Supported: Yes, External CPU: 27 PID: 13903 Comm: kworker/27:0 Tainted: G D X 4.4.126-94.22-default #1 Workqueue: events prrn_work_fn task: c000000747cfa390 ti: c00000074712c000 task.ti: c00000074712c000 NIP: c0000000008002a8 LR: c000000000090770 CTR: 000000000032e088 REGS: c00000074712f7b0 TRAP: 0901 Tainted: G D X (4.4.126-94.22-default) MSR: 8000000100009033 <SF,EE,ME,IR,DR,RI,LE> CR: 22482044 XER: 20040000 CFAR: c0000000008002c4 SOFTE: 1 GPR00: c000000000090770 c00000074712fa30 c000000000f09800 c000000000fa1928 6:02 GPR04: c000000775f5e000 fffffffffffffffe 0000000000000001 c000000000f42db8 GPR08: 0000000000000001 0000000080000007 0000000000000000 0000000000000000 GPR12: 8006210083180000 c000000007a14400 NIP [c0000000008002a8] _raw_spin_lock+0x68/0xd0 LR [c000000000090770] mobility_rtas_call+0x50/0x100 Call Trace: 59 5 [c00000074712fa60] [c000000000090770] mobility_rtas_call+0x50/0x100 [c00000074712faf0] [c000000000090b08] pseries_devicetree_update+0xf8/0x530 [c00000074712fc20] [c000000000031ba4] prrn_work_fn+0x34/0x50 [c00000074712fc40] [c0000000000e0390] process_one_work+0x1a0/0x4e0 [c00000074712fcd0] [c0000000000e0870] worker_thread+0x1a0/0x6105:57 2 [c00000074712fd80] [c0000000000e8b18] kthread+0x128/0x150 [c00000074712fe30] [c0000000000096f8] ret_from_kernel_thread+0x5c/0x64 Instruction dump: 2c090000 40c20010 7d40192d 40c2fff0 7c2004ac 2fa90000 40de0018 5:540030 3 e8010010 ebe1fff8 7c0803a6 4e800020 <7c210b78> e92d0000 89290009 792affe3

Signed-off-by: John Allen jallen@linux.ibm.com Signed-off-by: Haren Myneni haren@us.ibm.com Signed-off-by: Nathan Fontenot nfont@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/rtasd.c | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 0f0b1b2f3b60..7caeae73348d 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -274,27 +274,16 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) }

#ifdef CONFIG_PPC_PSERIES -static s32 prrn_update_scope; - -static void prrn_work_fn(struct work_struct *work) +static void handle_prrn_event(s32 scope) { /* * For PRRN, we must pass the negative of the scope value in * the RTAS event. */ - pseries_devicetree_update(-prrn_update_scope); + pseries_devicetree_update(-scope); numa_update_cpu_topology(false); }

-static DECLARE_WORK(prrn_work, prrn_work_fn); - -static void prrn_schedule_update(u32 scope) -{ - flush_work(&prrn_work); - prrn_update_scope = scope; - schedule_work(&prrn_work); -} - static void handle_rtas_event(const struct rtas_error_log *log) { if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled()) @@ -303,7 +292,7 @@ static void handle_rtas_event(const struct rtas_error_log *log) /* For PRRN Events the extended log length is used to denote * the scope for calling rtas update-nodes. */ - prrn_schedule_update(rtas_error_extended_log_length(log)); + handle_prrn_event(rtas_error_extended_log_length(log)); }

#else

From: Julian Sax jsbc@gmx.de

[ Upstream commit 9ee3e06610fdb8a601cde59c92089fb6c1deb4aa ]

A particular touchpad (SIPODEV SP1064) refuses to supply the HID descriptors. This patch provides the framework for overriding these descriptors based on DMI data. It also includes the descriptors for said touchpad, which were extracted by listening to the traffic of the windows filter driver, as well as the DMI data for the laptops known to use this device.

Relevant Bug: https://bugzilla.redhat.com/show_bug.cgi?id=1526312

Cc: Hans de Goede hdegoede@redhat.com Reported-and-tested-by: ahormann@gmx.net Reported-and-tested-by: Bruno Jesus bruno.fl.jesus@gmail.com Reported-and-tested-by: Dietrich enaut.w@googlemail.com Reported-and-tested-by: kloxdami@yahoo.com Signed-off-by: Julian Sax jsbc@gmx.de Reviewed-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/i2c-hid/Makefile | 3 + .../hid/i2c-hid/{i2c-hid.c => i2c-hid-core.c} | 56 ++- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 376 ++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid.h | 20 + 4 files changed, 437 insertions(+), 18 deletions(-) rename drivers/hid/i2c-hid/{i2c-hid.c => i2c-hid-core.c} (96%) create mode 100644 drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c create mode 100644 drivers/hid/i2c-hid/i2c-hid.h

diff --git a/drivers/hid/i2c-hid/Makefile b/drivers/hid/i2c-hid/Makefile index 832d8f9aaba2..099e1ce2f234 100644 --- a/drivers/hid/i2c-hid/Makefile +++ b/drivers/hid/i2c-hid/Makefile @@ -3,3 +3,6 @@ #

obj-$(CONFIG_I2C_HID) += i2c-hid.o + +i2c-hid-objs = i2c-hid-core.o +i2c-hid-$(CONFIG_DMI) += i2c-hid-dmi-quirks.o diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid-core.c similarity index 96% rename from drivers/hid/i2c-hid/i2c-hid.c rename to drivers/hid/i2c-hid/i2c-hid-core.c index 136a34dc31b8..7842d76aa813 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -43,6 +43,7 @@ #include <linux/platform_data/i2c-hid.h>

#include "../hid-ids.h" +#include "i2c-hid.h"

/* quirks to control the device */ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) @@ -663,6 +664,7 @@ static int i2c_hid_parse(struct hid_device *hid) char *rdesc; int ret; int tries = 3; + char *use_override;

i2c_hid_dbg(ihid, "entering %s\n", __func__);

@@ -681,26 +683,37 @@ static int i2c_hid_parse(struct hid_device *hid) if (ret) return ret;

- rdesc = kzalloc(rsize, GFP_KERNEL); + use_override = i2c_hid_get_dmi_hid_report_desc_override(client->name, + &rsize);

