From 667b8a37f34b39f752f59f4808762bd5c7688a71 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 3 May 2017 14:51:38 -0700 Subject: fs/ocfs2/cluster: use setup_timer Use setup_timer() instead of init_timer() to simplify the code. Link: http://lkml.kernel.org/r/5e75bf07beb91e092d5aa36c36769949a480456a.1489060564.git.geliangtang@gmail.com Signed-off-by: Geliang Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 5b51c31c892d..a4a6ba23b9a6 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -450,9 +450,8 @@ static struct o2net_sock_container *sc_alloc(struct o2nm_node *node) INIT_WORK(&sc->sc_shutdown_work, o2net_shutdown_sc); INIT_DELAYED_WORK(&sc->sc_keepalive_work, o2net_sc_send_keep_req); - init_timer(&sc->sc_idle_timeout); - sc->sc_idle_timeout.function = o2net_idle_timer; - sc->sc_idle_timeout.data = (unsigned long)sc; + setup_timer(&sc->sc_idle_timeout, o2net_idle_timer, + (unsigned long)sc); sclog(sc, "alloced\n"); -- cgit v1.2.3 From 33496c3c3d7b88dcbe5e55aa01288b05646c6aca Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Wed, 3 May 2017 14:51:41 -0700 Subject: ocfs2: o2hb: revert hb threshold to keep compatible Configfs is the interface for ocfs2-tools to set configure to kernel and $configfs_dir/cluster/$clustername/heartbeat/dead_threshold is the one used to configure heartbeat dead threshold. Kernel has a default value of it but user can set O2CB_HEARTBEAT_THRESHOLD in /etc/sysconfig/o2cb to override it. Commit 45b997737a80 ("ocfs2/cluster: use per-attribute show and store methods") changed heartbeat dead threshold name while ocfs2-tools did not, so ocfs2-tools won't set this configurable and the default value is always used. So revert it. Fixes: 45b997737a80 ("ocfs2/cluster: use per-attribute show and store methods") Link: http://lkml.kernel.org/r/1490665245-15374-1-git-send-email-junxiao.bi@oracle.com Signed-off-by: Junxiao Bi Acked-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/heartbeat.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index f6e871760f8d..0da0332725aa 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -2242,13 +2242,13 @@ unlock: spin_unlock(&o2hb_live_lock); } -static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item, char *page) { return sprintf(page, "%u\n", o2hb_dead_threshold); } -static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item, const char *page, size_t count) { unsigned long tmp; @@ -2297,11 +2297,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item, } -CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold); +CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold); CONFIGFS_ATTR(o2hb_heartbeat_group_, mode); static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = { - &o2hb_heartbeat_group_attr_threshold, + &o2hb_heartbeat_group_attr_dead_threshold, &o2hb_heartbeat_group_attr_mode, NULL, }; -- cgit v1.2.3 From d47736fafe779f0843e2d766f76832dec5b672d9 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 3 May 2017 14:51:44 -0700 Subject: fs/ocfs2/cluster: use offset_in_page() macro Use offset_in_page() macro instead of open-coding. Link: http://lkml.kernel.org/r/4dbc77ccaaed98b183cf4dba58a4fa325fd65048.1492758503.git.geliangtang@gmail.com Signed-off-by: Geliang Tang Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index a4a6ba23b9a6..8d779227370a 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -955,7 +955,7 @@ static void o2net_sendpage(struct o2net_sock_container *sc, mutex_lock(&sc->sc_send_lock); ret = sc->sc_sock->ops->sendpage(sc->sc_sock, virt_to_page(kmalloced_virt), - (long)kmalloced_virt & ~PAGE_MASK, + offset_in_page(kmalloced_virt), size, MSG_DONTWAIT); mutex_unlock(&sc->sc_send_lock); if (ret == size) -- cgit v1.2.3 From cf8496ea8020792ea32d0fbec0c140d8de93011a Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 3 May 2017 14:52:42 -0700 Subject: proc: show MADV_FREE pages info in smaps Show MADV_FREE pages info of each vma in smaps. The interface is for diganose or monitoring purpose, userspace could use it to understand what happens in the application. Since userspace could dirty MADV_FREE pages without notice from kernel, this interface is the only place we can get accurate accounting info about MADV_FREE pages. [mhocko@kernel.org: update Documentation/filesystems/proc.txt] Link: http://lkml.kernel.org/r/89efde633559de1ec07444f2ef0f4963a97a2ce8.1487965799.git.shli@fb.com