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

[PATCH] xen/netfront: tolerate frags with no data

by Juergen Gross

At least old Xen net backends seem to send frags with no real data sometimes. In case such a fragment happens to occur with the frag limit already reached the frontend will BUG currently even if this situation is easily recoverable. Modify the BUG_ON() condition accordingly. Cc: stable(a)vger.kernel.org Tested-by: Dietmar Hahn <dietmar.hahn(a)ts.fujitsu.com> Signed-off-by: Juergen Gross <jgross(a)suse.com> --- drivers/net/xen-netfront.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f17f602e6171..5b97cc946d70 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -905,7 +905,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; - BUG_ON(pull_to <= skb_headlen(skb)); + BUG_ON(pull_to < skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { -- 2.16.4

7 years

2
2
0 0

[PATCH] f2fs: fix missing unlock(sbi->gc_mutex)

by Jaegeuk Kim

This fixes missing unlock call. Cc: <stable(a)vger.kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> --- fs/f2fs/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b79677639108..2689a2cb56cc 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1462,6 +1462,9 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) while (!f2fs_time_over(sbi, DISABLE_TIME)) { err = f2fs_gc(sbi, true, false, NULL_SEGNO); + + /* f2fs_gc guarantees unlock gc_mutex */ + mutex_lock(&sbi->gc_mutex); if (err == -ENODATA) break; if (err && err != -EAGAIN) { -- 2.19.0.605.g01d371f741-goog

7 years

2
3
0 0

[PATCH] dm zoned: Fix target BIO completion handling

by Damien Le Moal

commit d57f9da890696af1484f4a47f7f123560197865a upstream. struct bioctx includes the ref refcount_t to track the number of I/O fragments used to process a target BIO as well as ensure that the zone of the BIO is kept in the active state throughout the lifetime of the BIO. However, since decrementing of this reference count is done in the target .end_io method, the function bio_endio() must be called multiple times for read and write target BIOs, which causes problems with the value of the __bi_remaining struct bio field for chained BIOs (e.g. the clone BIO passed by dm core is large and splits into fragments by the block layer), resulting in incorrect values and inconsistencies with the BIO_CHAIN flag setting. This is turn triggers the BUG_ON() call: BUG_ON(atomic_read(&bio->__bi_remaining) <= 0); in bio_remaining_done() called from bio_endio(). Fix this ensuring that bio_endio() is called only once for any target BIO by always using internal clone BIOs for processing any read or write target BIO. This allows reference counting using the target BIO context counter to trigger the target BIO completion bio_endio() call once all data, metadata and other zone work triggered by the BIO complete. Overall, this simplifies the code too as the target .end_io becomes unnecessary and differences between read and write BIO issuing and completion processing disappear. Fixes: 3b1a94c88b79 ("dm zoned: drive-managed zoned block device target") Cc: stable(a)vger.kernel.org #4.14 Signed-off-by: Damien Le Moal <damien.lemoal(a)wdc.com> Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> --- drivers/md/dm-zoned-target.c | 122 +++++++++++------------------------ 1 file changed, 38 insertions(+), 84 deletions(-) diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index ba6b0a90ecfb..532bfce7f072 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -20,7 +20,6 @@ struct dmz_bioctx { struct dm_zone *zone; struct bio *bio; atomic_t ref; - blk_status_t status; }; /* @@ -78,65 +77,66 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK) - bioctx->status = status; - bio_endio(bio); + if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) + bio->bi_status = status; + + if (atomic_dec_and_test(&bioctx->ref)) { + struct dm_zone *zone = bioctx->zone; + + if (zone) { + if (bio->bi_status != BLK_STS_OK && + bio_op(bio) == REQ_OP_WRITE && + dmz_is_seq(zone)) + set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); + dmz_deactivate_zone(zone); + } + bio_endio(bio); + } } /* - * Partial clone read BIO completion callback. This terminates the + * Completion callback for an internally cloned target BIO. This terminates the * target BIO when there are no more references to its context. */ -static void dmz_read_bio_end_io(struct bio *bio) +static void dmz_clone_endio(struct bio *clone) { - struct dmz_bioctx *bioctx = bio->bi_private; - blk_status_t status = bio->bi_status; + struct dmz_bioctx *bioctx = clone->bi_private; + blk_status_t status = clone->bi_status; - bio_put(bio); + bio_put(clone); dmz_bio_endio(bioctx->bio, status); } /* - * Issue a BIO to a zone. The BIO may only partially process the + * Issue a clone of a target BIO. The clone may only partially process the * original target BIO. */ -static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) +static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, + struct bio *bio, sector_t chunk_block, + unsigned int nr_blocks) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - sector_t sector; struct bio *clone; - /* BIO remap sector */ - sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - - /* If the read is not partial, there is no need to clone the BIO */ - if (nr_blocks == dmz_bio_blocks(bio)) { - /* Setup and submit the BIO */ - bio->bi_iter.bi_sector = sector; - atomic_inc(&bioctx->ref); - generic_make_request(bio); - return 0; - } - - /* Partial BIO: we need to clone the BIO */ clone = bio_clone_fast(bio, GFP_NOIO, dmz->bio_set); if (!clone) return -ENOMEM; - /* Setup the clone */ - clone->bi_iter.bi_sector = sector; + bio_set_dev(clone, dmz->dev->bdev); + clone->bi_iter.bi_sector = + dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT; - clone->bi_end_io = dmz_read_bio_end_io; + clone->bi_end_io = dmz_clone_endio; clone->bi_private = bioctx; bio_advance(bio, clone->bi_iter.bi_size); - /* Submit the clone */ atomic_inc(&bioctx->ref); generic_make_request(clone); + if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) + zone->wp_block += nr_blocks; + return 0; } @@ -214,7 +214,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks) { /* Valid blocks found: read them */ nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block); - ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks); if (ret) return ret; chunk_block += nr_blocks; @@ -228,25 +228,6 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, return 0; } -/* - * Issue a write BIO to a zone. - */ -static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - /* Setup and submit the BIO */ - bio_set_dev(bio, dmz->dev->bdev); - bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - atomic_inc(&bioctx->ref); - generic_make_request(bio); - - if (dmz_is_seq(zone)) - zone->wp_block += nr_blocks; -} - /* * Write blocks directly in a data zone, at the write pointer. * If a buffer zone is assigned, invalidate the blocks written @@ -265,7 +246,9 @@ static int dmz_handle_direct_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the data zone and invalidate @@ -301,7 +284,9 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the buffer zone @@ -600,7 +585,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) bioctx->zone = NULL; bioctx->bio = bio; atomic_set(&bioctx->ref, 1); - bioctx->status = BLK_STS_OK; /* Set the BIO pending in the flush list */ if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) { @@ -623,35 +607,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -/* - * Completed target BIO processing. - */ -static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - if (bioctx->status == BLK_STS_OK && *error) - bioctx->status = *error; - - if (!atomic_dec_and_test(&bioctx->ref)) - return DM_ENDIO_INCOMPLETE; - - /* Done */ - bio->bi_status = bioctx->status; - - if (bioctx->zone) { - struct dm_zone *zone = bioctx->zone; - - if (*error && bio_op(bio) == REQ_OP_WRITE) { - if (dmz_is_seq(zone)) - set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); - } - dmz_deactivate_zone(zone); - } - - return DM_ENDIO_DONE; -} - /* * Get zoned device information. */ @@ -946,7 +901,6 @@ static struct target_type dmz_type = { .ctr = dmz_ctr, .dtr = dmz_dtr, .map = dmz_map, - .end_io = dmz_end_io, .io_hints = dmz_io_hints, .prepare_ioctl = dmz_prepare_ioctl, .postsuspend = dmz_suspend, -- 2.19.2

7 years

1
0
0 0

Re: [PATCH 1/3] x86/pkeys: properly copy pkey state at fork()

by Thomas Gleixner

On Wed, 12 Dec 2018, Dave Hansen wrote: > From: Dave Hansen <dave.hansen(a)linux.intel.com> > > Memory protection key behavior should be the same in a child as it was > in the parent before a fork. But, there is a bug that resets the > state in the child at fork instead of preserving it. > > Our creation of new mm's is a bit convoluted. At fork(), the code > does: > > 1. memcpy() the parent mm to initialize child > 2. mm_init() to initalize some select stuff stuff > 3. dup_mmap() to create true copies that memcpy() > did not do right. > > For pkeys, we need to preserve two bits of state across a fork: > 'execute_only_pkey' and 'pkey_allocation_map'. Those are preserved by > the memcpy(), which I thought did the right thing. But, mm_init() > calls init_new_context(), which I thought was *only* for execve()-time > and overwrites 'execute_only_pkey' and 'pkey_allocation_map' with > "new" values. But, alas, init_new_context() is used at execve() and > fork(). > > The result is that, after a fork(), the child's pkey state ends up > looking like it does after an execve(), which is totally wrong. pkeys > that are already allocated can be allocated again, for instance. > > To fix this, add code called by dup_mmap() to copy the pkey state from > parent to child explicitly. Also add a comment above init_new_context() > to make it more clear to the next poor sod what this code is used for. > > Fixes: e8c24d3a23a ("x86/pkeys: Allocation/free syscalls") > Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> > Cc: Thomas Gleixner <tglx(a)linutronix.de> > Cc: Ingo Molnar <mingo(a)redhat.com> > Cc: Borislav Petkov <bp(a)alien8.de> > Cc: "H. Peter Anvin" <hpa(a)zytor.com> > Cc: x86(a)kernel.org > Cc: Dave Hansen <dave.hansen(a)linux.intel.com> > Cc: Peter Zijlstra <peterz(a)infradead.org> > Cc: Michael Ellerman <mpe(a)ellerman.id.au> > Cc: Will Deacon <will.deacon(a)arm.com> > Cc: Andy Lutomirski <luto(a)kernel.org> > Cc: Joerg Roedel <jroedel(a)suse.de> > Cc: stable(a)vger.kernel.org Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de>

7 years

1
0
0 0

[PATCH STABLE v4.9 00/10] Backport for "cache line starvation on x86

by Sebastian Andrzej Siewior

[ resending without broken headers ] this is a backport of commit 7aa54be297655 ("locking/qspinlock, x86: Provide liveness guarantee") for the v4.9 stable tree. For the v4.4 tree the ARCH_USE_QUEUED_SPINLOCKS option got disabled on x86. For v4.9 it has been decided to do a minimal backport of the final fix (including all its dependencies). With this backport I can't reproduce the issue in the latest v4.9-RT tree. I was able to boot (and use) an arm64 box with these patches so it is not broken in an abvious way. Sebastian

7 years

2
11
0 0

[PATCH 2/3] hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race

by Mike Kravetz

hugetlbfs page faults can race with truncate and hole punch operations. Current code in the page fault path attempts to handle this by 'backing out' operations if we encounter the race. One obvious omission in the current code is removing a page newly added to the page cache. This is pretty straight forward to address, but there is a more subtle and difficult issue of backing out hugetlb reservations. To handle this correctly, the 'reservation state' before page allocation needs to be noted so that it can be properly backed out. There are four distinct possibilities for reservation state: shared/reserved, shared/no-resv, private/reserved and private/no-resv. Backing out a reservation may require memory allocation which could fail so that needs to be taken into account as well. Instead of writing the required complicated code for this rare occurrence, just eliminate the race. i_mmap_rwsem is now held in read mode for the duration of page fault processing. Hold i_mmap_rwsem longer in truncation and hold punch code to cover the call to remove_inode_hugepages. Cc: <stable(a)vger.kernel.org> Fixes: ebed4bfc8da8 ("hugetlb: fix absurd HugePages_Rsvd") Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> --- fs/hugetlbfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 32920a10100e..3244147fc42b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -505,8 +505,8 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); - i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); + i_mmap_unlock_write(mapping); return 0; } @@ -540,8 +540,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); - i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, hole_start, hole_end); + i_mmap_unlock_write(mapping); inode_unlock(inode); } -- 2.17.2

7 years

3
5
0 0

[PATCH STABLE v4.19 0/2] Backport for "cache line starvation on x86"

by Sebastian Andrzej Siewior

this is a backport of commit 7aa54be297655 ("locking/qspinlock, x86: Provide liveness guarantee") for the v4.19 stable tree. Initially I assumed that this was merged late in v4.19-rc but actually it is just part v4.20-rc1. For v4.19, most things are already in the tree. The GEN_BINARY_RMWcc macro is still "old" and I skipped the documentation update. Sebastian