- if (!rdesc) { - dbg_hid("couldn't allocate rdesc memory\n"); - return -ENOMEM; - } + if (use_override) { + rdesc = use_override; + i2c_hid_dbg(ihid, "Using a HID report descriptor override\n"); + } else { + rdesc = kzalloc(rsize, GFP_KERNEL);

- i2c_hid_dbg(ihid, "asking HID report descriptor\n"); + if (!rdesc) { + dbg_hid("couldn't allocate rdesc memory\n"); + return -ENOMEM; + }

- ret = i2c_hid_command(client, &hid_report_descr_cmd, rdesc, rsize); - if (ret) { - hid_err(hid, "reading report descriptor failed\n"); - kfree(rdesc); - return -EIO; + i2c_hid_dbg(ihid, "asking HID report descriptor\n"); + + ret = i2c_hid_command(client, &hid_report_descr_cmd, + rdesc, rsize); + if (ret) { + hid_err(hid, "reading report descriptor failed\n"); + kfree(rdesc); + return -EIO; + } }

i2c_hid_dbg(ihid, "Report Descriptor: %*ph\n", rsize, rdesc);

ret = hid_parse_report(hid, rdesc, rsize); - kfree(rdesc); + if (!use_override) + kfree(rdesc); + if (ret) { dbg_hid("parsing report descriptor failed\n"); return ret; @@ -827,12 +840,19 @@ static int i2c_hid_fetch_hid_descriptor(struct i2c_hid *ihid) int ret;

/* i2c hid fetch using a fixed descriptor size (30 bytes) */ - i2c_hid_dbg(ihid, "Fetching the HID descriptor\n"); - ret = i2c_hid_command(client, &hid_descr_cmd, ihid->hdesc_buffer, - sizeof(struct i2c_hid_desc)); - if (ret) { - dev_err(&client->dev, "hid_descr_cmd failed\n"); - return -ENODEV; + if (i2c_hid_get_dmi_i2c_hid_desc_override(client->name)) { + i2c_hid_dbg(ihid, "Using a HID descriptor override\n"); + ihid->hdesc = + *i2c_hid_get_dmi_i2c_hid_desc_override(client->name); + } else { + i2c_hid_dbg(ihid, "Fetching the HID descriptor\n"); + ret = i2c_hid_command(client, &hid_descr_cmd, + ihid->hdesc_buffer, + sizeof(struct i2c_hid_desc)); + if (ret) { + dev_err(&client->dev, "hid_descr_cmd failed\n"); + return -ENODEV; + } }

