From: Trond Myklebust trondmy@gmail.com
mainline inclusion from mainline-v5.5-rc1 commit a25e3726b32c746c0098125d4c7463bb84df72bb category: bugfix bugzilla: 27346 CVE: NA
-------------------------------------------------
The NFSv4.2 CLONE operation has implicit persistence requirements on the target file, since there is no protocol requirement that the client issue a separate operation to persist data. For that reason, we should call vfs_fsync_range() on the destination file after a successful call to vfs_clone_file_range().
Fixes: ffa0160a1039 ("nfsd: implement the NFSv4.2 CLONE operation") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: J. Bruce Fields bfields@redhat.com
Conflicts: fs/nfsd/nfs4proc.c fs/nfsd/vfs.c 42ec3d4c0218 ("vfs: make remap_file_range functions take and return bytes completed") 2e5dfc99f2e6 ("vfs: combine the clone and dedupe into a single remap_file_range")
Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Reviewed-by: zhangyi (F) yi.zhang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/nfsd/nfs4proc.c | 3 ++- fs/nfsd/vfs.c | 16 +++++++++++++--- fs/nfsd/vfs.h | 2 +- 3 files changed, 16 insertions(+), 5 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f35aa9f..1c3e6de 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1082,7 +1082,8 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh) goto out;
status = nfsd4_clone_file_range(src, clone->cl_src_pos, - dst, clone->cl_dst_pos, clone->cl_count); + dst, clone->cl_dst_pos, clone->cl_count, + EX_ISSYNC(cstate->current_fh.fh_export));
fput(dst); fput(src); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 80ceded..90e97c8 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -552,10 +552,20 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, #endif
__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, - u64 dst_pos, u64 count) + u64 dst_pos, u64 count, bool sync) { - return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, - count)); + int cloned; + + cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count); + if (cloned < 0) + return nfserrno(cloned); + if (sync) { + loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX; + int status = vfs_fsync_range(dst, dst_pos, dst_end, 0); + if (status < 0) + return nfserrno(status); + } + return 0; }
ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index db35124..02b0a14 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -58,7 +58,7 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); __be32 nfsd4_clone_file_range(struct file *, u64, struct file *, - u64, u64); + u64, u64, bool); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create_locked(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs,
From: Trond Myklebust trondmy@gmail.com
mainline inclusion from mainline-5.6-rc1 commit 57f64034966fb945fc958f95f0c51e47af590344 category: bugfix bugzilla: 30516 CVE: NA
-----------------------------------------------
vfs_clone_file_range() can modify the metadata on the source file too, so we need to commit that to stable storage as well.
Reported-by: Dave Chinner david@fromorbit.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Acked-by: Dave Chinner david@fromorbit.com Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Reviewed-by: zhangyi (F) yi.zhang@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/nfsd/vfs.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 90e97c8..ace9125 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -307,19 +307,25 @@ int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) * Commit metadata changes to stable storage. */ static int -commit_metadata(struct svc_fh *fhp) +commit_inode_metadata(struct inode *inode) { - struct inode *inode = d_inode(fhp->fh_dentry); const struct export_operations *export_ops = inode->i_sb->s_export_op;
- if (!EX_ISSYNC(fhp->fh_export)) - return 0; - if (export_ops->commit_metadata) return export_ops->commit_metadata(inode); return sync_inode_metadata(inode, 1); }
+static int +commit_metadata(struct svc_fh *fhp) +{ + struct inode *inode = d_inode(fhp->fh_dentry); + + if (!EX_ISSYNC(fhp->fh_export)) + return 0; + return commit_inode_metadata(inode); +} + /* * Go over the attributes and take care of the small differences between * NFS semantics and what Linux expects. @@ -562,6 +568,9 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, if (sync) { loff_t dst_end = count ? dst_pos + count - 1 : LLONG_MAX; int status = vfs_fsync_range(dst, dst_pos, dst_end, 0); + + if (!status) + status = commit_inode_metadata(file_inode(src)); if (status < 0) return nfserrno(status); }
From: Wen Yang wenyang@linux.alibaba.com
mainline inclusion from mainline-5.5-rc7 commit d3ac946ec9de10ec4b9718ad30703c5e077916a1 category: bugfix bugzilla: 28317 CVE: NA
------------------------------------------------- The two variables 'numerator' and 'denominator', though they are declared as long, they should actually be unsigned long (according to the implementation of the fprop_fraction_percpu() function)
And do_div() does a 64-by-32 division, while the divisor 'denominator' is unsigned long, thus 64-bit on 64-bit platforms. Hence the proper function to call is div64_ul().
Link: http://lkml.kernel.org/r/20200102081442.8273-3-wenyang@linux.alibaba.com Signed-off-by: Wen Yang wenyang@linux.alibaba.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Qian Cai cai@lca.pw Cc: Tejun Heo tj@kernel.org Cc: Jens Axboe axboe@kernel.dk Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit d3ac946ec9de10ec4b9718ad30703c5e077916a1) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/page-writeback.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 078f146..566df02 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -765,7 +765,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; - long numerator, denominator; + unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio;
/* @@ -776,7 +776,7 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; wb_thresh *= numerator; - do_div(wb_thresh, denominator); + wb_thresh = div64_ul(wb_thresh, denominator);
wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio);
From: Wen Yang wenyang@linux.alibaba.com
mainline inclusion from mainline-5.5-rc7 commit 0a5d1a7f64702c351d1f47ef159a0df8c71be0b0 category: bugfix bugzilla: 28317 CVE: NA
------------------------------------------------- Use div64_ul() instead of do_div() if the divisor is unsigned long, to avoid truncation to 32-bit on 64-bit platforms.
Link: http://lkml.kernel.org/r/20200102081442.8273-4-wenyang@linux.alibaba.com Signed-off-by: Wen Yang wenyang@linux.alibaba.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Qian Cai cai@lca.pw Cc: Tejun Heo tj@kernel.org Cc: Jens Axboe axboe@kernel.dk Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 0a5d1a7f64702c351d1f47ef159a0df8c71be0b0) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/page-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 566df02..43e8393 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1101,7 +1101,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb, bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { - do_div(bw, elapsed); + bw = div64_ul(bw, elapsed); avg = bw; goto out; }
From: David Rientjes rientjes@google.com
mainline inclusion from mainline-5.6-rc1 commit f42f25526502d851d0e3ca1e46297da8aafce8a7 category: bugfix bugzilla: 29954 CVE: NA
------------------------------------------------- If thp defrag setting "defer" is used and a newline is *not* used when writing to the sysfs file, this is interpreted as the "defer+madvise" option.
This is because we do prefix matching and if five characters are written without a newline, the current code ends up comparing to the first five bytes of the "defer+madvise" option and using that instead.
Use the more appropriate sysfs_streq() that handles the trailing newline for us. Since this doubles as a nice cleanup, do it in enabled_store() as well.
The current implementation relies on prefix matching: the number of bytes compared is either the number of bytes written or the length of the option being compared. With a newline, "defer\n" does not match "defer+"madvise"; without a newline, however, "defer" is considered to match "defer+madvise" (prefix matching is only comparing the first five bytes). End result is that writing "defer" is broken unless it has an additional trailing character.
This means that writing "madv" in the past would match and set "madvise". With strict checking, that no longer is the case but it is unlikely anybody is currently doing this.
Link: http://lkml.kernel.org/r/alpine.DEB.2.21.2001171411020.56385@chino.kir.corp.... Fixes: 21440d7eb904 ("mm, thp: add new defer+madvise defrag option") Signed-off-by: David Rientjes rientjes@google.com Suggested-by: Andrew Morton akpm@linux-foundation.org Acked-by: Vlastimil Babka vbabka@suse.cz Cc: Mel Gorman mgorman@techsingularity.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit f42f25526502d851d0e3ca1e46297da8aafce8a7) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/huge_memory.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5bb93cf..eeb0611 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -173,16 +173,13 @@ static ssize_t enabled_store(struct kobject *kobj, { ssize_t ret = count;
- if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else @@ -246,32 +243,27 @@ static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer+madvise", buf, - min(sizeof("defer+madvise")-1, count))) { + } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { + } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
From: Wei Yang richardw.yang@linux.intel.com
mainline inclusion from mainline-5.6-rc1 commit cb829624867b5ab10bc6a7036d183b1b82bfe9f8 category: bugfix bugzilla: 29957 CVE: NA
------------------------------------------------- The page could be a tail page, if this is the case, this BUG_ON will never be triggered.
Link: http://lkml.kernel.org/r/20200110032610.26499-1-richardw.yang@linux.intel.co... Fixes: e9b61f19858a ("thp: reintroduce split_huge_page()")
Signed-off-by: Wei Yang richardw.yang@linux.intel.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit cb829624867b5ab10bc6a7036d183b1b82bfe9f8) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/huge_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index eeb0611..1469983 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2653,7 +2653,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) unsigned long flags; pgoff_t end;
- VM_BUG_ON_PAGE(is_huge_zero_page(page), page); + VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page);
From: Steven Price steven.price@arm.com
mainline inclusion from mainline-5.6-rc1 commit c02a98753e0a36ba65a05818626fa6adeb4e7c97 category: bugfix bugzilla: 30160 CVE: NA
------------------------------------------------- If walk_pte_range() is called with a 'end' argument that is beyond the last page of memory (e.g. ~0UL) then the comparison between 'addr' and 'end' will always fail and the loop will be infinite. Instead change the comparison to >= while accounting for overflow.
Link: http://lkml.kernel.org/r/20191218162402.45610-15-steven.price@arm.com Signed-off-by: Steven Price steven.price@arm.com Cc: Albert Ou aou@eecs.berkeley.edu Cc: Alexandre Ghiti alex@ghiti.fr Cc: Andy Lutomirski luto@kernel.org Cc: Ard Biesheuvel ard.biesheuvel@linaro.org Cc: Arnd Bergmann arnd@arndb.de Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Borislav Petkov bp@alien8.de Cc: Catalin Marinas catalin.marinas@arm.com Cc: Christian Borntraeger borntraeger@de.ibm.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: David S. Miller davem@davemloft.net Cc: Heiko Carstens heiko.carstens@de.ibm.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: Ingo Molnar mingo@redhat.com Cc: James Hogan jhogan@kernel.org Cc: James Morse james.morse@arm.com Cc: Jerome Glisse jglisse@redhat.com Cc: "Liang, Kan" kan.liang@linux.intel.com Cc: Mark Rutland mark.rutland@arm.com Cc: Michael Ellerman mpe@ellerman.id.au Cc: Paul Burton paul.burton@mips.com Cc: Paul Mackerras paulus@samba.org Cc: Paul Walmsley paul.walmsley@sifive.com Cc: Peter Zijlstra peterz@infradead.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Russell King linux@armlinux.org.uk Cc: Thomas Gleixner tglx@linutronix.de Cc: Vasily Gorbik gor@linux.ibm.com Cc: Vineet Gupta vgupta@synopsys.com Cc: Will Deacon will@kernel.org Cc: Zong Li zong.li@sifive.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit c02a98753e0a36ba65a05818626fa6adeb4e7c97) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/pagewalk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/pagewalk.c b/mm/pagewalk.c index c3084ff..3c0930d 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -15,9 +15,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; - addr += PAGE_SIZE; - if (addr == end) + if (addr >= end - PAGE_SIZE) break; + addr += PAGE_SIZE; pte++; }
From: Vasily Averin vvs@virtuozzo.com
mainline inclusion from mainline-5.6-rc3 commit 75866af62b439859d5146b7093ceb6b482852683 category: bugfix bugzilla: 30952 CVE: NA
------------------------------------------------- for_each_mem_cgroup() increases css reference counter for memory cgroup and requires to use mem_cgroup_iter_break() if the walk is cancelled.
Link: http://lkml.kernel.org/r/c98414fb-7e1f-da0f-867a-9340ec4bd30b@virtuozzo.com Fixes: 0a4465d34028 ("mm, memcg: assign memcg-aware shrinkers bitmap to memcg") Signed-off-by: Vasily Averin vvs@virtuozzo.com Acked-by: Kirill Tkhai ktkhai@virtuozzo.com Acked-by: Michal Hocko mhocko@suse.com Reviewed-by: Roman Gushchin guro@fb.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Vladimir Davydov vdavydov.dev@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 75866af62b439859d5146b7093ceb6b482852683) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Reviewed-by: Jing Xiangfeng jingxiangfeng@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/memcontrol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5d62c1f..9849166 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -419,8 +419,10 @@ int memcg_expand_shrinker_maps(int new_id) if (mem_cgroup_is_root(memcg)) continue; ret = memcg_expand_one_shrinker_map(memcg, size, old_size); - if (ret) + if (ret) { + mem_cgroup_iter_break(NULL, memcg); goto unlock; + } } unlock: if (!ret)
From: Theodore Ts'o tytso@mit.edu
mainline inclusion from mainline-5.6-rc1 commit d4c5e960bf202d99ec9a6922ad387eafb798b848 category: bugfix bugzilla: 29909 CVE: NA ---------------------------
Linus observed that an allmodconfig build which does a lot of stat(2) calls that ext4_getattr() was a noticeable (1%) amount of CPU time, due to the cache line for i_extra_isize getting pulled in. Since the normal stat system call doesn't return btime, it's a complete waste. So only calculate btime when it is explicitly requested.
[ Fixed to check against request_mask instead of query_flags. ]
Link: https://lore.kernel.org/r/CAHk-=wivmk_j6KbTX+Er64mLrG8abXZo0M10PNdAnHc8fWXfs... Reported-by: Linus Torvalds torvalds@linux-foundation.org Reviewed-by: Andreas Dilger adilger@dilger.ca Signed-off-by: Theodore Ts'o tytso@mit.edu
Signed-off-by: zhangyi (F) yi.zhang@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7c57a2f..0d9181d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5733,7 +5733,8 @@ int ext4_getattr(const struct path *path, struct kstat *stat, struct ext4_inode_info *ei = EXT4_I(inode); unsigned int flags;
- if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { + if ((request_mask & STATX_BTIME) && + EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
-
Yang Yingliang