Signed-off-by: Shaohua Li Acked-by: Johannes Weiner Acked-by: Minchan Kim Acked-by: Michal Hocko Acked-by: Hillf Danton Cc: Hugh Dickins Cc: Rik van Riel Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 6 ++++++ fs/proc/task_mmu.c | 8 +++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 9036dbf16156..4cddbce85ac9 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -413,6 +413,7 @@ Private_Clean: 0 kB Private_Dirty: 0 kB Referenced: 892 kB Anonymous: 0 kB +LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB Shared_Hugetlb: 0 kB @@ -442,6 +443,11 @@ accessed. "Anonymous" shows the amount of memory that does not belong to any file. Even a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE and a page is modified, the file page is replaced by a private anonymous copy. +"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). +The memory isn't freed immediately with madvise(). It's freed in memory +pressure if the memory is clean. Please note that the printed value might +be lower than the real value due to optimizations used in the current +implementation. If this is not desirable please file a bug report. "AnonHugePages" shows the ammount of memory backed by transparent hugepage. "ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by huge pages. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 312578089544..f0c8b33d99b1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -441,6 +441,7 @@ struct mem_size_stats { unsigned long private_dirty; unsigned long referenced; unsigned long anonymous; + unsigned long lazyfree; unsigned long anonymous_thp; unsigned long shmem_thp; unsigned long swap; @@ -457,8 +458,11 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; - if (PageAnon(page)) + if (PageAnon(page)) { mss->anonymous += size; + if (!PageSwapBacked(page) && !dirty && !PageDirty(page)) + mss->lazyfree += size; + } mss->resident += size; /* Accumulate the size in pages that have been accessed. */ @@ -771,6 +775,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) "Private_Dirty: %8lu kB\n" "Referenced: %8lu kB\n" "Anonymous: %8lu kB\n" + "LazyFree: %8lu kB\n" "AnonHugePages: %8lu kB\n" "ShmemPmdMapped: %8lu kB\n" "Shared_Hugetlb: %8lu kB\n" @@ -789,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) mss.private_dirty >> 10, mss.referenced >> 10, mss.anonymous >> 10, + mss.lazyfree >> 10, mss.anonymous_thp >> 10, mss.shmem_thp >> 10, mss.shared_hugetlb >> 10, -- cgit v1.2.3 From 9070733b4efac4bf17f299a81b01c15e206f9ff5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 May 2017 14:53:12 -0700 Subject: xfs: abstract PF_FSTRANS to PF_MEMALLOC_NOFS xfs has defined PF_FSTRANS to declare a scope GFP_NOFS semantic quite some time ago. We would like to make this concept more generic and use it for other filesystems as well. Let's start by giving the flag a more generic name PF_MEMALLOC_NOFS which is in line with an exiting PF_MEMALLOC_NOIO already used for the same purpose for GFP_NOIO contexts. Replace all PF_FSTRANS usage from the xfs code in the first step before we introduce a full API for it as xfs uses the flag directly anyway. This patch doesn't introduce any functional change. Link: http://lkml.kernel.org/r/20170306131408.9828-4-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Darrick J. Wong Reviewed-by: Brian Foster Acked-by: Vlastimil Babka Cc: Dave Chinner Cc: Theodore Ts'o Cc: Chris Mason Cc: David Sterba Cc: Jan Kara Cc: Nikolay Borisov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/xfs/kmem.c | 4 ++-- fs/xfs/kmem.h | 2 +- fs/xfs/libxfs/xfs_btree.c | 2 +- fs/xfs/xfs_aops.c | 6 +++--- fs/xfs/xfs_trans.c | 12 ++++++------ include/linux/sched.h | 2 ++ 6 files changed, 15 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 70a5b55e0870..d0ac1a065539 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -63,13 +63,13 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags) * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering * the filesystem here and potentially deadlocking. */ - if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS)) + if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) noio_flag = memalloc_noio_save(); lflags = kmem_flags_convert(flags); ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); - if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS)) + if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) memalloc_noio_restore(noio_flag); return ptr; diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index f0fc84fcaac2..a6c8da40c70d 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -50,7 +50,7 @@ kmem_flags_convert(xfs_km_flags_t flags) lflags = GFP_ATOMIC | __GFP_NOWARN; } else { lflags = GFP_KERNEL | __GFP_NOWARN; - if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS)) + if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) lflags &= ~__GFP_FS; } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index c3decedc9455..3059a3ec7ecb 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -2886,7 +2886,7 @@ xfs_btree_split_worker( struct xfs_btree_split_args *args = container_of(work, struct xfs_btree_split_args, work); unsigned long pflags; - unsigned long new_pflags = PF_FSTRANS; + unsigned long new_pflags = PF_MEMALLOC_NOFS; /* * we are in a transaction context here, but may also be doing work diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 61494295d92f..05eca126c688 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -189,7 +189,7 @@ xfs_setfilesize_trans_alloc( * We hand off the transaction to the completion thread now, so * clear the flag here. */ - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); return 0; } @@ -252,7 +252,7 @@ xfs_setfilesize_ioend( * thus we need to mark ourselves as being in a transaction manually. * Similarly for freeze protection. */ - current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); __sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS); /* we abort the update if there was an IO error */ @@ -1016,7 +1016,7 @@ xfs_do_writepage( * Given that we do not allow direct reclaim to call us, we should * never be called while in a filesystem transaction. */ - if (WARN_ON_ONCE(current->flags & PF_FSTRANS)) + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) goto redirty; /* diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 70f42ea86dfb..f5969c8274fc 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -134,7 +134,7 @@ xfs_trans_reserve( bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; /* Mark this thread as being in a transaction */ - current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); /* * Attempt to reserve the needed disk blocks by decrementing @@ -144,7 +144,7 @@ xfs_trans_reserve( if (blocks > 0) { error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd); if (error != 0) { - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); return -ENOSPC; } tp->t_blk_res += blocks; @@ -221,7 +221,7 @@ undo_blocks: tp->t_blk_res = 0; } - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); return error; } @@ -914,7 +914,7 @@ __xfs_trans_commit( xfs_log_commit_cil(mp, tp, &commit_lsn, regrant); - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free(tp); /* @@ -944,7 +944,7 @@ out_unreserve: if (commit_lsn == -1 && !error) error = -EIO; } - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free_items(tp, NULLCOMMITLSN, !!error); xfs_trans_free(tp); @@ -998,7 +998,7 @@ xfs_trans_cancel( xfs_log_done(mp, tp->t_ticket, NULL, false); /* mark this thread as no longer being in a transaction */ - current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); + current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); xfs_trans_free_items(tp, NULLCOMMITLSN, dirty); xfs_trans_free(tp); diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d4fa448223f..8ac11465ac5b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1237,6 +1237,8 @@ extern struct pid *cad_pid; #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ +#define PF_MEMALLOC_NOFS PF_FSTRANS /* Transition to a more generic GFP_NOFS scope semantic */ + /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example -- cgit v1.2.3 From 7dea19f9ee636cb244109a4dba426bbb3e5304b7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 May 2017 14:53:15 -0700 Subject: mm: introduce memalloc_nofs_{save,restore} API GFP_NOFS context is used for the following 5 reasons currently: - to prevent from deadlocks when the lock held by the allocation context would be needed during the memory reclaim - to prevent from stack overflows during the reclaim because the allocation is performed from a deep context already - to prevent lockups when the allocation context depends on other reclaimers to make a forward progress indirectly - just in case because this would be safe from the fs POV - silence lockdep false positives Unfortunately overuse of this allocation context brings some problems to the MM. Memory reclaim is much weaker (especially during heavy FS metadata workloads), OOM killer cannot be invoked because the MM layer doesn't have enough information about how much memory is freeable by the FS layer. In many cases it is far from clear why the weaker context is even used and so it might be used unnecessarily. We would like to get rid of those as much as possible. One way to do that is to use the flag in scopes rather than isolated cases. Such a scope is declared when really necessary, tracked per task and all the allocation requests from within the context will simply inherit the GFP_NOFS semantic. Not only this is easier to understand and maintain because there are much less problematic contexts than specific allocation requests, this also helps code paths where FS layer interacts with other layers (e.g. crypto, security modules, MM etc...) and there is no easy way to convey the allocation context between the layers. Introduce memalloc_nofs_{save,restore} API to control the scope of GFP_NOFS allocation context. This is basically copying memalloc_noio_{save,restore} API we have for other restricted allocation context GFP_NOIO. The PF_MEMALLOC_NOFS flag already exists and it is just an alias for PF_FSTRANS which has been xfs specific until recently. There are no more PF_FSTRANS users anymore so let's just drop it. PF_MEMALLOC_NOFS is now checked in the MM layer and drops __GFP_FS implicitly same as PF_MEMALLOC_NOIO drops __GFP_IO. memalloc_noio_flags is renamed to current_gfp_context because it now cares about both PF_MEMALLOC_NOFS and PF_MEMALLOC_NOIO contexts. Xfs code paths preserve their semantic. kmem_flags_convert() doesn't need to evaluate the flag anymore. This patch shouldn't introduce any functional changes. Let's hope that filesystems will drop direct GFP_NOFS (resp. ~__GFP_FS) usage as much as possible and only use a properly documented memalloc_nofs_{save,restore} checkpoints where they are appropriate. [akpm@linux-foundation.org: fix comment typo, reflow comment] Link: http://lkml.kernel.org/r/20170306131408.9828-5-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Dave Chinner Cc: Theodore Ts'o Cc: Chris Mason Cc: David Sterba Cc: Jan Kara Cc: Brian Foster Cc: Darrick J. Wong Cc: Nikolay Borisov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/xfs/kmem.h | 2 +- include/linux/gfp.h | 8 ++++++++ include/linux/sched.h | 8 +++----- include/linux/sched/mm.h | 26 +++++++++++++++++++++++--- kernel/locking/lockdep.c | 6 +++--- mm/page_alloc.c | 10 ++++++---- mm/vmscan.c | 6 +++--- 7 files changed, 47 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index a6c8da40c70d..d6ea520162b2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -50,7 +50,7 @@ kmem_flags_convert(xfs_km_flags_t flags) lflags = GFP_ATOMIC | __GFP_NOWARN; } else { lflags = GFP_KERNEL | __GFP_NOWARN; - if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) + if (flags & KM_NOFS) lflags &= ~__GFP_FS; } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 978232a3b4ae..2bfcfd33e476 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -210,8 +210,16 @@ struct vm_area_struct; * * GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. + * Please try to avoid using this flag directly and instead use + * memalloc_noio_{save,restore} to mark the whole scope which cannot + * perform any IO with a short explanation why. All allocation requests + * will inherit GFP_NOIO implicitly. * * GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * Please try to avoid using this flag directly and instead use + * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't + * recurse into the FS layer with a short explanation why. All allocation + * requests will inherit GFP_NOFS implicitly. * * GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware diff --git a/include/linux/sched.h b/include/linux/sched.h index 8ac11465ac5b..993e7e25a3a5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1224,9 +1224,9 @@ extern struct pid *cad_pid; #define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ -#define PF_FSTRANS 0x00020000 /* Inside a filesystem transaction */ -#define PF_KSWAPD 0x00040000 /* I am kswapd */ -#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */ +#define PF_KSWAPD 0x00020000 /* I am kswapd */ +#define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ +#define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ @@ -1237,8 +1237,6 @@ extern struct pid *cad_pid; #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ -#define PF_MEMALLOC_NOFS PF_FSTRANS /* Transition to a more generic GFP_NOFS scope semantic */ - /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 830953ebb391..9daabe138c99 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -149,13 +149,21 @@ static inline bool in_vfork(struct task_struct *tsk) return ret; } -/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags - * __GFP_FS is also cleared as it implies __GFP_IO. +/* + * Applies per-task gfp context to the given allocation flags. + * PF_MEMALLOC_NOIO implies GFP_NOIO + * PF_MEMALLOC_NOFS implies GFP_NOFS */ -static inline gfp_t memalloc_noio_flags(gfp_t flags) +static inline gfp_t current_gfp_context(gfp_t flags) { + /* + * NOIO implies both NOIO and NOFS and it is a weaker context + * so always make sure it makes precendence + */ if (unlikely(current->flags & PF_MEMALLOC_NOIO)) flags &= ~(__GFP_IO | __GFP_FS); + else if (unlikely(current->flags & PF_MEMALLOC_NOFS)) + flags &= ~__GFP_FS; return flags; } @@ -171,4 +179,16 @@ static inline void memalloc_noio_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; } +static inline unsigned int memalloc_nofs_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOFS; + current->flags |= PF_MEMALLOC_NOFS; + return flags; +} + +static inline void memalloc_nofs_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; +} + #endif /* _LINUX_SCHED_MM_H */ diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index f84294c9a018..fd440b5a3c75 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2877,7 +2877,7 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) if (unlikely(!debug_locks)) return; - gfp_mask = memalloc_noio_flags(gfp_mask); + gfp_mask = current_gfp_context(gfp_mask); /* no reclaim without waiting on it */ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) @@ -2888,7 +2888,7 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags) return; /* We're only interested __GFP_FS allocations for now */ - if (!(gfp_mask & __GFP_FS)) + if (!(gfp_mask & __GFP_FS) || (curr->flags & PF_MEMALLOC_NOFS)) return; /* @@ -3954,7 +3954,7 @@ EXPORT_SYMBOL_GPL(lock_unpin_lock); void lockdep_set_current_reclaim_state(gfp_t gfp_mask) { - current->lockdep_reclaim_gfp = memalloc_noio_flags(gfp_mask); + current->lockdep_reclaim_gfp = current_gfp_context(gfp_mask); } void lockdep_clear_current_reclaim_state(void) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 34ac32428de8..7a3751e53f91 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3951,10 +3951,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, goto out; /* - * Runtime PM, block IO and its error handling path can deadlock - * because I/O on the device might not complete. + * Apply scoped allocation constraints. This is mainly about GFP_NOFS + * resp. GFP_NOIO which has to be inherited for all allocation requests + * from a particular context which has been marked by + * memalloc_no{fs,io}_{save,restore}. */ - alloc_mask = memalloc_noio_flags(gfp_mask); + alloc_mask = current_gfp_context(gfp_mask); ac.spread_dirty_pages = false; /* @@ -7408,7 +7410,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, .zone = page_zone(pfn_to_page(start)), .mode = MIGRATE_SYNC, .ignore_skip_hint = true, - .gfp_mask = memalloc_noio_flags(gfp_mask), + .gfp_mask = current_gfp_context(gfp_mask), }; INIT_LIST_HEAD(&cc.migratepages); diff --git a/mm/vmscan.c b/mm/vmscan.c index ec4555369e17..3ad66580b8b4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2915,7 +2915,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, - .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, @@ -2995,7 +2995,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, int nid; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | + .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, @@ -3702,7 +3702,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in int classzone_idx = gfp_zone(gfp_mask); struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), - .gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)), + .gfp_mask = (gfp_mask = current_gfp_context(gfp_mask)), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), -- cgit v1.2.3 From 9ba1fb2c602a6f2323e3a08ec8e7a8e33bf335f4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 May 2017 14:53:19 -0700 Subject: xfs: use memalloc_nofs_{save,restore} instead of memalloc_noio* kmem_zalloc_large and _xfs_buf_map_pages use memalloc_noio_{save,restore} API to prevent from reclaim recursion into the fs because vmalloc can invoke unconditional GFP_KERNEL allocations and these functions might be called from the NOFS contexts. The memalloc_noio_save will enforce GFP_NOIO context which is even weaker than GFP_NOFS and that seems to be unnecessary. Let's use memalloc_nofs_{save,restore} instead as it should provide exactly what we need here - implicit GFP_NOFS context. Link: http://lkml.kernel.org/r/20170306131408.9828-6-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Acked-by: Vlastimil Babka Cc: Dave Chinner Cc: Theodore Ts'o Cc: Chris Mason Cc: David Sterba Cc: Jan Kara Cc: Nikolay Borisov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/xfs/kmem.c | 12 ++++++------ fs/xfs/xfs_buf.c | 8 ++++---- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index d0ac1a065539..780fc8986dab 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -48,7 +48,7 @@ kmem_alloc(size_t size, xfs_km_flags_t flags) void * kmem_zalloc_large(size_t size, xfs_km_flags_t flags) { - unsigned noio_flag = 0; + unsigned nofs_flag = 0; void *ptr; gfp_t lflags; @@ -60,17 +60,17 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags) * __vmalloc() will allocate data pages and auxillary structures (e.g. * pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context * here. Hence we need to tell memory reclaim that we are in such a - * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering + * context via PF_MEMALLOC_NOFS to prevent memory reclaim re-entering * the filesystem here and potentially deadlocking. */ - if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) - noio_flag = memalloc_noio_save(); + if (flags & KM_NOFS) + nofs_flag = memalloc_nofs_save(); lflags = kmem_flags_convert(flags); ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); - if ((current->flags & PF_MEMALLOC_NOFS) || (flags & KM_NOFS)) - memalloc_noio_restore(noio_flag); + if (flags & KM_NOFS) + memalloc_nofs_restore(nofs_flag); return ptr; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b6208728ba39..ca09061369cb 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -443,17 +443,17 @@ _xfs_buf_map_pages( bp->b_addr = NULL; } else { int retried = 0; - unsigned noio_flag; + unsigned nofs_flag; /* * vm_map_ram() will allocate auxillary structures (e.g. * pagetables) with GFP_KERNEL, yet we are likely to be under * GFP_NOFS context here. Hence we need to tell memory reclaim - * that we are in such a context via PF_MEMALLOC_NOIO to prevent + * that we are in such a context via PF_MEMALLOC_NOFS to prevent * memory reclaim re-entering the filesystem here and * potentially deadlocking. */ - noio_flag = memalloc_noio_save(); + nofs_flag = memalloc_nofs_save(); do { bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, -1, PAGE_KERNEL); @@ -461,7 +461,7 @@ _xfs_buf_map_pages( break; vm_unmap_aliases(); } while (retried++ <= 1); - memalloc_noio_restore(noio_flag); + memalloc_nofs_restore(nofs_flag); if (!bp->b_addr) return -ENOMEM; -- cgit v1.2.3 From 81378da64de6d33d0c200885f1de431c9a3e5ccd Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 May 2017 14:53:22 -0700 Subject: jbd2: mark the transaction context with the scope GFP_NOFS context now that we have memalloc_nofs_{save,restore} api we can mark the whole transaction context as implicitly GFP_NOFS. All allocations will automatically inherit GFP_NOFS this way. This means that we do not have to mark any of those requests with GFP_NOFS and moreover all the ext4_kv[mz]alloc(GFP_NOFS) are also safe now because even the hardcoded GFP_KERNEL allocations deep inside the vmalloc will be NOFS now. [akpm@linux-foundation.org: tweak comments] Link: http://lkml.kernel.org/r/20170306131408.9828-7-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Jan Kara Cc: Dave Chinner Cc: Theodore Ts'o Cc: Chris Mason Cc: David Sterba Cc: Brian Foster Cc: Darrick J. Wong Cc: Nikolay Borisov Cc: Peter Zijlstra Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd2/transaction.c | 12 ++++++++++++ include/linux/jbd2.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'fs') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 5e659ee08d6a..9ee4832b6f8b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -388,6 +389,11 @@ repeat: rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_); jbd2_journal_free_transaction(new_transaction); + /* + * Ensure that no allocations done while the transaction is open are + * going to recurse back to the fs layer. + */ + handle->saved_alloc_context = memalloc_nofs_save(); return 0; } @@ -466,6 +472,7 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, line_no, nblocks); + return handle; } EXPORT_SYMBOL(jbd2__journal_start); @@ -1760,6 +1767,11 @@ int jbd2_journal_stop(handle_t *handle) if (handle->h_rsv_handle) jbd2_journal_free_reserved(handle->h_rsv_handle); free_and_exit: + /* + * Scope of the GFP_NOFS context is over here and so we can restore the + * original alloc context. + */ + memalloc_nofs_restore(handle->saved_alloc_context); jbd2_free_handle(handle); return err; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index dfaa1f4dcb0c..606b6bce3a5b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -491,6 +491,8 @@ struct jbd2_journal_handle unsigned long h_start_jiffies; unsigned int h_requested_credits; + + unsigned int saved_alloc_context; }; -- cgit v1.2.3 From eb52da3f48f5b1ddceb7e8d4725b6c88204aa2c4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 3 May 2017 14:53:26 -0700 Subject: jbd2: make the whole kjournald2 kthread NOFS safe kjournald2 is central to the transaction commit processing. As such any potential allocation from this kernel thread has to be GFP_NOFS. Make sure to mark the whole kernel thread GFP_NOFS by the memalloc_nofs_save. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170306131408.9828-8-mhocko@kernel.org Signed-off-by: Michal Hocko Suggested-by: Jan Kara Reviewed-by: Jan Kara Cc: Dave Chinner Cc: Theodore Ts'o Cc: Chris Mason Cc: David Sterba Cc: Brian Foster Cc: Darrick J. Wong Cc: Nikolay Borisov Cc: Peter Zijlstra Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/jbd2/journal.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 5adc2fb62b0f..c43fe83ee708 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -43,6 +43,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -205,6 +206,14 @@ static int kjournald2(void *arg) journal->j_task = current; wake_up(&journal->j_wait_done_commit); + /* + * Make sure that no allocations from this kernel thread will ever + * recurse to the fs layer because we are responsible for the + * transaction commit and any fs involvement might get stuck waiting for + * the trasn. commit. + */ + memalloc_nofs_save(); + /* * And now, wait forever for commit wakeup events. */ -- cgit v1.2.3 From 55635ba76ef91f26b418702ace5e6287eb727f6a Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Wed, 3 May 2017 14:55:59 -0700 Subject: fs: fix data invalidation in the cleancache during direct IO Patch series "Properly invalidate data in the cleancache", v2. We've noticed that after direct IO write, buffered read sometimes gets stale data which is coming from the cleancache. The reason for this is that some direct write hooks call call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero, so we may not invalidate data in the cleancache. Another odd thing is that we check only for ->nrpages and don't check for ->nrexceptional, but invalidate_inode_pages2[_range] also invalidates exceptional entries as well. So we invalidate exceptional entries only if ->nrpages != 0? This doesn't feel right. - Patch 1 fixes direct IO writes by removing ->nrpages check. - Patch 2 fixes similar case in invalidate_bdev(). Note: I only fixed conditional cleancache_invalidate_inode() here. Do we also need to add ->nrexceptional check in into invalidate_bdev()? - Patches 3-4: some optimizations. This patch (of 4): Some direct IO write fs hooks call invalidate_inode_pages2[_range]() conditionally iff mapping->nrpages is not zero. This can't be right, because invalidate_inode_pages2[_range]() also invalidate data in the cleancache via cleancache_invalidate_inode() call. So if page cache is empty but there is some data in the cleancache, buffered read after direct IO write would get stale data from the cleancache. Also it doesn't feel right to check only for ->nrpages because invalidate_inode_pages2[_range] invalidates exceptional entries as well. Fix this by calling invalidate_inode_pages2[_range]() regardless of nrpages state. Note: nfs,cifs,9p doesn't need similar fix because the never call cleancache_get_page() (nor directly, nor via mpage_readpage[s]()), so they are not affected by this bug. Fixes: c515e1fd361c ("mm/fs: add hooks to support cleancache") Link: http://lkml.kernel.org/r/20170424164135.22350-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reviewed-by: Jan Kara Acked-by: Konrad Rzeszutek Wilk Cc: Alexander Viro Cc: Ross Zwisler Cc: Jens Axboe Cc: Johannes Weiner Cc: Alexey Kuznetsov Cc: Christoph Hellwig Cc: Nikolay Borisov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/iomap.c | 18 ++++++++---------- mm/filemap.c | 26 +++++++++++--------------- 2 files changed, 19 insertions(+), 25 deletions(-) (limited to 'fs') diff --git a/fs/iomap.c b/fs/iomap.c index 141c3cd55a8b..1c25ae30500e 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -887,16 +887,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, flags |= IOMAP_WRITE; } - if (mapping->nrpages) { - ret = filemap_write_and_wait_range(mapping, start, end); - if (ret) - goto out_free_dio; + ret = filemap_write_and_wait_range(mapping, start, end); + if (ret) + goto out_free_dio; - ret = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); - ret = 0; - } + ret = invalidate_inode_pages2_range(mapping, + start >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; inode_dio_begin(inode); @@ -951,7 +949,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... */ - if (iov_iter_rw(iter) == WRITE && mapping->nrpages) { + if (iov_iter_rw(iter) == WRITE) { int err = invalidate_inode_pages2_range(mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(err); diff --git a/mm/filemap.c b/mm/filemap.c index 7f425f18c158..681da61080bc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2720,18 +2720,16 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ - if (mapping->nrpages) { - written = invalidate_inode_pages2_range(mapping, + written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); - /* - * If a page can not be invalidated, return 0 to fall back - * to buffered write. - */ - if (written) { - if (written == -EBUSY) - return 0; - goto out; - } + /* + * If a page can not be invalidated, return 0 to fall back + * to buffered write. + */ + if (written) { + if (written == -EBUSY) + return 0; + goto out; } written = mapping->a_ops->direct_IO(iocb, from); @@ -2744,10 +2742,8 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... */ - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); - } + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; -- cgit v1.2.3 From a5f6a6a9c72eac38a7fadd1a038532bc8516337c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Wed, 3 May 2017 14:56:02 -0700 Subject: fs/block_dev: always invalidate cleancache in invalidate_bdev() invalidate_bdev() calls cleancache_invalidate_inode() iff ->nrpages != 0 which doen't make any sense. Make sure that invalidate_bdev() always calls cleancache_invalidate_inode() regardless of mapping->nrpages value. Fixes: c515e1fd361c ("mm/fs: add hooks to support cleancache") Link: http://lkml.kernel.org/r/20170424164135.22350-3-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reviewed-by: Jan Kara Acked-by: Konrad Rzeszutek Wilk Cc: Alexander Viro Cc: Ross Zwisler Cc: Jens Axboe Cc: Johannes Weiner Cc: Alexey Kuznetsov Cc: Christoph Hellwig Cc: Nikolay Borisov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 9ccabe3bb7de..0d435c794d76 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -103,12 +103,11 @@ void invalidate_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; - if (mapping->nrpages == 0) - return; - - invalidate_bh_lrus(); - lru_add_drain_all(); /* make sure all lru add caches are flushed */ - invalidate_mapping_pages(mapping, 0, -1); + if (mapping->nrpages) { + invalidate_bh_lrus(); + lru_add_drain_all(); /* make sure all lru add caches are flushed */ + invalidate_mapping_pages(mapping, 0, -1); + } /* 99% of the time, we don't need to flush the cleancache on the bdev. * But, for the strange corners, lets be cautious */ -- cgit v1.2.3