diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 1 | ||||
| -rw-r--r-- | mm/Makefile | 3 | ||||
| -rw-r--r-- | mm/debug.c | 4 | ||||
| -rw-r--r-- | mm/fadvise.c | 81 | ||||
| -rw-r--r-- | mm/hmm.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 8 | ||||
| -rw-r--r-- | mm/kmemleak.c | 9 | ||||
| -rw-r--r-- | mm/madvise.c | 16 | ||||
| -rw-r--r-- | mm/memcontrol.c | 2 | ||||
| -rw-r--r-- | mm/memory-failure.c | 210 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 3 | ||||
| -rw-r--r-- | mm/oom_kill.c | 14 | ||||
| -rw-r--r-- | mm/page-writeback.c | 1 | ||||
| -rw-r--r-- | mm/page_alloc.c | 5 | ||||
| -rw-r--r-- | mm/readahead.c | 45 | ||||
| -rw-r--r-- | mm/shmem.c | 2 | ||||
| -rw-r--r-- | mm/slub.c | 1 | ||||
| -rw-r--r-- | mm/util.c | 11 | ||||
| -rw-r--r-- | mm/vmacache.c | 38 | ||||
| -rw-r--r-- | mm/vmscan.c | 11 |
20 files changed, 299 insertions, 168 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index a550635ea5c3..de64ea658716 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -637,6 +637,7 @@ config DEFERRED_STRUCT_PAGE_INIT depends on NO_BOOTMEM depends on SPARSEMEM depends on !NEED_PER_CPU_KM + depends on 64BIT help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable diff --git a/mm/Makefile b/mm/Makefile index 8716bdabe1e6..26ef77a3883b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif -obj-y := filemap.o mempool.o oom_kill.o \ +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ @@ -49,7 +49,6 @@ else obj-y += bootmem.o endif -obj-$(CONFIG_ADVISE_SYSCALLS) += fadvise.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/fadvise.c b/mm/fadvise.c index 2d8376e3c640..467bcd032037 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -27,9 +27,9 @@ * deactivate the pages and clear PG_Referenced. */ -int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +static int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice) { - struct fd f = fdget(fd); struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; @@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; - int ret = 0; - - if (!f.file) - return -EBADF; - inode = file_inode(f.file); - if (S_ISFIFO(inode->i_mode)) { - ret = -ESPIPE; - goto out; - } + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; - mapping = f.file->f_mapping; - if (!mapping || len < 0) { - ret = -EINVAL; - goto out; - } + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; bdi = inode_to_bdi(mapping->host); @@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* no bad return value, but ignore advice */ break; default: - ret = -EINVAL; + return -EINVAL; } - goto out; + return 0; } /* @@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: - f.file->f_ra.ra_pages = bdi->ra_pages; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - spin_lock(&f.file->f_lock); - f.file->f_mode |= FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: - f.file->f_ra.ra_pages = bdi->ra_pages * 2; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ @@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) * Ignore return value because fadvise() shall return * success even if filesystem can't retrieve a hint, */ - force_page_cache_readahead(mapping, f.file, start_index, - nrpages); + force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: break; @@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) } break; default: - ret = -EINVAL; + return -EINVAL; } -out: + return 0; +} + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +#ifdef CONFIG_ADVISE_SYSCALLS + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + fdput(f); return ret; } @@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) } #endif +#endif @@ -968,6 +968,8 @@ static void hmm_devmem_free(struct page *page, void *data) { struct hmm_devmem *devmem = data; + page->mapping = NULL; + devmem->ops->free(devmem, page); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 08b544383d74..533f9b00147d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -752,7 +752,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, spin_unlock(ptl); } -int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, bool write) { pgprot_t pgprot = vma->vm_page_prot; @@ -812,7 +812,7 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, spin_unlock(ptl); } -int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, pfn_t pfn, bool write) { pgprot_t pgprot = vma->vm_page_prot; @@ -821,11 +821,11 @@ int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 9a085d525bbc..17dd883198ae 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void) kmemleak_initialized = 1; + dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, + &kmemleak_fops); + if (!dentry) + pr_warn("Failed to create the debugfs kmemleak file\n"); + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a @@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void) return -ENOMEM; } - dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, - &kmemleak_fops); - if (!dentry) - pr_warn("Failed to create the debugfs kmemleak file\n"); mutex_lock(&scan_mutex); start_scan_thread(); mutex_unlock(&scan_mutex); diff --git a/mm/madvise.c b/mm/madvise.c index 4d3c922ea1a1..972a9eaa898b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -631,11 +631,13 @@ static int madvise_inject_error(int behavior, for (; start < end; start += PAGE_SIZE << order) { + unsigned long pfn; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; + pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page @@ -651,17 +653,25 @@ static int madvise_inject_error(int behavior, if (behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", - page_to_pfn(page), start); + pfn, start); ret = soft_offline_page(page, MF_COUNT_INCREASED); if (ret) return ret; continue; } + pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", - page_to_pfn(page), start); + pfn, start); - ret = memory_failure(page_to_pfn(page), MF_COUNT_INCREASED); + /* + * Drop the page reference taken by get_user_pages_fast(). In + * the absence of MF_COUNT_INCREASED the memory_failure() + * routine is responsible for pinning the page to prevent it + * from being released back to the page allocator. + */ + put_page(page); + ret = memory_failure(pfn, 0); if (ret) return ret; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4ead5a4817de..e79cb59552d9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int if (mem_cgroup_out_of_memory(memcg, mask, order)) return OOM_SUCCESS; - WARN(1,"Memory cgroup charge failed because of no reclaimable memory! " - "This looks like a misconfiguration or a kernel bug."); return OOM_FAILED; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 192d0bbfc9ea..0cd3de3550f0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -55,6 +55,7 @@ #include <linux/hugetlb.h> #include <linux/memory_hotplug.h> #include <linux/mm_inline.h> +#include <linux/memremap.h> #include <linux/kfifo.h> #include <linux/ratelimit.h> #include <linux/page-isolation.h> @@ -175,22 +176,51 @@ int hwpoison_filter(struct page *p) EXPORT_SYMBOL_GPL(hwpoison_filter); /* + * Kill all processes that have a poisoned page mapped and then isolate + * the page. + * + * General strategy: + * Find all processes having the page mapped and kill them. + * But we keep a page reference around so that the page is not + * actually freed yet. + * Then stash the page away + * + * There's no convenient way to get back to mapped processes + * from the VMAs. So do a brute-force search over all + * running processes. + * + * Remember that machine checks are not common (or rather + * if they are common you have other problems), so this shouldn't + * be a performance issue. + * + * Also there are some races possible while we get from the + * error detection to actually handle it. + */ + +struct to_kill { + struct list_head nd; + struct task_struct *tsk; + unsigned long addr; + short size_shift; + char addr_valid; +}; + +/* * Send all the processes who have the page mapped a signal. * ``action optional'' if they are not immediately affected by the error * ``action required'' if error happened in current execution context */ -static int kill_proc(struct task_struct *t, unsigned long addr, - unsigned long pfn, struct page *page, int flags) +static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) { - short addr_lsb; + struct task_struct *t = tk->tsk; + short addr_lsb = tk->size_shift; int ret; pr_err("Memory failure: %#lx: Killing %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); - addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { - ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr, + ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr, addr_lsb, current); } else { /* @@ -199,7 +229,7 @@ static int kill_proc(struct task_struct *t, unsigned long addr, * This could cause a loop when the user sets SIGBUS * to SIG_IGN, but hopefully no one will do that? */ - ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)addr, + ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, addr_lsb, t); /* synchronous? */ } if (ret < 0) @@ -235,34 +265,39 @@ void shake_page(struct page *p, int access) } EXPORT_SYMBOL_GPL(shake_page); -/* - * Kill all processes that have a poisoned page mapped and then isolate - * the page. - * - * General strategy: - * Find all processes having the page mapped and kill them. - * But we keep a page reference around so that the page is not - * actually freed yet. - * Then stash the page away - * - * There's no convenient way to get back to mapped processes - * from the VMAs. So do a brute-force search over all - * running processes. - * - * Remember that machine checks are not common (or rather - * if they are common you have other problems), so this shouldn't - * be a performance issue. - * - * Also there are some races possible while we get from the - * error detection to actually handle it. - */ - -struct to_kill { - struct list_head nd; - struct task_struct *tsk; - unsigned long addr; - char addr_valid; -}; +static unsigned long dev_pagemap_mapping_shift(struct page *page, + struct vm_area_struct *vma) +{ + unsigned long address = vma_address(page, vma); + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset(vma->vm_mm, address); + if (!pgd_present(*pgd)) + return 0; + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return 0; + pud = pud_offset(p4d, address); + if (!pud_present(*pud)) + return 0; + if (pud_devmap(*pud)) + return PUD_SHIFT; + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return 0; + if (pmd_devmap(*pmd)) + return PMD_SHIFT; + pte = pte_offset_map(pmd, address); + if (!pte_present(*pte)) + return 