From 41b6167e8f746b475668f1da78599fc4284f18db Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 10 Jan 2017 16:57:42 -0800 Subject: mm: get rid of __GFP_OTHER_NODE The flag was introduced by commit 78afd5612deb ("mm: add __GFP_OTHER_NODE flag") to allow proper accounting of remote node allocations done by kernel daemons on behalf of a process - e.g. khugepaged. After "mm: fix remote numa hits statistics" we do not need and actually use the flag so we can safely remove it because all allocations which are satisfied from their "home" node are accounted properly. [mhocko@suse.com: fix build] Link: http://lkml.kernel.org/r/20170106122225.GK5556@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170102153057.9451-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Taku Izumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 10eedbf14421..72339a646fb1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -919,8 +919,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, } for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE | - __GFP_OTHER_NODE, vma, + pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma, vmf->address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_try_charge(pages[i], vma->vm_mm, -- cgit From 20f664aabeb88d582b623a625f83b0454fa34f07 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 10 Jan 2017 16:57:51 -0800 Subject: mm: pmd dirty emulation in page fault handler Andreas reported [1] made a test in jemalloc hang in THP mode in arm64: http://lkml.kernel.org/r/mvmmvfy37g1.fsf@hawking.suse.de The problem is currently page fault handler doesn't supports dirty bit emulation of pmd for non-HW dirty-bit architecture so that application stucks until VM marked the pmd dirty. How the emulation work depends on the architecture. In case of arm64, when it set up pte firstly, it sets pte PTE_RDONLY to get a chance to mark the pte dirty via triggering page fault when store access happens. Once the page fault occurs, VM marks the pmd dirty and arch code for setting pmd will clear PTE_RDONLY for application to proceed. IOW, if VM doesn't mark the pmd dirty, application hangs forever by repeated fault(i.e., store op but the pmd is PTE_RDONLY). This patch enables pmd dirty-bit emulation for those architectures. [1] b8d3c4c3009d, mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called Fixes: b8d3c4c3009d ("mm/huge_memory.c: don't split THP page when MADV_FREE syscall is called") Link: http://lkml.kernel.org/r/1482506098-6149-1-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim Reported-by: Andreas Schwab Tested-by: Andreas Schwab Acked-by: Kirill A. Shutemov Acked-by: Michal Hocko Cc: Jason Evans Cc: Will Deacon Cc: Catalin Marinas Cc: [4.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 72339a646fb1..9a6bd6c8d55a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) { pmd_t entry; unsigned long haddr; + bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) goto unlock; entry = pmd_mkyoung(orig_pmd); + if (write) + entry = pmd_mkdirty(entry); haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, - vmf->flags & FAULT_FLAG_WRITE)) + if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); unlock: -- cgit From 8310d48b125d19fcd9521d83b8293e63eb1646aa Mon Sep 17 00:00:00 2001 From: Keno Fischer Date: Tue, 24 Jan 2017 15:17:48 -0800 Subject: mm/huge_memory.c: respect FOLL_FORCE/FOLL_COW for thp In commit 19be0eaffa3a ("mm: remove gup_flags FOLL_WRITE games from __get_user_pages()"), the mm code was changed from unsetting FOLL_WRITE after a COW was resolved to setting the (newly introduced) FOLL_COW instead. Simultaneously, the check in gup.c was updated to still allow writes with FOLL_FORCE set if FOLL_COW had also been set. However, a similar check in huge_memory.c was forgotten. As a result, remote memory writes to ro regions of memory backed by transparent huge pages cause an infinite loop in the kernel (handle_mm_fault sets FOLL_COW and returns 0 causing a retry, but follow_trans_huge_pmd bails out immidiately because `(flags & FOLL_WRITE) && !pmd_write(*pmd)` is true. While in this state the process is stil SIGKILLable, but little else works (e.g. no ptrace attach, no other signals). This is easily reproduced with the following code (assuming thp are set to always): #include #include #include #include #include #include #include #include #include #include #define TEST_SIZE 5 * 1024 * 1024 int main(void) { int status; pid_t child; int fd = open("/proc/self/mem", O_RDWR); void *addr = mmap(NULL, TEST_SIZE, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); assert(addr != MAP_FAILED); pid_t parent_pid = getpid(); if ((child = fork()) == 0) { void *addr2 = mmap(NULL, TEST_SIZE, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); assert(addr2 != MAP_FAILED); memset(addr2, 'a', TEST_SIZE); pwrite(fd, addr2, TEST_SIZE, (uintptr_t)addr); return 0; } assert(child == waitpid(child, &status, 0)); assert(WIFEXITED(status) && WEXITSTATUS(status) == 0); return 0; } Fix this by updating follow_trans_huge_pmd in huge_memory.c analogously to the update in gup.c in the original commit. The same pattern exists in follow_devmap_pmd. However, we should not be able to reach that check with FOLL_COW set, so add WARN_ONCE to make sure we notice if we ever do. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170106015025.GA38411@juliacomputing.com Signed-off-by: Keno Fischer Acked-by: Kirill A. Shutemov Cc: Greg Thelen Cc: Nicholas Piggin Cc: Willy Tarreau Cc: Oleg Nesterov Cc: Kees Cook Cc: Andy Lutomirski Cc: Michal Hocko Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9a6bd6c8d55a..5f3ad65c85de 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -783,6 +783,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); + /* + * When we COW a devmap PMD entry, we split it into PTEs, so we should + * not be in this function with `flags & FOLL_COW` set. + */ + WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); + if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; @@ -1128,6 +1134,16 @@ out_unlock: return ret; } +/* + * FOLL_FORCE can write to even unwritable pmd's, but only + * after we've gone through a COW cycle and they are dirty. + */ +static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +{ + return pmd_write(pmd) || + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); +} + struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -1138,7 +1154,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !pmd_write(*pmd)) + if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) goto out; /* Avoid dumping huge zero page */ -- cgit