/* Validate the length of HID descriptor, the 4 first bytes: diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c new file mode 100644 index 000000000000..1d645c9ab417 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0+ + +/* + * Quirks for I2C-HID devices that do not supply proper descriptors + * + * Copyright (c) 2018 Julian Sax jsbc@gmx.de + * + */ + +#include <linux/types.h> +#include <linux/dmi.h> +#include <linux/mod_devicetable.h> + +#include "i2c-hid.h" + + +struct i2c_hid_desc_override { + union { + struct i2c_hid_desc *i2c_hid_desc; + uint8_t *i2c_hid_desc_buffer; + }; + uint8_t *hid_report_desc; + unsigned int hid_report_desc_size; + uint8_t *i2c_name; +}; + + +/* + * descriptors for the SIPODEV SP1064 touchpad + * + * This device does not supply any descriptors and on windows a filter + * driver operates between the i2c-hid layer and the device and injects + * these descriptors when the device is prompted. The descriptors were + * extracted by listening to the i2c-hid traffic that occurs between the + * windows filter driver and the windows i2c-hid driver. + */ + +static const struct i2c_hid_desc_override sipodev_desc = { + .i2c_hid_desc_buffer = (uint8_t []) + {0x1e, 0x00, /* Length of descriptor */ + 0x00, 0x01, /* Version of descriptor */ + 0xdb, 0x01, /* Length of report descriptor */ + 0x21, 0x00, /* Location of report descriptor */ + 0x24, 0x00, /* Location of input report */ + 0x1b, 0x00, /* Max input report length */ + 0x25, 0x00, /* Location of output report */ + 0x11, 0x00, /* Max output report length */ + 0x22, 0x00, /* Location of command register */ + 0x23, 0x00, /* Location of data register */ + 0x11, 0x09, /* Vendor ID */ + 0x88, 0x52, /* Product ID */ + 0x06, 0x00, /* Version ID */ + 0x00, 0x00, 0x00, 0x00 /* Reserved */ + }, + + .hid_report_desc = (uint8_t []) + {0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x02, /* Usage (Mouse), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x01, /* Report ID (1), */ + 0x09, 0x01, /* Usage (Pointer), */ + 0xA1, 0x00, /* Collection (Physical), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x19, 0x01, /* Usage Minimum (01h), */ + 0x29, 0x02, /* Usage Maximum (02h), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x06, /* Report Count (6), */ + 0x81, 0x01, /* Input (Constant), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x09, 0x30, /* Usage (X), */ + 0x09, 0x31, /* Usage (Y), */ + 0x15, 0x81, /* Logical Minimum (-127), */ + 0x25, 0x7F, /* Logical Maximum (127), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0x81, 0x06, /* Input (Variable, Relative), */ + 0xC0, /* End Collection, */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x05, /* Usage (Touchpad), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x04, /* Report ID (4), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x15, 0x00, /* Logical Minimum (0), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x55, 0x0E, /* Unit Exponent (14), */ + 0x65, 0x11, /* Unit (Centimeter), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x09, 0x47, /* Usage (Touch Valid), */ + 0x09, 0x42, /* Usage (Tip Switch), */ + 0x95, 0x02, /* Report Count (2), */ + 0x75, 0x01, /* Report Size (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x01, /* Report Count (1), */ + 0x75, 0x03, /* Report Size (3), */ + 0x25, 0x05, /* Logical Maximum (5), */ + 0x09, 0x51, /* Usage (Contact Identifier), */ + 0x81, 0x02, /* Input (Variable), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x03, /* Report Count (3), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x01, /* Usage Page (Desktop), */ + 0x26, 0x44, 0x0A, /* Logical Maximum (2628), */ + 0x75, 0x10, /* Report Size (16), */ + 0x09, 0x30, /* Usage (X), */ + 0x46, 0x1A, 0x04, /* Physical Maximum (1050), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x46, 0xBC, 0x02, /* Physical Maximum (700), */ + 0x26, 0x34, 0x05, /* Logical Maximum (1332), */ + 0x09, 0x31, /* Usage (Y), */ + 0x81, 0x02, /* Input (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x55, 0x0C, /* Unit Exponent (12), */ + 0x66, 0x01, 0x10, /* Unit (Seconds), */ + 0x47, 0xFF, 0xFF, 0x00, 0x00,/* Physical Maximum (65535), */ + 0x27, 0xFF, 0xFF, 0x00, 0x00,/* Logical Maximum (65535), */ + 0x75, 0x10, /* Report Size (16), */ + 0x95, 0x01, /* Report Count (1), */ + 0x09, 0x56, /* Usage (Scan Time), */ + 0x81, 0x02, /* Input (Variable), */ + 0x09, 0x54, /* Usage (Contact Count), */ + 0x25, 0x7F, /* Logical Maximum (127), */ + 0x75, 0x08, /* Report Size (8), */ + 0x81, 0x02, /* Input (Variable), */ + 0x05, 0x09, /* Usage Page (Button), */ + 0x09, 0x01, /* Usage (01h), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x01, /* Report Count (1), */ + 0x81, 0x02, /* Input (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0x81, 0x03, /* Input (Constant, Variable), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x85, 0x02, /* Report ID (2), */ + 0x09, 0x55, /* Usage (Contact Count Maximum), */ + 0x09, 0x59, /* Usage (59h), */ + 0x75, 0x04, /* Report Size (4), */ + 0x95, 0x02, /* Report Count (2), */ + 0x25, 0x0F, /* Logical Maximum (15), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x85, 0x07, /* Report ID (7), */ + 0x09, 0x60, /* Usage (60h), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x01, /* Report Count (1), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x95, 0x07, /* Report Count (7), */ + 0xB1, 0x03, /* Feature (Constant, Variable), */ + 0x85, 0x06, /* Report ID (6), */ + 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ + 0x09, 0xC5, /* Usage (C5h), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x75, 0x08, /* Report Size (8), */ + 0x96, 0x00, 0x01, /* Report Count (256), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x06, 0x00, 0xFF, /* Usage Page (FF00h), */ + 0x09, 0x01, /* Usage (01h), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x0D, /* Report ID (13), */ + 0x26, 0xFF, 0x00, /* Logical Maximum (255), */ + 0x19, 0x01, /* Usage Minimum (01h), */ + 0x29, 0x02, /* Usage Maximum (02h), */ + 0x75, 0x08, /* Report Size (8), */ + 0x95, 0x02, /* Report Count (2), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x05, 0x0D, /* Usage Page (Digitizer), */ + 0x09, 0x0E, /* Usage (Configuration), */ + 0xA1, 0x01, /* Collection (Application), */ + 0x85, 0x03, /* Report ID (3), */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x02, /* Collection (Logical), */ + 0x09, 0x52, /* Usage (Device Mode), */ + 0x25, 0x0A, /* Logical Maximum (10), */ + 0x95, 0x01, /* Report Count (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0xC0, /* End Collection, */ + 0x09, 0x22, /* Usage (Finger), */ + 0xA1, 0x00, /* Collection (Physical), */ + 0x85, 0x05, /* Report ID (5), */ + 0x09, 0x57, /* Usage (57h), */ + 0x09, 0x58, /* Usage (58h), */ + 0x75, 0x01, /* Report Size (1), */ + 0x95, 0x02, /* Report Count (2), */ + 0x25, 0x01, /* Logical Maximum (1), */ + 0xB1, 0x02, /* Feature (Variable), */ + 0x95, 0x06, /* Report Count (6), */ + 0xB1, 0x03, /* Feature (Constant, Variable),*/ + 0xC0, /* End Collection, */ + 0xC0 /* End Collection */ + }, + .hid_report_desc_size = 475, + .i2c_name = "SYNA3602:00" +}; + + +static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { + { + .ident = "Teclast F6 Pro", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "F6 Pro"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Teclast F7", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "F7"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Trekstor Primebook C13", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C13"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Trekstor Primebook C11", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C11"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Direkt-Tek DTLAPY116-2", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY116-2"), + }, + .driver_data = (void *)&sipodev_desc + }, + { + .ident = "Mediacom Flexbook Edge 11", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "FlexBook edge11 - M-FBE11"), + }, + .driver_data = (void *)&sipodev_desc + } +}; + + +struct i2c_hid_desc *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name) +{ + struct i2c_hid_desc_override *override; + const struct dmi_system_id *system_id; + + system_id = dmi_first_match(i2c_hid_dmi_desc_override_table); + if (!system_id) + return NULL; + + override = system_id->driver_data; + if (strcmp(override->i2c_name, i2c_name)) + return NULL; + + return override->i2c_hid_desc; +} + +char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size) +{ + struct i2c_hid_desc_override *override; + const struct dmi_system_id *system_id; + + system_id = dmi_first_match(i2c_hid_dmi_desc_override_table); + if (!system_id) + return NULL; + + override = system_id->driver_data; + if (strcmp(override->i2c_name, i2c_name)) + return NULL; + + *size = override->hid_report_desc_size; + return override->hid_report_desc; +} diff --git a/drivers/hid/i2c-hid/i2c-hid.h b/drivers/hid/i2c-hid/i2c-hid.h new file mode 100644 index 000000000000..a8c19aef5824 --- /dev/null +++ b/drivers/hid/i2c-hid/i2c-hid.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef I2C_HID_H +#define I2C_HID_H + + +#ifdef CONFIG_DMI +struct i2c_hid_desc *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name); +char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size); +#else +static inline struct i2c_hid_desc + *i2c_hid_get_dmi_i2c_hid_desc_override(uint8_t *i2c_name) +{ return NULL; } +static inline char *i2c_hid_get_dmi_hid_report_desc_override(uint8_t *i2c_name, + unsigned int *size) +{ return NULL; } +#endif + +#endif

From: Maciej Żenczykowski maze@google.com

[ Upstream commit e0a2e73e501c77037c8756137e87b12c7c3c9793 ]

Without this usbip fails on a machine with devices that lexicographically come after vhci_hcd.

ie. $ ls -l /sys/devices/platform ... drwxr-xr-x. 4 root root 0 Sep 19 16:21 serial8250 -rw-r--r--. 1 root root 4096 Sep 19 23:50 uevent drwxr-xr-x. 6 root root 0 Sep 20 13:15 vhci_hcd.0 drwxr-xr-x. 4 root root 0 Sep 19 16:22 w83627hf.656

Because it detects 'w83627hf.656' as another vhci_hcd controller, and then fails to be able to talk to it.

Note: this doesn't actually fix usbip's support for multiple controllers... that's still broken for other reasons ("vhci_hcd.0" is hardcoded in a string macro), but is enough to actually make it work on the above machine.

See also: https://bugzilla.redhat.com/show_bug.cgi?id=1631148

Cc: Jonathan Dieter jdieter@gmail.com Cc: Valentina Manea valentina.manea.m@gmail.com Cc: Shuah Khan shuah@kernel.org Cc: linux-usb@vger.kernel.org Signed-off-by: Maciej Żenczykowski zenczykowski@gmail.com Acked-by: Shuah Khan (Samsung OSG) shuah@kernel.org Tested-by: Jonathan Dieter jdieter@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/usb/usbip/libsrc/vhci_driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index ed8c9d360c0f..4225d462701d 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -150,7 +150,7 @@ static int get_nports(struct udev_device *hc_device)

static int vhci_hcd_filter(const struct dirent *dirent) { - return strcmp(dirent->d_name, "vhci_hcd") >= 0; + return !strncmp(dirent->d_name, "vhci_hcd.", 9); }

static int get_ncontrollers(void)

From: Sean Christopherson sean.j.christopherson@intel.com

[ Upstream commit bd18bffca35397214ae68d85cf7203aca25c3c1d ]

A VMEnter that VMFails (as opposed to VMExits) does not touch host state beyond registers that are explicitly noted in the VMFail path, e.g. EFLAGS. Host state does not need to be loaded because VMFail is only signaled for consistency checks that occur before the CPU starts to load guest state, i.e. there is no need to restore any state as nothing has been modified. But in the case where a VMFail is detected by hardware and not by KVM (due to deferring consistency checks to hardware), KVM has already loaded some amount of guest state. Luckily, "loaded" only means loaded to KVM's software model, i.e. vmcs01 has not been modified. So, unwind our software model to the pre-VMEntry host state.

Not restoring host state in this VMFail path leads to a variety of failures because we end up with stale data in vcpu->arch, e.g. CR0, CR4, EFER, etc... will all be out of sync relative to vmcs01. Any significant delta in the stale data is all but guaranteed to crash L1, e.g. emulation of SMEP, SMAP, UMIP, WP, etc... will be wrong.

An alternative to this "soft" reload would be to load host state from vmcs12 as if we triggered a VMExit (as opposed to VMFail), but that is wildly inconsistent with respect to the VMX architecture, e.g. an L1 VMM with separate VMExit and VMFail paths would explode.

Note that this approach does not mean KVM is 100% accurate with respect to VMX hardware behavior, even at an architectural level (the exact order of consistency checks is microarchitecture specific). But 100% emulation accuracy isn't the goal (with this patch), rather the goal is to be consistent in the information delivered to L1, e.g. a VMExit should not fall-through VMENTER, and a VMFail should not jump to HOST_RIP.

This technically reverts commit "5af4157388ad (KVM: nVMX: Fix mmu context after VMLAUNCH/VMRESUME failure)", but retains the core aspects of that patch, just in an open coded form due to the need to pull state from vmcs01 instead of vmcs12. Restoring host state resolves a variety of issues introduced by commit "4f350c6dbcb9 (kvm: nVMX: Handle deferred early VMLAUNCH/VMRESUME failure properly)", which remedied the incorrect behavior of treating VMFail like VMExit but in doing so neglected to restore arch state that had been modified prior to attempting nested VMEnter.

A sample failure that occurs due to stale vcpu.arch state is a fault of some form while emulating an LGDT (due to emulated UMIP) from L1 after a failed VMEntry to L3, in this case when running the KVM unit test test_tpr_threshold_values in L1. L0 also hits a WARN in this case due to a stale arch.cr4.UMIP.

L1: BUG: unable to handle kernel paging request at ffffc90000663b9e PGD 276512067 P4D 276512067 PUD 276513067 PMD 274efa067 PTE 8000000271de2163 Oops: 0009 [#1] SMP CPU: 5 PID: 12495 Comm: qemu-system-x86 Tainted: G W 4.18.0-rc2+ #2 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:native_load_gdt+0x0/0x10

...

Call Trace: load_fixmap_gdt+0x22/0x30 __vmx_load_host_state+0x10e/0x1c0 [kvm_intel] vmx_switch_vmcs+0x2d/0x50 [kvm_intel] nested_vmx_vmexit+0x222/0x9c0 [kvm_intel] vmx_handle_exit+0x246/0x15a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0x850/0x1830 [kvm] kvm_vcpu_ioctl+0x3a1/0x5c0 [kvm] do_vfs_ioctl+0x9f/0x600 ksys_ioctl+0x66/0x70 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x4f/0x100 entry_SYSCALL_64_after_hwframe+0x44/0xa9

L0: WARNING: CPU: 2 PID: 3529 at arch/x86/kvm/vmx.c:6618 handle_desc+0x28/0x30 [kvm_intel] ... CPU: 2 PID: 3529 Comm: qemu-system-x86 Not tainted 4.17.2-coffee+ #76 Hardware name: Intel Corporation Kabylake Client platform/KBL S RIP: 0010:handle_desc+0x28/0x30 [kvm_intel]

...

Call Trace: kvm_arch_vcpu_ioctl_run+0x863/0x1840 [kvm] kvm_vcpu_ioctl+0x3a1/0x5c0 [kvm] do_vfs_ioctl+0x9f/0x5e0 ksys_ioctl+0x66/0x70 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x49/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 5af4157388ad (KVM: nVMX: Fix mmu context after VMLAUNCH/VMRESUME failure) Fixes: 4f350c6dbcb9 (kvm: nVMX: Handle deferred early VMLAUNCH/VMRESUME failure properly) Cc: Jim Mattson jmattson@google.com Cc: Krish Sadhukhan krish.sadhukhan@oracle.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Radim KrÄmář rkrcmar@redhat.com Cc: Wanpeng Li wanpeng.li@hotmail.com Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx.c | 173 +++++++++++++++++++++++++++++++++++++++------ 1 file changed, 153 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 229d5e39f5c0..28faf781e6fd 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11860,24 +11860,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_clear_interrupt_queue(vcpu); }

-static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) -{ - u32 entry_failure_code; - - nested_ept_uninit_mmu_context(vcpu); - - /* - * Only PDPTE load can fail as the value of cr3 was checked on entry and - * couldn't have changed. - */ - if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) - nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); - - if (!enable_ept) - vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; -} - /* * A part of what we need to when the nested L2 guest exits and we want to * run its L1 parent, is to reset L1's guest state to the host state specified @@ -11891,6 +11873,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct kvm_segment seg; + u32 entry_failure_code;

if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -11917,7 +11900,17 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); vmx_set_cr4(vcpu, vmcs12->host_cr4);

- load_vmcs12_mmu_host_state(vcpu, vmcs12); + nested_ept_uninit_mmu_context(vcpu); + + /* + * Only PDPTE load can fail as the value of cr3 was checked on entry and + * couldn't have changed. + */ + if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) + nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); + + if (!enable_ept) + vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;

if (enable_vpid) { /* @@ -12008,6 +12001,140 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); }

+static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) +{ + struct shared_msr_entry *efer_msr; + unsigned int i; + + if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER) + return vmcs_read64(GUEST_IA32_EFER); + + if (cpu_has_load_ia32_efer) + return host_efer; + + for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) { + if (vmx->msr_autoload.guest.val[i].index == MSR_EFER) + return vmx->msr_autoload.guest.val[i].value; + } + + efer_msr = find_msr_entry(vmx, MSR_EFER); + if (efer_msr) + return efer_msr->data; + + return host_efer; +} + +static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmx_msr_entry g, h; + struct msr_data msr; + gpa_t gpa; + u32 i, j; + + vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT); + + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + /* + * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set + * as vmcs01.GUEST_DR7 contains a userspace defined value + * and vcpu->arch.dr7 is not squirreled away before the + * nested VMENTER (not worth adding a variable in nested_vmx). + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + kvm_set_dr(vcpu, 7, DR7_FIXED_1); + else + WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); + } + + /* + * Note that calling vmx_set_{efer,cr0,cr4} is important as they + * handle a variety of side effects to KVM's software model. + */ + vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); + + vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); + + vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); + vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); + + nested_ept_uninit_mmu_context(vcpu); + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + /* + * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs + * from vmcs01 (if necessary). The PDPTRs are not loaded on + * VMFail, like everything else we just need to ensure our + * software model is up-to-date. + */ + ept_save_pdptrs(vcpu); + + kvm_mmu_reset_context(vcpu); + + if (cpu_has_vmx_msr_bitmap()) + vmx_update_msr_bitmap(vcpu); + + /* + * This nasty bit of open coding is a compromise between blindly + * loading L1's MSRs using the exit load lists (incorrect emulation + * of VMFail), leaving the nested VM's MSRs in the software model + * (incorrect behavior) and snapshotting the modified MSRs (too + * expensive since the lists are unbound by hardware). For each + * MSR that was (prematurely) loaded from the nested VMEntry load + * list, reload it from the exit load list if it exists and differs + * from the guest value. The intent is to stuff host state as + * silently as possible, not to fully process the exit load list. + */ + msr.host_initiated = false; + for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) { + gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g)); + if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) { + pr_debug_ratelimited( + "%s read MSR index failed (%u, 0x%08llx)\n", + __func__, i, gpa); + goto vmabort; + } + + for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) { + gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h)); + if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) { + pr_debug_ratelimited( + "%s read MSR failed (%u, 0x%08llx)\n", + __func__, j, gpa); + goto vmabort; + } + if (h.index != g.index) + continue; + if (h.value == g.value) + break; + + if (nested_vmx_load_msr_check(vcpu, &h)) { + pr_debug_ratelimited( + "%s check failed (%u, 0x%x, 0x%x)\n", + __func__, j, h.index, h.reserved); + goto vmabort; + } + + msr.index = h.index; + msr.data = h.value; + if (kvm_set_msr(vcpu, &msr)) { + pr_debug_ratelimited( + "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", + __func__, j, h.index, h.value); + goto vmabort; + } + } + } + + return; + +vmabort: + nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); +} + /* * Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1 * and modify vmcs12 to make it see what it would expect to see there if @@ -12140,7 +12267,13 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);

- load_vmcs12_mmu_host_state(vcpu, vmcs12); + /* + * Restore L1's host state to KVM's software model. We're here + * because a consistency check was caught by hardware, which + * means some amount of guest state has been propagated to KVM's + * model and needs to be unwound to the host's state. + */ + nested_vmx_restore_host_state(vcpu);

/* * The emulated instruction was already skipped in

From: Steve French stfrench@microsoft.com

[ Upstream commit 3b7960caceafdfc2cdfe2850487f8d091eb41144 ]

In cases where queryinfo fails, we have cases in cifs (vers=1.0) where with backupuid mounts we retry the query info with findfirst. This doesn't work to some NetApp servers which don't support WindowsXP (and later) infolevel 261 (SMB_FIND_FILE_ID_FULL_DIR_INFO) so in this case use other info levels (in this case it will usually be level 257, SMB_FIND_FILE_DIRECTORY_INFO).

(Also fixes some indentation)

See kernel bugzilla 201435

Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/inode.c | 67 +++++++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 30 deletions(-)

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a90a637ae79a..6fd4a6a75234 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -779,43 +779,50 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, } else if ((rc == -EACCES) && backup_cred(cifs_sb) && (strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0)) { - /* - * For SMB2 and later the backup intent flag is already - * sent if needed on open and there is no path based - * FindFirst operation to use to retry with - */ + /* + * For SMB2 and later the backup intent flag is already + * sent if needed on open and there is no path based + * FindFirst operation to use to retry with + */

- srchinf = kzalloc(sizeof(struct cifs_search_info), - GFP_KERNEL); - if (srchinf == NULL) { - rc = -ENOMEM; - goto cgii_exit; - } + srchinf = kzalloc(sizeof(struct cifs_search_info), + GFP_KERNEL); + if (srchinf == NULL) { + rc = -ENOMEM; + goto cgii_exit; + }

- srchinf->endOfSearch = false; + srchinf->endOfSearch = false; + if (tcon->unix_ext) + srchinf->info_level = SMB_FIND_FILE_UNIX; + else if ((tcon->ses->capabilities & + tcon->ses->server->vals->cap_nt_find) == 0) + srchinf->info_level = SMB_FIND_FILE_INFO_STANDARD; + else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) srchinf->info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; + else /* no srvino useful for fallback to some netapp */ + srchinf->info_level = SMB_FIND_FILE_DIRECTORY_INFO;

- srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | - CIFS_SEARCH_CLOSE_AT_END | - CIFS_SEARCH_BACKUP_SEARCH; + srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | + CIFS_SEARCH_CLOSE_AT_END | + CIFS_SEARCH_BACKUP_SEARCH;

- rc = CIFSFindFirst(xid, tcon, full_path, - cifs_sb, NULL, srchflgs, srchinf, false); - if (!rc) { - data = - (FILE_ALL_INFO *)srchinf->srch_entries_start; + rc = CIFSFindFirst(xid, tcon, full_path, + cifs_sb, NULL, srchflgs, srchinf, false); + if (!rc) { + data = (FILE_ALL_INFO *)srchinf->srch_entries_start;

- cifs_dir_info_to_fattr(&fattr, - (FILE_DIRECTORY_INFO *)data, cifs_sb); - fattr.cf_uniqueid = le64_to_cpu( - ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); - validinum = true; + cifs_dir_info_to_fattr(&fattr, + (FILE_DIRECTORY_INFO *)data, cifs_sb); + fattr.cf_uniqueid = le64_to_cpu( + ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); + validinum = true;

- cifs_buf_release(srchinf->ntwrk_buf_start); - } - kfree(srchinf); - if (rc) - goto cgii_exit; + cifs_buf_release(srchinf->ntwrk_buf_start); + } + kfree(srchinf); + if (rc) + goto cgii_exit; } else goto cgii_exit;

From: Keith Busch keith.busch@intel.com

[ Upstream commit 9fe5c59ff6a1e5e26a39b75489a1420e7eaaf0b1 ]

The nvme pci driver had been adding its CMB resource to the P2P DMA subsystem everytime on on a controller reset. This results in the following warning:

------------[ cut here ]------------ nvme 0000:00:03.0: Conflicting mapping in same section WARNING: CPU: 7 PID: 81 at kernel/memremap.c:155 devm_memremap_pages+0xa6/0x380 ... Call Trace: pci_p2pdma_add_resource+0x153/0x370 nvme_reset_work+0x28c/0x17b1 [nvme] ? add_timer+0x107/0x1e0 ? dequeue_entity+0x81/0x660 ? dequeue_entity+0x3b0/0x660 ? pick_next_task_fair+0xaf/0x610 ? __switch_to+0xbc/0x410 process_one_work+0x1cf/0x350 worker_thread+0x215/0x3d0 ? process_one_work+0x350/0x350 kthread+0x107/0x120 ? kthread_park+0x80/0x80 ret_from_fork+0x1f/0x30 ---[ end trace f7ea76ac6ee72727 ]--- nvme nvme0: failed to register the CMB

This patch fixes this by registering the CMB with P2P only once.

Signed-off-by: Keith Busch keith.busch@intel.com Reviewed-by: Logan Gunthorpe logang@deltatee.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/pci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 06355ca832db..ae03a5b70324 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1546,6 +1546,9 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) void __iomem *cmb; int bar;

+ if (dev->cmb_size) + return; + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!(NVME_CMB_SZ(dev->cmbsz))) return NULL; @@ -2034,7 +2037,6 @@ static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev);

- nvme_release_cmb(dev); pci_free_irq_vectors(pdev);

if (pci_is_enabled(pdev)) { @@ -2434,6 +2436,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_stop_ctrl(&dev->ctrl); nvme_remove_namespaces(&dev->ctrl); nvme_dev_disable(dev, true); + nvme_release_cmb(dev); nvme_free_host_mem(dev); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0);

From: Ard Biesheuvel ard.biesheuvel@linaro.org

[ Upstream commit 69216a545cf81b2b32d01948f7039315abaf75a0 ]

The SHA256 code we adopted from the OpenSSL project uses a rather peculiar way to take the address of the round constant table: it takes the address of the sha256_block_data_order() routine, and substracts a constant known quantity to arrive at the base of the table, which is emitted by the same assembler code right before the routine's entry point.

However, recent versions of binutils have helpfully changed the behavior of references emitted via an ADR instruction when running in Thumb2 mode: it now takes the Thumb execution mode bit into account, which is bit 0 af the address. This means the produced table address also has bit 0 set, and so we end up with an address value pointing 1 byte past the start of the table, which results in crashes such as

Unable to handle kernel paging request at virtual address bf825000 pgd = 42f44b11 [bf825000] *pgd=80000040206003, *pmd=5f1bd003, *pte=00000000 Internal error: Oops: 207 [#1] PREEMPT SMP THUMB2 Modules linked in: sha256_arm(+) sha1_arm_ce sha1_arm ... CPU: 7 PID: 396 Comm: cryptomgr_test Not tainted 5.0.0-rc6+ #144 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 PC is at sha256_block_data_order+0xaaa/0xb30 [sha256_arm] LR is at __this_module+0x17fd/0xffffe800 [sha256_arm] pc : [<bf820bca>] lr : [<bf824ffd>] psr: 800b0033 sp : ebc8bbe8 ip : faaabe1c fp : 2fdd3433 r10: 4c5f1692 r9 : e43037df r8 : b04b0a5a r7 : c369d722 r6 : 39c3693e r5 : 7a013189 r4 : 1580d26b r3 : 8762a9b0 r2 : eea9c2cd r1 : 3e9ab536 r0 : 1dea4ae7 Flags: Nzcv IRQs on FIQs on Mode SVC_32 ISA Thumb Segment user Control: 70c5383d Table: 6b8467c0 DAC: dbadc0de Process cryptomgr_test (pid: 396, stack limit = 0x69e1fe23) Stack: (0xebc8bbe8 to 0xebc8c000) ... unwind: Unknown symbol address bf820bca unwind: Index not found bf820bca Code: 441a ea80 40f9 440a (f85e) 3b04 ---[ end trace e560cce92700ef8a ]---

