From adbd914dcde0b03bfc08ffe40b81f31b0457833f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 21 Apr 2021 14:31:50 +0100 Subject: [PATCH 01/72] btrfs: zoned: fix silent data loss after failure splitting ordered extent On a zoned filesystem, sometimes we need to split an ordered extent into 3 different ordered extents. The original ordered extent is shortened, at the front and at the rear, and we create two other new ordered extents to represent the trimmed parts of the original ordered extent. After adjusting the original ordered extent, we create an ordered extent to represent the pre-range, and that may fail with ENOMEM for example. After that we always try to create the ordered extent for the post-range, and if that happens to succeed we end up returning success to the caller as we overwrite the 'ret' variable which contained the previous error. This means we end up with a file range for which there is no ordered extent, which results in the range never getting a new file extent item pointing to the new data location. And since the split operation did not return an error, writeback does not fail and the inode's mapping is not flagged with an error, resulting in a subsequent fsync not reporting an error either. It's possibly very unlikely to have the creation of the post-range ordered extent succeed after the creation of the pre-range ordered extent failed, but it's not impossible. So fix this by making sure we only create the post-range ordered extent if there was no error creating the ordered extent for the pre-range. Fixes: d22002fd37bd97 ("btrfs: zoned: split ordered extent when bio is sent") CC: stable@vger.kernel.org # 5.12+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ordered-data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 07b0b4218791..6c413bb451a3 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -984,7 +984,7 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, if (pre) ret = clone_ordered_extent(ordered, 0, pre); - if (post) + if (ret == 0 && post) ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, post); From ffb7c2e923cb3232454a513dcb5636e73091aa88 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 22 Apr 2021 12:09:21 +0100 Subject: [PATCH 02/72] btrfs: do not consider send context as valid when trying to flush qgroups At qgroup.c:try_flush_qgroup() we are asserting that current->journal_info is either NULL or has the value BTRFS_SEND_TRANS_STUB. However allowing for BTRFS_SEND_TRANS_STUB makes no sense because: 1) It is misleading, because send operations are read-only and do not ever need to reserve qgroup space; 2) We already assert that current->journal_info != BTRFS_SEND_TRANS_STUB at transaction.c:start_transaction(); 3) On a kernel without CONFIG_BTRFS_ASSERT=y set, it would result in a crash if try_flush_qgroup() is ever called in a send context, because at transaction.c:start_transaction we cast current->journal_info into a struct btrfs_trans_handle pointer and then dereference it. So just do allow a send context at try_flush_qgroup() and update the comment about it. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 2319c923c9e6..b1caf5acf1e2 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3545,11 +3545,15 @@ static int try_flush_qgroup(struct btrfs_root *root) struct btrfs_trans_handle *trans; int ret; - /* Can't hold an open transaction or we run the risk of deadlocking */ - ASSERT(current->journal_info == NULL || - current->journal_info == BTRFS_SEND_TRANS_STUB); - if (WARN_ON(current->journal_info && - current->journal_info != BTRFS_SEND_TRANS_STUB)) + /* + * Can't hold an open transaction or we run the risk of deadlocking, + * and can't either be under the context of a send operation (where + * current->journal_info is set to BTRFS_SEND_TRANS_STUB), as that + * would result in a crash when starting a transaction and does not + * make sense either (send is a read-only operation). + */ + ASSERT(current->journal_info == NULL); + if (WARN_ON(current->journal_info)) return 0; /* From 626e9f41f7c281ba3e02843702f68471706aa6d9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 27 Apr 2021 11:27:20 +0100 Subject: [PATCH 03/72] btrfs: fix race leading to unpersisted data and metadata on fsync When doing a fast fsync on a file, there is a race which can result in the fsync returning success to user space without logging the inode and without durably persisting new data. The following example shows one possible scenario for this: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ touch /mnt/bar $ xfs_io -f -c "pwrite -S 0xab 0 1M" -c "fsync" /mnt/baz # Now we have: # file bar == inode 257 # file baz == inode 258 $ mv /mnt/baz /mnt/foo # Now we have: # file bar == inode 257 # file foo == inode 258 $ xfs_io -c "pwrite -S 0xcd 0 1M" /mnt/foo # fsync bar before foo, it is important to trigger the race. $ xfs_io -c "fsync" /mnt/bar $ xfs_io -c "fsync" /mnt/foo # After this: # inode 257, file bar, is empty # inode 258, file foo, has 1M filled with 0xcd # Replay the log: $ mount /dev/sdc /mnt # After this point file foo should have 1M filled with 0xcd and not 0xab The following steps explain how the race happens: 1) Before the first fsync of inode 258, when it has the "baz" name, its ->logged_trans is 0, ->last_sub_trans is 0 and ->last_log_commit is -1. The inode also has the full sync flag set; 2) After the first fsync, we set inode 258 ->logged_trans to 6, which is the generation of the current transaction, and set ->last_log_commit to 0, which is the current value of ->last_sub_trans (done at btrfs_log_inode()). The full sync flag is cleared from the inode during the fsync. The log sub transaction that was committed had an ID of 0 and when we synced the log, at btrfs_sync_log(), we incremented root->log_transid from 0 to 1; 3) During the rename: We update inode 258, through btrfs_update_inode(), and that causes its ->last_sub_trans to be set to 1 (the current log transaction ID), and ->last_log_commit remains with a value of 0. After updating inode 258, because we have previously logged the inode in the previous fsync, we log again the inode through the call to btrfs_log_new_name(). This results in updating the inode's ->last_log_commit from 0 to 1 (the current value of its ->last_sub_trans). The ->last_sub_trans of inode 257 is updated to 1, which is the ID of the next log transaction; 4) Then a buffered write against inode 258 is made. This leaves the value of ->last_sub_trans as 1 (the ID of the current log transaction, stored at root->log_transid); 5) Then an fsync against inode 257 (or any other inode other than 258), happens. This results in committing the log transaction with ID 1, which results in updating root->last_log_commit to 1 and bumping root->log_transid from 1 to 2; 6) Then an fsync against inode 258 starts. We flush delalloc and wait only for writeback to complete, since the full sync flag is not set in the inode's runtime flags - we do not wait for ordered extents to complete. Then, at btrfs_sync_file(), we call btrfs_inode_in_log() before the ordered extent completes. The call returns true: static inline bool btrfs_inode_in_log(...) { bool ret = false; spin_lock(&inode->lock); if (inode->logged_trans == generation && inode->last_sub_trans <= inode->last_log_commit && inode->last_sub_trans <= inode->root->last_log_commit) ret = true; spin_unlock(&inode->lock); return ret; } generation has a value of 6 (fs_info->generation), ->logged_trans also has a value of 6 (set when we logged the inode during the first fsync and when logging it during the rename), ->last_sub_trans has a value of 1, set during the rename (step 3), ->last_log_commit also has a value of 1 (set in step 3) and root->last_log_commit has a value of 1, which was set in step 5 when fsyncing inode 257. As a consequence we don't log the inode, any new extents and do not sync the log, resulting in a data loss if a power failure happens after the fsync and before the current transaction commits. Also, because we do not log the inode, after a power failure the mtime and ctime of the inode do not match those we had before. When the ordered extent completes before we call btrfs_inode_in_log(), then the call returns false and we log the inode and sync the log, since at the end of ordered extent completion we update the inode and set ->last_sub_trans to 2 (the value of root->log_transid) and ->last_log_commit to 1. This problem is found after removing the check for the emptiness of the inode's list of modified extents in the recent commit 209ecbb8585bf6 ("btrfs: remove stale comment and logic from btrfs_inode_in_log()"), added in the 5.13 merge window. However checking the emptiness of the list is not really the way to solve this problem, and was never intended to, because while that solves the problem for COW writes, the problem persists for NOCOW writes because in that case the list is always empty. In the case of NOCOW writes, even though we wait for the writeback to complete before returning from btrfs_sync_file(), we end up not logging the inode, which has a new mtime/ctime, and because we don't sync the log, we never issue disk barriers (send REQ_PREFLUSH to the device) since that only happens when we sync the log (when we write super blocks at btrfs_sync_log()). So effectively, for a NOCOW case, when we return from btrfs_sync_file() to user space, we are not guaranteeing that the data is durably persisted on disk. Also, while the example above uses a rename exchange to show how the problem happens, it is not the only way to trigger it. An alternative could be adding a new hard link to inode 258, since that also results in calling btrfs_log_new_name() and updating the inode in the log. An example reproducer using the addition of a hard link instead of a rename operation: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ touch /mnt/bar $ xfs_io -f -c "pwrite -S 0xab 0 1M" -c "fsync" /mnt/foo $ ln /mnt/foo /mnt/foo_link $ xfs_io -c "pwrite -S 0xcd 0 1M" /mnt/foo $ xfs_io -c "fsync" /mnt/bar $ xfs_io -c "fsync" /mnt/foo # Replay the log: $ mount /dev/sdc /mnt # After this point file foo often has 1M filled with 0xab and not 0xcd The reasons leading to the final fsync of file foo, inode 258, not persisting the new data are the same as for the previous example with a rename operation. So fix by never skipping logging and log syncing when there are still any ordered extents in flight. To avoid making the conditional if statement that checks if logging an inode is needed harder to read, place all the logic into an helper function with separate if statements to make it more manageable and easier to read. A test case for fstests will follow soon. For NOCOW writes, the problem existed before commit b5e6c3e170b770 ("btrfs: always wait on ordered extents at fsync time"), introduced in kernel 4.19, then it went away with that commit since we started to always wait for ordered extent completion before logging. The problem came back again once the fast fsync path was changed again to avoid waiting for ordered extent completion, in commit 487781796d3022 ("btrfs: make fast fsyncs wait only for writeback"), added in kernel 5.10. However, for COW writes, the race only happens after the recent commit 209ecbb8585bf6 ("btrfs: remove stale comment and logic from btrfs_inode_in_log()"), introduced in the 5.13 merge window. For NOCOW writes, the bug existed before that commit. So tag 5.10+ as the release for stable backports. CC: stable@vger.kernel.org # 5.10+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/file.c | 35 +++++++++++++++++++++++++---------- fs/btrfs/tree-log.c | 3 ++- 2 files changed, 27 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 864c08d08a35..3b10d98b4ebb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2067,6 +2067,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) return ret; } +static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) +{ + struct btrfs_inode *inode = BTRFS_I(ctx->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + + if (btrfs_inode_in_log(inode, fs_info->generation) && + list_empty(&ctx->ordered_extents)) + return true; + + /* + * If we are doing a fast fsync we can not bail out if the inode's + * last_trans is <= then the last committed transaction, because we only + * update the last_trans of the inode during ordered extent completion, + * and for a fast fsync we don't wait for that, we only wait for the + * writeback to complete. + */ + if (inode->last_trans <= fs_info->last_trans_committed && + (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) || + list_empty(&ctx->ordered_extents))) + return true; + + return false; +} + /* * fsync call for both files and directories. This logs the inode into * the tree log instead of forcing full commits whenever possible. @@ -2185,17 +2209,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); - /* - * If we are doing a fast fsync we can not bail out if the inode's - * last_trans is <= then the last committed transaction, because we only - * update the last_trans of the inode during ordered extent completion, - * and for a fast fsync we don't wait for that, we only wait for the - * writeback to complete. - */ smp_mb(); - if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || - (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed && - (full_sync || list_empty(&ctx.ordered_extents)))) { + if (skip_inode_logging(&ctx)) { /* * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c1353b84ae54..a0fc3a1390ab 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6060,7 +6060,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * (since logging them is pointless, a link count of 0 means they * will never be accessible). */ - if (btrfs_inode_in_log(inode, trans->transid) || + if ((btrfs_inode_in_log(inode, trans->transid) && + list_empty(&ctx->ordered_extents)) || inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; From f9baa501b4fd6962257853d46ddffbc21f27e344 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 22 Apr 2021 12:08:05 +0100 Subject: [PATCH 04/72] btrfs: fix deadlock when cloning inline extents and using qgroups There are a few exceptional cases where cloning an inline extent needs to copy the inline extent data into a page of the destination inode. When this happens, we end up starting a transaction while having a dirty page for the destination inode and while having the range locked in the destination's inode iotree too. Because when reserving metadata space for a transaction we may need to flush existing delalloc in case there is not enough free space, we have a mechanism in place to prevent a deadlock, which was introduced in commit 3d45f221ce627d ("btrfs: fix deadlock when cloning inline extent and low on free metadata space"). However when using qgroups, a transaction also reserves metadata qgroup space, which can also result in flushing delalloc in case there is not enough available space at the moment. When this happens we deadlock, since flushing delalloc requires locking the file range in the inode's iotree and the range was already locked at the very beginning of the clone operation, before attempting to start the transaction. When this issue happens, stack traces like the following are reported: [72747.556262] task:kworker/u81:9 state:D stack: 0 pid: 225 ppid: 2 flags:0x00004000 [72747.556268] Workqueue: writeback wb_workfn (flush-btrfs-1142) [72747.556271] Call Trace: [72747.556273] __schedule+0x296/0x760 [72747.556277] schedule+0x3c/0xa0 [72747.556279] io_schedule+0x12/0x40 [72747.556284] __lock_page+0x13c/0x280 [72747.556287] ? generic_file_readonly_mmap+0x70/0x70 [72747.556325] extent_write_cache_pages+0x22a/0x440 [btrfs] [72747.556331] ? __set_page_dirty_nobuffers+0xe7/0x160 [72747.556358] ? set_extent_buffer_dirty+0x5e/0x80 [btrfs] [72747.556362] ? update_group_capacity+0x25/0x210 [72747.556366] ? cpumask_next_and+0x1a/0x20 [72747.556391] extent_writepages+0x44/0xa0 [btrfs] [72747.556394] do_writepages+0x41/0xd0 [72747.556398] __writeback_single_inode+0x39/0x2a0 [72747.556403] writeback_sb_inodes+0x1ea/0x440 [72747.556407] __writeback_inodes_wb+0x5f/0xc0 [72747.556410] wb_writeback+0x235/0x2b0 [72747.556414] ? get_nr_inodes+0x35/0x50 [72747.556417] wb_workfn+0x354/0x490 [72747.556420] ? newidle_balance+0x2c5/0x3e0 [72747.556424] process_one_work+0x1aa/0x340 [72747.556426] worker_thread+0x30/0x390 [72747.556429] ? create_worker+0x1a0/0x1a0 [72747.556432] kthread+0x116/0x130 [72747.556435] ? kthread_park+0x80/0x80 [72747.556438] ret_from_fork+0x1f/0x30 [72747.566958] Workqueue: btrfs-flush_delalloc btrfs_work_helper [btrfs] [72747.566961] Call Trace: [72747.566964] __schedule+0x296/0x760 [72747.566968] ? finish_wait+0x80/0x80 [72747.566970] schedule+0x3c/0xa0 [72747.566995] wait_extent_bit.constprop.68+0x13b/0x1c0 [btrfs] [72747.566999] ? finish_wait+0x80/0x80 [72747.567024] lock_extent_bits+0x37/0x90 [btrfs] [72747.567047] btrfs_invalidatepage+0x299/0x2c0 [btrfs] [72747.567051] ? find_get_pages_range_tag+0x2cd/0x380 [72747.567076] __extent_writepage+0x203/0x320 [btrfs] [72747.567102] extent_write_cache_pages+0x2bb/0x440 [btrfs] [72747.567106] ? update_load_avg+0x7e/0x5f0 [72747.567109] ? enqueue_entity+0xf4/0x6f0 [72747.567134] extent_writepages+0x44/0xa0 [btrfs] [72747.567137] ? enqueue_task_fair+0x93/0x6f0 [72747.567140] do_writepages+0x41/0xd0 [72747.567144] __filemap_fdatawrite_range+0xc7/0x100 [72747.567167] btrfs_run_delalloc_work+0x17/0x40 [btrfs] [72747.567195] btrfs_work_helper+0xc2/0x300 [btrfs] [72747.567200] process_one_work+0x1aa/0x340 [72747.567202] worker_thread+0x30/0x390 [72747.567205] ? create_worker+0x1a0/0x1a0 [72747.567208] kthread+0x116/0x130 [72747.567211] ? kthread_park+0x80/0x80 [72747.567214] ret_from_fork+0x1f/0x30 [72747.569686] task:fsstress state:D stack: 0 pid:841421 ppid:841417 flags:0x00000000 [72747.569689] Call Trace: [72747.569691] __schedule+0x296/0x760 [72747.569694] schedule+0x3c/0xa0 [72747.569721] try_flush_qgroup+0x95/0x140 [btrfs] [72747.569725] ? finish_wait+0x80/0x80 [72747.569753] btrfs_qgroup_reserve_data+0x34/0x50 [btrfs] [72747.569781] btrfs_check_data_free_space+0x5f/0xa0 [btrfs] [72747.569804] btrfs_buffered_write+0x1f7/0x7f0 [btrfs] [72747.569810] ? path_lookupat.isra.48+0x97/0x140 [72747.569833] btrfs_file_write_iter+0x81/0x410 [btrfs] [72747.569836] ? __kmalloc+0x16a/0x2c0 [72747.569839] do_iter_readv_writev+0x160/0x1c0 [72747.569843] do_iter_write+0x80/0x1b0 [72747.569847] vfs_writev+0x84/0x140 [72747.569869] ? btrfs_file_llseek+0x38/0x270 [btrfs] [72747.569873] do_writev+0x65/0x100 [72747.569876] do_syscall_64+0x33/0x40 [72747.569879] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [72747.569899] task:fsstress state:D stack: 0 pid:841424 ppid:841417 flags:0x00004000 [72747.569903] Call Trace: [72747.569906] __schedule+0x296/0x760 [72747.569909] schedule+0x3c/0xa0 [72747.569936] try_flush_qgroup+0x95/0x140 [btrfs] [72747.569940] ? finish_wait+0x80/0x80 [72747.569967] __btrfs_qgroup_reserve_meta+0x36/0x50 [btrfs] [72747.569989] start_transaction+0x279/0x580 [btrfs] [72747.570014] clone_copy_inline_extent+0x332/0x490 [btrfs] [72747.570041] btrfs_clone+0x5b7/0x7a0 [btrfs] [72747.570068] ? lock_extent_bits+0x64/0x90 [btrfs] [72747.570095] btrfs_clone_files+0xfc/0x150 [btrfs] [72747.570122] btrfs_remap_file_range+0x3d8/0x4a0 [btrfs] [72747.570126] do_clone_file_range+0xed/0x200 [72747.570131] vfs_clone_file_range+0x37/0x110 [72747.570134] ioctl_file_clone+0x7d/0xb0 [72747.570137] do_vfs_ioctl+0x138/0x630 [72747.570140] __x64_sys_ioctl+0x62/0xc0 [72747.570143] do_syscall_64+0x33/0x40 [72747.570146] entry_SYSCALL_64_after_hwframe+0x44/0xa9 So fix this by skipping the flush of delalloc for an inode that is flagged with BTRFS_INODE_NO_DELALLOC_FLUSH, meaning it is currently under such a special case of cloning an inline extent, when flushing delalloc during qgroup metadata reservation. The special cases for cloning inline extents were added in kernel 5.7 by by commit 05a5a7621ce66c ("Btrfs: implement full reflink support for inline extents"), while having qgroup metadata space reservation flushing delalloc when low on space was added in kernel 5.9 by commit c53e9653605dbf ("btrfs: qgroup: try to flush qgroup space when we get -EDQUOT"). So use a "Fixes:" tag for the later commit to ease stable kernel backports. Reported-by: Wang Yugui Link: https://lore.kernel.org/linux-btrfs/20210421083137.31E3.409509F4@e16-tech.com/ Fixes: c53e9653605dbf ("btrfs: qgroup: try to flush qgroup space when we get -EDQUOT") CC: stable@vger.kernel.org # 5.9+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 2 +- fs/btrfs/qgroup.c | 2 +- fs/btrfs/send.c | 4 ++-- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 278e0cbc9a98..0f5b0b12762b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3127,7 +3127,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 new_size, u32 min_type); -int btrfs_start_delalloc_snapshot(struct btrfs_root *root); +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1a349759efae..69fcdf8f0b1c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9691,7 +9691,7 @@ out: return ret; } -int btrfs_start_delalloc_snapshot(struct btrfs_root *root) +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, @@ -9704,7 +9704,7 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root) if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &wbc, true, false); + return start_delalloc_inodes(root, &wbc, true, in_reclaim_context); } int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b1328f17607e..0ba0e4ddaf6b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1051,7 +1051,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent, */ btrfs_drew_read_lock(&root->snapshot_lock); - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) goto out; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index b1caf5acf1e2..3ded812f522c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3566,7 +3566,7 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, true); if (ret < 0) goto out; btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 55741adf9071..bd69db72acc5 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7170,7 +7170,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) int i; if (root) { - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); @@ -7178,7 +7178,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) for (i = 0; i < sctx->clone_roots_cnt; i++) { root = sctx->clone_roots[i].root; - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); From ff76d506030daeeeb967be8b8a189bf7aee8e7a8 Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Thu, 29 Apr 2021 16:12:26 +1200 Subject: [PATCH 05/72] KVM: x86/mmu: Avoid unnecessary page table allocation in kvm_tdp_mmu_map() In kvm_tdp_mmu_map(), while iterating TDP MMU page table entries, it is possible SPTE has already been frozen by another thread but the frozen is not done yet, for instance, when another thread is still in middle of zapping large page. In this case, the !is_shadow_present_pte() check for old SPTE in tdp_mmu_for_each_pte() may hit true, and in this case allocating new page table is unnecessary since tdp_mmu_set_spte_atomic() later will return false and page table will need to be freed. Add is_removed_spte() check before allocating new page table to avoid this. Signed-off-by: Kai Huang Message-Id: <20210429041226.50279-1-kai.huang@intel.com> Reviewed-by: Ben Gardon Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 88f69a6cc492..3c8284841bed 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1009,6 +1009,14 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, } if (!is_shadow_present_pte(iter.old_spte)) { + /* + * If SPTE has been forzen by another thread, just + * give up and retry, avoiding unnecessary page table + * allocation and free. + */ + if (is_removed_spte(iter.old_spte)) + break; + sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); child_pt = sp->spt; From 1699f65c8b658d434fe92563c906cd1a136c9cb6 Mon Sep 17 00:00:00 2001 From: "Shahin, Md Shahadat Hossain" Date: Fri, 30 Apr 2021 11:52:31 +0000 Subject: [PATCH 06/72] kvm/x86: Fix 'lpages' kvm stat for TDM MMU Large pages not being created properly may result in increased memory access time. The 'lpages' kvm stat used to keep track of the current number of large pages in the system, but with TDP MMU enabled the stat is not showing the correct number. This patch extends the lpages counter to cover the TDP case. Signed-off-by: Md Shahadat Hossain Shahin Cc: Bartosz Szczepanek Message-Id: <1619783551459.35424@amazon.de> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 3c8284841bed..c743894fe0b7 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -444,6 +444,13 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte); + if (is_large_pte(old_spte) != is_large_pte(new_spte)) { + if (is_large_pte(old_spte)) + atomic64_sub(1, (atomic64_t*)&kvm->stat.lpages); + else + atomic64_add(1, (atomic64_t*)&kvm->stat.lpages); + } + /* * The only times a SPTE should be changed from a non-present to * non-present state is when an MMIO entry is installed/modified/ From d981dd15498b188636ec5a7d8ad485e650f63d8d Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 28 Apr 2021 19:08:02 +0800 Subject: [PATCH 07/72] KVM: LAPIC: Accurately guarantee busy wait for timer to expire when using hv_timer Commit ee66e453db13d (KVM: lapic: Busy wait for timer to expire when using hv_timer) tries to set ktime->expired_tscdeadline by checking ktime->hv_timer_in_use since lapic timer oneshot/periodic modes which are emulated by vmx preemption timer also get advanced, they leverage the same vmx preemption timer logic with tsc-deadline mode. However, ktime->hv_timer_in_use is cleared before apic_timer_expired() handling, let's delay this clearing in preemption-disabled region. Fixes: ee66e453db13d ("KVM: lapic: Busy wait for timer to expire when using hv_timer") Reviewed-by: Sean Christopherson Signed-off-by: Wanpeng Li Message-Id: <1619608082-4187-1-git-send-email-wanpengli@tencent.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 152591f9243a..c0ebef560bd1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1913,8 +1913,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (!apic->lapic_timer.hv_timer_in_use) goto out; WARN_ON(rcuwait_active(&vcpu->wait)); - cancel_hv_timer(apic); apic_timer_expired(apic, false); + cancel_hv_timer(apic); if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); From 262de4102c7bb8e59f26a967a8ffe8cce85cc537 Mon Sep 17 00:00:00 2001 From: Benjamin Segall Date: Thu, 29 Apr 2021 16:22:34 +0000 Subject: [PATCH 08/72] kvm: exit halt polling on need_resched() as well single_task_running() is usually more general than need_resched() but CFS_BANDWIDTH throttling will use resched_task() when there is just one task to get the task to block. This was causing long-need_resched warnings and was likely allowing VMs to overrun their quota when halt polling. Signed-off-by: Ben Segall Signed-off-by: Venkatesh Srinivas Message-Id: <20210429162233.116849-1-venkateshs@chromium.org> Signed-off-by: Paolo Bonzini Cc: stable@vger.kernel.org Reviewed-by: Jim Mattson --- virt/kvm/kvm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2799c6660cce..b9f12da6af0e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2973,7 +2973,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (single_task_running() && !need_resched() && + ktime_before(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); From deee59bacb2402c20e6b1b6800f9a5127367eb2a Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 3 May 2021 15:54:42 +0300 Subject: [PATCH 09/72] KVM: nSVM: fix a typo in svm_leave_nested When forcibly leaving the nested mode, we should switch to vmcb01 Fixes: 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") Signed-off-by: Maxim Levitsky Message-Id: <20210503125446.1353307-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 540d43ba2cf4..3321220f3deb 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -886,7 +886,7 @@ void svm_leave_nested(struct vcpu_svm *svm) svm->nested.nested_run_pending = 0; leave_guest_mode(vcpu); - svm_switch_vmcb(svm, &svm->nested.vmcb02); + svm_switch_vmcb(svm, &svm->vmcb01); nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); From c74ad08f3333db2e44d3346b863f6d10d35e37dd Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 3 May 2021 15:54:43 +0300 Subject: [PATCH 10/72] KVM: nSVM: fix few bugs in the vmcb02 caching logic * Define and use an invalid GPA (all ones) for init value of last and current nested vmcb physical addresses. * Reset the current vmcb12 gpa to the invalid value when leaving the nested mode, similar to what is done on nested vmexit. * Reset the last seen vmcb12 address when disabling the nested SVM, as it relies on vmcb02 fields which are freed at that point. Fixes: 4995a3685f1b ("KVM: SVM: Use a separate vmcb for the nested L2 guest") Signed-off-by: Maxim Levitsky Message-Id: <20210503125446.1353307-3-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm/nested.c | 11 +++++++++++ arch/x86/kvm/svm/svm.c | 4 ++-- 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cbbcee0a84f9..848956bb3cf1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -113,6 +113,7 @@ #define VALID_PAGE(x) ((x) != INVALID_PAGE) #define UNMAPPED_GVA (~(gpa_t)0) +#define INVALID_GPA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 3321220f3deb..a88c64e004c3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -872,6 +872,15 @@ void svm_free_nested(struct vcpu_svm *svm) __free_page(virt_to_page(svm->nested.vmcb02.ptr)); svm->nested.vmcb02.ptr = NULL; + /* + * When last_vmcb12_gpa matches the current vmcb12 gpa, + * some vmcb12 fields are not loaded if they are marked clean + * in the vmcb12, since in this case they are up to date already. + * + * When the vmcb02 is freed, this optimization becomes invalid. + */ + svm->nested.last_vmcb12_gpa = INVALID_GPA; + svm->nested.initialized = false; } @@ -884,6 +893,8 @@ void svm_leave_nested(struct vcpu_svm *svm) if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + leave_guest_mode(vcpu); svm_switch_vmcb(svm, &svm->vmcb01); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9790c73f2a32..be5cf612ab1f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1235,8 +1235,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->current_vmcb->asid_generation = 0; svm->asid = 0; - svm->nested.vmcb12_gpa = 0; - svm->nested.last_vmcb12_gpa = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.last_vmcb12_gpa = INVALID_GPA; vcpu->arch.hflags = 0; if (!kvm_pause_in_guest(vcpu->kvm)) { From 9d290e16432cacd448475d38dec2753b75b9665f Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 3 May 2021 15:54:44 +0300 Subject: [PATCH 11/72] KVM: nSVM: leave the guest mode prior to loading a nested state This allows the KVM to load the nested state more than once without warnings. Signed-off-by: Maxim Levitsky Message-Id: <20210503125446.1353307-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index a88c64e004c3..32400cba608d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1309,12 +1309,15 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * L2 registers if needed are moved from the current VMCB to VMCB02. */ + if (is_guest_mode(vcpu)) + svm_leave_nested(svm); + else + svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; + svm->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - if (svm->current_vmcb == &svm->vmcb01) - svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; svm->vmcb01.ptr->save.es = save->es; svm->vmcb01.ptr->save.cs = save->cs; From 7f6231a39117c2781beead59d6ae4923c2703147 Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Mon, 3 May 2021 16:24:46 +1200 Subject: [PATCH 12/72] KVM: x86/mmu: Fix kdoc of __handle_changed_spte The function name of kdoc of __handle_changed_spte() should be itself, rather than handle_changed_spte(). Fix the typo. Signed-off-by: Kai Huang Message-Id: <20210503042446.154695-1-kai.huang@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c743894fe0b7..95eeb5ac6a8a 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -388,7 +388,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, } /** - * handle_changed_spte - handle bookkeeping associated with an SPTE change + * __handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of * @gfn: the base GFN that was mapped by the SPTE From 8899a5fc7da516460f841189a28aac0b52b554fd Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 30 Apr 2021 18:03:03 +0100 Subject: [PATCH 13/72] KVM: x86: Fix potential fput on a null source_kvm_file The fget can potentially return null, so the fput on the error return path can cause a null pointer dereference. Fix this by checking for a null source_kvm_file before doing a fput. Addresses-Coverity: ("Dereference null return") Fixes: 54526d1fd593 ("KVM: x86: Support KVM VMs sharing SEV context") Signed-off-by: Colin Ian King Message-Id: <20210430170303.131924-1-colin.king@canonical.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1356ee095cd5..8b11c711a0e4 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1764,7 +1764,8 @@ e_mirror_unlock: e_source_unlock: mutex_unlock(&source_kvm->lock); e_source_put: - fput(source_kvm_file); + if (source_kvm_file) + fput(source_kvm_file); return ret; } From 5e753a817b2d5991dfe8a801b7b1e8e79a1c5a20 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Fri, 30 Apr 2021 19:59:51 +0800 Subject: [PATCH 14/72] btrfs: fix unmountable seed device after fstrim The following test case reproduces an issue of wrongly freeing in-use blocks on the readonly seed device when fstrim is called on the rw sprout device. As shown below. Create a seed device and add a sprout device to it: $ mkfs.btrfs -fq -dsingle -msingle /dev/loop0 $ btrfstune -S 1 /dev/loop0 $ mount /dev/loop0 /btrfs $ btrfs dev add -f /dev/loop1 /btrfs BTRFS info (device loop0): relocating block group 290455552 flags system BTRFS info (device loop0): relocating block group 1048576 flags system BTRFS info (device loop0): disk added /dev/loop1 $ umount /btrfs Mount the sprout device and run fstrim: $ mount /dev/loop1 /btrfs $ fstrim /btrfs $ umount /btrfs Now try to mount the seed device, and it fails: $ mount /dev/loop0 /btrfs mount: /btrfs: wrong fs type, bad option, bad superblock on /dev/loop0, missing codepage or helper program, or other error. Block 5292032 is missing on the readonly seed device: $ dmesg -kt | tail BTRFS error (device loop0): bad tree block start, want 5292032 have 0 BTRFS warning (device loop0): couldn't read-tree root BTRFS error (device loop0): open_ctree failed From the dump-tree of the seed device (taken before the fstrim). Block 5292032 belonged to the block group starting at 5242880: $ btrfs inspect dump-tree -e /dev/loop0 | grep -A1 BLOCK_GROUP item 3 key (5242880 BLOCK_GROUP_ITEM 8388608) itemoff 16169 itemsize 24 block group used 114688 chunk_objectid 256 flags METADATA From the dump-tree of the sprout device (taken before the fstrim). fstrim used block-group 5242880 to find the related free space to free: $ btrfs inspect dump-tree -e /dev/loop1 | grep -A1 BLOCK_GROUP item 1 key (5242880 BLOCK_GROUP_ITEM 8388608) itemoff 16226 itemsize 24 block group used 32768 chunk_objectid 256 flags METADATA BPF kernel tracing the fstrim command finds the missing block 5292032 within the range of the discarded blocks as below: kprobe:btrfs_discard_extent { printf("freeing start %llu end %llu num_bytes %llu:\n", arg1, arg1+arg2, arg2); } freeing start 5259264 end 5406720 num_bytes 147456 Fix this by avoiding the discard command to the readonly seed device. Reported-by: Chris Murphy CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7a28314189b4..f1d15b68994a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1340,12 +1340,16 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; + struct btrfs_device *device = stripe->dev; - if (!stripe->dev->bdev) { + if (!device->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } + if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) + continue; + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; From 784daf2b9628f2d0117f1f0b578cfe5ab6634919 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 30 Apr 2021 15:34:17 +0200 Subject: [PATCH 15/72] btrfs: zoned: sanity check zone type The fstests test case generic/475 creates a dm-linear device that gets changed to a dm-error device. This leads to errors in loading the block group's zone information when running on a zoned file system, ultimately resulting in a list corruption. When running on a kernel with list debugging enabled this leads to the following crash. BTRFS: error (device dm-2) in cleanup_transaction:1953: errno=-5 IO failure kernel BUG at lib/list_debug.c:54! invalid opcode: 0000 [#1] SMP PTI CPU: 1 PID: 2433 Comm: umount Tainted: G W 5.12.0+ #1018 RIP: 0010:__list_del_entry_valid.cold+0x1d/0x47 RSP: 0018:ffffc90001473df0 EFLAGS: 00010296 RAX: 0000000000000054 RBX: ffff8881038fd000 RCX: ffffc90001473c90 RDX: 0000000100001a31 RSI: 0000000000000003 RDI: 0000000000000003 RBP: ffff888308871108 R08: 0000000000000003 R09: 0000000000000001 R10: 3961373532383838 R11: 6666666620736177 R12: ffff888308871000 R13: ffff8881038fd088 R14: ffff8881038fdc78 R15: dead000000000100 FS: 00007f353c9b1540(0000) GS:ffff888627d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f353cc2c710 CR3: 000000018e13c000 CR4: 00000000000006a0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_free_block_groups+0xc9/0x310 [btrfs] close_ctree+0x2ee/0x31a [btrfs] ? call_rcu+0x8f/0x270 ? mutex_lock+0x1c/0x40 generic_shutdown_super+0x67/0x100 kill_anon_super+0x14/0x30 btrfs_kill_super+0x12/0x20 [btrfs] deactivate_locked_super+0x31/0x90 cleanup_mnt+0x13e/0x1b0 task_work_run+0x63/0xb0 exit_to_user_mode_loop+0xd9/0xe0 exit_to_user_mode_prepare+0x3e/0x60 syscall_exit_to_user_mode+0x1d/0x50 entry_SYSCALL_64_after_hwframe+0x44/0xae As dm-error has no support for zones, btrfs will run it's zone emulation mode on this device. The zone emulation mode emulates conventional zones, so bail out if the zone bitmap that gets populated on mount sees the zone as sequential while we're thinking it's a conventional zone when creating a block group. Note: this scenario is unlikely in a real wold application and can only happen by this (ab)use of device-mapper targets. CC: stable@vger.kernel.org # 5.12+ Signed-off-by: Naohiro Aota Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 70b23a0d03b1..304ce64c70a4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1126,6 +1126,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } + if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) { + ret = -EIO; + goto out; + } + switch (zone.cond) { case BLK_ZONE_COND_OFFLINE: case BLK_ZONE_COND_READONLY: From 77364faf21b4105ee5adbb4844fdfb461334d249 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 30 Apr 2021 11:06:55 -0700 Subject: [PATCH 16/72] btrfs: initialize return variable in cleanup_free_space_cache_v1 Static analysis reports this problem free-space-cache.c:3965:2: warning: Undefined or garbage value returned return ret; ^~~~~~~~~~ ret is set in the node handling loop. Treat doing nothing as a success and initialize ret to 0, although it's unlikely the loop would be skipped. We always have block groups, but as it could lead to transaction abort in the caller it's better to be safe. CC: stable@vger.kernel.org # 5.12+ Signed-off-by: Tom Rix Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/free-space-cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index e54466fc101f..4806295116d8 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -3949,7 +3949,7 @@ static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, { struct btrfs_block_group *block_group; struct rb_node *node; - int ret; + int ret = 0; btrfs_info(fs_info, "cleaning free space cache v1"); From 0a269a008f837e76ce285679ab3005059fadc2a6 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 14 Apr 2021 14:35:40 +0200 Subject: [PATCH 17/72] x86/kvm: Fix pr_info() for async PF setup/teardown 'pr_fmt' already has 'kvm-guest: ' so 'KVM' prefix is redundant. "Unregister pv shared memory" is very ambiguous, it's hard to say which particular PV feature it relates to. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210414123544.1060604-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d307c22e5c18..dc440bb69222 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -345,7 +345,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - pr_info("KVM setup async PF for cpu %d\n", smp_processor_id()); + pr_info("setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { @@ -371,7 +371,7 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id()); + pr_info("disable async PF for cpu %d\n", smp_processor_id()); } static void kvm_pv_guest_cpu_reboot(void *unused) From 8b79feffeca28c5459458fe78676b081e87c93a4 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 14 Apr 2021 14:35:41 +0200 Subject: [PATCH 18/72] x86/kvm: Teardown PV features on boot CPU as well Various PV features (Async PF, PV EOI, steal time) work through memory shared with hypervisor and when we restore from hibernation we must properly teardown all these features to make sure hypervisor doesn't write to stale locations after we jump to the previously hibernated kernel (which can try to place anything there). For secondary CPUs the job is already done by kvm_cpu_down_prepare(), register syscore ops to do the same for boot CPU. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210414123544.1060604-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 62 ++++++++++++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 19 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index dc440bb69222..9d5f96321c7f 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -451,6 +452,25 @@ static void __init sev_map_percpu_data(void) } } +static void kvm_guest_cpu_offline(void) +{ + kvm_disable_steal_time(); + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); + apf_task_wake_all(); +} + +static int kvm_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + kvm_guest_cpu_init(); + local_irq_restore(flags); + return 0; +} + #ifdef CONFIG_SMP static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); @@ -635,33 +655,35 @@ static void __init kvm_smp_prepare_boot_cpu(void) kvm_spinlock_init(); } -static void kvm_guest_cpu_offline(void) -{ - kvm_disable_steal_time(); - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - apf_task_wake_all(); -} - -static int kvm_cpu_online(unsigned int cpu) -{ - local_irq_disable(); - kvm_guest_cpu_init(); - local_irq_enable(); - return 0; -} - static int kvm_cpu_down_prepare(unsigned int cpu) { - local_irq_disable(); + unsigned long flags; + + local_irq_save(flags); kvm_guest_cpu_offline(); - local_irq_enable(); + local_irq_restore(flags); return 0; } #endif +static int kvm_suspend(void) +{ + kvm_guest_cpu_offline(); + + return 0; +} + +static void kvm_resume(void) +{ + kvm_cpu_online(raw_smp_processor_id()); +} + +static struct syscore_ops kvm_syscore_ops = { + .suspend = kvm_suspend, + .resume = kvm_resume, +}; + static void __init kvm_guest_init(void) { int i; @@ -704,6 +726,8 @@ static void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif + register_syscore_ops(&kvm_syscore_ops); + /* * Hard lockup detection is enabled by default. Disable it, as guests * can get false positives too easily, for example if the host is From c02027b5742b5aa804ef08a4a9db433295533046 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 14 Apr 2021 14:35:42 +0200 Subject: [PATCH 19/72] x86/kvm: Disable kvmclock on all CPUs on shutdown Currenly, we disable kvmclock from machine_shutdown() hook and this only happens for boot CPU. We need to disable it for all CPUs to guard against memory corruption e.g. on restore from hibernate. Note, writing '0' to kvmclock MSR doesn't clear memory location, it just prevents hypervisor from updating the location so for the short while after write and while CPU is still alive, the clock remains usable and correct so we don't need to switch to some other clocksource. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210414123544.1060604-4-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_para.h | 4 ++-- arch/x86/kernel/kvm.c | 1 + arch/x86/kernel/kvmclock.c | 5 +---- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 338119852512..9c56e0defd45 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,8 +7,6 @@ #include #include -extern void kvmclock_init(void); - #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -86,6 +84,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, } #ifdef CONFIG_KVM_GUEST +void kvmclock_init(void); +void kvmclock_disable(void); bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); unsigned int kvm_arch_para_hints(void); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9d5f96321c7f..25dd126a3325 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -459,6 +459,7 @@ static void kvm_guest_cpu_offline(void) wrmsrl(MSR_KVM_PV_EOI_EN, 0); kvm_pv_disable_apf(); apf_task_wake_all(); + kvmclock_disable(); } static int kvm_cpu_online(unsigned int cpu) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d37ed4e1d033..081686df6cd8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -220,11 +220,9 @@ static void kvm_crash_shutdown(struct pt_regs *regs) } #endif -static void kvm_shutdown(void) +void kvmclock_disable(void) { native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_shutdown(); } static void __init kvmclock_init_mem(void) @@ -351,7 +349,6 @@ void __init kvmclock_init(void) #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; - machine_ops.shutdown = kvm_shutdown; #ifdef CONFIG_KEXEC_CORE machine_ops.crash_shutdown = kvm_crash_shutdown; #endif From 3d6b84132d2a57b5a74100f6923a8feb679ac2ce Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 14 Apr 2021 14:35:43 +0200 Subject: [PATCH 20/72] x86/kvm: Disable all PV features on crash Crash shutdown handler only disables kvmclock and steal time, other PV features remain active so we risk corrupting memory or getting some side-effects in kdump kernel. Move crash handler to kvm.c and unify with CPU offline. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210414123544.1060604-5-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_para.h | 6 ----- arch/x86/kernel/kvm.c | 44 ++++++++++++++++++++++++--------- arch/x86/kernel/kvmclock.c | 21 ---------------- 3 files changed, 32 insertions(+), 39 deletions(-) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 9c56e0defd45..69299878b200 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -92,7 +92,6 @@ unsigned int kvm_arch_para_hints(void); void kvm_async_pf_task_wait_schedule(u32 token); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_apf_flags(void); -void kvm_disable_steal_time(void); bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token); DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -137,11 +136,6 @@ static inline u32 kvm_read_and_reset_apf_flags(void) return 0; } -static inline void kvm_disable_steal_time(void) -{ - return; -} - static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) { return false; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 25dd126a3325..8eb91dc0f5a8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -38,6 +38,7 @@ #include #include #include +#include #include DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -375,6 +376,14 @@ static void kvm_pv_disable_apf(void) pr_info("disable async PF for cpu %d\n", smp_processor_id()); } +static void kvm_disable_steal_time(void) +{ + if (!has_steal_clock) + return; + + wrmsr(MSR_KVM_STEAL_TIME, 0, 0); +} + static void kvm_pv_guest_cpu_reboot(void *unused) { /* @@ -417,14 +426,6 @@ static u64 kvm_steal_clock(int cpu) return steal; } -void kvm_disable_steal_time(void) -{ - if (!has_steal_clock) - return; - - wrmsr(MSR_KVM_STEAL_TIME, 0, 0); -} - static inline void __set_percpu_decrypted(void *ptr, unsigned long size) { early_set_memory_decrypted((unsigned long) ptr, size); @@ -452,13 +453,14 @@ static void __init sev_map_percpu_data(void) } } -static void kvm_guest_cpu_offline(void) +static void kvm_guest_cpu_offline(bool shutdown) { kvm_disable_steal_time(); if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) wrmsrl(MSR_KVM_PV_EOI_EN, 0); kvm_pv_disable_apf(); - apf_task_wake_all(); + if (!shutdown) + apf_task_wake_all(); kvmclock_disable(); } @@ -661,7 +663,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu) unsigned long flags; local_irq_save(flags); - kvm_guest_cpu_offline(); + kvm_guest_cpu_offline(false); local_irq_restore(flags); return 0; } @@ -670,7 +672,7 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static int kvm_suspend(void) { - kvm_guest_cpu_offline(); + kvm_guest_cpu_offline(false); return 0; } @@ -685,6 +687,20 @@ static struct syscore_ops kvm_syscore_ops = { .resume = kvm_resume, }; +/* + * After a PV feature is registered, the host will keep writing to the + * registered memory location. If the guest happens to shutdown, this memory + * won't be valid. In cases like kexec, in which you install a new kernel, this + * means a random memory location will be kept being written. + */ +#ifdef CONFIG_KEXEC_CORE +static void kvm_crash_shutdown(struct pt_regs *regs) +{ + kvm_guest_cpu_offline(true); + native_machine_crash_shutdown(regs); +} +#endif + static void __init kvm_guest_init(void) { int i; @@ -727,6 +743,10 @@ static void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif +#ifdef CONFIG_KEXEC_CORE + machine_ops.crash_shutdown = kvm_crash_shutdown; +#endif + register_syscore_ops(&kvm_syscore_ops); /* diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 081686df6cd8..ad273e5861c1 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -20,7 +20,6 @@ #include #include #include -#include #include static int kvmclock __initdata = 1; @@ -203,23 +202,6 @@ static void kvm_setup_secondary_clock(void) } #endif -/* - * After the clock is registered, the host will keep writing to the - * registered memory location. If the guest happens to shutdown, this memory - * won't be valid. In cases like kexec, in which you install a new kernel, this - * means a random memory location will be kept being written. So before any - * kind of shutdown from our side, we unregister the clock by writing anything - * that does not have the 'enable' bit set in the msr - */ -#ifdef CONFIG_KEXEC_CORE -static void kvm_crash_shutdown(struct pt_regs *regs) -{ - native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_crash_shutdown(regs); -} -#endif - void kvmclock_disable(void) { native_write_msr(msr_kvm_system_time, 0, 0); @@ -349,9 +331,6 @@ void __init kvmclock_init(void) #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; -#ifdef CONFIG_KEXEC_CORE - machine_ops.crash_shutdown = kvm_crash_shutdown; -#endif kvm_get_preset_lpj(); /* From 384fc672f528d3b84eacd9a86ecf35df3363b8ba Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 14 Apr 2021 14:35:44 +0200 Subject: [PATCH 21/72] x86/kvm: Unify kvm_pv_guest_cpu_reboot() with kvm_guest_cpu_offline() Simplify the code by making PV features shutdown happen in one place. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210414123544.1060604-6-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 42 +++++++++++++++++------------------------- 1 file changed, 17 insertions(+), 25 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8eb91dc0f5a8..a26643dc6bd6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -384,31 +384,6 @@ static void kvm_disable_steal_time(void) wrmsr(MSR_KVM_STEAL_TIME, 0, 0); } -static void kvm_pv_guest_cpu_reboot(void *unused) -{ - /* - * We disable PV EOI before we load a new kernel by kexec, - * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory. - * New kernel can re-enable when it boots. - */ - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - kvm_disable_steal_time(); -} - -static int kvm_pv_reboot_notify(struct notifier_block *nb, - unsigned long code, void *unused) -{ - if (code == SYS_RESTART) - on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); - return NOTIFY_DONE; -} - -static struct notifier_block kvm_pv_reboot_nb = { - .notifier_call = kvm_pv_reboot_notify, -}; - static u64 kvm_steal_clock(int cpu) { u64 steal; @@ -687,6 +662,23 @@ static struct syscore_ops kvm_syscore_ops = { .resume = kvm_resume, }; +static void kvm_pv_guest_cpu_reboot(void *unused) +{ + kvm_guest_cpu_offline(true); +} + +static int kvm_pv_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + if (code == SYS_RESTART) + on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); + return NOTIFY_DONE; +} + +static struct notifier_block kvm_pv_reboot_nb = { + .notifier_call = kvm_pv_reboot_notify, +}; + /* * After a PV feature is registered, the host will keep writing to the * registered memory location. If the guest happens to shutdown, this memory From 46a63924b05f335b0765ad13dae4d2d7569f25c9 Mon Sep 17 00:00:00 2001 From: Siddharth Chandrasekaran Date: Mon, 3 May 2021 14:00:58 +0200 Subject: [PATCH 22/72] doc/kvm: Fix wrong entry for KVM_CAP_X86_MSR_FILTER The capability that exposes new ioctl KVM_X86_SET_MSR_FILTER to userspace is specified incorrectly as the ioctl itself (instead of KVM_CAP_X86_MSR_FILTER). This patch fixes it. Fixes: 1a155254ff93 ("KVM: x86: Introduce MSR filtering") Reviewed-by: Alexander Graf Signed-off-by: Siddharth Chandrasekaran Message-Id: <20210503120059.9283-1-sidcha@amazon.de> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 22d077562149..7fcb2fd38f42 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4803,7 +4803,7 @@ KVM_PV_VM_VERIFY 4.126 KVM_X86_SET_MSR_FILTER ---------------------------- -:Capability: KVM_X86_SET_MSR_FILTER +:Capability: KVM_CAP_X86_MSR_FILTER :Architectures: x86 :Type: vm ioctl :Parameters: struct kvm_msr_filter @@ -6715,7 +6715,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.27 KVM_X86_SET_MSR_FILTER +8.27 KVM_CAP_X86_MSR_FILTER --------------------------- :Architectures: x86 From f5c7e8425f18fdb9bdb7d13340651d7876890329 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 3 May 2021 17:08:51 +0200 Subject: [PATCH 23/72] KVM: nVMX: Always make an attempt to map eVMCS after migration When enlightened VMCS is in use and nested state is migrated with vmx_get_nested_state()/vmx_set_nested_state() KVM can't map evmcs page right away: evmcs gpa is not 'struct kvm_vmx_nested_state_hdr' and we can't read it from VP assist page because userspace may decide to restore HV_X64_MSR_VP_ASSIST_PAGE after restoring nested state (and QEMU, for example, does exactly that). To make sure eVMCS is mapped /vmx_set_nested_state() raises KVM_REQ_GET_NESTED_STATE_PAGES request. Commit f2c7ef3ba955 ("KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit") added KVM_REQ_GET_NESTED_STATE_PAGES clearing to nested_vmx_vmexit() to make sure MSR permission bitmap is not switched when an immediate exit from L2 to L1 happens right after migration (caused by a pending event, for example). Unfortunately, in the exact same situation we still need to have eVMCS mapped so nested_sync_vmcs12_to_shadow() reflects changes in VMCS12 to eVMCS. As a band-aid, restore nested_get_evmcs_page() when clearing KVM_REQ_GET_NESTED_STATE_PAGES in nested_vmx_vmexit(). The 'fix' is far from being ideal as we can't easily propagate possible failures and even if we could, this is most likely already too late to do so. The whole 'KVM_REQ_GET_NESTED_STATE_PAGES' idea for mapping eVMCS after migration seems to be fragile as we diverge too much from the 'native' path when vmptr loading happens on vmx_set_nested_state(). Fixes: f2c7ef3ba955 ("KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit") Signed-off-by: Vitaly Kuznetsov Message-Id: <20210503150854.1144255-2-vkuznets@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bced76637823..6058a65a6ede 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3098,15 +3098,8 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || - evmptrld_status == EVMPTRLD_ERROR) { - pr_debug_ratelimited("%s: enlightened vmptrld failed\n", - __func__); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + evmptrld_status == EVMPTRLD_ERROR) return false; - } } return true; @@ -3194,8 +3187,16 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { - if (!nested_get_evmcs_page(vcpu)) + if (!nested_get_evmcs_page(vcpu)) { + pr_debug_ratelimited("%s: enlightened vmptrld failed\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -4435,7 +4436,15 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* Similarly, triple faults in L2 should never escape. */ WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { + /* + * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map + * Enlightened VMCS after migration and we still need to + * do that when something is forcing L2->L1 exit prior to + * the first L2 run. + */ + (void)nested_get_evmcs_page(vcpu); + } /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) From 32d1b3ab588c1231dbfa9eb08819c50529ce77d7 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 5 May 2021 17:18:21 +0200 Subject: [PATCH 24/72] KVM: selftests: evmcs_test: Check that VMLAUNCH with bogus EVMPTR is causing #UD 'run->exit_reason == KVM_EXIT_SHUTDOWN' check is not ideal as we may be getting some unexpected exception. Directly check for #UD instead. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210505151823.1341678-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- .../testing/selftests/kvm/x86_64/evmcs_test.c | 24 ++++++++++++------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index ca22ee6d19cb..b01f64ac6ce3 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -19,6 +19,14 @@ #define VCPU_ID 5 +static int ud_count; + +static void guest_ud_handler(struct ex_regs *regs) +{ + ud_count++; + regs->rip += 3; /* VMLAUNCH */ +} + void l2_guest_code(void) { GUEST_SYNC(7); @@ -71,11 +79,11 @@ void guest_code(struct vmx_pages *vmx_pages) if (vmx_pages) l1_guest_code(vmx_pages); - GUEST_DONE(); - /* Try enlightened vmptrld with an incorrect GPA */ evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(ud_count == 1); + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -109,6 +117,10 @@ int main(int argc, char *argv[]) vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + for (stage = 1;; stage++) { _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -124,7 +136,7 @@ int main(int argc, char *argv[]) case UCALL_SYNC: break; case UCALL_DONE: - goto part1_done; + goto done; default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } @@ -156,10 +168,6 @@ int main(int argc, char *argv[]) (ulong) regs2.rdi, (ulong) regs2.rsi); } -part1_done: - _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Unexpected successful VMEnter with invalid eVMCS pointer!"); - +done: kvm_vm_free(vm); } From c9ecafaf0113a305f5085ceb9c7a4b64ca70eae9 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 5 May 2021 17:18:22 +0200 Subject: [PATCH 25/72] KVM: selftests: evmcs_test: Check that VMCS12 is alway properly synced to eVMCS after restore Add a test for the regression, introduced by commit f2c7ef3ba955 ("KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit"). When L2->L1 exit is forced immediately after restoring nested state, KVM_REQ_GET_NESTED_STATE_PAGES request is cleared and VMCS12 changes (e.g. fresh RIP) are not reflected to eVMCS. The consequent nested vCPU run gets broken. Utilize NMI injection to do the job. Signed-off-by: Vitaly Kuznetsov Message-Id: <20210505151823.1341678-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- .../testing/selftests/kvm/x86_64/evmcs_test.c | 66 +++++++++++++++---- 1 file changed, 55 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index b01f64ac6ce3..63096cea26c6 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -18,30 +18,52 @@ #include "vmx.h" #define VCPU_ID 5 +#define NMI_VECTOR 2 static int ud_count; +void enable_x2apic(void) +{ + uint32_t spiv_reg = APIC_BASE_MSR + (APIC_SPIV >> 4); + + wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) | + MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD); + wrmsr(spiv_reg, rdmsr(spiv_reg) | APIC_SPIV_APIC_ENABLED); +} + static void guest_ud_handler(struct ex_regs *regs) { ud_count++; regs->rip += 3; /* VMLAUNCH */ } +static void guest_nmi_handler(struct ex_regs *regs) +{ +} + void l2_guest_code(void) { GUEST_SYNC(7); GUEST_SYNC(8); + /* Forced exit to L1 upon restore */ + GUEST_SYNC(9); + /* Done, exit to L1 and never come back. */ vmcall(); } -void l1_guest_code(struct vmx_pages *vmx_pages) +void guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + enable_x2apic(); + + GUEST_SYNC(1); + GUEST_SYNC(2); + enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist); GUEST_ASSERT(vmx_pages->vmcs_gpa); @@ -63,21 +85,22 @@ void l1_guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); + current_evmcs->pin_based_vm_exec_control |= + PIN_BASED_NMI_EXITING; GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); - GUEST_SYNC(9); + + /* + * NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is + * up-to-date (RIP points where it should and not at the beginning + * of l2_guest_code(). GUEST_SYNC(9) checkes that. + */ GUEST_ASSERT(!vmresume()); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(10); -} -void guest_code(struct vmx_pages *vmx_pages) -{ - GUEST_SYNC(1); - GUEST_SYNC(2); - - if (vmx_pages) - l1_guest_code(vmx_pages); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(11); /* Try enlightened vmptrld with an incorrect GPA */ evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); @@ -86,6 +109,18 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_DONE(); } +void inject_nmi(struct kvm_vm *vm) +{ + struct kvm_vcpu_events events; + + vcpu_events_get(vm, VCPU_ID, &events); + + events.nmi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING; + + vcpu_events_set(vm, VCPU_ID, &events); +} + int main(int argc, char *argv[]) { vm_vaddr_t vmx_pages_gva = 0; @@ -120,6 +155,9 @@ int main(int argc, char *argv[]) vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vm, VCPU_ID); vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + vm_handle_exception(vm, NMI_VECTOR, guest_nmi_handler); + + pr_info("Running L1 which uses EVMCS to run L2\n"); for (stage = 1;; stage++) { _vcpu_run(vm, VCPU_ID); @@ -166,6 +204,12 @@ int main(int argc, char *argv[]) TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); + + /* Force immediate L2->L1 exit before resuming */ + if (stage == 8) { + pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); + inject_nmi(vm); + } } done: From 70f094f4f01dc4d6f78ac6407f85627293a6553c Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 3 May 2021 17:08:52 +0200 Subject: [PATCH 26/72] KVM: nVMX: Properly pad 'struct kvm_vmx_nested_state_hdr' Eliminate the probably unwanted hole in 'struct kvm_vmx_nested_state_hdr': Pre-patch: struct kvm_vmx_nested_state_hdr { __u64 vmxon_pa; /* 0 8 */ __u64 vmcs12_pa; /* 8 8 */ struct { __u16 flags; /* 16 2 */ } smm; /* 16 2 */ /* XXX 2 bytes hole, try to pack */ __u32 flags; /* 20 4 */ __u64 preemption_timer_deadline; /* 24 8 */ }; Post-patch: struct kvm_vmx_nested_state_hdr { __u64 vmxon_pa; /* 0 8 */ __u64 vmcs12_pa; /* 8 8 */ struct { __u16 flags; /* 16 2 */ } smm; /* 16 2 */ __u16 pad; /* 18 2 */ __u32 flags; /* 20 4 */ __u64 preemption_timer_deadline; /* 24 8 */ }; Signed-off-by: Vitaly Kuznetsov Message-Id: <20210503150854.1144255-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..0662f644aad9 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; From 5f443e424efab56baa8021da04878f88eb0815d4 Mon Sep 17 00:00:00 2001 From: Bill Wendling Date: Thu, 10 Dec 2020 17:23:17 -0800 Subject: [PATCH 27/72] selftests: kvm: remove reassignment of non-absolute variables Clang's integrated assembler does not allow symbols with non-absolute values to be reassigned. Modify the interrupt entry loop macro to be compatible with IAS by using a label and an offset. Cc: Jian Cai Signed-off-by: Bill Wendling References: https://lore.kernel.org/lkml/20200714233024.1789985-1-caij2003@gmail.com/ Message-Id: <20201211012317.3722214-1-morbo@google.com> Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/lib/x86_64/handlers.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S index aaf7bc7d2ce1..7629819734af 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -54,9 +54,9 @@ idt_handlers: .align 8 /* Fetch current address and append it to idt_handlers. */ - current_handler = . +666 : .pushsection .rodata -.quad current_handler + .quad 666b .popsection .if ! \has_error From aca352886ebdd675b5131ed4c83bf5477eee5d72 Mon Sep 17 00:00:00 2001 From: Siddharth Chandrasekaran Date: Mon, 3 May 2021 14:21:11 +0200 Subject: [PATCH 28/72] KVM: x86: Hoist input checks in kvm_add_msr_filter() In ioctl KVM_X86_SET_MSR_FILTER, input from user space is validated after a memdup_user(). For invalid inputs we'd memdup and then call kfree unnecessarily. Hoist input validation to avoid kfree altogether. Signed-off-by: Siddharth Chandrasekaran Message-Id: <20210503122111.13775-1-sidcha@amazon.de> Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cebdaa1e3cf5..102f116d9bb4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5468,14 +5468,18 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; - int r; if (!user_range->nmsrs) return 0; + if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + return -EINVAL; + + if (!user_range->flags) + return -EINVAL; + bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; @@ -5484,31 +5488,15 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (IS_ERR(bitmap)) return PTR_ERR(bitmap); - range = (struct msr_bitmap_range) { + msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; - if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) { - r = -EINVAL; - goto err; - } - - if (!range.flags) { - r = -EINVAL; - goto err; - } - - /* Everything ok, add this range identifier. */ - msr_filter->ranges[msr_filter->count] = range; msr_filter->count++; - return 0; -err: - kfree(bitmap); - return r; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) From 063ab16c14db5a2ef52d54d0475b7fed19c982d7 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 4 May 2021 17:39:35 +0300 Subject: [PATCH 29/72] KVM: nSVM: always restore the L1's GIF on migration While usually the L1's GIF is set while L2 runs, and usually migration nested state is loaded after a vCPU reset which also sets L1's GIF to true, this is not guaranteed. Signed-off-by: Maxim Levitsky Message-Id: <20210504143936.1644378-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 32400cba608d..b331446f67f3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1314,6 +1314,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, else svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + svm->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); From 809c79137a192d7e881a517f803ebbf96305f066 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 4 May 2021 17:39:36 +0300 Subject: [PATCH 30/72] KVM: nSVM: remove a warning about vmcb01 VM exit reason While in most cases, when returning to use the VMCB01, the exit reason stored in it will be SVM_EXIT_VMRUN, on first VM exit after a nested migration this field can contain anything since the VM entry did happen before the migration. Remove this warning to avoid the false positive. Signed-off-by: Maxim Levitsky Message-Id: <20210504143936.1644378-3-mlevitsk@redhat.com> Fixes: 9a7de6ecc3ed ("KVM: nSVM: If VMRUN is single-stepped, queue the #DB intercept in nested_svm_vmexit()") Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b331446f67f3..5e8d8443154e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -764,7 +764,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); svm_switch_vmcb(svm, &svm->vmcb01); - WARN_ON_ONCE(svm->vmcb->control.exit_code != SVM_EXIT_VMRUN); /* * On vmexit the GIF is set to false and From 8aec21c04caa2000f91cf8822ae0811e4b0c3971 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:20 -0700 Subject: [PATCH 31/72] KVM: VMX: Do not advertise RDPID if ENABLE_RDTSCP control is unsupported Clear KVM's RDPID capability if the ENABLE_RDTSCP secondary exec control is unsupported. Despite being enumerated in a separate CPUID flag, RDPID is bundled under the same VMCS control as RDTSCP and will #UD in VMX non-root if ENABLE_RDTSCP is not enabled. Fixes: 41cd02c6f7f6 ("kvm: x86: Expose RDPID in KVM_GET_SUPPORTED_CPUID") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-2-seanjc@google.com> Reviewed-by: Jim Mattson Reviewed-by: Reiji Watanabe Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cbe0cdade38a..46573b862638 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7377,9 +7377,11 @@ static __init void vmx_set_cpu_caps(void) if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); - /* CPUID 0x80000001 */ - if (!cpu_has_vmx_rdtscp()) + /* CPUID 0x80000001 and 0x7 (RDPID) */ + if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); From 85d0011264da24be08ae907d7f29983a597ca9b1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:21 -0700 Subject: [PATCH 32/72] KVM: x86: Emulate RDPID only if RDTSCP is supported Do not advertise emulation support for RDPID if RDTSCP is unsupported. RDPID emulation subtly relies on MSR_TSC_AUX to exist in hardware, as both vmx_get_msr() and svm_get_msr() will return an error if the MSR is unsupported, i.e. ctxt->ops->get_msr() will fail and the emulator will inject a #UD. Note, RDPID emulation also relies on RDTSCP being enabled in the guest, but this is a KVM bug and will eventually be fixed. Fixes: fb6d4d340e05 ("KVM: x86: emulate RDPID") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-3-seanjc@google.com> Reviewed-by: Jim Mattson Reviewed-by: Reiji Watanabe Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 19606a341888..c0e8c5e92189 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -637,7 +637,8 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; - entry->ecx = F(RDPID); + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + entry->ecx = F(RDPID); ++array->nent; default: break; From 3b195ac9260235624b1c18f7bdaef184479c1d41 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:22 -0700 Subject: [PATCH 33/72] KVM: SVM: Inject #UD on RDTSCP when it should be disabled in the guest Intercept RDTSCP to inject #UD if RDTSC is disabled in the guest. Note, SVM does not support intercepting RDPID. Unlike VMX's ENABLE_RDTSCP control, RDTSCP interception does not apply to RDPID. This is a benign virtualization hole as the host kernel (incorrectly) sets MSR_TSC_AUX if RDTSCP is supported, and KVM loads the guest's MSR_TSC_AUX into hardware if RDTSCP is supported in the host, i.e. KVM will not leak the host's MSR_TSC_AUX to the guest. But, when the kernel bug is fixed, KVM will start leaking the host's MSR_TSC_AUX if RDPID is supported in hardware, but RDTSCP isn't available for whatever reason. This leak will be remedied in a future commit. Fixes: 46896c73c1a4 ("KVM: svm: add support for RDTSCP") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-4-seanjc@google.com> Reviewed-by: Jim Mattson Reviewed-by: Reiji Watanabe Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index be5cf612ab1f..ebcb5849d69b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1100,7 +1100,9 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) return svm->vmcb->control.tsc_offset; } -static void svm_check_invpcid(struct vcpu_svm *svm) +/* Evaluate instruction intercepts that depend on guest CPUID features. */ +static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, + struct vcpu_svm *svm) { /* * Intercept INVPCID if shadow paging is enabled to sync/free shadow @@ -1113,6 +1115,13 @@ static void svm_check_invpcid(struct vcpu_svm *svm) else svm_clr_intercept(svm, INTERCEPT_INVPCID); } + + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { + if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + svm_clr_intercept(svm, INTERCEPT_RDTSCP); + else + svm_set_intercept(svm, INTERCEPT_RDTSCP); + } } static void init_vmcb(struct kvm_vcpu *vcpu) @@ -1248,7 +1257,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_PAUSE); } - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* * If the host supports V_SPEC_CTRL then disable the interception @@ -3084,6 +3093,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, + [SVM_EXIT_RDTSCP] = kvm_handle_invalid_op, [SVM_EXIT_WBINVD] = kvm_emulate_wbinvd, [SVM_EXIT_MONITOR] = kvm_emulate_monitor, [SVM_EXIT_MWAIT] = kvm_emulate_mwait, @@ -4007,8 +4017,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); - /* Check again if INVPCID interception if required */ - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { From 2183de4161b90bd3851ccd3910c87b2c9adfc6ed Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:23 -0700 Subject: [PATCH 34/72] KVM: x86: Move RDPID emulation intercept to its own enum Add a dedicated intercept enum for RDPID instead of piggybacking RDTSCP. Unlike VMX's ENABLE_RDTSCP, RDPID is not bound to SVM's RDTSCP intercept. Fixes: fb6d4d340e05 ("KVM: x86: emulate RDPID") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-5-seanjc@google.com> Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 2 +- arch/x86/kvm/kvm_emulate.h | 1 + arch/x86/kvm/vmx/vmx.c | 3 ++- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 77e1c89a95a7..8a0ccdb56076 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4502,7 +4502,7 @@ static const struct opcode group8[] = { * from the register case of group9. */ static const struct gprefix pfx_0f_c7_7 = { - N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdpid), }; diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 0d359115429a..f016838faedd 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -468,6 +468,7 @@ enum x86_intercept { x86_intercept_clgi, x86_intercept_skinit, x86_intercept_rdtscp, + x86_intercept_rdpid, x86_intercept_icebp, x86_intercept_wbinvd, x86_intercept_monitor, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 46573b862638..4a625c748275 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7437,8 +7437,9 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. + * Note, RDPID is hidden behind ENABLE_RDTSCP. */ - case x86_intercept_rdtscp: + case x86_intercept_rdpid: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; From 5104d7ffcf24749939bea7fdb5378d186473f890 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:24 -0700 Subject: [PATCH 35/72] KVM: VMX: Disable preemption when probing user return MSRs Disable preemption when probing a user return MSR via RDSMR/WRMSR. If the MSR holds a different value per logical CPU, the WRMSR could corrupt the host's value if KVM is preempted between the RDMSR and WRMSR, and then rescheduled on a different CPU. Opportunistically land the helper in common x86, SVM will use the helper in a future commit. Fixes: 4be534102624 ("KVM: VMX: Initialize vmx->guest_msrs[] right after allocation") Cc: stable@vger.kernel.org Cc: Xiaoyao Li Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-6-seanjc@google.com> Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx/vmx.c | 5 +---- arch/x86/kvm/x86.c | 16 ++++++++++++++++ 3 files changed, 18 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 848956bb3cf1..e8dcbc632cf8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1777,6 +1777,7 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long icr, int op_64_bit); void kvm_define_user_return_msr(unsigned index, u32 msr); +int kvm_probe_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4a625c748275..11ff9c3d95d5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6914,12 +6914,9 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { u32 index = vmx_uret_msrs_list[i]; - u32 data_low, data_high; int j = vmx->nr_uret_msrs; - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) + if (kvm_probe_user_return_msr(index)) continue; vmx->guest_uret_msrs[j].slot = i; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 102f116d9bb4..bd90c73c37b4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -339,6 +339,22 @@ static void kvm_on_user_return(struct user_return_notifier *urn) } } +int kvm_probe_user_return_msr(u32 msr) +{ + u64 val; + int ret; + + preempt_disable(); + ret = rdmsrl_safe(msr, &val); + if (ret) + goto out; + ret = wrmsrl_safe(msr, val); +out: + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(kvm_probe_user_return_msr); + void kvm_define_user_return_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); From 0caa0a77c2f6fcd0830cdcd018db1af98fe35e28 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:25 -0700 Subject: [PATCH 36/72] KVM: SVM: Probe and load MSR_TSC_AUX regardless of RDTSCP support in host Probe MSR_TSC_AUX whether or not RDTSCP is supported in the host, and if probing succeeds, load the guest's MSR_TSC_AUX into hardware prior to VMRUN. Because SVM doesn't support interception of RDPID, RDPID cannot be disallowed in the guest (without resorting to binary translation). Leaving the host's MSR_TSC_AUX in hardware would leak the host's value to the guest if RDTSCP is not supported. Note, there is also a kernel bug that prevents leaking the host's value. The host kernel initializes MSR_TSC_AUX if and only if RDTSCP is supported, even though the vDSO usage consumes MSR_TSC_AUX via RDPID. I.e. if RDTSCP is not supported, there is no host value to leak. But, if/when the host kernel bug is fixed, KVM would start leaking MSR_TSC_AUX in the case where hardware supports RDPID but RDTSCP is unavailable for whatever reason. Probing MSR_TSC_AUX will also allow consolidating the probe and define logic in common x86, and will make it simpler to condition the existence of MSR_TSX_AUX (from the guest's perspective) on RDTSCP *or* RDPID. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-7-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ebcb5849d69b..13e4dd128177 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -212,7 +212,7 @@ DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to * defer the restoration of TSC_AUX until the CPU returns to userspace. */ -#define TSC_AUX_URET_SLOT 0 +static int tsc_aux_uret_slot __read_mostly = -1; static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; @@ -959,8 +959,10 @@ static __init int svm_hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 32; } - if (boot_cpu_has(X86_FEATURE_RDTSCP)) - kvm_define_user_return_msr(TSC_AUX_URET_SLOT, MSR_TSC_AUX); + if (!kvm_probe_user_return_msr(MSR_TSC_AUX)) { + tsc_aux_uret_slot = 0; + kvm_define_user_return_msr(tsc_aux_uret_slot, MSR_TSC_AUX); + } /* Check for pause filtering support */ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { @@ -1454,8 +1456,8 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) } } - if (static_cpu_has(X86_FEATURE_RDTSCP)) - kvm_set_user_return_msr(TSC_AUX_URET_SLOT, svm->tsc_aux, -1ull); + if (likely(tsc_aux_uret_slot >= 0)) + kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; } @@ -2664,7 +2666,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data |= (u64)svm->sysenter_esp_hi << 32; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + if (tsc_aux_uret_slot < 0) return 1; if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) @@ -2885,7 +2887,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + if (tsc_aux_uret_slot < 0) return 1; if (!msr->host_initiated && @@ -2908,7 +2910,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * guest via direct_access_msrs, and switch it via user return. */ preempt_disable(); - r = kvm_set_user_return_msr(TSC_AUX_URET_SLOT, data, -1ull); + r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); preempt_enable(); if (r) return 1; From 36fa06f9ff39f23e03cd8206dc6bbb7711c23be6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:26 -0700 Subject: [PATCH 37/72] KVM: x86: Add support for RDPID without RDTSCP Allow userspace to enable RDPID for a guest without also enabling RDTSCP. Aside from checking for RDPID support in the obvious flows, VMX also needs to set ENABLE_RDTSCP=1 when RDPID is exposed. For the record, there is no known scenario where enabling RDPID without RDTSCP is desirable. But, both AMD and Intel architectures allow for the condition, i.e. this is purely to make KVM more architecturally accurate. Fixes: 41cd02c6f7f6 ("kvm: x86: Expose RDPID in KVM_GET_SUPPORTED_CPUID") Cc: stable@vger.kernel.org Reported-by: Reiji Watanabe Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-8-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 6 ++++-- arch/x86/kvm/vmx/vmx.c | 27 +++++++++++++++++++++++---- arch/x86/kvm/x86.c | 3 ++- 3 files changed, 29 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 13e4dd128177..0ba0a00f8dc6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2669,7 +2669,8 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (tsc_aux_uret_slot < 0) return 1; if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; msr_info->data = svm->tsc_aux; break; @@ -2891,7 +2892,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) return 1; if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 11ff9c3d95d5..b304e372aab3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1788,7 +1788,8 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (update_transition_efer(vmx)) vmx_setup_uret_msr(vmx, MSR_EFER); - if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) + if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)) vmx_setup_uret_msr(vmx, MSR_TSC_AUX); vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL); @@ -1994,7 +1995,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_TSC_AUX: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; goto find_uret_msr; case MSR_IA32_DEBUGCTLMSR: @@ -2314,7 +2316,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_TSC_AUX: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -4368,7 +4371,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) xsaves_enabled, false); } - vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); + /* + * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either + * feature is exposed to the guest. This creates a virtualization hole + * if both are supported in hardware but only one is exposed to the + * guest, but letting the guest execute RDTSCP or RDPID when either one + * is advertised is preferable to emulating the advertised instruction + * in KVM on #UD, and obviously better than incorrectly injecting #UD. + */ + if (cpu_has_vmx_rdtscp()) { + bool rdpid_or_rdtscp_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + vmx_adjust_secondary_exec_control(vmx, &exec_control, + SECONDARY_EXEC_ENABLE_RDTSCP, + rdpid_or_rdtscp_enabled, false); + } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd90c73c37b4..0856636efc44 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5941,7 +5941,8 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) continue; break; case MSR_IA32_UMWAIT_CONTROL: From b6194b94a2ca4affce5aab1bbf773a977ad73671 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:27 -0700 Subject: [PATCH 38/72] KVM: VMX: Configure list of user return MSRs at module init Configure the list of user return MSRs that are actually supported at module init instead of reprobing the list of possible MSRs every time a vCPU is created. Curating the list on a per-vCPU basis is pointless; KVM is completely hosed if the set of supported MSRs changes after module init, or if the set of MSRs differs per physical PCU. The per-vCPU lists also increase complexity (see __vmx_find_uret_msr()) and creates corner cases that _should_ be impossible, but theoretically exist in KVM, e.g. advertising RDTSCP to userspace without actually being able to virtualize RDTSCP if probing MSR_TSC_AUX fails. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-9-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 61 ++++++++++++++++++++++++++++-------------- arch/x86/kvm/vmx/vmx.h | 10 ++++++- 2 files changed, 50 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b304e372aab3..887db1af1312 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -461,7 +461,7 @@ static unsigned long host_idt_base; * support this emulation, IA32_STAR must always be included in * vmx_uret_msrs_list[], even in i386 builds. */ -static const u32 vmx_uret_msrs_list[] = { +static u32 vmx_uret_msrs_list[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif @@ -469,6 +469,12 @@ static const u32 vmx_uret_msrs_list[] = { MSR_IA32_TSX_CTRL, }; +/* + * Number of user return MSRs that are actually supported in hardware. + * vmx_uret_msrs_list is modified when KVM is loaded to drop unsupported MSRs. + */ +static int vmx_nr_uret_msrs; + #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -700,9 +706,16 @@ static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - for (i = 0; i < vmx->nr_uret_msrs; ++i) + /* + * Note, vmx->guest_uret_msrs is the same size as vmx_uret_msrs_list, + * but is ordered differently. The MSR is matched against the list of + * supported uret MSRs using "slot", but the index that is returned is + * the index into guest_uret_msrs. + */ + for (i = 0; i < vmx_nr_uret_msrs; ++i) { if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr) return i; + } return -1; } @@ -6929,18 +6942,10 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); + for (i = 0; i < vmx_nr_uret_msrs; ++i) { + vmx->guest_uret_msrs[i].data = 0; - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { - u32 index = vmx_uret_msrs_list[i]; - int j = vmx->nr_uret_msrs; - - if (kvm_probe_user_return_msr(index)) - continue; - - vmx->guest_uret_msrs[j].slot = i; - vmx->guest_uret_msrs[j].data = 0; - switch (index) { + switch (vmx_uret_msrs_list[i]) { case MSR_IA32_TSX_CTRL: /* * TSX_CTRL_CPUID_CLEAR is handled in the CPUID @@ -6954,15 +6959,14 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) * host so that TSX remains always disabled. */ if (boot_cpu_has(X86_FEATURE_RTM)) - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; else - vmx->guest_uret_msrs[j].mask = 0; + vmx->guest_uret_msrs[i].mask = 0; break; default: - vmx->guest_uret_msrs[j].mask = -1ull; + vmx->guest_uret_msrs[i].mask = -1ull; break; } - ++vmx->nr_uret_msrs; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -7821,17 +7825,34 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; +static __init void vmx_setup_user_return_msrs(void) +{ + u32 msr; + int i; + + BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); + + for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { + msr = vmx_uret_msrs_list[i]; + + if (kvm_probe_user_return_msr(msr)) + continue; + + kvm_define_user_return_msr(vmx_nr_uret_msrs, msr); + vmx_uret_msrs_list[vmx_nr_uret_msrs++] = msr; + } +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i, ept_lpage_level; + int r, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) - kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]); + vmx_setup_user_return_msrs(); if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 008cb87ff088..d71ed8b425c5 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -245,8 +245,16 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; + /* + * User return MSRs are always emulated when enabled in the guest, but + * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside + * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to + * be loaded into hardware if those conditions aren't met. + * nr_active_uret_msrs tracks the number of MSRs that need to be loaded + * into hardware when running the guest. guest_uret_msrs[] is resorted + * whenever the number of "active" uret MSRs is modified. + */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_uret_msrs; int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 From ee9d22e08d1341692a43926e5e1d84c90a5dac1d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:28 -0700 Subject: [PATCH 39/72] KVM: VMX: Use flag to indicate "active" uret MSRs instead of sorting list Explicitly flag a uret MSR as needing to be loaded into hardware instead of resorting the list of "active" MSRs and tracking how many MSRs in total need to be loaded. The only benefit to sorting the list is that the loop to load MSRs during vmx_prepare_switch_to_guest() doesn't need to iterate over all supported uret MRS, only those that are active. But that is a pointless optimization, as the most common case, running a 64-bit guest, will load the vast majority of MSRs. Not to mention that a single WRMSR is far more expensive than iterating over the list. Providing a stable list order obviates the need to track a given MSR's "slot" in the per-CPU list of user return MSRs; all lists simply use the same ordering. Future patches will take advantage of the stable order to further simplify the related code. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-10-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 80 ++++++++++++++++++++++-------------------- arch/x86/kvm/vmx/vmx.h | 2 +- 2 files changed, 42 insertions(+), 40 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 887db1af1312..adefedac0e3b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -458,8 +458,9 @@ static unsigned long host_idt_base; * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm * will emulate SYSCALL in legacy mode if the vendor string in guest * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_uret_msrs_list[], even in i386 builds. + * support this emulation, MSR_STAR is included in the list for i386, + * but is never loaded into hardware. MSR_CSTAR is also never loaded + * into hardware and is here purely for emulation purposes. */ static u32 vmx_uret_msrs_list[] = { #ifdef CONFIG_X86_64 @@ -702,18 +703,12 @@ static bool is_valid_passthrough_msr(u32 msr) return r; } -static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) +static inline int __vmx_find_uret_msr(u32 msr) { int i; - /* - * Note, vmx->guest_uret_msrs is the same size as vmx_uret_msrs_list, - * but is ordered differently. The MSR is matched against the list of - * supported uret MSRs using "slot", but the index that is returned is - * the index into guest_uret_msrs. - */ for (i = 0; i < vmx_nr_uret_msrs; ++i) { - if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr) + if (vmx_uret_msrs_list[i] == msr) return i; } return -1; @@ -723,7 +718,7 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - i = __vmx_find_uret_msr(vmx, msr); + i = __vmx_find_uret_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; @@ -732,13 +727,14 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { + unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; u64 old_msr_data = msr->data; msr->data = data; - if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) { + if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); preempt_enable(); if (ret) msr->data = old_msr_data; @@ -1090,7 +1086,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) return false; } - i = __vmx_find_uret_msr(vmx, MSR_EFER); + i = __vmx_find_uret_msr(MSR_EFER); if (i < 0) return false; @@ -1252,11 +1248,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; - for (i = 0; i < vmx->nr_active_uret_msrs; ++i) - kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot, + for (i = 0; i < vmx_nr_uret_msrs; ++i) { + if (!vmx->guest_uret_msrs[i].load_into_hardware) + continue; + + kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); - + } } if (vmx->nested.need_vmcs12_to_shadow_sync) @@ -1763,19 +1762,16 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) +static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, + bool load_into_hardware) { - struct vmx_uret_msr tmp; - int from, to; + struct vmx_uret_msr *uret_msr; - from = __vmx_find_uret_msr(vmx, msr); - if (from < 0) + uret_msr = vmx_find_uret_msr(vmx, msr); + if (!uret_msr) return; - to = vmx->nr_active_uret_msrs++; - tmp = vmx->guest_uret_msrs[to]; - vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from]; - vmx->guest_uret_msrs[from] = tmp; + uret_msr->load_into_hardware = load_into_hardware; } /* @@ -1785,30 +1781,36 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) */ static void setup_msrs(struct vcpu_vmx *vmx) { - vmx->guest_uret_msrs_loaded = false; - vmx->nr_active_uret_msrs = 0; #ifdef CONFIG_X86_64 + bool load_syscall_msrs; + /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - vmx_setup_uret_msr(vmx, MSR_STAR); - vmx_setup_uret_msr(vmx, MSR_LSTAR); - vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK); - } + load_syscall_msrs = is_long_mode(&vmx->vcpu) && + (vmx->vcpu.arch.efer & EFER_SCE); + + vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif - if (update_transition_efer(vmx)) - vmx_setup_uret_msr(vmx, MSR_EFER); + vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); - if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)) - vmx_setup_uret_msr(vmx, MSR_TSC_AUX); + vmx_setup_uret_msr(vmx, MSR_TSC_AUX, + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); - vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL); + vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, true); if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); + + /* + * The set of MSRs to load may have changed, reload MSRs before the + * next VM-Enter. + */ + vmx->guest_uret_msrs_loaded = false; } static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index d71ed8b425c5..16e4e457ba23 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -36,7 +36,7 @@ struct vmx_msrs { }; struct vmx_uret_msr { - unsigned int slot; /* The MSR's slot in kvm_user_return_msrs. */ + bool load_into_hardware; u64 data; u64 mask; }; From 8ea8b8d6f869425e21f34e60bdbe7e47e6c9d6b9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:29 -0700 Subject: [PATCH 40/72] KVM: VMX: Use common x86's uret MSR list as the one true list Drop VMX's global list of user return MSRs now that VMX doesn't resort said list to isolate "active" MSRs, i.e. now that VMX's list and x86's list have the same MSRs in the same order. In addition to eliminating the redundant list, this will also allow moving more of the list management into common x86. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-11-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx/vmx.c | 97 ++++++++++++++------------------- arch/x86/kvm/x86.c | 12 ++++ 3 files changed, 53 insertions(+), 57 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e8dcbc632cf8..6b15f27f49d0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1777,6 +1777,7 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long icr, int op_64_bit); void kvm_define_user_return_msr(unsigned index, u32 msr); +int kvm_find_user_return_msr(u32 msr); int kvm_probe_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index adefedac0e3b..39506704be96 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -454,26 +454,7 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, MSR_STAR is included in the list for i386, - * but is never loaded into hardware. MSR_CSTAR is also never loaded - * into hardware and is here purely for emulation purposes. - */ -static u32 vmx_uret_msrs_list[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - -/* - * Number of user return MSRs that are actually supported in hardware. - * vmx_uret_msrs_list is modified when KVM is loaded to drop unsupported MSRs. - */ +/* Number of user return MSRs that are actually supported in hardware. */ static int vmx_nr_uret_msrs; #if IS_ENABLED(CONFIG_HYPERV) @@ -703,22 +684,11 @@ static bool is_valid_passthrough_msr(u32 msr) return r; } -static inline int __vmx_find_uret_msr(u32 msr) -{ - int i; - - for (i = 0; i < vmx_nr_uret_msrs; ++i) { - if (vmx_uret_msrs_list[i] == msr) - return i; - } - return -1; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - i = __vmx_find_uret_msr(msr); + i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; @@ -1086,7 +1056,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) return false; } - i = __vmx_find_uret_msr(MSR_EFER); + i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; @@ -6922,6 +6892,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { + struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, cpu, err; @@ -6946,29 +6917,25 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) for (i = 0; i < vmx_nr_uret_msrs; ++i) { vmx->guest_uret_msrs[i].data = 0; - - switch (vmx_uret_msrs_list[i]) { - case MSR_IA32_TSX_CTRL: - /* - * TSX_CTRL_CPUID_CLEAR is handled in the CPUID - * interception. Keep the host value unchanged to avoid - * changing CPUID bits under the host kernel's feet. - * - * hle=0, rtm=0, tsx_ctrl=1 can be found with some - * combinations of new kernel and old userspace. If - * those guests run on a tsx=off host, do allow guests - * to use TSX_CTRL, but do not change the value on the - * host so that TSX remains always disabled. - */ - if (boot_cpu_has(X86_FEATURE_RTM)) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - else - vmx->guest_uret_msrs[i].mask = 0; - break; - default: - vmx->guest_uret_msrs[i].mask = -1ull; - break; - } + vmx->guest_uret_msrs[i].mask = -1ull; + } + tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); + if (tsx_ctrl) { + /* + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. + * Keep the host value unchanged to avoid changing CPUID bits + * under the host kernel's feet. + * + * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations + * of new kernel and old userspace. If those guests run on a + * tsx=off host, do allow guests to use TSX_CTRL, but do not + * change the value on the host so that TSX remains always + * disabled. + */ + if (boot_cpu_has(X86_FEATURE_RTM)) + vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + else + vmx->guest_uret_msrs[i].mask = 0; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -7829,6 +7796,22 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { static __init void vmx_setup_user_return_msrs(void) { + + /* + * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm + * will emulate SYSCALL in legacy mode if the vendor string in guest + * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To + * support this emulation, MSR_STAR is included in the list for i386, + * but is never loaded into hardware. MSR_CSTAR is also never loaded + * into hardware and is here purely for emulation purposes. + */ + const u32 vmx_uret_msrs_list[] = { + #ifdef CONFIG_X86_64 + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, + #endif + MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, + }; u32 msr; int i; @@ -7841,7 +7824,7 @@ static __init void vmx_setup_user_return_msrs(void) continue; kvm_define_user_return_msr(vmx_nr_uret_msrs, msr); - vmx_uret_msrs_list[vmx_nr_uret_msrs++] = msr; + vmx_nr_uret_msrs++; } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0856636efc44..d514031ed25f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -364,6 +364,18 @@ void kvm_define_user_return_msr(unsigned slot, u32 msr) } EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); +int kvm_find_user_return_msr(u32 msr) +{ + int i; + + for (i = 0; i < user_return_msrs_global.nr; ++i) { + if (user_return_msrs_global.msrs[i] == msr) + return i; + } + return -1; +} +EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); + static void kvm_user_return_msr_cpu_online(void) { unsigned int cpu = smp_processor_id(); From 5e17c624010a82bbcca9b955155781927eb6532a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:30 -0700 Subject: [PATCH 41/72] KVM: VMX: Disable loading of TSX_CTRL MSR the more conventional way Tag TSX_CTRL as not needing to be loaded when RTM isn't supported in the host. Crushing the write mask to '0' has the same effect, but requires more mental gymnastics to understand. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-12-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 39506704be96..bd2187b4cc53 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1771,7 +1771,13 @@ static void setup_msrs(struct vcpu_vmx *vmx) guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); - vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, true); + /* + * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new + * kernel and old userspace. If those guests run on a tsx=off host, do + * allow guests to use TSX_CTRL, but don't change the value in hardware + * so that TSX remains always disabled. + */ + vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); @@ -6919,23 +6925,15 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->guest_uret_msrs[i].data = 0; vmx->guest_uret_msrs[i].mask = -1ull; } - tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); - if (tsx_ctrl) { + if (boot_cpu_has(X86_FEATURE_RTM)) { /* * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. * Keep the host value unchanged to avoid changing CPUID bits * under the host kernel's feet. - * - * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations - * of new kernel and old userspace. If those guests run on a - * tsx=off host, do allow guests to use TSX_CTRL, but do not - * change the value on the host so that TSX remains always - * disabled. */ - if (boot_cpu_has(X86_FEATURE_RTM)) + tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); + if (tsx_ctrl) vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - else - vmx->guest_uret_msrs[i].mask = 0; } err = alloc_loaded_vmcs(&vmx->vmcs01); From 9cc39a5a43c05f8eda206bf9e144119820ecf5c8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:31 -0700 Subject: [PATCH 42/72] KVM: x86: Export the number of uret MSRs to vendor modules Split out and export the number of configured user return MSRs so that VMX can iterate over the set of MSRs without having to do its own tracking. Keep the list itself internal to x86 so that vendor code still has to go through the "official" APIs to add/modify entries. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-13-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 29 +++++++++++++---------------- 2 files changed, 14 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6b15f27f49d0..22505e74c3da 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1418,6 +1418,7 @@ struct kvm_arch_async_pf { bool direct_map; }; +extern u32 __read_mostly kvm_nr_uret_msrs; extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; extern struct kvm_x86_ops kvm_x86_ops; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d514031ed25f..5e1deed8ea5d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -184,11 +184,6 @@ module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 -struct kvm_user_return_msrs_global { - int nr; - u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS]; -}; - struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; @@ -198,7 +193,9 @@ struct kvm_user_return_msrs { } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; -static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global; +u32 __read_mostly kvm_nr_uret_msrs; +EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); +static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ @@ -330,10 +327,10 @@ static void kvm_on_user_return(struct user_return_notifier *urn) user_return_notifier_unregister(urn); } local_irq_restore(flags); - for (slot = 0; slot < user_return_msrs_global.nr; ++slot) { + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { - wrmsrl(user_return_msrs_global.msrs[slot], values->host); + wrmsrl(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } @@ -358,9 +355,9 @@ EXPORT_SYMBOL_GPL(kvm_probe_user_return_msr); void kvm_define_user_return_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); - user_return_msrs_global.msrs[slot] = msr; - if (slot >= user_return_msrs_global.nr) - user_return_msrs_global.nr = slot + 1; + kvm_uret_msrs_list[slot] = msr; + if (slot >= kvm_nr_uret_msrs) + kvm_nr_uret_msrs = slot + 1; } EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); @@ -368,8 +365,8 @@ int kvm_find_user_return_msr(u32 msr) { int i; - for (i = 0; i < user_return_msrs_global.nr; ++i) { - if (user_return_msrs_global.msrs[i] == msr) + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (kvm_uret_msrs_list[i] == msr) return i; } return -1; @@ -383,8 +380,8 @@ static void kvm_user_return_msr_cpu_online(void) u64 value; int i; - for (i = 0; i < user_return_msrs_global.nr; ++i) { - rdmsrl_safe(user_return_msrs_global.msrs[i], &value); + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + rdmsrl_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } @@ -399,7 +396,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; - err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value); + err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; From e5fda4bbadb053e3b5164476146cf43092785c0b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:32 -0700 Subject: [PATCH 43/72] KVM: x86: Move uret MSR slot management to common x86 Now that SVM and VMX both probe MSRs before "defining" user return slots for them, consolidate the code for probe+define into common x86 and eliminate the odd behavior of having the vendor code define the slot for a given MSR. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-14-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 +-- arch/x86/kvm/svm/svm.c | 5 +---- arch/x86/kvm/vmx/vmx.c | 19 ++++--------------- arch/x86/kvm/x86.c | 19 +++++++++++-------- 4 files changed, 17 insertions(+), 29 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 22505e74c3da..8155eaac22a7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1777,9 +1777,8 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); -void kvm_define_user_return_msr(unsigned index, u32 msr); +int kvm_add_user_return_msr(u32 msr); int kvm_find_user_return_msr(u32 msr); -int kvm_probe_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0ba0a00f8dc6..d13b72bfb736 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -959,10 +959,7 @@ static __init int svm_hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 32; } - if (!kvm_probe_user_return_msr(MSR_TSC_AUX)) { - tsc_aux_uret_slot = 0; - kvm_define_user_return_msr(tsc_aux_uret_slot, MSR_TSC_AUX); - } + tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); /* Check for pause filtering support */ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index bd2187b4cc53..042823b49273 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -454,9 +454,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; -/* Number of user return MSRs that are actually supported in hardware. */ -static int vmx_nr_uret_msrs; - #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -1218,7 +1215,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; - for (i = 0; i < vmx_nr_uret_msrs; ++i) { + for (i = 0; i < kvm_nr_uret_msrs; ++i) { if (!vmx->guest_uret_msrs[i].load_into_hardware) continue; @@ -6921,7 +6918,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - for (i = 0; i < vmx_nr_uret_msrs; ++i) { + for (i = 0; i < kvm_nr_uret_msrs; ++i) { vmx->guest_uret_msrs[i].data = 0; vmx->guest_uret_msrs[i].mask = -1ull; } @@ -7810,20 +7807,12 @@ static __init void vmx_setup_user_return_msrs(void) MSR_EFER, MSR_TSC_AUX, MSR_STAR, MSR_IA32_TSX_CTRL, }; - u32 msr; int i; BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { - msr = vmx_uret_msrs_list[i]; - - if (kvm_probe_user_return_msr(msr)) - continue; - - kvm_define_user_return_msr(vmx_nr_uret_msrs, msr); - vmx_nr_uret_msrs++; - } + for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) + kvm_add_user_return_msr(vmx_uret_msrs_list[i]); } static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5e1deed8ea5d..0a0eebf35dd5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -336,7 +336,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn) } } -int kvm_probe_user_return_msr(u32 msr) +static int kvm_probe_user_return_msr(u32 msr) { u64 val; int ret; @@ -350,16 +350,18 @@ out: preempt_enable(); return ret; } -EXPORT_SYMBOL_GPL(kvm_probe_user_return_msr); -void kvm_define_user_return_msr(unsigned slot, u32 msr) +int kvm_add_user_return_msr(u32 msr) { - BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); - kvm_uret_msrs_list[slot] = msr; - if (slot >= kvm_nr_uret_msrs) - kvm_nr_uret_msrs = slot + 1; + BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); + + if (kvm_probe_user_return_msr(msr)) + return -1; + + kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; + return kvm_nr_uret_msrs++; } -EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); +EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); int kvm_find_user_return_msr(u32 msr) { @@ -8132,6 +8134,7 @@ int kvm_arch_init(void *opaque) printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); goto out_free_x86_emulator_cache; } + kvm_nr_uret_msrs = 0; r = kvm_mmu_module_init(); if (r) From 61a05d444d2ca8d40add453a5f7058fbb1b57eca Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:33 -0700 Subject: [PATCH 44/72] KVM: x86: Tie Intel and AMD behavior for MSR_TSC_AUX to guest CPU model Squish the Intel and AMD emulation of MSR_TSC_AUX together and tie it to the guest CPU model instead of the host CPU behavior. While not strictly necessary to avoid guest breakage, emulating cross-vendor "architecture" will provide consistent behavior for the guest, e.g. WRMSR fault behavior won't change if the vCPU is migrated to a host with divergent behavior. Note, the "new" kvm_is_supported_user_return_msr() checks do not add new functionality on either SVM or VMX. On SVM, the equivalent was "tsc_aux_uret_slot < 0", and on VMX the check was buried in the vmx_find_uret_msr() call at the find_uret_msr label. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-15-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 5 +++++ arch/x86/kvm/svm/svm.c | 24 ---------------------- arch/x86/kvm/vmx/vmx.c | 15 -------------- arch/x86/kvm/x86.c | 36 +++++++++++++++++++++++++++++++++ 4 files changed, 41 insertions(+), 39 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8155eaac22a7..f85480b1d215 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1781,6 +1781,11 @@ int kvm_add_user_return_msr(u32 msr); int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); +static inline bool kvm_is_supported_user_return_msr(u32 msr) +{ + return kvm_find_user_return_msr(msr) >= 0; +} + u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d13b72bfb736..0922d8e173e6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2663,12 +2663,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data |= (u64)svm->sysenter_esp_hi << 32; break; case MSR_TSC_AUX: - if (tsc_aux_uret_slot < 0) - return 1; - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) - return 1; msr_info->data = svm->tsc_aux; break; /* @@ -2885,24 +2879,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; break; case MSR_TSC_AUX: - if (tsc_aux_uret_slot < 0) - return 1; - - if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) - return 1; - - /* - * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has - * incomplete and conflicting architectural behavior. Current - * AMD CPUs completely ignore bits 63:32, i.e. they aren't - * reserved and always read as zeros. Emulate AMD CPU behavior - * to avoid explosions if the vCPU is migrated from an AMD host - * to an Intel host. - */ - data = (u32)data; - /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 042823b49273..61f7e5221bf3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1981,12 +1981,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) - return 1; - goto find_uret_msr; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); break; @@ -2302,15 +2296,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else vmx->pt_desc.guest.addr_a[index / 2] = data; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_uret_msr; case MSR_IA32_PERF_CAPABILITIES: if (data && !vcpu_to_pmu(vcpu)->version) return 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0a0eebf35dd5..4efd2978ec08 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1642,6 +1642,30 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * invokes 64-bit SYSENTER. */ data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); + break; + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + + /* + * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has + * incomplete and conflicting architectural behavior. Current + * AMD CPUs completely ignore bits 63:32, i.e. they aren't + * reserved and always read as zeros. Enforce Intel's reserved + * bits check if and only if the guest CPU is Intel, and clear + * the bits in all other cases. This ensures cross-vendor + * migration will provide consistent behavior for the guest. + */ + if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) + return 1; + + data = (u32)data; + break; } msr.data = data; @@ -1678,6 +1702,18 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; + switch (index) { + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + break; + } + msr.index = index; msr.host_initiated = host_initiated; From 78bba966ee3cdbbfc585d8e39237378fba50a142 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 May 2021 10:17:34 -0700 Subject: [PATCH 45/72] KVM: x86: Hide RDTSCP and RDPID if MSR_TSC_AUX probing failed If probing MSR_TSC_AUX failed, hide RDTSCP and RDPID, and WARN if either feature was reported as supported. In theory, such a scenario should never happen as both Intel and AMD state that MSR_TSC_AUX is available if RDTSCP or RDPID is supported. But, KVM injects #GP on MSR_TSC_AUX accesses if probing failed, faults on WRMSR(MSR_TSC_AUX) may be fatal to the guest (because they happen during early CPU bringup), and KVM itself has effectively misreported RDPID support in the past. Note, this also has the happy side effect of omitting MSR_TSC_AUX from the list of MSRs that are exposed to userspace if probing the MSR fails. Signed-off-by: Sean Christopherson Message-Id: <20210504171734.1434054-16-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c0e8c5e92189..f42e9491a6c8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -567,6 +567,21 @@ void kvm_set_cpu_caps(void) F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN) ); + + /* + * Hide RDTSCP and RDPID if either feature is reported as supported but + * probing MSR_TSC_AUX failed. This is purely a sanity check and + * should never happen, but the guest will likely crash if RDTSCP or + * RDPID is misreported, and KVM has botched MSR_TSC_AUX emulation in + * the past. For example, the sanity check may fire if this instance of + * KVM is running as L1 on top of an older, broken KVM. + */ + if (WARN_ON((kvm_cpu_cap_has(X86_FEATURE_RDTSCP) || + kvm_cpu_cap_has(X86_FEATURE_RDPID)) && + !kvm_is_supported_user_return_msr(MSR_TSC_AUX))) { + kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); From 34114136f725cbd0c83e7b5a0c8a977976cd82f7 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 5 May 2021 22:15:09 +1000 Subject: [PATCH 46/72] KVM: PPC: Book3S HV: Fix conversion to gfn-based MMU notifier callbacks Commit b1c5356e873c ("KVM: PPC: Convert to the gfn-based MMU notifier callbacks") causes unmap_gfn_range and age_gfn callbacks to only work on the first gfn in the range. It also makes the aging callbacks call into both radix and hash aging functions for radix guests. Fix this. Add warnings for the single-gfn calls that have been converted to range callbacks, in case they ever receieve ranges greater than 1. Fixes: b1c5356e873c ("KVM: PPC: Convert to the gfn-based MMU notifier callbacks") Reported-by: Bharata B Rao Tested-by: Bharata B Rao Signed-off-by: Nicholas Piggin Message-Id: <20210505121509.1470207-1-npiggin@gmail.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/include/asm/kvm_book3s.h | 2 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 48 ++++++++++++++++++-------- arch/powerpc/kvm/book3s_64_mmu_radix.c | 5 ++- 3 files changed, 37 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index a6e9a5585e61..e6b53c6e21e3 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -210,7 +210,7 @@ extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, unsigned int lpid); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); -extern bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, +extern void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); extern bool kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index b7bd9ca040b8..2d9193cd73be 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -795,7 +795,7 @@ static void kvmppc_unmap_hpte(struct kvm *kvm, unsigned long i, } } -static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, +static void kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { unsigned long i; @@ -829,15 +829,21 @@ static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unlock_rmap(rmapp); __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } - return false; } bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range) { - if (kvm_is_radix(kvm)) - return kvm_unmap_radix(kvm, range->slot, range->start); + gfn_t gfn; - return kvm_unmap_rmapp(kvm, range->slot, range->start); + if (kvm_is_radix(kvm)) { + for (gfn = range->start; gfn < range->end; gfn++) + kvm_unmap_radix(kvm, range->slot, gfn); + } else { + for (gfn = range->start; gfn < range->end; gfn++) + kvm_unmap_rmapp(kvm, range->slot, range->start); + } + + return false; } void kvmppc_core_flush_memslot_hv(struct kvm *kvm, @@ -924,10 +930,18 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range) { - if (kvm_is_radix(kvm)) - kvm_age_radix(kvm, range->slot, range->start); + gfn_t gfn; + bool ret = false; - return kvm_age_rmapp(kvm, range->slot, range->start); + if (kvm_is_radix(kvm)) { + for (gfn = range->start; gfn < range->end; gfn++) + ret |= kvm_age_radix(kvm, range->slot, gfn); + } else { + for (gfn = range->start; gfn < range->end; gfn++) + ret |= kvm_age_rmapp(kvm, range->slot, gfn); + } + + return ret; } static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -965,18 +979,24 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range) { - if (kvm_is_radix(kvm)) - kvm_test_age_radix(kvm, range->slot, range->start); + WARN_ON(range->start + 1 != range->end); - return kvm_test_age_rmapp(kvm, range->slot, range->start); + if (kvm_is_radix(kvm)) + return kvm_test_age_radix(kvm, range->slot, range->start); + else + return kvm_test_age_rmapp(kvm, range->slot, range->start); } bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range) { - if (kvm_is_radix(kvm)) - return kvm_unmap_radix(kvm, range->slot, range->start); + WARN_ON(range->start + 1 != range->end); - return kvm_unmap_rmapp(kvm, range->slot, range->start); + if (kvm_is_radix(kvm)) + kvm_unmap_radix(kvm, range->slot, range->start); + else + kvm_unmap_rmapp(kvm, range->slot, range->start); + + return false; } static int vcpus_running(struct kvm *kvm) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index ec4f58fa9f5a..d909c069363e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -993,7 +993,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, } /* Called with kvm->mmu_lock held */ -bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, +void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { pte_t *ptep; @@ -1002,14 +1002,13 @@ bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) { uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT); - return false; + return; } ptep = find_kvm_secondary_pte(kvm, gpa, &shift); if (ptep && pte_present(*ptep)) kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot, kvm->arch.lpid); - return false; } /* Called with kvm->mmu_lock held */ From e8ea85fb280ec55674bca88ea7cd85f60d19567f Mon Sep 17 00:00:00 2001 From: Chenyi Qiang Date: Tue, 2 Feb 2021 17:04:32 +0800 Subject: [PATCH 47/72] KVM: X86: Add support for the emulation of DR6_BUS_LOCK bit Bus lock debug exception introduces a new bit DR6_BUS_LOCK (bit 11 of DR6) to indicate that bus lock #DB exception is generated. The set/clear of DR6_BUS_LOCK is similar to the DR6_RTM. The processor clears DR6_BUS_LOCK when the exception is generated. For all other #DB, the processor sets this bit to 1. Software #DB handler should set this bit before returning to the interrupted task. In VMM, to avoid breaking the CPUs without bus lock #DB exception support, activate the DR6_BUS_LOCK conditionally in DR6_FIXED_1 bits. When intercepting the #DB exception caused by bus locks, bit 11 of the exit qualification is set to identify it. The VMM should emulate the exception by clearing the bit 11 of the guest DR6. Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Chenyi Qiang Message-Id: <20210202090433.13441-3-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 ++- arch/x86/kvm/x86.c | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f85480b1d215..8836b3096217 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -200,6 +200,7 @@ enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 +#define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) @@ -213,7 +214,7 @@ enum x86_intercept_stage; * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. */ #define DR6_ACTIVE_LOW 0xffff0ff0 -#define DR6_VOLATILE 0x0001e00f +#define DR6_VOLATILE 0x0001e80f #define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4efd2978ec08..9b1a7040eae3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1176,6 +1176,9 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + fixed |= DR6_BUS_LOCK; return fixed; } From 76ea438b4afcd9ee8da3387e9af4625eaccff58f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 6 May 2021 06:30:04 -0400 Subject: [PATCH 48/72] KVM: X86: Expose bus lock debug exception to guest Bus lock debug exception is an ability to notify the kernel by an #DB trap after the instruction acquires a bus lock and is executed when CPL>0. This allows the kernel to enforce user application throttling or mitigations. Existence of bus lock debug exception is enumerated via CPUID.(EAX=7,ECX=0).ECX[24]. Software can enable these exceptions by setting bit 2 of the MSR_IA32_DEBUGCTL. Expose the CPUID to guest and emulate the MSR handling when guest enables it. Support for this feature was originally developed by Xiaoyao Li and Chenyi Qiang, but code has since changed enough that this patch has nothing in common with theirs, except for this commit message. Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Chenyi Qiang Message-Id: <20210202090433.13441-4-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/vmx/capabilities.h | 3 +++ arch/x86/kvm/vmx/vmx.c | 3 +++ 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index f42e9491a6c8..9a48f138832d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -458,7 +458,7 @@ void kvm_set_cpu_caps(void) F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | - F(SGX_LC) + F(SGX_LC) | F(BUS_LOCK_DETECT) ); /* Set LA57 based on hardware capability. */ if (cpuid_ecx(7) & F(LA57)) diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d1d77985e889..8dee8a5fbc17 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -398,6 +398,9 @@ static inline u64 vmx_supported_debugctl(void) { u64 debugctl = 0; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; + if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) debugctl |= DEBUGCTLMSR_LBR_MASK; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 61f7e5221bf3..f2fd447eed45 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2014,6 +2014,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) if (!intel_pmu_lbr_is_enabled(vcpu)) debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + return debugctl; } From 03ca4589fabcc66b27e4cb8f8e95d64cf43badd0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 5 May 2021 13:42:21 -0700 Subject: [PATCH 49/72] KVM: x86: Prevent KVM SVM from loading on kernels with 5-level paging Disallow loading KVM SVM if 5-level paging is supported. In theory, NPT for L1 should simply work, but there unknowns with respect to how the guest's MAXPHYADDR will be handled by hardware. Nested NPT is more problematic, as running an L1 VMM that is using 2-level page tables requires stacking single-entry PDP and PML4 tables in KVM's NPT for L2, as there are no equivalent entries in L1's NPT to shadow. Barring hardware magic, for 5-level paging, KVM would need stack another layer to handle PML5. Opportunistically rename the lm_root pointer, which is used for the aforementioned stacking when shadowing 2-level L1 NPT, to pml4_root to call out that it's specifically for PML4. Suggested-by: Paolo Bonzini Signed-off-by: Sean Christopherson Message-Id: <20210505204221.1934471-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu/mmu.c | 20 ++++++++++---------- arch/x86/kvm/svm/svm.c | 5 +++++ 3 files changed, 16 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8836b3096217..55efbacfc244 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -409,7 +409,7 @@ struct kvm_mmu { u32 pkru_mask; u64 *pae_root; - u64 *lm_root; + u64 *pml4_root; /* * check zero bits on shadow page table entries, these diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4b3ee244ebe0..0144c40d09c7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3310,12 +3310,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; - if (WARN_ON_ONCE(!mmu->lm_root)) { + if (WARN_ON_ONCE(!mmu->pml4_root)) { r = -EIO; goto out_unlock; } - mmu->lm_root[0] = __pa(mmu->pae_root) | pm_mask; + mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask; } for (i = 0; i < 4; ++i) { @@ -3335,7 +3335,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) - mmu->root_hpa = __pa(mmu->lm_root); + mmu->root_hpa = __pa(mmu->pml4_root); else mmu->root_hpa = __pa(mmu->pae_root); @@ -3350,7 +3350,7 @@ out_unlock: static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; - u64 *lm_root, *pae_root; + u64 *pml4_root, *pae_root; /* * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP @@ -3369,14 +3369,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL)) return -EIO; - if (mmu->pae_root && mmu->lm_root) + if (mmu->pae_root && mmu->pml4_root) return 0; /* * The special roots should always be allocated in concert. Yell and * bail if KVM ends up in a state where only one of the roots is valid. */ - if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->lm_root)) + if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root)) return -EIO; /* @@ -3387,14 +3387,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (!pae_root) return -ENOMEM; - lm_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!lm_root) { + pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml4_root) { free_page((unsigned long)pae_root); return -ENOMEM; } mmu->pae_root = pae_root; - mmu->lm_root = lm_root; + mmu->pml4_root = pml4_root; return 0; } @@ -5261,7 +5261,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu) if (!tdp_enabled && mmu->pae_root) set_memory_encrypted((unsigned long)mmu->pae_root, 1); free_page((unsigned long)mmu->pae_root); - free_page((unsigned long)mmu->lm_root); + free_page((unsigned long)mmu->pml4_root); } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0922d8e173e6..8124f51e9488 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -447,6 +447,11 @@ static int has_svm(void) return 0; } + if (pgtable_l5_enabled()) { + pr_info("KVM doesn't yet support 5-level paging on AMD SVM\n"); + return 0; + } + return 1; } From 594b27e677b35f9734b1969d175ebc6146741109 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 5 May 2021 23:48:17 +0200 Subject: [PATCH 50/72] KVM: x86: Cancel pvclock_gtod_work on module removal Nothing prevents the following: pvclock_gtod_notify() queue_work(system_long_wq, &pvclock_gtod_work); ... remove_module(kvm); ... work_queue_run() pvclock_gtod_work() <- UAF Ditto for any other operation on that workqueue list head which touches pvclock_gtod_work after module removal. Cancel the work in kvm_arch_exit() to prevent that. Fixes: 16e8d74d2da9 ("KVM: x86: notifier for clocksource changes") Signed-off-by: Thomas Gleixner Message-Id: <87czu4onry.ffs@nanos.tec.linutronix.de> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9b1a7040eae3..259139a145cb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8224,6 +8224,7 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); From 3f804f6d201ca93adf4c3df04d1bfd152c1129d6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 6 May 2021 15:21:37 +0200 Subject: [PATCH 51/72] KVM: x86: Prevent deadlock against tk_core.seq syzbot reported a possible deadlock in pvclock_gtod_notify(): CPU 0 CPU 1 write_seqcount_begin(&tk_core.seq); pvclock_gtod_notify() spin_lock(&pool->lock); queue_work(..., &pvclock_gtod_work) ktime_get() spin_lock(&pool->lock); do { seq = read_seqcount_begin(tk_core.seq) ... } while (read_seqcount_retry(&tk_core.seq, seq); While this is unlikely to happen, it's possible. Delegate queue_work() to irq_work() which postpones it until the tk_core.seq write held region is left and interrupts are reenabled. Fixes: 16e8d74d2da9 ("KVM: x86: notifier for clocksource changes") Reported-by: syzbot+6beae4000559d41d80f8@syzkaller.appspotmail.com Signed-off-by: Thomas Gleixner Message-Id: <87h7jgm1zy.ffs@nanos.tec.linutronix.de> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 259139a145cb..5bd550eaf683 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8094,6 +8094,18 @@ static void pvclock_gtod_update_fn(struct work_struct *work) static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); +/* + * Indirection to move queue_work() out of the tk_core.seq write held + * region to prevent possible deadlocks against time accessors which + * are invoked with work related locks held. + */ +static void pvclock_irq_work_fn(struct irq_work *w) +{ + queue_work(system_long_wq, &pvclock_gtod_work); +} + +static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); + /* * Notification about pvclock gtod data update. */ @@ -8105,13 +8117,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); - /* disable master clock if host does not trust, or does not - * use, TSC based clocksource. + /* + * Disable master clock if host does not trust, or does not use, + * TSC based clocksource. Delegate queue_work() to irq_work as + * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) - queue_work(system_long_wq, &pvclock_gtod_work); - + irq_work_queue(&pvclock_irq_work); return 0; } @@ -8224,6 +8237,7 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; From b26990987ffce0525abbd84b36595869cfdbbfe6 Mon Sep 17 00:00:00 2001 From: Stefan Raspl Date: Thu, 6 May 2021 16:03:52 +0200 Subject: [PATCH 52/72] tools/kvm_stat: Fix documentation typo Makes the dash in front of option '-z' disappear in the generated man-page. Signed-off-by: Stefan Raspl Message-Id: <20210506140352.4178789-1-raspl@linux.ibm.com> Signed-off-by: Paolo Bonzini --- tools/kvm/kvm_stat/kvm_stat.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index feaf46451e83..3a9f2037bd23 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -111,7 +111,7 @@ OPTIONS --tracepoints:: retrieve statistics from tracepoints -*z*:: +-z:: --skip-zero-records:: omit records with all zeros in logging mode From 258785ef08b323bddd844b4926a32c2b2045a1b0 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Thu, 6 May 2021 15:24:43 +0000 Subject: [PATCH 53/72] kvm: Cap halt polling at kvm->max_halt_poll_ns When growing halt-polling, there is no check that the poll time exceeds the per-VM limit. It's possible for vcpu->halt_poll_ns to grow past kvm->max_halt_poll_ns and stay there until a halt which takes longer than kvm->halt_poll_ns. Signed-off-by: David Matlack Signed-off-by: Venkatesh Srinivas Message-Id: <20210506152442.4010298-1-venkateshs@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b9f12da6af0e..6b4feb92dc79 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2893,8 +2893,8 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > halt_poll_ns) - val = halt_poll_ns; + if (val > vcpu->kvm->max_halt_poll_ns) + val = vcpu->kvm->max_halt_poll_ns; vcpu->halt_poll_ns = val; out: From 368340a3c7d9a207bfe544721d464b7109be8eae Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 6 May 2021 16:15:42 -0700 Subject: [PATCH 54/72] KVM: SVM: Invert user pointer casting in SEV {en,de}crypt helpers Invert the user pointer params for SEV's helpers for encrypting and decrypting guest memory so that they take a pointer and cast to an unsigned long as necessary, as opposed to doing the opposite. Tagging a non-pointer as __user is confusing and weird since a cast of some form needs to occur to actually access the user data. This also fixes Sparse warnings triggered by directly consuming the unsigned longs, which are "noderef" due to the __user tag. Cc: Brijesh Singh Cc: Tom Lendacky Cc: Ashish Kalra Signed-off-by: Sean Christopherson Message-Id: <20210506231542.2331138-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 8b11c711a0e4..eb241c1a4add 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -763,7 +763,7 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, } static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user dst_uaddr, + void __user *dst_uaddr, unsigned long dst_paddr, int size, int *err) { @@ -787,8 +787,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (tpage) { offset = paddr & 15; - if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, - page_address(tpage) + offset, size)) + if (copy_to_user(dst_uaddr, page_address(tpage) + offset, size)) ret = -EFAULT; } @@ -800,9 +799,9 @@ e_free: } static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user vaddr, + void __user *vaddr, unsigned long dst_paddr, - unsigned long __user dst_vaddr, + void __user *dst_vaddr, int size, int *error) { struct page *src_tpage = NULL; @@ -810,13 +809,12 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, int ret, len = size; /* If source buffer is not aligned then use an intermediate buffer */ - if (!IS_ALIGNED(vaddr, 16)) { + if (!IS_ALIGNED((unsigned long)vaddr, 16)) { src_tpage = alloc_page(GFP_KERNEL); if (!src_tpage) return -ENOMEM; - if (copy_from_user(page_address(src_tpage), - (void __user *)(uintptr_t)vaddr, size)) { + if (copy_from_user(page_address(src_tpage), vaddr, size)) { __free_page(src_tpage); return -EFAULT; } @@ -830,7 +828,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, * - copy the source buffer in an intermediate buffer * - use the intermediate buffer as source buffer */ - if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; dst_tpage = alloc_page(GFP_KERNEL); @@ -855,7 +853,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, page_address(src_tpage), size); else { if (copy_from_user(page_address(dst_tpage) + dst_offset, - (void __user *)(uintptr_t)vaddr, size)) { + vaddr, size)) { ret = -EFAULT; goto e_free; } @@ -935,15 +933,15 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (dec) ret = __sev_dbg_decrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - dst_vaddr, + (void __user *)dst_vaddr, __sme_page_pa(dst_p[0]) + d_off, len, &argp->error); else ret = __sev_dbg_encrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - vaddr, + (void __user *)vaddr, __sme_page_pa(dst_p[0]) + d_off, - dst_vaddr, + (void __user *)dst_vaddr, len, &argp->error); sev_unpin_memory(kvm, src_p, n); From ce7ea0cfdc2e9ff31d12da31c3226deddb9644f5 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 6 May 2021 15:14:41 -0500 Subject: [PATCH 55/72] KVM: SVM: Move GHCB unmapping to fix RCU warning When an SEV-ES guest is running, the GHCB is unmapped as part of the vCPU run support. However, kvm_vcpu_unmap() triggers an RCU dereference warning with CONFIG_PROVE_LOCKING=y because the SRCU lock is released before invoking the vCPU run support. Move the GHCB unmapping into the prepare_guest_switch callback, which is invoked while still holding the SRCU lock, eliminating the RCU dereference warning. Fixes: 291bd20d5d88 ("KVM: SVM: Add initial support for a VMGEXIT VMEXIT") Reported-by: Borislav Petkov Signed-off-by: Tom Lendacky Message-Id: Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 5 +---- arch/x86/kvm/svm/svm.c | 3 +++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index eb241c1a4add..5bc887e9a986 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2197,7 +2197,7 @@ vmgexit_err: return -EINVAL; } -static void pre_sev_es_run(struct vcpu_svm *svm) +void sev_es_unmap_ghcb(struct vcpu_svm *svm) { if (!svm->ghcb) return; @@ -2233,9 +2233,6 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); - /* Perform any SEV-ES pre-run actions */ - pre_sev_es_run(svm); - /* Assign the asid allocated with this SEV guest */ svm->asid = asid; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8124f51e9488..4dd9b7856e5b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1437,6 +1437,9 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + if (sev_es_guest(vcpu->kvm)) + sev_es_unmap_ghcb(svm); + if (svm->guest_state_loaded) return; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 84b3133c2251..e44567ceb865 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -581,6 +581,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ From a3bc4ffeedf4693262fe7c6d133dcfcacd3d18c2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 3 May 2021 11:48:26 -0300 Subject: [PATCH 56/72] tools headers UAPI: Update tools's copy of drm.h headers Picking the changes from: b603e810f740e76b ("drm/uapi: document kernel capabilities") Doesn't result in any tooling changes: $ tools/perf/trace/beauty/drm_ioctl.sh > before $ cp include/uapi/drm/drm.h tools/include/uapi/drm/drm.h $ tools/perf/trace/beauty/drm_ioctl.sh > after $ diff -u before after Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h Cc: Simon Ser Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 125 +++++++++++++++++++++++++++++++++-- 1 file changed, 121 insertions(+), 4 deletions(-) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 0827037c5484..67b94bc3c885 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -625,30 +625,147 @@ struct drm_gem_open { __u64 size; }; +/** + * DRM_CAP_DUMB_BUFFER + * + * If set to 1, the driver supports creating dumb buffers via the + * &DRM_IOCTL_MODE_CREATE_DUMB ioctl. + */ #define DRM_CAP_DUMB_BUFFER 0x1 +/** + * DRM_CAP_VBLANK_HIGH_CRTC + * + * If set to 1, the kernel supports specifying a CRTC index in the high bits of + * &drm_wait_vblank_request.type. + * + * Starting kernel version 2.6.39, this capability is always set to 1. + */ #define DRM_CAP_VBLANK_HIGH_CRTC 0x2 +/** + * DRM_CAP_DUMB_PREFERRED_DEPTH + * + * The preferred bit depth for dumb buffers. + * + * The bit depth is the number of bits used to indicate the color of a single + * pixel excluding any padding. This is different from the number of bits per + * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per + * pixel. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3 +/** + * DRM_CAP_DUMB_PREFER_SHADOW + * + * If set to 1, the driver prefers userspace to render to a shadow buffer + * instead of directly rendering to a dumb buffer. For best speed, userspace + * should do streaming ordered memory copies into the dumb buffer and never + * read from it. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFER_SHADOW 0x4 +/** + * DRM_CAP_PRIME + * + * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT + * and &DRM_PRIME_CAP_EXPORT. + * + * PRIME buffers are exposed as dma-buf file descriptors. See + * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + */ #define DRM_CAP_PRIME 0x5 +/** + * DRM_PRIME_CAP_IMPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME + * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + */ #define DRM_PRIME_CAP_IMPORT 0x1 +/** + * DRM_PRIME_CAP_EXPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME + * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + */ #define DRM_PRIME_CAP_EXPORT 0x2 +/** + * DRM_CAP_TIMESTAMP_MONOTONIC + * + * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in + * struct drm_event_vblank. If set to 1, the kernel will report timestamps with + * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these + * clocks. + * + * Starting from kernel version 2.6.39, the default value for this capability + * is 1. Starting kernel version 4.15, this capability is always set to 1. + */ #define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 +/** + * DRM_CAP_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + */ #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 -/* - * The CURSOR_WIDTH and CURSOR_HEIGHT capabilities return a valid widthxheight - * combination for the hardware cursor. The intention is that a hardware - * agnostic userspace can query a cursor plane size to use. +/** + * DRM_CAP_CURSOR_WIDTH + * + * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid + * width x height combination for the hardware cursor. The intention is that a + * hardware agnostic userspace can query a cursor plane size to use. * * Note that the cross-driver contract is to merely return a valid size; * drivers are free to attach another meaning on top, eg. i915 returns the * maximum plane size. */ #define DRM_CAP_CURSOR_WIDTH 0x8 +/** + * DRM_CAP_CURSOR_HEIGHT + * + * See &DRM_CAP_CURSOR_WIDTH. + */ #define DRM_CAP_CURSOR_HEIGHT 0x9 +/** + * DRM_CAP_ADDFB2_MODIFIERS + * + * If set to 1, the driver supports supplying modifiers in the + * &DRM_IOCTL_MODE_ADDFB2 ioctl. + */ #define DRM_CAP_ADDFB2_MODIFIERS 0x10 +/** + * DRM_CAP_PAGE_FLIP_TARGET + * + * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and + * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in + * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP + * ioctl. + */ #define DRM_CAP_PAGE_FLIP_TARGET 0x11 +/** + * DRM_CAP_CRTC_IN_VBLANK_EVENT + * + * If set to 1, the kernel supports reporting the CRTC ID in + * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and + * &DRM_EVENT_FLIP_COMPLETE events. + * + * Starting kernel version 4.12, this capability is always set to 1. + */ #define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 +/** + * DRM_CAP_SYNCOBJ + * + * If set to 1, the driver supports sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ 0x13 +/** + * DRM_CAP_SYNCOBJ_TIMELINE + * + * If set to 1, the driver supports timeline operations on sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 /* DRM_IOCTL_GET_CAP ioctl argument type */ From 0fdee797d60d71e5a6fd59aa573d84a858e715dd Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 3 May 2021 11:51:17 -0300 Subject: [PATCH 57/72] tools headers UAPI: Sync drm/i915_drm.h with the kernel sources To pick the changes in: b5b6f6a610127b17 ("drm/i915/gem: Drop legacy execbuffer support (v2)") That don't result in any change in tooling as this is just adding a comment. Only silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Cc: Daniel Vetter Cc: Jason Ekstrand Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 1987e2ea79a3..ddc47bbf48b6 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -943,6 +943,7 @@ struct drm_i915_gem_exec_object { __u64 offset; }; +/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */ struct drm_i915_gem_execbuffer { /** * List of buffers to be validated with their relocations to be From b3172585b13d7171c32cfabdf938eca7fdfe9b31 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 3 May 2021 11:53:37 -0300 Subject: [PATCH 58/72] tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes from these csets: d0946a882e622022 ("perf/x86/intel: Hybrid PMU support for perf capabilities") That cause no changes to tooling as it isn't adding any new MSR, just some capabilities for a pre-existing one: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after $ Just silences this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Cc: Kan Liang Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 45029354e0a8..742d89a00721 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -185,6 +185,9 @@ #define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define PERF_CAP_METRICS_IDX 15 +#define PERF_CAP_PT_IDX 16 + #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 @@ -265,6 +268,7 @@ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) #define DEBUGCTLMSR_BTINT (1UL << 8) From e8c1167606c63fd8f9934d0b6ce80281463a4945 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 2 Apr 2021 18:40:20 +0900 Subject: [PATCH 59/72] perf record: Disallow -c and -F option at the same time It's confusing which one is effective when the both options are given. The current code happens to use -c in this case but users might not be aware of it. We can change it to complain about that instead of relying on the implicit priority. Before: $ perf record -c 111111 -F 99 true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.031 MB perf.data (8 samples) ] $ perf evlist -F cycles: sample_period=111111 $ After: $ perf record -c 111111 -F 99 true cannot set frequency and period at the same time $ So this change can break existing usages, but I think it's rare to have both options and it'd be better changing them. Suggested-by: Alexey Alexandrov Signed-off-by: Namhyung Kim Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210402094020.28164-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/record.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index f99852d54b14..43e5b563dee8 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -157,9 +157,15 @@ static int get_max_rate(unsigned int *rate) static int record_opts__config_freq(struct record_opts *opts) { bool user_freq = opts->user_freq != UINT_MAX; + bool user_interval = opts->user_interval != ULLONG_MAX; unsigned int max_rate; - if (opts->user_interval != ULLONG_MAX) + if (user_interval && user_freq) { + pr_err("cannot set frequency and period at the same time\n"); + return -1; + } + + if (user_interval) opts->default_interval = opts->user_interval; if (user_freq) opts->freq = opts->user_freq; From 7aa3c9eabdf76017679e975e2ffd50cde3c010b8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 May 2021 15:56:40 -0700 Subject: [PATCH 60/72] perf jevents: Silence warning for ArchStd files JSON files in the level 1 directory are used for ArchStd events (see preprocess_arch_std_files), as such they shouldn't be warned about. Signed-off-by: Ian Rogers Reviewed-by: John Garry Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Joakim Zhang Cc: Kajol Jain Cc: Kim Phillips Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210506225640.1461000-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index ed4f0bd72e5a..7422b0ea8790 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1123,8 +1123,10 @@ static int process_one_file(const char *fpath, const struct stat *sb, mapfile = strdup(fpath); return 0; } - - pr_info("%s: Ignoring file %s\n", prog, fpath); + if (is_json_file(bname)) + pr_debug("%s: ArchStd json is preprocessed %s\n", prog, fpath); + else + pr_info("%s: Ignoring file %s\n", prog, fpath); return 0; } From a11c9a6e472457cf9eeafb585fc5c912f51d1b23 Mon Sep 17 00:00:00 2001 From: Dmitry Koshelev Date: Thu, 6 May 2021 13:11:49 +0000 Subject: [PATCH 61/72] perf session: Fix swapping of cpu_map and stat_config records 'data' field in perf_record_cpu_map_data struct is 16-bit wide and so should be swapped using bswap_16(). 'nr' field in perf_record_stat_config struct should be swapped before being used for size calculation. Signed-off-by: Dmitry Koshelev Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210506131244.13328-1-karaghiozis@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a12cf4f0e97a..106b3d60881a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -904,7 +904,7 @@ static void perf_event__cpu_map_swap(union perf_event *event, struct perf_record_record_cpu_map *mask; unsigned i; - data->type = bswap_64(data->type); + data->type = bswap_16(data->type); switch (data->type) { case PERF_CPU_MAP__CPUS: @@ -937,7 +937,7 @@ static void perf_event__stat_config_swap(union perf_event *event, { u64 size; - size = event->stat_config.nr * sizeof(event->stat_config.data[0]); + size = bswap_64(event->stat_config.nr) * sizeof(event->stat_config.data[0]); size += 1; /* nr item itself */ mem_bswap_64(&event->stat_config.nr, size); } From ad1237c30d975535a669746496cbed136aa5a045 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 8 May 2021 22:50:20 +0200 Subject: [PATCH 62/72] perf tools: Fix dynamic libbpf link Justin reported broken build with LIBBPF_DYNAMIC=1. When linking libbpf dynamically we need to use perf's hashmap object, because it's not exported in libbpf.so (only in libbpf.a). Following build is now passing: $ make LIBBPF_DYNAMIC=1 BUILD: Doing 'make -j8' parallel build ... $ ldd perf | grep libbpf libbpf.so.0 => /lib64/libbpf.so.0 (0x00007fa7630db000) Fixes: eee19501926d ("perf tools: Grab a copy of libbpf's hashmap") Reported-by: Justin M. Forbes Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ian Rogers Cc: Mark Rutland Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210508205020.617984-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 1 + tools/perf/util/Build | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0d6619064a83..406a9519145e 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -540,6 +540,7 @@ ifndef NO_LIBELF ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf + $(call detected,CONFIG_LIBBPF_DYNAMIC) else dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8c0d9f368ebc..b64bdc1a7026 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -145,7 +145,14 @@ perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o perf-$(CONFIG_LIBELF) += probe-event.o +ifdef CONFIG_LIBBPF_DYNAMIC + hashmap := 1 +endif ifndef CONFIG_LIBBPF + hashmap := 1 +endif + +ifdef hashmap perf-y += hashmap.o endif From 0d943d5fde6070c2661a99618ea95b99655589ad Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:39:02 -0300 Subject: [PATCH 63/72] tools headers UAPI: Sync linux/kvm.h with the kernel sources To pick the changes in: 15fb7de1a7f5af0d ("KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command") 3bf725699bf62494 ("KVM: arm64: Add support for the KVM PTP service") 4cfdd47d6d95aca4 ("KVM: SVM: Add KVM_SEV SEND_START command") 54526d1fd59338fd ("KVM: x86: Support KVM VMs sharing SEV context") 5569e2e7a650dfff ("KVM: SVM: Add support for KVM_SEV_SEND_CANCEL command") 8b13c36493d8cb56 ("KVM: introduce KVM_CAP_SET_GUEST_DEBUG2") af43cbbf954b50ca ("KVM: SVM: Add support for KVM_SEV_RECEIVE_START command") d3d1af85e2c75bb5 ("KVM: SVM: Add KVM_SEND_UPDATE_DATA command") fe7e948837f312d8 ("KVM: x86: Add capability to grant VM access to privileged SGX attribute") That don't cause any change in tooling as it doesn't introduce any new ioctl. $ grep kvm tools/perf/trace/beauty/*.sh tools/perf/trace/beauty/kvm_ioctl.sh:printf "static const char *kvm_ioctl_cmds[] = {\n" tools/perf/trace/beauty/kvm_ioctl.sh:egrep $regex ${header_dir}/kvm.h | \ $ $ tools/perf/trace/beauty/kvm_ioctl.sh > before $ cp include/uapi/linux/kvm.h tools/include/uapi/linux/kvm.h $ tools/perf/trace/beauty/kvm_ioctl.sh > after $ diff -u before after $ This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Cc: Brijesh Singh Cc: Jianyong Wu Cc: Marc Zyngier Cc: Nathan Tempelman Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Steve Rutherford Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/kvm.h | 45 ++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f6afee209620..3fd9a7e9d90c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1078,6 +1078,10 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 #define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_SET_GUEST_DEBUG2 195 +#define KVM_CAP_SGX_ATTRIBUTE 196 +#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 +#define KVM_CAP_PTP_KVM 198 #ifdef KVM_CAP_IRQ_ROUTING @@ -1671,6 +1675,8 @@ enum sev_cmd_id { KVM_SEV_CERT_EXPORT, /* Attestation report */ KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, KVM_SEV_NR_MAX, }; @@ -1729,6 +1735,45 @@ struct kvm_sev_attestation_report { __u32 len; }; +struct kvm_sev_send_start { + __u32 policy; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) From b35629bc2fd59691504debda99c320cf966c8e3a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:45:25 -0300 Subject: [PATCH 64/72] tools headers kvm: Sync kvm headers with the kernel sources To pick the changes in: 3c0c2ad1ae75963c ("KVM: VMX: Add basic handling of VM-Exit from SGX enclave") None of them trigger any changes in tooling, this time this is just to silence these perf build warnings: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/vmx.h' differs from latest version at 'arch/x86/include/uapi/asm/vmx.h' diff -u tools/arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/vmx.h Cc: Paolo Bonzini Cc: Sean Christopherson Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/vmx.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index b8e650a985e3..946d761adbd3 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -27,6 +27,7 @@ #define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 +#define VMX_EXIT_REASONS_SGX_ENCLAVE_MODE 0x08000000 #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 From a00b7e39d6b56e6f49cdd51a9ebf92627a19d877 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 7 May 2021 17:54:35 +0900 Subject: [PATCH 65/72] perf tools: Fix a build error on arm64 with clang Since clang's -Wmissing-field-initializers warns if a data structure is initialized with a signle NULL as below, ---- tools/perf $ make CC=clang LLVM=1 ... arch/arm64/util/kvm-stat.c:74:9: error: missing field 'ops' initializer [-Werror,-Wmissing-field-initializers] { NULL }, ^ 1 error generated. ---- add another field initializer expressly as same as other arch's kvm-stat.c code. Signed-off-by: Masami Hiramatsu Cc: Anders Roxell Cc: Leo Yan Cc: Sergey Senozhatsky Link: http://lore.kernel.org/lkml/162037767540.94840.15758657049033010518.stgit@devnote2 Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/kvm-stat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 2303256b7d05..73d18e0ed6f6 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -71,7 +71,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = { .name = "vmexit", .ops = &exit_events, }, - { NULL }, + { NULL, NULL }, }; const char * const kvm_skip_events[] = { From f8bcb061ea013a9b39a071b9dd9f6ea0aa2caf72 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 09:55:30 -0300 Subject: [PATCH 66/72] tools headers UAPI: Sync files changed by landlock, quotactl_path and mount_settattr new syscalls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To pick the changes in these csets: a49f4f81cb48925e ("arch: Wire up Landlock syscalls") 2a1867219c7b27f9 ("fs: add mount_setattr()") fa8b90070a80bb1a ("quota: wire up quotactl_path") That silences these perf build warnings and add support for those new syscalls in tools such as 'perf trace'. For instance, this is now possible: # ~acme/bin/perf trace -v -e landlock* event qualifier tracepoint filter: (common_pid != 129365 && common_pid != 3502) && (id == 444 || id == 445 || id == 446) ^C# That is tha filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep landlock tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self $ This addresses these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl Warning: Kernel ABI header at 'tools/perf/arch/powerpc/entry/syscalls/syscall.tbl' differs from latest version at 'arch/powerpc/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Warning: Kernel ABI header at 'tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl' differs from latest version at 'arch/mips/kernel/syscalls/syscall_n64.tbl' diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl Cc: Christian Brauner Cc: James Morris Cc: Jan Kara Cc: Mickaël Salaün Cc: Sascha Hauer Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 11 ++++++++++- tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 5 +++++ tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 4 ++++ tools/perf/arch/s390/entry/syscalls/syscall.tbl | 4 ++++ tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 4 ++++ 5 files changed, 27 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index ce58cff99b66..6de5a7fc066b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -863,9 +863,18 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) +#define __NR_quotactl_path 443 +__SYSCALL(__NR_quotactl_path, sys_quotactl_path) + +#define __NR_landlock_create_ruleset 444 +__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) +#define __NR_landlock_add_rule 445 +__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) +#define __NR_landlock_restrict_self 446 +__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #undef __NR_syscalls -#define __NR_syscalls 443 +#define __NR_syscalls 447 /* * 32 bit systems traditionally used different diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 91649690b52f..9974f5f8e49b 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -356,3 +356,8 @@ 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 +442 n64 mount_setattr sys_mount_setattr +443 n64 quotactl_path sys_quotactl_path +444 n64 landlock_create_ruleset sys_landlock_create_ruleset +445 n64 landlock_add_rule sys_landlock_add_rule +446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 0b2480cf3e47..2e68fbb57cc6 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,3 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 3abef2144dac..7e4a2aba366d 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,3 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7bf01cbe582f..ecd551b08d05 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,6 +364,10 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self # # Due to a historical design error, certain syscalls are numbered differently From 5a80ee4219a52194f0e815bbceec40eb32c523ec Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 10:06:40 -0300 Subject: [PATCH 67/72] tools headers UAPI: Sync linux/prctl.h with the kernel sources To pick a new prctl introduced in: 201698626fbca1cf ("arm64: Introduce prctl(PR_PAC_{SET,GET}_ENABLED_KEYS)") That results in $ grep prctl tools/perf/trace/beauty/*.sh tools/perf/trace/beauty/prctl_option.sh:printf "static const char *prctl_options[] = {\n" tools/perf/trace/beauty/prctl_option.sh:egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \ tools/perf/trace/beauty/prctl_option.sh:printf "static const char *prctl_set_mm_options[] = {\n" tools/perf/trace/beauty/prctl_option.sh:egrep $regex ${header_dir}/prctl.h | \ tools/perf/trace/beauty/x86_arch_prctl.sh:prctl_arch_header=${x86_header_dir}/prctl.h tools/perf/trace/beauty/x86_arch_prctl.sh: printf "#define x86_arch_prctl_codes_%d_offset %s\n" $idx $first_entry tools/perf/trace/beauty/x86_arch_prctl.sh: printf "static const char *x86_arch_prctl_codes_%d[] = {\n" $idx tools/perf/trace/beauty/x86_arch_prctl.sh: egrep -q $regex ${prctl_arch_header} && \ tools/perf/trace/beauty/x86_arch_prctl.sh: (egrep $regex ${prctl_arch_header} | \ $ tools/perf/trace/beauty/prctl_option.sh > before $ cp include/uapi/linux/prctl.h tools/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after $ diff -u before after --- before 2021-05-09 10:06:10.064559675 -0300 +++ after 2021-05-09 10:06:21.319791396 -0300 @@ -54,6 +54,8 @@ [57] = "SET_IO_FLUSHER", [58] = "GET_IO_FLUSHER", [59] = "SET_SYSCALL_USER_DISPATCH", + [60] = "PAC_SET_ENABLED_KEYS", + [61] = "PAC_GET_ENABLED_KEYS", }; static const char *prctl_set_mm_options[] = { [1] = "START_CODE", $ Now users can do: # perf trace -e syscalls:sys_enter_prctl --filter "option==PAC_GET_ENABLED_KEYS" ^C# # trace -v -e syscalls:sys_enter_prctl --filter "option==PAC_GET_ENABLED_KEYS" New filter for syscalls:sys_enter_prctl: (option==0x3d) && (common_pid != 5519 && common_pid != 3404) ^C# And also when prctl appears in a session, its options will be translated to the string. Cc: Catalin Marinas Cc: Peter Collingbourne Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/prctl.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 667f1aed091c..18a9f59dc067 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -255,4 +255,8 @@ struct prctl_mm_map { # define SYSCALL_DISPATCH_FILTER_ALLOW 0 # define SYSCALL_DISPATCH_FILTER_BLOCK 1 +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + #endif /* _LINUX_PRCTL_H */ From fb24e308b6310541e70d11a3f19dc40742974b95 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 10:19:37 -0300 Subject: [PATCH 68/72] tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' To bring in the change made in this cset: 5e21a3ecad1500e3 ("x86/alternative: Merge include files") This just silences these perf tools build warnings, no change in the tools: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Cc: Borislav Petkov Cc: Juergen Gross Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 2 +- tools/arch/x86/lib/memset_64.S | 2 +- tools/include/asm/{alternative-asm.h => alternative.h} | 0 3 files changed, 2 insertions(+), 2 deletions(-) rename tools/include/asm/{alternative-asm.h => alternative.h} (100%) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1e299ac73c86..1cc9da6e29c7 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include .pushsection .noinstr.text, "ax" diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..9827ae267f96 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -3,7 +3,7 @@ #include #include -#include +#include #include /* diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative.h similarity index 100% rename from tools/include/asm/alternative-asm.h rename to tools/include/asm/alternative.h From 3916329309eace19e8c32bc821064a119474c309 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 10:21:33 -0300 Subject: [PATCH 69/72] tools include UAPI powerpc: Sync errno.h with the kernel headers To pick the change in: 7de21e679e6a789f ("powerpc: fix EDEADLOCK redefinition error in uapi/asm/errno.h") That will make the errno number -> string tables to pick this change on powerpc. Silencing this perf build warning: Warning: Kernel ABI header at 'tools/arch/powerpc/include/uapi/asm/errno.h' differs from latest version at 'arch/powerpc/include/uapi/asm/errno.h' diff -u tools/arch/powerpc/include/uapi/asm/errno.h arch/powerpc/include/uapi/asm/errno.h Cc: Michael Ellerman Cc: Tony Ambardar Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/powerpc/include/uapi/asm/errno.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/arch/powerpc/include/uapi/asm/errno.h b/tools/arch/powerpc/include/uapi/asm/errno.h index cc79856896a1..4ba87de32be0 100644 --- a/tools/arch/powerpc/include/uapi/asm/errno.h +++ b/tools/arch/powerpc/include/uapi/asm/errno.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H +#undef EDEADLOCK #include #undef EDEADLOCK From 6faf64f5248166ecaf50107e883c383e0b66bb70 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 10:24:29 -0300 Subject: [PATCH 70/72] tools headers cpufeatures: Sync with the kernel sources To pick the changes from: 4e6292114c741221 ("x86/paravirt: Add new features for paravirt patching") a161545ab53b174c ("x86/cpufeatures: Enumerate Intel Hybrid Technology feature bit") a89dfde3dc3c2dbf ("x86: Remove dynamic NOP selection") b8921dccf3b25798 ("x86/cpufeatures: Add SGX1 and SGX2 sub-features") f21d4d3b97a86035 ("x86/cpufeatures: Enumerate #DB for bus lock detection") f333374e108e7e4c ("x86/cpufeatures: Add the Virtual SPEC_CTRL feature") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Babu Moger Cc: Borislav Petkov Cc: Fenghua Yu Cc: Juergen Gross Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Ricardo Neri Cc: Sean Christopherson Cc: Thomas Gleixner Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cc96e26d69f7..ac37830ae941 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -84,7 +84,7 @@ /* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -236,6 +236,8 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -290,6 +292,8 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -336,6 +340,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -354,6 +359,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ @@ -374,6 +380,7 @@ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ From 71d7924b3e8acaca6a3b0fc3261170031ada3b70 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sun, 9 May 2021 10:29:10 -0300 Subject: [PATCH 71/72] tools headers UAPI: Sync perf_event.h with the kernel sources To pick up the changes in: 2b26f0aa004995f4 ("perf: Support only inheriting events if cloned with CLONE_THREAD") 2e498d0a74e5b88a ("perf: Add support for event removal on exec") 547b60988e631f74 ("perf: aux: Add flags for the buffer format") 55bcf6ef314ae8ba ("perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE") 7dde51767ca5339e ("perf: aux: Add CoreSight PMU buffer formats") 97ba62b278674293 ("perf: Add support for SIGTRAP on perf events") d0d1dd628527c77d ("perf core: Add PERF_COUNT_SW_CGROUP_SWITCHES event") Also change the expected sizeof(struct perf_event_attr) from 120 to 128 due to fields being added for the SIGTRAP changes. Addressing this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h' diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Cc: Kan Liang Cc: Marco Elver Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki K Poulose Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 26 ++++++++++++++++++++----- tools/perf/tests/attr/base-record | 2 +- tools/perf/tests/attr/base-stat | 2 +- tools/perf/tests/attr/system-wide-dummy | 2 +- 4 files changed, 24 insertions(+), 8 deletions(-) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 14332f4cf816..bf8143505c49 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -127,6 +127,7 @@ enum perf_sw_ids { PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, PERF_COUNT_SW_BPF_OUTPUT = 10, + PERF_COUNT_SW_CGROUP_SWITCHES = 11, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -326,6 +327,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -404,7 +406,10 @@ struct perf_event_attr { cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ build_id : 1, /* use build id in mmap2 events */ - __reserved_1 : 29; + inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ + remove_on_exec : 1, /* event is removed from task on exec */ + sigtrap : 1, /* send synchronous SIGTRAP on event */ + __reserved_1 : 26; union { __u32 wakeup_events; /* wakeup every n events */ @@ -456,6 +461,12 @@ struct perf_event_attr { __u16 __reserved_2; __u32 aux_sample_size; __u32 __reserved_3; + + /* + * User provided data if sigtrap=1, passed back to user via + * siginfo_t::si_perf, e.g. to permit user to identify the event. + */ + __u64 sig_data; }; /* @@ -1171,10 +1182,15 @@ enum perf_callchain_context { /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ + +/* CoreSight PMU AUX buffer formats */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 645009c08b3c..4a7b8deef3fd 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=120 +size=128 config=0 sample_period=* sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index b0f42c34882e..408164456530 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=120 +size=128 config=0 sample_period=0 sample_type=65536 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index eba723cc0d38..86a15dd359d9 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -7,7 +7,7 @@ cpu=* pid=-1 flags=8 type=1 -size=120 +size=128 config=9 sample_period=4000 sample_type=455 From 9b8a233bc294dd71d3c7d30692a78ab32f246a0f Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Fri, 30 Apr 2021 21:30:55 +0530 Subject: [PATCH 72/72] btrfs: handle transaction start error in btrfs_fileattr_set Add error handling in btrfs_fileattr_set in case of an error while starting a transaction. This fixes btrfs/232 which otherwise used to fail with below signature on Power. btrfs/232 [ 1119.474650] run fstests btrfs/232 at 2021-04-21 02:21:22 <...> [ 1366.638585] BUG: Unable to handle kernel data access on read at 0xffffffffffffff86 [ 1366.638768] Faulting instruction address: 0xc0000000009a5c88 cpu 0x0: Vector: 380 (Data SLB Access) at [c000000014f177b0] pc: c0000000009a5c88: btrfs_update_root_times+0x58/0xc0 lr: c0000000009a5c84: btrfs_update_root_times+0x54/0xc0 <...> pid = 24881, comm = fsstress btrfs_update_inode+0xa0/0x140 btrfs_fileattr_set+0x5d0/0x6f0 vfs_fileattr_set+0x2a8/0x390 do_vfs_ioctl+0x1290/0x1ac0 sys_ioctl+0x6c/0x120 system_call_exception+0x3d4/0x410 system_call_common+0xec/0x278 Fixes: 97fc29775487 ("btrfs: convert to fileattr") Signed-off-by: Ritesh Harjani Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ee1dbabb5d3c..98ecb70466bf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -259,6 +259,8 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, if (!fa->flags_valid) { /* 1 item for the inode */ trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); goto update_flags; }