7 years

2
4
0 0

[to-be-updated] hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: hugetlbfs: remove unnecessary code after i_mmap_rwsem synchronization has been removed from the -mm tree. Its filename was hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Mike Kravetz <mike.kravetz(a)oracle.com> Subject: hugetlbfs: remove unnecessary code after i_mmap_rwsem synchronization After expanding i_mmap_rwsem use for better shared pmd and page fault/ truncation synchronization, remove code that is no longer necessary. Link: http://lkml.kernel.org/r/20181203200850.6460-4-mike.kravetz@oracle.com Fixes: ebed4bfc8da8 ("hugetlb: fix absurd HugePages_Rsvd") Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Davidlohr Bueso <dave(a)stgolabs.net> Cc: Hugh Dickins <hughd(a)google.com> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com> Cc: Prakash Sangappa <prakash.sangappa(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/hugetlbfs/inode.c | 46 +++++++++++++---------------------------- mm/hugetlb.c | 21 ++++++++---------- 2 files changed, 25 insertions(+), 42 deletions(-) --- a/fs/hugetlbfs/inode.c~hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization +++ a/fs/hugetlbfs/inode.c @@ -383,17 +383,16 @@ hugetlb_vmdelete_list(struct rb_root_cac * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. Page faults can not race with truncation - * in this routine. hugetlb_no_page() prevents page faults in the - * truncated range. It checks i_size before allocation, and again after - * with the page table lock for the page held. The same lock must be - * acquired to unmap a page. + * maps and global counts. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. Page faults can race with hole punch. - * This is indicated if we find a mapped page. + * pages are not modified. + * + * Callers of this routine must hold the i_mmap_rwsem in write mode to prevent + * races with page faults. + * * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -423,32 +422,14 @@ static void remove_inode_hugepages(struc for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; - u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, current->mm, - &pseudo_vma, - mapping, index, 0); - mutex_lock(&hugetlb_fault_mutex_table[hash]); - /* - * If page is mapped, it was faulted in after being - * unmapped in caller. Unmap (again) now after taking - * the fault mutex. The mutex will prevent faults - * until we finish removing the page. - * - * This race can only happen in the hole punch case. - * Getting here in a truncate operation is a bug. + * A mapped page is impossible as callers should unmap + * all references before calling. And, i_mmap_rwsem + * prevents the creation of additional mappings. */ - if (unlikely(page_mapped(page))) { - BUG_ON(truncate_op); - - i_mmap_lock_write(mapping); - hugetlb_vmdelete_list(&mapping->i_mmap, - index * pages_per_huge_page(h), - (index + 1) * pages_per_huge_page(h)); - i_mmap_unlock_write(mapping); - } + VM_BUG_ON(page_mapped(page)); lock_page(page); /* @@ -470,7 +451,6 @@ static void remove_inode_hugepages(struc } unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); } huge_pagevec_release(&pvec); cond_resched(); @@ -624,7 +604,11 @@ static long hugetlbfs_fallocate(struct f /* addr is the offset within the file (zero based) */ addr = index * hpage_size; - /* mutex taken here, fault path and hole punch */ + /* + * fault mutex taken here, protects against fault path + * and hole punch. inode_lock previously taken protects + * against truncation. + */ hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); --- a/mm/hugetlb.c~hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization +++ a/mm/hugetlb.c @@ -3761,16 +3761,16 @@ static vm_fault_t hugetlb_no_page(struct } /* - * Use page lock to guard against racing truncation - * before we get page_table_lock. + * We can not race with truncation due to holding i_mmap_rwsem. + * Check once here for faults beyond end of file. */ + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto out; + retry: page = find_lock_page(mapping, idx); if (!page) { - size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) - goto out; - /* * Check for page in userfault range */ @@ -3860,9 +3860,6 @@ retry: } ptl = huge_pte_lock(h, mm, ptep); - size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) - goto backout; ret = 0; if (!huge_pte_none(huge_ptep_get(ptep))) @@ -3965,8 +3962,10 @@ vm_fault_t hugetlb_fault(struct mm_struc /* * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold - * until finished with ptep. This prevents huge_pmd_unshare from - * being called elsewhere and making the ptep no longer valid. + * until finished with ptep. This serves two purposes: + * 1) It prevents huge_pmd_unshare from being called elsewhere + * and making the ptep no longer valid. + * 2) It synchronizes us with file truncation. * * ptep could have already be assigned via huge_pte_offset. That * is OK, as huge_pte_alloc will return the same value unless _ Patches currently in -mm which might be from mike.kravetz(a)oracle.com are