Given that this affects older kernels as well, in case they are built with a recent toolchain, apply a minimal backportable fix, which is to emit another non-code label at the start of the routine, and reference that instead. (This is similar to the current upstream state of this file in OpenSSL)

Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/crypto/sha256-armv4.pl | 3 ++- arch/arm/crypto/sha256-core.S_shipped | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl index fac0533ea633..f64e8413ab9a 100644 --- a/arch/arm/crypto/sha256-armv4.pl +++ b/arch/arm/crypto/sha256-armv4.pl @@ -205,10 +205,11 @@ K256: .global sha256_block_data_order .type sha256_block_data_order,%function sha256_block_data_order: +.Lsha256_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha256_block_data_order #else - adr r3,sha256_block_data_order + adr r3,.Lsha256_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped index 555a1a8eec90..72c248081d27 100644 --- a/arch/arm/crypto/sha256-core.S_shipped +++ b/arch/arm/crypto/sha256-core.S_shipped @@ -86,10 +86,11 @@ K256: .global sha256_block_data_order .type sha256_block_data_order,%function sha256_block_data_order: +.Lsha256_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha256_block_data_order #else - adr r3,sha256_block_data_order + adr r3,.Lsha256_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap

From: Julia Cartwright julia@ni.com

[ Upstream commit cffaaf0c816238c45cd2d06913476c83eb50f682 ]

Commit 57384592c433 ("iommu/vt-d: Store bus information in RMRR PCI device path") changed the type of the path data, however, the change in path type was not reflected in size calculations. Update to use the correct type and prevent a buffer overflow.

This bug manifests in systems with deep PCI hierarchies, and can lead to an overflow of the static allocated buffer (dmar_pci_notify_info_buf), or can lead to overflow of slab-allocated data.

BUG: KASAN: global-out-of-bounds in dmar_alloc_pci_notify_info+0x1d5/0x2e0 Write of size 1 at addr ffffffff90445d80 by task swapper/0/1 CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.14.87-rt49-02406-gd0a0e96 #1 Call Trace: ? dump_stack+0x46/0x59 ? print_address_description+0x1df/0x290 ? dmar_alloc_pci_notify_info+0x1d5/0x2e0 ? kasan_report+0x256/0x340 ? dmar_alloc_pci_notify_info+0x1d5/0x2e0 ? e820__memblock_setup+0xb0/0xb0 ? dmar_dev_scope_init+0x424/0x48f ? __down_write_common+0x1ec/0x230 ? dmar_dev_scope_init+0x48f/0x48f ? dmar_free_unused_resources+0x109/0x109 ? cpumask_next+0x16/0x20 ? __kmem_cache_create+0x392/0x430 ? kmem_cache_create+0x135/0x2f0 ? e820__memblock_setup+0xb0/0xb0 ? intel_iommu_init+0x170/0x1848 ? _raw_spin_unlock_irqrestore+0x32/0x60 ? migrate_enable+0x27a/0x5b0 ? sched_setattr+0x20/0x20 ? migrate_disable+0x1fc/0x380 ? task_rq_lock+0x170/0x170 ? try_to_run_init_process+0x40/0x40 ? locks_remove_file+0x85/0x2f0 ? dev_prepare_static_identity_mapping+0x78/0x78 ? rt_spin_unlock+0x39/0x50 ? lockref_put_or_lock+0x2a/0x40 ? dput+0x128/0x2f0 ? __rcu_read_unlock+0x66/0x80 ? __fput+0x250/0x300 ? __rcu_read_lock+0x1b/0x30 ? mntput_no_expire+0x38/0x290 ? e820__memblock_setup+0xb0/0xb0 ? pci_iommu_init+0x25/0x63 ? pci_iommu_init+0x25/0x63 ? do_one_initcall+0x7e/0x1c0 ? initcall_blacklisted+0x120/0x120 ? kernel_init_freeable+0x27b/0x307 ? rest_init+0xd0/0xd0 ? kernel_init+0xf/0x120 ? rest_init+0xd0/0xd0 ? ret_from_fork+0x1f/0x40 The buggy address belongs to the variable: dmar_pci_notify_info_buf+0x40/0x60

Fixes: 57384592c433 ("iommu/vt-d: Store bus information in RMRR PCI device path") Signed-off-by: Julia Cartwright julia@ni.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index c0d1c4db5794..38d0128b8135 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -144,7 +144,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) for (tmp = dev; tmp; tmp = tmp->bus->self) level++;

- size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path); + size = sizeof(*info) + level * sizeof(info->path[0]); if (size <= sizeof(dmar_pci_notify_info_buf)) { info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf; } else {

From: Dmitry Osipenko digetx@gmail.com

[ Upstream commit b6e1fd17a38bd1d97c11d69fd3207b3ef9bfa4b3 ]

This fixes splats like the one below if CONFIG_DEBUG_ATOMIC_SLEEP=y and machine (Tegra30) booted with SMP=n or all secondary CPU's are put offline. Locking isn't needed because it protects atomic operation.

BUG: sleeping function called from invalid context at kernel/locking/mutex.c:254 in_atomic(): 1, irqs_disabled(): 128, pid: 0, name: swapper/0 CPU: 0 PID: 0 Comm: swapper/0 Tainted: G C 4.18.0-next-20180821-00180-gc3ebb6544e44-dirty #823 Hardware name: NVIDIA Tegra SoC (Flattened Device Tree) [<c01134f4>] (unwind_backtrace) from [<c010db2c>] (show_stack+0x20/0x24) [<c010db2c>] (show_stack) from [<c0bd0f3c>] (dump_stack+0x94/0xa8) [<c0bd0f3c>] (dump_stack) from [<c0151df8>] (___might_sleep+0x13c/0x174) [<c0151df8>] (___might_sleep) from [<c0151ea0>] (__might_sleep+0x70/0xa8) [<c0151ea0>] (__might_sleep) from [<c0bec2b8>] (mutex_lock+0x2c/0x70) [<c0bec2b8>] (mutex_lock) from [<c0589844>] (tegra_powergate_is_powered+0x44/0xa8) [<c0589844>] (tegra_powergate_is_powered) from [<c0581a60>] (tegra30_cpu_rail_off_ready+0x30/0x74) [<c0581a60>] (tegra30_cpu_rail_off_ready) from [<c0122244>] (tegra30_idle_lp2+0xa0/0x108) [<c0122244>] (tegra30_idle_lp2) from [<c0853438>] (cpuidle_enter_state+0x140/0x540) [<c0853438>] (cpuidle_enter_state) from [<c08538a4>] (cpuidle_enter+0x40/0x4c) [<c08538a4>] (cpuidle_enter) from [<c01595e0>] (call_cpuidle+0x30/0x48) [<c01595e0>] (call_cpuidle) from [<c01599f8>] (do_idle+0x238/0x28c) [<c01599f8>] (do_idle) from [<c0159d28>] (cpu_startup_entry+0x28/0x2c) [<c0159d28>] (cpu_startup_entry) from [<c0be76c8>] (rest_init+0xd8/0xdc) [<c0be76c8>] (rest_init) from [<c1200f50>] (start_kernel+0x41c/0x430)

Signed-off-by: Dmitry Osipenko digetx@gmail.com Acked-by: Jon Hunter jonathanh@nvidia.com Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/tegra/pmc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 7e9ef3431bea..2422ed56895a 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -521,16 +521,10 @@ EXPORT_SYMBOL(tegra_powergate_power_off); */ int tegra_powergate_is_powered(unsigned int id) { - int status; - if (!tegra_powergate_is_valid(id)) return -EINVAL;

- mutex_lock(&pmc->powergates_lock); - status = tegra_powergate_state(id); - mutex_unlock(&pmc->powergates_lock); - - return status; + return tegra_powergate_state(id); }

/**

From: Christophe Leroy christophe.leroy@c-s.fr

[ Upstream commit 4c411157a42f122051ae3469bee0b5cabe89e139 ]

Today, when doing a lkdtm test before the readiness of the random generator, (ptrval) is printed instead of the address at which it perform the fault:

[ 1597.337030] lkdtm: Performing direct entry EXEC_USERSPACE [ 1597.337142] lkdtm: attempting ok execution at (ptrval) [ 1597.337398] lkdtm: attempting bad execution at (ptrval) [ 1597.337460] kernel tried to execute user page (77858000) -exploit attempt? (uid: 0) [ 1597.344769] Unable to handle kernel paging request for instruction fetch [ 1597.351392] Faulting instruction address: 0x77858000 [ 1597.356312] Oops: Kernel access of bad area, sig: 11 [#1]

If the lkdtm test is done later on, it prints an hashed address.

In both cases this is pointless. The purpose of the test is to ensure the kernel generates an Oops at the expected address, so real addresses needs to be printed. This patch fixes that.

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/lkdtm_perms.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/misc/lkdtm_perms.c b/drivers/misc/lkdtm_perms.c index 53b85c9d16b8..fa54add6375a 100644 --- a/drivers/misc/lkdtm_perms.c +++ b/drivers/misc/lkdtm_perms.c @@ -47,7 +47,7 @@ static noinline void execute_location(void *dst, bool write) { void (*func)(void) = dst;

- pr_info("attempting ok execution at %p\n", do_nothing); + pr_info("attempting ok execution at %px\n", do_nothing); do_nothing();

if (write == CODE_WRITE) { @@ -55,7 +55,7 @@ static noinline void execute_location(void *dst, bool write) flush_icache_range((unsigned long)dst, (unsigned long)dst + EXEC_SIZE); } - pr_info("attempting bad execution at %p\n", func); + pr_info("attempting bad execution at %px\n", func); func(); }

@@ -66,14 +66,14 @@ static void execute_user_location(void *dst) /* Intentionally crossing kernel/user memory boundary. */ void (*func)(void) = dst;

- pr_info("attempting ok execution at %p\n", do_nothing); + pr_info("attempting ok execution at %px\n", do_nothing); do_nothing();

copied = access_process_vm(current, (unsigned long)dst, do_nothing, EXEC_SIZE, FOLL_WRITE); if (copied < EXEC_SIZE) return; - pr_info("attempting bad execution at %p\n", func); + pr_info("attempting bad execution at %px\n", func); func(); }

@@ -82,7 +82,7 @@ void lkdtm_WRITE_RO(void) /* Explicitly cast away "const" for the test. */ unsigned long *ptr = (unsigned long *)&rodata;

- pr_info("attempting bad rodata write at %p\n", ptr); + pr_info("attempting bad rodata write at %px\n", ptr); *ptr ^= 0xabcd1234; }

@@ -100,7 +100,7 @@ void lkdtm_WRITE_RO_AFTER_INIT(void) return; }

- pr_info("attempting bad ro_after_init write at %p\n", ptr); + pr_info("attempting bad ro_after_init write at %px\n", ptr); *ptr ^= 0xabcd1234; }

@@ -112,7 +112,7 @@ void lkdtm_WRITE_KERN(void) size = (unsigned long)do_overwritten - (unsigned long)do_nothing; ptr = (unsigned char *)do_overwritten;

- pr_info("attempting bad %zu byte write at %p\n", size, ptr); + pr_info("attempting bad %zu byte write at %px\n", size, ptr); memcpy(ptr, (unsigned char *)do_nothing, size); flush_icache_range((unsigned long)ptr, (unsigned long)(ptr + size));

@@ -185,11 +185,11 @@ void lkdtm_ACCESS_USERSPACE(void)

ptr = (unsigned long *)user_addr;

- pr_info("attempting bad read at %p\n", ptr); + pr_info("attempting bad read at %px\n", ptr); tmp = *ptr; tmp += 0xc0dec0de;

- pr_info("attempting bad write at %p\n", ptr); + pr_info("attempting bad write at %px\n", ptr); *ptr = tmp;

vm_munmap(user_addr, PAGE_SIZE);