From f4cb767d76cf7ee72f97dd76f6cfa6c76a5edc89 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 20 Jun 2017 02:10:44 -0700 Subject: mm: fix new crash in unmapped_area_topdown() Trinity gets kernel BUG at mm/mmap.c:1963! in about 3 minutes of mmap testing. That's the VM_BUG_ON(gap_end < gap_start) at the end of unmapped_area_topdown(). Linus points out how MAP_FIXED (which does not have to respect our stack guard gap intentions) could result in gap_end below gap_start there. Fix that, and the similar case in its alternative, unmapped_area(). Cc: stable@vger.kernel.org Fixes: 1be7107fbe18 ("mm: larger stack guard gap, between vmas") Reported-by: Dave Jones Debugged-by: Linus Torvalds Signed-off-by: Hugh Dickins Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- mm/mmap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 8e07976d5e47..290b77d9a01e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1817,7 +1817,8 @@ check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; - if (gap_end >= low_limit && gap_end - gap_start >= length) + if (gap_end >= low_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ @@ -1920,7 +1921,8 @@ check_current: gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; - if (gap_start <= high_limit && gap_end - gap_start >= length) + if (gap_start <= high_limit && + gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ -- cgit From bd726c90b6b8ce87602208701b208a208e6d5600 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 19 Jun 2017 17:34:05 +0200 Subject: Allow stack to grow up to address space limit Fix expand_upwards() on architectures with an upward-growing stack (parisc, metag and partly IA-64) to allow the stack to reliably grow exactly up to the address space limit given by TASK_SIZE. Signed-off-by: Helge Deller Acked-by: Hugh Dickins Signed-off-by: Linus Torvalds --- mm/mmap.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 290b77d9a01e..a5e3dcd75e79 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2230,16 +2230,19 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* Guard against wrapping around to address 0. */ + /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; - address += PAGE_SIZE; - if (!address) + if (address >= TASK_SIZE) return -ENOMEM; + address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; - if (gap_addr < address) - return -ENOMEM; + + /* Guard against overflow */ + if (gap_addr < address || gap_addr > TASK_SIZE) + gap_addr = TASK_SIZE; + next = vma->vm_next; if (next && next->vm_start < gap_addr) { if (!(next->vm_flags & VM_GROWSUP)) -- cgit From c891d9f6bf2a78c9c657656872a60807820db4c8 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 23 Jun 2017 15:08:38 -0700 Subject: mm, thp: remove cond_resched from __collapse_huge_page_copy This is a partial revert of commit 338a16ba1549 ("mm, thp: copying user pages must schedule on collapse") which added a cond_resched() to __collapse_huge_page_copy(). On x86 with CONFIG_HIGHPTE, __collapse_huge_page_copy is called in atomic context and thus scheduling is not possible. This is only a possible config on arm and i386. Although need_resched has been shown to be set for over 100 jiffies while doing the iteration in __collapse_huge_page_copy, this is better than doing if (in_atomic()) cond_resched() to cover only non-CONFIG_HIGHPTE configs. Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1706191341550.97821@chino.kir.corp.google.com Signed-off-by: David Rientjes Reported-by: Larry Finger Tested-by: Larry Finger Acked-by: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/khugepaged.