4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tadeusz Struk tadeusz.struk@intel.com

commit 3ab2011ea368ec3433ad49e1b9e1c7b70d2e65df upstream.

There is a race condition in tpm_common_write function allowing two threads on the same /dev/tpm<N>, or two different applications on the same /dev/tpmrm<N> to overwrite each other commands/responses. Fixed this by taking the priv->buffer_mutex early in the function.

Also converted the priv->data_pending from atomic to a regular size_t type. There is no need for it to be atomic since it is only touched under the protection of the priv->buffer_mutex.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Tadeusz Struk tadeusz.struk@intel.com Reviewed-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/tpm/tpm-dev.c | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-)

--- a/drivers/char/tpm/tpm-dev.c +++ b/drivers/char/tpm/tpm-dev.c @@ -25,7 +25,7 @@ struct file_priv { struct tpm_chip *chip;

/* Data passed to and from the tpm via the read/write calls */ - atomic_t data_pending; + size_t data_pending; struct mutex buffer_mutex;

struct timer_list user_read_timer; /* user needs to claim result */ @@ -46,7 +46,7 @@ static void timeout_work(struct work_str struct file_priv *priv = container_of(work, struct file_priv, work);

mutex_lock(&priv->buffer_mutex); - atomic_set(&priv->data_pending, 0); + priv->data_pending = 0; memset(priv->data_buffer, 0, sizeof(priv->data_buffer)); mutex_unlock(&priv->buffer_mutex); } @@ -72,7 +72,6 @@ static int tpm_open(struct inode *inode, }

priv->chip = chip; - atomic_set(&priv->data_pending, 0); mutex_init(&priv->buffer_mutex); setup_timer(&priv->user_read_timer, user_reader_timeout, (unsigned long)priv); @@ -86,28 +85,24 @@ static ssize_t tpm_read(struct file *fil size_t size, loff_t *off) { struct file_priv *priv = file->private_data; - ssize_t ret_size; + ssize_t ret_size = 0; int rc;

del_singleshot_timer_sync(&priv->user_read_timer); flush_work(&priv->work); - ret_size = atomic_read(&priv->data_pending); - if (ret_size > 0) { /* relay data */ - ssize_t orig_ret_size = ret_size; - if (size < ret_size) - ret_size = size; + mutex_lock(&priv->buffer_mutex);

- mutex_lock(&priv->buffer_mutex); + if (priv->data_pending) { + ret_size = min_t(ssize_t, size, priv->data_pending); rc = copy_to_user(buf, priv->data_buffer, ret_size); - memset(priv->data_buffer, 0, orig_ret_size); + memset(priv->data_buffer, 0, priv->data_pending); if (rc) ret_size = -EFAULT;

- mutex_unlock(&priv->buffer_mutex); + priv->data_pending = 0; }

- atomic_set(&priv->data_pending, 0); - + mutex_unlock(&priv->buffer_mutex); return ret_size; }

@@ -118,18 +113,20 @@ static ssize_t tpm_write(struct file *fi size_t in_size = size; ssize_t out_size;

- /* cannot perform a write until the read has cleared - either via tpm_read or a user_read_timer timeout. - This also prevents splitted buffered writes from blocking here. - */ - if (atomic_read(&priv->data_pending) != 0) - return -EBUSY; - if (in_size > TPM_BUFSIZE) return -E2BIG;

mutex_lock(&priv->buffer_mutex);

+ /* Cannot perform a write until the read has cleared either via + * tpm_read or a user_read_timer timeout. This also prevents split + * buffered writes from blocking here. + */ + if (priv->data_pending != 0) { + mutex_unlock(&priv->buffer_mutex); + return -EBUSY; + } + if (copy_from_user (priv->data_buffer, (void __user *) buf, in_size)) { mutex_unlock(&priv->buffer_mutex); @@ -159,7 +156,7 @@ static ssize_t tpm_write(struct file *fi return out_size; }

- atomic_set(&priv->data_pending, out_size); + priv->data_pending = out_size; mutex_unlock(&priv->buffer_mutex);

/* Set a timeout by which the reader must come claim the result */ @@ -178,7 +175,7 @@ static int tpm_release(struct inode *ino del_singleshot_timer_sync(&priv->user_read_timer); flush_work(&priv->work); file->private_data = NULL; - atomic_set(&priv->data_pending, 0); + priv->data_pending = 0; clear_bit(0, &priv->chip->is_open); kfree(priv); return 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrey Konovalov andreyknvl@google.com

commit 12c8f25a016dff69ee284aa3338bebfd2cfcba33 upstream.

KASAN uses the __no_sanitize_address macro to disable instrumentation of particular functions. Right now it's defined only for GCC build, which causes false positives when clang is used.

This patch adds a definition for clang.

Note, that clang's revision 329612 or higher is required.

[andreyknvl@google.com: remove redundant #ifdef CONFIG_KASAN check] Link: http://lkml.kernel.org/r/c79aa31a2a2790f6131ed607c58b0dd45dd62a6c.1523967959... Link: http://lkml.kernel.org/r/4ad725cc903f8534f8c8a60f0daade5e3d674f8d.1523554166... Signed-off-by: Andrey Konovalov andreyknvl@google.com Acked-by: Andrey Ryabinin aryabinin@virtuozzo.com Cc: Alexander Potapenko glider@google.com Cc: Dmitry Vyukov dvyukov@google.com Cc: David Rientjes rientjes@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Ingo Molnar mingo@kernel.org Cc: David Woodhouse dwmw@amazon.co.uk Cc: Andrey Konovalov andreyknvl@google.com Cc: Will Deacon will.deacon@arm.com Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Paul Lawrence paullawrence@google.com Cc: Sandipan Das sandipan@linux.vnet.ibm.com Cc: Kees Cook keescook@chromium.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Cc: Sodagudi Prasad psodagud@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/compiler-clang.h | 3 +++ 1 file changed, 3 insertions(+)

--- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -16,6 +16,9 @@ */ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)

+#undef __no_sanitize_address +#define __no_sanitize_address __attribute__((no_sanitize("address"))) + /* Clang doesn't have a way to turn it off per-function, yet. */ #ifdef __noretpoline #undef __noretpoline

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Juergen Gross jgross@suse.com

commit d472b3a6cf63cd31cae1ed61930f07e6cd6671b5 upstream.

skb_shinfo() can change when calling __pskb_pull_tail(): Don't cache its return value.

Cc: stable@vger.kernel.org Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Wei Liu wei.liu2@citrix.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/xen-netfront.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -893,7 +893,6 @@ static RING_IDX xennet_fill_frags(struct struct sk_buff *skb, struct sk_buff_head *list) { - struct skb_shared_info *shinfo = skb_shinfo(skb); RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *nskb;

@@ -902,15 +901,16 @@ static RING_IDX xennet_fill_frags(struct RING_GET_RESPONSE(&queue->rx, ++cons); skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];

- if (shinfo->nr_frags == MAX_SKB_FRAGS) { + if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;

BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS); + BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);

- skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag), + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + skb_frag_page(nfrag), rx->offset, rx->status, PAGE_SIZE);

skb_shinfo(nskb)->nr_frags = 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bart Van Assche bart.vanassche@wdc.com

commit 1214fd7b497400d200e3f4e64e2338b303a20949 upstream.

Surround scsi_execute() calls with scsi_autopm_get_device() and scsi_autopm_put_device(). Note: removing sr_mutex protection from the scsi_cd_get() and scsi_cd_put() calls is safe because the purpose of sr_mutex is to serialize cdrom_*() calls.

This patch avoids that complaints similar to the following appear in the kernel log if runtime power management is enabled:

INFO: task systemd-udevd:650 blocked for more than 120 seconds. Not tainted 4.18.0-rc7-dbg+ #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. systemd-udevd D28176 650 513 0x00000104 Call Trace: __schedule+0x444/0xfe0 schedule+0x4e/0xe0 schedule_preempt_disabled+0x18/0x30 __mutex_lock+0x41c/0xc70 mutex_lock_nested+0x1b/0x20 __blkdev_get+0x106/0x970 blkdev_get+0x22c/0x5a0 blkdev_open+0xe9/0x100 do_dentry_open.isra.19+0x33e/0x570 vfs_open+0x7c/0xd0 path_openat+0x6e3/0x1120 do_filp_open+0x11c/0x1c0 do_sys_open+0x208/0x2d0 __x64_sys_openat+0x59/0x70 do_syscall_64+0x77/0x230 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Signed-off-by: Bart Van Assche bart.vanassche@wdc.com Cc: Maurizio Lombardi mlombard@redhat.com Cc: Johannes Thumshirn jthumshirn@suse.de Cc: Alan Stern stern@rowland.harvard.edu Cc: stable@vger.kernel.org Tested-by: Johannes Thumshirn jthumshirn@suse.de Reviewed-by: Johannes Thumshirn jthumshirn@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/sr.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)

--- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -520,18 +520,26 @@ static int sr_init_command(struct scsi_c static int sr_block_open(struct block_device *bdev, fmode_t mode) { struct scsi_cd *cd; + struct scsi_device *sdev; int ret = -ENXIO;

+ cd = scsi_cd_get(bdev->bd_disk); + if (!cd) + goto out; + + sdev = cd->device; + scsi_autopm_get_device(sdev); check_disk_change(bdev);

mutex_lock(&sr_mutex); - cd = scsi_cd_get(bdev->bd_disk); - if (cd) { - ret = cdrom_open(&cd->cdi, bdev, mode); - if (ret) - scsi_cd_put(cd); - } + ret = cdrom_open(&cd->cdi, bdev, mode); mutex_unlock(&sr_mutex); + + scsi_autopm_put_device(sdev); + if (ret) + scsi_cd_put(cd); + +out: return ret; }

@@ -559,6 +567,8 @@ static int sr_block_ioctl(struct block_d if (ret) goto out;

+ scsi_autopm_get_device(sdev); + /* * Send SCSI addressing ioctls directly to mid level, send other * ioctls to cdrom/block level. @@ -567,15 +577,18 @@ static int sr_block_ioctl(struct block_d case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: ret = scsi_ioctl(sdev, cmd, argp); - goto out; + goto put; }

ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) - goto out; + goto put;

ret = scsi_ioctl(sdev, cmd, argp);

+put: + scsi_autopm_put_device(sdev); + out: mutex_unlock(&sr_mutex); return ret;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro viro@zeniv.linux.org.uk

commit 90bad5e05bcdb0308cfa3d3a60f5c0b9c8e2efb3 upstream.

Since mountpoint crossing can happen without leaving lazy mode, root dentries do need the same protection against having their memory freed without RCU delay as everything else in the tree.

It's partially hidden by RCU delay between detaching from the mount tree and dropping the vfsmount reference, but the starting point of pathwalk can be on an already detached mount, in which case umount-caused RCU delay has already passed by the time the lazy pathwalk grabs rcu_read_lock(). If the starting point happens to be at the root of that vfsmount *and* that vfsmount covers the entire filesystem, we get trouble.

Fixes: 48a066e72d97 ("RCU'd vsfmounts") Cc: stable@vger.kernel.org Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/dcache.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/dcache.c +++ b/fs/dcache.c @@ -1914,10 +1914,12 @@ struct dentry *d_make_root(struct inode

if (root_inode) { res = __d_alloc(root_inode->i_sb, NULL); - if (res) + if (res) { + res->d_flags |= DCACHE_RCUACCESS; d_instantiate(res, root_inode); - else + } else { iput(root_inode); + } } return res; }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro viro@zeniv.linux.org.uk

commit 9ea0a46ca2c318fcc449c1e6b62a7230a17888f1 upstream.

mntput_no_expire() does the calculation of total refcount under mount_lock; unfortunately, the decrement (as well as all increments) are done outside of it, leading to false positives in the "are we dropping the last reference" test. Consider the following situation: * mnt is a lazy-umounted mount, kept alive by two opened files. One of those files gets closed. Total refcount of mnt is 2. On CPU 42 mntput(mnt) (called from __fput()) drops one reference, decrementing component * After it has looked at component #0, the process on CPU 0 does mntget(), incrementing component #0, gets preempted and gets to run again - on CPU 69. There it does mntput(), which drops the reference (component #69) and proceeds to spin on mount_lock. * On CPU 42 our first mntput() finishes counting. It observes the decrement of component #69, but not the increment of component #0. As the result, the total it gets is not 1 as it should've been - it's 0. At which point we decide that vfsmount needs to be killed and proceed to free it and shut the filesystem down. However, there's still another opened file on that filesystem, with reference to (now freed) vfsmount, etc. and we are screwed.

It's not a wide race, but it can be reproduced with artificial slowdown of the mnt_get_count() loop, and it should be easier to hit on SMP KVM setups.

Fix consists of moving the refcount decrement under mount_lock; the tricky part is that we want (and can) keep the fast case (i.e. mount that still has non-NULL ->mnt_ns) entirely out of mount_lock. All places that zero mnt->mnt_ns are dropping some reference to mnt and they call synchronize_rcu() before that mntput(). IOW, if mntput() observes (under rcu_read_lock()) a non-NULL ->mnt_ns, it is guaranteed that there is another reference yet to be dropped.

Reported-by: Jann Horn jannh@google.com Tested-by: Jann Horn jannh@google.com Fixes: 48a066e72d97 ("RCU'd vsfmounts") Cc: stable@vger.kernel.org Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/namespace.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

--- a/fs/namespace.c +++ b/fs/namespace.c @@ -1139,12 +1139,22 @@ static DECLARE_DELAYED_WORK(delayed_mntp static void mntput_no_expire(struct mount *mnt) { rcu_read_lock(); - mnt_add_count(mnt, -1); - if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */ + if (likely(READ_ONCE(mnt->mnt_ns))) { + /* + * Since we don't do lock_mount_hash() here, + * ->mnt_ns can change under us. However, if it's + * non-NULL, then there's a reference that won't + * be dropped until after an RCU delay done after + * turning ->mnt_ns NULL. So if we observe it + * non-NULL under rcu_read_lock(), the reference + * we are dropping is not the final one. + */ + mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); + mnt_add_count(mnt, -1); if (mnt_get_count(mnt)) { rcu_read_unlock(); unlock_mount_hash();

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konstantin Khlebnikov khlebnikov@yandex-team.ru

commit d6cffbbe9a7e51eb705182965a189457c17ba8a3 upstream.

Currently unregistering sysctl table does not prune its dentries. Stale dentries could slowdown sysctl operations significantly.

For example, command:

# for i in {1..100000} ; do unshare -n -- sysctl -a &> /dev/null ; done creates a millions of stale denties around sysctls of loopback interface:

# sysctl fs.dentry-state fs.dentry-state = 25812579 24724135 45 0 0 0

All of them have matching names thus lookup have to scan though whole hash chain and call d_compare (proc_sys_compare) which checks them under system-wide spinlock (sysctl_lock).

# time sysctl -a > /dev/null real 1m12.806s user 0m0.016s sys 1m12.400s

Currently only memory reclaimer could remove this garbage. But without significant memory pressure this never happens.

This patch collects sysctl inodes into list on sysctl table header and prunes all their dentries once that table unregisters.

Konstantin Khlebnikov khlebnikov@yandex-team.ru writes:

On 10.02.2017 10:47, Al Viro wrote:

...

how about >> the matching stats *after* that patch?

dcache size doesn't grow endlessly, so stats are fine

# sysctl fs.dentry-state fs.dentry-state = 92712 58376 45 0 0 0

# time sysctl -a &>/dev/null

real 0m0.013s user 0m0.004s sys 0m0.008s

Signed-off-by: Konstantin Khlebnikov khlebnikov@yandex-team.ru Suggested-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/proc/inode.c | 3 +- fs/proc/internal.h | 7 ++++- fs/proc/proc_sysctl.c | 59 +++++++++++++++++++++++++++++++++++-------------- include/linux/sysctl.h | 1 4 files changed, 51 insertions(+), 19 deletions(-)

--- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -43,10 +43,11 @@ static void proc_evict_inode(struct inod de = PDE(inode); if (de) pde_put(de); + head = PROC_I(inode)->sysctl; if (head) { RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL); - sysctl_head_put(head); + proc_sys_evict_inode(inode, head); } }

--- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -65,6 +65,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; + struct list_head sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; }; @@ -249,10 +250,12 @@ extern void proc_thread_self_init(void); */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); -extern void sysctl_head_put(struct ctl_table_header *); +extern void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } -static inline void sysctl_head_put(struct ctl_table_header *head) { } +static inline void proc_sys_evict_inode(struct inode *inode, + struct ctl_table_header *head) { } #endif

/* --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -190,6 +190,7 @@ static void init_header(struct ctl_table head->set = set; head->parent = NULL; head->node = node; + INIT_LIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -259,6 +260,29 @@ static void unuse_table(struct ctl_table complete(p->unregistering); }

+/* called under sysctl_lock */ +static void proc_sys_prune_dcache(struct ctl_table_header *head) +{ + struct inode *inode, *prev = NULL; + struct proc_inode *ei; + + list_for_each_entry(ei, &head->inodes, sysctl_inodes) { + inode = igrab(&ei->vfs_inode); + if (inode) { + spin_unlock(&sysctl_lock); + iput(prev); + prev = inode; + d_prune_aliases(inode); + spin_lock(&sysctl_lock); + } + } + if (prev) { + spin_unlock(&sysctl_lock); + iput(prev); + spin_lock(&sysctl_lock); + } +} + /* called under sysctl_lock, will reacquire if has to wait */ static void start_unregistering(struct ctl_table_header *p) { @@ -278,27 +302,17 @@ static void start_unregistering(struct c p->unregistering = ERR_PTR(-EINVAL); } /* + * Prune dentries for unregistered sysctls: namespaced sysctls + * can have duplicate names and contaminate dcache very badly. + */ + proc_sys_prune_dcache(p); + /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. */ erase_header(p); }

-static void sysctl_head_get(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - head->count++; - spin_unlock(&sysctl_lock); -} - -void sysctl_head_put(struct ctl_table_header *head) -{ - spin_lock(&sysctl_lock); - if (!--head->count) - kfree_rcu(head, rcu); - spin_unlock(&sysctl_lock); -} - static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) { BUG_ON(!head); @@ -440,11 +454,15 @@ static struct inode *proc_sys_make_inode

inode->i_ino = get_next_ino();

- sysctl_head_get(head); ei = PROC_I(inode); ei->sysctl = head; ei->sysctl_entry = table;

+ spin_lock(&sysctl_lock); + list_add(&ei->sysctl_inodes, &head->inodes); + head->count++; + spin_unlock(&sysctl_lock); + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = table->mode; if (!S_ISDIR(table->mode)) { @@ -466,6 +484,15 @@ out: return inode; }

+void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) +{ + spin_lock(&sysctl_lock); + list_del(&PROC_I(inode)->sysctl_inodes); + if (!--head->count) + kfree_rcu(head, rcu); + spin_unlock(&sysctl_lock); +} + static struct ctl_table_header *grab_header(struct inode *inode) { struct ctl_table_header *head = PROC_I(inode)->sysctl; --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -143,6 +143,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; + struct list_head inodes; /* head for proc_inode->sysctl_inodes */ };

struct ctl_dir {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric W. Biederman ebiederm@xmission.com

commit 2fd1d2c4ceb2248a727696962cf3370dc9f5a0a4 upstream.

Andrei Vagin writes: FYI: This bug has been reproduced on 4.11.7

BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo} still in use (1) [unmount of proc proc] ------------[ cut here ]------------ WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80 CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1 Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015 Workqueue: events proc_cleanup_work Call Trace: dump_stack+0x63/0x86 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 umount_check+0x6e/0x80 d_walk+0xc6/0x270 ? dentry_free+0x80/0x80 do_one_tree+0x26/0x40 shrink_dcache_for_umount+0x2d/0x90 generic_shutdown_super+0x1f/0xf0 kill_anon_super+0x12/0x20 proc_kill_sb+0x40/0x50 deactivate_locked_super+0x43/0x70 deactivate_super+0x5a/0x60 cleanup_mnt+0x3f/0x90 mntput_no_expire+0x13b/0x190 kern_unmount+0x3e/0x50 pid_ns_release_proc+0x15/0x20 proc_cleanup_work+0x15/0x20 process_one_work+0x197/0x450 worker_thread+0x4e/0x4a0 kthread+0x109/0x140 ? process_one_work+0x450/0x450 ? kthread_park+0x90/0x90 ret_from_fork+0x2c/0x40 ---[ end trace e1c109611e5d0b41 ]--- VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds. Have a nice day... BUG: unable to handle kernel NULL pointer dereference at (null) IP: _raw_spin_lock+0xc/0x30 PGD 0

Fix this by taking a reference to the super block in proc_sys_prune_dcache.

The superblock reference is the core of the fix however the sysctl_inodes list is converted to a hlist so that hlist_del_init_rcu may be used. This allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while not causing problems for proc_sys_evict_inode when if it later choses to remove the inode from the sysctl_inodes list. Removing inodes from the sysctl_inodes list allows proc_sys_prune_dcache to have a progress guarantee, while still being able to drop all locks. The fact that head->unregistering is set in start_unregistering ensures that no more inodes will be added to the the sysctl_inodes list.

Previously the code did a dance where it delayed calling iput until the next entry in the list was being considered to ensure the inode remained on the sysctl_inodes list until the next entry was walked to. The structure of the loop in this patch does not need that so is much easier to understand and maintain.

Cc: stable@vger.kernel.org Reported-by: Andrei Vagin avagin@gmail.com Tested-by: Andrei Vagin avagin@openvz.org Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.") Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering") Signed-off-by: "Eric W. Biederman" ebiederm@xmission.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/proc/internal.h | 2 +- fs/proc/proc_sysctl.c | 43 ++++++++++++++++++++++++++++++------------- include/linux/sysctl.h | 2 +- 3 files changed, 32 insertions(+), 15 deletions(-)

--- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -65,7 +65,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; - struct list_head sysctl_inodes; + struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; }; --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -190,7 +190,7 @@ static void init_header(struct ctl_table head->set = set; head->parent = NULL; head->node = node; - INIT_LIST_HEAD(&head->inodes); + INIT_HLIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -260,25 +260,42 @@ static void unuse_table(struct ctl_table complete(p->unregistering); }

-/* called under sysctl_lock */ static void proc_sys_prune_dcache(struct ctl_table_header *head) { - struct inode *inode, *prev = NULL; + struct inode *inode; struct proc_inode *ei; + struct hlist_node *node; + struct super_block *sb;

rcu_read_lock(); - list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) { - inode = igrab(&ei->vfs_inode); - if (inode) { - rcu_read_unlock(); - iput(prev); - prev = inode; - d_prune_aliases(inode); + for (;;) { + node = hlist_first_rcu(&head->inodes); + if (!node) + break; + ei = hlist_entry(node, struct proc_inode, sysctl_inodes); + spin_lock(&sysctl_lock); + hlist_del_init_rcu(&ei->sysctl_inodes); + spin_unlock(&sysctl_lock); + + inode = &ei->vfs_inode; + sb = inode->i_sb; + if (!atomic_inc_not_zero(&sb->s_active)) + continue; + inode = igrab(inode); + rcu_read_unlock(); + if (unlikely(!inode)) { + deactivate_super(sb); rcu_read_lock(); + continue; } + + d_prune_aliases(inode); + iput(inode); + deactivate_super(sb); + + rcu_read_lock(); } rcu_read_unlock(); - iput(prev); }

/* called under sysctl_lock, will reacquire if has to wait */ @@ -464,7 +481,7 @@ static struct inode *proc_sys_make_inode } ei->sysctl = head; ei->sysctl_entry = table; - list_add_rcu(&ei->sysctl_inodes, &head->inodes); + hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes); head->count++; spin_unlock(&sysctl_lock);

@@ -492,7 +509,7 @@ out: void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { spin_lock(&sysctl_lock); - list_del_rcu(&PROC_I(inode)->sysctl_inodes); + hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes); if (!--head->count) kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -143,7 +143,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; - struct list_head inodes; /* head for proc_inode->sysctl_inodes */ + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ };

struct ctl_dir {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jack Morgenstein jackm@dev.mellanox.co.il

commit d8f9cc328c8888369880e2527e9186d745f2bbf6 upstream.

To allow rereg_user_mr to modify the MR from read-only to writable without using get_user_pages again, we needed to define the initial MR as writable. However, this was originally done unconditionally, without taking into account the writability of the underlying virtual memory.

As a result, any attempt to register a read-only MR over read-only virtual memory failed.

To fix this, do not add the writable flag bit when the user virtual memory is not writable (e.g. const memory).

However, when the underlying memory is NOT writable (and we therefore do not define the initial MR as writable), the IB core adds a "force writable" flag to its user-pages request. If this succeeds, the reg_user_mr caller gets a writable copy of the original pages.

If the user-space caller then does a rereg_user_mr operation to enable writability, this will succeed. This should not be allowed, since the original virtual memory was not writable.

Cc: stable@vger.kernel.org Fixes: 9376932d0c26 ("IB/mlx4_ib: Add support for user MR re-registration") Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Jack Morgenstein jackm@dev.mellanox.co.il Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/hw/mlx4/mr.c | 50 +++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 8 deletions(-)

--- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -131,6 +131,40 @@ out: return err; }

+static struct ib_umem *mlx4_get_umem_mr(struct ib_ucontext *context, u64 start, + u64 length, u64 virt_addr, + int access_flags) +{ + /* + * Force registering the memory as writable if the underlying pages + * are writable. This is so rereg can change the access permissions + * from readable to writable without having to run through ib_umem_get + * again + */ + if (!ib_access_writable(access_flags)) { + struct vm_area_struct *vma; + + down_read(&current->mm->mmap_sem); + /* + * FIXME: Ideally this would iterate over all the vmas that + * cover the memory, but for now it requires a single vma to + * entirely cover the MR to support RO mappings. + */ + vma = find_vma(current->mm, start); + if (vma && vma->vm_end >= start + length && + vma->vm_start <= start) { + if (vma->vm_flags & VM_WRITE) + access_flags |= IB_ACCESS_LOCAL_WRITE; + } else { + access_flags |= IB_ACCESS_LOCAL_WRITE; + } + + up_read(&current->mm->mmap_sem); + } + + return ib_umem_get(context, start, length, access_flags, 0); +} + struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int access_flags, struct ib_udata *udata) @@ -145,10 +179,8 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct if (!mr) return ERR_PTR(-ENOMEM);

- /* Force registering the memory as writable. */ - /* Used for memory re-registeration. HCA protects the access */ - mr->umem = ib_umem_get(pd->uobject->context, start, length, - access_flags | IB_ACCESS_LOCAL_WRITE, 0); + mr->umem = mlx4_get_umem_mr(pd->uobject->context, start, length, + virt_addr, access_flags); if (IS_ERR(mr->umem)) { err = PTR_ERR(mr->umem); goto err_free; @@ -215,6 +247,9 @@ int mlx4_ib_rereg_user_mr(struct ib_mr * }

if (flags & IB_MR_REREG_ACCESS) { + if (ib_access_writable(mr_access_flags) && !mmr->umem->writable) + return -EPERM; + err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry, convert_access(mr_access_flags));

@@ -228,10 +263,9 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *

mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr); ib_umem_release(mmr->umem); - mmr->umem = ib_umem_get(mr->uobject->context, start, length, - mr_access_flags | - IB_ACCESS_LOCAL_WRITE, - 0); + mmr->umem = + mlx4_get_umem_mr(mr->uobject->context, start, length, + virt_addr, mr_access_flags); if (IS_ERR(mmr->umem)) { err = PTR_ERR(mmr->umem); /* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Mera dev@michaelmera.com

commit 062d0f22a30c39840ea49b72cfcfc1aa4cc538fa upstream.

In write to debugfs file 'resource_stats' the local buffer 'tmp_str' is written at index 'count-1' where 'count' is the size of the write, so potentially 0.

This patch filters odd values for the write size/position to avoid this type of problem.

Signed-off-by: Michael Mera dev@michaelmera.com Reviewed-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Amit Pundir amit.pundir@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/hw/ocrdma/ocrdma_stats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c @@ -645,7 +645,7 @@ static ssize_t ocrdma_dbgfs_ops_write(st struct ocrdma_stats *pstats = filp->private_data; struct ocrdma_dev *dev = pstats->dev;

- if (count > 32) + if (*ppos != 0 || count == 0 || count > sizeof(tmp_str)) goto err;

if (copy_from_user(tmp_str, buffer, count))

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra peterz@infradead.org

commit 5800dc5c19f34e6e03b5adab1282535cb102fafd upstream.

Nadav reported that on guests we're failing to rewrite the indirect calls to CALLEE_SAVE paravirt functions. In particular the pv_queued_spin_unlock() call is left unpatched and that is all over the place. This obviously wrecks Spectre-v2 mitigation (for paravirt guests) which relies on not actually having indirect calls around.

The reason is an incorrect clobber test in paravirt_patch_call(); this function rewrites an indirect call with a direct call to the _SAME_ function, there is no possible way the clobbers can be different because of this.

Therefore remove this clobber check. Also put WARNs on the other patch failure case (not enough room for the instruction) which I've not seen trigger in my (limited) testing.

Three live kernel image disassemblies for lock_sock_nested (as a small function that illustrates the problem nicely). PRE is the current situation for guests, POST is with this patch applied and NATIVE is with or without the patch for !guests.

PRE:

(gdb) disassemble lock_sock_nested Dump of assembler code for function lock_sock_nested: 0xffffffff817be970 <+0>: push %rbp 0xffffffff817be971 <+1>: mov %rdi,%rbp 0xffffffff817be974 <+4>: push %rbx 0xffffffff817be975 <+5>: lea 0x88(%rbp),%rbx 0xffffffff817be97c <+12>: callq 0xffffffff819f7160 <_cond_resched> 0xffffffff817be981 <+17>: mov %rbx,%rdi 0xffffffff817be984 <+20>: callq 0xffffffff819fbb00 <_raw_spin_lock_bh> 0xffffffff817be989 <+25>: mov 0x8c(%rbp),%eax 0xffffffff817be98f <+31>: test %eax,%eax 0xffffffff817be991 <+33>: jne 0xffffffff817be9ba <lock_sock_nested+74> 0xffffffff817be993 <+35>: movl $0x1,0x8c(%rbp) 0xffffffff817be99d <+45>: mov %rbx,%rdi 0xffffffff817be9a0 <+48>: callq *0xffffffff822299e8 0xffffffff817be9a7 <+55>: pop %rbx 0xffffffff817be9a8 <+56>: pop %rbp 0xffffffff817be9a9 <+57>: mov $0x200,%esi 0xffffffff817be9ae <+62>: mov $0xffffffff817be993,%rdi 0xffffffff817be9b5 <+69>: jmpq 0xffffffff81063ae0 <__local_bh_enable_ip> 0xffffffff817be9ba <+74>: mov %rbp,%rdi 0xffffffff817be9bd <+77>: callq 0xffffffff817be8c0 <__lock_sock> 0xffffffff817be9c2 <+82>: jmp 0xffffffff817be993 <lock_sock_nested+35> End of assembler dump.

POST:

(gdb) disassemble lock_sock_nested Dump of assembler code for function lock_sock_nested: 0xffffffff817be970 <+0>: push %rbp 0xffffffff817be971 <+1>: mov %rdi,%rbp 0xffffffff817be974 <+4>: push %rbx 0xffffffff817be975 <+5>: lea 0x88(%rbp),%rbx 0xffffffff817be97c <+12>: callq 0xffffffff819f7160 <_cond_resched> 0xffffffff817be981 <+17>: mov %rbx,%rdi 0xffffffff817be984 <+20>: callq 0xffffffff819fbb00 <_raw_spin_lock_bh> 0xffffffff817be989 <+25>: mov 0x8c(%rbp),%eax 0xffffffff817be98f <+31>: test %eax,%eax 0xffffffff817be991 <+33>: jne 0xffffffff817be9ba <lock_sock_nested+74> 0xffffffff817be993 <+35>: movl $0x1,0x8c(%rbp) 0xffffffff817be99d <+45>: mov %rbx,%rdi 0xffffffff817be9a0 <+48>: callq 0xffffffff810a0c20 <__raw_callee_save___pv_queued_spin_unlock> 0xffffffff817be9a5 <+53>: xchg %ax,%ax 0xffffffff817be9a7 <+55>: pop %rbx 0xffffffff817be9a8 <+56>: pop %rbp 0xffffffff817be9a9 <+57>: mov $0x200,%esi 0xffffffff817be9ae <+62>: mov $0xffffffff817be993,%rdi 0xffffffff817be9b5 <+69>: jmpq 0xffffffff81063aa0 <__local_bh_enable_ip> 0xffffffff817be9ba <+74>: mov %rbp,%rdi 0xffffffff817be9bd <+77>: callq 0xffffffff817be8c0 <__lock_sock> 0xffffffff817be9c2 <+82>: jmp 0xffffffff817be993 <lock_sock_nested+35> End of assembler dump.

NATIVE:

(gdb) disassemble lock_sock_nested Dump of assembler code for function lock_sock_nested: 0xffffffff817be970 <+0>: push %rbp 0xffffffff817be971 <+1>: mov %rdi,%rbp 0xffffffff817be974 <+4>: push %rbx 0xffffffff817be975 <+5>: lea 0x88(%rbp),%rbx 0xffffffff817be97c <+12>: callq 0xffffffff819f7160 <_cond_resched> 0xffffffff817be981 <+17>: mov %rbx,%rdi 0xffffffff817be984 <+20>: callq 0xffffffff819fbb00 <_raw_spin_lock_bh> 0xffffffff817be989 <+25>: mov 0x8c(%rbp),%eax 0xffffffff817be98f <+31>: test %eax,%eax 0xffffffff817be991 <+33>: jne 0xffffffff817be9ba <lock_sock_nested+74> 0xffffffff817be993 <+35>: movl $0x1,0x8c(%rbp) 0xffffffff817be99d <+45>: mov %rbx,%rdi 0xffffffff817be9a0 <+48>: movb $0x0,(%rdi) 0xffffffff817be9a3 <+51>: nopl 0x0(%rax) 0xffffffff817be9a7 <+55>: pop %rbx 0xffffffff817be9a8 <+56>: pop %rbp 0xffffffff817be9a9 <+57>: mov $0x200,%esi 0xffffffff817be9ae <+62>: mov $0xffffffff817be993,%rdi 0xffffffff817be9b5 <+69>: jmpq 0xffffffff81063ae0 <__local_bh_enable_ip> 0xffffffff817be9ba <+74>: mov %rbp,%rdi 0xffffffff817be9bd <+77>: callq 0xffffffff817be8c0 <__lock_sock> 0xffffffff817be9c2 <+82>: jmp 0xffffffff817be993 <lock_sock_nested+35> End of assembler dump.

