From 7258ae5c5a2ce2f5969e8b18b881be40ab55433d Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 16 Jun 2017 14:02:29 -0700 Subject: mm/memory-failure.c: use compound_head() flags for huge pages memory_failure() chooses a recovery action function based on the page flags. For huge pages it uses the tail page flags which don't have anything interesting set, resulting in: > Memory failure: 0x9be3b4: Unknown page state > Memory failure: 0x9be3b4: recovery action for unknown page: Failed Instead, save a copy of the head page's flags if this is a huge page, this means if there are no relevant flags for this tail page, we use the head pages flags instead. This results in the me_huge_page() recovery action being called: > Memory failure: 0x9b7969: recovery action for huge page: Delayed For hugepages that have not yet been allocated, this allows the hugepage to be dequeued. Fixes: 524fca1e7356 ("HWPOISON: fix misjudgement of page_action() for errors on mlocked pages") Link: http://lkml.kernel.org/r/20170524130204.21845-1-james.morse@arm.com Signed-off-by: James Morse Tested-by: Punit Agrawal Acked-by: Punit Agrawal Acked-by: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 342fac9ba89b..ecc183fd94f3 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1184,7 +1184,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * page_remove_rmap() in try_to_unmap_one(). So to determine page status * correctly, we save a copy of the page flags at this time. */ - page_flags = p->flags; + if (PageHuge(p)) + page_flags = hpage->flags; + else + page_flags = p->flags; /* * unpoison always clear PG_hwpoison inside page lock -- cgit v1.2.3 From ef70762948dde012146926720b70e79736336764 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 16 Jun 2017 14:02:31 -0700 Subject: swap: cond_resched in swap_cgroup_prepare() I saw need_resched() warnings when swapping on large swapfile (TBs) because continuously allocating many pages in swap_cgroup_prepare() took too long. We already cond_resched when freeing page in swap_cgroup_swapoff(). Do the same for the page allocation. Link: http://lkml.kernel.org/r/20170604200109.17606-1-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Michal Hocko Acked-by: Vladimir Davydov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap_cgroup.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c index ac6318a064d3..3405b4ee1757 100644 --- a/mm/swap_cgroup.c +++ b/mm/swap_cgroup.c @@ -48,6 +48,9 @@ static int swap_cgroup_prepare(int type) if (!page) goto not_enough_page; ctrl->map[idx] = page; + + if (!(idx % SWAP_CLUSTER_MAX)) + cond_resched(); } return 0; not_enough_page: -- cgit v1.2.3 From 3c226c637b69104f6b9f1c6ec5b08d7b741b3229 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 16 Jun 2017 14:02:34 -0700 Subject: mm: numa: avoid waiting on freed migrated pages In do_huge_pmd_numa_page(), we attempt to handle a migrating thp pmd by waiting until the pmd is unlocked before we return and retry. However, we can race with migrate_misplaced_transhuge_page(): // do_huge_pmd_numa_page // migrate_misplaced_transhuge_page() // Holds 0 refs on page // Holds 2 refs on page vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); /* ... */ if (pmd_trans_migrating(*vmf->pmd)) { page = pmd_page(*vmf->pmd); spin_unlock(vmf->ptl); ptl = pmd_lock(mm, pmd); if (page_count(page) != 2)) { /* roll back */ } /* ... */ mlock_migrate_page(new_page, page); /* ... */ spin_unlock(ptl); put_page(page); put_page(page); // page freed here wait_on_page_locked(page); goto out; } This can result in the freed page having its waiters flag set unexpectedly, which trips the PAGE_FLAGS_CHECK_AT_PREP checks in the page alloc/free functions. This has been observed on arm64 KVM guests. We can avoid this by having do_huge_pmd_numa_page() take a reference on the page before dropping the pmd lock, mirroring what we do in __migration_entry_wait(). When we hit the race, migrate_misplaced_transhuge_page() will see the reference and abort the migration, as it may do today in other cases. Fixes: b8916634b77bffb2 ("mm: Prevent parallel splits during THP migration") Link: http://lkml.kernel.org/r/1497349722-6731-2-git-send-email-will.deacon@arm.com Signed-off-by: Mark Rutland Signed-off-by: Will Deacon Acked-by: Steve Capper Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a84909cf20d3..88c6167f194d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1426,8 +1426,11 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) */ if (unlikely(pmd_trans_migrating(*vmf->pmd))) { page = pmd_page(*vmf->pmd); + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(vmf->ptl); wait_on_page_locked(page); + put_page(page); goto out; } @@ -1459,9 +1462,12 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { + page_nid = -1; + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(vmf->ptl); wait_on_page_locked(page); - page_nid = -1; + put_page(page); goto out; } -- cgit v1.2.3 From d7143e31259cb029e207619209b31aa7520f8e28 Mon Sep 17 00:00:00 2001 From: zhongjiang Date: Fri, 16 Jun 2017 14:02:40 -0700 Subject: mm: correct the comment when reclaimed pages exceed the scanned pages Commit e1587a494540 ("mm: vmpressure: fix sending wrong events on underflow") declared that reclaimed pages exceed the scanned pages due to the thp reclaim. That is incorrect because THP will be spilt to normal page and loop again, which will result in the scanned pages increment. [akpm@linux-foundation.org: tweak comment text] Link: http://lkml.kernel.org/r/1496824266-25235-1-git-send-email-zhongjiang@huawei.com Signed-off-by: zhongjiang Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmpressure.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 6063581f705c..ce0618bfa8d0 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -115,9 +115,9 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long pressure = 0; /* - * reclaimed can be greater than scanned in cases - * like THP, where the scanned is 1 and reclaimed - * could be 512 + * reclaimed can be greater than scanned for things such as reclaimed + * slab pages. shrink_node() just adds reclaimed pages without a + * related increment to scanned pages. */ if (reclaimed >= scanned) goto out; -- cgit v1.2.3 From 1be7107fbe18eed3e319a6c3e83c78254b693acb Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 19 Jun 2017 04:03:24 -0700 Subject: mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov Original-patch-by: Michal Hocko Signed-off-by: Hugh Dickins Acked-by: Michal Hocko Tested-by: Helge Deller # parisc Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 7 ++ arch/arc/mm/mmap.c | 2 +- arch/arm/mm/mmap.c | 4 +- arch/frv/mm/elf-fdpic.c | 2 +- arch/mips/mm/mmap.c | 2 +- arch/parisc/kernel/sys_parisc.c | 15 ++- arch/powerpc/mm/hugetlbpage-radix.c | 2 +- arch/powerpc/mm/mmap.c | 4 +- arch/powerpc/mm/slice.c | 2 +- arch/s390/mm/mmap.c | 4 +- arch/sh/mm/mmap.c | 4 +- arch/sparc/kernel/sys_sparc_64.c | 4 +- arch/sparc/mm/hugetlbpage.c | 2 +- arch/tile/mm/hugetlbpage.c | 2 +- arch/x86/kernel/sys_x86_64.c | 4 +- arch/x86/mm/hugetlbpage.c | 2 +- arch/xtensa/kernel/syscall.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/proc/task_mmu.c | 4 - include/linux/mm.h | 53 ++++----- mm/gup.c | 5 - mm/memory.c | 38 ------ mm/mmap.c | 149 ++++++++++++++---------- 23 files changed, 152 insertions(+), 163 deletions(-) (limited to 'mm') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0f5c3b4347c6..7737ab5d04b2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3811,6 +3811,13 @@ expediting. Set to zero to disable automatic expediting. + stack_guard_gap= [MM] + override the default stack gap protection. The value + is in page units and it defines how many pages prior + to (for stacks growing down) resp. after (for stacks + growing up) the main stack are reserved for no other + mapping. Default value is 256 pages. + stacktrace [FTRACE] Enabled the stack tracer on boot up. diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 3e25e8d6486b..2e13683dfb24 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -65,7 +65,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 2239fde10b80..f0701d8d24df 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -90,7 +90,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -141,7 +141,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/frv/mm/elf-fdpic.c b/arch/frv/mm/elf-fdpic.c index da82c25301e7..46aa289c5102 100644 --- a/arch/frv/mm/elf-fdpic.c +++ b/arch/frv/mm/elf-fdpic.c @@ -75,7 +75,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi addr = PAGE_ALIGN(addr); vma = find_vma(current->mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto success; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 64dd8bdd92c3..28adeabe851f 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -93,7 +93,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index e5288638a1d9..378a754ca186 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -90,7 +90,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; unsigned long task_size = TASK_SIZE; int do_color_align, last_mmap; struct vm_unmapped_area_info info; @@ -117,9 +117,10 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } @@ -143,7 +144,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; int do_color_align, last_mmap; @@ -177,9 +178,11 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = COLOR_ALIGN(addr, last_mmap, pgoff); else addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) goto found_addr; } diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 6575b9aabef4..a12e86395025 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -68,7 +68,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } /* diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 9dbd2a733d6b..0ee6be4f1ba4 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -112,7 +112,7 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -157,7 +157,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 966b9fccfa66..45f6740dd407 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -99,7 +99,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, if ((mm->task_size - len) < addr) return 0; vma = find_vma(mm, addr); - return (!vma || (addr + len) <= vma->vm_start); + return (!vma || (addr + len) <= vm_start_gap(vma)); } static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b017daed6887..b854b1da281a 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -101,7 +101,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto check_asce_limit; } @@ -151,7 +151,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) goto check_asce_limit; } diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index 08e7af0be4a7..6a1a1297baae 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -64,7 +64,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -114,7 +114,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index ef4520efc813..043544d0cda3 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -120,7 +120,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -183,7 +183,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 7c29d38e6b99..88855e383b34 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -120,7 +120,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index cb10153b5c9f..03e5cc4e76e4 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -233,7 +233,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (current->mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 207b8f2582c7..213ddf3e937d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -187,7 +187,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 302f43fd9c28..adad702b39cd 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -148,7 +148,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index 06937928cb72..74afbf02d07e 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -88,7 +88,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, /* At this point: (!vmm || addr < vmm->vm_end). */ if (TASK_SIZE - len < addr) return -ENOMEM; - if (!vmm || addr + len <= vmm->vm_start) + if (!vmm || addr + len <= vm_start_gap(vmm)) return addr; addr = vmm->vm_end; if (flags & MAP_SHARED) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index dde861387a40..d44f5456eb9b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -200,7 +200,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0c8b33d99b1..520802da059c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -300,11 +300,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; - if (stack_guard_page_start(vma, start)) - start += PAGE_SIZE; end = vma->vm_end; - if (stack_guard_page_end(vma, end)) - end -= PAGE_SIZE; seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", diff --git a/include/linux/mm.h b/include/linux/mm.h index b892e95d4929..6f543a47fc92 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1393,12 +1393,6 @@ int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); -/* Is the vma a continuation of the stack vma above it? */ -static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); -} - static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; @@ -1414,28 +1408,6 @@ bool vma_is_shmem(struct vm_area_struct *vma); static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif -static inline int stack_guard_page_start(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_growsdown(vma->vm_prev, addr); -} - -/* Is the vma a continuation of the stack vma below it? */ -static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) -{ - return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); -} - -static inline int stack_guard_page_end(struct vm_area_struct *vma, - unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSUP) && - (vma->vm_end == addr) && - !vma_growsup(vma->vm_next, addr); -} - int vma_is_stack_for_current(struct vm_area_struct *vma); extern unsigned long move_page_tables(struct vm_area_struct *vma, @@ -2222,6 +2194,7 @@ void page_cache_async_readahead(struct address_space *mapping, pgoff_t offset, unsigned long size); +extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); @@ -2250,6 +2223,30 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m return vma; } +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long vm_start = vma->vm_start; + + if (vma->vm_flags & VM_GROWSDOWN) { + vm_start -= stack_guard_gap; + if (vm_start > vma->vm_start) + vm_start = 0; + } + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; diff --git a/mm/gup.c b/mm/gup.c index b3c7214d710d..576c4df58882 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -387,11 +387,6 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, /* mlock all present pages, but do not fault in new pages */ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) return -ENOENT; - /* For mm_populate(), just skip the stack guard page. */ - if ((*flags & FOLL_POPULATE) && - (stack_guard_page_start(vma, address) || - stack_guard_page_end(vma, address + PAGE_SIZE))) - return -ENOENT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) diff --git a/mm/memory.c b/mm/memory.c index 2e65df1831d9..bb11c474857e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2854,40 +2854,6 @@ out_release: return ret; } -/* - * This is like a special single-page "expand_{down|up}wards()", - * except we must first make sure that 'address{-|+}PAGE_SIZE' - * doesn't hit another vma. - */ -static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) -{ - address &= PAGE_MASK; - if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) { - struct vm_area_struct *prev = vma->vm_prev; - - /* - * Is there a mapping abutting this one below? - * - * That's only ok if it's the same stack mapping - * that has gotten split.. - */ - if (prev && prev->vm_end == address) - return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - - return expand_downwards(vma, address - PAGE_SIZE); - } - if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { - struct vm_area_struct *next = vma->vm_next; - - /* As VM_GROWSDOWN but s/below/above/ */ - if (next && next->vm_start == address + PAGE_SIZE) - return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - - return expand_upwards(vma, address + PAGE_SIZE); - } - return 0; -} - /* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -2904,10 +2870,6 @@ static int do_anonymous_page(struct vm_fault *vmf) if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; - /* Check if we need to add a guard page to the stack */ - if (check_stack_guard_page(vma, vmf->address) < 0) - return VM_FAULT_SIGSEGV; - /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created diff --git a/mm/mmap.c b/mm/mmap.c index f82741e199c0..8e07976d5e47 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -183,6 +183,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) unsigned long retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; + struct vm_area_struct *next; unsigned long min_brk; bool populate; LIST_HEAD(uf); @@ -229,7 +230,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) } /* Check against existing mmap mappings. */ - if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE)) + next = find_vma(mm, oldbrk); + if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ @@ -253,10 +255,22 @@ out: static long vma_compute_subtree_gap(struct vm_area_struct *vma) { - unsigned long max, subtree_gap; - max = vma->vm_start; - if (vma->vm_prev) - max -= vma->vm_prev->vm_end; + unsigned long max, prev_end, subtree_gap; + + /* + * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we + * allow two stack_guard_gaps between them here, and when choosing + * an unmapped area; whereas when expanding we only require one. + * That's a little inconsistent, but keeps the code here simpler. + */ + max = vm_start_gap(vma); + if (vma->vm_prev) { + prev_end = vm_end_gap(vma->vm_prev); + if (max > prev_end) + max -= prev_end; + else + max = 0; + } if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; @@ -352,7 +366,7 @@ static void validate_mm(struct mm_struct *mm) anon_vma_unlock_read(anon_vma); } - highest_address = vma->vm_end; + highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } @@ -541,7 +555,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = vma->vm_end; + mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the @@ -856,7 +870,7 @@ again: vma_gap_update(vma); if (end_changed) { if (!next) - mm->highest_vm_end = end; + mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } @@ -941,7 +955,7 @@ again: * mm->highest_vm_end doesn't need any update * in remove_next == 1 case. */ - VM_WARN_ON(mm->highest_vm_end != end); + VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } } if (insert && file) @@ -1787,7 +1801,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) while (true) { /* Visit left subtree if it looks promising */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, @@ -1798,7 +1812,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) } } - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) @@ -1825,8 +1839,8 @@ check_current: vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { - gap_start = vma->vm_prev->vm_end; - gap_end = vma->vm_start; + gap_start = vm_end_gap(vma->vm_prev); + gap_end = vm_start_gap(vma); goto check_current; } } @@ -1890,7 +1904,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) while (true) { /* Visit right subtree if it looks promising */ - gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0; + gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, @@ -1903,7 +1917,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) check_current: /* Check if current node has a suitable gap */ - gap_end = vma->vm_start; + gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && gap_end - gap_start >= length) @@ -1929,7 +1943,7 @@ check_current: struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? - vma->vm_prev->vm_end : 0; + vm_end_gap(vma->vm_prev) : 0; goto check_current; } } @@ -1967,7 +1981,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; if (len > TASK_SIZE - mmap_min_addr) @@ -1978,9 +1992,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -2003,7 +2018,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; @@ -2018,9 +2033,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); - vma = find_vma(mm, addr); + vma = find_vma_prev(mm, addr, &prev); if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) return addr; } @@ -2155,21 +2171,19 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, * update accounting. This is shared with both the * grow-up and grow-down cases. */ -static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) +static int acct_stack_growth(struct vm_area_struct *vma, + unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start, actual_size; + unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ - actual_size = size; - if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) - actual_size -= PAGE_SIZE; - if (actual_size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2207,17 +2221,30 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *next; + unsigned long gap_addr; int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else + address &= PAGE_MASK; + address += PAGE_SIZE; + if (!address) return -ENOMEM; + /* Enforce stack_guard_gap */ + gap_addr = address + stack_guard_gap; + if (gap_addr < address) + return -ENOMEM; + next = vma->vm_next; + if (next && next->vm_start < gap_addr) { + if (!(next->vm_flags & VM_GROWSUP)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; @@ -2261,7 +2288,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (vma->vm_next) vma_gap_update(vma->vm_next); else - mm->highest_vm_end = address; + mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); @@ -2282,6 +2309,8 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; + struct vm_area_struct *prev; + unsigned long gap_addr; int error; address &= PAGE_MASK; @@ -2289,6 +2318,17 @@ int expand_downwards(struct vm_area_struct *vma, if (error) return error; + /* Enforce stack_guard_gap */ + gap_addr = address - stack_guard_gap; + if (gap_addr > address) + return -ENOMEM; + prev = vma->vm_prev; + if (prev && prev->vm_end > gap_addr) { + if (!(prev->vm_flags & VM_GROWSDOWN)) + return -ENOMEM; + /* Check that both stack segments have the same anon_vma? */ + } + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; @@ -2343,28 +2383,25 @@ int expand_downwards(struct vm_area_struct *vma, return error; } -/* - * Note how expand_stack() refuses to expand the stack all the way to - * abut the next virtual mapping, *unless* that mapping itself is also - * a stack mapping. We want to leave room for a guard page, after all - * (the guard page itself is not added here, that is done by the - * actual page faulting logic) - * - * This matches the behavior of the guard page logic (see mm/memory.c: - * check_stack_guard_page()), which only allows the guard page to be - * removed under these circumstances. - */ +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL< 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 v1.2.3 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 v1.2.3