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

[PATCH] arm64: Ensure VM_WRITE|VM_SHARED ptes are clean by default

by Catalin Marinas

Shared and writable mappings (__S.1.) should be clean (!dirty) initially and made dirty on a subsequent write either through the hardware DBM (dirty bit management) mechanism or through a write page fault. A clean pte for the arm64 kernel is one that has PTE_RDONLY set and PTE_DIRTY clear. The PAGE_SHARED{,_EXEC} attributes have PTE_WRITE set (PTE_DBM) and PTE_DIRTY clear. Prior to commit 73e86cb03cf2 ("arm64: Move PTE_RDONLY bit handling out of set_pte_at()"), it was the responsibility of set_pte_at() to set the PTE_RDONLY bit and mark the pte clean if the software PTE_DIRTY bit was not set. However, the above commit removed the pte_sw_dirty() check and the subsequent setting of PTE_RDONLY in set_pte_at() while leaving the PAGE_SHARED{,_EXEC} definitions unchanged. The result is that shared+writable mappings are now dirty by default Fix the above by explicitly setting PTE_RDONLY in PAGE_SHARED{,_EXEC}. In addition, remove the superfluous PTE_DIRTY bit from the kernel PROT_* attributes. Fixes: 73e86cb03cf2 ("arm64: Move PTE_RDONLY bit handling out of set_pte_at()") Cc: <stable(a)vger.kernel.org> # 4.14.x- Cc: Will Deacon <will(a)kernel.org> Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> --- arch/arm64/include/asm/pgtable-prot.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9a21b84536f2..8dc6c5cdabe6 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -32,11 +32,11 @@ #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -80,8 +80,9 @@ #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)

6 years

3
11
0 0

[PATCH] drm/i915/userptr: Try to acquire the page lock around set_page_dirty()

by Chris Wilson

set_page_dirty says: For pages with a mapping this should be done under the page lock for the benefit of asynchronous memory errors who prefer a consistent dirty state. This rule can be broken in some special cases, but should be better not to. Under those rules, it is only safe for us to use the plain set_page_dirty calls for shmemfs/anonymous memory. Userptr may be used with real mappings and so needs to use the locked version (set_page_dirty_lock). However, following a try_to_unmap() we may want to remove the userptr and so call put_pages(). However, try_to_unmap() acquires the page lock and so we must avoid recursively locking the pages ourselves -- which means that we cannot safely acquire the lock around set_page_dirty(). Since we can't be sure of the lock, we have to risk skip dirtying the page, or else risk calling set_page_dirty() without a lock and so risk fs corruption. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203317 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=112012 Fixes: 5cc9ed4b9a7a ("drm/i915: Introduce mapping of user pages into video m References: cb6d7c7dc7ff ("drm/i915/userptr: Acquire the page lock around set_page_dirty()") References: 505a8ec7e11a ("Revert "drm/i915/userptr: Acquire the page lock around set_page_dirty()"") References: 6dcc693bc57f ("ext4: warn when page is dirtied without buffers") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Lionel Landwerlin <lionel.g.landwerlin(a)intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 22 ++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 1e045c337044..4c72d74d6576 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -646,8 +646,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, obj->mm.dirty = false; for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. + */ set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); -- 2.24.0

6 years

1
0
0 0

[PATCH 1/5] drm/i915/userptr: Beware recursive lock_page()

by Chris Wilson

Following a try_to_unmap() we may want to remove the userptr and so call put_pages(). However, try_to_unmap() acquires the page lock and so we must avoid recursively locking the pages ourselves -- which means that we cannot safely acquire the lock around set_page_dirty(). Since we can't be sure of the lock, we have to risk skip dirtying the page, or else risk calling set_page_dirty() without a lock and so risk fs corruption. Reported-by: Lionel Landwerlin <lionel.g.landwerlin(a)intel.com> Fixes: cb6d7c7dc7ff ("drm/i915/userptr: Acquire the page lock around set_page_dirty()") Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk> Cc: Lionel Landwerlin <lionel.g.landwerlin(a)intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index b9d2bb15e4a6..1ad2047a6dbd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -672,7 +672,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, obj->mm.dirty = false; for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { /* * As this may not be anonymous memory (e.g. shmem) * but exist on a real mapping, we have to lock @@ -680,8 +680,20 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, * the page reference is not sufficient to * prevent the inode from being truncated. * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. */ - set_page_dirty_lock(page); + set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); -- 2.22.0