0; + if (pte_devmap(*pte)) + return PAGE_SHIFT; + return 0; +} /* * Failure handling: if we can't find or can't kill a process there's @@ -293,6 +328,10 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } tk->addr = page_address_in_vma(p, vma); tk->addr_valid = 1; + if (is_zone_device_page(p)) + tk->size_shift = dev_pagemap_mapping_shift(p, vma); + else + tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* * In theory we don't have to kill when the page was @@ -300,7 +339,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * likely very rare kill anyways just out of paranoia, but use * a SIGKILL because the error is not contained anymore. */ - if (tk->addr == -EFAULT) { + if (tk->addr == -EFAULT || tk->size_shift == 0) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); tk->addr_valid = 0; @@ -318,9 +357,8 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs(struct list_head *to_kill, int forcekill, - bool fail, struct page *page, unsigned long pfn, - int flags) +static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, + unsigned long pfn, int flags) { struct to_kill *tk, *next; @@ -343,8 +381,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, * check for that, but we need to tell the * process anyways. */ - else if (kill_proc(tk->tsk, tk->addr, - pfn, page, flags) < 0) + else if (kill_proc(tk, pfn, flags) < 0) pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } @@ -516,6 +553,7 @@ static const char * const action_page_types[] = { [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", + [MF_MSG_DAX] = "dax page", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1013,7 +1051,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * any accesses to the poisoned memory. */ forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL); - kill_procs(&tokill, forcekill, !unmap_success, p, pfn, flags); + kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); return unmap_success; } @@ -1113,6 +1151,83 @@ out: return res; } +static int memory_failure_dev_pagemap(unsigned long pfn, int flags, + struct dev_pagemap *pgmap) +{ + struct page *page = pfn_to_page(pfn); + const bool unmap_success = true; + unsigned long size = 0; + struct to_kill *tk; + LIST_HEAD(tokill); + int rc = -EBUSY; + loff_t start; + + /* + * Prevent the inode from being freed while we are interrogating + * the address_space, typically this would be handled by + * lock_page(), but dax pages do not use the page lock. This + * also prevents changes to the mapping of this pfn until + * poison signaling is complete. + */ + if (!dax_lock_mapping_entry(page)) + goto out; + + if (hwpoison_filter(page)) { + rc = 0; + goto unlock; + } + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + case MEMORY_DEVICE_PUBLIC: + /* + * TODO: Handle HMM pages which may need coordination + * with device-side memory. + */ + goto unlock; + default: + break; + } + + /* + * Use this flag as an indication that the dax page has been + * remapped UC to prevent speculative consumption of poison. + */ + SetPageHWPoison(page); + + /* + * Unlike System-RAM there is no possibility to swap in a + * different physical page at a given virtual address, so all + * userspace consumption of ZONE_DEVICE memory necessitates + * SIGBUS (i.e. MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + collect_procs(page, &tokill, flags & MF_ACTION_REQUIRED); + + list_for_each_entry(tk, &tokill, nd) + if (tk->size_shift) + size = max(size, 1UL << tk->size_shift); + if (size) { + /* + * Unmap the largest mapping to avoid breaking up + * device-dax mappings which are constant size. The + * actual size of the mapping being torn down is + * communicated in siginfo, see kill_proc() + */ + start = (page->index << PAGE_SHIFT) & ~(size - 1); + unmap_mapping_range(page->mapping, start, start + size, 0); + } + kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); + rc = 0; +unlock: + dax_unlock_mapping_entry(page); +out: + /* drop pgmap ref acquired in caller */ + put_dev_pagemap(pgmap); + action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); + return rc; +} + /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -1135,6 +1250,7 @@ int memory_failure(unsigned long pfn, int flags) struct page *p; struct page *hpage; struct page *orig_head; + struct dev_pagemap *pgmap; int res; unsigned long page_flags; @@ -1147,6 +1263,10 @@ int memory_failure(unsigned long pfn, int flags) return -ENXIO; } + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, pgmap); + p = pfn_to_page(pfn); if (PageHuge(p)) return memory_failure_hugetlb(pfn, flags); @@ -1777,6 +1897,14 @@ int soft_offline_page(struct page *page, int flags) int ret; unsigned long pfn = page_to_pfn(page); + if (is_zone_device_page(page)) { + pr_debug_ratelimited("soft_offline: %#lx page is device page\n", + pfn); + if (flags & MF_COUNT_INCREASED) + put_page(page); + return -EIO; + } + if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); if (flags & MF_COUNT_INCREASED) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9eea6e809a4e..38d94b703e9d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (__PageMovable(page)) return pfn; if (PageHuge(page)) { - if (page_huge_active(page)) + if (hugepage_migration_supported(page_hstate(page)) && + page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b5b25e4dcbbb..f10aa5360616 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, start, end); if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) { + tlb_finish_mmu(&tlb, start, end); ret = false; continue; } @@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc) } select_bad_process(oc); - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) { + /* Found nothing?!?! */ + if (!oc->chosen) { dump_header(oc, NULL); - panic("Out of memory and no killable processes...\n"); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); } if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6551d3b0dc30..84ae9bf5858a 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -27,7 +27,6 @@ #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> -#include <linux/notifier.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e75865d58ba7..89d2a2ab3fe6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -32,7 +32,6 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/oom.h> -#include <linux/notifier.h> #include <linux/topology.h> #include <linux/sysctl.h> #include <linux/cpu.h> @@ -7709,6 +7708,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * handle each tail page individually in migration. */ if (PageHuge(page)) { + + if (!hugepage_migration_supported(page_hstate(page))) + goto unmovable; + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; continue; } diff --git a/mm/readahead.c b/mm/readahead.c index a59ea70527b9..4e630143a0ba 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -20,6 +20,7 @@ #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> +#include <linux/fadvise.h> #include "internal.h" @@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping, } EXPORT_SYMBOL_GPL(page_cache_async_readahead); -static ssize_t -do_readahead(struct address_space *mapping, struct file *filp, - pgoff_t index, unsigned long nr) -{ - if (!mapping || !mapping->a_ops) - return -EINVAL; - - /* - * Readahead doesn't make sense for DAX inodes, but we don't want it - * to report a failure either. Instead, we just return success and - * don't do any work. - */ - if (dax_mapping(mapping)) - return 0; - - return force_page_cache_readahead(mapping, filp, index, nr); -} - ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; @@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) ret = -EBADF; f = fdget(fd); - if (f.file) { - if (f.file->f_mode & FMODE_READ) { - struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; - unsigned long len = end - start + 1; - ret = do_readahead(mapping, f.file, start, len); - } - fdput(f); - } + if (!f.file || !(f.file->f_mode & FMODE_READ)) + goto out; + + /* + * The readahead() syscall is intended to run only on files + * that can execute readahead. If readahead is not possible + * on this file, then we must return -EINVAL. + */ + ret = -EINVAL; + if (!f.file->f_mapping || !f.file->f_mapping->a_ops || + !S_ISREG(file_inode(f.file)->i_mode)) + goto out; + + ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); +out: + fdput(f); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 0376c124b043..446942677cd4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2227,6 +2227,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode mpol_shared_policy_init(&info->policy, NULL); break; } + + lockdep_annotate_inode_mutex_key(inode); } else shmem_free_inode(sb); return inode; diff --git a/mm/slub.c b/mm/slub.c index ce2b9e5cea77..8da34a8af53d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -19,7 +19,6 @@ #include <linux/slab.h> #include "slab.h" #include <linux/proc_fs.h> -#include <linux/notifier.h> #include <linux/seq_file.h> #include <linux/kasan.h> #include <linux/cpu.h> diff --git a/mm/util.c b/mm/util.c index d2890a407332..9e3ebd2ef65f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(kvmalloc_node); /** - * kvfree - free memory allocated with kvmalloc - * @addr: pointer returned by kvmalloc + * kvfree() - Free memory. + * @addr: Pointer to allocated memory. * - * If the memory is allocated from vmalloc area it is freed with vfree(). - * Otherwise kfree() is used. + * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). + * It is slightly more efficient to use kfree() or vfree() if you are certain + * that you know which one to use. + * + * Context: Any context except NMI. */ void kvfree(const void *addr) { diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -20,44 +20,6 @@ #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - -/* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is diff --git a/mm/vmscan.c b/mm/vmscan.c index 7e7d25504651..c7ce2c161225 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -476,6 +476,17 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); + + /* + * Make sure we apply some minimal pressure on default priority + * even on small cgroups. Stale objects are not only consuming memory + * by themselves, but can also hold a reference to a dying cgroup, + * preventing it from being reclaimed. A dying cgroup with all + * corresponding structures like per-cpu stats and kmem caches + * can be really big, so it may lead to a significant waste of memory. + */ + delta = max_t(unsigned long long, delta, min(freeable, batch_size)); + total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", |