Fixes: 63f70270ccd9 ("[PATCH] i386: PARAVIRT: add common patching machinery") Fixes: 3010a0663fd9 ("x86/paravirt, objtool: Annotate indirect calls") Reported-by: Nadav Amit namit@vmware.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Juergen Gross jgross@suse.com Cc: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Cc: Boris Ostrovsky boris.ostrovsky@oracle.com Cc: David Woodhouse dwmw2@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/paravirt.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

--- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnb struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5);

- if (tgt_clobbers & ~site_clobbers) - return len; /* target would clobber too much for this site */ - if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + }

b->opcode = 0xe8; /* call */ b->delta = delta; @@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbu struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5);

- if (len < 5) + if (len < 5) { +#ifdef CONFIG_RETPOLINE + WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); +#endif return len; /* call too long for patch site */ + }

b->opcode = 0xe9; /* jmp */ b->delta = delta;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Hiramatsu mhiramat@kernel.org

commit 0ea063306eecf300fcf06d2f5917474b580f666f upstream.

Remove all %p uses in error messages in kprobes/x86.

Signed-off-by: Masami Hiramatsu mhiramat@kernel.org Cc: Ananth N Mavinakayanahalli ananth@in.ibm.com Cc: Anil S Keshavamurthy anil.s.keshavamurthy@intel.com Cc: Arnd Bergmann arnd@arndb.de Cc: David Howells dhowells@redhat.com Cc: David S . Miller davem@davemloft.net Cc: Heiko Carstens heiko.carstens@de.ibm.com Cc: Jon Medhurst tixy@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Thomas Richter tmricht@linux.ibm.com Cc: Tobin C . Harding me@tobin.cc Cc: Will Deacon will.deacon@arm.com Cc: acme@kernel.org Cc: akpm@linux-foundation.org Cc: brueckner@linux.vnet.ibm.com Cc: linux-arch@vger.kernel.org Cc: rostedt@goodmis.org Cc: schwidefsky@de.ibm.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/lkml/152491902310.9916.13355297638917767319.stgit@de... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kernel/kprobes/core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -396,7 +396,6 @@ int __copy_instruction(u8 *dest, u8 *src newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); - pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(&insn); @@ -612,8 +611,7 @@ static int reenter_kprobe(struct kprobe * Raise a BUG or we'll continue in an endless reentering loop * and eventually a stack overflow. */ - printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n", - p->addr); + pr_err("Unrecoverable kprobe detected.\n"); dump_kprobe(p); BUG(); default:

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 50896e180c6aa3a9c61a26ced99e15d602666a4c upstream

L1 Terminal Fault (L1TF) is a speculation related vulnerability. The CPU speculates on PTE entries which do not have the PRESENT bit set, if the content of the resulting physical address is available in the L1D cache.

The OS side mitigation makes sure that a !PRESENT PTE entry points to a physical address outside the actually existing and cachable memory space. This is achieved by inverting the upper bits of the PTE. Due to the address space limitations this only works for 64bit and 32bit PAE kernels, but not for 32bit non PAE.

This mitigation applies to both host and guest kernels, but in case of a 64bit host (hypervisor) and a 32bit PAE guest, inverting the upper bits of the PAE address space (44bit) is not enough if the host has more than 43 bits of populated memory address space, because the speculation treats the PTE content as a physical host address bypassing EPT.

The host (hypervisor) protects itself against the guest by flushing L1D as needed, but pages inside the guest are not protected against attacks from other processes inside the same guest.

For the guest the inverted PTE mask has to match the host to provide the full protection for all pages the host could possibly map into the guest. The hosts populated address space is not known to the guest, so the mask must cover the possible maximal host address space, i.e. 52 bit.

On 32bit PAE the maximum PTE mask is currently set to 44 bit because that is the limit imposed by 32bit unsigned long PFNs in the VMs. This limits the mask to be below what the host could possible use for physical pages.

The L1TF PROT_NONE protection code uses the PTE masks to determine which bits to invert to make sure the higher bits are set for unmapped entries to prevent L1TF speculation attacks against EPT inside guests.

In order to invert all bits that could be used by the host, increase __PHYSICAL_PAGE_SHIFT to 52 to match 64bit.

The real limit for a 32bit PAE kernel is still 44 bits because all Linux PTEs are created from unsigned long PFNs, so they cannot be higher than 44 bits on a 32bit kernel. So these extra PFN bits should be never set. The only users of this macro are using it to look at PTEs, so it's safe.

[ tglx: Massaged changelog ]

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Michal Hocko mhocko@suse.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/page_32_types.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -28,8 +28,13 @@ #define N_EXCEPTION_STACKS 1

#ifdef CONFIG_X86_PAE -/* 44=32+12, the limit we can fit into an unsigned long pfn */ -#define __PHYSICAL_MASK_SHIFT 44 +/* + * This is beyond the 44 bit limit imposed by the 32bit long pfns, + * but we need the full mask to make sure inverted PROT_NONE + * entries have all the host bits set in a guest. + * The real limit is still 44 bits. + */ +#define __PHYSICAL_MASK_SHIFT 52 #define __VIRTUAL_MASK_SHIFT 32

#else /* !CONFIG_X86_PAE */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Linus Torvalds torvalds@linux-foundation.org

commit bcd11afa7adad8d720e7ba5ef58bdcd9775cf45f upstream

If pages are swapped out, the swap entry is stored in the corresponding PTE, which has the Present bit cleared. CPUs vulnerable to L1TF speculate on PTE entries which have the present bit set and would treat the swap entry as phsyical address (PFN). To mitigate that the upper bits of the PTE must be set so the PTE points to non existent memory.

The swap entry stores the type and the offset of a swapped out page in the PTE. type is stored in bit 9-13 and offset in bit 14-63. The hardware ignores the bits beyond the phsyical address space limit, so to make the mitigation effective its required to start 'offset' at the lowest possible bit so that even large swap offsets do not reach into the physical address space limit bits.

Move offset to bit 9-58 and type to bit 59-63 which are the bits that hardware generally doesn't care about.

That, in turn, means that if you on desktop chip with only 40 bits of physical addressing, now that the offset starts at bit 9, there needs to be 30 bits of offset actually *in use* until bit 39 ends up being set, which means when inverted it will again point into existing memory.

So that's 4 terabyte of swap space (because the offset is counted in pages, so 30 bits of offset is 42 bits of actual coverage). With bigger physical addressing, that obviously grows further, until the limit of the offset is hit (at 50 bits of offset - 62 bits of actual swap file coverage).

This is a preparatory change for the actual swap entry inversion to protect against L1TF.

[ AK: Updated description and minor tweaks. Split into two parts ] [ tglx: Massaged changelog ]

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Andi Kleen ak@linux.intel.com Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Michal Hocko mhocko@suse.com Acked-by: Vlastimil Babka vbabka@suse.cz Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/pgtable_64.h | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-)

--- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -168,7 +168,7 @@ static inline int pgd_large(pgd_t pgd) { * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names - * | OFFSET (14->63) | TYPE (9-13) |0|0|X|X| X| X|X|SD|0| <- swp entry + * | TYPE (59-63) | OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -182,19 +182,28 @@ static inline int pgd_large(pgd_t pgd) { * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. */ -#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) -#define SWP_TYPE_BITS 5 -/* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)

#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)

-#define __swp_type(x) (((x).val >> (SWP_TYPE_FIRST_BIT)) \ - & ((1U << SWP_TYPE_BITS) - 1)) -#define __swp_offset(x) ((x).val >> SWP_OFFSET_FIRST_BIT) -#define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << (SWP_TYPE_FIRST_BIT)) \ - | ((offset) << SWP_OFFSET_FIRST_BIT) }) +/* Extract the high bits for type */ +#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) + +/* Shift up (to get rid of type), then down to get value */ +#define __swp_offset(x) ((x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) + +/* + * Shift the offset up "too far" by TYPE bits, then down again + */ +#define __swp_entry(type, offset) ((swp_entry_t) { \ + ((unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) + #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 6b28baca9b1f0d4a42b865da7a05b1c81424bd5c upstream

When PTEs are set to PROT_NONE the kernel just clears the Present bit and preserves the PFN, which creates attack surface for L1TF speculation speculation attacks.

This is important inside guests, because L1TF speculation bypasses physical page remapping. While the host has its own migitations preventing leaking data from other VMs into the guest, this would still risk leaking the wrong page inside the current guest.

This uses the same technique as Linus' swap entry patch: while an entry is is in PROTNONE state invert the complete PFN part part of it. This ensures that the the highest bit will point to non existing memory.

The invert is done by pte/pmd_modify and pfn/pmd/pud_pte for PROTNONE and pte/pmd/pud_pfn undo it.

This assume that no code path touches the PFN part of a PTE directly without using these primitives.

This doesn't handle the case that MMIO is on the top of the CPU physical memory. If such an MMIO region was exposed by an unpriviledged driver for mmap it would be possible to attack some real memory. However this situation is all rather unlikely.

For 32bit non PAE the inversion is not done because there are really not enough bits to protect anything.

Q: Why does the guest need to be protected when the HyperVisor already has L1TF mitigations?

A: Here's an example:

Physical pages 1 2 get mapped into a guest as GPA 1 -> PA 2 GPA 2 -> PA 1 through EPT.

The L1TF speculation ignores the EPT remapping.

Now the guest kernel maps GPA 1 to process A and GPA 2 to process B, and they belong to different users and should be isolated.

A sets the GPA 1 PA 2 PTE to PROT_NONE to bypass the EPT remapping and gets read access to the underlying physical page. Which in this case points to PA 2, so it can read process B's data, if it happened to be in L1, so isolation inside the guest is broken.

There's nothing the hypervisor can do about this. This mitigation has to be done in the guest itself.

[ tglx: Massaged changelog ] [ dwmw2: backported to 4.9 ]

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Michal Hocko mhocko@suse.com Acked-by: Vlastimil Babka vbabka@suse.cz Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/pgtable-2level.h | 17 +++++++++++++++ arch/x86/include/asm/pgtable-3level.h | 2 + arch/x86/include/asm/pgtable-invert.h | 32 ++++++++++++++++++++++++++++ arch/x86/include/asm/pgtable.h | 38 ++++++++++++++++++++++++---------- arch/x86/include/asm/pgtable_64.h | 2 + 5 files changed, 80 insertions(+), 11 deletions(-) create mode 100644 arch/x86/include/asm/pgtable-invert.h

--- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -77,4 +77,21 @@ static inline unsigned long pte_bitop(un #define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })

+/* No inverted PFNs on 2 level page tables */ + +static inline u64 protnone_mask(u64 val) +{ + return 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + return val; +} + +static inline bool __pte_needs_invert(u64 val) +{ + return false; +} + #endif /* _ASM_X86_PGTABLE_2LEVEL_H */ --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -184,4 +184,6 @@ static inline pmd_t native_pmdp_get_and_ #define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } })

+#include <asm/pgtable-invert.h> + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ --- /dev/null +++ b/arch/x86/include/asm/pgtable-invert.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_PGTABLE_INVERT_H +#define _ASM_PGTABLE_INVERT_H 1 + +#ifndef __ASSEMBLY__ + +static inline bool __pte_needs_invert(u64 val) +{ + return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE; +} + +/* Get a mask to xor with the page table entry to get the correct pfn. */ +static inline u64 protnone_mask(u64 val) +{ + return __pte_needs_invert(val) ? ~0ull : 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + /* + * When a PTE transitions from NONE to !NONE or vice-versa + * invert the PFN part to stop speculation. + * pte_pfn undoes this when needed. + */ + if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) + val = (val & ~mask) | (~val & mask); + return val; +} + +#endif /* __ASSEMBLY__ */ + +#endif --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -165,19 +165,29 @@ static inline int pte_special(pte_t pte) return pte_flags(pte) & _PAGE_SPECIAL; }

+/* Entries that were set to PROT_NONE are inverted */ + +static inline u64 protnone_mask(u64 val); + static inline unsigned long pte_pfn(pte_t pte) { - return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT; + unsigned long pfn = pte_val(pte); + pfn ^= protnone_mask(pfn); + return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; }

static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; + unsigned long pfn = pmd_val(pmd); + pfn ^= protnone_mask(pfn); + return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; }

static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; + unsigned long pfn = pud_val(pud); + pfn ^= protnone_mask(pfn); + return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; }

#define pte_page(pte) pfn_to_page(pte_pfn(pte)) @@ -394,19 +404,25 @@ static inline pgprotval_t massage_pgprot

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) | - massage_pgprot(pgprot)); + phys_addr_t pfn = page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PTE_PFN_MASK; + return __pte(pfn | massage_pgprot(pgprot)); }

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) | - massage_pgprot(pgprot)); + phys_addr_t pfn = page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PMD_PAGE_MASK; + return __pmd(pfn | massage_pgprot(pgprot)); }

+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - pteval_t val = pte_val(pte); + pteval_t val = pte_val(pte), oldval = val;

/* * Chop off the NX bit (if present), and add the NX portion of @@ -414,17 +430,17 @@ static inline pte_t pte_modify(pte_t pte */ val &= _PAGE_CHG_MASK; val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); }

static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmdval_t val = pmd_val(pmd); + pmdval_t val = pmd_val(pmd), oldval = val;

val &= _HPAGE_CHG_MASK; val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK; - + val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); }

--- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -235,6 +235,8 @@ extern void cleanup_highmap(void); extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);

+#include <asm/pgtable-invert.h> + #endif /* !__ASSEMBLY__ */

#endif /* _ASM_X86_PGTABLE_64_H */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 17dbca119312b4e8173d4e25ff64262119fcef38 upstream

L1TF core kernel workarounds are cheap and normally always enabled, However they still should be reported in sysfs if the system is vulnerable or mitigated. Add the necessary CPU feature/bug bits.

- Extend the existing checks for Meltdowns to determine if the system is vulnerable. All CPUs which are not vulnerable to Meltdown are also not vulnerable to L1TF

- Check for 32bit non PAE and emit a warning as there is no practical way for mitigation due to the limited physical address bits

- If the system has more than MAX_PA/2 physical memory the invert page workarounds don't protect the system against the L1TF attack anymore, because an inverted physical address will also point to valid memory. Print a warning in this case and report that the system is vulnerable.

Add a function which returns the PFN limit for the L1TF mitigation, which will be used in follow up patches for sanity and range checks.

[ tglx: Renamed the CPU feature bit to L1TF_PTEINV ] [ dwmw2: Backport to 4.9 (cpufeatures.h, E820) ]

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 3 +- arch/x86/include/asm/processor.h | 5 ++++ arch/x86/kernel/cpu/bugs.c | 40 +++++++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/common.c | 20 ++++++++++++++++++ drivers/base/cpu.c | 8 +++++++ include/linux/cpu.h | 2 + 6 files changed, 77 insertions(+), 1 deletion(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -213,7 +213,7 @@ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ - +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */

/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -349,5 +349,6 @@ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */

#endif /* _ASM_X86_CPUFEATURES_H */ --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -173,6 +173,11 @@ extern const struct seq_operations cpuin

extern void cpu_detect(struct cpuinfo_x86 *c);

+static inline unsigned long l1tf_pfn_limit(void) +{ + return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1; +} + extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -26,9 +26,11 @@ #include <asm/pgtable.h> #include <asm/cacheflush.h> #include <asm/intel-family.h> +#include <asm/e820.h>

static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); +static void __init l1tf_select_mitigation(void);

/* * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any @@ -80,6 +82,8 @@ void __init check_bugs(void) */ ssb_select_mitigation();

+ l1tf_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -204,6 +208,32 @@ static void x86_amd_ssb_disable(void) wrmsrl(MSR_AMD64_LS_CFG, msrval); }

+static void __init l1tf_select_mitigation(void) +{ + u64 half_pa; + + if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return; + +#if CONFIG_PGTABLE_LEVELS == 2 + pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n"); + return; +#endif + + /* + * This is extremely unlikely to happen because almost all + * systems have far more MAX_PA/2 than RAM can be fit into + * DIMM slots. + */ + half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; + if (e820_any_mapped(half_pa, ULLONG_MAX - half_pa, E820_RAM)) { + pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); + return; + } + + setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV); +} + #ifdef RETPOLINE static bool spectre_v2_bad_module;

@@ -656,6 +686,11 @@ static ssize_t cpu_show_common(struct de case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);

+ case X86_BUG_L1TF: + if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) + return sprintf(buf, "Mitigation: Page Table Inversion\n"); + break; + default: break; } @@ -682,4 +717,9 @@ ssize_t cpu_show_spec_store_bypass(struc { return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } + +ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); +} #endif --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -925,6 +925,21 @@ static const __initconst struct x86_cpu_ {} };

+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { + /* in addition to cpu_no_speculation */ + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + {} +}; + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; @@ -950,6 +965,11 @@ static void __init cpu_set_bug_bits(stru return;

setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + + if (x86_match_cpu(cpu_no_l1tf)) + return; + + setup_force_cpu_bug(X86_BUG_L1TF); }

/* --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -525,16 +525,24 @@ ssize_t __weak cpu_show_spec_store_bypas return sprintf(buf, "Not affected\n"); }

+ssize_t __weak cpu_show_l1tf(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL); +static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);

static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, &dev_attr_spectre_v1.attr, &dev_attr_spectre_v2.attr, &dev_attr_spec_store_bypass.attr, + &dev_attr_l1tf.attr, NULL };

--- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -52,6 +52,8 @@ extern ssize_t cpu_show_spectre_v2(struc struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_l1tf(struct device *dev, + struct device_attribute *attr, char *buf);

extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 377eeaa8e11fe815b1d07c81c4a0e2843a8c15eb upstream

For the L1TF workaround its necessary to limit the swap file size to below MAX_PA/2, so that the higher bits of the swap offset inverted never point to valid memory.

Add a mechanism for the architecture to override the swap file size check in swapfile.c and add a x86 specific max swapfile check function that enforces that limit.

The check is only enabled if the CPU is vulnerable to L1TF.

In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system with 46bit PA it is 32TB. The limit is only per individual swap file, so it's always possible to exceed these limits with multiple swap files or partitions.

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Michal Hocko mhocko@suse.com Acked-by: Dave Hansen dave.hansen@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/init.c | 15 +++++++++++++++ include/linux/swapfile.h | 2 ++ mm/swapfile.c | 46 ++++++++++++++++++++++++++++++---------------- 3 files changed, 47 insertions(+), 16 deletions(-)

--- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -4,6 +4,8 @@ #include <linux/swap.h> #include <linux/memblock.h> #include <linux/bootmem.h> /* for max_low_pfn */ +#include <linux/swapfile.h> +#include <linux/swapops.h>

#include <asm/cacheflush.h> #include <asm/e820.h> @@ -780,3 +782,16 @@ void update_cache_mode_entry(unsigned en __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } + +unsigned long max_swapfile_size(void) +{ + unsigned long pages; + + pages = generic_max_swapfile_size(); + + if (boot_cpu_has_bug(X86_BUG_L1TF)) { + /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ + pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages); + } + return pages; +} --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -9,5 +9,7 @@ extern spinlock_t swap_lock; extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern int try_to_unuse(unsigned int, bool, unsigned long); +extern unsigned long generic_max_swapfile_size(void); +extern unsigned long max_swapfile_size(void);

#endif /* _LINUX_SWAPFILE_H */ --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2219,6 +2219,35 @@ static int claim_swapfile(struct swap_in return 0; }

+ +/* + * Find out how many pages are allowed for a single swap device. There + * are two limiting factors: + * 1) the number of bits for the swap offset in the swp_entry_t type, and + * 2) the number of bits in the swap pte, as defined by the different + * architectures. + * + * In order to find the largest possible bit mask, a swap entry with + * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, + * decoded to a swp_entry_t again, and finally the swap offset is + * extracted. + * + * This will mask all the bits from the initial ~0UL mask that can't + * be encoded in either the swp_entry_t or the architecture definition + * of a swap pte. + */ +unsigned long generic_max_swapfile_size(void) +{ + return swp_offset(pte_to_swp_entry( + swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; +} + +/* Can be overridden by an architecture for additional checks. */ +__weak unsigned long max_swapfile_size(void) +{ + return generic_max_swapfile_size(); +} + static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) @@ -2254,22 +2283,7 @@ static unsigned long read_swap_header(st p->cluster_next = 1; p->cluster_nr = 0;

- /* - * Find out how many pages are allowed for a single swap - * device. There are two limiting factors: 1) the number - * of bits for the swap offset in the swp_entry_t type, and - * 2) the number of bits in the swap pte as defined by the - * different architectures. In order to find the - * largest possible bit mask, a swap entry with swap type 0 - * and swap offset ~0UL is created, encoded to a swap pte, - * decoded to a swp_entry_t again, and finally the swap - * offset is extracted. This will mask all the bits from - * the initial ~0UL mask that can't be encoded in either - * the swp_entry_t or the architecture definition of a - * swap pte. - */ - maxpages = swp_offset(pte_to_swp_entry( - swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; + maxpages = max_swapfile_size(); last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n");

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 6a4d2657e048f096c7ffcad254010bd94891c8c0 upstream

If the CPU is supporting SMT then the primary thread can be found by checking the lower APIC ID bits for zero. smp_num_siblings is used to build the mask for the APIC ID bits which need to be taken into account.

This uses the MPTABLE or ACPI/MADT supplied APIC ID, which can be different than the initial APIC ID in CPUID. But according to AMD the lower bits have to be consistent. Intel gave a tentative confirmation as well.

Preparatory patch to support disabling SMT at boot/runtime.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/apic.h | 7 +++++++ arch/x86/include/asm/topology.h | 4 +++- arch/x86/kernel/apic/apic.c | 15 +++++++++++++++ arch/x86/kernel/smpboot.c | 9 +++++++++ 4 files changed, 34 insertions(+), 1 deletion(-)

--- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -633,6 +633,13 @@ extern int default_check_phys_apicid_pre #endif

#endif /* CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_SMP +bool apic_id_is_primary_thread(unsigned int id); +#else +static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } +#endif + extern void irq_enter(void); extern void irq_exit(void);

--- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -129,13 +129,15 @@ static inline int topology_max_smt_threa }

int topology_update_package_map(unsigned int apicid, unsigned int cpu); -extern int topology_phys_to_logical_pkg(unsigned int pkg); +int topology_phys_to_logical_pkg(unsigned int pkg); +bool topology_is_primary_thread(unsigned int cpu); #else #define topology_max_packages() (1) static inline int topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_smt_threads(void) { return 1; } +static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } #endif

static inline void arch_fix_phys_package_id(int num, u32 slot) --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2041,6 +2041,21 @@ static int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, };

+/** + * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread + * @id: APIC ID to check + */ +bool apic_id_is_primary_thread(unsigned int apicid) +{ + u32 mask; + + if (smp_num_siblings == 1) + return true; + /* Isolate the SMT bit(s) in the APICID and check for 0 */ + mask = (1U << (fls(smp_num_siblings) - 1)) - 1; + return !(apicid & mask); +} + /* * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids * and cpuid_to_apicid[] synchronized. --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -296,6 +296,15 @@ found: }

/** + * topology_is_primary_thread - Check whether CPU is the primary SMT thread + * @cpu: CPU to check + */ +bool topology_is_primary_thread(unsigned int cpu) +{ + return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu)); +} + +/** * topology_phys_to_logical_pkg - Map a physical package id to a logical * * Returns logical package id or -1 if not found

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit c4de65696d865c225fda3b9913b31284ea65ea96 upstream

The asymmetry caused a warning to trigger if the bootup was stopped in state CPUHP_AP_ONLINE_IDLE. The warning no longer triggers as kthread_park() can now be invoked on already or still parked threads. But there is still no reason to have this be asymmetric.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cpu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -817,7 +817,6 @@ static int takedown_cpu(unsigned int cpu

/* Park the smpboot threads */ kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); - smpboot_park_threads(cpu);

/* * Prevent irq alloc/free while the dying cpu reorganizes the @@ -1389,7 +1388,7 @@ static struct cpuhp_step cpuhp_ap_states [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, - .teardown.single = NULL, + .teardown.single = smpboot_park_threads, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online",

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 05736e4ac13c08a4a9b1ef2de26dd31a32cbee57 upstream

Provide a command line and a sysfs knob to control SMT.

The command line options are:

'nosmt': Enumerate secondary threads, but do not online them

'nosmt=force': Ignore secondary threads completely during enumeration via MP table and ACPI/MADT.

The sysfs control file has the following states (read/write):

'on': SMT is enabled. Secondary threads can be freely onlined 'off': SMT is disabled. Secondary threads, even if enumerated cannot be onlined 'forceoff': SMT is permanentely disabled. Writes to the control file are rejected. 'notsupported': SMT is not supported by the CPU

The command line option 'nosmt' sets the sysfs control to 'off'. This can be changed to 'on' to reenable SMT during runtime.

The command line option 'nosmt=force' sets the sysfs control to 'forceoff'. This cannot be changed during runtime.

When SMT is 'on' and the control file is changed to 'off' then all online secondary threads are offlined and attempts to online a secondary thread later on are rejected.

When SMT is 'off' and the control file is changed to 'on' then secondary threads can be onlined again. The 'off' -> 'on' transition does not automatically online the secondary threads.

When the control file is set to 'forceoff', the behaviour is the same as setting it to 'off', but the operation is irreversible and later writes to the control file are rejected.

When the control status is 'notsupported' then writes to the control file are rejected.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/ABI/testing/sysfs-devices-system-cpu | 20 ++ Documentation/kernel-parameters.txt | 8 arch/Kconfig | 3 arch/x86/Kconfig | 1 include/linux/cpu.h | 13 + kernel/cpu.c | 170 +++++++++++++++++++++ 6 files changed, 215 insertions(+)

--- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -367,3 +367,23 @@ Description: Information about CPU vulne "Not affected" CPU is not affected by the vulnerability "Vulnerable" CPU is affected and no mitigation in effect "Mitigation: $M" CPU is affected and mitigation $M is in effect + +What: /sys/devices/system/cpu/smt + /sys/devices/system/cpu/smt/active + /sys/devices/system/cpu/smt/control +Date: June 2018 +Contact: Linux kernel mailing list linux-kernel@vger.kernel.org +Description: Control Symetric Multi Threading (SMT) + + active: Tells whether SMT is active (enabled and siblings online) + + control: Read/write interface to control SMT. Possible + values: + + "on" SMT is enabled + "off" SMT is disabled + "forceoff" SMT is force disabled. Cannot be changed. + "notsupported" SMT is not supported by the CPU + + If control status is "forceoff" or "notsupported" writes + are rejected. --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2694,6 +2694,14 @@ bytes respectively. Such letter suffixes nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1.

+ [KNL,x86] Disable symmetric multithreading (SMT). + nosmt=force: Force disable SMT, similar to disabling + it in the BIOS except that some of the + resource partitioning effects which are + caused by having SMT enabled in the BIOS + cannot be undone. Depending on the CPU + type this might have a performance impact. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) vulnerability. System may allow data leaks with this option, which is equivalent --- a/arch/Kconfig +++ b/arch/Kconfig @@ -5,6 +5,9 @@ config KEXEC_CORE bool

+config HOTPLUG_SMT + bool + config OPROFILE tristate "OProfile system profiling" depends on PROFILING --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -147,6 +147,7 @@ config X86 select HAVE_UID16 if X86_32 || IA32_EMULATION select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER + select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if X86_64 select MODULES_USE_ELF_REL if X86_32 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -257,4 +257,17 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */

+enum cpuhp_smt_control { + CPU_SMT_ENABLED, + CPU_SMT_DISABLED, + CPU_SMT_FORCE_DISABLED, + CPU_SMT_NOT_SUPPORTED, +}; + +#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) +extern enum cpuhp_smt_control cpu_smt_control; +#else +# define cpu_smt_control (CPU_SMT_ENABLED) +#endif + #endif /* _LINUX_CPU_H_ */ --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -978,6 +978,29 @@ int cpu_down(unsigned int cpu) EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/

+#ifdef CONFIG_HOTPLUG_SMT +enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; + +static int __init smt_cmdline_disable(char *str) +{ + cpu_smt_control = CPU_SMT_DISABLED; + if (str && !strcmp(str, "force")) { + pr_info("SMT: Force disabled\n"); + cpu_smt_control = CPU_SMT_FORCE_DISABLED; + } + return 0; +} +early_param("nosmt", smt_cmdline_disable); + +static inline bool cpu_smt_allowed(unsigned int cpu) +{ + return cpu_smt_control == CPU_SMT_ENABLED || + topology_is_primary_thread(cpu); +} +#else +static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +#endif + /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started @@ -1096,6 +1119,10 @@ static int do_cpu_up(unsigned int cpu, e err = -EBUSY; goto out; } + if (!cpu_smt_allowed(cpu)) { + err = -EPERM; + goto out; + }

err = _cpu_up(cpu, 0, target); out: @@ -1842,10 +1869,153 @@ static struct attribute_group cpuhp_cpu_ NULL };

+#ifdef CONFIG_HOTPLUG_SMT + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); +} + +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +static void cpuhp_smt_enable(void) +{ + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + cpu_maps_update_done(); +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int ctrlval, ret; + + if (sysfs_streq(buf, "on")) + ctrlval = CPU_SMT_ENABLED; + else if (sysfs_streq(buf, "off")) + ctrlval = CPU_SMT_DISABLED; + else if (sysfs_streq(buf, "forceoff")) + ctrlval = CPU_SMT_FORCE_DISABLED; + else + return -EINVAL; + + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) + return -EPERM; + + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + return -ENODEV; + + ret = lock_device_hotplug_sysfs(); + if (ret) + return ret; + + if (ctrlval != cpu_smt_control) { + switch (ctrlval) { + case CPU_SMT_ENABLED: + cpuhp_smt_enable(); + break; + case CPU_SMT_DISABLED: + case CPU_SMT_FORCE_DISABLED: + ret = cpuhp_smt_disable(ctrlval); + break; + } + } + + unlock_device_hotplug(); + return ret ? ret : count; +} +static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); + +static ssize_t +show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) +{ + bool active = topology_max_smt_threads() > 1; + + return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); +} +static DEVICE_ATTR(active, 0444, show_smt_active, NULL); + +static struct attribute *cpuhp_smt_attrs[] = { + &dev_attr_control.attr, + &dev_attr_active.attr, + NULL +}; + +static const struct attribute_group cpuhp_smt_attr_group = { + .attrs = cpuhp_smt_attrs, + .name = "smt", + NULL +}; + +static int __init cpu_smt_state_init(void) +{ + if (!topology_smt_supported()) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; + + return sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpuhp_smt_attr_group); +} + +#else +static inline int cpu_smt_state_init(void) { return 0; } +#endif + static int __init cpuhp_sysfs_init(void) { int cpu, ret;

+ ret = cpu_smt_state_init(); + if (ret) + return ret; + ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 44ca36de56d1bf196dca2eb67cd753a46961ffe6 upstream

Real 32bit AMD CPUs do not have SMT and the only value of the call was to reach the magic printout which got removed.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/amd.c | 4 ---- 1 file changed, 4 deletions(-)

--- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -805,10 +805,6 @@ static void init_amd(struct cpuinfo_x86 srat_detect_node(c); }

-#ifdef CONFIG_X86_32 - detect_ht(c); -#endif - init_amd_cacheinfo(c);

if (c->x86 >= 0xf)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 95f3d39ccf7aaea79d1ffdac1c887c2e100ec1b6 upstream

To support force disabling of SMT it's required to know the number of thread siblings early. detect_extended_topology() cannot be called before the APIC driver is selected, so split out the part which initializes smp_num_siblings.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/cpu.h | 1 + arch/x86/kernel/cpu/topology.c | 30 ++++++++++++++++++++++++------ 2 files changed, 25 insertions(+), 6 deletions(-)

--- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -46,6 +46,7 @@ extern const struct cpu_dev *const __x86

extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); +extern int detect_extended_topology_early(struct cpuinfo_x86 *c); extern int detect_ht_early(struct cpuinfo_x86 *c);

extern void x86_spec_ctrl_setup_ap(void); --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -26,15 +26,13 @@ * exists, use it for populating initial_apicid and cpu topology * detection. */ -void detect_extended_topology(struct cpuinfo_x86 *c) +int detect_extended_topology_early(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int ht_mask_width, core_plus_mask_width; - unsigned int core_select_mask, core_level_siblings; + unsigned int eax, ebx, ecx, edx;

if (c->cpuid_level < 0xb) - return; + return -1;

cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);

@@ -42,7 +40,7 @@ void detect_extended_topology(struct cpu * check if the cpuid leaf 0xb is actually implemented. */ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) - return; + return -1;

set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);

@@ -50,10 +48,30 @@ void detect_extended_topology(struct cpu * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; + smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); +#endif + return 0; +} + +/* + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. + */ +void detect_extended_topology(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int eax, ebx, ecx, edx, sub_index; + unsigned int ht_mask_width, core_plus_mask_width; + unsigned int core_select_mask, core_level_siblings; + + if (detect_extended_topology_early(c) < 0) + return;

/* * Populate HT related information from sub-leaf level 0. */ + cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Borislav Petkov bp@suse.de

commit 119bff8a9c9bb00116a844ec68be7bc4b1c768f5 upstream

Old code used to check whether CPUID ext max level is >= 0x80000008 because that last leaf contains the number of cores of the physical CPU. The three functions called there now do not depend on that leaf anymore so the check can go.

Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Ingo Molnar mingo@kernel.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/amd.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)

--- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -799,11 +799,8 @@ static void init_amd(struct cpuinfo_x86

cpu_detect_cache_sizes(c);

- /* Multi core CPU? */ - if (c->extended_cpuid_level >= 0x80000008) { - amd_detect_cmp(c); - srat_detect_node(c); - } + amd_detect_cmp(c); + srat_detect_node(c);

init_amd_cacheinfo(c);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vlastimil Babka vbabka@suse.cz

commit 1a7ed1ba4bba6c075d5ad61bb75e3fbc870840d6 upstream

The previous patch has limited swap file size so that large offsets cannot clear bits above MAX_PA/2 in the pte and interfere with L1TF mitigation.

It assumed that offsets are encoded starting with bit 12, same as pfn. But on x86_64, offsets are encoded starting with bit 9.

Thus the limit can be raised by 3 bits. That means 16TB with 42bit MAX_PA and 256TB with 46bit MAX_PA.

Fixes: 377eeaa8e11f ("x86/speculation/l1tf: Limit swap file size to MAX_PA/2") Signed-off-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/mm/init.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -791,7 +791,15 @@ unsigned long max_swapfile_size(void)

if (boot_cpu_has_bug(X86_BUG_L1TF)) { /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ - pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages); + unsigned long l1tf_limit = l1tf_pfn_limit() + 1; + /* + * We encode swap offsets also with 3 bits below those for pfn + * which makes the usable limit higher. + */ +#ifdef CONFIG_X86_64 + l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT; +#endif + pages = min_t(unsigned long, l1tf_limit, pages); } return pages; }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Borislav Petkov bp@suse.de

commit 7ce2f0393ea2396142b7faf6ee9b1f3676d08a5f upstream

The TOPOEXT reenablement is a workaround for broken BIOSen which didn't enable the CPUID bit. amd_get_topology_early(), however, relies on that bit being set so that it can read out the CPUID leaf and set smp_num_siblings properly.

Move the reenablement up to early_init_amd(). While at it, simplify amd_get_topology_early().

[dwmw2: Backport to 4.9]

Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/amd.c | 39 +++++++++++++++++++-------------------- 1 file changed, 19 insertions(+), 20 deletions(-)

--- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -300,12 +300,8 @@ static int nearby_node(int apicid)

static void amd_get_topology_early(struct cpuinfo_x86 *c) { - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 eax, ebx, ecx, edx; - - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - smp_num_siblings = ((ebx >> 8) & 0xff) + 1; - } + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; }

/* @@ -326,7 +322,6 @@ static void amd_get_topology(struct cpui cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);

node_id = ecx & 0xff; - smp_num_siblings = ((ebx >> 8) & 0xff) + 1;

if (c->x86 == 0x15) c->cu_id = ebx & 0xff; @@ -578,6 +573,8 @@ static void bsp_init_amd(struct cpuinfo_

static void early_init_amd(struct cpuinfo_x86 *c) { + u64 value; + early_init_amd_mc(c);

/* @@ -645,6 +642,21 @@ static void early_init_amd(struct cpuinf if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400);

+ + /* Re-enable TopologyExtensions if switched off by BIOS */ + if (c->x86 == 0x15 && + (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && + !cpu_has(c, X86_FEATURE_TOPOEXT)) { + + if (msr_set_bit(0xc0011005, 54) > 0) { + rdmsrl(0xc0011005, value); + if (value & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } + } + } + amd_get_topology_early(c); }

@@ -737,19 +749,6 @@ static void init_amd_bd(struct cpuinfo_x { u64 value;

- /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - /* * The way access filter has a performance penalty on some workloads. * Disable it on the affected CPUs.

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michal Hocko mhocko@suse.cz

commit e14d7dfb41f5807a0c1c26a13f2b8ef16af24935 upstream

Jan has noticed that pte_pfn and co. resp. pfn_pte are incorrect for CONFIG_PAE because phys_addr_t is wider than unsigned long and so the pte_val reps. shift left would get truncated. Fix this up by using proper types.

[dwmw2: Backport to 4.9]

Fixes: 6b28baca9b1f ("x86/speculation/l1tf: Protect PROT_NONE PTEs against speculation") Reported-by: Jan Beulich JBeulich@suse.com Signed-off-by: Michal Hocko mhocko@suse.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Vlastimil Babka vbabka@suse.cz Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/pgtable.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -171,21 +171,21 @@ static inline u64 protnone_mask(u64 val)

static inline unsigned long pte_pfn(pte_t pte) { - unsigned long pfn = pte_val(pte); + phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; }

static inline unsigned long pmd_pfn(pmd_t pmd) { - unsigned long pfn = pmd_val(pmd); + phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; }

static inline unsigned long pud_pfn(pud_t pud) { - unsigned long pfn = pud_val(pud); + phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } @@ -404,7 +404,7 @@ static inline pgprotval_t massage_pgprot

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { - phys_addr_t pfn = page_nr << PAGE_SHIFT; + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | massage_pgprot(pgprot)); @@ -412,7 +412,7 @@ static inline pte_t pfn_pte(unsigned lon

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { - phys_addr_t pfn = page_nr << PAGE_SHIFT; + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | massage_pgprot(pgprot));

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 0cc3cd21657be04cb0559fe8063f2130493f92cf upstream

Due to the way Machine Check Exceptions work on X86 hyperthreads it's required to boot up _all_ logical cores at least once in order to set the CR4.MCE bit.

So instead of ignoring the sibling threads right away, let them boot up once so they can configure themselves. After they came out of the initial boot stage check whether its a "secondary" sibling and cancel the operation which puts the CPU back into offline state.

[dwmw2: Backport to 4.9]

Reported-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Tony Luck tony.luck@intel.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cpu.c | 72 +++++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 48 insertions(+), 24 deletions(-)

--- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -54,6 +54,7 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; + bool booted_once; struct hlist_node *node; enum cpuhp_state cb_state; int result; @@ -355,6 +356,40 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */

+#ifdef CONFIG_HOTPLUG_SMT +enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; + +static int __init smt_cmdline_disable(char *str) +{ + cpu_smt_control = CPU_SMT_DISABLED; + if (str && !strcmp(str, "force")) { + pr_info("SMT: Force disabled\n"); + cpu_smt_control = CPU_SMT_FORCE_DISABLED; + } + return 0; +} +early_param("nosmt", smt_cmdline_disable); + +static inline bool cpu_smt_allowed(unsigned int cpu) +{ + if (cpu_smt_control == CPU_SMT_ENABLED) + return true; + + if (topology_is_primary_thread(cpu)) + return true; + + /* + * On x86 it's required to boot all logical CPUs at least once so + * that the init code can get a chance to set CR4.MCE on each + * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any + * core will shutdown the machine. + */ + return !per_cpu(cpuhp_state, cpu).booted_once; +} +#else +static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +#endif + /* Need to know about CPUs going up/down? */ int register_cpu_notifier(struct notifier_block *nb) { @@ -431,6 +466,16 @@ static int bringup_wait_for_ap(unsigned stop_machine_unpark(cpu); kthread_unpark(st->thread);

+ /* + * SMT soft disabling on X86 requires to bring the CPU out of the + * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The + * CPU marked itself as booted_once in cpu_notify_starting() so the + * cpu_smt_allowed() check will now return false if this is not the + * primary sibling. + */ + if (!cpu_smt_allowed(cpu)) + return -ECANCELED; + /* Should we go further up ? */ if (st->target > CPUHP_AP_ONLINE_IDLE) { __cpuhp_kick_ap_work(st); @@ -978,29 +1023,6 @@ int cpu_down(unsigned int cpu) EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/

-#ifdef CONFIG_HOTPLUG_SMT -enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; - -static int __init smt_cmdline_disable(char *str) -{ - cpu_smt_control = CPU_SMT_DISABLED; - if (str && !strcmp(str, "force")) { - pr_info("SMT: Force disabled\n"); - cpu_smt_control = CPU_SMT_FORCE_DISABLED; - } - return 0; -} -early_param("nosmt", smt_cmdline_disable); - -static inline bool cpu_smt_allowed(unsigned int cpu) -{ - return cpu_smt_control == CPU_SMT_ENABLED || - topology_is_primary_thread(cpu); -} -#else -static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } -#endif - /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started @@ -1014,6 +1036,7 @@ void notify_cpu_starting(unsigned int cp enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);

rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ + st->booted_once = true; while (st->state < target) { st->state++; cpuhp_invoke_callback(cpu, st->state, true, NULL); @@ -2114,5 +2137,6 @@ void __init boot_cpu_init(void) */ void __init boot_cpu_hotplug_init(void) { - per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; + this_cpu_write(cpuhp_state.booted_once, true); + this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

commit a399477e52c17e148746d3ce9a483f681c2aa9a0 upstream

Add a mitigation mode parameter "vmentry_l1d_flush" for CVE-2018-3620, aka L1 terminal fault. The valid arguments are:

- "always" L1D cache flush on every VMENTER. - "cond" Conditional L1D cache flush, explained below - "never" Disable the L1D cache flush mitigation

"cond" is trying to avoid L1D cache flushes on VMENTER if the code executed between VMEXIT and VMENTER is considered safe, i.e. is not bringing any interesting information into L1D which might exploited.

[ tglx: Split out from a larger patch ]

Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/kernel-parameters.txt | 12 ++++++ arch/x86/kvm/vmx.c | 65 ++++++++++++++++++++++++++++++++++-- 2 files changed, 75 insertions(+), 2 deletions(-)

--- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2016,6 +2016,18 @@ bytes respectively. Such letter suffixes (virtualized real and unpaged mode) on capable Intel chips. Default is 1 (enabled)

+ kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault + CVE-2018-3620. + + Valid arguments: never, cond, always + + always: L1D cache flush on every VMENTER. + cond: Flush L1D on VMENTER only when the code between + VMEXIT and VMENTER can leak host memory. + never: Disables the mitigation + + Default is cond (do L1 cache flush in specific instances) + kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification feature (tagged TLBs) on capable Intel chips. Default is 1 (enabled) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -192,6 +192,54 @@ module_param(ple_window_max, int, S_IRUG

extern const ulong vmx_return;

+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); + +/* These MUST be in sync with vmentry_l1d_param order. */ +enum vmx_l1d_flush_state { + VMENTER_L1D_FLUSH_NEVER, + VMENTER_L1D_FLUSH_COND, + VMENTER_L1D_FLUSH_ALWAYS, +}; + +static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND; + +static const struct { + const char *option; + enum vmx_l1d_flush_state cmd; +} vmentry_l1d_param[] = { + {"never", VMENTER_L1D_FLUSH_NEVER}, + {"cond", VMENTER_L1D_FLUSH_COND}, + {"always", VMENTER_L1D_FLUSH_ALWAYS}, +}; + +static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) +{ + unsigned int i; + + if (!s) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { + if (!strcmp(s, vmentry_l1d_param[i].option)) { + vmentry_l1d_flush = vmentry_l1d_param[i].cmd; + return 0; + } + } + + return -EINVAL; +} + +static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) +{ + return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option); +} + +static const struct kernel_param_ops vmentry_l1d_flush_ops = { + .set = vmentry_l1d_flush_set, + .get = vmentry_l1d_flush_get, +}; +module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO); + #define NR_AUTOLOAD_MSRS 8

struct vmcs { @@ -11505,10 +11553,23 @@ static struct kvm_x86_ops vmx_x86_ops __ .setup_mce = vmx_setup_mce, };

+static void __init vmx_setup_l1d_flush(void) +{ + if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER || + !boot_cpu_has_bug(X86_BUG_L1TF)) + return; + + static_branch_enable(&vmx_l1d_should_flush); +} + static int __init vmx_init(void) { - int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + int r; + + vmx_setup_l1d_flush(); + + r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), + __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) return r;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini pbonzini@redhat.com

commit 3fa045be4c720146b18a19cea7a767dc6ad5df94 upstream

336996-Speculative-Execution-Side-Channel-Mitigations.pdf defines a new MSR (IA32_FLUSH_CMD aka 0x10B) which has similar write-only semantics to other MSRs defined in the document.

The semantics of this MSR is to allow "finer granularity invalidation of caching structures than existing mechanisms like WBINVD. It will writeback and invalidate the L1 data cache, including all cachelines brought in by preceding instructions, without invalidating all caches (eg. L2 or LLC). Some processors may also invalidate the first level level instruction cache on a L1D_FLUSH command. The L1 data and instruction caches may be shared across the logical processors of a core."

Use it instead of the loop based L1 flush algorithm.

A copy of this document is available at https://bugzilla.kernel.org/show_bug.cgi?id=199511

[ tglx: Avoid allocating pages when the MSR is available ]

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/msr-index.h | 6 ++++++ arch/x86/kvm/vmx.c | 15 +++++++++++---- 2 files changed, 17 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -69,6 +69,12 @@ * control required. */

+#define MSR_IA32_FLUSH_CMD 0x0000010b +#define L1D_FLUSH (1 << 0) /* + * Writeback and invalidate the + * L1 data cache. + */ + #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8553,6 +8553,11 @@ static void __maybe_unused vmx_l1d_flush { int size = PAGE_SIZE << L1D_CACHE_ORDER;

+ if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + return; + } + asm volatile( /* First ensure the pages are in the TLB */ "xorl %%eax, %%eax\n" @@ -11601,11 +11606,13 @@ static int __init vmx_setup_l1d_flush(vo !boot_cpu_has_bug(X86_BUG_L1TF)) return 0;

- page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); - if (!page) - return -ENOMEM; + if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { + page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); + if (!page) + return -ENOMEM; + vmx_l1d_flush_pages = page_address(page); + }

- vmx_l1d_flush_pages = page_address(page); static_branch_enable(&vmx_l1d_should_flush); return 0; }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

commit 33966dd6b2d2c352fae55412db2ea8cfff5df13a upstream

There is no semantic change but this change allows an unbalanced amount of MSRs to be loaded on VMEXIT and VMENTER, i.e. the number of MSRs to save or restore on VMEXIT or VMENTER may be different.

Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 65 ++++++++++++++++++++++++++++------------------------- 1 file changed, 35 insertions(+), 30 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -592,6 +592,11 @@ static inline int pi_test_sn(struct pi_d (unsigned long *)&pi_desc->control); }

+struct vmx_msrs { + unsigned int nr; + struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -624,9 +629,8 @@ struct vcpu_vmx { struct loaded_vmcs *loaded_vmcs; bool __launched; /* temporary, used in vmx_vcpu_run */ struct msr_autoload { - unsigned nr; - struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS]; - struct vmx_msr_entry host[NR_AUTOLOAD_MSRS]; + struct vmx_msrs guest; + struct vmx_msrs host; } msr_autoload; struct { int loaded; @@ -1994,18 +1998,18 @@ static void clear_atomic_switch_msr(stru } break; } - - for (i = 0; i < m->nr; ++i) - if (m->guest[i].index == msr) + for (i = 0; i < m->guest.nr; ++i) + if (m->guest.val[i].index == msr) break;

- if (i == m->nr) + if (i == m->guest.nr) return; - --m->nr; - m->guest[i] = m->guest[m->nr]; - m->host[i] = m->host[m->nr]; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); + --m->guest.nr; + --m->host.nr; + m->guest.val[i] = m->guest.val[m->guest.nr]; + m->host.val[i] = m->host.val[m->host.nr]; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); }

static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -2057,24 +2061,25 @@ static void add_atomic_switch_msr(struct wrmsrl(MSR_IA32_PEBS_ENABLE, 0); }

- for (i = 0; i < m->nr; ++i) - if (m->guest[i].index == msr) + for (i = 0; i < m->guest.nr; ++i) + if (m->guest.val[i].index == msr) break;

if (i == NR_AUTOLOAD_MSRS) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; - } else if (i == m->nr) { - ++m->nr; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr); + } else if (i == m->guest.nr) { + ++m->guest.nr; + ++m->host.nr; + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); }

- m->guest[i].index = msr; - m->guest[i].value = guest_val; - m->host[i].index = msr; - m->host[i].value = host_val; + m->guest.val[i].index = msr; + m->guest.val[i].value = guest_val; + m->host.val[i].index = msr; + m->host.val[i].value = host_val; }

static void reload_tss(void) @@ -5316,9 +5321,9 @@ static int vmx_vcpu_setup(struct vcpu_vm

vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));

if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); @@ -10224,10 +10229,10 @@ static void prepare_vmcs02(struct kvm_vc * Set the MSR load/store lists to match L0's settings. */ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));

/* * HOST_RSP is normally set correctly in vmx_vcpu_run() just before @@ -11076,8 +11081,8 @@ static void nested_vmx_vmexit(struct kvm load_vmcs12_host_state(vcpu, vmcs12);

/* 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); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (vmx->hv_deadline_tsc == -1) vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

commit 3190709335dd31fe1aeeebfe4ffb6c7624ef971f upstream

This allows to load a different number of MSRs depending on the context: VMEXIT or VMENTER.

Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2011,12 +2011,18 @@ static void clear_atomic_switch_msr(stru } i = find_msr(&m->guest, msr); if (i < 0) - return; + goto skip_guest; --m->guest.nr; - --m->host.nr; m->guest.val[i] = m->guest.val[m->guest.nr]; - m->host.val[i] = m->host.val[m->host.nr]; vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); + +skip_guest: + i = find_msr(&m->host, msr); + if (i < 0) + return; + + --m->host.nr; + m->host.val[i] = m->host.val[m->host.nr]; vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); }

@@ -2034,7 +2040,7 @@ static void add_atomic_switch_msr_specia static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, u64 guest_val, u64 host_val) { - int i; + int i, j; struct msr_autoload *m = &vmx->msr_autoload;

switch (msr) { @@ -2070,21 +2076,24 @@ static void add_atomic_switch_msr(struct }

i = find_msr(&m->guest, msr); - if (i == NR_AUTOLOAD_MSRS) { + j = find_msr(&m->host, msr); + if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; - } else if (i < 0) { + } + if (i < 0) { i = m->guest.nr++; - ++m->host.nr; vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); + } + if (j < 0) { + j = m->host.nr++; vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } - m->guest.val[i].index = msr; m->guest.val[i].value = guest_val; - m->host.val[i].index = msr; - m->host.val[i].value = host_val; + m->host.val[j].index = msr; + m->host.val[j].value = host_val; }

static void reload_tss(void)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

commit 390d975e0c4e60ce70d4157e0dd91ede37824603 upstream

If the L1D flush module parameter is set to 'always' and the IA32_FLUSH_CMD MSR is available, optimize the VMENTER code with the MSR save list.

Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 42 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5269,6 +5269,16 @@ static void ept_set_mmio_spte_mask(void) kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull); }

+static bool vmx_l1d_use_msr_save_list(void) +{ + if (!enable_ept || !boot_cpu_has_bug(X86_BUG_L1TF) || + static_cpu_has(X86_FEATURE_HYPERVISOR) || + !static_cpu_has(X86_FEATURE_FLUSH_L1D)) + return false; + + return vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS; +} + #define VMX_XSS_EXIT_BITMAP 0 /* * Sets up the vmcs for emulated real mode. @@ -5618,6 +5628,12 @@ static void vmx_set_nmi_mask(struct kvm_ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); } + /* + * If flushing the L1D cache on every VMENTER is enforced and the + * MSR is available, use the MSR save list. + */ + if (vmx_l1d_use_msr_save_list()) + add_atomic_switch_msr(vmx, MSR_IA32_FLUSH_CMD, L1D_FLUSH, 0, true); }

static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) @@ -8581,11 +8597,26 @@ static void vmx_l1d_flush(struct kvm_vcp bool always;

/* - * If the mitigation mode is 'flush always', keep the flush bit - * set, otherwise clear it. It gets set again either from - * vcpu_run() or from one of the unsafe VMEXIT handlers. + * This code is only executed when: + * - the flush mode is 'cond' + * - the flush mode is 'always' and the flush MSR is not + * available + * + * If the CPU has the flush MSR then clear the flush bit because + * 'always' mode is handled via the MSR save list. + * + * If the MSR is not avaibable then act depending on the mitigation + * mode: If 'flush always', keep the flush bit set, otherwise clear + * it. + * + * The flush bit gets set again either from vcpu_run() or from one + * of the unsafe VMEXIT handlers. */ - always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS; + if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) + always = false; + else + always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS; + vcpu->arch.l1tf_flush_l1d = always;

vcpu->stat.l1d_flush++; @@ -11660,7 +11691,8 @@ static int __init vmx_setup_l1d_flush(vo struct page *page;

if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER || - !boot_cpu_has_bug(X86_BUG_L1TF)) + !boot_cpu_has_bug(X86_BUG_L1TF) || + vmx_l1d_use_msr_save_list()) return 0;

if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 72c6d2db64fa18c996ece8f06e499509e6c9a37e upstream

Store the effective mitigation of VMX in a status variable and use it to report the VMX state in the l1tf sysfs file.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Jiri Kosina jkosina@suse.cz Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20180713142322.433098358@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/vmx.h | 9 +++++++++ arch/x86/kernel/cpu/bugs.c | 36 ++++++++++++++++++++++++++++++++++-- arch/x86/kvm/vmx.c | 22 +++++++++++----------- 3 files changed, 54 insertions(+), 13 deletions(-)

--- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -499,4 +499,13 @@ enum vm_instruction_error_number { VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28, };

+enum vmx_l1d_flush_state { + VMENTER_L1D_FLUSH_AUTO, + VMENTER_L1D_FLUSH_NEVER, + VMENTER_L1D_FLUSH_COND, + VMENTER_L1D_FLUSH_ALWAYS, +}; + +extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; + #endif --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -21,6 +21,7 @@ #include <asm/processor-flags.h> #include <asm/fpu/internal.h> #include <asm/msr.h> +#include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/alternative.h> #include <asm/pgtable.h> @@ -635,6 +636,12 @@ void x86_spec_ctrl_setup_ap(void)

#undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt + +#if IS_ENABLED(CONFIG_KVM_INTEL) +enum vmx_l1d_flush_state l1tf_vmx_mitigation __ro_after_init = VMENTER_L1D_FLUSH_AUTO; +EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); +#endif + static void __init l1tf_select_mitigation(void) { u64 half_pa; @@ -664,6 +671,32 @@ static void __init l1tf_select_mitigatio

#ifdef CONFIG_SYSFS

+#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" + +#if IS_ENABLED(CONFIG_KVM_INTEL) +static const char *l1tf_vmx_states[] = { + [VMENTER_L1D_FLUSH_AUTO] = "auto", + [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", + [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", + [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", +}; + +static ssize_t l1tf_show_state(char *buf) +{ + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + + return sprintf(buf, "%s; VMX: SMT %s, L1D %s\n", L1TF_DEFAULT_MSG, + cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled", + l1tf_vmx_states[l1tf_vmx_mitigation]); +} +#else +static ssize_t l1tf_show_state(char *buf) +{ + return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); +} +#endif + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -691,9 +724,8 @@ static ssize_t cpu_show_common(struct de

case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) - return sprintf(buf, "Mitigation: Page Table Inversion\n"); + return l1tf_show_state(buf); break; - default: break; } --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -194,19 +194,13 @@ extern const ulong vmx_return;

static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);

-/* These MUST be in sync with vmentry_l1d_param order. */ -enum vmx_l1d_flush_state { - VMENTER_L1D_FLUSH_NEVER, - VMENTER_L1D_FLUSH_COND, - VMENTER_L1D_FLUSH_ALWAYS, -}; - static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;

static const struct { const char *option; enum vmx_l1d_flush_state cmd; } vmentry_l1d_param[] = { + {"auto", VMENTER_L1D_FLUSH_AUTO}, {"never", VMENTER_L1D_FLUSH_NEVER}, {"cond", VMENTER_L1D_FLUSH_COND}, {"always", VMENTER_L1D_FLUSH_ALWAYS}, @@ -11690,8 +11684,12 @@ static int __init vmx_setup_l1d_flush(vo { struct page *page;

+ if (!boot_cpu_has_bug(X86_BUG_L1TF)) + return 0; + + l1tf_vmx_mitigation = vmentry_l1d_flush; + if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER || - !boot_cpu_has_bug(X86_BUG_L1TF) || vmx_l1d_use_msr_save_list()) return 0;

@@ -11706,12 +11704,14 @@ static int __init vmx_setup_l1d_flush(vo return 0; }

-static void vmx_free_l1d_flush_pages(void) +static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); vmx_l1d_flush_pages = NULL; } + /* Restore state so sysfs ignores VMX */ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; }

static int __init vmx_init(void) @@ -11725,7 +11725,7 @@ static int __init vmx_init(void) r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) { - vmx_free_l1d_flush_pages(); + vmx_cleanup_l1d_flush(); return r; }

@@ -11746,7 +11746,7 @@ static void __exit vmx_exit(void)

kvm_exit();

- vmx_free_l1d_flush_pages(); + vmx_cleanup_l1d_flush(); }

module_init(vmx_init)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit a7b9020b06ec6d7c3f3b0d4ef1a9eba12654f4f7 upstream

If Extended Page Tables (EPT) are disabled or not supported, no L1D flushing is required. The setup function can just avoid setting up the L1D flush for the EPT=n case.

Invoke it after the hardware setup has be done and enable_ept has the correct state and expose the EPT disabled state in the mitigation status as well.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Jiri Kosina jkosina@suse.cz Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20180713142322.612160168@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/vmx.h | 1 + arch/x86/kernel/cpu/bugs.c | 9 +++++---- arch/x86/kvm/vmx.c | 44 ++++++++++++++++++++++++++------------------ 3 files changed, 32 insertions(+), 22 deletions(-)

--- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -504,6 +504,7 @@ enum vmx_l1d_flush_state { VMENTER_L1D_FLUSH_NEVER, VMENTER_L1D_FLUSH_COND, VMENTER_L1D_FLUSH_ALWAYS, + VMENTER_L1D_FLUSH_EPT_DISABLED, };

extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -675,10 +675,11 @@ static void __init l1tf_select_mitigatio

#if IS_ENABLED(CONFIG_KVM_INTEL) static const char *l1tf_vmx_states[] = { - [VMENTER_L1D_FLUSH_AUTO] = "auto", - [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", - [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", - [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", + [VMENTER_L1D_FLUSH_AUTO] = "auto", + [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", + [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", + [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", + [VMENTER_L1D_FLUSH_EPT_DISABLED] = "EPT disabled", };

static ssize_t l1tf_show_state(char *buf) --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11659,6 +11659,11 @@ static int __init vmx_setup_l1d_flush(vo if (!boot_cpu_has_bug(X86_BUG_L1TF)) return 0;

+ if (!enable_ept) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; + return 0; + } + l1tf_vmx_mitigation = vmentry_l1d_flush;

if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER) @@ -11685,18 +11690,35 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; }

+ +static void vmx_exit(void) +{ +#ifdef CONFIG_KEXEC_CORE + RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); + synchronize_rcu(); +#endif + + kvm_exit(); + + vmx_cleanup_l1d_flush(); +} +module_exit(vmx_exit) + static int __init vmx_init(void) { int r;

- r = vmx_setup_l1d_flush(); + r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), + __alignof__(struct vcpu_vmx), THIS_MODULE); if (r) return r;

- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + /* + * Must be called after kvm_init() so enable_ept is properly set up + */ + r = vmx_setup_l1d_flush(); if (r) { - vmx_cleanup_l1d_flush(); + vmx_exit(); return r; }

@@ -11707,18 +11729,4 @@ static int __init vmx_init(void)

return 0; } - -static void __exit vmx_exit(void) -{ -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif - - kvm_exit(); - - vmx_cleanup_l1d_flush(); -} - module_init(vmx_init) -module_exit(vmx_exit)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 4c6523ec59fe895ea352a650218a6be0653910b1 upstream

Avoid the conditional in the L1D flush control path.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Jiri Kosina jkosina@suse.cz Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20180713142322.790914912@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -193,6 +193,7 @@ module_param(ple_window_max, int, S_IRUG extern const ulong vmx_return;

static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); +static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_always);

/* Storage for pre module init parameter parsing */ static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; @@ -233,8 +234,12 @@ static int vmx_setup_l1d_flush(enum vmx_

l1tf_vmx_mitigation = l1tf;

- if (l1tf != VMENTER_L1D_FLUSH_NEVER) - static_branch_enable(&vmx_l1d_should_flush); + if (l1tf == VMENTER_L1D_FLUSH_NEVER) + return 0; + + static_branch_enable(&vmx_l1d_should_flush); + if (l1tf == VMENTER_L1D_FLUSH_ALWAYS) + static_branch_enable(&vmx_l1d_flush_always); return 0; }

@@ -8625,7 +8630,6 @@ static void *vmx_l1d_flush_pages; static void vmx_l1d_flush(struct kvm_vcpu *vcpu) { int size = PAGE_SIZE << L1D_CACHE_ORDER; - bool always;

/* * This code is only executed when the the flush mode is 'cond' or @@ -8635,8 +8639,10 @@ static void vmx_l1d_flush(struct kvm_vcp * it. The flush bit gets set again either from vcpu_run() or from * one of the unsafe VMEXIT handlers. */ - always = l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_ALWAYS; - vcpu->arch.l1tf_flush_l1d = always; + if (static_branch_unlikely(&vmx_l1d_flush_always)) + vcpu->arch.l1tf_flush_l1d = true; + else + vcpu->arch.l1tf_flush_l1d = false;

vcpu->stat.l1d_flush++;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 895ae47f9918833c3a880fbccd41e0692b37e7d9 upstream

All mitigation modes can be switched at run time with a static key now:

- Use sysfs_streq() instead of strcmp() to handle the trailing new line from sysfs writes correctly. - Make the static key management handle multiple invocations properly. - Set the module parameter file to RW

Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Jiri Kosina jkosina@suse.cz Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20180713142322.954525119@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kvm/vmx.c | 13 ++++++++----- 2 files changed, 9 insertions(+), 6 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -638,7 +638,7 @@ void x86_spec_ctrl_setup_ap(void) #define pr_fmt(fmt) "L1TF: " fmt

#if IS_ENABLED(CONFIG_KVM_INTEL) -enum vmx_l1d_flush_state l1tf_vmx_mitigation __ro_after_init = VMENTER_L1D_FLUSH_AUTO; +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); #endif

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -235,12 +235,15 @@ static int vmx_setup_l1d_flush(enum vmx_

l1tf_vmx_mitigation = l1tf;

- if (l1tf == VMENTER_L1D_FLUSH_NEVER) - return 0; + if (l1tf != VMENTER_L1D_FLUSH_NEVER) + static_branch_enable(&vmx_l1d_should_flush); + else + static_branch_disable(&vmx_l1d_should_flush);

- static_branch_enable(&vmx_l1d_should_flush); if (l1tf == VMENTER_L1D_FLUSH_ALWAYS) static_branch_enable(&vmx_l1d_flush_always); + else + static_branch_disable(&vmx_l1d_flush_always); return 0; }

@@ -250,7 +253,7 @@ static int vmentry_l1d_flush_parse(const

if (s) { for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { - if (!strcmp(s, vmentry_l1d_param[i].option)) + if (sysfs_streq(s, vmentry_l1d_param[i].option)) return vmentry_l1d_param[i].cmd; } } @@ -294,7 +297,7 @@ static const struct kernel_param_ops vme .set = vmentry_l1d_flush_set, .get = vmentry_l1d_flush_get, }; -module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, S_IRUGO); +module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);

#define NR_AUTOLOAD_MSRS 8

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit fee0aede6f4739c87179eca76136f83210953b86 upstream

The CPU_SMT_NOT_SUPPORTED state is set (if the processor does not support SMT) when the sysfs SMT control file is initialized.

That was fine so far as this was only required to make the output of the control file correct and to prevent writes in that case.

With the upcoming l1tf command line parameter, this needs to be set up before the L1TF mitigation selection and command line parsing happens.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Jiri Kosina jkosina@suse.cz Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20180713142323.121795971@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 6 ++++++ include/linux/cpu.h | 2 ++ kernel/cpu.c | 13 ++++++++++--- 3 files changed, 18 insertions(+), 3 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -57,6 +57,12 @@ void __init check_bugs(void) { identify_boot_cpu();

+ /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); print_cpu_info(&boot_cpu_data); --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -267,9 +267,11 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); +extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } +static inline void cpu_smt_check_topology(void) { } #endif

#endif /* _LINUX_CPU_H_ */ --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -374,6 +374,16 @@ void __init cpu_smt_disable(bool force) } }

+/* + * The decision whether SMT is supported can only be done after the full + * CPU identification. Called from architecture code. + */ +void __init cpu_smt_check_topology(void) +{ + if (!topology_smt_supported()) + cpu_smt_control = CPU_SMT_NOT_SUPPORTED; +} + static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); @@ -2053,9 +2063,6 @@ static const struct attribute_group cpuh

static int __init cpu_smt_state_init(void) { - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; - return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 3ec8ce5d866ec6a08a9cfab82b62acf4a830b35f upstream

Add documentation for the L1TF vulnerability and the mitigation mechanisms:

- Explain the problem and risks - Document the mitigation mechanisms - Document the command line controls - Document the sysfs files

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Linus Torvalds torvalds@linux-foundation.org Link: https://lkml.kernel.org/r/20180713142323.287429944@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/index.rst | 1 Documentation/l1tf.rst | 591 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 592 insertions(+) create mode 100644 Documentation/l1tf.rst

--- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -12,6 +12,7 @@ Contents: :maxdepth: 2

kernel-documentation + l1tf development-process/index dev-tools/tools driver-api/index --- /dev/null +++ b/Documentation/l1tf.rst @@ -0,0 +1,591 @@ +L1TF - L1 Terminal Fault +======================== + +L1 Terminal Fault is a hardware vulnerability which allows unprivileged +speculative access to data which is available in the Level 1 Data Cache +when the page table entry controlling the virtual address, which is used +for the access, has the Present bit cleared or other reserved bits set. + +Affected processors +------------------- + +This vulnerability affects a wide range of Intel processors. The +vulnerability is not present on: + + - Processors from AMD, Centaur and other non Intel vendors + + - Older processor models, where the CPU family is < 6 + + - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft, + Penwell, Pineview, Slivermont, Airmont, Merrifield) + + - The Intel Core Duo Yonah variants (2006 - 2008) + + - The Intel XEON PHI family + + - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the + IA32_ARCH_CAPABILITIES MSR. If the bit is set the CPU is not affected + by the Meltdown vulnerability either. These CPUs should become + available by end of 2018. + +Whether a processor is affected or not can be read out from the L1TF +vulnerability file in sysfs. See :ref:`l1tf_sys_info`. + +Related CVEs +------------ + +The following CVE entries are related to the L1TF vulnerability: + + ============= ================= ============================== + CVE-2018-3615 L1 Terminal Fault SGX related aspects + CVE-2018-3620 L1 Terminal Fault OS, SMM related aspects + CVE-2018-3646 L1 Terminal Fault Virtualization related aspects + ============= ================= ============================== + +Problem +------- + +If an instruction accesses a virtual address for which the relevant page +table entry (PTE) has the Present bit cleared or other reserved bits set, +then speculative execution ignores the invalid PTE and loads the referenced +data if it is present in the Level 1 Data Cache, as if the page referenced +by the address bits in the PTE was still present and accessible. + +While this is a purely speculative mechanism and the instruction will raise +a page fault when it is retired eventually, the pure act of loading the +data and making it available to other speculative instructions opens up the +opportunity for side channel attacks to unprivileged malicious code, +similar to the Meltdown attack. + +While Meltdown breaks the user space to kernel space protection, L1TF +allows to attack any physical memory address in the system and the attack +works across all protection domains. It allows an attack of SGX and also +works from inside virtual machines because the speculation bypasses the +extended page table (EPT) protection mechanism. + + +Attack scenarios +---------------- + +1. Malicious user space +^^^^^^^^^^^^^^^^^^^^^^^ + + Operating Systems store arbitrary information in the address bits of a + PTE which is marked non present. This allows a malicious user space + application to attack the physical memory to which these PTEs resolve. + In some cases user-space can maliciously influence the information + encoded in the address bits of the PTE, thus making attacks more + deterministic and more practical. + + The Linux kernel contains a mitigation for this attack vector, PTE + inversion, which is permanently enabled and has no performance + impact. The kernel ensures that the address bits of PTEs, which are not + marked present, never point to cacheable physical memory space. + + A system with an up to date kernel is protected against attacks from + malicious user space applications. + +2. Malicious guest in a virtual machine +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + The fact that L1TF breaks all domain protections allows malicious guest + OSes, which can control the PTEs directly, and malicious guest user + space applications, which run on an unprotected guest kernel lacking the + PTE inversion mitigation for L1TF, to attack physical host memory. + + A special aspect of L1TF in the context of virtualization is symmetric + multi threading (SMT). The Intel implementation of SMT is called + HyperThreading. The fact that Hyperthreads on the affected processors + share the L1 Data Cache (L1D) is important for this. As the flaw allows + only to attack data which is present in L1D, a malicious guest running + on one Hyperthread can attack the data which is brought into the L1D by + the context which runs on the sibling Hyperthread of the same physical + core. This context can be host OS, host user space or a different guest. + + If the processor does not support Extended Page Tables, the attack is + only possible, when the hypervisor does not sanitize the content of the + effective (shadow) page tables. + + While solutions exist to mitigate these attack vectors fully, these + mitigations are not enabled by default in the Linux kernel because they + can affect performance significantly. The kernel provides several + mechanisms which can be utilized to address the problem depending on the + deployment scenario. The mitigations, their protection scope and impact + are described in the next sections. + + The default mitigations and the rationale for chosing them are explained + at the end of this document. See :ref:`default_mitigations`. + +.. _l1tf_sys_info: + +L1TF system information +----------------------- + +The Linux kernel provides a sysfs interface to enumerate the current L1TF +status of the system: whether the system is vulnerable, and which +mitigations are active. The relevant sysfs file is: + +/sys/devices/system/cpu/vulnerabilities/l1tf + +The possible values in this file are: + + =========================== =============================== + 'Not affected' The processor is not vulnerable + 'Mitigation: PTE Inversion' The host protection is active + =========================== =============================== + +If KVM/VMX is enabled and the processor is vulnerable then the following +information is appended to the 'Mitigation: PTE Inversion' part: + + - SMT status: + + ===================== ================ + 'VMX: SMT vulnerable' SMT is enabled + 'VMX: SMT disabled' SMT is disabled + ===================== ================ + + - L1D Flush mode: + + ================================ ==================================== + 'L1D vulnerable' L1D flushing is disabled + + 'L1D conditional cache flushes' L1D flush is conditionally enabled + + 'L1D cache flushes' L1D flush is unconditionally enabled + ================================ ==================================== + +The resulting grade of protection is discussed in the following sections. + + +Host mitigation mechanism +------------------------- + +The kernel is unconditionally protected against L1TF attacks from malicious +user space running on the host. + + +Guest mitigation mechanisms +--------------------------- + +.. _l1d_flush: + +1. L1D flush on VMENTER +^^^^^^^^^^^^^^^^^^^^^^^ + + To make sure that a guest cannot attack data which is present in the L1D + the hypervisor flushes the L1D before entering the guest. + + Flushing the L1D evicts not only the data which should not be accessed + by a potentially malicious guest, it also flushes the guest + data. Flushing the L1D has a performance impact as the processor has to + bring the flushed guest data back into the L1D. Depending on the + frequency of VMEXIT/VMENTER and the type of computations in the guest + performance degradation in the range of 1% to 50% has been observed. For + scenarios where guest VMEXIT/VMENTER are rare the performance impact is + minimal. Virtio and mechanisms like posted interrupts are designed to + confine the VMEXITs to a bare minimum, but specific configurations and + application scenarios might still suffer from a high VMEXIT rate. + + The kernel provides two L1D flush modes: + - conditional ('cond') + - unconditional ('always') + + The conditional mode avoids L1D flushing after VMEXITs which execute + only audited code pathes before the corresponding VMENTER. These code + pathes have beed verified that they cannot expose secrets or other + interesting data to an attacker, but they can leak information about the + address space layout of the hypervisor. + + Unconditional mode flushes L1D on all VMENTER invocations and provides + maximum protection. It has a higher overhead than the conditional + mode. The overhead cannot be quantified correctly as it depends on the + work load scenario and the resulting number of VMEXITs. + + The general recommendation is to enable L1D flush on VMENTER. The kernel + defaults to conditional mode on affected processors. + + **Note**, that L1D flush does not prevent the SMT problem because the + sibling thread will also bring back its data into the L1D which makes it + attackable again. + + L1D flush can be controlled by the administrator via the kernel command + line and sysfs control files. See :ref:`mitigation_control_command_line` + and :ref:`mitigation_control_kvm`. + +.. _guest_confinement: + +2. Guest VCPU confinement to dedicated physical cores +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + To address the SMT problem, it is possible to make a guest or a group of + guests affine to one or more physical cores. The proper mechanism for + that is to utilize exclusive cpusets to ensure that no other guest or + host tasks can run on these cores. + + If only a single guest or related guests run on sibling SMT threads on + the same physical core then they can only attack their own memory and + restricted parts of the host memory. + + Host memory is attackable, when one of the sibling SMT threads runs in + host OS (hypervisor) context and the other in guest context. The amount + of valuable information from the host OS context depends on the context + which the host OS executes, i.e. interrupts, soft interrupts and kernel + threads. The amount of valuable data from these contexts cannot be + declared as non-interesting for an attacker without deep inspection of + the code. + + **Note**, that assigning guests to a fixed set of physical cores affects + the ability of the scheduler to do load balancing and might have + negative effects on CPU utilization depending on the hosting + scenario. Disabling SMT might be a viable alternative for particular + scenarios. + + For further information about confining guests to a single or to a group + of cores consult the cpusets documentation: + + https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt + +.. _interrupt_isolation: + +3. Interrupt affinity +^^^^^^^^^^^^^^^^^^^^^ + + Interrupts can be made affine to logical CPUs. This is not universally + true because there are types of interrupts which are truly per CPU + interrupts, e.g. the local timer interrupt. Aside of that multi queue + devices affine their interrupts to single CPUs or groups of CPUs per + queue without allowing the administrator to control the affinities. + + Moving the interrupts, which can be affinity controlled, away from CPUs + which run untrusted guests, reduces the attack vector space. + + Whether the interrupts with are affine to CPUs, which run untrusted + guests, provide interesting data for an attacker depends on the system + configuration and the scenarios which run on the system. While for some + of the interrupts it can be assumed that they wont expose interesting + information beyond exposing hints about the host OS memory layout, there + is no way to make general assumptions. + + Interrupt affinity can be controlled by the administrator via the + /proc/irq/$NR/smp_affinity[_list] files. Limited documentation is + available at: + + https://www.kernel.org/doc/Documentation/IRQ-affinity.txt + +.. _smt_control: + +4. SMT control +^^^^^^^^^^^^^^ + + To prevent the SMT issues of L1TF it might be necessary to disable SMT + completely. Disabling SMT can have a significant performance impact, but + the impact depends on the hosting scenario and the type of workloads. + The impact of disabling SMT needs also to be weighted against the impact + of other mitigation solutions like confining guests to dedicated cores. + + The kernel provides a sysfs interface to retrieve the status of SMT and + to control it. It also provides a kernel command line interface to + control SMT. + + The kernel command line interface consists of the following options: + + =========== ========================================================== + nosmt Affects the bring up of the secondary CPUs during boot. The + kernel tries to bring all present CPUs online during the + boot process. "nosmt" makes sure that from each physical + core only one - the so called primary (hyper) thread is + activated. Due to a design flaw of Intel processors related + to Machine Check Exceptions the non primary siblings have + to be brought up at least partially and are then shut down + again. "nosmt" can be undone via the sysfs interface. + + nosmt=force Has the same effect as "nosmt' but it does not allow to + undo the SMT disable via the sysfs interface. + =========== ========================================================== + + The sysfs interface provides two files: + + - /sys/devices/system/cpu/smt/control + - /sys/devices/system/cpu/smt/active + + /sys/devices/system/cpu/smt/control: + + This file allows to read out the SMT control state and provides the + ability to disable or (re)enable SMT. The possible states are: + + ============== =================================================== + on SMT is supported by the CPU and enabled. All + logical CPUs can be onlined and offlined without + restrictions. + + off SMT is supported by the CPU and disabled. Only + the so called primary SMT threads can be onlined + and offlined without restrictions. An attempt to + online a non-primary sibling is rejected + + forceoff Same as 'off' but the state cannot be controlled. + Attempts to write to the control file are rejected. + + notsupported The processor does not support SMT. It's therefore + not affected by the SMT implications of L1TF. + Attempts to write to the control file are rejected. + ============== =================================================== + + The possible states which can be written into this file to control SMT + state are: + + - on + - off + - forceoff + + /sys/devices/system/cpu/smt/active: + + This file reports whether SMT is enabled and active, i.e. if on any + physical core two or more sibling threads are online. + + SMT control is also possible at boot time via the l1tf kernel command + line parameter in combination with L1D flush control. See + :ref:`mitigation_control_command_line`. + +5. Disabling EPT +^^^^^^^^^^^^^^^^ + + Disabling EPT for virtual machines provides full mitigation for L1TF even + with SMT enabled, because the effective page tables for guests are + managed and sanitized by the hypervisor. Though disabling EPT has a + significant performance impact especially when the Meltdown mitigation + KPTI is enabled. + + EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter. + +There is ongoing research and development for new mitigation mechanisms to +address the performance impact of disabling SMT or EPT. + +.. _mitigation_control_command_line: + +Mitigation control on the kernel command line +--------------------------------------------- + +The kernel command line allows to control the L1TF mitigations at boot +time with the option "l1tf=". The valid arguments for this option are: + + ============ ============================================================= + full Provides all available mitigations for the L1TF + vulnerability. Disables SMT and enables all mitigations in + the hypervisors, i.e. unconditional L1D flushing + + SMT control and L1D flush control via the sysfs interface + is still possible after boot. Hypervisors will issue a + warning when the first VM is started in a potentially + insecure configuration, i.e. SMT enabled or L1D flush + disabled. + + full,force Same as 'full', but disables SMT and L1D flush runtime + control. Implies the 'nosmt=force' command line option. + (i.e. sysfs control of SMT is disabled.) + + flush Leaves SMT enabled and enables the default hypervisor + mitigation, i.e. conditional L1D flushing + + SMT control and L1D flush control via the sysfs interface + is still possible after boot. Hypervisors will issue a + warning when the first VM is started in a potentially + insecure configuration, i.e. SMT enabled or L1D flush + disabled. + + flush,nosmt Disables SMT and enables the default hypervisor mitigation, + i.e. conditional L1D flushing. + + SMT control and L1D flush control via the sysfs interface + is still possible after boot. Hypervisors will issue a + warning when the first VM is started in a potentially + insecure configuration, i.e. SMT enabled or L1D flush + disabled. + + flush,nowarn Same as 'flush', but hypervisors will not warn when a VM is + started in a potentially insecure configuration. + + off Disables hypervisor mitigations and doesn't emit any + warnings. + ============ ============================================================= + +The default is 'flush'. For details about L1D flushing see :ref:`l1d_flush`. + + +.. _mitigation_control_kvm: + +Mitigation control for KVM - module parameter +------------------------------------------------------------- + +The KVM hypervisor mitigation mechanism, flushing the L1D cache when +entering a guest, can be controlled with a module parameter. + +The option/parameter is "kvm-intel.vmentry_l1d_flush=". It takes the +following arguments: + + ============ ============================================================== + always L1D cache flush on every VMENTER. + + cond Flush L1D on VMENTER only when the code between VMEXIT and + VMENTER can leak host memory which is considered + interesting for an attacker. This still can leak host memory + which allows e.g. to determine the hosts address space layout. + + never Disables the mitigation + ============ ============================================================== + +The parameter can be provided on the kernel command line, as a module +parameter when loading the modules and at runtime modified via the sysfs +file: + +/sys/module/kvm_intel/parameters/vmentry_l1d_flush + +The default is 'cond'. If 'l1tf=full,force' is given on the kernel command +line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush +module parameter is ignored and writes to the sysfs file are rejected. + + +Mitigation selection guide +-------------------------- + +1. No virtualization in use +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + The system is protected by the kernel unconditionally and no further + action is required. + +2. Virtualization with trusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + If the guest comes from a trusted source and the guest OS kernel is + guaranteed to have the L1TF mitigations in place the system is fully + protected against L1TF and no further action is required. + + To avoid the overhead of the default L1D flushing on VMENTER the + administrator can disable the flushing via the kernel command line and + sysfs control files. See :ref:`mitigation_control_command_line` and + :ref:`mitigation_control_kvm`. + + +3. Virtualization with untrusted guests +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +3.1. SMT not supported or disabled +"""""""""""""""""""""""""""""""""" + + If SMT is not supported by the processor or disabled in the BIOS or by + the kernel, it's only required to enforce L1D flushing on VMENTER. + + Conditional L1D flushing is the default behaviour and can be tuned. See + :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`. + +3.2. EPT not supported or disabled +"""""""""""""""""""""""""""""""""" + + If EPT is not supported by the processor or disabled in the hypervisor, + the system is fully protected. SMT can stay enabled and L1D flushing on + VMENTER is not required. + + EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter. + +3.3. SMT and EPT supported and active +""""""""""""""""""""""""""""""""""""" + + If SMT and EPT are supported and active then various degrees of + mitigations can be employed: + + - L1D flushing on VMENTER: + + L1D flushing on VMENTER is the minimal protection requirement, but it + is only potent in combination with other mitigation methods. + + Conditional L1D flushing is the default behaviour and can be tuned. See + :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`. + + - Guest confinement: + + Confinement of guests to a single or a group of physical cores which + are not running any other processes, can reduce the attack surface + significantly, but interrupts, soft interrupts and kernel threads can + still expose valuable data to a potential attacker. See + :ref:`guest_confinement`. + + - Interrupt isolation: + + Isolating the guest CPUs from interrupts can reduce the attack surface + further, but still allows a malicious guest to explore a limited amount + of host physical memory. This can at least be used to gain knowledge + about the host address space layout. The interrupts which have a fixed + affinity to the CPUs which run the untrusted guests can depending on + the scenario still trigger soft interrupts and schedule kernel threads + which might expose valuable information. See + :ref:`interrupt_isolation`. + +The above three mitigation methods combined can provide protection to a +certain degree, but the risk of the remaining attack surface has to be +carefully analyzed. For full protection the following methods are +available: + + - Disabling SMT: + + Disabling SMT and enforcing the L1D flushing provides the maximum + amount of protection. This mitigation is not depending on any of the + above mitigation methods. + + SMT control and L1D flushing can be tuned by the command line + parameters 'nosmt', 'l1tf', 'kvm-intel.vmentry_l1d_flush' and at run + time with the matching sysfs control files. See :ref:`smt_control`, + :ref:`mitigation_control_command_line` and + :ref:`mitigation_control_kvm`. + + - Disabling EPT: + + Disabling EPT provides the maximum amount of protection as well. It is + not depending on any of the above mitigation methods. SMT can stay + enabled and L1D flushing is not required, but the performance impact is + significant. + + EPT can be disabled in the hypervisor via the 'kvm-intel.ept' + parameter. + + +.. _default_mitigations: + +Default mitigations +------------------- + + The kernel default mitigations for vulnerable processors are: + + - PTE inversion to protect against malicious user space. This is done + unconditionally and cannot be controlled. + + - L1D conditional flushing on VMENTER when EPT is enabled for + a guest. + + The kernel does not by default enforce the disabling of SMT, which leaves + SMT systems vulnerable when running untrusted guests with EPT enabled. + + The rationale for this choice is: + + - Force disabling SMT can break existing setups, especially with + unattended updates. + + - If regular users run untrusted guests on their machine, then L1TF is + just an add on to other malware which might be embedded in an untrusted + guest, e.g. spam-bots or attacks on the local network. + + There is no technical way to prevent a user from running untrusted code + on their machines blindly. + + - It's technically extremely unlikely and from today's knowledge even + impossible that L1TF can be exploited via the most popular attack + mechanisms like JavaScript because these mechanisms have no way to + control PTEs. If this would be possible and not other mitigation would + be possible, then the default might be different. + + - The administrators of cloud and hosting setups have to carefully + analyze the risk for their scenarios and make the appropriate + mitigation choices, which might even vary across their deployed + machines and also result in other changes of their overall setup. + There is no way for the kernel to provide a sensible default for this + kind of scenarios.

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tony Luck tony.luck@intel.com

commit 1949f9f49792d65dba2090edddbe36a5f02e3ba3 upstream

Fix spelling and other typos

Signed-off-by: Tony Luck tony.luck@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/l1tf.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/Documentation/l1tf.rst +++ b/Documentation/l1tf.rst @@ -17,7 +17,7 @@ vulnerability is not present on: - Older processor models, where the CPU family is < 6

- A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft, - Penwell, Pineview, Slivermont, Airmont, Merrifield) + Penwell, Pineview, Silvermont, Airmont, Merrifield)

- The Intel Core Duo Yonah variants (2006 - 2008)

@@ -113,7 +113,7 @@ Attack scenarios deployment scenario. The mitigations, their protection scope and impact are described in the next sections.

- The default mitigations and the rationale for chosing them are explained + The default mitigations and the rationale for choosing them are explained at the end of this document. See :ref:`default_mitigations`.

.. _l1tf_sys_info: @@ -191,15 +191,15 @@ Guest mitigation mechanisms - unconditional ('always')

The conditional mode avoids L1D flushing after VMEXITs which execute - only audited code pathes before the corresponding VMENTER. These code - pathes have beed verified that they cannot expose secrets or other + only audited code paths before the corresponding VMENTER. These code + paths have been verified that they cannot expose secrets or other interesting data to an attacker, but they can leak information about the address space layout of the hypervisor.

Unconditional mode flushes L1D on all VMENTER invocations and provides maximum protection. It has a higher overhead than the conditional mode. The overhead cannot be quantified correctly as it depends on the - work load scenario and the resulting number of VMEXITs. + workload scenario and the resulting number of VMEXITs.

The general recommendation is to enable L1D flush on VMENTER. The kernel defaults to conditional mode on affected processors. @@ -262,7 +262,7 @@ Guest mitigation mechanisms Whether the interrupts with are affine to CPUs, which run untrusted guests, provide interesting data for an attacker depends on the system configuration and the scenarios which run on the system. While for some - of the interrupts it can be assumed that they wont expose interesting + of the interrupts it can be assumed that they won't expose interesting information beyond exposing hints about the host OS memory layout, there is no way to make general assumptions.

@@ -299,7 +299,7 @@ Guest mitigation mechanisms to be brought up at least partially and are then shut down again. "nosmt" can be undone via the sysfs interface.

- nosmt=force Has the same effect as "nosmt' but it does not allow to + nosmt=force Has the same effect as "nosmt" but it does not allow to undo the SMT disable via the sysfs interface. =========== ==========================================================

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange nstange@suse.de

commit 379fd0c7e6a391e5565336a646f19f218fb98c6c upstream

vmx_l1d_flush() gets invoked only if l1tf_flush_l1d is true. There's no point in setting l1tf_flush_l1d to true from there again.

Signed-off-by: Nicolai Stange nstange@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8665,15 +8665,15 @@ static void vmx_l1d_flush(struct kvm_vcp /* * This code is only executed when the the flush mode is 'cond' or * 'always' - * - * If 'flush always', keep the flush bit set, otherwise clear - * it. The flush bit gets set again either from vcpu_run() or from - * one of the unsafe VMEXIT handlers. */ - if (static_branch_unlikely(&vmx_l1d_flush_always)) - vcpu->arch.l1tf_flush_l1d = true; - else + if (!static_branch_unlikely(&vmx_l1d_flush_always)) { + /* + * Clear the flush bit, it gets set again either from + * vcpu_run() or from one of the unsafe VMEXIT + * handlers. + */ vcpu->arch.l1tf_flush_l1d = false; + }

vcpu->stat.l1d_flush++;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange nstange@suse.de

commit 5b6ccc6c3b1a477fbac9ec97a0b4c1c48e765209 upstream

Currently, vmx_vcpu_run() checks if l1tf_flush_l1d is set and invokes vmx_l1d_flush() if so.

This test is unncessary for the "always flush L1D" mode.

Move the check to vmx_l1d_flush()'s conditional mode code path.

Notes: - vmx_l1d_flush() is likely to get inlined anyway and thus, there's no extra function call.

- This inverts the (static) branch prediction, but there hadn't been any explicit likely()/unlikely() annotations before and so it stays as is.

Signed-off-by: Nicolai Stange nstange@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8667,12 +8667,16 @@ static void vmx_l1d_flush(struct kvm_vcp * 'always' */ if (static_branch_likely(&vmx_l1d_flush_cond)) { + bool flush_l1d = vcpu->arch.l1tf_flush_l1d; + /* * Clear the flush bit, it gets set again either from * vcpu_run() or from one of the unsafe VMEXIT * handlers. */ vcpu->arch.l1tf_flush_l1d = false; + if (!flush_l1d) + return; }

vcpu->stat.l1d_flush++; @@ -9162,10 +9166,8 @@ static void __noclone vmx_vcpu_run(struc

vmx->__launched = vmx->loaded_vmcs->launched;

- if (static_branch_unlikely(&vmx_l1d_should_flush)) { - if (vcpu->arch.l1tf_flush_l1d) - vmx_l1d_flush(vcpu); - } + if (static_branch_unlikely(&vmx_l1d_should_flush)) + vmx_l1d_flush(vcpu);

asm( /* Store host registers */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange nstange@suse.de

commit 45b575c00d8e72d69d75dd8c112f044b7b01b069 upstream

Part of the L1TF mitigation for vmx includes flushing the L1D cache upon VMENTRY.

L1D flushes are costly and two modes of operations are provided to users: "always" and the more selective "conditional" mode.

If operating in the latter, the cache would get flushed only if a host side code path considered unconfined had been traversed. "Unconfined" in this context means that it might have pulled in sensitive data like user data or kernel crypto keys.

The need for L1D flushes is tracked by means of the per-vcpu flag l1tf_flush_l1d. KVM exit handlers considered unconfined set it. A vmx_l1d_flush() subsequently invoked before the next VMENTER will conduct a L1d flush based on its value and reset that flag again.

Currently, interrupts delivered "normally" while in root operation between VMEXIT and VMENTER are not taken into account. Part of the reason is that these don't leave any traces and thus, the vmx code is unable to tell if any such has happened.

As proposed by Paolo Bonzini, prepare for tracking all interrupts by introducing a new per-cpu flag, "kvm_cpu_l1tf_flush_l1d". It will be in strong analogy to the per-vcpu ->l1tf_flush_l1d.

A later patch will make interrupt handlers set it.

For the sake of cache locality, group kvm_cpu_l1tf_flush_l1d into x86' per-cpu irq_cpustat_t as suggested by Peter Zijlstra.

Provide the helpers kvm_set_cpu_l1tf_flush_l1d(), kvm_clear_cpu_l1tf_flush_l1d() and kvm_get_cpu_l1tf_flush_l1d(). Make them trivial resp. non-existent for !CONFIG_KVM_INTEL as appropriate.

Let vmx_l1d_flush() handle kvm_cpu_l1tf_flush_l1d in the same way as l1tf_flush_l1d.

Suggested-by: Paolo Bonzini pbonzini@redhat.com Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Nicolai Stange nstange@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/hardirq.h | 23 +++++++++++++++++++++++ arch/x86/kvm/vmx.c | 17 +++++++++++++---- 2 files changed, 36 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -6,6 +6,9 @@

typedef struct { u16 __softirq_pending; +#if IS_ENABLED(CONFIG_KVM_INTEL) + u8 kvm_cpu_l1tf_flush_l1d; +#endif unsigned int __nmi_count; /* arch dependent */ #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ @@ -60,4 +63,24 @@ extern u64 arch_irq_stat_cpu(unsigned in extern u64 arch_irq_stat(void); #define arch_irq_stat arch_irq_stat

+ +#if IS_ENABLED(CONFIG_KVM_INTEL) +static inline void kvm_set_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); +} + +static inline void kvm_clear_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0); +} + +static inline bool kvm_get_cpu_l1tf_flush_l1d(void) +{ + return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); +} +#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ +static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ + #endif /* _ASM_X86_HARDIRQ_H */ --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8667,14 +8667,23 @@ static void vmx_l1d_flush(struct kvm_vcp * 'always' */ if (static_branch_likely(&vmx_l1d_flush_cond)) { - bool flush_l1d = vcpu->arch.l1tf_flush_l1d; + bool flush_l1d;

/* - * Clear the flush bit, it gets set again either from - * vcpu_run() or from one of the unsafe VMEXIT - * handlers. + * Clear the per-vcpu flush bit, it gets set again + * either from vcpu_run() or from one of the unsafe + * VMEXIT handlers. */ + flush_l1d = vcpu->arch.l1tf_flush_l1d; vcpu->arch.l1tf_flush_l1d = false; + + /* + * Clear the per-cpu flush bit, it gets set again from + * the interrupt handlers. + */ + flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); + kvm_clear_cpu_l1tf_flush_l1d(); + if (!flush_l1d) return; }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Stange nstange@suse.de

commit ffcba43ff66c7dab34ec700debd491d2a4d319b4 upstream

The last missing piece to having vmx_l1d_flush() take interrupts after VMEXIT into account is to set the kvm_cpu_l1tf_flush_l1d per-cpu flag on irq entry.

Issue calls to kvm_set_cpu_l1tf_flush_l1d() from entering_irq(), ipi_entering_ack_irq(), smp_reschedule_interrupt() and uv_bau_message_interrupt().

Suggested-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Nicolai Stange nstange@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/apic.h | 3 +++ arch/x86/kernel/smp.c | 1 + arch/x86/platform/uv/tlb_uv.c | 1 + 3 files changed, 5 insertions(+)

--- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -12,6 +12,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/idle.h> +#include <asm/hardirq.h>

#define ARCH_APICTIMER_STOPS_ON_C3 1

@@ -647,6 +648,7 @@ static inline void entering_irq(void) { irq_enter(); exit_idle(); + kvm_set_cpu_l1tf_flush_l1d(); }

static inline void entering_ack_irq(void) @@ -659,6 +661,7 @@ static inline void ipi_entering_ack_irq( { irq_enter(); ack_APIC_irq(); + kvm_set_cpu_l1tf_flush_l1d(); }

static inline void exiting_irq(void) --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -271,6 +271,7 @@ __visible void __irq_entry smp_reschedul /* * KVM uses this interrupt to force a cpu out of guest mode */ + kvm_set_cpu_l1tf_flush_l1d(); }

__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs) --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1283,6 +1283,7 @@ void uv_bau_message_interrupt(struct pt_ struct msg_desc msgdesc;

ack_APIC_irq(); + kvm_set_cpu_l1tf_flush_l1d(); time_start = get_cycles();

bcp = &per_cpu(bau_control, smp_processor_id());

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

commit 58331136136935c631c2b5f06daf4c3006416e91 upstream

Dave reported, that it's not confirmed that Yonah processors are unaffected. Remove them from the list.

Reported-by: ave Hansen dave.hansen@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/l1tf.rst | 2 -- 1 file changed, 2 deletions(-)

--- a/Documentation/l1tf.rst +++ b/Documentation/l1tf.rst @@ -19,8 +19,6 @@ vulnerability is not present on: - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft, Penwell, Pineview, Silvermont, Airmont, Merrifield)

- - The Intel Core Duo Yonah variants (2006 - 2008) - - The Intel XEON PHI family

- Intel processors which have the ARCH_CAP_RDCL_NO bit set in the

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini pbonzini@redhat.com

commit ea156d192f5257a5bf393d33910d3b481bf8a401 upstream

Three changes to the content of the sysfs file:

- If EPT is disabled, L1TF cannot be exploited even across threads on the same core, and SMT is irrelevant.

- If mitigation is completely disabled, and SMT is enabled, print "vulnerable" instead of "vulnerable, SMT vulnerable"

- Reorder the two parts so that the main vulnerability state comes first and the detail on SMT is second.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -737,9 +737,15 @@ static ssize_t l1tf_show_state(char *buf if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);

- return sprintf(buf, "%s; VMX: SMT %s, L1D %s\n", L1TF_DEFAULT_MSG, - cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled", - l1tf_vmx_states[l1tf_vmx_mitigation]); + if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || + (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && + cpu_smt_control == CPU_SMT_ENABLED)) + return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); + + return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled"); } #else static ssize_t l1tf_show_state(char *buf)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini pbonzini@redhat.com

commit 5b76a3cff011df2dcb6186c965a2e4d809a05ad4 upstream

When nested virtualization is in use, VMENTER operations from the nested hypervisor into the nested guest will always be processed by the bare metal hypervisor, and KVM's "conditional cache flushes" mode in particular does a flush on nested vmentry. Therefore, include the "skip L1D flush on vmentry" bit in KVM's suggested ARCH_CAPABILITIES setting.

Add the relevant Documentation.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/l1tf.rst | 21 +++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx.c | 3 +-- arch/x86/kvm/x86.c | 26 +++++++++++++++++++++++++- 4 files changed, 48 insertions(+), 3 deletions(-)

--- a/Documentation/l1tf.rst +++ b/Documentation/l1tf.rst @@ -546,6 +546,27 @@ available: EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.

+3.4. Nested virtual machines +"""""""""""""""""""""""""""" + +When nested virtualization is in use, three operating systems are involved: +the bare metal hypervisor, the nested hypervisor and the nested virtual +machine. VMENTER operations from the nested hypervisor into the nested +guest will always be processed by the bare metal hypervisor. If KVM is the +bare metal hypervisor it wiil: + + - Flush the L1D cache on every switch from the nested hypervisor to the + nested virtual machine, so that the nested hypervisor's secrets are not + exposed to the nested virtual machine; + + - Flush the L1D cache on every switch from the nested virtual machine to + the nested hypervisor; this is a complex operation, and flushing the L1D + cache avoids that the bare metal hypervisor's secrets are exposed to the + nested virtual machine; + + - Instruct the nested hypervisor to not perform any L1D cache flush. This + is an optimization to avoid double L1D flushing. +

.. _default_mitigations:

--- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1346,6 +1346,7 @@ void kvm_vcpu_reload_apic_access_page(st void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address);

+u64 kvm_get_arch_capabilities(void); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5461,8 +5461,7 @@ static int vmx_vcpu_setup(struct vcpu_vm ++vmx->nmsrs; }

- if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities); + vmx->arch_capabilities = kvm_get_arch_capabilities();

vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1020,11 +1020,35 @@ static u32 msr_based_features[] = {

static unsigned int num_msr_based_features;

+u64 kvm_get_arch_capabilities(void) +{ + u64 data; + + rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data); + + /* + * If we're doing cache flushes (either "always" or "cond") + * we will do one whenever the guest does a vmlaunch/vmresume. + * If an outer hypervisor is doing the cache flush for us + * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that + * capability to the guest too, and if EPT is disabled we're not + * vulnerable. Overall, only VMENTER_L1D_FLUSH_NEVER will + * require a nested hypervisor to do a flush of its own. + */ + if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER) + data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH; + + return data; +} +EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities); + static int kvm_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { - case MSR_IA32_UCODE_REV: case MSR_IA32_ARCH_CAPABILITIES: + msr->data = kvm_get_arch_capabilities(); + break; + case MSR_IA32_UCODE_REV: rdmsrl_safe(msr->index, &msr->data); break; default:

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit f22cc87f6c1f771b57c407555cfefd811cdd9507 upstream

For kernel mappings PAGE_PROTNONE is not necessarily set for a non present mapping, but the inversion logic explicitely checks for !PRESENT and PROT_NONE.

Remove the PROT_NONE check and make the inversion unconditional for all not present mappings.

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/pgtable-invert.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/include/asm/pgtable-invert.h +++ b/arch/x86/include/asm/pgtable-invert.h @@ -6,7 +6,7 @@

static inline bool __pte_needs_invert(u64 val) { - return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE; + return !(val & _PAGE_PRESENT); }

/* Get a mask to xor with the page table entry to get the correct pfn. */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andi Kleen ak@linux.intel.com

commit 958f79b9ee55dfaf00c8106ed1c22a2919e0028b upstream

set_memory_np() is used to mark kernel mappings not present, but it has it's own open coded mechanism which does not have the L1TF protection of inverting the address bits.

Replace the open coded PTE manipulation with the L1TF protecting low level PTE routines.

Passes the CPA self test.

Signed-off-by: Andi Kleen ak@linux.intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de [ dwmw2: Pull in pud_mkhuge() from commit a00cc7d9dd, and pfn_pud() ] Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/pgtable.h | 27 +++++++++++++++++++++++++++ arch/x86/mm/pageattr.c | 8 ++++---- 2 files changed, 31 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -413,12 +413,39 @@ static inline pmd_t pfn_pmd(unsigned lon return __pmd(pfn | massage_pgprot(pgprot)); }

+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) +{ + phys_addr_t pfn = page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PUD_PAGE_MASK; + return __pud(pfn | massage_pgprot(pgprot)); +} + static inline pmd_t pmd_mknotpresent(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); }

+static inline pud_t pud_set_flags(pud_t pud, pudval_t set) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v | set); +} + +static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v & ~clear); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_PSE); +} + static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1001,8 +1001,8 @@ static long populate_pmd(struct cpa_data

pmd = pmd_offset(pud, start);

- set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pmd_pgprot))); + set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn, + canon_pgprot(pmd_pgprot))));

start += PMD_SIZE; cpa->pfn += PMD_SIZE >> PAGE_SHIFT; @@ -1074,8 +1074,8 @@ static long populate_pud(struct cpa_data * Map everything starting from the Gb boundary, possibly with 1G pages */ while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { - set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE | - massage_pgprot(pud_pgprot))); + set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, + canon_pgprot(pud_pgprot))));

start += PUD_SIZE; cpa->pfn += PUD_SIZE >> PAGE_SHIFT;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Woodhouse dwmw@amazon.co.uk

commit e24f14b0ff985f3e09e573ba1134bfdf42987e05 upstream

Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/arch/x86/include/asm/cpufeatures.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -213,7 +213,7 @@ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ - +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */

/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -317,6 +317,7 @@ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #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_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */

@@ -349,5 +350,6 @@ #define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ #define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */

#endif /* _ASM_X86_CPUFEATURES_H */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf jpoimboe@redhat.com

commit 07d981ad4cf1e78361c6db1c28ee5ba105f96cc1 upstream

The kernel unnecessarily prevents late microcode loading when SMT is disabled. It should be safe to allow it if all the primary threads are online.

Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Acked-by: Borislav Petkov bp@suse.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/microcode/core.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

--- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -386,12 +386,20 @@ static struct platform_device *microcode

static int check_online_cpus(void) { - if (num_online_cpus() == num_present_cpus()) - return 0; + unsigned int cpu;

- pr_err("Not all CPUs online, aborting microcode update.\n"); + /* + * Make sure all CPUs are online. It's fine for SMT to be disabled if + * all the primary threads are still online. + */ + for_each_present_cpu(cpu) { + if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) { + pr_err("Not all CPUs online, aborting microcode update.\n"); + return -EINVAL; + } + }

- return -EINVAL; + return 0; }

static int reload_for_cpu(int cpu)