summaryrefslogtreecommitdiff
path: root/fs/fuse
diff options
context:
space:
mode:
Diffstat (limited to 'fs/fuse')
-rw-r--r--fs/fuse/Kconfig1
-rw-r--r--fs/fuse/control.c30
-rw-r--r--fs/fuse/dax.c3
-rw-r--r--fs/fuse/dev.c342
-rw-r--r--fs/fuse/dev_uring.c75
-rw-r--r--fs/fuse/dev_uring_i.h18
-rw-r--r--fs/fuse/dir.c69
-rw-r--r--fs/fuse/file.c797
-rw-r--r--fs/fuse/fuse_dev_i.h11
-rw-r--r--fs/fuse/fuse_i.h68
-rw-r--r--fs/fuse/inode.c72
-rw-r--r--fs/fuse/ioctl.c8
-rw-r--r--fs/fuse/readdir.c40
-rw-r--r--fs/fuse/sysctl.c24
-rw-r--r--fs/fuse/virtio_fs.c14
15 files changed, 800 insertions, 772 deletions
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index ca215a3cba3e..a774166264de 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -2,6 +2,7 @@
config FUSE_FS
tristate "FUSE (Filesystem in Userspace) support"
select FS_POSIX_ACL
+ select FS_IOMAP
help
With FUSE it is possible to implement a fully functional filesystem
in a userspace program.
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 2a730d88cc3b..bb407705603c 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -11,6 +11,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs_context.h>
+#include <linux/namei.h>
#define FUSE_CTL_SUPER_MAGIC 0x65735543
@@ -212,7 +213,6 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
struct dentry *dentry;
struct inode *inode;
- BUG_ON(fc->ctl_ndents >= FUSE_CTL_NUM_DENTRIES);
dentry = d_alloc_name(parent, name);
if (!dentry)
return NULL;
@@ -236,8 +236,6 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
inode->i_private = fc;
d_add(dentry, inode);
- fc->ctl_dentry[fc->ctl_ndents++] = dentry;
-
return dentry;
}
@@ -280,27 +278,29 @@ int fuse_ctl_add_conn(struct fuse_conn *fc)
return -ENOMEM;
}
+static void remove_one(struct dentry *dentry)
+{
+ d_inode(dentry)->i_private = NULL;
+}
+
/*
* Remove a connection from the control filesystem (if it exists).
* Caller must hold fuse_mutex
*/
void fuse_ctl_remove_conn(struct fuse_conn *fc)
{
- int i;
+ struct dentry *dentry;
+ char name[32];
if (!fuse_control_sb || fc->no_control)
return;
- for (i = fc->ctl_ndents - 1; i >= 0; i--) {
- struct dentry *dentry = fc->ctl_dentry[i];
- d_inode(dentry)->i_private = NULL;
- if (!i) {
- /* Get rid of submounts: */
- d_invalidate(dentry);
- }
- dput(dentry);
+ sprintf(name, "%u", fc->dev);
+ dentry = lookup_noperm_positive_unlocked(&QSTR(name), fuse_control_sb->s_root);
+ if (!IS_ERR(dentry)) {
+ simple_recursive_removal(dentry, remove_one);
+ dput(dentry); // paired with lookup_noperm_positive_unlocked()
}
- drop_nlink(d_inode(fuse_control_sb->s_root));
}
static int fuse_ctl_fill_super(struct super_block *sb, struct fs_context *fsc)
@@ -346,12 +346,8 @@ static int fuse_ctl_init_fs_context(struct fs_context *fsc)
static void fuse_ctl_kill_sb(struct super_block *sb)
{
- struct fuse_conn *fc;
-
mutex_lock(&fuse_mutex);
fuse_control_sb = NULL;
- list_for_each_entry(fc, &fuse_conn_list, entry)
- fc->ctl_ndents = 0;
mutex_unlock(&fuse_mutex);
kill_litter_super(sb);
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 0502bf3cdf6a..ac6d4c1064cc 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -10,7 +10,6 @@
#include <linux/dax.h>
#include <linux/uio.h>
#include <linux/pagemap.h>
-#include <linux/pfn_t.h>
#include <linux/iomap.h>
#include <linux/interval_tree.h>
@@ -757,7 +756,7 @@ static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf, unsigned int order,
vm_fault_t ret;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
- pfn_t pfn;
+ unsigned long pfn;
int error = 0;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_conn_dax *fcd = fc->dax;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 51e31df4c546..e80cd8f2c049 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -23,6 +23,7 @@
#include <linux/swap.h>
#include <linux/splice.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#define CREATE_TRACE_POINTS
#include "fuse_trace.h"
@@ -32,6 +33,100 @@ MODULE_ALIAS("devname:fuse");
static struct kmem_cache *fuse_req_cachep;
+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)
+{
+ 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_wq, &fc->timeout.work,
+ fuse_timeout_timer_freq);
+ return;
+
+abort_conn:
+ fuse_abort_conn(fc);
+}
+
static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
{
INIT_LIST_HEAD(&req->list);
@@ -40,6 +135,7 @@ static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
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(struct fuse_mount *fm, gfp_t flags)
@@ -407,6 +503,24 @@ static int queue_interrupt(struct fuse_req *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)) {
+ /*
+ * FR_PENDING does not get cleared as the request will end
+ * up in destruction anyway.
+ */
+ list_del(&req->list);
+ spin_unlock(lock);
+ __fuse_put_request(req);
+ req->out.h.error = -EINTR;
+ return true;
+ }
+ spin_unlock(lock);
+ return false;
+}
+
static void request_wait_answer(struct fuse_req *req)
{
struct fuse_conn *fc = req->fm->fc;
@@ -428,22 +542,20 @@ static void request_wait_answer(struct fuse_req *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);
}
/*
@@ -705,7 +817,7 @@ static int unlock_request(struct fuse_req *req)
return err;
}
-void fuse_copy_init(struct fuse_copy_state *cs, int write,
+void fuse_copy_init(struct fuse_copy_state *cs, bool write,
struct iov_iter *iter)
{
memset(cs, 0, sizeof(*cs));
@@ -844,10 +956,10 @@ static int fuse_check_folio(struct folio *folio)
* 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_page(struct fuse_copy_state *cs, struct page **pagep)
+static int fuse_try_move_folio(struct fuse_copy_state *cs, struct folio **foliop)
{
int err;
- struct folio *oldfolio = page_folio(*pagep);
+ struct folio *oldfolio = *foliop;
struct folio *newfolio;
struct pipe_buffer *buf = cs->pipebufs;
@@ -868,7 +980,7 @@ 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))
@@ -914,7 +1026,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
if (test_bit(FR_ABORTED, &cs->req->flags))
err = -ENOENT;
else
- *pagep = &newfolio->page;
+ *foliop = newfolio;
spin_unlock(&cs->req->waitq.lock);
if (err) {
@@ -947,8 +1059,8 @@ out_fallback:
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;
@@ -956,17 +1068,17 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
if (cs->nr_segs >= cs->pipe->max_usage)
return -EIO;
- get_page(page);
+ folio_get(folio);
err = unlock_request(cs->req);
if (err) {
- put_page(page);
+ folio_put(folio);
return err;
}
fuse_copy_finish(cs);
buf = cs->pipebufs;
- buf->page = page;
+ buf->page = &folio->page;
buf->offset = offset;
buf->len = count;
@@ -978,20 +1090,24 @@ 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) {
+ if (cs->write && cs->pipebufs && folio) {
/*
* Can't control lifetime of pipe buffers, so always
* copy user pages.
@@ -1001,12 +1117,12 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
if (err)
return err;
} else {
- return fuse_ref_page(cs, page, offset, count);
+ 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 {
@@ -1015,22 +1131,30 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
return err;
}
}
- if (page) {
- void *mapaddr = kmap_local_page(page);
- void *buf = mapaddr + offset;
- offset += fuse_copy_do(cs, &buf, &count);
+ 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;
@@ -1040,23 +1164,12 @@ static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
int err;
unsigned int offset = ap->descs[i].offset;
unsigned int count = min(nbytes, ap->descs[i].length);
- struct page *orig, *pagep;
-
- orig = pagep = &ap->folios[i]->page;
- err = fuse_copy_page(cs, &pagep, offset, count, zeroing);
+ err = fuse_copy_folio(cs, &ap->folios[i], offset, count, zeroing);
if (err)
return err;
nbytes -= count;
-
- /*
- * fuse_copy_page may have moved a page from a pipe instead of
- * copying into our given page, so update the folios if it was
- * replaced.
- */
- if (pagep != orig)
- ap->folios[i] = page_folio(pagep);
}
return 0;
}
@@ -1086,7 +1199,7 @@ 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);
}
@@ -1427,7 +1540,7 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *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));
}
@@ -1450,7 +1563,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
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);
@@ -1533,14 +1646,10 @@ 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;
- char *buf;
+ int err;
+ char *buf = NULL;
struct qstr name;
- buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
- if (!buf)
- goto err;
-
err = -EINVAL;
if (size < sizeof(outarg))
goto err;
@@ -1550,13 +1659,18 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
goto err;
err = -ENAMETOOLONG;
- if (outarg.namelen > FUSE_NAME_MAX)
+ if (outarg.namelen > fc->name_max)
goto err;
err = -EINVAL;
if (size != sizeof(outarg) + outarg.namelen + 1)
goto err;
+ err = -ENOMEM;
+ buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+ if (!buf)
+ goto err;
+
name.name = buf;
name.len = outarg.namelen;
err = fuse_copy_one(cs, buf, outarg.namelen + 1);
@@ -1581,14 +1695,10 @@ 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;
- char *buf;
+ int err;
+ char *buf = NULL;
struct qstr name;
- buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
- if (!buf)
- goto err;
-
err = -EINVAL;
if (size < sizeof(outarg))
goto err;
@@ -1598,13 +1708,18 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
goto err;
err = -ENAMETOOLONG;
- if (outarg.namelen > FUSE_NAME_MAX)
+ if (outarg.namelen > fc->name_max)
goto err;
err = -EINVAL;
if (size != sizeof(outarg) + outarg.namelen + 1)
goto err;
+ err = -ENOMEM;
+ buf = kzalloc(outarg.namelen + 1, GFP_KERNEL);
+ if (!buf)
+ goto err;
+
name.name = buf;
name.len = outarg.namelen;
err = fuse_copy_one(cs, buf, outarg.namelen + 1);
@@ -1673,20 +1788,23 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
num = outarg.size;
while (num) {
struct folio *folio;
- struct page *page;
- unsigned int this_num;
+ 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;
- page = &folio->page;
- this_num = min_t(unsigned, num, folio_size(folio) - offset);
- err = fuse_copy_page(cs, &page, offset, this_num, 0);
+ 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 &&
- (this_num == folio_size(folio) || file_size == end)) {
- folio_zero_segment(folio, this_num, folio_size(folio));
+ (nr_bytes == folio_size(folio) || file_size == end)) {
+ folio_zero_segment(folio, nr_bytes, folio_size(folio));
folio_mark_uptodate(folio);
}
folio_unlock(folio);
@@ -1695,9 +1813,9 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
if (err)
goto out_iput;
- num -= this_num;
+ num -= nr_bytes;
offset = 0;
- index++;
+ index += nr_pages;
}
err = 0;
@@ -1736,7 +1854,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
unsigned int num;
unsigned int offset;
size_t total_len = 0;
- unsigned int num_pages, cur_pages = 0;
+ unsigned int num_pages;
struct fuse_conn *fc = fm->fc;
struct fuse_retrieve_args *ra;
size_t args_size = sizeof(*ra);
@@ -1754,6 +1872,7 @@ static int fuse_retrieve(struct fuse_mount *fm, 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->folios[0]) + sizeof(ap->descs[0]));
@@ -1774,25 +1893,29 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
index = outarg->offset >> PAGE_SHIFT;
- while (num && cur_pages < num_pages) {
+ while (num) {
struct folio *folio;
- unsigned int this_num;
+ unsigned int folio_offset;
+ unsigned int nr_bytes;
+ unsigned int nr_pages;
folio = filemap_get_folio(mapping, index);
if (IS_ERR(folio))
break;
- this_num = min_t(unsigned, num, PAGE_SIZE - offset);
+ 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 = offset;
- ap->descs[ap->num_folios].length = this_num;
+ ap->descs[ap->num_folios].offset = folio_offset;
+ ap->descs[ap->num_folios].length = nr_bytes;
ap->num_folios++;
- cur_pages++;
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;
@@ -1908,11 +2031,24 @@ static int fuse_notify_resend(struct fuse_conn *fc)
return 0;
}
+/*
+ * Increments the fuse connection epoch. This will result of dentries from
+ * previous epochs to be invalidated.
+ *
+ * XXX optimization: add call to shrink_dcache_sb()?
+ */
+static int fuse_notify_inc_epoch(struct fuse_conn *fc)
+{
+ atomic_inc(&fc->epoch);
+
+ 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:
@@ -1936,6 +2072,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
case FUSE_NOTIFY_RESEND:
return fuse_notify_resend(fc);
+ case FUSE_NOTIFY_INC_EPOCH:
+ return fuse_notify_inc_epoch(fc);
+
default:
fuse_copy_finish(cs);
return -EINVAL;
@@ -2060,7 +2199,7 @@ 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;
@@ -2098,7 +2237,7 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *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));
}
@@ -2172,13 +2311,13 @@ 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);
@@ -2275,6 +2414,9 @@ 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;
@@ -2486,6 +2628,17 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
}
}
+#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,
@@ -2501,6 +2654,9 @@ const struct file_operations fuse_dev_operations = {
#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);
diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
index 82bf458fa9db..249b210becb1 100644
--- a/fs/fuse/dev_uring.c
+++ b/fs/fuse/dev_uring.c
@@ -140,6 +140,49 @@ void fuse_uring_abort_end_requests(struct fuse_ring *ring)
}
}
+static bool ent_list_request_expired(struct fuse_conn *fc, struct list_head *list)
+{
+ struct fuse_ring_ent *ent;
+ struct fuse_req *req;
+
+ ent = list_first_entry_or_null(list, struct fuse_ring_ent, list);
+ if (!ent)
+ return false;
+
+ req = ent->fuse_req;
+
+ return time_is_before_jiffies(req->create_time +
+ fc->timeout.req_timeout);
+}
+
+bool fuse_uring_request_expired(struct fuse_conn *fc)
+{
+ struct fuse_ring *ring = fc->ring;
+ struct fuse_ring_queue *queue;
+ int qid;
+
+ if (!ring)
+ return false;
+
+ for (qid = 0; qid < ring->nr_queues; qid++) {
+ queue = READ_ONCE(ring->queues[qid]);
+ if (!queue)
+ continue;
+
+ spin_lock(&queue->lock);
+ if (fuse_request_expired(fc, &queue->fuse_req_queue) ||
+ fuse_request_expired(fc, &queue->fuse_req_bg_queue) ||
+ ent_list_request_expired(fc, &queue->ent_w_req_queue) ||
+ ent_list_request_expired(fc, &queue->ent_in_userspace)) {
+ spin_unlock(&queue->lock);
+ return true;
+ }
+ spin_unlock(&queue->lock);
+ }
+
+ return false;
+}
+
void fuse_uring_destruct(struct fuse_conn *fc)
{
struct fuse_ring *ring = fc->ring;
@@ -211,7 +254,6 @@ static struct fuse_ring *fuse_uring_create(struct fuse_conn *fc)
ring->nr_queues = nr_queues;
ring->fc = fc;
ring->max_payload_sz = max_payload_size;
- atomic_set(&ring->queue_refs, 0);
smp_store_release(&fc->ring, ring);
spin_unlock(&fc->lock);
@@ -468,7 +510,7 @@ static void fuse_uring_cancel(struct io_uring_cmd *cmd,
spin_lock(&queue->lock);
if (ent->state == FRRS_AVAILABLE) {
ent->state = FRRS_USERSPACE;
- list_move(&ent->list, &queue->ent_in_userspace);
+ list_move_tail(&ent->list, &queue->ent_in_userspace);
need_cmd_done = true;
ent->cmd = NULL;
}
@@ -551,8 +593,8 @@ static int fuse_uring_copy_from_ring(struct fuse_ring *ring,
if (err)
return err;
- fuse_copy_init(&cs, 0, &iter);
- cs.is_uring = 1;
+ fuse_copy_init(&cs, false, &iter);
+ cs.is_uring = true;
cs.req = req;
return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz);
@@ -581,8 +623,8 @@ static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req,
return err;
}
- fuse_copy_init(&cs, 1, &iter);
- cs.is_uring = 1;
+ fuse_copy_init(&cs, true, &iter);
+ cs.is_uring = true;
cs.req = req;
if (num_args > 0) {
@@ -688,7 +730,7 @@ static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ent,
cmd = ent->cmd;
ent->cmd = NULL;
ent->state = FRRS_USERSPACE;
- list_move(&ent->list, &queue->ent_in_userspace);
+ list_move_tail(&ent->list, &queue->ent_in_userspace);
spin_unlock(&queue->lock);
io_uring_cmd_done(cmd, 0, 0, issue_flags);
@@ -726,8 +768,6 @@ static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent,
struct fuse_req *req)
{
struct fuse_ring_queue *queue = ent->queue;
- struct fuse_conn *fc = req->fm->fc;
- struct fuse_iqueue *fiq = &fc->iq;
lockdep_assert_held(&queue->lock);
@@ -737,12 +777,10 @@ static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent,
ent->state);
}
- spin_lock(&fiq->lock);
clear_bit(FR_PENDING, &req->flags);
- spin_unlock(&fiq->lock);
ent->fuse_req = req;
ent->state = FRRS_FUSE_REQ;
- list_move(&ent->list, &queue->ent_w_req_queue);
+ list_move_tail(&ent->list, &queue->ent_w_req_queue);
fuse_uring_add_to_pq(ent, req);
}
@@ -1158,7 +1196,7 @@ static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd,
spin_lock(&queue->lock);
ent->state = FRRS_USERSPACE;
- list_move(&ent->list, &queue->ent_in_userspace);
+ list_move_tail(&ent->list, &queue->ent_in_userspace);
ent->cmd = NULL;
spin_unlock(&queue->lock);
@@ -1238,6 +1276,8 @@ void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req)
if (unlikely(queue->stopped))
goto err_unlock;
+ set_bit(FR_URING, &req->flags);
+ req->ring_queue = queue;
ent = list_first_entry_or_null(&queue->ent_avail_queue,
struct fuse_ring_ent, list);
if (ent)
@@ -1276,6 +1316,8 @@ bool fuse_uring_queue_bq_req(struct fuse_req *req)
return false;
}
+ set_bit(FR_URING, &req->flags);
+ req->ring_queue = queue;
list_add_tail(&req->list, &queue->fuse_req_bg_queue);
ent = list_first_entry_or_null(&queue->ent_avail_queue,
@@ -1306,6 +1348,13 @@ bool fuse_uring_queue_bq_req(struct fuse_req *req)
return true;
}
+bool fuse_uring_remove_pending_req(struct fuse_req *req)
+{
+ struct fuse_ring_queue *queue = req->ring_queue;
+
+ return fuse_remove_pending_req(req, &queue->lock);
+}
+
static const struct fuse_iqueue_ops fuse_io_uring_ops = {
/* should be send over io-uring as enhancement */
.send_forget = fuse_dev_queue_forget,
diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h
index 2102b3d0c1ae..51a563922ce1 100644
--- a/fs/fuse/dev_uring_i.h
+++ b/fs/fuse/dev_uring_i.h
@@ -142,6 +142,8 @@ void fuse_uring_abort_end_requests(struct fuse_ring *ring);
int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags);
void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req);
bool fuse_uring_queue_bq_req(struct fuse_req *req);
+bool fuse_uring_remove_pending_req(struct fuse_req *req);
+bool fuse_uring_request_expired(struct fuse_conn *fc);
static inline void fuse_uring_abort(struct fuse_conn *fc)
{
@@ -172,12 +174,6 @@ static inline bool fuse_uring_ready(struct fuse_conn *fc)
#else /* CONFIG_FUSE_IO_URING */
-struct fuse_ring;
-
-static inline void fuse_uring_create(struct fuse_conn *fc)
-{
-}
-
static inline void fuse_uring_destruct(struct fuse_conn *fc)
{
}
@@ -200,6 +196,16 @@ static inline bool fuse_uring_ready(struct fuse_conn *fc)
return false;
}
+static inline bool fuse_uring_remove_pending_req(struct fuse_req *req)
+{
+ return false;
+}
+
+static inline bool fuse_uring_request_expired(struct fuse_conn *fc)
+{
+ return false;
+}
+
#endif /* CONFIG_FUSE_IO_URING */
#endif /* _FS_FUSE_DEV_URING_I_H */
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 85e4f894a59f..2d817d7cab26 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -200,9 +200,14 @@ static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
{
struct inode *inode;
struct fuse_mount *fm;
+ struct fuse_conn *fc;
struct fuse_inode *fi;
int ret;
+ fc = get_fuse_conn_super(dir->i_sb);
+ if (entry->d_time < atomic_read(&fc->epoch))
+ goto invalid;
+
inode = d_inode_rcu(entry);
if (inode && fuse_is_bad(inode))
goto invalid;
@@ -319,9 +324,6 @@ static struct vfsmount *fuse_dentry_automount(struct path *path)
/* Create the submount */
mnt = fc_mount(fsc);
- if (!IS_ERR(mnt))
- mntget(mnt);
-
put_fs_context(fsc);
return mnt;
}
@@ -336,13 +338,6 @@ const struct dentry_operations fuse_dentry_operations = {
.d_automount = fuse_dentry_automount,
};
-const struct dentry_operations fuse_root_dentry_operations = {
-#if BITS_PER_LONG < 64
- .d_init = fuse_dentry_init,
- .d_release = fuse_dentry_release,
-#endif
-};
-
int fuse_valid_type(int m)
{
return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) ||
@@ -370,7 +365,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
*inode = NULL;
err = -ENAMETOOLONG;
- if (name->len > FUSE_NAME_MAX)
+ if (name->len > fm->fc->name_max)
goto out;
@@ -415,16 +410,20 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name
static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
unsigned int flags)
{
- int err;
struct fuse_entry_out outarg;
+ struct fuse_conn *fc;
struct inode *inode;
struct dentry *newent;
+ int err, epoch;
bool outarg_valid = true;
bool locked;
if (fuse_is_bad(dir))
return ERR_PTR(-EIO);
+ fc = get_fuse_conn_super(dir->i_sb);
+ epoch = atomic_read(&fc->epoch);
+
locked = fuse_lock_inode(dir);
err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
&outarg, &inode);
@@ -446,6 +445,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
goto out_err;
entry = newent ? newent : entry;
+ entry->d_time = epoch;
if (outarg_valid)
fuse_change_entry_timeout(entry, &outarg);
else
@@ -619,7 +619,6 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *entry, struct file *file,
unsigned int flags, umode_t mode, u32 opcode)
{
- int err;
struct inode *inode;
struct fuse_mount *fm = get_fuse_mount(dir);
FUSE_ARGS(args);
@@ -629,11 +628,13 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
struct fuse_entry_out outentry;
struct fuse_inode *fi;
struct fuse_file *ff;
+ int epoch, err;
bool trunc = flags & O_TRUNC;
/* Userspace expects S_IFREG in create mode */
BUG_ON((mode & S_IFMT) != S_IFREG);
+ epoch = atomic_read(&fm->fc->epoch);
forget = fuse_alloc_forget();
err = -ENOMEM;
if (!forget)
@@ -702,6 +703,7 @@ static int fuse_create_open(struct mnt_idmap *idmap, struct inode *dir,
}
kfree(forget);
d_instantiate(entry, inode);
+ entry->d_time = epoch;
fuse_change_entry_timeout(entry, &outentry);
fuse_dir_changed(dir);
err = generic_file_open(inode, file);
@@ -788,12 +790,14 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun
struct fuse_entry_out outarg;
struct inode *inode;
struct dentry *d;
- int err;
struct fuse_forget_link *forget;
+ int epoch, err;
if (fuse_is_bad(dir))
return ERR_PTR(-EIO);
+ epoch = atomic_read(&fm->fc->epoch);
+
forget = fuse_alloc_forget();
if (!forget)
return ERR_PTR(-ENOMEM);
@@ -835,10 +839,13 @@ static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_moun
if (IS_ERR(d))
return d;
- if (d)
+ if (d) {
+ d->d_time = epoch;
fuse_change_entry_timeout(d, &outarg);
- else
+ } else {
+ entry->d_time = epoch;
fuse_change_entry_timeout(entry, &outarg);
+ }
fuse_dir_changed(dir);
return d;
@@ -1137,6 +1144,9 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
struct fuse_mount *fm = get_fuse_mount(inode);
FUSE_ARGS(args);
+ if (fm->fc->no_link)
+ goto out;
+
memset(&inarg, 0, sizeof(inarg));
inarg.oldnodeid = get_node_id(inode);
args.opcode = FUSE_LINK;
@@ -1151,6 +1161,12 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
else if (err == -EINTR)
fuse_invalidate_attr(inode);
+ if (err == -ENOSYS)
+ fm->fc->no_link = 1;
+out:
+ if (fm->fc->no_link)
+ return -EPERM;
+
return err;
}
@@ -1603,10 +1619,10 @@ static int fuse_permission(struct mnt_idmap *idmap,
return err;
}
-static int fuse_readlink_page(struct inode *inode, struct folio *folio)
+static int fuse_readlink_folio(struct inode *inode, struct folio *folio)
{
struct fuse_mount *fm = get_fuse_mount(inode);
- struct fuse_folio_desc desc = { .length = PAGE_SIZE - 1 };
+ struct fuse_folio_desc desc = { .length = folio_size(folio) - 1 };
struct fuse_args_pages ap = {
.num_folios = 1,
.folios = &folio,
@@ -1661,13 +1677,13 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
if (!folio)
goto out_err;
- err = fuse_readlink_page(inode, folio);
+ err = fuse_readlink_folio(inode, folio);
if (err) {
folio_put(folio);
goto out_err;
}
- set_delayed_call(callback, page_put_link, &folio->page);
+ set_delayed_call(callback, page_put_link, folio);
return folio_address(folio);
@@ -1937,6 +1953,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
int err;
bool trust_local_cmtime = is_wb;
bool fault_blocked = false;
+ u64 attr_version;
if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
@@ -2021,6 +2038,8 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (fc->handle_killpriv_v2 && !capable(CAP_FSETID))
inarg.valid |= FATTR_KILL_SUIDGID;
}
+
+ attr_version = fuse_get_attr_version(fm->fc);
fuse_setattr_fill(fc, &args, inode, &inarg, &outarg);
err = fuse_simple_request(fm, &args);
if (err) {
@@ -2046,6 +2065,14 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
/* FIXME: clear I_DIRTY_SYNC? */
}
+ if (fi->attr_version > attr_version) {
+ /*
+ * Apply attributes, for example for fsnotify_change(), but set
+ * attribute timeout to zero.
+ */
+ outarg.attr_valid = outarg.attr_valid_nsec = 0;
+ }
+
fuse_change_attributes_common(inode, &outarg.attr, NULL,
ATTR_TIMEOUT(&outarg),
fuse_get_cache_mask(inode), 0);
@@ -2251,7 +2278,7 @@ void fuse_init_dir(struct inode *inode)
static int fuse_symlink_read_folio(struct file *null, struct folio *folio)
{
- int err = fuse_readlink_page(folio->mapping->host, folio);
+ int err = fuse_readlink_folio(folio->mapping->host, folio);
if (!err)
folio_mark_uptodate(folio);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 754378dd9f71..5525a4520b0f 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -21,6 +21,7 @@
#include <linux/filelock.h>
#include <linux/splice.h>
#include <linux/task_io_accounting_ops.h>
+#include <linux/iomap.h>
static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
unsigned int open_flags, int opcode,
@@ -415,89 +416,11 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
struct fuse_writepage_args {
struct fuse_io_args ia;
- struct rb_node writepages_entry;
struct list_head queue_entry;
- struct fuse_writepage_args *next;
struct inode *inode;
struct fuse_sync_bucket *bucket;
};
-static struct fuse_writepage_args *fuse_find_writeback(struct fuse_inode *fi,
- pgoff_t idx_from, pgoff_t idx_to)
-{
- struct rb_node *n;
-
- n = fi->writepages.rb_node;
-
- while (n) {
- struct fuse_writepage_args *wpa;
- pgoff_t curr_index;
-
- wpa = rb_entry(n, struct fuse_writepage_args, writepages_entry);
- WARN_ON(get_fuse_inode(wpa->inode) != fi);
- curr_index = wpa->ia.write.in.offset >> PAGE_SHIFT;
- if (idx_from >= curr_index + wpa->ia.ap.num_folios)
- n = n->rb_right;
- else if (idx_to < curr_index)
- n = n->rb_left;
- else
- return wpa;
- }
- return NULL;
-}
-
-/*
- * Check if any page in a range is under writeback
- */
-static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
- pgoff_t idx_to)
-{
- struct fuse_inode *fi = get_fuse_inode(inode);
- bool found;
-
- if (RB_EMPTY_ROOT(&fi->writepages))
- return false;
-
- spin_lock(&fi->lock);
- found = fuse_find_writeback(fi, idx_from, idx_to);
- spin_unlock(&fi->lock);
-
- return found;
-}
-
-static inline bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
-{
- return fuse_range_is_writeback(inode, index, index);
-}
-
-/*
- * Wait for page writeback to be completed.
- *
- * Since fuse doesn't rely on the VM writeback tracking, this has to
- * use some other means.
- */
-static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
-{
- struct fuse_inode *fi = get_fuse_inode(inode);
-
- wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index));
-}
-
-static inline bool fuse_folio_is_writeback(struct inode *inode,
- struct folio *folio)
-{
- pgoff_t last = folio_next_index(folio) - 1;
- return fuse_range_is_writeback(inode, folio_index(folio), last);
-}
-
-static void fuse_wait_on_folio_writeback(struct inode *inode,
- struct folio *folio)
-{
- struct fuse_inode *fi = get_fuse_inode(inode);
-
- wait_event(fi->page_waitq, !fuse_folio_is_writeback(inode, folio));
-}
-
/*
* Wait for all pending writepages on the inode to finish.
*
@@ -532,10 +455,6 @@ static int fuse_flush(struct file *file, fl_owner_t id)
if (err)
return err;
- inode_lock(inode);
- fuse_sync_writes(inode);
- inode_unlock(inode);
-
err = filemap_check_errors(file->f_mapping);
if (err)
return err;
@@ -870,12 +789,16 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
}
}
-static int fuse_do_readfolio(struct file *file, struct folio *folio)
+static int fuse_do_readfolio(struct file *file, struct folio *folio,
+ size_t off, size_t len)
{
struct inode *inode = folio->mapping->host;
struct fuse_mount *fm = get_fuse_mount(inode);
- loff_t pos = folio_pos(folio);
- struct fuse_folio_desc desc = { .length = PAGE_SIZE };
+ loff_t pos = folio_pos(folio) + off;
+ struct fuse_folio_desc desc = {
+ .offset = off,
+ .length = len,
+ };
struct fuse_io_args ia = {
.ap.args.page_zeroing = true,
.ap.args.out_pages = true,
@@ -886,13 +809,6 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
ssize_t res;
u64 attr_ver;
- /*
- * With the temporary pages that are used to complete writeback, we can
- * have writeback that extends beyond the lifetime of the folio. So
- * make sure we read a properly synced folio.
- */
- fuse_wait_on_folio_writeback(inode, folio);
-
attr_ver = fuse_get_attr_version(fm->fc);
/* Don't overflow end offset */
@@ -909,8 +825,6 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
if (res < desc.length)
fuse_short_read(inode, attr_ver, res, &ia.ap);
- folio_mark_uptodate(folio);
-
return 0;
}
@@ -923,13 +837,26 @@ static int fuse_read_folio(struct file *file, struct folio *folio)
if (fuse_is_bad(inode))
goto out;
- err = fuse_do_readfolio(file, folio);
+ err = fuse_do_readfolio(file, folio, 0, folio_size(folio));
+ if (!err)
+ folio_mark_uptodate(folio);
+
fuse_invalidate_atime(inode);
out:
folio_unlock(folio);
return err;
}
+static int fuse_iomap_read_folio_range(const struct iomap_iter *iter,
+ struct folio *folio, loff_t pos,
+ size_t len)
+{
+ struct file *file = iter->private;
+ size_t off = offset_in_folio(folio, pos);
+
+ return fuse_do_readfolio(file, folio, off, len);
+}
+
static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
int err)
{
@@ -965,14 +892,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
fuse_io_free(ia);
}
-static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
+static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
+ unsigned int count)
{
struct fuse_file *ff = file->private_data;
struct fuse_mount *fm = ff->fm;
struct fuse_args_pages *ap = &ia->ap;
loff_t pos = folio_pos(ap->folios[0]);
- /* Currently, all folios in FUSE are one page */
- size_t count = ap->num_folios << PAGE_SHIFT;
ssize_t res;
int err;
@@ -1005,17 +931,13 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
static void fuse_readahead(struct readahead_control *rac)
{
struct inode *inode = rac->mapping->host;
- struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = get_fuse_conn(inode);
unsigned int max_pages, nr_pages;
- pgoff_t first = readahead_index(rac);
- pgoff_t last = first + readahead_count(rac) - 1;
+ struct folio *folio = NULL;
if (fuse_is_bad(inode))
return;
- wait_event(fi->page_waitq, !fuse_range_is_writeback(inode, first, last));
-
max_pages = min_t(unsigned int, fc->max_pages,
fc->max_read / PAGE_SIZE);
@@ -1033,8 +955,8 @@ static void fuse_readahead(struct readahead_control *rac)
while (nr_pages) {
struct fuse_io_args *ia;
struct fuse_args_pages *ap;
- struct folio *folio;
unsigned cur_pages = min(max_pages, nr_pages);
+ unsigned int pages = 0;
if (fc->num_background >= fc->congestion_threshold &&
rac->ra->async_size >= readahead_count(rac))
@@ -1046,10 +968,12 @@ static void fuse_readahead(struct readahead_control *rac)
ia = fuse_io_alloc(NULL, cur_pages);
if (!ia)
- return;
+ break;
ap = &ia->ap;
- while (ap->num_folios < cur_pages) {
+ while (pages < cur_pages) {
+ unsigned int folio_pages;
+
/*
* This returns a folio with a ref held on it.
* The ref needs to be held until the request is
@@ -1057,13 +981,31 @@ static void fuse_readahead(struct readahead_control *rac)
* fuse_try_move_page()) drops the ref after it's
* replaced in the page cache.
*/
- folio = __readahead_folio(rac);
+ if (!folio)
+ folio = __readahead_folio(rac);
+
+ folio_pages = folio_nr_pages(folio);
+ if (folio_pages > cur_pages - pages) {
+ /*
+ * Large folios belonging to fuse will never
+ * have more pages than max_pages.
+ */
+ WARN_ON(!pages);
+ break;
+ }
+
ap->folios[ap->num_folios] = folio;
ap->descs[ap->num_folios].length = folio_size(folio);
ap->num_folios++;
+ pages += folio_pages;
+ folio = NULL;
}
- fuse_send_readpages(ia, rac->file);
- nr_pages -= cur_pages;
+ fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
+ nr_pages -= pages;
+ }
+ if (folio) {
+ folio_end_read(folio, false);
+ folio_put(folio);
}
}
@@ -1181,7 +1123,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
int err;
for (i = 0; i < ap->num_folios; i++)
- fuse_wait_on_folio_writeback(inode, ap->folios[i]);
+ folio_wait_writeback(ap->folios[i]);
fuse_write_args_fill(ia, ff, pos, count);
ia->write.in.flags = fuse_write_flags(iocb);
@@ -1221,32 +1163,28 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
struct address_space *mapping,
struct iov_iter *ii, loff_t pos,
- unsigned int max_pages)
+ unsigned int max_folios)
{
struct fuse_args_pages *ap = &ia->ap;
struct fuse_conn *fc = get_fuse_conn(mapping->host);
unsigned offset = pos & (PAGE_SIZE - 1);
- unsigned int nr_pages = 0;
size_t count = 0;
- int err;
+ unsigned int num;
+ int err = 0;
+
+ num = min(iov_iter_count(ii), fc->max_write);
ap->args.in_pages = true;
ap->descs[0].offset = offset;
- do {
+ while (num && ap->num_folios < max_folios) {
size_t tmp;
struct folio *folio;
pgoff_t index = pos >> PAGE_SHIFT;
- size_t bytes = min_t(size_t, PAGE_SIZE - offset,
- iov_iter_count(ii));
-
- bytes = min_t(size_t, bytes, fc->max_write - count);
+ unsigned int bytes;
+ unsigned int folio_offset;
again:
- err = -EFAULT;
- if (fault_in_iov_iter_readable(ii, bytes))
- break;
-
folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping));
if (IS_ERR(folio)) {
@@ -1257,29 +1195,42 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
if (mapping_writably_mapped(mapping))
flush_dcache_folio(folio);
- tmp = copy_folio_from_iter_atomic(folio, offset, bytes, ii);
+ folio_offset = ((index - folio->index) << PAGE_SHIFT) + offset;
+ bytes = min(folio_size(folio) - folio_offset, num);
+
+ tmp = copy_folio_from_iter_atomic(folio, folio_offset, bytes, ii);
flush_dcache_folio(folio);
if (!tmp) {
folio_unlock(folio);
folio_put(folio);
+
+ /*
+ * Ensure forward progress by faulting in
+ * while not holding the folio lock:
+ */
+ if (fault_in_iov_iter_readable(ii, bytes)) {
+ err = -EFAULT;
+ break;
+ }
+
goto again;
}
- err = 0;
ap->folios[ap->num_folios] = folio;
+ ap->descs[ap->num_folios].offset = folio_offset;
ap->descs[ap->num_folios].length = tmp;
ap->num_folios++;
- nr_pages++;
count += tmp;
pos += tmp;
+ num -= tmp;
offset += tmp;
- if (offset == PAGE_SIZE)
+ if (offset == folio_size(folio))
offset = 0;
- /* If we copied full page, mark it uptodate */
- if (tmp == PAGE_SIZE)
+ /* If we copied full folio, mark it uptodate */
+ if (tmp == folio_size(folio))
folio_mark_uptodate(folio);
if (folio_test_uptodate(folio)) {
@@ -1288,10 +1239,9 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
ia->write.folio_locked = true;
break;
}
- if (!fc->big_writes)
+ if (!fc->big_writes || offset != 0)
break;
- } while (iov_iter_count(ii) && count < fc->max_write &&
- nr_pages < max_pages && offset == 0);
+ }
return count > 0 ? count : err;
}
@@ -1440,6 +1390,24 @@ static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive)
}
}
+static const struct iomap_write_ops fuse_iomap_write_ops = {
+ .read_folio_range = fuse_iomap_read_folio_range,
+};
+
+static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned int flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ iomap->type = IOMAP_MAPPED;
+ iomap->length = length;
+ iomap->offset = offset;
+ return 0;
+}
+
+static const struct iomap_ops fuse_iomap_ops = {
+ .iomap_begin = fuse_iomap_begin,
+};
+
static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
@@ -1449,6 +1417,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct inode *inode = mapping->host;
ssize_t err, count;
struct fuse_conn *fc = get_fuse_conn(inode);
+ bool writeback = false;
if (fc->writeback_cache) {
/* Update size (EOF optimization) and mode (SUID clearing) */
@@ -1457,16 +1426,11 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (err)
return err;
- if (fc->handle_killpriv_v2 &&
- setattr_should_drop_suidgid(idmap,
- file_inode(file))) {
- goto writethrough;
- }
-
- return generic_file_write_iter(iocb, from);
+ if (!fc->handle_killpriv_v2 ||
+ !setattr_should_drop_suidgid(idmap, file_inode(file)))
+ writeback = true;
}
-writethrough:
inode_lock(inode);
err = count = generic_write_checks(iocb, from);
@@ -1485,6 +1449,15 @@ writethrough:
goto out;
written = direct_write_fallback(iocb, from, written,
fuse_perform_write(iocb, from));
+ } else if (writeback) {
+ /*
+ * Use iomap so that we can do granular uptodate reads
+ * and granular dirty tracking for large folios.
+ */
+ written = iomap_file_buffered_write(iocb, from,
+ &fuse_iomap_ops,
+ &fuse_iomap_write_ops,
+ file);
} else {
written = fuse_perform_write(iocb, from);
}
@@ -1638,7 +1611,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
return res;
}
}
- if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) {
+ if (!cuse && filemap_range_has_writeback(mapping, pos, (pos + count - 1))) {
if (!write)
inode_lock(inode);
fuse_sync_writes(inode);
@@ -1835,38 +1808,34 @@ static ssize_t fuse_splice_write(struct pipe_inode_info *pipe, struct file *out,
static void fuse_writepage_free(struct fuse_writepage_args *wpa)
{
struct fuse_args_pages *ap = &wpa->ia.ap;
- int i;
if (wpa->bucket)
fuse_sync_bucket_dec(wpa->bucket);
- for (i = 0; i < ap->num_folios; i++)
- folio_put(ap->folios[i]);
-
fuse_file_put(wpa->ia.ff, false);
kfree(ap->folios);
kfree(wpa);
}
-static void fuse_writepage_finish_stat(struct inode *inode, struct folio *folio)
-{
- struct backing_dev_info *bdi = inode_to_bdi(inode);
-
- dec_wb_stat(&bdi->wb, WB_WRITEBACK);
- node_stat_sub_folio(folio, NR_WRITEBACK_TEMP);
- wb_writeout_inc(&bdi->wb);
-}
-
static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
{
struct fuse_args_pages *ap = &wpa->ia.ap;
struct inode *inode = wpa->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
int i;
- for (i = 0; i < ap->num_folios; i++)
- fuse_writepage_finish_stat(inode, ap->folios[i]);
+ for (i = 0; i < ap->num_folios; i++) {
+ /*
+ * Benchmarks showed that ending writeback within the
+ * scope of the fi->lock alleviates xarray lock
+ * contention and noticeably improves performance.
+ */
+ iomap_finish_folio_write(inode, ap->folios[i], 1);
+ dec_wb_stat(&bdi->wb, WB_WRITEBACK);
+ wb_writeout_inc(&bdi->wb);
+ }
wake_up(&fi->page_waitq);
}
@@ -1877,13 +1846,15 @@ static void fuse_send_writepage(struct fuse_mount *fm,
__releases(fi->lock)
__acquires(fi->lock)
{
- struct fuse_writepage_args *aux, *next;
struct fuse_inode *fi = get_fuse_inode(wpa->inode);
+ struct fuse_args_pages *ap = &wpa->ia.ap;
struct fuse_write_in *inarg = &wpa->ia.write.in;
- struct fuse_args *args = &wpa->ia.ap.args;
- /* Currently, all folios in FUSE are one page */
- __u64 data_size = wpa->ia.ap.num_folios * PAGE_SIZE;
- int err;
+ struct fuse_args *args = &ap->args;
+ __u64 data_size = 0;
+ int err, i;
+
+ for (i = 0; i < ap->num_folios; i++)
+ data_size += ap->descs[i].length;
fi->writectr++;
if (inarg->offset + data_size <= size) {
@@ -1914,19 +1885,8 @@ __acquires(fi->lock)
out_free:
fi->writectr--;
- rb_erase(&wpa->writepages_entry, &fi->writepages);
fuse_writepage_finish(wpa);
spin_unlock(&fi->lock);
-
- /* After rb_erase() aux request list is private */
- for (aux = wpa->next; aux; aux = next) {
- next = aux->next;
- aux->next = NULL;
- fuse_writepage_finish_stat(aux->inode,
- aux->ia.ap.folios[0]);
- fuse_writepage_free(aux);
- }
-
fuse_writepage_free(wpa);
spin_lock(&fi->lock);
}
@@ -1954,43 +1914,6 @@ __acquires(fi->lock)
}
}
-static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
- struct fuse_writepage_args *wpa)
-{
- pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
- pgoff_t idx_to = idx_from + wpa->ia.ap.num_folios - 1;
- struct rb_node **p = &root->rb_node;
- struct rb_node *parent = NULL;
-
- WARN_ON(!wpa->ia.ap.num_folios);
- while (*p) {
- struct fuse_writepage_args *curr;
- pgoff_t curr_index;
-
- parent = *p;
- curr = rb_entry(parent, struct fuse_writepage_args,
- writepages_entry);
- WARN_ON(curr->inode != wpa->inode);
- curr_index = curr->ia.write.in.offset >> PAGE_SHIFT;
-
- if (idx_from >= curr_index + curr->ia.ap.num_folios)
- p = &(*p)->rb_right;
- else if (idx_to < curr_index)
- p = &(*p)->rb_left;
- else
- return curr;
- }
-
- rb_link_node(&wpa->writepages_entry, parent, p);
- rb_insert_color(&wpa->writepages_entry, root);
- return NULL;
-}
-
-static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
-{
- WARN_ON(fuse_insert_writeback(root, wpa));
-}
-
static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
int error)
{
@@ -2010,41 +1933,6 @@ static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
if (!fc->writeback_cache)
fuse_invalidate_attr_mask(inode, FUSE_STATX_MODIFY);
spin_lock(&fi->lock);
- rb_erase(&wpa->writepages_entry, &fi->writepages);
- while (wpa->next) {
- struct fuse_mount *fm = get_fuse_mount(inode);
- struct fuse_write_in *inarg = &wpa->ia.write.in;
- struct fuse_writepage_args *next = wpa->next;
-
- wpa->next = next->next;
- next->next = NULL;
- tree_insert(&fi->writepages, next);
-
- /*
- * Skip fuse_flush_writepages() to make it easy to crop requests
- * based on primary request size.
- *
- * 1st case (trivial): there are no concurrent activities using
- * fuse_set/release_nowrite. Then we're on safe side because
- * fuse_flush_writepages() would call fuse_send_writepage()
- * anyway.
- *
- * 2nd case: someone called fuse_set_nowrite and it is waiting
- * now for completion of all in-flight requests. This happens
- * rarely and no more than once per page, so this should be
- * okay.
- *
- * 3rd case: someone (e.g. fuse_do_setattr()) is in the middle
- * of fuse_set_nowrite..fuse_release_nowrite section. The fact
- * that fuse_set_nowrite returned implies that all in-flight
- * requests were completed along with all of their secondary
- * requests. Further primary requests are blocked by negative
- * writectr. Hence there cannot be any in-flight requests and
- * no invocations of fuse_writepage_end() while we're in
- * fuse_set_nowrite..fuse_release_nowrite section.
- */
- fuse_send_writepage(fm, next, inarg->offset + inarg->size);
- }
fi->writectr--;
fuse_writepage_finish(wpa);
spin_unlock(&fi->lock);
@@ -2078,17 +1966,6 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
struct fuse_file *ff;
int err;
- /*
- * Inode is always written before the last reference is dropped and
- * hence this should not be reached from reclaim.
- *
- * Writing back the inode from reclaim can deadlock if the request
- * processing itself needs an allocation. Allocations triggering
- * reclaim while serving a request can't be prevented, because it can
- * involve any number of unrelated userspace processes.
- */
- WARN_ON(wbc->for_reclaim);
-
ff = __fuse_write_file_get(fi);
err = fuse_flush_times(inode, ff);
if (ff)
@@ -2131,22 +2008,20 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
}
static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio,
- struct folio *tmp_folio, uint32_t folio_index)
+ uint32_t folio_index, loff_t offset, unsigned len)
{
struct inode *inode = folio->mapping->host;
struct fuse_args_pages *ap = &wpa->ia.ap;
- folio_copy(tmp_folio, folio);
-
- ap->folios[folio_index] = tmp_folio;
- ap->descs[folio_index].offset = 0;
- ap->descs[folio_index].length = PAGE_SIZE;
+ ap->folios[folio_index] = folio;
+ ap->descs[folio_index].offset = offset;
+ ap->descs[folio_index].length = len;
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
- node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP);
}
static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio,
+ size_t offset,
struct fuse_file *ff)
{
struct inode *inode = folio->mapping->host;
@@ -2159,7 +2034,7 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
return NULL;
fuse_writepage_add_to_bucket(fc, wpa);
- fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio), 0);
+ fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio) + offset, 0);
wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
wpa->inode = inode;
wpa->ia.ff = ff;
@@ -2171,74 +2046,28 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
return wpa;
}
-static int fuse_writepage_locked(struct folio *folio)
-{
- struct address_space *mapping = folio->mapping;
- struct inode *inode = mapping->host;
- struct fuse_inode *fi = get_fuse_inode(inode);
- struct fuse_writepage_args *wpa;
- struct fuse_args_pages *ap;
- struct folio *tmp_folio;
- struct fuse_file *ff;
- int error = -ENOMEM;
-
- tmp_folio = folio_alloc(GFP_NOFS | __GFP_HIGHMEM, 0);
- if (!tmp_folio)
- goto err;
-
- error = -EIO;
- ff = fuse_write_file_get(fi);
- if (!ff)
- goto err_nofile;
-
- wpa = fuse_writepage_args_setup(folio, ff);
- error = -ENOMEM;
- if (!wpa)
- goto err_writepage_args;
-
- ap = &wpa->ia.ap;
- ap->num_folios = 1;
-
- folio_start_writeback(folio);
- fuse_writepage_args_page_fill(wpa, folio, tmp_folio, 0);
-
- spin_lock(&fi->lock);
- tree_insert(&fi->writepages, wpa);
- list_add_tail(&wpa->queue_entry, &fi->queued_writes);
- fuse_flush_writepages(inode);
- spin_unlock(&fi->lock);
-
- folio_end_writeback(folio);
-
- return 0;
-
-err_writepage_args:
- fuse_file_put(ff, false);
-err_nofile:
- folio_put(tmp_folio);
-err:
- mapping_set_error(folio->mapping, error);
- return error;
-}
-
struct fuse_fill_wb_data {
struct fuse_writepage_args *wpa;
struct fuse_file *ff;
- struct inode *inode;
- struct folio **orig_folios;
unsigned int max_folios;
+ /*
+ * nr_bytes won't overflow since fuse_writepage_need_send() caps
+ * wb requests to never exceed fc->max_pages (which has an upper bound
+ * of U16_MAX).
+ */
+ unsigned int nr_bytes;
};
-static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
+static bool fuse_pages_realloc(struct fuse_fill_wb_data *data,
+ unsigned int max_pages)
{
struct fuse_args_pages *ap = &data->wpa->ia.ap;
- struct fuse_conn *fc = get_fuse_conn(data->inode);
struct folio **folios;
struct fuse_folio_desc *descs;
unsigned int nfolios = min_t(unsigned int,
max_t(unsigned int, data->max_folios * 2,
FUSE_DEFAULT_MAX_PAGES_PER_REQ),
- fc->max_pages);
+ max_pages);
WARN_ON(nfolios <= data->max_folios);
folios = fuse_folios_alloc(nfolios, GFP_NOFS, &descs);
@@ -2255,319 +2084,162 @@ static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
return true;
}
-static void fuse_writepages_send(struct fuse_fill_wb_data *data)
+static void fuse_writepages_send(struct inode *inode,
+ struct fuse_fill_wb_data *data)
{
struct fuse_writepage_args *wpa = data->wpa;
- struct inode *inode = data->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
- int num_folios = wpa->ia.ap.num_folios;
- int i;
spin_lock(&fi->lock);
list_add_tail(&wpa->queue_entry, &fi->queued_writes);
fuse_flush_writepages(inode);
spin_unlock(&fi->lock);
-
- for (i = 0; i < num_folios; i++)
- folio_end_writeback(data->orig_folios[i]);
}
-/*
- * Check under fi->lock if the page is under writeback, and insert it onto the
- * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's
- * one already added for a page at this offset. If there's none, then insert
- * this new request onto the auxiliary list, otherwise reuse the existing one by
- * swapping the new temp page with the old one.
- */
-static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
- struct folio *folio)
-{
- struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
- struct fuse_writepage_args *tmp;
- struct fuse_writepage_args *old_wpa;
- struct fuse_args_pages *new_ap = &new_wpa->ia.ap;
-
- WARN_ON(new_ap->num_folios != 0);
- new_ap->num_folios = 1;
-
- spin_lock(&fi->lock);
- old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
- if (!old_wpa) {
- spin_unlock(&fi->lock);
- return true;
- }
-
- for (tmp = old_wpa->next; tmp; tmp = tmp->next) {
- pgoff_t curr_index;
-
- WARN_ON(tmp->inode != new_wpa->inode);
- curr_index = tmp->ia.write.in.offset >> PAGE_SHIFT;
- if (curr_index == folio->index) {
- WARN_ON(tmp->ia.ap.num_folios != 1);
- swap(tmp->ia.ap.folios[0], new_ap->folios[0]);
- break;
- }
- }
-
- if (!tmp) {
- new_wpa->next = old_wpa->next;
- old_wpa->next = new_wpa;
- }
-
- spin_unlock(&fi->lock);
-
- if (tmp) {
- fuse_writepage_finish_stat(new_wpa->inode,
- folio);
- fuse_writepage_free(new_wpa);
- }
-
- return false;
-}
-
-static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
- struct fuse_args_pages *ap,
+static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos,
+ unsigned len, struct fuse_args_pages *ap,
struct fuse_fill_wb_data *data)
{
- WARN_ON(!ap->num_folios);
+ struct folio *prev_folio;
+ struct fuse_folio_desc prev_desc;
+ unsigned bytes = data->nr_bytes + len;
+ loff_t prev_pos;
- /*
- * Being under writeback is unlikely but possible. For example direct
- * read to an mmaped fuse file will set the page dirty twice; once when
- * the pages are faulted with get_user_pages(), and then after the read
- * completed.
- */
- if (fuse_folio_is_writeback(data->inode, folio))
- return true;
+ WARN_ON(!ap->num_folios);
/* Reached max pages */
- if (ap->num_folios == fc->max_pages)
+ if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages)
return true;
/* Reached max write bytes */
- if ((ap->num_folios + 1) * PAGE_SIZE > fc->max_write)
+ if (bytes > fc->max_write)
return true;
/* Discontinuity */
- if (data->orig_folios[ap->num_folios - 1]->index + 1 != folio_index(folio))
+ prev_folio = ap->folios[ap->num_folios - 1];
+ prev_desc = ap->descs[ap->num_folios - 1];
+ prev_pos = folio_pos(prev_folio) + prev_desc.offset + prev_desc.length;
+ if (prev_pos != pos)
return true;
/* Need to grow the pages array? If so, did the expansion fail? */
- if (ap->num_folios == data->max_folios && !fuse_pages_realloc(data))
+ if (ap->num_folios == data->max_folios &&
+ !fuse_pages_realloc(data, fc->max_pages))
return true;
return false;
}
-static int fuse_writepages_fill(struct folio *folio,
- struct writeback_control *wbc, void *_data)
+static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+ struct folio *folio, u64 pos,
+ unsigned len, u64 end_pos)
{
- struct fuse_fill_wb_data *data = _data;
+ struct fuse_fill_wb_data *data = wpc->wb_ctx;
struct fuse_writepage_args *wpa = data->wpa;
struct fuse_args_pages *ap = &wpa->ia.ap;
- struct inode *inode = data->inode;
+ struct inode *inode = wpc->inode;
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = get_fuse_conn(inode);
- struct folio *tmp_folio;
- int err;
+ loff_t offset = offset_in_folio(folio, pos);
+
+ WARN_ON_ONCE(!data);
if (!data->ff) {
- err = -EIO;
data->ff = fuse_write_file_get(fi);
if (!data->ff)
- goto out_unlock;
+ return -EIO;
}
- if (wpa && fuse_writepage_need_send(fc, folio, ap, data)) {
- fuse_writepages_send(data);
+ if (wpa && fuse_writepage_need_send(fc, pos, len, ap, data)) {
+ fuse_writepages_send(inode, data);
data->wpa = NULL;
+ data->nr_bytes = 0;
}
- err = -ENOMEM;
- tmp_folio = folio_alloc(GFP_NOFS | __GFP_HIGHMEM, 0);
- if (!tmp_folio)
- goto out_unlock;
-
- /*
- * The page must not be redirtied until the writeout is completed
- * (i.e. userspace has sent a reply to the write request). Otherwise
- * there could be more than one temporary page instance for each real
- * page.
- *
- * This is ensured by holding the page lock in page_mkwrite() while
- * checking fuse_page_is_writeback(). We already hold the page lock
- * since clear_page_dirty_for_io() and keep it held until we add the
- * request to the fi->writepages list and increment ap->num_folios.
- * After this fuse_page_is_writeback() will indicate that the page is
- * under writeback, so we can release the page lock.
- */
if (data->wpa == NULL) {
- err = -ENOMEM;
- wpa = fuse_writepage_args_setup(folio, data->ff);
- if (!wpa) {
- folio_put(tmp_folio);
- goto out_unlock;
- }
+ wpa = fuse_writepage_args_setup(folio, offset, data->ff);
+ if (!wpa)
+ return -ENOMEM;
fuse_file_get(wpa->ia.ff);
data->max_folios = 1;
ap = &wpa->ia.ap;
}
- folio_start_writeback(folio);
- fuse_writepage_args_page_fill(wpa, folio, tmp_folio, ap->num_folios);
- data->orig_folios[ap->num_folios] = folio;
+ iomap_start_folio_write(inode, folio, 1);
+ fuse_writepage_args_page_fill(wpa, folio, ap->num_folios,
+ offset, len);
+ data->nr_bytes += len;
- err = 0;
- if (data->wpa) {
- /*
- * Protected by fi->lock against concurrent access by
- * fuse_page_is_writeback().
- */
- spin_lock(&fi->lock);
- ap->num_folios++;
- spin_unlock(&fi->lock);
- } else if (fuse_writepage_add(wpa, folio)) {
+ ap->num_folios++;
+ if (!data->wpa)
data->wpa = wpa;
- } else {
- folio_end_writeback(folio);
+
+ return len;
+}
+
+static int fuse_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
+ int error)
+{
+ struct fuse_fill_wb_data *data = wpc->wb_ctx;
+
+ WARN_ON_ONCE(!data);
+
+ if (data->wpa) {
+ WARN_ON(!data->wpa->ia.ap.num_folios);
+ fuse_writepages_send(wpc->inode, data);
}
-out_unlock:
- folio_unlock(folio);
- return err;
+ if (data->ff)
+ fuse_file_put(data->ff, false);
+
+ return error;
}
+static const struct iomap_writeback_ops fuse_writeback_ops = {
+ .writeback_range = fuse_iomap_writeback_range,
+ .writeback_submit = fuse_iomap_writeback_submit,
+};
+
static int fuse_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_fill_wb_data data;
- int err;
+ struct fuse_fill_wb_data data = {};
+ struct iomap_writepage_ctx wpc = {
+ .inode = inode,
+ .iomap.type = IOMAP_MAPPED,
+ .wbc = wbc,
+ .ops = &fuse_writeback_ops,
+ .wb_ctx = &data,
+ };
- err = -EIO;
if (fuse_is_bad(inode))
- goto out;
+ return -EIO;
if (wbc->sync_mode == WB_SYNC_NONE &&
fc->num_background >= fc->congestion_threshold)
return 0;
- data.inode = inode;
- data.wpa = NULL;
- data.ff = NULL;
-
- err = -ENOMEM;
- data.orig_folios = kcalloc(fc->max_pages,
- sizeof(struct folio *),
- GFP_NOFS);
- if (!data.orig_folios)
- goto out;
-
- err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
- if (data.wpa) {
- WARN_ON(!data.wpa->ia.ap.num_folios);
- fuse_writepages_send(&data);
- }
- if (data.ff)
- fuse_file_put(data.ff, false);
-
- kfree(data.orig_folios);
-out:
- return err;
-}
-
-/*
- * It's worthy to make sure that space is reserved on disk for the write,
- * but how to implement it without killing performance need more thinking.
- */
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
-{
- pgoff_t index = pos >> PAGE_SHIFT;
- struct fuse_conn *fc = get_fuse_conn(file_inode(file));
- struct folio *folio;
- loff_t fsize;
- int err = -ENOMEM;
-
- WARN_ON(!fc->writeback_cache);
-
- folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
- mapping_gfp_mask(mapping));
- if (IS_ERR(folio))
- goto error;
-
- fuse_wait_on_page_writeback(mapping->host, folio->index);
-
- if (folio_test_uptodate(folio) || len >= folio_size(folio))
- goto success;
- /*
- * Check if the start of this folio comes after the end of file,
- * in which case the readpage can be optimized away.
- */
- fsize = i_size_read(mapping->host);
- if (fsize <= folio_pos(folio)) {
- size_t off = offset_in_folio(folio, pos);
- if (off)
- folio_zero_segment(folio, 0, off);
- goto success;
- }
- err = fuse_do_readfolio(file, folio);
- if (err)
- goto cleanup;
-success:
- *foliop = folio;
- return 0;
-
-cleanup:
- folio_unlock(folio);
- folio_put(folio);
-error:
- return err;
-}
-
-static int fuse_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct folio *folio, void *fsdata)
-{
- struct inode *inode = folio->mapping->host;
-
- /* Haven't copied anything? Skip zeroing, size extending, dirtying. */
- if (!copied)
- goto unlock;
-
- pos += copied;
- if (!folio_test_uptodate(folio)) {
- /* Zero any unwritten bytes at the end of the page */
- size_t endoff = pos & ~PAGE_MASK;
- if (endoff)
- folio_zero_segment(folio, endoff, PAGE_SIZE);
- folio_mark_uptodate(folio);
- }
-
- if (pos > inode->i_size)
- i_size_write(inode, pos);
-
- folio_mark_dirty(folio);
-
-unlock:
- folio_unlock(folio);
- folio_put(folio);
-
- return copied;
+ return iomap_writepages(&wpc);
}
static int fuse_launder_folio(struct folio *folio)
{
int err = 0;
- if (folio_clear_dirty_for_io(folio)) {
- struct inode *inode = folio->mapping->host;
+ struct fuse_fill_wb_data data = {};
+ struct iomap_writepage_ctx wpc = {
+ .inode = folio->mapping->host,
+ .iomap.type = IOMAP_MAPPED,
+ .ops = &fuse_writeback_ops,
+ .wb_ctx = &data,
+ };
- /* Serialize with pending writeback for the same page */
- fuse_wait_on_page_writeback(inode, folio->index);
- err = fuse_writepage_locked(folio);
+ if (folio_clear_dirty_for_io(folio)) {
+ err = iomap_writeback_folio(&wpc, folio);
+ err = fuse_iomap_writeback_submit(&wpc, err);
if (!err)
- fuse_wait_on_page_writeback(inode, folio->index);
+ folio_wait_writeback(folio);
}
return err;
}
@@ -2611,7 +2283,7 @@ static vm_fault_t fuse_page_mkwrite(struct vm_fault *vmf)
return VM_FAULT_NOPAGE;
}
- fuse_wait_on_folio_writeback(inode, folio);
+ folio_wait_writeback(folio);
return VM_FAULT_LOCKED;
}
@@ -3418,20 +3090,24 @@ static const struct address_space_operations fuse_file_aops = {
.readahead = fuse_readahead,
.writepages = fuse_writepages,
.launder_folio = fuse_launder_folio,
- .dirty_folio = filemap_dirty_folio,
+ .dirty_folio = iomap_dirty_folio,
+ .release_folio = iomap_release_folio,
+ .invalidate_folio = iomap_invalidate_folio,
+ .is_partially_uptodate = iomap_is_partially_uptodate,
.migrate_folio = filemap_migrate_folio,
.bmap = fuse_bmap,
.direct_IO = fuse_direct_IO,
- .write_begin = fuse_write_begin,
- .write_end = fuse_write_end,
};
void fuse_init_file_inode(struct inode *inode, unsigned int flags)
{
struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_conn *fc = get_fuse_conn(inode);
inode->i_fop = &fuse_file_operations;
inode->i_data.a_ops = &fuse_file_aops;
+ if (fc->writeback_cache)
+ mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data);
INIT_LIST_HEAD(&fi->write_files);
INIT_LIST_HEAD(&fi->queued_writes);
@@ -3439,7 +3115,6 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags)
fi->iocachectr = 0;
init_waitqueue_head(&fi->page_waitq);
init_waitqueue_head(&fi->direct_io_waitq);
- fi->writepages = RB_ROOT;
if (IS_ENABLED(CONFIG_FUSE_DAX))
fuse_dax_inode_init(inode, flags);
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
index 3b2bfe1248d3..5a9bd771a319 100644
--- a/fs/fuse/fuse_dev_i.h
+++ b/fs/fuse/fuse_dev_i.h
@@ -20,7 +20,6 @@ struct fuse_iqueue;
struct fuse_forget_link;
struct fuse_copy_state {
- int write;
struct fuse_req *req;
struct iov_iter *iter;
struct pipe_buffer *pipebufs;
@@ -30,8 +29,9 @@ struct fuse_copy_state {
struct page *pg;
unsigned int len;
unsigned int offset;
- unsigned int move_pages:1;
- unsigned int is_uring:1;
+ bool write:1;
+ bool move_folios:1;
+ bool is_uring:1;
struct {
unsigned int copied_sz; /* copied size into the user buffer */
} ring;
@@ -51,7 +51,7 @@ struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique);
void fuse_dev_end_requests(struct list_head *head);
-void fuse_copy_init(struct fuse_copy_state *cs, int write,
+void fuse_copy_init(struct fuse_copy_state *cs, bool write,
struct iov_iter *iter);
int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs,
unsigned int argpages, struct fuse_arg *args,
@@ -61,6 +61,9 @@ int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
struct fuse_forget_link *forget);
void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req);
+bool fuse_remove_pending_req(struct fuse_req *req, spinlock_t *lock);
+
+bool fuse_request_expired(struct fuse_conn *fc, struct list_head *list);
#endif
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fee96fe7887b..ec248d13c8bf 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -38,14 +38,34 @@
/** Bias for fi->writectr, meaning new writepages must not be sent */
#define FUSE_NOWRITE INT_MIN
-/** It could be as large as PATH_MAX, but would that have any uses? */
-#define FUSE_NAME_MAX 1024
+/** Maximum length of a filename, not including terminating null */
+
+/* maximum, small enough for FUSE_MIN_READ_BUFFER*/
+#define FUSE_NAME_LOW_MAX 1024
+/* maximum, but needs a request buffer > FUSE_MIN_READ_BUFFER */
+#define FUSE_NAME_MAX (PATH_MAX - 1)
/** Number of dentries for each connection in the control filesystem */
#define FUSE_CTL_NUM_DENTRIES 5
+/* Frequency (in seconds) of request timeout checks, if opted into */
+#define FUSE_TIMEOUT_TIMER_FREQ 15
+
+/** Frequency (in jiffies) of request timeout checks, if opted into */
+extern const unsigned long fuse_timeout_timer_freq;
+
/** Maximum of max_pages received in init_out */
extern unsigned int fuse_max_pages_limit;
+/*
+ * Default timeout (in seconds) for the server to reply to a request
+ * before the connection is aborted, if no timeout was specified on mount.
+ */
+extern unsigned int fuse_default_req_timeout;
+/*
+ * Max timeout (in seconds) for the server to reply to a request before
+ * the connection is aborted.
+ */
+extern unsigned int fuse_max_req_timeout;
/** List of active connections */
extern struct list_head fuse_conn_list;
@@ -54,8 +74,8 @@ extern struct list_head fuse_conn_list;
extern struct mutex fuse_mutex;
/** Module parameters */
-extern unsigned max_user_bgreq;
-extern unsigned max_user_congthresh;
+extern unsigned int max_user_bgreq;
+extern unsigned int max_user_congthresh;
/* One forget request */
struct fuse_forget_link {
@@ -141,9 +161,6 @@ struct fuse_inode {
/* waitq for direct-io completion */
wait_queue_head_t direct_io_waitq;
-
- /* List of writepage requestst (pending or sent) */
- struct rb_root writepages;
};
/* readdir cache (directory only) */
@@ -378,6 +395,7 @@ struct fuse_io_priv {
* FR_FINISHED: request is finished
* FR_PRIVATE: request is on private list
* FR_ASYNC: request is asynchronous
+ * FR_URING: request is handled through fuse-io-uring
*/
enum fuse_req_flag {
FR_ISREPLY,
@@ -392,6 +410,7 @@ enum fuse_req_flag {
FR_FINISHED,
FR_PRIVATE,
FR_ASYNC,
+ FR_URING,
};
/**
@@ -441,7 +460,10 @@ struct fuse_req {
#ifdef CONFIG_FUSE_IO_URING
void *ring_entry;
+ void *ring_queue;
#endif
+ /** When (in jiffies) the request was created */
+ unsigned long create_time;
};
struct fuse_iqueue;
@@ -611,6 +633,9 @@ struct fuse_conn {
/** Number of fuse_dev's */
atomic_t dev_count;
+ /** Current epoch for up-to-date dentries */
+ atomic_t epoch;
+
struct rcu_head rcu;
/** The user id for this mount */
@@ -867,6 +892,9 @@ struct fuse_conn {
/* Use pages instead of pointer for kernel I/O */
unsigned int use_pages_for_kvec_io:1;
+ /* Is link not implemented by fs? */
+ unsigned int no_link:1;
+
/* Use io_uring for communication */
unsigned int io_uring;
@@ -885,12 +913,6 @@ struct fuse_conn {
/** Device ID from the root super block */
dev_t dev;
- /** Dentries in the control filesystem */
- struct dentry *ctl_dentry[FUSE_CTL_NUM_DENTRIES];
-
- /** number of dentries used in the above array */
- int ctl_ndents;
-
/** Key for lock owner ID scrambling */
u32 scramble_key[4];
@@ -900,6 +922,9 @@ struct fuse_conn {
/** Version counter for evict inode */
atomic64_t evict_ctr;
+ /* maximum file name length */
+ u32 name_max;
+
/** Called on final put */
void (*release)(struct fuse_conn *);
@@ -935,6 +960,15 @@ struct fuse_conn {
/** uring connection information*/
struct fuse_ring *ring;
#endif
+
+ /** Only used if the connection opts into request timeouts */
+ struct {
+ /* Worker for checking if any requests have timed out */
+ struct delayed_work work;
+
+ /* Request timeout (in jiffies). 0 = no timeout */
+ unsigned int req_timeout;
+ } timeout;
};
/*
@@ -1069,7 +1103,6 @@ static inline void fuse_sync_bucket_dec(struct fuse_sync_bucket *bucket)
extern const struct file_operations fuse_dev_operations;
extern const struct dentry_operations fuse_dentry_operations;
-extern const struct dentry_operations fuse_root_dentry_operations;
/**
* Get a filled in inode
@@ -1216,6 +1249,9 @@ void fuse_request_end(struct fuse_req *req);
void fuse_abort_conn(struct fuse_conn *fc);
void fuse_wait_aborted(struct fuse_conn *fc);
+/* Check if any requests timed out */
+void fuse_check_timeout(struct work_struct *work);
+
/**
* Invalidate inode attributes
*/
@@ -1443,9 +1479,9 @@ void fuse_dax_cancel_work(struct fuse_conn *fc);
long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
-int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int fuse_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
int fuse_fileattr_set(struct mnt_idmap *idmap,
- struct dentry *dentry, struct fileattr *fa);
+ struct dentry *dentry, struct file_kattr *fa);
/* iomode.c */
int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e9db2cb8c150..ecb869e895ab 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -9,6 +9,7 @@
#include "fuse_i.h"
#include "dev_uring_i.h"
+#include <linux/dax.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/file.h>
@@ -37,8 +38,11 @@ DEFINE_MUTEX(fuse_mutex);
static int set_global_limit(const char *val, const struct kernel_param *kp);
unsigned int fuse_max_pages_limit = 256;
+/* default is no timeout */
+unsigned int fuse_default_req_timeout;
+unsigned int fuse_max_req_timeout;
-unsigned max_user_bgreq;
+unsigned int max_user_bgreq;
module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
&max_user_bgreq, 0644);
__MODULE_PARM_TYPE(max_user_bgreq, "uint");
@@ -46,7 +50,7 @@ MODULE_PARM_DESC(max_user_bgreq,
"Global limit for the maximum number of backgrounded requests an "
"unprivileged user can set");
-unsigned max_user_congthresh;
+unsigned int max_user_congthresh;
module_param_call(max_user_congthresh, set_global_limit, param_get_uint,
&max_user_congthresh, 0644);
__MODULE_PARM_TYPE(max_user_congthresh, "uint");
@@ -159,6 +163,9 @@ static void fuse_evict_inode(struct inode *inode)
/* Will write inode on close/munmap and in all other dirtiers */
WARN_ON(inode->i_state & I_DIRTY_INODE);
+ if (FUSE_IS_DAX(inode))
+ dax_break_layout_final(inode);
+
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
if (inode->i_sb->s_flags & SB_ACTIVE) {
@@ -959,6 +966,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
init_rwsem(&fc->killsb);
refcount_set(&fc->count, 1);
atomic_set(&fc->dev_count, 1);
+ atomic_set(&fc->epoch, 1);
init_waitqueue_head(&fc->blocked_waitq);
fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv);
INIT_LIST_HEAD(&fc->bg_queue);
@@ -979,6 +987,8 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
fc->user_ns = get_user_ns(user_ns);
fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
fc->max_pages_limit = fuse_max_pages_limit;
+ fc->name_max = FUSE_NAME_LOW_MAX;
+ fc->timeout.req_timeout = 0;
if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
fuse_backing_files_init(fc);
@@ -1007,6 +1017,8 @@ void fuse_conn_put(struct fuse_conn *fc)
if (IS_ENABLED(CONFIG_FUSE_DAX))
fuse_dax_conn_free(fc);
+ if (fc->timeout.req_timeout)
+ cancel_delayed_work_sync(&fc->timeout.work);
if (fiq->ops->release)
fiq->ops->release(fiq);
put_pid_ns(fc->pid_ns);
@@ -1029,7 +1041,7 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
}
EXPORT_SYMBOL_GPL(fuse_conn_get);
-static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
+static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned int mode)
{
struct fuse_attr attr;
memset(&attr, 0, sizeof(attr));
@@ -1204,7 +1216,7 @@ static const struct super_operations fuse_super_operations = {
.show_options = fuse_show_options,
};
-static void sanitize_global_limit(unsigned *limit)
+static void sanitize_global_limit(unsigned int *limit)
{
/*
* The default maximum number of async requests is calculated to consume
@@ -1225,7 +1237,7 @@ static int set_global_limit(const char *val, const struct kernel_param *kp)
if (rv)
return rv;
- sanitize_global_limit((unsigned *)kp->arg);
+ sanitize_global_limit((unsigned int *)kp->arg);
return 0;
}
@@ -1257,6 +1269,34 @@ static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg)
spin_unlock(&fc->bg_lock);
}
+static void set_request_timeout(struct fuse_conn *fc, unsigned int timeout)
+{
+ fc->timeout.req_timeout = secs_to_jiffies(timeout);
+ INIT_DELAYED_WORK(&fc->timeout.work, fuse_check_timeout);
+ queue_delayed_work(system_wq, &fc->timeout.work,
+ fuse_timeout_timer_freq);
+}
+
+static void init_server_timeout(struct fuse_conn *fc, unsigned int timeout)
+{
+ if (!timeout && !fuse_max_req_timeout && !fuse_default_req_timeout)
+ return;
+
+ if (!timeout)
+ timeout = fuse_default_req_timeout;
+
+ if (fuse_max_req_timeout) {
+ if (timeout)
+ timeout = min(fuse_max_req_timeout, timeout);
+ else
+ timeout = fuse_max_req_timeout;
+ }
+
+ timeout = max(FUSE_TIMEOUT_TIMER_FREQ, timeout);
+
+ set_request_timeout(fc, timeout);
+}
+
struct fuse_init_args {
struct fuse_args args;
struct fuse_init_in in;
@@ -1275,6 +1315,7 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
ok = false;
else {
unsigned long ra_pages;
+ unsigned int timeout = 0;
process_init_limits(fc, arg);
@@ -1338,6 +1379,13 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
fc->max_pages =
min_t(unsigned int, fc->max_pages_limit,
max_t(unsigned int, arg->max_pages, 1));
+
+ /*
+ * PATH_MAX file names might need two pages for
+ * ops like rename
+ */
+ if (fc->max_pages > 1)
+ fc->name_max = FUSE_NAME_MAX;
}
if (IS_ENABLED(CONFIG_FUSE_DAX)) {
if (flags & FUSE_MAP_ALIGNMENT &&
@@ -1392,12 +1440,17 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
}
if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled())
fc->io_uring = 1;
+
+ if (flags & FUSE_REQUEST_TIMEOUT)
+ timeout = arg->request_timeout;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
fc->no_flock = 1;
}
+ init_server_timeout(fc, timeout);
+
fm->sb->s_bdi->ra_pages =
min(fm->sb->s_bdi->ra_pages, ra_pages);
fc->minor = arg->minor;
@@ -1439,7 +1492,8 @@ void fuse_send_init(struct fuse_mount *fm)
FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP |
- FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND | FUSE_ALLOW_IDMAP;
+ FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND | FUSE_ALLOW_IDMAP |
+ FUSE_REQUEST_TIMEOUT;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
flags |= FUSE_MAP_ALIGNMENT;
@@ -1665,7 +1719,7 @@ static int fuse_fill_super_submount(struct super_block *sb,
fi = get_fuse_inode(root);
fi->nlookup--;
- sb->s_d_op = &fuse_dentry_operations;
+ set_default_d_op(sb, &fuse_dentry_operations);
sb->s_root = d_make_root(root);
if (!sb->s_root)
return -ENOMEM;
@@ -1800,12 +1854,10 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
err = -ENOMEM;
root = fuse_get_root_inode(sb, ctx->rootmode);
- sb->s_d_op = &fuse_root_dentry_operations;
+ set_default_d_op(sb, &fuse_dentry_operations);
root_dentry = d_make_root(root);
if (!root_dentry)
goto err_dev_free;
- /* Root dentry doesn't have .d_revalidate */
- sb->s_d_op = &fuse_dentry_operations;
mutex_lock(&fuse_mutex);
err = -EINVAL;
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 2d9abf48828f..57032eadca6c 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -502,7 +502,7 @@ static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff)
fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode));
}
-int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int fuse_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
{
struct inode *inode = d_inode(dentry);
struct fuse_file *ff;
@@ -536,11 +536,13 @@ int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa)
cleanup:
fuse_priv_ioctl_cleanup(inode, ff);
+ if (err == -ENOTTY)
+ err = -EOPNOTSUPP;
return err;
}
int fuse_fileattr_set(struct mnt_idmap *idmap,
- struct dentry *dentry, struct fileattr *fa)
+ struct dentry *dentry, struct file_kattr *fa)
{
struct inode *inode = d_inode(dentry);
struct fuse_file *ff;
@@ -572,5 +574,7 @@ int fuse_fileattr_set(struct mnt_idmap *idmap,
cleanup:
fuse_priv_ioctl_cleanup(inode, ff);
+ if (err == -ENOTTY)
+ err = -EOPNOTSUPP;
return err;
}
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index 17ce9636a2b1..c2aae2eef086 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -120,7 +120,7 @@ static bool fuse_emit(struct file *file, struct dir_context *ctx,
fuse_add_dirent_to_cache(file, dirent, ctx->pos);
return dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino,
- dirent->type);
+ dirent->type | FILLDIR_FLAG_NOINTR);
}
static int parse_dirfile(char *buf, size_t nbytes, struct file *file,
@@ -161,6 +161,7 @@ static int fuse_direntplus_link(struct file *file,
struct fuse_conn *fc;
struct inode *inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+ int epoch;
if (!o->nodeid) {
/*
@@ -190,6 +191,7 @@ static int fuse_direntplus_link(struct file *file,
return -EIO;
fc = get_fuse_conn(dir);
+ epoch = atomic_read(&fc->epoch);
name.hash = full_name_hash(parent, name.name, name.len);
dentry = d_lookup(parent, &name);
@@ -256,6 +258,7 @@ retry:
}
if (fc->readdirplus_auto)
set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
+ dentry->d_time = epoch;
fuse_change_entry_timeout(dentry, o);
dput(dentry);
@@ -332,35 +335,32 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
{
int plus;
ssize_t res;
- struct folio *folio;
struct inode *inode = file_inode(file);
struct fuse_mount *fm = get_fuse_mount(inode);
+ struct fuse_conn *fc = fm->fc;
struct fuse_io_args ia = {};
- struct fuse_args_pages *ap = &ia.ap;
- struct fuse_folio_desc desc = { .length = PAGE_SIZE };
+ struct fuse_args *args = &ia.ap.args;
+ void *buf;
+ size_t bufsize = clamp((unsigned int) ctx->count, PAGE_SIZE, fc->max_pages << PAGE_SHIFT);
u64 attr_version = 0, evict_ctr = 0;
bool locked;
- folio = folio_alloc(GFP_KERNEL, 0);
- if (!folio)
+ buf = kvmalloc(bufsize, GFP_KERNEL);
+ if (!buf)
return -ENOMEM;
+ args->out_args[0].value = buf;
+
plus = fuse_use_readdirplus(inode, ctx);
- ap->args.out_pages = true;
- ap->num_folios = 1;
- ap->folios = &folio;
- ap->descs = &desc;
if (plus) {
attr_version = fuse_get_attr_version(fm->fc);
evict_ctr = fuse_get_evict_ctr(fm->fc);
- fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
- FUSE_READDIRPLUS);
+ fuse_read_args_fill(&ia, file, ctx->pos, bufsize, FUSE_READDIRPLUS);
} else {
- fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
- FUSE_READDIR);
+ fuse_read_args_fill(&ia, file, ctx->pos, bufsize, FUSE_READDIR);
}
locked = fuse_lock_inode(inode);
- res = fuse_simple_request(fm, &ap->args);
+ res = fuse_simple_request(fm, args);
fuse_unlock_inode(inode, locked);
if (res >= 0) {
if (!res) {
@@ -369,16 +369,14 @@ static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
if (ff->open_flags & FOPEN_CACHE_DIR)
fuse_readdir_cache_end(file, ctx->pos);
} else if (plus) {
- res = parse_dirplusfile(folio_address(folio), res,
- file, ctx, attr_version,
+ res = parse_dirplusfile(buf, res, file, ctx, attr_version,
evict_ctr);
} else {
- res = parse_dirfile(folio_address(folio), res, file,
- ctx);
+ res = parse_dirfile(buf, res, file, ctx);
}
}
- folio_put(folio);
+ kvfree(buf);
fuse_invalidate_atime(inode);
return res;
}
@@ -419,7 +417,7 @@ static enum fuse_parse_result fuse_parse_cache(struct fuse_file *ff,
if (ff->readdir.pos == ctx->pos) {
res = FOUND_SOME;
if (!dir_emit(ctx, dirent->name, dirent->namelen,
- dirent->ino, dirent->type))
+ dirent->ino, dirent->type | FILLDIR_FLAG_NOINTR))
return FOUND_ALL;
ctx->pos = dirent->off;
}
diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c
index 63fb1e5bee30..e2d921abcb88 100644
--- a/fs/fuse/sysctl.c
+++ b/fs/fuse/sysctl.c
@@ -13,6 +13,12 @@ static struct ctl_table_header *fuse_table_header;
/* Bound by fuse_init_out max_pages, which is a u16 */
static unsigned int sysctl_fuse_max_pages_limit = 65535;
+/*
+ * fuse_init_out request timeouts are u16.
+ * This goes up to ~18 hours, which is plenty for a timeout.
+ */
+static unsigned int sysctl_fuse_req_timeout_limit = 65535;
+
static const struct ctl_table fuse_sysctl_table[] = {
{
.procname = "max_pages_limit",
@@ -23,6 +29,24 @@ static const struct ctl_table fuse_sysctl_table[] = {
.extra1 = SYSCTL_ONE,
.extra2 = &sysctl_fuse_max_pages_limit,
},
+ {
+ .procname = "default_request_timeout",
+ .data = &fuse_default_req_timeout,
+ .maxlen = sizeof(fuse_default_req_timeout),
+ .mode = 0644,
+ .proc_handler = proc_douintvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &sysctl_fuse_req_timeout_limit,
+ },
+ {
+ .procname = "max_request_timeout",
+ .data = &fuse_max_req_timeout,
+ .maxlen = sizeof(fuse_max_req_timeout),
+ .mode = 0644,
+ .proc_handler = proc_douintvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &sysctl_fuse_req_timeout_limit,
+ },
};
int fuse_sysctl_register(void)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 2c7b24cb67ad..c826e7ca49f5 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -9,7 +9,6 @@
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/group_cpus.h>
-#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/module.h>
#include <linux/virtio.h>
@@ -862,7 +861,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs)
{
const struct cpumask *mask, *masks;
- unsigned int q, cpu;
+ unsigned int q, cpu, nr_masks;
/* First attempt to map using existing transport layer affinities
* e.g. PCIe MSI-X
@@ -882,7 +881,7 @@ static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *f
return;
fallback:
/* Attempt to map evenly in groups over the CPUs */
- masks = group_cpus_evenly(fs->num_request_queues);
+ masks = group_cpus_evenly(fs->num_request_queues, &nr_masks);
/* If even this fails we default to all CPUs use first request queue */
if (!masks) {
for_each_possible_cpu(cpu)
@@ -891,7 +890,7 @@ fallback:
}
for (q = 0; q < fs->num_request_queues; q++) {
- for_each_cpu(cpu, &masks[q])
+ for_each_cpu(cpu, &masks[q % nr_masks])
fs->mq_map[cpu] = q + VQ_REQUEST;
}
kfree(masks);
@@ -1008,7 +1007,7 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev)
*/
static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
long nr_pages, enum dax_access_mode mode,
- void **kaddr, pfn_t *pfn)
+ void **kaddr, unsigned long *pfn)
{
struct virtio_fs *fs = dax_get_private(dax_dev);
phys_addr_t offset = PFN_PHYS(pgoff);
@@ -1017,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
if (kaddr)
*kaddr = fs->window_kaddr + offset;
if (pfn)
- *pfn = phys_to_pfn_t(fs->window_phys_addr + offset, 0);
+ *pfn = fs->window_phys_addr + offset;
return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}
@@ -1669,6 +1668,9 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
unsigned int virtqueue_size;
int err = -EIO;
+ if (!fsc->source)
+ return invalf(fsc, "No source specified");
+
/* This gets a reference on virtio_fs object. This ptr gets installed
* in fc->iq->priv. Once fuse_conn is going away, it calls ->put()
* to drop the reference to this object.
generated by cgit (git 2.34.1) at 2025-08-06 01:35:42 +0000