7 years

1
0
0 0

[to-be-updated] hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race has been removed from the -mm tree. Its filename was hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Mike Kravetz <mike.kravetz(a)oracle.com> Subject: hugetlbfs: Use i_mmap_rwsem to fix page fault/truncate race hugetlbfs page faults can race with truncate and hole punch operations. Current code in the page fault path attempts to handle this by 'backing out' operations if we encounter the race. One obvious omission in the current code is removing a page newly added to the page cache. This is pretty straight forward to address, but there is a more subtle and difficult issue of backing out hugetlb reservations. To handle this correctly, the 'reservation state' before page allocation needs to be noted so that it can be properly backed out. There are four distinct possibilities for reservation state: shared/reserved, shared/no-resv, private/reserved and private/no-resv. Backing out a reservation may require memory allocation which could fail so that needs to be taken into account as well. Instead of writing the required complicated code for this rare occurrence, just eliminate the race. i_mmap_rwsem is now held in read mode for the duration of page fault processing. Hold i_mmap_rwsem longer in truncation and hold punch code to cover the call to remove_inode_hugepages. Link: http://lkml.kernel.org/r/20181203200850.6460-3-mike.kravetz@oracle.com Fixes: ebed4bfc8da8 ("hugetlb: fix absurd HugePages_Rsvd") Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Davidlohr Bueso <dave(a)stgolabs.net> Cc: Hugh Dickins <hughd(a)google.com> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com> Cc: Prakash Sangappa <prakash.sangappa(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/hugetlbfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/fs/hugetlbfs/inode.c~hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race +++ a/fs/hugetlbfs/inode.c @@ -505,8 +505,8 @@ static int hugetlb_vmtruncate(struct ino i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); - i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); + i_mmap_unlock_write(mapping); return 0; } @@ -540,8 +540,8 @@ static long hugetlbfs_punch_hole(struct hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); - i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, hole_start, hole_end); + i_mmap_unlock_write(mapping); inode_unlock(inode); } _ Patches currently in -mm which might be from mike.kravetz(a)oracle.com are hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization.patch

7 years

1
0
0 0

[to-be-updated] hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization.patch removed from -mm tree