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 945fd1ca49b5..df4ebdb2b10a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -652,7 +652,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, spin_unlock(ptl); free_page_and_swap_cache(src_page); } - cond_resched(); } } -- cgit From 029c54b09599573015a5c18dbe59cbdf42742237 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 23 Jun 2017 15:08:41 -0700 Subject: mm/vmalloc.c: huge-vmap: fail gracefully on unexpected huge vmap mappings Existing code that uses vmalloc_to_page() may assume that any address for which is_vmalloc_addr() returns true may be passed into vmalloc_to_page() to retrieve the associated struct page. This is not un unreasonable assumption to make, but on architectures that have CONFIG_HAVE_ARCH_HUGE_VMAP=y, it no longer holds, and we need to ensure that vmalloc_to_page() does not go off into the weeds trying to dereference huge PUDs or PMDs as table entries. Given that vmalloc() and vmap() themselves never create huge mappings or deal with compound pages at all, there is no correct answer in this case, so return NULL instead, and issue a warning. When reading /proc/kcore on arm64, you will hit an oops as soon as you hit the huge mappings used for the various segments that make up the mapping of vmlinux. With this patch applied, you will no longer hit the oops, but the kcore contents willl be incorrect (these regions will be zeroed out) We are fixing this for kcore specifically, so it avoids vread() for those regions. At least one other problematic user exists, i.e., /dev/kmem, but that is currently broken on arm64 for other reasons. Link: http://lkml.kernel.org/r/20170609082226.26152-1-ard.biesheuvel@linaro.org Signed-off-by: Ard Biesheuvel Acked-by: Mark Rutland Reviewed-by: Laura Abbott Cc: Michal Hocko Cc: zhong jiang Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 34a1c3e46ed7..ecc97f74ab18 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -287,10 +287,21 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (p4d_none(*p4d)) return NULL; pud = pud_offset(p4d, addr); - if (pud_none(*pud)) + + /* + * Don't dereference bad PUD or PMD (below) entries. This will also + * identify huge mappings, which we may encounter on architectures + * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be + * identified as vmalloc addresses by is_vmalloc_addr(), but are + * not [unambiguously] associated with a struct page, so there is + * no correct value to return for them. + */ + WARN_ON_ONCE(pud_bad(*pud)); + if (pud_none(*pud) || pud_bad(*pud)) return NULL; pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + WARN_ON_ONCE(pmd_bad(*pmd)); + if (pmd_none(*pmd) || pmd_bad(*pmd)) return NULL; ptep = pte_offset_map(pmd, addr); -- cgit From 3b7b314053d021601940c50b07f5f1423ae67e21 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 23 Jun 2017 15:08:52 -0700 Subject: slub: make sysfs file removal asynchronous Commit bf5eb3de3847 ("slub: separate out sysfs_slab_release() from sysfs_slab_remove()") made slub sysfs file removals synchronous to kmem_cache shutdown. Unfortunately, this created a possible ABBA deadlock between slab_mutex and sysfs draining mechanism triggering the following lockdep warning. ====================================================== [ INFO: possible circular locking dependency detected ] 4.10.0-test+ #48 Not tainted ------------------------------------------------------- rmmod/1211 is trying to acquire lock: (s_active#120){++++.+}, at: [] kernfs_remove+0x23/0x40 but task is already holding lock: (slab_mutex){+.+.+.}, at: [] kmem_cache_destroy+0x41/0x2d0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (slab_mutex){+.+.+.}: lock_acquire+0xf6/0x1f0 __mutex_lock+0x75/0x950 mutex_lock_nested+0x1b/0x20 slab_attr_store+0x75/0xd0 sysfs_kf_write+0x45/0x60 kernfs_fop_write+0x13c/0x1c0 __vfs_write+0x28/0x120 vfs_write+0xc8/0x1e0 SyS_write+0x49/0xa0 entry_SYSCALL_64_fastpath+0x1f/0xc2 -> #0 (s_active#120){++++.+}: __lock_acquire+0x10ed/0x1260 lock_acquire+0xf6/0x1f0 __kernfs_remove+0x254/0x320 kernfs_remove+0x23/0x40 sysfs_remove_dir+0x51/0x80 kobject_del+0x18/0x50 __kmem_cache_shutdown+0x3e6/0x460 kmem_cache_destroy+0x1fb/0x2d0 kvm_exit+0x2d/0x80 [kvm] vmx_exit+0x19/0xa1b [kvm_intel] SyS_delete_module+0x198/0x1f0 entry_SYSCALL_64_fastpath+0x1f/0xc2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(slab_mutex); lock(s_active#120); lock(slab_mutex); lock(s_active#120); *** DEADLOCK *** 2 locks held by rmmod/1211: #0: (cpu_hotplug.dep_map){++++++}, at: [] get_online_cpus+0x37/0x80 #1: (slab_mutex){+.+.+.}, at: [] kmem_cache_destroy+0x41/0x2d0 stack backtrace: CPU: 3 PID: 1211 Comm: rmmod Not tainted 4.10.0-test+ #48 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v02.05 05/07/2012 Call Trace: print_circular_bug+0x1be/0x210 __lock_acquire+0x10ed/0x1260 lock_acquire+0xf6/0x1f0 __kernfs_remove+0x254/0x320 kernfs_remove+0x23/0x40 sysfs_remove_dir+0x51/0x80 kobject_del+0x18/0x50 __kmem_cache_shutdown+0x3e6/0x460 kmem_cache_destroy+0x1fb/0x2d0 kvm_exit+0x2d/0x80 [kvm] vmx_exit+0x19/0xa1b [kvm_intel] SyS_delete_module+0x198/0x1f0 ? SyS_delete_module+0x5/0x1f0 entry_SYSCALL_64_fastpath+0x1f/0xc2 It'd be the cleanest to deal with the issue by removing sysfs files without holding slab_mutex before the rest of shutdown; however, given the current code structure, it is pretty difficult to do so. This patch punts sysfs file removal to a work item. Before commit bf5eb3de3847, the removal was punted to a RCU delayed work item which is executed after release. Now, we're punting to a different work item on shutdown which still maintains the goal removing the sysfs files earlier when destroying kmem_caches. Link: http://lkml.kernel.org/r/20170620204512.GI21326@htj.duckdns.org Fixes: bf5eb3de3847 ("slub: separate out sysfs_slab_release() from sysfs_slab_remove()") Signed-off-by: Tejun Heo Reported-by: Steven Rostedt (VMware) Tested-by: Steven Rostedt (VMware) Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 40 ++++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 7449593fca72..8addc535bcdc 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5625,6 +5625,28 @@ static char *create_unique_id(struct kmem_cache *s) return name; } +static void sysfs_slab_remove_workfn(struct work_struct *work) +{ + struct kmem_cache *s = + container_of(work, struct kmem_cache, kobj_remove_work); + + if (!s->kobj.state_in_sysfs) + /* + * For a memcg cache, this may be called during + * deactivation and again on shutdown. Remove only once. + * A cache is never shut down before deactivation is + * complete, so no need to worry about synchronization. + */ + return; + +#ifdef CONFIG_MEMCG + kset_unregister(s->memcg_kset); +#endif + kobject_uevent(&s->kobj, KOBJ_REMOVE); + kobject_del(&s->kobj); + kobject_put(&s->kobj); +} + static int sysfs_slab_add(struct kmem_cache *s) { int err; @@ -5632,6 +5654,8 @@ static int sysfs_slab_add(struct kmem_cache *s) struct kset *kset = cache_kset(s); int unmergeable = slab_unmergeable(s); + INIT_WORK(&s->kobj_remove_work, sysfs_slab_remove_workfn); + if (!kset) { kobject_init(&s->kobj, &slab_ktype); return 0; @@ -5695,20 +5719,8 @@ static void sysfs_slab_remove(struct kmem_cache *s) */ return; - if (!s->kobj.state_in_sysfs) - /* - * For a memcg cache, this may be called during - * deactivation and again on shutdown. Remove only once. - * A cache is never shut down before deactivation is - * complete, so no need to worry about synchronization. - */ - return; - -#ifdef CONFIG_MEMCG - kset_unregister(s->memcg_kset); -#endif - kobject_uevent(&s->kobj, KOBJ_REMOVE); - kobject_del(&s->kobj); + kobject_get(&s->kobj); + schedule_work(&s->kobj_remove_work); } void sysfs_slab_release(struct kmem_cache *s) -- cgit