6 years

3
15
0 0

[patch 17/17] mm: memcontrol: fix network errors from failing __GFP_ATOMIC charges

by akpm＠linux-foundation.org

From: Johannes Weiner <hannes(a)cmpxchg.org> Subject: mm: memcontrol: fix network errors from failing __GFP_ATOMIC charges While upgrading from 4.16 to 5.2, we noticed these allocation errors in the log of the new kernel: [ 8642.253395] SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC) [ 8642.269170] cache: tw_sock_TCPv6(960:helper-logs), object size: 232, buffer size: 240, default order: 1, min order: 0 [ 8642.293009] node 0: slabs: 5, objs: 170, free: 0 slab_out_of_memory+1 ___slab_alloc+969 __slab_alloc+14 kmem_cache_alloc+346 inet_twsk_alloc+60 tcp_time_wait+46 tcp_fin+206 tcp_data_queue+2034 tcp_rcv_state_process+784 tcp_v6_do_rcv+405 __release_sock+118 tcp_close+385 inet_release+46 __sock_release+55 sock_close+17 __fput+170 task_work_run+127 exit_to_usermode_loop+191 do_syscall_64+212 entry_SYSCALL_64_after_hwframe+68 accompanied by an increase in machines going completely radio silent under memory pressure. One thing that changed since 4.16 is e699e2c6a654 ("net, mm: account sock objects to kmemcg"), which made these slab caches subject to cgroup memory accounting and control. The problem with that is that cgroups, unlike the page allocator, do not maintain dedicated atomic reserves. As a cgroup's usage hovers at its limit, atomic allocations - such as done during network rx - can fail consistently for extended periods of time. The kernel is not able to operate under these conditions. We don't want to revert the culprit patch, because it indeed tracks a potentially substantial amount of memory used by a cgroup. We also don't want to implement dedicated atomic reserves for cgroups. There is no point in keeping a fixed margin of unused bytes in the cgroup's memory budget to accomodate a consumer that is impossible to predict - we'd be wasting memory and get into configuration headaches, not unlike what we have going with min_free_kbytes. We do this for physical mem because we have to, but cgroups are an accounting game. Instead, account these privileged allocations to the cgroup, but let them bypass the configured limit if they have to. This way, we get the benefits of accounting the consumed memory and have it exert pressure on the rest of the cgroup, but like with the page allocator, we shift the burden of reclaimining on behalf of atomic allocations onto the regular allocations that can block. Link: http://lkml.kernel.org/r/20191022233708.365764-1-hannes@cmpxchg.org Fixes: e699e2c6a654 ("net, mm: account sock objects to kmemcg") Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Cc: Suleiman Souhlal <suleiman(a)google.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: <stable(a)vger.kernel.org> [4.18+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memcontrol.c | 9 +++++++++ 1 file changed, 9 insertions(+) --- a/mm/memcontrol.c~mm-memcontrol-fix-network-errors-from-failing-__gfp_atomic-charges +++ a/mm/memcontrol.c @@ -2535,6 +2535,15 @@ retry: } /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (gfp_mask & __GFP_ATOMIC) + goto force; + + /* * Unlike in global OOM situations, memcg is not in a physical * memory shortage. Allow dying and OOM-killed tasks to * bypass the last charges so that they can exit quickly and _

6 years

1
0
0 0

[patch 14/17] mm: slab: make page_cgroup_ino() to recognize non-compound slab pages properly

by akpm＠linux-foundation.org

From: Roman Gushchin <guro(a)fb.com> Subject: mm: slab: make page_cgroup_ino() to recognize non-compound slab pages properly page_cgroup_ino() doesn't return a valid memcg pointer for non-compound slab pages, because it depends on PgHead AND PgSlab flags to be set to determine the memory cgroup from the kmem_cache. It's correct for compound pages, but not for generic small pages. Those don't have PgHead set, so it ends up returning zero. Fix this by replacing the condition to PageSlab() && !PageTail(). Before this patch: [root@localhost ~]# ./page-types -c /sys/fs/cgroup/user.slice/user-0.slice/user(a)0.service/ | grep slab 0x0000000000000080 38 0 _______S___________________________________ slab After this patch: [root@localhost ~]# ./page-types -c /sys/fs/cgroup/user.slice/user-0.slice/user(a)0.service/ | grep slab 0x0000000000000080 147 0 _______S___________________________________ slab Also, hwpoison_filter_task() uses output of page_cgroup_ino() in order to filter error injection events based on memcg. So if page_cgroup_ino() fails to return memcg pointer, we just fail to inject memory error. Considering that hwpoison filter is for testing, affected users are limited and the impact should be marginal. [n-horiguchi(a)ah.jp.nec.com: changelog additions] Link: http://lkml.kernel.org/r/20191031012151.2722280-1-guro@fb.com Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") Signed-off-by: Roman Gushchin <guro(a)fb.com> Reviewed-by: Shakeel Butt <shakeelb(a)google.com> Acked-by: David Rientjes <rientjes(a)google.com> Cc: Vladimir Davydov <vdavydov.dev(a)gmail.com> Cc: Daniel Jordan <daniel.m.jordan(a)oracle.com> Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memcontrol.c | 2 +- mm/slab.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) --- a/mm/memcontrol.c~mm-slab-make-page_cgroup_ino-to-recognize-non-compound-slab-pages-properly +++ a/mm/memcontrol.c @@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - if (PageHead(page) && PageSlab(page)) + if (PageSlab(page) && !PageTail(page)) memcg = memcg_from_slab_page(page); else memcg = READ_ONCE(page->mem_cgroup); --- a/mm/slab.h~mm-slab-make-page_cgroup_ino-to-recognize-non-compound-slab-pages-properly +++ a/mm/slab.h @@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_r * Expects a pointer to a slab page. Please note, that PageSlab() check * isn't sufficient, as it returns true also for tail compound slab pages, * which do not have slab_cache pointer set. - * So this function assumes that the page can pass PageHead() and PageSlab() - * checks. + * So this function assumes that the page can pass PageSlab() && !PageTail() + * check. * * The kmem_cache can be reparented asynchronously. The caller must ensure * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex. _

6 years

1
0
0 0

[patch 12/17] dump_stack: avoid the livelock of the dump_lock

by akpm＠linux-foundation.org

From: Kevin Hao <haokexin(a)gmail.com> Subject: dump_stack: avoid the livelock of the dump_lock In the current code, we use the atomic_cmpxchg() to serialize the output of the dump_stack(), but this implementation suffers the thundering herd problem. We have observed such kind of livelock on a Marvell cn96xx board(24 cpus) when heavily using the dump_stack() in a kprobe handler. Actually we can let the competitors to wait for the releasing of the lock before jumping to atomic_cmpxchg(). This will definitely mitigate the thundering herd problem. Thanks Linus for the suggestion. [akpm(a)linux-foundation.org: fix comment] Link: http://lkml.kernel.org/r/20191030031637.6025-1-haokexin@gmail.com Fixes: b58d977432c8 ("dump_stack: serialize the output from dump_stack()") Signed-off-by: Kevin Hao <haokexin(a)gmail.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/dump_stack.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) --- a/lib/dump_stack.c~dump_stack-avoid-the-livelock-of-the-dump_lock +++ a/lib/dump_stack.c @@ -106,7 +106,12 @@ retry: was_locked = 1; } else { local_irq_restore(flags); - cpu_relax(); + /* + * Wait for the lock to release before jumping to + * atomic_cmpxchg() in order to mitigate the thundering herd + * problem. + */ + do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); goto retry; } _

6 years

1
0
0 0

[patch 09/17] mm/khugepaged: fix might_sleep() warn with CONFIG_HIGHPTE=y

by akpm＠linux-foundation.org

From: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Subject: mm/khugepaged: fix might_sleep() warn with CONFIG_HIGHPTE=y I got some khugepaged spew on a 32bit x86: [ 217.490026] BUG: sleeping function called from invalid context at include/linux/mmu_notifier.h:346 [ 217.492826] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 25, name: khugepaged [ 217.495589] INFO: lockdep is turned off. [ 217.498371] CPU: 1 PID: 25 Comm: khugepaged Not tainted 5.4.0-rc5-elk+ #206 [ 217.501233] Hardware name: System manufacturer P5Q-EM/P5Q-EM, BIOS 2203 07/08/2009 [ 217.501697] Call Trace: [ 217.501697] dump_stack+0x66/0x8e [ 217.501697] ___might_sleep.cold.96+0x95/0xa6 [ 217.501697] __might_sleep+0x2e/0x80 [ 217.501697] collapse_huge_page.isra.51+0x5ac/0x1360 [ 217.501697] ? __alloc_pages_nodemask+0xec/0xf80 [ 217.501697] ? __alloc_pages_nodemask+0x191/0xf80 [ 217.501697] ? trace_hardirqs_on+0x4a/0xf0 [ 217.501697] khugepaged+0x9a9/0x20f0 [ 217.501697] ? _raw_spin_unlock+0x21/0x30 [ 217.501697] ? trace_hardirqs_on+0x4a/0xf0 [ 217.501697] ? wait_woken+0xa0/0xa0 [ 217.501697] kthread+0xf5/0x110 [ 217.501697] ? collapse_pte_mapped_thp+0x3b0/0x3b0 [ 217.501697] ? kthread_create_worker_on_cpu+0x20/0x20 [ 217.501697] ret_from_fork+0x2e/0x38 Looks like it's due to CONFIG_HIGHPTE=y pte_offset_map()->kmap_atomic() vs. mmu_notifier_invalidate_range_start(). Let's do the naive approach and just reorder the two operations. Link: http://lkml.kernel.org/r/20191029201513.GG1208@intel.com Fixes: 810e24e009cf71 ("mm/mmu_notifiers: annotate with might_sleep()") Signed-off-by: Ville Syrjl <ville.syrjala(a)linux.intel.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Acked-by: Kirill A. Shutemov <kirill.shutemov(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: Jérôme Glisse <jglisse(a)redhat.com> Cc: Ralph Campbell <rcampbell(a)nvidia.com> Cc: Ira Weiny <ira.weiny(a)intel.com> Cc: Jason Gunthorpe <jgg(a)mellanox.com> Cc: Daniel Vetter <daniel.vetter(a)intel.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/khugepaged.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) --- a/mm/khugepaged.c~khugepaged-might_sleep-warn-due-to-config_highpte=y +++ a/mm/khugepaged.c @@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm anon_vma_lock_write(vma->anon_vma); - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes _

6 years

1
0
0 0

[patch 07/17] mm, vmstat: hide /proc/pagetypeinfo from normal users

by akpm＠linux-foundation.org

From: Michal Hocko <mhocko(a)suse.com> Subject: mm, vmstat: hide /proc/pagetypeinfo from normal users /proc/pagetypeinfo is a debugging tool to examine internal page allocator state wrt to fragmentation. It is not very useful for any other use so normal users really do not need to read this file. Waiman Long has noticed that reading this file can have negative side effects because zone->lock is necessary for gathering data and that a) interferes with the page allocator and its users and b) can lead to hard lockups on large machines which have very long free_list. Reduce both issues by simply not exporting the file to regular users. Link: http://lkml.kernel.org/r/20191025072610.18526-2-mhocko@kernel.org Fixes: 467c996c1e19 ("Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo") Signed-off-by: Michal Hocko <mhocko(a)suse.com> Reported-by: Waiman Long <longman(a)redhat.com> Acked-by: Mel Gorman <mgorman(a)suse.de> Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Acked-by: Waiman Long <longman(a)redhat.com> Acked-by: Rafael Aquini <aquini(a)redhat.com> Acked-by: David Rientjes <rientjes(a)google.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Roman Gushchin <guro(a)fb.com> Cc: Konstantin Khlebnikov <khlebnikov(a)yandex-team.ru> Cc: Jann Horn <jannh(a)google.com> Cc: Song Liu <songliubraving(a)fb.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmstat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/vmstat.c~mm-vmstat-hide-proc-pagetypeinfo-from-normal-users +++ a/mm/vmstat.c @@ -1972,7 +1972,7 @@ void __init init_mm_internals(void) #endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); - proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); proc_create_seq("vmstat", 0444, NULL, &vmstat_op); proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif _

6 years

1
0
0 0

[patch 04/17] mm: thp: handle page cache THP correctly in PageTransCompoundMap

by akpm＠linux-foundation.org

From: Yang Shi <yang.shi(a)linux.alibaba.com> Subject: mm: thp: handle page cache THP correctly in PageTransCompoundMap We have a usecase to use tmpfs as QEMU memory backend and we would like to take the advantage of THP as well. But, our test shows the EPT is not PMD mapped even though the underlying THP are PMD mapped on host. The number showed by /sys/kernel/debug/kvm/largepage is much less than the number of PMD mapped shmem pages as the below: 7f2778200000-7f2878200000 rw-s 00000000 00:14 262232 /dev/shm/qemu_back_mem.mem.Hz2hSf (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 579584 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 12 And some benchmarks do worse than with anonymous THPs. By digging into the code we figured out that commit 127393fbe597 ("mm: thp: kvm: fix memory corruption in KVM with THP enabled") checks if there is a single PTE mapping on the page for anonymous THP when setting up EPT map. But, the _mapcount < 0 check doesn't fit to page cache THP since every subpage of page cache THP would get _mapcount inc'ed once it is PMD mapped, so PageTransCompoundMap() always returns false for page cache THP. This would prevent KVM from setting up PMD mapped EPT entry. So we need handle page cache THP correctly. However, when page cache THP's PMD gets split, kernel just remove the map instead of setting up PTE map like what anonymous THP does. Before KVM calls get_user_pages() the subpages may get PTE mapped even though it is still a THP since the page cache THP may be mapped by other processes at the mean time. Checking its _mapcount and whether the THP has PTE mapped or not. Although this may report some false negative cases (PTE mapped by other processes), it looks not trivial to make this accurate. With this fix /sys/kernel/debug/kvm/largepage would show reasonable pages are PMD mapped by EPT as the below: 7fbeaee00000-7fbfaee00000 rw-s 00000000 00:14 275464 /dev/shm/qemu_back_mem.mem.SKUvat (deleted) Size: 4194304 kB [snip] AnonHugePages: 0 kB ShmemPmdMapped: 557056 kB [snip] Locked: 0 kB cat /sys/kernel/debug/kvm/largepages 271 And the benchmarks are as same as anonymous THPs. [yang.shi(a)linux.alibaba.com: v4] Link: http://lkml.kernel.org/r/1571865575-42913-1-git-send-email-yang.shi@linux.a… Link: http://lkml.kernel.org/r/1571769577-89735-1-git-send-email-yang.shi@linux.a… Fixes: dd78fedde4b9 ("rmap: support file thp") Signed-off-by: Yang Shi <yang.shi(a)linux.alibaba.com> Reported-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Tested-by: Gang Deng <gavin.dg(a)linux.alibaba.com> Suggested-by: Hugh Dickins <hughd(a)google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> [4.8+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 5 ----- include/linux/mm_types.h | 5 +++++ include/linux/page-flags.h | 20 ++++++++++++++++++-- 3 files changed, 23 insertions(+), 7 deletions(-) --- a/include/linux/mm.h~mm-thp-handle-page-cache-thp-correctly-in-pagetranscompoundmap +++ a/include/linux/mm.h @@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, s extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); --- a/include/linux/mm_types.h~mm-thp-handle-page-cache-thp-correctly-in-pagetranscompoundmap +++ a/include/linux/mm_types.h @@ -221,6 +221,11 @@ struct page { #endif } _struct_page_alignment; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * Used for sizing the vmemmap region on some architectures */ --- a/include/linux/page-flags.h~mm-thp-handle-page-cache-thp-correctly-in-pagetranscompoundmap +++ a/include/linux/page-flags.h @@ -622,12 +622,28 @@ static inline int PageTransCompound(stru * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + /* File THP is PMD mapped and not PTE mapped */ + return atomic_read(&page->_mapcount) == + atomic_read(compound_mapcount_ptr(head)); } /* _

6 years

1
0
0 0

[patch 03/17] mm, meminit: recalculate pcpu batch and high limits after init completes

by akpm＠linux-foundation.org

From: Mel Gorman <mgorman(a)techsingularity.net> Subject: mm, meminit: recalculate pcpu batch and high limits after init completes Deferred memory initialisation updates zone->managed_pages during the initialisation phase but before that finishes, the per-cpu page allocator (pcpu) calculates the number of pages allocated/freed in batches as well as the maximum number of pages allowed on a per-cpu list. As zone->managed_pages is not up to date yet, the pcpu initialisation calculates inappropriately low batch and high values. This increases zone lock contention quite severely in some cases with the degree of severity depending on how many CPUs share a local zone and the size of the zone. A private report indicated that kernel build times were excessive with extremely high system CPU usage. A perf profile indicated that a large chunk of time was lost on zone->lock contention. This patch recalculates the pcpu batch and high values after deferred initialisation completes for every populated zone in the system. It was tested on a 2-socket AMD EPYC 2 machine using a kernel compilation workload -- allmodconfig and all available CPUs. mmtests configuration: config-workload-kernbench-max Configuration was modified to build on a fresh XFS partition. kernbench 5.4.0-rc3 5.4.0-rc3 vanilla resetpcpu-v2 Amean user-256 13249.50 ( 0.00%) 16401.31 * -23.79%* Amean syst-256 14760.30 ( 0.00%) 4448.39 * 69.86%* Amean elsp-256 162.42 ( 0.00%) 119.13 * 26.65%* Stddev user-256 42.97 ( 0.00%) 19.15 ( 55.43%) Stddev syst-256 336.87 ( 0.00%) 6.71 ( 98.01%) Stddev elsp-256 2.46 ( 0.00%) 0.39 ( 84.03%) 5.4.0-rc3 5.4.0-rc3 vanilla resetpcpu-v2 Duration User 39766.24 49221.79 Duration System 44298.10 13361.67 Duration Elapsed 519.11 388.87 The patch reduces system CPU usage by 69.86% and total build time by 26.65%. The variance of system CPU usage is also much reduced. Before, this was the breakdown of batch and high values over all zones was. 256 batch: 1 256 batch: 63 512 batch: 7 256 high: 0 256 high: 378 512 high: 42 512 pcpu pagesets had a batch limit of 7 and a high limit of 42. After the patch: 256 batch: 1 768 batch: 63 256 high: 0 768 high: 378 [mgorman(a)techsingularity.net: fix merge/linkage snafu] Link: http://lkml.kernel.org/r/20191023084705.GD3016@techsingularity.netLink: http://lkml.kernel.org/r/20191021094808.28824-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman(a)techsingularity.net> Acked-by: Michal Hocko <mhocko(a)suse.com> Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Matt Fleming <matt(a)codeblueprint.co.uk> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Qian Cai <cai(a)lca.pw> Cc: <stable(a)vger.kernel.org> [4.1+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) --- a/mm/page_alloc.c~mm-meminit-recalculate-pcpu-batch-and-high-limits-after-init-completes +++ a/mm/page_alloc.c @@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -8514,7 +8522,6 @@ void free_contig_range(unsigned long pfn WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. @@ -8528,7 +8535,6 @@ void __meminit zone_pcp_update(struct zo per_cpu_ptr(zone->pageset, cpu)); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { _

6 years

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror