diff options
Diffstat (limited to '')
-rw-r--r-- | fs/userfaultfd.c | 713 |
1 files changed, 448 insertions, 265 deletions
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 37df7c9eedb1..98ac37e34e3d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -15,6 +15,8 @@ #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> +#include <linux/mm_inline.h> +#include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> @@ -27,16 +29,13 @@ #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> +#include <linux/swapops.h> +#include <linux/miscdevice.h> -int sysctl_unprivileged_userfaultfd __read_mostly = 1; +int sysctl_unprivileged_userfaultfd __read_mostly; static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; -enum userfaultfd_state { - UFFD_STATE_WAIT_API, - UFFD_STATE_RUNNING, -}; - /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. @@ -61,19 +60,17 @@ struct userfaultfd_ctx { /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ - struct seqcount refile_seq; + 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; - /* state machine */ - enum userfaultfd_state state; /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ - bool mmap_changing; + atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; @@ -103,6 +100,14 @@ struct userfaultfd_wake_range { unsigned long len; }; +/* internal indication that UFFD_API ioctl was successfully executed */ +#define UFFD_FEATURE_INITIALIZED (1u << 31) + +static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) +{ + return ctx->features & UFFD_FEATURE_INITIALIZED; +} + static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { @@ -188,32 +193,34 @@ static inline void msg_init(struct uffd_msg *msg) } static inline struct uffd_msg userfault_msg(unsigned long address, + unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; + msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; - msg.arg.pagefault.address = address; + + msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? + real_address : address; + + /* + * These flags indicate why the userfault occurred: + * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. + * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. + * - Neither of these flags being set indicates a MISSING fault. + * + * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write + * fault. Otherwise, it was a read fault. + */ if (flags & FAULT_FLAG_WRITE) - /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the - * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE - * was not set in a UFFD_EVENT_PAGEFAULT, it means it - * was a read fault, otherwise if set it means it's - * a write fault. - */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) - /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the - * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was - * not set in a UFFD_EVENT_PAGEFAULT, it means it was - * a missing fault, otherwise if set it means it's a - * write protect fault. - */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; + if (reason & VM_UFFD_MINOR) + msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; @@ -234,7 +241,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, pte_t *ptep, pte; bool ret = true; - VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); + mmap_assert_locked(mm); ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); @@ -246,9 +253,10 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, /* * Lockless access: we're in a wait_event so it's ok if it - * changes under us. + * changes under us. PTE markers should be handled the same as none + * ptes here. */ - if (huge_pte_none(pte)) + if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; @@ -286,7 +294,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pte_t *pte; bool ret = true; - VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); + mmap_assert_locked(mm); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -314,8 +322,11 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, if (!pmd_present(_pmd)) goto out; - if (pmd_trans_huge(_pmd)) + if (pmd_trans_huge(_pmd)) { + if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) + ret = true; goto out; + } /* * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it @@ -324,9 +335,12 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pte = pte_offset_map(pmd, address); /* * Lockless access: we're in a wait_event so it's ok if it - * changes under us. + * changes under us. PTE markers should be handled the same as none + * ptes here. */ - if (pte_none(*pte)) + if (pte_none_mostly(*pte)) + ret = true; + if (!pte_write(*pte) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); @@ -334,19 +348,30 @@ out: return ret; } +static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) +{ + if (flags & FAULT_FLAG_INTERRUPTIBLE) + return TASK_INTERRUPTIBLE; + + if (flags & FAULT_FLAG_KILLABLE) + return TASK_KILLABLE; + + return TASK_UNINTERRUPTIBLE; +} + /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * - * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_sem must be released + * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are - * fatal_signal_pending()s, and the mmap_sem must be released before + * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) @@ -355,8 +380,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; - bool must_wait, return_to_userland; - long blocking_state; + bool must_wait; + unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update. @@ -367,16 +392,16 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with * the no_page_table() helper in follow_page_mask(), but the * shmem_vm_ops->fault method is invoked even during - * coredumping without mmap_sem and it ends up here. + * coredumping without mmap_lock and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* - * Coredumping runs without mmap_sem so we can only check that - * the mmap_sem is held, if PF_DUMPCORE was not set. + * Coredumping runs without mmap_lock so we can only check that + * the mmap_lock is held, if PF_DUMPCORE was not set. */ - WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem)); + mmap_assert_locked(mm); ctx = vmf->vma->vm_userfaultfd_ctx.ctx; if (!ctx) @@ -384,16 +409,20 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) BUG_ON(ctx->mm != mm); - VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); - VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); + /* Any unrecognized flag is a bug. */ + VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); + /* 0 or > 1 flags set is a bug; we expect exactly 1. */ + VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; + if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY)) + goto out; /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the - * caller of handle_userfault to release the mmap_sem. + * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* @@ -452,21 +481,17 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; - /* take the reference before dropping the mmap_sem */ + /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, - ctx->features); + uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, + reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; - return_to_userland = - (vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) == - (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE); - blocking_state = return_to_userland ? TASK_INTERRUPTIBLE : - TASK_KILLABLE; + blocking_state = userfaultfd_get_blocking_state(vmf->flags); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* @@ -489,65 +514,15 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, vmf->address, vmf->flags, reason); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); - if (likely(must_wait && !READ_ONCE(ctx->released) && - (return_to_userland ? !signal_pending(current) : - !fatal_signal_pending(current)))) { + if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); - ret |= VM_FAULT_MAJOR; - - /* - * False wakeups can orginate even from rwsem before - * up_read() however userfaults will wait either for a - * targeted wakeup on the specific uwq waitqueue from - * wake_userfault() or for signals or for uffd - * release. - */ - while (!READ_ONCE(uwq.waken)) { - /* - * This needs the full smp_store_mb() - * guarantee as the state write must be - * visible to other CPUs before reading - * uwq.waken from other CPUs. - */ - set_current_state(blocking_state); - if (READ_ONCE(uwq.waken) || - READ_ONCE(ctx->released) || - (return_to_userland ? signal_pending(current) : - fatal_signal_pending(current))) - break; - schedule(); - } } __set_current_state(TASK_RUNNING); - if (return_to_userland) { - if (signal_pending(current) && - !fatal_signal_pending(current)) { - /* - * If we got a SIGSTOP or SIGCONT and this is - * a normal userland page fault, just let - * userland return so the signal will be - * handled and gdb debugging works. The page - * fault code immediately after we return from - * this function is going to release the - * mmap_sem and it's not depending on it - * (unlike gup would if we were not to return - * VM_FAULT_RETRY). - * - * If a fatal signal is pending we still take - * the streamlined VM_FAULT_RETRY failure path - * and there's no need to retake the mmap_sem - * in such case. - */ - down_read(&mm->mmap_sem); - ret = VM_FAULT_NOPAGE; - } - } - /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run @@ -636,17 +611,17 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, if (release_new_ctx) { struct vm_area_struct *vma; struct mm_struct *mm = release_new_ctx->mm; + VMA_ITERATOR(vmi, mm, 0); /* the various vma->vm_userfaultfd_ctx still points to it */ - down_write(&mm->mmap_sem); - /* no task can run (and in turn coredump) yet */ - VM_WARN_ON(!mmget_still_valid(mm)); - for (vma = mm->mmap; vma; vma = vma->vm_next) + mmap_write_lock(mm); + for_each_vma(vmi, vma) { if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; } - up_write(&mm->mmap_sem); + } + mmap_write_unlock(mm); userfaultfd_ctx_put(release_new_ctx); } @@ -656,7 +631,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, * already released. */ out: - WRITE_ONCE(ctx->mmap_changing, false); + atomic_dec(&ctx->mmap_changing); + VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } @@ -676,7 +652,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; return 0; } @@ -699,15 +675,14 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; - ctx->state = UFFD_STATE_RUNNING; ctx->features = octx->features; ctx->released = false; - ctx->mmap_changing = false; + atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); - WRITE_ONCE(octx->mmap_changing, true); + atomic_inc(&octx->mmap_changing); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); @@ -754,11 +729,11 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); + atomic_inc(&ctx->mmap_changing); } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; } } @@ -799,8 +774,8 @@ bool userfaultfd_remove(struct vm_area_struct *vma, return true; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); - up_read(&mm->mmap_sem); + atomic_inc(&ctx->mmap_changing); + mmap_read_unlock(mm); msg_init(&ewq.msg); @@ -826,11 +801,13 @@ static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, return false; } -int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *unmaps) +int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *unmaps) { - for ( ; vma && vma->vm_start < end; vma = vma->vm_next) { + VMA_ITERATOR(vmi, mm, start); + struct vm_area_struct *vma; + + for_each_vma_range(vmi, vma, end) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; @@ -843,7 +820,7 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, return -ENOMEM; userfaultfd_ctx_get(ctx); - WRITE_ONCE(ctx->mmap_changing, true); + atomic_inc(&ctx->mmap_changing); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; @@ -880,7 +857,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; - bool still_valid; + MA_STATE(mas, &mm->mm_mt, 0, 0); WRITE_ONCE(ctx->released, true); @@ -891,37 +868,37 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * Flush page faults out of all CPUs. NOTE: all page faults * must be retried without returning VM_FAULT_SIGBUS if * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx - * changes while handle_userfault released the mmap_sem. So + * changes while handle_userfault released the mmap_lock. So * it's critical that released is set to true (above), before - * taking the mmap_sem for writing. + * taking the mmap_lock for writing. */ - down_write(&mm->mmap_sem); - still_valid = mmget_still_valid(mm); + mmap_write_lock(mm); prev = NULL; - for (vma = mm->mmap; vma; vma = vma->vm_next) { + mas_for_each(&mas, vma, ULONG_MAX) { cond_resched(); BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ - !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(vma->vm_flags & __VM_UFFD_FLAGS)); if (vma->vm_userfaultfd_ctx.ctx != ctx) { prev = vma; continue; } - new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); - if (still_valid) { - prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, - new_flags, vma->anon_vma, - vma->vm_file, vma->vm_pgoff, - vma_policy(vma), - NULL_VM_UFFD_CTX); - if (prev) - vma = prev; - else - prev = vma; + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; + prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, + new_flags, vma->anon_vma, + vma->vm_file, vma->vm_pgoff, + vma_policy(vma), + NULL_VM_UFFD_CTX, anon_vma_name(vma)); + if (prev) { + mas_pause(&mas); + vma = prev; + } else { + prev = vma; } + vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); mmput(mm); wakeup: /* @@ -980,50 +957,45 @@ static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) poll_wait(file, &ctx->fd_wqh, wait); - switch (ctx->state) { - case UFFD_STATE_WAIT_API: + if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; - case UFFD_STATE_RUNNING: - /* - * poll() never guarantees that read won't block. - * userfaults can be waken before they're read(). - */ - if (unlikely(!(file->f_flags & O_NONBLOCK))) - return EPOLLERR; - /* - * lockless access to see if there are pending faults - * __pollwait last action is the add_wait_queue but - * the spin_unlock would allow the waitqueue_active to - * pass above the actual list_add inside - * add_wait_queue critical section. So use a full - * memory barrier to serialize the list_add write of - * add_wait_queue() with the waitqueue_active read - * below. - */ - ret = 0; - smp_mb(); - if (waitqueue_active(&ctx->fault_pending_wqh)) - ret = EPOLLIN; - else if (waitqueue_active(&ctx->event_wqh)) - ret = EPOLLIN; - return ret; - default: - WARN_ON_ONCE(1); + /* + * poll() never guarantees that read won't block. + * userfaults can be waken before they're read(). + */ + if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; - } + /* + * lockless access to see if there are pending faults + * __pollwait last action is the add_wait_queue but + * the spin_unlock would allow the waitqueue_active to + * pass above the actual list_add inside + * add_wait_queue critical section. So use a full + * memory barrier to serialize the list_add write of + * add_wait_queue() with the waitqueue_active read + * below. + */ + ret = 0; + smp_mb(); + if (waitqueue_active(&ctx->fault_pending_wqh)) + ret = EPOLLIN; + else if (waitqueue_active(&ctx->event_wqh)) + ret = EPOLLIN; + + return ret; } static const struct file_operations userfaultfd_fops; -static int resolve_userfault_fork(struct userfaultfd_ctx *ctx, - struct userfaultfd_ctx *new, +static int resolve_userfault_fork(struct userfaultfd_ctx *new, + struct inode *inode, struct uffd_msg *msg) { int fd; - fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, new, - O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS)); + fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, + O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; @@ -1033,7 +1005,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *ctx, } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, - struct uffd_msg *msg) + struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); @@ -1144,7 +1116,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { - ret = resolve_userfault_fork(ctx, fork_nctx, msg); + ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* @@ -1204,14 +1176,15 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf, ssize_t _ret, ret = 0; struct uffd_msg msg; int no_wait = file->f_flags & O_NONBLOCK; + struct inode *inode = file_inode(file); - if (ctx->state == UFFD_STATE_WAIT_API) + if (!userfaultfd_is_initialized(ctx)) return -EINVAL; for (;;) { if (count < sizeof(msg)) return ret ? ret : -EINVAL; - _ret = userfaultfd_ctx_read(ctx, no_wait, &msg); + _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg))) @@ -1249,7 +1222,7 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory - * barrier here. PT lock release or up_read(mmap_sem) still + * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ @@ -1272,33 +1245,25 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, } static __always_inline int validate_range(struct mm_struct *mm, - __u64 *start, __u64 len) + __u64 start, __u64 len) { __u64 task_size = mm->task_size; - *start = untagged_addr(*start); - - if (*start & ~PAGE_MASK) + if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; - if (*start < mmap_min_addr) + if (start < mmap_min_addr) return -EINVAL; - if (*start >= task_size) + if (start >= task_size) return -EINVAL; - if (len > task_size - *start) + if (len > task_size - start) return -EINVAL; return 0; } -static inline bool vma_can_userfault(struct vm_area_struct *vma) -{ - return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || - vma_is_shmem(vma); -} - static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { @@ -1311,6 +1276,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, bool found; bool basic_ioctls; unsigned long start, end, vma_end; + MA_STATE(mas, &mm->mm_mt, 0, 0); user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1322,23 +1288,25 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, ret = -EINVAL; if (!uffdio_register.mode) goto out; - if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING| - UFFDIO_REGISTER_MODE_WP)) + if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP + goto out; +#endif vm_flags |= VM_UFFD_WP; - /* - * FIXME: remove the below error constraint by - * implementing the wprotect tracking mode. - */ - ret = -EINVAL; + } + if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; +#endif + vm_flags |= VM_UFFD_MINOR; } - ret = validate_range(mm, &uffdio_register.range.start, + ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; @@ -1350,10 +1318,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, if (!mmget_not_zero(mm)) goto out; - down_write(&mm->mmap_sem); - if (!mmget_still_valid(mm)) - goto out_unlock; - vma = find_vma_prev(mm, start, &prev); + mmap_write_lock(mm); + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); if (!vma) goto out_unlock; @@ -1378,15 +1345,15 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, */ found = false; basic_ioctls = false; - for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { + for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ - !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; - if (!vma_can_userfault(cur)) + if (!vma_can_userfault(cur, vm_flags)) goto out_unlock; /* @@ -1414,6 +1381,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, if (end & (vma_hpagesize - 1)) goto out_unlock; } + if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) + goto out_unlock; /* * Check that this vma isn't already owned by a @@ -1436,14 +1405,16 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, } BUG_ON(!found); - if (vma->vm_start < start) - prev = vma; + mas_set(&mas, start); + prev = mas_prev(&mas, 0); + if (prev != vma) + mas_next(&mas, ULONG_MAX); ret = 0; do { cond_resched(); - BUG_ON(!vma_can_userfault(vma)); + BUG_ON(!vma_can_userfault(vma, vm_flags)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); @@ -1460,13 +1431,15 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, start = vma->vm_start; vma_end = min(end, vma->vm_end); - new_flags = (vma->vm_flags & - ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags; + new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), + anon_vma_name(vma)); if (prev) { + /* vma_merge() invalidated the mas */ + mas_pause(&mas); vma = prev; goto next; } @@ -1474,11 +1447,15 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, ret = split_vma(mm, vma, start, 1); if (ret) break; + /* split_vma() invalidated the mas */ + mas_pause(&mas); } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; + /* split_vma() invalidated the mas */ + mas_pause(&mas); } next: /* @@ -1489,23 +1466,40 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx.ctx = ctx; + if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) + hugetlb_unshare_all_pmds(vma); + skip: prev = vma; start = vma->vm_end; - vma = vma->vm_next; - } while (vma && vma->vm_start < end); + vma = mas_next(&mas, end - 1); + } while (vma); out_unlock: - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); mmput(mm); if (!ret) { + __u64 ioctls_out; + + ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : + UFFD_API_RANGE_IOCTLS; + + /* + * Declare the WP ioctl only if the WP mode is + * specified and all checks passed with the range + */ + if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) + ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); + + /* CONTINUE ioctl is only supported for MINOR ranges. */ + if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) + ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); + /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ - if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : - UFFD_API_RANGE_IOCTLS, - &user_uffdio_register->ioctls)) + if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: @@ -1523,12 +1517,13 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; + MA_STATE(mas, &mm->mm_mt, 0, 0); ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; - ret = validate_range(mm, &uffdio_unregister.start, + ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; @@ -1540,10 +1535,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (!mmget_not_zero(mm)) goto out; - down_write(&mm->mmap_sem); - if (!mmget_still_valid(mm)) - goto out_unlock; - vma = find_vma_prev(mm, start, &prev); + mmap_write_lock(mm); + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); if (!vma) goto out_unlock; @@ -1568,11 +1562,11 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, */ found = false; ret = -EINVAL; - for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { + for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ - !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required @@ -1581,21 +1575,23 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * provides for more strict behavior to notice * unregistration errors. */ - if (!vma_can_userfault(cur)) + if (!vma_can_userfault(cur, cur->vm_flags)) goto out_unlock; found = true; } BUG_ON(!found); - if (vma->vm_start < start) - prev = vma; + mas_set(&mas, start); + prev = mas_prev(&mas, 0); + if (prev != vma) + mas_next(&mas, ULONG_MAX); ret = 0; do { cond_resched(); - BUG_ON(!vma_can_userfault(vma)); + BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); /* * Nothing to do: this vma is already registered into this @@ -1623,24 +1619,31 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } - new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(mm, vma, start, vma_end - start, false); + + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; + mas_pause(&mas); goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; + mas_pause(&mas); } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; + mas_pause(&mas); } next: /* @@ -1654,10 +1657,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, skip: prev = vma; start = vma->vm_end; - vma = vma->vm_next; - } while (vma && vma->vm_start < end); + vma = mas_next(&mas, end - 1); + } while (vma); out_unlock: - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); mmput(mm); out: return ret; @@ -1679,7 +1682,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; - ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len); + ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; @@ -1710,7 +1713,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; @@ -1719,7 +1722,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, sizeof(uffdio_copy)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len); + ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* @@ -1730,11 +1733,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, ret = -EINVAL; if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src) goto out; - if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE) + if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len, &ctx->mmap_changing); + uffdio_copy.len, &ctx->mmap_changing, + uffdio_copy.mode); mmput(ctx->mm); } else { return -ESRCH; @@ -1766,7 +1770,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (READ_ONCE(ctx->mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; @@ -1775,7 +1779,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_zeropage.range.start, + ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; @@ -1807,12 +1811,126 @@ out: return ret; } +static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, + unsigned long arg) +{ + int ret; + struct uffdio_writeprotect uffdio_wp; + struct uffdio_writeprotect __user *user_uffdio_wp; + struct userfaultfd_wake_range range; + bool mode_wp, mode_dontwake; + + if (atomic_read(&ctx->mmap_changing)) + return -EAGAIN; + + user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; + + if (copy_from_user(&uffdio_wp, user_uffdio_wp, + sizeof(struct uffdio_writeprotect))) + return -EFAULT; + + ret = validate_range(ctx->mm, uffdio_wp.range.start, + uffdio_wp.range.len); + if (ret) + return ret; + + if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | + UFFDIO_WRITEPROTECT_MODE_WP)) + return -EINVAL; + + mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; + mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; + + if (mode_wp && mode_dontwake) + 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); + mmput(ctx->mm); + } else { + return -ESRCH; + } + + if (ret) + return ret; + + if (!mode_wp && !mode_dontwake) { + range.start = uffdio_wp.range.start; + range.len = uffdio_wp.range.len; + wake_userfault(ctx, &range); + } + return ret; +} + +static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) +{ + __s64 ret; + struct uffdio_continue uffdio_continue; + struct uffdio_continue __user *user_uffdio_continue; + struct userfaultfd_wake_range range; + + user_uffdio_continue = (struct uffdio_continue __user *)arg; + + ret = -EAGAIN; + if (atomic_read(&ctx->mmap_changing)) + goto out; + + ret = -EFAULT; + if (copy_from_user(&uffdio_continue, user_uffdio_continue, + /* don't copy the output fields */ + sizeof(uffdio_continue) - (sizeof(__s64)))) + goto out; + + ret = validate_range(ctx->mm, uffdio_continue.range.start, + uffdio_continue.range.len); + if (ret) + goto out; + + ret = -EINVAL; + /* double check for wraparound just in case. */ + if (uffdio_continue.range.start + uffdio_continue.range.len <= + uffdio_continue.range.start) { + goto out; + } + if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) + goto out; + + if (mmget_not_zero(ctx->mm)) { + ret = mcopy_continue(ctx->mm, uffdio_continue.range.start, + uffdio_continue.range.len, + &ctx->mmap_changing); + mmput(ctx->mm); + } else { + return -ESRCH; + } + + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; + if (ret < 0) + goto out; + + /* len == 0 would wake all */ + BUG_ON(!ret); + range.len = ret; + if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { + range.start = uffdio_continue.range.start; + wake_userfault(ctx, &range); + } + ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; + +out: + return ret; +} + static inline unsigned int uffd_ctx_features(__u64 user_features) { /* - * For the current set of features the bits just coincide + * For the current set of features the bits just coincide. Set + * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ - return (unsigned int)user_features; + return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } /* @@ -1825,31 +1943,41 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; + unsigned int ctx_features; int ret; __u64 features; - ret = -EINVAL; - if (ctx->state != UFFD_STATE_WAIT_API) - goto out; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - features = uffdio_api.features; - ret = -EINVAL; - if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) - goto err_out; + /* Ignore unsupported features (userspace built against newer kernel) */ + features = uffdio_api.features & UFFD_API_FEATURES; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR + uffdio_api.features &= + ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); +#endif +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP + uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; +#endif +#ifndef CONFIG_PTE_MARKER_UFFD_WP + uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; +#endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; - ctx->state = UFFD_STATE_RUNNING; + /* only enable the requested features for this uffd context */ - ctx->features = uffd_ctx_features(features); + ctx_features = uffd_ctx_features(features); + ret = -EINVAL; + if (cmpxchg(&ctx->features, 0, ctx_features) != 0) + goto err_out; + ret = 0; out: return ret; @@ -1866,7 +1994,7 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; - if (cmd != UFFDIO_API && ctx->state == UFFD_STATE_WAIT_API) + if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { @@ -1888,6 +2016,12 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; + case UFFDIO_WRITEPROTECT: + ret = userfaultfd_writeprotect(ctx, arg); + break; + case UFFDIO_CONTINUE: + ret = userfaultfd_continue(ctx, arg); + break; } return ret; } @@ -1940,24 +2074,22 @@ static void init_once_userfaultfd_ctx(void *mem) init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); - seqcount_init(&ctx->refile_seq); + seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } -SYSCALL_DEFINE1(userfaultfd, int, flags) +static int new_userfaultfd(int flags) { struct userfaultfd_ctx *ctx; int fd; - if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE)) - return -EPERM; - BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ + BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); - if (flags & ~UFFD_SHARED_FCNTL_FLAGS) + if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); @@ -1967,15 +2099,14 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; - ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; - ctx->mmap_changing = false; + atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); - fd = anon_inode_getfd("[userfaultfd]", &userfaultfd_fops, ctx, - O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS)); + fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, + O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); @@ -1983,8 +2114,60 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) return fd; } +static inline bool userfaultfd_syscall_allowed(int flags) +{ + /* Userspace-only page faults are always allowed */ + if (flags & UFFD_USER_MODE_ONLY) + return true; + + /* + * The user is requesting a userfaultfd which can handle kernel faults. + * Privileged users are always allowed to do this. + */ + if (capable(CAP_SYS_PTRACE)) + return true; + + /* Otherwise, access to kernel fault handling is sysctl controlled. */ + return sysctl_unprivileged_userfaultfd; +} + +SYSCALL_DEFINE1(userfaultfd, int, flags) +{ + if (!userfaultfd_syscall_allowed(flags)) + return -EPERM; + + return new_userfaultfd(flags); +} + +static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags) +{ + if (cmd != USERFAULTFD_IOC_NEW) + return -EINVAL; + + return new_userfaultfd(flags); +} + +static const struct file_operations userfaultfd_dev_fops = { + .unlocked_ioctl = userfaultfd_dev_ioctl, + .compat_ioctl = userfaultfd_dev_ioctl, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice userfaultfd_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "userfaultfd", + .fops = &userfaultfd_dev_fops +}; + static int __init userfaultfd_init(void) { + int ret; + + ret = misc_register(&userfaultfd_misc); + if (ret) + return ret; + userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, |