by akpm＠linux-foundation.org

The patch titled Subject: hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization has been removed from the -mm tree. Its filename was hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Mike Kravetz <mike.kravetz(a)oracle.com> Subject: hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization Patch series "hugetlbfs: use i_mmap_rwsem for better synchronization". These patches are a follow up to the RFC, http://lkml.kernel.org/r/20181024045053.1467-1-mike.kravetz@oracle.com Comments made by Naoya were addressed. There are two primary issues addressed here: 1) For shared pmds, huge PE pointers returned by huge_pte_alloc can become invalid via a call to huge_pmd_unshare by another thread. 2) hugetlbfs page faults can race with truncation causing invalid global reserve counts and state. Both issues are addressed by expanding the use of i_mmap_rwsem. These issues have existed for a long time. They can be recreated with a test program that causes page fault/truncation races. For simple mappings, this results in a negative HugePages_Rsvd count. If racing with mappings that contain shared pmds, we can hit "BUG at fs/hugetlbfs/inode.c:444!" or Oops! as the result of an invalid memory reference. I broke up the larger RFC into separate patches addressing each issue. Hopefully, this is easier to understand/review. This patch (of 3): While looking at BUGs associated with invalid huge page map counts, it was discovered and observed that a huge pte pointer could become 'invalid' and point to another task's page table. Consider the following: A task takes a page fault on a shared hugetlbfs file and calls huge_pte_alloc to get a ptep. Suppose the returned ptep points to a shared pmd. Now, another task truncates the hugetlbfs file. As part of truncation, it unmaps everyone who has the file mapped. If the range being truncated is covered by a shared pmd, huge_pmd_unshare will be called. For all but the last user of the shared pmd, huge_pmd_unshare will clear the pud pointing to the pmd. If the task in the middle of the page fault is not the last user, the ptep returned by huge_pte_alloc now points to another task's page table or worse. This leads to bad things such as incorrect page map/reference counts or invalid memory references. To fix, expand the use of i_mmap_rwsem as follows: - i_mmap_rwsem is held in read mode whenever huge_pmd_share is called. huge_pmd_share is only called via huge_pte_alloc, so callers of huge_pte_alloc take i_mmap_rwsem before calling. In addition, callers of huge_pte_alloc continue to hold the semaphore until finished with the ptep. - i_mmap_rwsem is held in write mode whenever huge_pmd_unshare is called. Link: http://lkml.kernel.org/r/20181203200850.6460-2-mike.kravetz@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com> Cc: "Aneesh Kumar K . V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Davidlohr Bueso <dave(a)stgolabs.net> Cc: Prakash Sangappa <prakash.sangappa(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 70 ++++++++++++++++++++++++++++++++---------- mm/memory-failure.c | 14 +++++++- mm/migrate.c | 13 +++++++ mm/rmap.c | 3 + mm/userfaultfd.c | 11 +++++- 5 files changed, 91 insertions(+), 20 deletions(-) --- a/mm/hugetlb.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization +++ a/mm/hugetlb.c @@ -3240,6 +3240,7 @@ int copy_hugetlb_page_range(struct mm_st int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); + struct address_space *mapping = vma->vm_file->f_mapping; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ int ret = 0; @@ -3253,11 +3254,23 @@ int copy_hugetlb_page_range(struct mm_st for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; + src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; + + /* + * i_mmap_rwsem must be held to call huge_pte_alloc. + * Continue to hold until finished with dst_pte, otherwise + * it could go away if part of a shared pmd. + * + * Technically, i_mmap_rwsem is only needed in the non-cow + * case as cow mappings are not shared. + */ + i_mmap_lock_read(mapping); dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) { + i_mmap_unlock_read(mapping); ret = -ENOMEM; break; } @@ -3272,8 +3285,10 @@ int copy_hugetlb_page_range(struct mm_st * after taking the lock below. */ dst_entry = huge_ptep_get(dst_pte); - if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) { + i_mmap_unlock_read(mapping); continue; + } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); @@ -3322,6 +3337,8 @@ int copy_hugetlb_page_range(struct mm_st } spin_unlock(src_ptl); spin_unlock(dst_ptl); + + i_mmap_unlock_read(mapping); } if (cow) @@ -3773,14 +3790,18 @@ retry: }; /* - * hugetlb_fault_mutex must be dropped before - * handling userfault. Reacquire after handling - * fault to make calling code simpler. + * hugetlb_fault_mutex and i_mmap_rwsem must be + * dropped before handling userfault. Reacquire + * after handling fault to make calling code simpler. */ hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr); mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + ret = handle_userfault(&vmf, VM_UFFD_MISSING); + + i_mmap_lock_read(mapping); mutex_lock(&hugetlb_fault_mutex_table[hash]); goto out; } @@ -3928,6 +3949,11 @@ vm_fault_t hugetlb_fault(struct mm_struc ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { + /* + * Since we hold no locks, ptep could be stale. That is + * OK as we are only making decisions based on content and + * not actually modifying content here. + */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { migration_entry_wait_huge(vma, mm, ptep); @@ -3935,20 +3961,31 @@ vm_fault_t hugetlb_fault(struct mm_struc } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); - } else { - ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; } + /* + * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold + * until finished with ptep. This prevents huge_pmd_unshare from + * being called elsewhere and making the ptep no longer valid. + * + * ptep could have already be assigned via huge_pte_offset. That + * is OK, as huge_pte_alloc will return the same value unless + * something changed. + */ mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, haddr); + i_mmap_lock_read(mapping); + ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); + if (!ptep) { + i_mmap_unlock_read(mapping); + return VM_FAULT_OOM; + } /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ + idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -4036,6 +4073,7 @@ out_ptl: } out_mutex: mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and @@ -4640,10 +4678,12 @@ void adjust_range_if_pmd_sharing_possibl * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the - * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_rwsem section - otherwise - * racing tasks could either miss the sharing (see huge_pte_offset) or select a - * bad pmd for sharing. + * code much cleaner. + * + * This routine must be called with i_mmap_rwsem held in at least read mode. + * For hugetlbfs, this prevents removal of any page table entries associated + * with the address space. This is important as we are setting up sharing + * based on existing page table entries (mappings). */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { @@ -4660,7 +4700,6 @@ pte_t *huge_pmd_share(struct mm_struct * if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_lock_write(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; @@ -4690,7 +4729,6 @@ pte_t *huge_pmd_share(struct mm_struct * spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_unlock_write(mapping); return pte; } @@ -4701,7 +4739,7 @@ out: * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * - * called with page table lock held. + * Called with page table lock held and i_mmap_rwsem held in write mode. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user --- a/mm/memory-failure.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization +++ a/mm/memory-failure.c @@ -1028,7 +1028,19 @@ static bool hwpoison_user_mappings(struc if (kill) collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); - unmap_success = try_to_unmap(hpage, ttu); + if (!PageHuge(hpage)) { + unmap_success = try_to_unmap(hpage, ttu); + } else { + /* + * For hugetlb pages, try_to_unmap could potentially call + * huge_pmd_unshare. Because of this, take semaphore in + * write mode here and set TTU_RMAP_LOCKED to indicate we + * have taken the lock at this higer level. + */ + i_mmap_lock_write(mapping); + unmap_success = try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); + i_mmap_unlock_write(mapping); + } if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); --- a/mm/migrate.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization +++ a/mm/migrate.c @@ -1297,8 +1297,19 @@ static int unmap_and_move_huge_page(new_ goto put_anon; if (page_mapped(hpage)) { + struct address_space *mapping = page_mapping(hpage); + + /* + * try_to_unmap could potentially call huge_pmd_unshare. + * Because of this, take semaphore in write mode here and + * set TTU_RMAP_LOCKED to let lower levels know we have + * taken the lock. + */ + i_mmap_lock_write(mapping); try_to_unmap(hpage, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| + TTU_RMAP_LOCKED); + i_mmap_unlock_write(mapping); page_was_mapped = 1; } --- a/mm/rmap.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization +++ a/mm/rmap.c @@ -1374,6 +1374,9 @@ static bool try_to_unmap_one(struct page /* * If sharing is possible, start and end will be adjusted * accordingly. + * + * If called for a huge page, caller must hold i_mmap_rwsem + * in write mode as it is possible to call huge_pmd_unshare. */ adjust_range_if_pmd_sharing_possible(vma, &start, &end); } --- a/mm/userfaultfd.c~hugetlbfs-use-i_mmap_rwsem-for-more-pmd-sharing-synchronization +++ a/mm/userfaultfd.c @@ -267,10 +267,14 @@ retry: VM_BUG_ON(dst_addr & ~huge_page_mask(h)); /* - * Serialize via hugetlb_fault_mutex + * Serialize via i_mmap_rwsem and hugetlb_fault_mutex. + * i_mmap_rwsem ensures the dst_pte remains valid even + * in the case of shared pmds. fault mutex prevents + * races with other faulting threads. */ - idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; + i_mmap_lock_read(mapping); + idx = linear_page_index(dst_vma, dst_addr); hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping, idx, dst_addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -279,6 +283,7 @@ retry: dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); goto out_unlock; } @@ -286,6 +291,7 @@ retry: dst_pteval = huge_ptep_get(dst_pte); if (!huge_pte_none(dst_pteval)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); goto out_unlock; } @@ -293,6 +299,7 @@ retry: dst_addr, src_addr, &page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); vm_alloc_shared = vm_shared; cond_resched(); _ Patches currently in -mm which might be from mike.kravetz(a)oracle.com are hugetlbfs-use-i_mmap_rwsem-to-fix-page-fault-truncate-race.patch hugetlbfs-remove-unnecessary-code-after-i_mmap_rwsem-synchronization.patch

7 years

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror