diff options
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/Kconfig | 2 | ||||
| -rw-r--r-- | fs/fuse/virtio_fs.c | 15 | ||||
| -rw-r--r-- | fs/proc/Kconfig | 2 | ||||
| -rw-r--r-- | fs/proc/kcore.c | 2 | ||||
| -rw-r--r-- | fs/proc/task_mmu.c | 17 | ||||
| -rw-r--r-- | fs/userfaultfd.c | 86 |
6 files changed, 44 insertions, 80 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index ea2f77446080..a46b0cbc4d8f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -60,7 +60,6 @@ endif # BLOCK config FS_DAX bool "File system based Direct Access (DAX) support" depends on MMU - depends on !(ARM || MIPS || SPARC) depends on ZONE_DEVICE || FS_DAX_LIMITED select FS_IOMAP select DAX @@ -261,6 +260,7 @@ menuconfig HUGETLBFS depends on X86 || SPARC64 || ARCH_SUPPORTS_HUGETLBFS || BROKEN depends on (SYSFS || SYSCTL) select MEMFD_CREATE + select PADATA if SMP help hugetlbfs is a filesystem backing for HugeTLB pages, based on ramfs. For architectures that support it, say Y here and read diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 5f1be1da92ce..a28466c2da71 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -16,6 +16,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/highmem.h> +#include <linux/cleanup.h> #include <linux/uio.h> #include "fuse_i.h" @@ -795,8 +796,11 @@ static void virtio_fs_cleanup_dax(void *data) put_dax(dax_dev); } +DEFINE_FREE(cleanup_dax, struct dax_dev *, if (!IS_ERR_OR_NULL(_T)) virtio_fs_cleanup_dax(_T)) + static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) { + struct dax_device *dax_dev __free(cleanup_dax) = NULL; struct virtio_shm_region cache_reg; struct dev_pagemap *pgmap; bool have_cache; @@ -804,6 +808,12 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) if (!IS_ENABLED(CONFIG_FUSE_DAX)) return 0; + dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); + if (IS_ERR(dax_dev)) { + int rc = PTR_ERR(dax_dev); + return rc == -EOPNOTSUPP ? 0 : rc; + } + /* Get cache region */ have_cache = virtio_get_shm_region(vdev, &cache_reg, (u8)VIRTIO_FS_SHMCAP_ID_CACHE); @@ -849,10 +859,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); - fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); - if (IS_ERR(fs->dax_dev)) - return PTR_ERR(fs->dax_dev); - + fs->dax_dev = no_free_ptr(dax_dev); return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax, fs->dax_dev); } diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 32b1116ae137..d80a1431ef7b 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -32,7 +32,7 @@ config PROC_FS config PROC_KCORE bool "/proc/kcore support" if !ARM depends on PROC_FS && MMU - select CRASH_CORE + select VMCORE_INFO help Provides a virtual ELF core file of the live kernel. This can be read with gdb and other ELF tools. No modifications can be diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 6422e569b080..8e08a9a1b7ed 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -10,7 +10,7 @@ * Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com> */ -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/kcore.h> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3f78ebbb795f..23fbab954c20 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1352,8 +1352,7 @@ static inline pagemap_entry_t make_pme(u64 frame, u64 flags) return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags }; } -static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, - struct pagemapread *pm) +static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm) { pm->buffer[pm->pos++] = *pme; if (pm->pos >= pm->len) @@ -1380,7 +1379,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, hole_end = end; for (; addr < hole_end; addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) goto out; } @@ -1392,7 +1391,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, if (vma->vm_flags & VM_SOFTDIRTY) pme = make_pme(0, PM_SOFT_DIRTY); for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) goto out; } @@ -1519,7 +1518,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, for (; addr != end; addr += PAGE_SIZE) { pagemap_entry_t pme = make_pme(frame, flags); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) break; if (pm->show_pfn) { @@ -1547,7 +1546,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, pagemap_entry_t pme; pme = pte_to_pagemap_entry(pm, vma, addr, ptep_get(pte)); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) break; } @@ -1597,7 +1596,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, for (; addr != end; addr += PAGE_SIZE) { pagemap_entry_t pme = make_pme(frame, flags); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) return err; if (pm->show_pfn && (flags & PM_PRESENT)) @@ -1807,7 +1806,7 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (p->masks_of_interest & PAGE_IS_FILE) { swp = pte_to_swp_entry(pte); if (is_pfn_swap_entry(swp) && - !PageAnon(pfn_swap_entry_to_page(swp))) + !folio_test_anon(pfn_swap_entry_folio(swp))) categories |= PAGE_IS_FILE; } if (pte_swp_soft_dirty(pte)) @@ -1873,7 +1872,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, if (p->masks_of_interest & PAGE_IS_FILE) { swp = pmd_to_swp_entry(pmd); if (is_pfn_swap_entry(swp) && - !PageAnon(pfn_swap_entry_to_page(swp))) + !folio_test_anon(pfn_swap_entry_folio(swp))) categories |= PAGE_IS_FILE; } } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 959551ff9a95..60dcfafdc11a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -50,45 +50,6 @@ static struct ctl_table vm_userfaultfd_table[] = { static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init; -/* - * Start with fault_pending_wqh and fault_wqh so they're more likely - * to be in the same cacheline. - * - * Locking order: - * fd_wqh.lock - * fault_pending_wqh.lock - * fault_wqh.lock - * event_wqh.lock - * - * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, - * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's - * also taken in IRQ context. - */ -struct userfaultfd_ctx { - /* waitqueue head for the pending (i.e. not read) userfaults */ - wait_queue_head_t fault_pending_wqh; - /* waitqueue head for the userfaults */ - wait_queue_head_t fault_wqh; - /* waitqueue head for the pseudo fd to wakeup poll/read */ - wait_queue_head_t fd_wqh; - /* waitqueue head for events */ - wait_queue_head_t event_wqh; - /* a refile sequence protected by fault_pending_wqh lock */ - seqcount_spinlock_t refile_seq; - /* pseudo fd refcounting */ - refcount_t refcount; - /* userfaultfd syscall flags */ - unsigned int flags; - /* features requested from the userspace */ - unsigned int features; - /* released */ - bool released; - /* memory mappings are changing because of non-cooperative event */ - atomic_t mmap_changing; - /* mm with one ore more vmas attached to this userfaultfd_ctx */ - struct mm_struct *mm; -}; - struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; @@ -724,12 +685,15 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; + init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); + down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); + up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); @@ -776,7 +740,9 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ vma_start_write(vma); @@ -822,7 +788,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma, return true; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); @@ -864,7 +832,9 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, return -ENOMEM; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; @@ -1748,9 +1718,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len, &ctx->mmap_changing, - flags); + ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src, + uffdio_copy.len, flags); mmput(ctx->mm); } else { return -ESRCH; @@ -1800,9 +1769,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, goto out; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start, - uffdio_zeropage.range.len, - &ctx->mmap_changing); + ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start, + uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; @@ -1857,9 +1825,8 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, return -EINVAL; if (mmget_not_zero(ctx->mm)) { - ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start, - uffdio_wp.range.len, mode_wp, - &ctx->mmap_changing); + ret = mwriteprotect_range(ctx, uffdio_wp.range.start, + uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; @@ -1909,9 +1876,8 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start, - uffdio_continue.range.len, - &ctx->mmap_changing, flags); + ret = mfill_atomic_continue(ctx, uffdio_continue.range.start, + uffdio_continue.range.len, flags); mmput(ctx->mm); } else { return -ESRCH; @@ -1964,9 +1930,8 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long goto out; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_poison(ctx->mm, uffdio_poison.range.start, - uffdio_poison.range.len, - &ctx->mmap_changing, 0); + ret = mfill_atomic_poison(ctx, uffdio_poison.range.start, + uffdio_poison.range.len, 0); mmput(ctx->mm); } else { return -ESRCH; @@ -2040,16 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, return -EINVAL; if (mmget_not_zero(mm)) { - mmap_read_lock(mm); - - /* Re-check after taking mmap_lock */ - if (likely(!atomic_read(&ctx->mmap_changing))) - ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src, - uffdio_move.len, uffdio_move.mode); - else - ret = -EINVAL; - - mmap_read_unlock(mm); + ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src, + uffdio_move.len, uffdio_move.mode); mmput(mm); } else { return -ESRCH; @@ -2255,6 +2212,7 @@ static int new_userfaultfd(int flags) ctx->flags = flags; ctx->features = 0; ctx->released = false; + init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ |