summaryrefslogtreecommitdiff
path: root/fs/fuse/dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/fuse/dev.c')
-rw-r--r--fs/fuse/dev.c1339
1 files changed, 895 insertions, 444 deletions
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 02b3c36b3676..6d59cbc877c6 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -6,7 +6,9 @@
See the file COPYING.
*/
+#include "dev_uring_i.h"
#include "fuse_i.h"
+#include "fuse_dev_i.h"
#include <linux/init.h>
#include <linux/module.h>
@@ -21,39 +23,125 @@
#include <linux/swap.h>
#include <linux/splice.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
+
+#include "fuse_trace.h"
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
-/* Ordinary requests have even IDs, while interrupts IDs are odd */
-#define FUSE_INT_REQ_BIT (1ULL << 0)
-#define FUSE_REQ_ID_STEP (1ULL << 1)
-
static struct kmem_cache *fuse_req_cachep;
-static struct fuse_dev *fuse_get_dev(struct file *file)
+const unsigned long fuse_timeout_timer_freq =
+ secs_to_jiffies(FUSE_TIMEOUT_TIMER_FREQ);
+
+bool fuse_request_expired(struct fuse_conn *fc, struct list_head *list)
{
- /*
- * Lockless access is OK, because file->private data is set
- * once during mount and is valid until the file is released.
- */
- return READ_ONCE(file->private_data);
+ struct fuse_req *req;
+
+ req = list_first_entry_or_null(list, struct fuse_req, list);
+ if (!req)
+ return false;
+ return time_is_before_jiffies(req->create_time + fc->timeout.req_timeout);
+}
+
+static bool fuse_fpq_processing_expired(struct fuse_conn *fc, struct list_head *processing)
+{
+ int i;
+
+ for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+ if (fuse_request_expired(fc, &processing[i]))
+ return true;
+
+ return false;
+}
+
+/*
+ * Check if any requests aren't being completed by the time the request timeout
+ * elapses. To do so, we:
+ * - check the fiq pending list
+ * - check the bg queue
+ * - check the fpq io and processing lists
+ *
+ * To make this fast, we only check against the head request on each list since
+ * these are generally queued in order of creation time (eg newer requests get
+ * queued to the tail). We might miss a few edge cases (eg requests transitioning
+ * between lists, re-sent requests at the head of the pending list having a
+ * later creation time than other requests on that list, etc.) but that is fine
+ * since if the request never gets fulfilled, it will eventually be caught.
+ */
+void fuse_check_timeout(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct fuse_conn *fc = container_of(dwork, struct fuse_conn,
+ timeout.work);
+ struct fuse_iqueue *fiq = &fc->iq;
+ struct fuse_dev *fud;
+ struct fuse_pqueue *fpq;
+ bool expired = false;
+
+ if (!atomic_read(&fc->num_waiting))
+ goto out;
+
+ spin_lock(&fiq->lock);
+ expired = fuse_request_expired(fc, &fiq->pending);
+ spin_unlock(&fiq->lock);
+ if (expired)
+ goto abort_conn;
+
+ spin_lock(&fc->bg_lock);
+ expired = fuse_request_expired(fc, &fc->bg_queue);
+ spin_unlock(&fc->bg_lock);
+ if (expired)
+ goto abort_conn;
+
+ spin_lock(&fc->lock);
+ if (!fc->connected) {
+ spin_unlock(&fc->lock);
+ return;
+ }
+ list_for_each_entry(fud, &fc->devices, entry) {
+ fpq = &fud->pq;
+ spin_lock(&fpq->lock);
+ if (fuse_request_expired(fc, &fpq->io) ||
+ fuse_fpq_processing_expired(fc, fpq->processing)) {
+ spin_unlock(&fpq->lock);
+ spin_unlock(&fc->lock);
+ goto abort_conn;
+ }
+
+ spin_unlock(&fpq->lock);
+ }
+ spin_unlock(&fc->lock);
+
+ if (fuse_uring_request_expired(fc))
+ goto abort_conn;
+
+out:
+ queue_delayed_work(system_percpu_wq, &fc->timeout.work,
+ fuse_timeout_timer_freq);
+ return;
+
+abort_conn:
+ fuse_abort_conn(fc);
}
-static void fuse_request_init(struct fuse_req *req)
+static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
{
INIT_LIST_HEAD(&req->list);
INIT_LIST_HEAD(&req->intr_entry);
init_waitqueue_head(&req->waitq);
refcount_set(&req->count, 1);
__set_bit(FR_PENDING, &req->flags);
+ req->fm = fm;
+ req->create_time = jiffies;
}
-static struct fuse_req *fuse_request_alloc(gfp_t flags)
+static struct fuse_req *fuse_request_alloc(struct fuse_mount *fm, gfp_t flags)
{
struct fuse_req *req = kmem_cache_zalloc(fuse_req_cachep, flags);
if (req)
- fuse_request_init(req);
+ fuse_request_init(fm, req);
return req;
}
@@ -83,14 +171,15 @@ void fuse_set_initialized(struct fuse_conn *fc)
static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
{
- return !fc->initialized || (for_background && fc->blocked);
+ return !fc->initialized || (for_background && fc->blocked) ||
+ (fc->io_uring && fc->connected && !fuse_uring_ready(fc));
}
static void fuse_drop_waiting(struct fuse_conn *fc)
{
/*
* lockess check of fc->connected is okay, because atomic_dec_and_test()
- * provides a memory barrier mached with the one in fuse_wait_aborted()
+ * provides a memory barrier matched with the one in fuse_wait_aborted()
* to ensure no wake-up is missed.
*/
if (atomic_dec_and_test(&fc->num_waiting) &&
@@ -100,18 +189,26 @@ static void fuse_drop_waiting(struct fuse_conn *fc)
}
}
-static void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req);
+static void fuse_put_request(struct fuse_req *req);
-static struct fuse_req *fuse_get_req(struct fuse_conn *fc, bool for_background)
+static struct fuse_req *fuse_get_req(struct mnt_idmap *idmap,
+ struct fuse_mount *fm,
+ bool for_background)
{
+ struct fuse_conn *fc = fm->fc;
struct fuse_req *req;
+ bool no_idmap = !fm->sb || (fm->sb->s_iflags & SB_I_NOIDMAP);
+ kuid_t fsuid;
+ kgid_t fsgid;
int err;
+
atomic_inc(&fc->num_waiting);
if (fuse_block_alloc(fc, for_background)) {
err = -EINTR;
- if (wait_event_killable_exclusive(fc->blocked_waitq,
- !fuse_block_alloc(fc, for_background)))
+ if (wait_event_state_exclusive(fc->blocked_waitq,
+ !fuse_block_alloc(fc, for_background),
+ (TASK_KILLABLE | TASK_FREEZABLE)))
goto out;
}
/* Matches smp_wmb() in fuse_set_initialized() */
@@ -125,7 +222,7 @@ static struct fuse_req *fuse_get_req(struct fuse_conn *fc, bool for_background)
if (fc->conn_error)
goto out;
- req = fuse_request_alloc(GFP_KERNEL);
+ req = fuse_request_alloc(fm, GFP_KERNEL);
err = -ENOMEM;
if (!req) {
if (for_background)
@@ -133,19 +230,32 @@ static struct fuse_req *fuse_get_req(struct fuse_conn *fc, bool for_background)
goto out;
}
- req->in.h.uid = from_kuid(fc->user_ns, current_fsuid());
- req->in.h.gid = from_kgid(fc->user_ns, current_fsgid());
req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
__set_bit(FR_WAITING, &req->flags);
if (for_background)
__set_bit(FR_BACKGROUND, &req->flags);
- if (unlikely(req->in.h.uid == ((uid_t)-1) ||
- req->in.h.gid == ((gid_t)-1))) {
- fuse_put_request(fc, req);
+ /*
+ * Keep the old behavior when idmappings support was not
+ * declared by a FUSE server.
+ *
+ * For those FUSE servers who support idmapped mounts,
+ * we send UID/GID only along with "inode creation"
+ * fuse requests, otherwise idmap == &invalid_mnt_idmap and
+ * req->in.h.{u,g}id will be equal to FUSE_INVALID_UIDGID.
+ */
+ fsuid = no_idmap ? current_fsuid() : mapped_fsuid(idmap, fc->user_ns);
+ fsgid = no_idmap ? current_fsgid() : mapped_fsgid(idmap, fc->user_ns);
+ req->in.h.uid = from_kuid(fc->user_ns, fsuid);
+ req->in.h.gid = from_kgid(fc->user_ns, fsgid);
+
+ if (no_idmap && unlikely(req->in.h.uid == ((uid_t)-1) ||
+ req->in.h.gid == ((gid_t)-1))) {
+ fuse_put_request(req);
return ERR_PTR(-EOVERFLOW);
}
+
return req;
out:
@@ -153,8 +263,10 @@ static struct fuse_req *fuse_get_req(struct fuse_conn *fc, bool for_background)
return ERR_PTR(err);
}
-static void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
+static void fuse_put_request(struct fuse_req *req)
{
+ struct fuse_conn *fc = req->fm->fc;
+
if (refcount_dec_and_test(&req->count)) {
if (test_bit(FR_BACKGROUND, &req->flags)) {
/*
@@ -188,19 +300,31 @@ unsigned int fuse_len_args(unsigned int numargs, struct fuse_arg *args)
}
EXPORT_SYMBOL_GPL(fuse_len_args);
-u64 fuse_get_unique(struct fuse_iqueue *fiq)
+static u64 fuse_get_unique_locked(struct fuse_iqueue *fiq)
{
fiq->reqctr += FUSE_REQ_ID_STEP;
return fiq->reqctr;
}
+
+u64 fuse_get_unique(struct fuse_iqueue *fiq)
+{
+ u64 ret;
+
+ spin_lock(&fiq->lock);
+ ret = fuse_get_unique_locked(fiq);
+ spin_unlock(&fiq->lock);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(fuse_get_unique);
-static unsigned int fuse_req_hash(u64 unique)
+unsigned int fuse_req_hash(u64 unique)
{
return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS);
}
+EXPORT_SYMBOL_GPL(fuse_req_hash);
-/**
+/*
* A new request is available, wake fiq->waitq
*/
static void fuse_dev_wake_and_unlock(struct fuse_iqueue *fiq)
@@ -211,22 +335,90 @@ __releases(fiq->lock)
spin_unlock(&fiq->lock);
}
+void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
+ struct fuse_forget_link *forget)
+{
+ spin_lock(&fiq->lock);
+ if (fiq->connected) {
+ fiq->forget_list_tail->next = forget;
+ fiq->forget_list_tail = forget;
+ fuse_dev_wake_and_unlock(fiq);
+ } else {
+ kfree(forget);
+ spin_unlock(&fiq->lock);
+ }
+}
+
+void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
+{
+ spin_lock(&fiq->lock);
+ if (list_empty(&req->intr_entry)) {
+ list_add_tail(&req->intr_entry, &fiq->interrupts);
+ /*
+ * Pairs with smp_mb() implied by test_and_set_bit()
+ * from fuse_request_end().
+ */
+ smp_mb();
+ if (test_bit(FR_FINISHED, &req->flags)) {
+ list_del_init(&req->intr_entry);
+ spin_unlock(&fiq->lock);
+ } else {
+ fuse_dev_wake_and_unlock(fiq);
+ }
+ } else {
+ spin_unlock(&fiq->lock);
+ }
+}
+
+static inline void fuse_request_assign_unique_locked(struct fuse_iqueue *fiq,
+ struct fuse_req *req)
+{
+ if (req->in.h.opcode != FUSE_NOTIFY_REPLY)
+ req->in.h.unique = fuse_get_unique_locked(fiq);
+
+ /* tracepoint captures in.h.unique and in.h.len */
+ trace_fuse_request_send(req);
+}
+
+inline void fuse_request_assign_unique(struct fuse_iqueue *fiq,
+ struct fuse_req *req)
+{
+ if (req->in.h.opcode != FUSE_NOTIFY_REPLY)
+ req->in.h.unique = fuse_get_unique(fiq);
+
+ /* tracepoint captures in.h.unique and in.h.len */
+ trace_fuse_request_send(req);
+}
+EXPORT_SYMBOL_GPL(fuse_request_assign_unique);
+
+static void fuse_dev_queue_req(struct fuse_iqueue *fiq, struct fuse_req *req)
+{
+ spin_lock(&fiq->lock);
+ if (fiq->connected) {
+ fuse_request_assign_unique_locked(fiq, req);
+ list_add_tail(&req->list, &fiq->pending);
+ fuse_dev_wake_and_unlock(fiq);
+ } else {
+ spin_unlock(&fiq->lock);
+ req->out.h.error = -ENOTCONN;
+ clear_bit(FR_PENDING, &req->flags);
+ fuse_request_end(req);
+ }
+}
+
const struct fuse_iqueue_ops fuse_dev_fiq_ops = {
- .wake_forget_and_unlock = fuse_dev_wake_and_unlock,
- .wake_interrupt_and_unlock = fuse_dev_wake_and_unlock,
- .wake_pending_and_unlock = fuse_dev_wake_and_unlock,
+ .send_forget = fuse_dev_queue_forget,
+ .send_interrupt = fuse_dev_queue_interrupt,
+ .send_req = fuse_dev_queue_req,
};
EXPORT_SYMBOL_GPL(fuse_dev_fiq_ops);
-static void queue_request_and_unlock(struct fuse_iqueue *fiq,
- struct fuse_req *req)
-__releases(fiq->lock)
+static void fuse_send_one(struct fuse_iqueue *fiq, struct fuse_req *req)
{
req->in.h.len = sizeof(struct fuse_in_header) +
fuse_len_args(req->args->in_numargs,
(struct fuse_arg *) req->args->in_args);
- list_add_tail(&req->list, &fiq->pending);
- fiq->ops->wake_pending_and_unlock(fiq);
+ fiq->ops->send_req(fiq, req);
}
void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
@@ -237,15 +429,7 @@ void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
forget->forget_one.nodeid = nodeid;
forget->forget_one.nlookup = nlookup;
- spin_lock(&fiq->lock);
- if (fiq->connected) {
- fiq->forget_list_tail->next = forget;
- fiq->forget_list_tail = forget;
- fiq->ops->wake_forget_and_unlock(fiq);
- } else {
- kfree(forget);
- spin_unlock(&fiq->lock);
- }
+ fiq->ops->send_forget(fiq, forget);
}
static void flush_bg_queue(struct fuse_conn *fc)
@@ -259,9 +443,7 @@ static void flush_bg_queue(struct fuse_conn *fc)
req = list_first_entry(&fc->bg_queue, struct fuse_req, list);
list_del(&req->list);
fc->active_background++;
- spin_lock(&fiq->lock);
- req->in.h.unique = fuse_get_unique(fiq);
- queue_request_and_unlock(fiq, req);
+ fuse_send_one(fiq, req);
}
}
@@ -273,19 +455,22 @@ static void flush_bg_queue(struct fuse_conn *fc)
* the 'end' callback is called if given, else the reference to the
* request is released
*/
-void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
+void fuse_request_end(struct fuse_req *req)
{
+ struct fuse_mount *fm = req->fm;
+ struct fuse_conn *fc = fm->fc;
struct fuse_iqueue *fiq = &fc->iq;
if (test_and_set_bit(FR_FINISHED, &req->flags))
goto put_request;
+ trace_fuse_request_end(req);
/*
* test_and_set_bit() implies smp_mb() between bit
- * changing and below intr_entry check. Pairs with
+ * changing and below FR_INTERRUPTED check. Pairs with
* smp_mb() from queue_interrupt().
*/
- if (!list_empty(&req->intr_entry)) {
+ if (test_bit(FR_INTERRUPTED, &req->flags)) {
spin_lock(&fiq->lock);
list_del_init(&req->intr_entry);
spin_unlock(&fiq->lock);
@@ -309,10 +494,6 @@ void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
wake_up(&fc->blocked_waitq);
}
- if (fc->num_background == fc->congestion_threshold && fc->sb) {
- clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
- clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
- }
fc->num_background--;
fc->active_background--;
flush_bg_queue(fc);
@@ -323,42 +504,46 @@ void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
}
if (test_bit(FR_ASYNC, &req->flags))
- req->args->end(fc, req->args, req->out.h.error);
+ req->args->end(fm, req->args, req->out.h.error);
put_request:
- fuse_put_request(fc, req);
+ fuse_put_request(req);
}
EXPORT_SYMBOL_GPL(fuse_request_end);
-static int queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
+static int queue_interrupt(struct fuse_req *req)
{
- spin_lock(&fiq->lock);
+ struct fuse_iqueue *fiq = &req->fm->fc->iq;
+
/* Check for we've sent request to interrupt this req */
- if (unlikely(!test_bit(FR_INTERRUPTED, &req->flags))) {
- spin_unlock(&fiq->lock);
+ if (unlikely(!test_bit(FR_INTERRUPTED, &req->flags)))
return -EINVAL;
- }
- if (list_empty(&req->intr_entry)) {
- list_add_tail(&req->intr_entry, &fiq->interrupts);
+ fiq->ops->send_interrupt(fiq, req);
+
+ return 0;
+}
+
+bool fuse_remove_pending_req(struct fuse_req *req, spinlock_t *lock)
+{
+ spin_lock(lock);
+ if (test_bit(FR_PENDING, &req->flags)) {
/*
- * Pairs with smp_mb() implied by test_and_set_bit()
- * from fuse_request_end().
+ * FR_PENDING does not get cleared as the request will end
+ * up in destruction anyway.
*/
- smp_mb();
- if (test_bit(FR_FINISHED, &req->flags)) {
- list_del_init(&req->intr_entry);
- spin_unlock(&fiq->lock);
- return 0;
- }
- fiq->ops->wake_interrupt_and_unlock(fiq);
- } else {
- spin_unlock(&fiq->lock);
+ list_del(&req->list);
+ spin_unlock(lock);
+ __fuse_put_request(req);
+ req->out.h.error = -EINTR;
+ return true;
}
- return 0;
+ spin_unlock(lock);
+ return false;
}
-static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
+static void request_wait_answer(struct fuse_req *req)
{
+ struct fuse_conn *fc = req->fm->fc;
struct fuse_iqueue *fiq = &fc->iq;
int err;
@@ -373,26 +558,24 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
/* matches barrier in fuse_dev_do_read() */
smp_mb__after_atomic();
if (test_bit(FR_SENT, &req->flags))
- queue_interrupt(fiq, req);
+ queue_interrupt(req);
}
if (!test_bit(FR_FORCE, &req->flags)) {
+ bool removed;
+
/* Only fatal signals may interrupt this */
err = wait_event_killable(req->waitq,
test_bit(FR_FINISHED, &req->flags));
if (!err)
return;
- spin_lock(&fiq->lock);
- /* Request is not yet in userspace, bail out */
- if (test_bit(FR_PENDING, &req->flags)) {
- list_del(&req->list);
- spin_unlock(&fiq->lock);
- __fuse_put_request(req);
- req->out.h.error = -EINTR;
+ if (test_bit(FR_URING, &req->flags))
+ removed = fuse_uring_remove_pending_req(req);
+ else
+ removed = fuse_remove_pending_req(req, &fiq->lock);
+ if (removed)
return;
- }
- spin_unlock(&fiq->lock);
}
/*
@@ -402,26 +585,20 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags));
}
-static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
+static void __fuse_request_send(struct fuse_req *req)
{
- struct fuse_iqueue *fiq = &fc->iq;
+ struct fuse_iqueue *fiq = &req->fm->fc->iq;
BUG_ON(test_bit(FR_BACKGROUND, &req->flags));
- spin_lock(&fiq->lock);
- if (!fiq->connected) {
- spin_unlock(&fiq->lock);
- req->out.h.error = -ENOTCONN;
- } else {
- req->in.h.unique = fuse_get_unique(fiq);
- /* acquire extra reference, since request is still needed
- after fuse_request_end() */
- __fuse_get_request(req);
- queue_request_and_unlock(fiq, req);
- request_wait_answer(fc, req);
- /* Pairs with smp_wmb() in fuse_request_end() */
- smp_rmb();
- }
+ /* acquire extra reference, since request is still needed after
+ fuse_request_end() */
+ __fuse_get_request(req);
+ fuse_send_one(fiq, req);
+
+ request_wait_answer(req);
+ /* Pairs with smp_wmb() in fuse_request_end() */
+ smp_rmb();
}
static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args)
@@ -457,10 +634,18 @@ static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args)
}
}
-static void fuse_force_creds(struct fuse_conn *fc, struct fuse_req *req)
+static void fuse_force_creds(struct fuse_req *req)
{
- req->in.h.uid = from_kuid_munged(fc->user_ns, current_fsuid());
- req->in.h.gid = from_kgid_munged(fc->user_ns, current_fsgid());
+ struct fuse_conn *fc = req->fm->fc;
+
+ if (!req->fm->sb || req->fm->sb->s_iflags & SB_I_NOIDMAP) {
+ req->in.h.uid = from_kuid_munged(fc->user_ns, current_fsuid());
+ req->in.h.gid = from_kgid_munged(fc->user_ns, current_fsgid());
+ } else {
+ req->in.h.uid = FUSE_INVALID_UIDGID;
+ req->in.h.gid = FUSE_INVALID_UIDGID;
+ }
+
req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
}
@@ -469,27 +654,32 @@ static void fuse_args_to_req(struct fuse_req *req, struct fuse_args *args)
req->in.h.opcode = args->opcode;
req->in.h.nodeid = args->nodeid;
req->args = args;
+ if (args->is_ext)
+ req->in.h.total_extlen = args->in_args[args->ext_idx].size / 8;
if (args->end)
__set_bit(FR_ASYNC, &req->flags);
}
-ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
+ssize_t __fuse_simple_request(struct mnt_idmap *idmap,
+ struct fuse_mount *fm,
+ struct fuse_args *args)
{
+ struct fuse_conn *fc = fm->fc;
struct fuse_req *req;
ssize_t ret;
if (args->force) {
atomic_inc(&fc->num_waiting);
- req = fuse_request_alloc(GFP_KERNEL | __GFP_NOFAIL);
+ req = fuse_request_alloc(fm, GFP_KERNEL | __GFP_NOFAIL);
if (!args->nocreds)
- fuse_force_creds(fc, req);
+ fuse_force_creds(req);
__set_bit(FR_WAITING, &req->flags);
__set_bit(FR_FORCE, &req->flags);
} else {
WARN_ON(args->nocreds);
- req = fuse_get_req(fc, false);
+ req = fuse_get_req(idmap, fm, false);
if (IS_ERR(req))
return PTR_ERR(req);
}
@@ -500,20 +690,39 @@ ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
if (!args->noreply)
__set_bit(FR_ISREPLY, &req->flags);
- __fuse_request_send(fc, req);
+ __fuse_request_send(req);
ret = req->out.h.error;
if (!ret && args->out_argvar) {
BUG_ON(args->out_numargs == 0);
ret = args->out_args[args->out_numargs - 1].size;
}
- fuse_put_request(fc, req);
+ fuse_put_request(req);
return ret;
}
-static bool fuse_request_queue_background(struct fuse_conn *fc,
- struct fuse_req *req)
+#ifdef CONFIG_FUSE_IO_URING
+static bool fuse_request_queue_background_uring(struct fuse_conn *fc,
+ struct fuse_req *req)
+{
+ struct fuse_iqueue *fiq = &fc->iq;
+
+ req->in.h.len = sizeof(struct fuse_in_header) +
+ fuse_len_args(req->args->in_numargs,
+ (struct fuse_arg *) req->args->in_args);
+ fuse_request_assign_unique(fiq, req);
+
+ return fuse_uring_queue_bq_req(req);
+}
+#endif
+
+/*
+ * @return true if queued
+ */
+static int fuse_request_queue_background(struct fuse_req *req)
{
+ struct fuse_mount *fm = req->fm;
+ struct fuse_conn *fc = fm->fc;
bool queued = false;
WARN_ON(!test_bit(FR_BACKGROUND, &req->flags));
@@ -522,15 +731,17 @@ static bool fuse_request_queue_background(struct fuse_conn *fc,
atomic_inc(&fc->num_waiting);
}
__set_bit(FR_ISREPLY, &req->flags);
+
+#ifdef CONFIG_FUSE_IO_URING
+ if (fuse_uring_ready(fc))
+ return fuse_request_queue_background_uring(fc, req);
+#endif
+
spin_lock(&fc->bg_lock);
if (likely(fc->connected)) {
fc->num_background++;
if (fc->num_background == fc->max_background)
fc->blocked = 1;
- if (fc->num_background == fc->congestion_threshold && fc->sb) {
- set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
- set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
- }
list_add_tail(&req->list, &fc->bg_queue);
flush_bg_queue(fc);
queued = true;
@@ -540,28 +751,28 @@ static bool fuse_request_queue_background(struct fuse_conn *fc,
return queued;
}
-int fuse_simple_background(struct fuse_conn *fc, struct fuse_args *args,
+int fuse_simple_background(struct fuse_mount *fm, struct fuse_args *args,
gfp_t gfp_flags)
{
struct fuse_req *req;
if (args->force) {
WARN_ON(!args->nocreds);
- req = fuse_request_alloc(gfp_flags);
+ req = fuse_request_alloc(fm, gfp_flags);
if (!req)
return -ENOMEM;
__set_bit(FR_BACKGROUND, &req->flags);
} else {
WARN_ON(args->nocreds);
- req = fuse_get_req(fc, true);
+ req = fuse_get_req(&invalid_mnt_idmap, fm, true);
if (IS_ERR(req))
return PTR_ERR(req);
}
fuse_args_to_req(req, args);
- if (!fuse_request_queue_background(fc, req)) {
- fuse_put_request(fc, req);
+ if (!fuse_request_queue_background(req)) {
+ fuse_put_request(req);
return -ENOTCONN;
}
@@ -569,14 +780,13 @@ int fuse_simple_background(struct fuse_conn *fc, struct fuse_args *args,
}
EXPORT_SYMBOL_GPL(fuse_simple_background);
-static int fuse_simple_notify_reply(struct fuse_conn *fc,
+static int fuse_simple_notify_reply(struct fuse_mount *fm,
struct fuse_args *args, u64 unique)
{
struct fuse_req *req;
- struct fuse_iqueue *fiq = &fc->iq;
- int err = 0;
+ struct fuse_iqueue *fiq = &fm->fc->iq;
- req = fuse_get_req(fc, false);
+ req = fuse_get_req(&invalid_mnt_idmap, fm, false);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -585,16 +795,9 @@ static int fuse_simple_notify_reply(struct fuse_conn *fc,
fuse_args_to_req(req, args);
- spin_lock(&fiq->lock);
- if (fiq->connected) {
- queue_request_and_unlock(fiq, req);
- } else {
- err = -ENODEV;
- spin_unlock(&fiq->lock);
- fuse_put_request(fc, req);
- }
+ fuse_send_one(fiq, req);
- return err;
+ return 0;
}
/*
@@ -634,22 +837,8 @@ static int unlock_request(struct fuse_req *req)
return err;
}
-struct fuse_copy_state {
- int write;
- struct fuse_req *req;
- struct iov_iter *iter;
- struct pipe_buffer *pipebufs;
- struct pipe_buffer *currbuf;
- struct pipe_inode_info *pipe;
- unsigned long nr_segs;
- struct page *pg;
- unsigned len;
- unsigned offset;
- unsigned move_pages:1;
-};
-
-static void fuse_copy_init(struct fuse_copy_state *cs, int write,
- struct iov_iter *iter)
+void fuse_copy_init(struct fuse_copy_state *cs, bool write,
+ struct iov_iter *iter)
{
memset(cs, 0, sizeof(*cs));
cs->write = write;
@@ -657,7 +846,7 @@ static void fuse_copy_init(struct fuse_copy_state *cs, int write,
}
/* Unmap and put previous page of userspace buffer */
-static void fuse_copy_finish(struct fuse_copy_state *cs)
+void fuse_copy_finish(struct fuse_copy_state *cs)
{
if (cs->currbuf) {
struct pipe_buffer *buf = cs->currbuf;
@@ -725,14 +914,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
}
} else {
size_t off;
- err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
+ err = iov_iter_get_pages2(cs->iter, &page, PAGE_SIZE, 1, &off);
if (err < 0)
return err;
BUG_ON(!err);
cs->len = err;
cs->offset = off;
cs->pg = page;
- iov_iter_advance(cs->iter, err);
}
return lock_request(cs->req);
@@ -743,7 +931,7 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
unsigned ncpy = min(*size, cs->len);
if (val) {
- void *pgaddr = kmap_atomic(cs->pg);
+ void *pgaddr = kmap_local_page(cs->pg);
void *buf = pgaddr + cs->offset;
if (cs->write)
@@ -751,49 +939,60 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
else
memcpy(*val, buf, ncpy);
- kunmap_atomic(pgaddr);
+ kunmap_local(pgaddr);
*val += ncpy;
}
*size -= ncpy;
cs->len -= ncpy;
cs->offset += ncpy;
+ if (cs->is_uring)
+ cs->ring.copied_sz += ncpy;
+
return ncpy;
}
-static int fuse_check_page(struct page *page)
+static int fuse_check_folio(struct folio *folio)
{
- if (page_mapcount(page) ||
- page->mapping != NULL ||
- (page->flags & PAGE_FLAGS_CHECK_AT_PREP &
+ if (folio_mapped(folio) ||
+ folio->mapping != NULL ||
+ (folio->flags.f & PAGE_FLAGS_CHECK_AT_PREP &
~(1 << PG_locked |
1 << PG_referenced |
- 1 << PG_uptodate |
1 << PG_lru |
1 << PG_active |
+ 1 << PG_workingset |
1 << PG_reclaim |
- 1 << PG_waiters))) {
- dump_page(page, "fuse: trying to steal weird page");
+ 1 << PG_waiters |
+ LRU_GEN_MASK | LRU_REFS_MASK))) {
+ dump_page(&folio->page, "fuse: trying to steal weird page");
return 1;
}
return 0;
}
-static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
+/*
+ * Attempt to steal a page from the splice() pipe and move it into the
+ * pagecache. If successful, the pointer in @pagep will be updated. The
+ * folio that was originally in @pagep will lose a reference and the new
+ * folio returned in @pagep will carry a reference.
+ */
+static int fuse_try_move_folio(struct fuse_copy_state *cs, struct folio **foliop)
{
int err;
- struct page *oldpage = *pagep;
- struct page *newpage;
+ struct folio *oldfolio = *foliop;
+ struct folio *newfolio;
struct pipe_buffer *buf = cs->pipebufs;
+ folio_get(oldfolio);
err = unlock_request(cs->req);
if (err)
- return err;
+ goto out_put_old;
fuse_copy_finish(cs);
err = pipe_buf_confirm(cs->pipe, buf);
if (err)
- return err;
+ goto out_put_old;
BUG_ON(!cs->nr_segs);
cs->currbuf = buf;
@@ -801,81 +1000,87 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
cs->pipebufs++;
cs->nr_segs--;
- if (cs->len != PAGE_SIZE)
+ if (cs->len != folio_size(oldfolio))
goto out_fallback;
if (!pipe_buf_try_steal(cs->pipe, buf))
goto out_fallback;
- newpage = buf->page;
+ newfolio = page_folio(buf->page);
- if (!PageUptodate(newpage))
- SetPageUptodate(newpage);
+ folio_clear_uptodate(newfolio);
+ folio_clear_mappedtodisk(newfolio);
- ClearPageMappedToDisk(newpage);
-
- if (fuse_check_page(newpage) != 0)
+ if (fuse_check_folio(newfolio) != 0)
goto out_fallback_unlock;
/*
* This is a new and locked page, it shouldn't be mapped or
* have any special flags on it
*/
- if (WARN_ON(page_mapped(oldpage)))
+ if (WARN_ON(folio_mapped(oldfolio)))
goto out_fallback_unlock;
- if (WARN_ON(page_has_private(oldpage)))
+ if (WARN_ON(folio_has_private(oldfolio)))
goto out_fallback_unlock;
- if (WARN_ON(PageDirty(oldpage) || PageWriteback(oldpage)))
+ if (WARN_ON(folio_test_dirty(oldfolio) ||
+ folio_test_writeback(oldfolio)))
goto out_fallback_unlock;
- if (WARN_ON(PageMlocked(oldpage)))
+ if (WARN_ON(folio_test_mlocked(oldfolio)))
goto out_fallback_unlock;
- err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL);
- if (err) {
- unlock_page(newpage);
- return err;
- }
+ replace_page_cache_folio(oldfolio, newfolio);
- get_page(newpage);
+ folio_get(newfolio);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
- lru_cache_add(newpage);
+ folio_add_lru(newfolio);
+
+ /*
+ * Release while we have extra ref on stolen page. Otherwise
+ * anon_pipe_buf_release() might think the page can be reused.
+ */
+ pipe_buf_release(cs->pipe, buf);
err = 0;
spin_lock(&cs->req->waitq.lock);
if (test_bit(FR_ABORTED, &cs->req->flags))
err = -ENOENT;
else
- *pagep = newpage;
+ *foliop = newfolio;
spin_unlock(&cs->req->waitq.lock);
if (err) {
- unlock_page(newpage);
- put_page(newpage);
- return err;
+ folio_unlock(newfolio);
+ folio_put(newfolio);
+ goto out_put_old;
}
- unlock_page(oldpage);
- put_page(oldpage);
+ folio_unlock(oldfolio);
+ /* Drop ref for ap->pages[] array */
+ folio_put(oldfolio);
cs->len = 0;
- return 0;
+ err = 0;
+out_put_old:
+ /* Drop ref obtained in this function */
+ folio_put(oldfolio);
+ return err;
out_fallback_unlock:
- unlock_page(newpage);
+ folio_unlock(newfolio);
out_fallback:
cs->pg = buf->page;
cs->offset = buf->offset;
err = lock_request(cs->req);
- if (err)
- return err;
+ if (!err)
+ err = 1;
- return 1;
+ goto out_put_old;
}
-static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
- unsigned offset, unsigned count)
+static int fuse_ref_folio(struct fuse_copy_state *cs, struct folio *folio,
+ unsigned offset, unsigned count)
{
struct pipe_buffer *buf;
int err;
@@ -883,15 +1088,17 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
+ folio_get(folio);
err = unlock_request(cs->req);
- if (err)
+ if (err) {
+ folio_put(folio);
return err;
+ }
fuse_copy_finish(cs);
buf = cs->pipebufs;
- get_page(page);
- buf->page = page;
+ buf->page = &folio->page;
buf->offset = offset;
buf->len = count;
@@ -903,25 +1110,39 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
}
/*
- * Copy a page in the request to/from the userspace buffer. Must be
+ * Copy a folio in the request to/from the userspace buffer. Must be
* done atomically
*/
-static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
- unsigned offset, unsigned count, int zeroing)
+static int fuse_copy_folio(struct fuse_copy_state *cs, struct folio **foliop,
+ unsigned offset, unsigned count, int zeroing)
{
int err;
- struct page *page = *pagep;
+ struct folio *folio = *foliop;
+ size_t size;
- if (page && zeroing && count < PAGE_SIZE)
- clear_highpage(page);
+ if (folio) {
+ size = folio_size(folio);
+ if (zeroing && count < size)
+ folio_zero_range(folio, 0, size);
+ }
while (count) {
- if (cs->write && cs->pipebufs && page) {
- return fuse_ref_page(cs, page, offset, count);
+ if (cs->write && cs->pipebufs && folio) {
+ /*
+ * Can't control lifetime of pipe buffers, so always
+ * copy user pages.
+ */
+ if (cs->req->args->user_pages) {
+ err = fuse_copy_fill(cs);
+ if (err)
+ return err;
+ } else {
+ return fuse_ref_folio(cs, folio, offset, count);
+ }
} else if (!cs->len) {
- if (cs->move_pages && page &&
- offset == 0 && count == PAGE_SIZE) {
- err = fuse_try_move_page(cs, pagep);
+ if (cs->move_folios && folio &&
+ offset == 0 && count == size) {
+ err = fuse_try_move_folio(cs, foliop);
if (err <= 0)
return err;
} else {
@@ -930,34 +1151,41 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
return err;
}
}
- if (page) {
- void *mapaddr = kmap_atomic(page);
- void *buf = mapaddr + offset;
- offset += fuse_copy_do(cs, &buf, &count);
- kunmap_atomic(mapaddr);
+ if (folio) {
+ void *mapaddr = kmap_local_folio(folio, offset);
+ void *buf = mapaddr;
+ unsigned int copy = count;
+ unsigned int bytes_copied;
+
+ if (folio_test_highmem(folio) && count > PAGE_SIZE - offset_in_page(offset))
+ copy = PAGE_SIZE - offset_in_page(offset);
+
+ bytes_copied = fuse_copy_do(cs, &buf, &copy);
+ kunmap_local(mapaddr);
+ offset += bytes_copied;
+ count -= bytes_copied;
} else
offset += fuse_copy_do(cs, NULL, &count);
}
- if (page && !cs->write)
- flush_dcache_page(page);
+ if (folio && !cs->write)
+ flush_dcache_folio(folio);
return 0;
}
-/* Copy pages in the request to/from userspace buffer */
-static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
- int zeroing)
+/* Copy folios in the request to/from userspace buffer */
+static int fuse_copy_folios(struct fuse_copy_state *cs, unsigned nbytes,
+ int zeroing)
{
unsigned i;
struct fuse_req *req = cs->req;
struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args);
-
- for (i = 0; i < ap->num_pages && (nbytes || zeroing); i++) {
+ for (i = 0; i < ap->num_folios && (nbytes || zeroing); i++) {
int err;
unsigned int offset = ap->descs[i].offset;
unsigned int count = min(nbytes, ap->descs[i].length);
- err = fuse_copy_page(cs, &ap->pages[i], offset, count, zeroing);
+ err = fuse_copy_folio(cs, &ap->folios[i], offset, count, zeroing);
if (err)
return err;
@@ -981,9 +1209,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
}
/* Copy request arguments to/from userspace buffer */
-static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
- unsigned argpages, struct fuse_arg *args,
- int zeroing)
+int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
+ unsigned argpages, struct fuse_arg *args,
+ int zeroing)
{
int err = 0;
unsigned i;
@@ -991,7 +1219,7 @@ static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
for (i = 0; !err && i < numargs; i++) {
struct fuse_arg *arg = &args[i];
if (i == numargs - 1 && argpages)
- err = fuse_copy_pages(cs, arg->size, zeroing);
+ err = fuse_copy_folios(cs, arg->size, zeroing);
else
err = fuse_copy_one(cs, arg->value, arg->size);
}
@@ -1047,9 +1275,9 @@ __releases(fiq->lock)
return err ? err : reqsize;
}
-struct fuse_forget_link *fuse_dequeue_forget(struct fuse_iqueue *fiq,
- unsigned int max,
- unsigned int *countp)
+static struct fuse_forget_link *fuse_dequeue_forget(struct fuse_iqueue *fiq,
+ unsigned int max,
+ unsigned int *countp)
{
struct fuse_forget_link *head = fiq->forget_list_head.next;
struct fuse_forget_link **newhead = &head;
@@ -1068,7 +1296,6 @@ struct fuse_forget_link *fuse_dequeue_forget(struct fuse_iqueue *fiq,
return head;
}
-EXPORT_SYMBOL(fuse_dequeue_forget);
static int fuse_read_single_forget(struct fuse_iqueue *fiq,
struct fuse_copy_state *cs,
@@ -1083,7 +1310,7 @@ __releases(fiq->lock)
struct fuse_in_header ih = {
.opcode = FUSE_FORGET,
.nodeid = forget->forget_one.nodeid,
- .unique = fuse_get_unique(fiq),
+ .unique = fuse_get_unique_locked(fiq),
.len = sizeof(ih) + sizeof(arg),
};
@@ -1114,7 +1341,7 @@ __releases(fiq->lock)
struct fuse_batch_forget_in arg = { .count = 0 };
struct fuse_in_header ih = {
.opcode = FUSE_BATCH_FORGET,
- .unique = fuse_get_unique(fiq),
+ .unique = fuse_get_unique_locked(fiq),
.len = sizeof(ih) + sizeof(arg),
};
@@ -1250,10 +1477,19 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
/* SETXATTR is special, since it may contain too large data */
if (args->opcode == FUSE_SETXATTR)
req->out.h.error = -E2BIG;
- fuse_request_end(fc, req);
+ fuse_request_end(req);
goto restart;
}
spin_lock(&fpq->lock);
+ /*
+ * Must not put request on fpq->io queue after having been shut down by
+ * fuse_abort_conn()
+ */
+ if (!fpq->connected) {
+ req->out.h.error = err = -ECONNABORTED;
+ goto out_end;
+
+ }
list_add(&req->list, &fpq->io);
spin_unlock(&fpq->lock);
cs->req = req;
@@ -1284,8 +1520,8 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
/* matches barrier in request_wait_answer() */
smp_mb__after_atomic();
if (test_bit(FR_INTERRUPTED, &req->flags))
- queue_interrupt(fiq, req);
- fuse_put_request(fc, req);
+ queue_interrupt(req);
+ fuse_put_request(req);
return reqsize;
@@ -1293,7 +1529,7 @@ out_end:
if (!test_bit(FR_PRIVATE, &req->flags))
list_del_init(&req->list);
spin_unlock(&fpq->lock);
- fuse_request_end(fc, req);
+ fuse_request_end(req);
return err;
err_unlock:
@@ -1312,19 +1548,39 @@ static int fuse_dev_open(struct inode *inode, struct file *file)
return 0;
}
+struct fuse_dev *fuse_get_dev(struct file *file)
+{
+ struct fuse_dev *fud = __fuse_get_dev(file);
+ int err;
+
+ if (likely(fud))
+ return fud;
+
+ err = wait_event_interruptible(fuse_dev_waitq,
+ READ_ONCE(file->private_data) != FUSE_DEV_SYNC_INIT);
+ if (err)
+ return ERR_PTR(err);
+
+ fud = __fuse_get_dev(file);
+ if (!fud)
+ return ERR_PTR(-EPERM);
+
+ return fud;
+}
+
static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to)
{
struct fuse_copy_state cs;
struct file *file = iocb->ki_filp;
struct fuse_dev *fud = fuse_get_dev(file);
- if (!fud)
- return -EPERM;
+ if (IS_ERR(fud))
+ return PTR_ERR(fud);
- if (!iter_is_iovec(to))
+ if (!user_backed_iter(to))
return -EINVAL;
- fuse_copy_init(&cs, 1, to);
+ fuse_copy_init(&cs, true, to);
return fuse_dev_do_read(fud, file, &cs, iov_iter_count(to));
}
@@ -1339,22 +1595,22 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
struct fuse_copy_state cs;
struct fuse_dev *fud = fuse_get_dev(in);
- if (!fud)
- return -EPERM;
+ if (IS_ERR(fud))
+ return PTR_ERR(fud);
bufs = kvmalloc_array(pipe->max_usage, sizeof(struct pipe_buffer),
GFP_KERNEL);
if (!bufs)
return -ENOMEM;
- fuse_copy_init(&cs, 1, NULL);
+ fuse_copy_init(&cs, true, NULL);
cs.pipebufs = bufs;
cs.pipe = pipe;
ret = fuse_dev_do_read(fud, in, &cs, len);
if (ret < 0)
goto out;
- if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
+ if (pipe_buf_usage(pipe) + cs.nr_segs > pipe->max_usage) {
ret = -EIO;
goto out;
}
@@ -1384,78 +1640,65 @@ static int fuse_notify_poll(struct fuse_conn *fc, unsigned int size,
struct fuse_copy_state *cs)
{
struct fuse_notify_poll_wakeup_out outarg;
- int err = -EINVAL;
+ int err;
if (size != sizeof(outarg))
- goto err;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto err;
+ return err;
fuse_copy_finish(cs);
return fuse_notify_poll_wakeup(fc, &outarg);
-
-err:
- fuse_copy_finish(cs);
- return err;
}
static int fuse_notify_inval_inode(struct fuse_conn *fc, unsigned int size,
struct fuse_copy_state *cs)
{
struct fuse_notify_inval_inode_out outarg;
- int err = -EINVAL;
+ int err;
if (size != sizeof(outarg))
- goto err;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto err;
+ return err;
fuse_copy_finish(cs);
down_read(&fc->killsb);
- err = -ENOENT;
- if (fc->sb) {
- err = fuse_reverse_inval_inode(fc->sb, outarg.ino,
- outarg.off, outarg.len);
- }
+ err = fuse_reverse_inval_inode(fc, outarg.ino,
+ outarg.off, outarg.len);
up_read(&fc->killsb);
return err;
-
-err:
- fuse_copy_finish(cs);
- return err;
}
static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
struct fuse_copy_state *cs)
{
struct fuse_notify_inval_entry_out outarg;
- int err = -ENOMEM;
+ int err;
char *buf;
struct qstr name;
- buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
- if (!buf)
- goto err;
-
- err = -EINVAL;
if (size < sizeof(outarg))
- goto err;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto err;
+ return err;
- err = -ENAMETOOLONG;
- if (outarg.namelen > FUSE_NAME_MAX)
- goto err;
+ if (outarg.namelen > fc->name_max)
+ return -ENAMETOOLONG;
err = -EINVAL;
if (size != sizeof(outarg) + outarg.namelen + 1)
- goto err;
+ return -EINVAL;
+
+ buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
name.name = buf;
name.len = outarg.namelen;
@@ -1466,16 +1709,10 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
buf[outarg.namelen] = 0;
down_read(&fc->killsb);
- err = -ENOENT;
- if (fc->sb)
- err = fuse_reverse_inval_entry(fc->sb, outarg.parent, 0, &name);
+ err = fuse_reverse_inval_entry(fc, outarg.parent, 0, &name, outarg.flags);
up_read(&fc->killsb);
- kfree(buf);
- return err;
-
err:
kfree(buf);
- fuse_copy_finish(cs);
return err;
}
@@ -1483,29 +1720,26 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
struct fuse_copy_state *cs)
{
struct fuse_notify_delete_out outarg;
- int err = -ENOMEM;
+ int err;
char *buf;
struct qstr name;
- buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
- if (!buf)
- goto err;
-
- err = -EINVAL;
if (size < sizeof(outarg))
- goto err;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto err;
+ return err;
- err = -ENAMETOOLONG;
- if (outarg.namelen > FUSE_NAME_MAX)
- goto err;
+ if (outarg.namelen > fc->name_max)
+ return -ENAMETOOLONG;
- err = -EINVAL;
if (size != sizeof(outarg) + outarg.namelen + 1)
- goto err;
+ return -EINVAL;
+
+ buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
name.name = buf;
name.len = outarg.namelen;
@@ -1516,17 +1750,10 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
buf[outarg.namelen] = 0;
down_read(&fc->killsb);
- err = -ENOENT;
- if (fc->sb)
- err = fuse_reverse_inval_entry(fc->sb, outarg.parent,
- outarg.child, &name);
+ err = fuse_reverse_inval_entry(fc, outarg.parent, outarg.child, &name, 0);
up_read(&fc->killsb);
- kfree(buf);
- return err;
-
err:
kfree(buf);
- fuse_copy_finish(cs);
return err;
}
@@ -1544,27 +1771,22 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
loff_t file_size;
loff_t end;
- err = -EINVAL;
if (size < sizeof(outarg))
- goto out_finish;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto out_finish;
+ return err;
- err = -EINVAL;
if (size - sizeof(outarg) != outarg.size)
- goto out_finish;
+ return -EINVAL;
nodeid = outarg.nodeid;
down_read(&fc->killsb);
err = -ENOENT;
- if (!fc->sb)
- goto out_up_killsb;
-
- inode = ilookup5(fc->sb, nodeid, fuse_inode_eq, &nodeid);
+ inode = fuse_ilookup(fc, nodeid, NULL);
if (!inode)
goto out_up_killsb;
@@ -1575,34 +1797,40 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
end = outarg.offset + outarg.size;
if (end > file_size) {
file_size = end;
- fuse_write_update_size(inode, file_size);
+ fuse_write_update_attr(inode, file_size, outarg.size);
}
num = outarg.size;
while (num) {
- struct page *page;
- unsigned int this_num;
-
- err = -ENOMEM;
- page = find_or_create_page(mapping, index,
- mapping_gfp_mask(mapping));
- if (!page)
+ struct folio *folio;
+ unsigned int folio_offset;
+ unsigned int nr_bytes;
+ unsigned int nr_pages;
+
+ folio = filemap_grab_folio(mapping, index);
+ err = PTR_ERR(folio);
+ if (IS_ERR(folio))
goto out_iput;
- this_num = min_t(unsigned, num, PAGE_SIZE - offset);
- err = fuse_copy_page(cs, &page, offset, this_num, 0);
- if (!err && offset == 0 &&
- (this_num == PAGE_SIZE || file_size == end))
- SetPageUptodate(page);
- unlock_page(page);
- put_page(page);
+ folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+ nr_bytes = min_t(unsigned, num, folio_size(folio) - folio_offset);
+ nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ err = fuse_copy_folio(cs, &folio, folio_offset, nr_bytes, 0);
+ if (!folio_test_uptodate(folio) && !err && offset == 0 &&
+ (nr_bytes == folio_size(folio) || file_size == end)) {
+ folio_zero_segment(folio, nr_bytes, folio_size(folio));
+ folio_mark_uptodate(folio);
+ }
+ folio_unlock(folio);
+ folio_put(folio);
if (err)
goto out_iput;
- num -= this_num;
+ num -= nr_bytes;
offset = 0;
- index++;
+ index += nr_pages;
}
err = 0;
@@ -1611,8 +1839,6 @@ out_iput:
iput(inode);
out_up_killsb:
up_read(&fc->killsb);
-out_finish:
- fuse_copy_finish(cs);
return err;
}
@@ -1621,17 +1847,17 @@ struct fuse_retrieve_args {
struct fuse_notify_retrieve_in inarg;
};
-static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_args *args,
+static void fuse_retrieve_end(struct fuse_mount *fm, struct fuse_args *args,
int error)
{
struct fuse_retrieve_args *ra =
container_of(args, typeof(*ra), ap.args);
- release_pages(ra->ap.pages, ra->ap.num_pages);
+ release_pages(ra->ap.folios, ra->ap.num_folios);
kfree(ra);
}
-static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
+static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
struct fuse_notify_retrieve_out *outarg)
{
int err;
@@ -1642,6 +1868,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
unsigned int offset;
size_t total_len = 0;
unsigned int num_pages;
+ struct fuse_conn *fc = fm->fc;
struct fuse_retrieve_args *ra;
size_t args_size = sizeof(*ra);
struct fuse_args_pages *ap;
@@ -1658,54 +1885,61 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
num_pages = min(num_pages, fc->max_pages);
+ num = min(num, num_pages << PAGE_SHIFT);
- args_size += num_pages * (sizeof(ap->pages[0]) + sizeof(ap->descs[0]));
+ args_size += num_pages * (sizeof(ap->folios[0]) + sizeof(ap->descs[0]));
ra = kzalloc(args_size, GFP_KERNEL);
if (!ra)
return -ENOMEM;
ap = &ra->ap;
- ap->pages = (void *) (ra + 1);
- ap->descs = (void *) (ap->pages + num_pages);
+ ap->folios = (void *) (ra + 1);
+ ap->descs = (void *) (ap->folios + num_pages);
args = &ap->args;
args->nodeid = outarg->nodeid;
args->opcode = FUSE_NOTIFY_REPLY;
- args->in_numargs = 2;
+ args->in_numargs = 3;
args->in_pages = true;
args->end = fuse_retrieve_end;
index = outarg->offset >> PAGE_SHIFT;
- while (num && ap->num_pages < num_pages) {
- struct page *page;
- unsigned int this_num;
+ while (num && ap->num_folios < num_pages) {
+ struct folio *folio;
+ unsigned int folio_offset;
+ unsigned int nr_bytes;
+ unsigned int nr_pages;
- page = find_get_page(mapping, index);
- if (!page)
+ folio = filemap_get_folio(mapping, index);
+ if (IS_ERR(folio))
break;
- this_num = min_t(unsigned, num, PAGE_SIZE - offset);
- ap->pages[ap->num_pages] = page;
- ap->descs[ap->num_pages].offset = offset;
- ap->descs[ap->num_pages].length = this_num;
- ap->num_pages++;
+ folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+ nr_bytes = min(folio_size(folio) - folio_offset, num);
+ nr_pages = (offset + nr_bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ ap->folios[ap->num_folios] = folio;
+ ap->descs[ap->num_folios].offset = folio_offset;
+ ap->descs[ap->num_folios].length = nr_bytes;
+ ap->num_folios++;
offset = 0;
- num -= this_num;
- total_len += this_num;
- index++;
+ num -= nr_bytes;
+ total_len += nr_bytes;
+ index += nr_pages;
}
ra->inarg.offset = outarg->offset;
ra->inarg.size = total_len;
- args->in_args[0].size = sizeof(ra->inarg);
- args->in_args[0].value = &ra->inarg;
- args->in_args[1].size = total_len;
+ fuse_set_zero_arg0(args);
+ args->in_args[1].size = sizeof(ra->inarg);
+ args->in_args[1].value = &ra->inarg;
+ args->in_args[2].size = total_len;
- err = fuse_simple_notify_reply(fc, args, outarg->notify_unique);
+ err = fuse_simple_notify_reply(fm, args, outarg->notify_unique);
if (err)
- fuse_retrieve_end(fc, args, err);
+ fuse_retrieve_end(fm, args, err);
return err;
}
@@ -1714,44 +1948,152 @@ static int fuse_notify_retrieve(struct fuse_conn *fc, unsigned int size,
struct fuse_copy_state *cs)
{
struct fuse_notify_retrieve_out outarg;
+ struct fuse_mount *fm;
struct inode *inode;
+ u64 nodeid;
int err;
- err = -EINVAL;
if (size != sizeof(outarg))
- goto copy_finish;
+ return -EINVAL;
err = fuse_copy_one(cs, &outarg, sizeof(outarg));
if (err)
- goto copy_finish;
+ return err;
fuse_copy_finish(cs);
down_read(&fc->killsb);
err = -ENOENT;
- if (fc->sb) {
- u64 nodeid = outarg.nodeid;
+ nodeid = outarg.nodeid;
- inode = ilookup5(fc->sb, nodeid, fuse_inode_eq, &nodeid);
- if (inode) {
- err = fuse_retrieve(fc, inode, &outarg);
- iput(inode);
- }
+ inode = fuse_ilookup(fc, nodeid, &fm);
+ if (inode) {
+ err = fuse_retrieve(fm, inode, &outarg);
+ iput(inode);
}
up_read(&fc->killsb);
return err;
+}
-copy_finish:
- fuse_copy_finish(cs);
- return err;
+/*
+ * Resending all processing queue requests.
+ *
+ * During a FUSE daemon panics and failover, it is possible for some inflight
+ * requests to be lost and never returned. As a result, applications awaiting
+ * replies would become stuck forever. To address this, we can use notification
+ * to trigger resending of these pending requests to the FUSE daemon, ensuring
+ * they are properly processed again.
+ *
+ * Please note that this strategy is applicable only to idempotent requests or
+ * if the FUSE daemon takes careful measures to avoid processing duplicated
+ * non-idempotent requests.
+ */
+static void fuse_resend(struct fuse_conn *fc)
+{
+ struct fuse_dev *fud;
+ struct fuse_req *req, *next;
+ struct fuse_iqueue *fiq = &fc->iq;
+ LIST_HEAD(to_queue);
+ unsigned int i;
+
+ spin_lock(&fc->lock);
+ if (!fc->connected) {
+ spin_unlock(&fc->lock);
+ return;
+ }
+
+ list_for_each_entry(fud, &fc->devices, entry) {
+ struct fuse_pqueue *fpq = &fud->pq;
+
+ spin_lock(&fpq->lock);
+ for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+ list_splice_tail_init(&fpq->processing[i], &to_queue);
+ spin_unlock(&fpq->lock);
+ }
+ spin_unlock(&fc->lock);
+
+ list_for_each_entry_safe(req, next, &to_queue, list) {
+ set_bit(FR_PENDING, &req->flags);
+ clear_bit(FR_SENT, &req->flags);
+ /* mark the request as resend request */
+ req->in.h.unique |= FUSE_UNIQUE_RESEND;
+ }
+
+ spin_lock(&fiq->lock);
+ if (!fiq->connected) {
+ spin_unlock(&fiq->lock);
+ list_for_each_entry(req, &to_queue, list)
+ clear_bit(FR_PENDING, &req->flags);
+ fuse_dev_end_requests(&to_queue);
+ return;
+ }
+ /* iq and pq requests are both oldest to newest */
+ list_splice(&to_queue, &fiq->pending);
+ fuse_dev_wake_and_unlock(fiq);
+}
+
+static int fuse_notify_resend(struct fuse_conn *fc)
+{
+ fuse_resend(fc);
+ return 0;
+}
+
+/*
+ * Increments the fuse connection epoch. This will result of dentries from
+ * previous epochs to be invalidated. Additionally, if inval_wq is set, a work
+ * queue is scheduled to trigger the invalidation.
+ */
+static int fuse_notify_inc_epoch(struct fuse_conn *fc)
+{
+ atomic_inc(&fc->epoch);
+ if (inval_wq)
+ schedule_work(&fc->epoch_work);
+
+ return 0;
+}
+
+static int fuse_notify_prune(struct fuse_conn *fc, unsigned int size,
+ struct fuse_copy_state *cs)
+{
+ struct fuse_notify_prune_out outarg;
+ const unsigned int batch = 512;
+ u64 *nodeids __free(kfree) = kmalloc(sizeof(u64) * batch, GFP_KERNEL);
+ unsigned int num, i;
+ int err;
+
+ if (!nodeids)
+ return -ENOMEM;
+
+ if (size < sizeof(outarg))
+ return -EINVAL;
+
+ err = fuse_copy_one(cs, &outarg, sizeof(outarg));
+ if (err)
+ return err;
+
+ if (size - sizeof(outarg) != outarg.count * sizeof(u64))
+ return -EINVAL;
+
+ for (; outarg.count; outarg.count -= num) {
+ num = min(batch, outarg.count);
+ err = fuse_copy_one(cs, nodeids, num * sizeof(u64));
+ if (err)
+ return err;
+
+ scoped_guard(rwsem_read, &fc->killsb) {
+ for (i = 0; i < num; i++)
+ fuse_try_prune_one_inode(fc, nodeids[i]);
+ }
+ }
+ return 0;
}
static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
unsigned int size, struct fuse_copy_state *cs)
{
- /* Don't try to move pages (yet) */
- cs->move_pages = 0;
+ /* Don't try to move folios (yet) */
+ cs->move_folios = false;
switch (code) {
case FUSE_NOTIFY_POLL:
@@ -1772,14 +2114,22 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
case FUSE_NOTIFY_DELETE:
return fuse_notify_delete(fc, size, cs);
+ case FUSE_NOTIFY_RESEND:
+ return fuse_notify_resend(fc);
+
+ case FUSE_NOTIFY_INC_EPOCH:
+ return fuse_notify_inc_epoch(fc);
+
+ case FUSE_NOTIFY_PRUNE:
+ return fuse_notify_prune(fc, size, cs);
+
default:
- fuse_copy_finish(cs);
return -EINVAL;
}
}
/* Look up request on processing list by unique ID */
-static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
+struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique)
{
unsigned int hash = fuse_req_hash(unique);
struct fuse_req *req;
@@ -1791,10 +2141,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
return NULL;
}
-static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
- unsigned nbytes)
+int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
+ unsigned nbytes)
{
- unsigned reqsize = sizeof(struct fuse_out_header);
+
+ unsigned int reqsize = 0;
+
+ /*
+ * Uring has all headers separated from args - args is payload only
+ */
+ if (!cs->is_uring)
+ reqsize = sizeof(struct fuse_out_header);
reqsize += fuse_len_args(args->out_numargs, args->out_args);
@@ -1846,17 +2203,17 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
*/
if (!oh.unique) {
err = fuse_notify(fc, oh.error, nbytes - sizeof(oh), cs);
- goto out;
+ goto copy_finish;
}
err = -EINVAL;
- if (oh.error <= -1000 || oh.error > 0)
+ if (oh.error <= -512 || oh.error > 0)
goto copy_finish;
spin_lock(&fpq->lock);
req = NULL;
if (fpq->connected)
- req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
+ req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
err = -ENOENT;
if (!req) {
@@ -1875,9 +2232,9 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
else if (oh.error == -ENOSYS)
fc->no_interrupt = 1;
else if (oh.error == -EAGAIN)
- err = queue_interrupt(&fc->iq, req);
+ err = queue_interrupt(req);
- fuse_put_request(fc, req);
+ fuse_put_request(req);
goto copy_finish;
}
@@ -1889,12 +2246,12 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
spin_unlock(&fpq->lock);
cs->req = req;
if (!req->args->page_replace)
- cs->move_pages = 0;
+ cs->move_folios = false;
if (oh.error)
err = nbytes != sizeof(oh) ? -EINVAL : 0;
else
- err = copy_out_args(cs, req->args, nbytes);
+ err = fuse_copy_out_args(cs, req->args, nbytes);
fuse_copy_finish(cs);
spin_lock(&fpq->lock);
@@ -1907,7 +2264,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
list_del_init(&req->list);
spin_unlock(&fpq->lock);
- fuse_request_end(fc, req);
+ fuse_request_end(req);
out:
return err ? err : nbytes;
@@ -1919,15 +2276,15 @@ copy_finish:
static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from)
{
struct fuse_copy_state cs;
- struct fuse_dev *fud = fuse_get_dev(iocb->ki_filp);
+ struct fuse_dev *fud = __fuse_get_dev(iocb->ki_filp);
if (!fud)
return -EPERM;
- if (!iter_is_iovec(from))
+ if (!user_backed_iter(from))
return -EINVAL;
- fuse_copy_init(&cs, 0, from);
+ fuse_copy_init(&cs, false, from);
return fuse_dev_do_write(fud, &cs, iov_iter_count(from));
}
@@ -1936,16 +2293,15 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
- unsigned int head, tail, mask, count;
+ unsigned int head, tail, count;
unsigned nbuf;
unsigned idx;
struct pipe_buffer *bufs;
struct fuse_copy_state cs;
- struct fuse_dev *fud;
+ struct fuse_dev *fud = __fuse_get_dev(out);
size_t rem;
ssize_t ret;
- fud = fuse_get_dev(out);
if (!fud)
return -EPERM;
@@ -1953,8 +2309,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
head = pipe->head;
tail = pipe->tail;
- mask = pipe->ring_size - 1;
- count = head - tail;
+ count = pipe_occupancy(head, tail);
bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
if (!bufs) {
@@ -1964,8 +2319,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
nbuf = 0;
rem = 0;
- for (idx = tail; idx != head && rem < len; idx++)
- rem += pipe->bufs[idx & mask].len;
+ for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++)
+ rem += pipe_buf(pipe, idx)->len;
ret = -EINVAL;
if (rem < len)
@@ -1976,10 +2331,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct pipe_buffer *ibuf;
struct pipe_buffer *obuf;
- if (WARN_ON(nbuf >= count || tail == head))
+ if (WARN_ON(nbuf >= count || pipe_empty(head, tail)))
goto out_free;
- ibuf = &pipe->bufs[tail & mask];
+ ibuf = pipe_buf(pipe, tail);
obuf = &bufs[nbuf];
if (rem >= ibuf->len) {
@@ -2002,20 +2357,24 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
}
pipe_unlock(pipe);
- fuse_copy_init(&cs, 0, NULL);
+ fuse_copy_init(&cs, false, NULL);
cs.pipebufs = bufs;
cs.nr_segs = nbuf;
cs.pipe = pipe;
if (flags & SPLICE_F_MOVE)
- cs.move_pages = 1;
+ cs.move_folios = true;
ret = fuse_dev_do_write(fud, &cs, len);
pipe_lock(pipe);
out_free:
- for (idx = 0; idx < nbuf; idx++)
- pipe_buf_release(pipe, &bufs[idx]);
+ for (idx = 0; idx < nbuf; idx++) {
+ struct pipe_buffer *buf = &bufs[idx];
+
+ if (buf->ops)
+ pipe_buf_release(pipe, buf);
+ }
pipe_unlock(pipe);
kvfree(bufs);
@@ -2028,7 +2387,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait)
struct fuse_iqueue *fiq;
struct fuse_dev *fud = fuse_get_dev(file);
- if (!fud)
+ if (IS_ERR(fud))
return EPOLLERR;
fiq = &fud->fc->iq;
@@ -2045,7 +2404,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait)
}
/* Abort all requests on the given list (pending or processing) */
-static void end_requests(struct fuse_conn *fc, struct list_head *head)
+void fuse_dev_end_requests(struct list_head *head)
{
while (!list_empty(head)) {
struct fuse_req *req;
@@ -2053,7 +2412,7 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
req->out.h.error = -ECONNABORTED;
clear_bit(FR_SENT, &req->flags);
list_del_init(&req->list);
- fuse_request_end(fc, req);
+ fuse_request_end(req);
}
}
@@ -2081,7 +2440,7 @@ static void end_polls(struct fuse_conn *fc)
* The same effect is usually achievable through killing the filesystem daemon
* and all users of the filesystem. The exception is the combination of an
* asynchronous request and the tricky deadlock (see
- * Documentation/filesystems/fuse.rst).
+ * Documentation/filesystems/fuse/fuse.rst).
*
* Aborting requests under I/O goes as follows: 1: Separate out unlocked
* requests, they should be finished off immediately. Locked requests will be
@@ -2101,6 +2460,9 @@ void fuse_abort_conn(struct fuse_conn *fc)
LIST_HEAD(to_end);
unsigned int i;
+ if (fc->timeout.req_timeout)
+ cancel_delayed_work(&fc->timeout.work);
+
/* Background queuing checks fc->connected under bg_lock */
spin_lock(&fc->bg_lock);
fc->connected = 0;
@@ -2148,7 +2510,13 @@ void fuse_abort_conn(struct fuse_conn *fc)
wake_up_all(&fc->blocked_waitq);
spin_unlock(&fc->lock);
- end_requests(fc, &to_end);
+ fuse_dev_end_requests(&to_end);
+
+ /*
+ * fc->lock must not be taken to avoid conflicts with io-uring
+ * locks
+ */
+ fuse_uring_abort(fc);
} else {
spin_unlock(&fc->lock);
}
@@ -2160,11 +2528,13 @@ void fuse_wait_aborted(struct fuse_conn *fc)
/* matches implicit memory barrier in fuse_drop_waiting() */
smp_mb();
wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0);
+
+ fuse_uring_wait_stopped_queues(fc);
}
int fuse_dev_release(struct inode *inode, struct file *file)
{
- struct fuse_dev *fud = fuse_get_dev(file);
+ struct fuse_dev *fud = __fuse_get_dev(file);
if (fud) {
struct fuse_conn *fc = fud->fc;
@@ -2178,7 +2548,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
list_splice_init(&fpq->processing[i], &to_end);
spin_unlock(&fpq->lock);
- end_requests(fc, &to_end);
+ fuse_dev_end_requests(&to_end);
/* Are we the last open device? */
if (atomic_dec_and_test(&fc->dev_count)) {
@@ -2195,8 +2565,8 @@ static int fuse_dev_fasync(int fd, struct file *file, int on)
{
struct fuse_dev *fud = fuse_get_dev(file);
- if (!fud)
- return -EPERM;
+ if (IS_ERR(fud))
+ return PTR_ERR(fud);
/* No locking - fasync_helper does its own locking */
return fasync_helper(fd, file, on, &fud->fc->iq.fasync);
@@ -2206,7 +2576,7 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
{
struct fuse_dev *fud;
- if (new->private_data)
+ if (__fuse_get_dev(new))
return -EINVAL;
fud = fuse_dev_alloc_install(fc);
@@ -2219,46 +2589,121 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
return 0;
}
+static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
+{
+ int res;
+ int oldfd;
+ struct fuse_dev *fud = NULL;
+
+ if (get_user(oldfd, argp))
+ return -EFAULT;
+
+ CLASS(fd, f)(oldfd);
+ if (fd_empty(f))
+ return -EINVAL;
+
+ /*
+ * Check against file->f_op because CUSE
+ * uses the same ioctl handler.
+ */
+ if (fd_file(f)->f_op == file->f_op)
+ fud = __fuse_get_dev(fd_file(f));
+
+ res = -EINVAL;
+ if (fud) {
+ mutex_lock(&fuse_mutex);
+ res = fuse_device_clone(fud->fc, file);
+ mutex_unlock(&fuse_mutex);
+ }
+
+ return res;
+}
+
+static long fuse_dev_ioctl_backing_open(struct file *file,
+ struct fuse_backing_map __user *argp)
+{
+ struct fuse_dev *fud = fuse_get_dev(file);
+ struct fuse_backing_map map;
+
+ if (IS_ERR(fud))
+ return PTR_ERR(fud);
+
+ if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&map, argp, sizeof(map)))
+ return -EFAULT;
+
+ return fuse_backing_open(fud->fc, &map);
+}
+
+static long fuse_dev_ioctl_backing_close(struct file *file, __u32 __user *argp)
+{
+ struct fuse_dev *fud = fuse_get_dev(file);
+ int backing_id;
+
+ if (IS_ERR(fud))
+ return PTR_ERR(fud);
+
+ if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ return -EOPNOTSUPP;
+
+ if (get_user(backing_id, argp))
+ return -EFAULT;
+
+ return fuse_backing_close(fud->fc, backing_id);
+}
+
+static long fuse_dev_ioctl_sync_init(struct file *file)
+{
+ int err = -EINVAL;
+
+ mutex_lock(&fuse_mutex);
+ if (!__fuse_get_dev(file)) {
+ WRITE_ONCE(file->private_data, FUSE_DEV_SYNC_INIT);
+ err = 0;
+ }
+ mutex_unlock(&fuse_mutex);
+ return err;
+}
+
static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- int err = -ENOTTY;
+ void __user *argp = (void __user *)arg;
- if (cmd == FUSE_DEV_IOC_CLONE) {
- int oldfd;
+ switch (cmd) {
+ case FUSE_DEV_IOC_CLONE:
+ return fuse_dev_ioctl_clone(file, argp);
- err = -EFAULT;
- if (!get_user(oldfd, (__u32 __user *) arg)) {
- struct file *old = fget(oldfd);
+ case FUSE_DEV_IOC_BACKING_OPEN:
+ return fuse_dev_ioctl_backing_open(file, argp);
- err = -EINVAL;
- if (old) {
- struct fuse_dev *fud = NULL;
-
- /*
- * Check against file->f_op because CUSE
- * uses the same ioctl handler.
- */
- if (old->f_op == file->f_op &&
- old->f_cred->user_ns == file->f_cred->user_ns)
- fud = fuse_get_dev(old);
-
- if (fud) {
- mutex_lock(&fuse_mutex);
- err = fuse_device_clone(fud->fc, file);
- mutex_unlock(&fuse_mutex);
- }
- fput(old);
- }
- }
+ case FUSE_DEV_IOC_BACKING_CLOSE:
+ return fuse_dev_ioctl_backing_close(file, argp);
+
+ case FUSE_DEV_IOC_SYNC_INIT:
+ return fuse_dev_ioctl_sync_init(file);
+
+ default:
+ return -ENOTTY;
}
- return err;
}
+#ifdef CONFIG_PROC_FS
+static void fuse_dev_show_fdinfo(struct seq_file *seq, struct file *file)
+{
+ struct fuse_dev *fud = __fuse_get_dev(file);
+ if (!fud)
+ return;
+
+ seq_printf(seq, "fuse_connection:\t%u\n", fud->fc->dev);
+}
+#endif
+
const struct file_operations fuse_dev_operations = {
.owner = THIS_MODULE,
.open = fuse_dev_open,
- .llseek = no_llseek,
.read_iter = fuse_dev_read,
.splice_read = fuse_dev_splice_read,
.write_iter = fuse_dev_write,
@@ -2268,6 +2713,12 @@ const struct file_operations fuse_dev_operations = {
.fasync = fuse_dev_fasync,
.unlocked_ioctl = fuse_dev_ioctl,
.compat_ioctl = compat_ptr_ioctl,
+#ifdef CONFIG_FUSE_IO_URING
+ .uring_cmd = fuse_uring_cmd,
+#endif
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = fuse_dev_show_fdinfo,
+#endif
};
EXPORT_SYMBOL_GPL(fuse_dev_operations);
generated by cgit (git 2.34.1) at 2025-12-25 21:10:00 +0000