io_uring/cmd: rename struct uring_cache to io_uring_cmd_data
Subsystems (2)
PATCH 1/4 io_uring/cmd: rename struct uring_cache to io_uring_cmd_data
From: Jens Axboe <[email protected]>
In preparation for making this more generically available for ->uring_cmd() usage that needs stable command data, rename it and move it to io_uring/cmd.h instead.
--- include/linux/io_uring/cmd.h | 4 ++++ io_uring/io_uring.c | 2 +- io_uring/uring_cmd.c | 10 +++++----- io_uring/uring_cmd.h | 4 ---- 4 files changed, 10 insertions(+), 10 deletions(-)
include/linux/io_uring/cmd.h +4 -0
@@ -18,6 +18,10 @@ struct io_uring_cmd {u8 pdu[32 ];/* available inline for free use */ }; +struct io_uring_cmd_data { +struct io_uring_sqe sqes[2 ]; +}; +static inline const void *io_uring_sqe_cmd (const struct io_uring_sqe *sqe) {return sqe->cmd;
io_uring/io_uring.c +1 -1
@@ -315,7 +315,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ret |=io_alloc_cache_init (&ctx->rw_cache,IO_ALLOC_CACHE_MAX ,sizeof (struct io_async_rw )); ret |=io_alloc_cache_init (&ctx->uring_cache,IO_ALLOC_CACHE_MAX , -sizeof (struct uring_cache )); +sizeof (struct io_uring_cmd_data ));spin_lock_init (&ctx->msg_lock); ret |=io_alloc_cache_init (&ctx->msg_cache,IO_ALLOC_CACHE_MAX ,sizeof (struct io_kiocb ));
io_uring/uring_cmd.c +5 -5
@@ -16,10 +16,10 @@#include "rsrc.h" #include "uring_cmd.h" -static struct uring_cache *io_uring_async_get (struct io_kiocb *req) +static struct io_uring_cmd_data *io_uring_async_get (struct io_kiocb *req) {struct io_ring_ctx *ctx = req->ctx; -struct uring_cache *cache; +struct io_uring_cmd_data *cache; cache =io_alloc_cache_get (&ctx->uring_cache);if (cache) {
@@ -35,7 +35,7 @@ static struct uring_cache *io_uring_async_get(struct io_kiocb *req)static void io_req_uring_cleanup (struct io_kiocb *req,unsigned int issue_flags) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); -struct uring_cache *cache = req->async_data; +struct io_uring_cmd_data *cache = req->async_data;if (issue_flags &IO_URING_F_UNLOCKED )return ;
@@ -183,7 +183,7 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); -struct uring_cache *cache; +struct io_uring_cmd_data *cache; cache =io_uring_async_get (req);if (unlikely (!cache))
@@ -256,7 +256,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) ret = file->f_op->uring_cmd (ioucmd, issue_flags);if (ret == -EAGAIN ) { -struct uring_cache *cache = req->async_data; +struct io_uring_cmd_data *cache = req->async_data;if (ioucmd->sqe != (void *) cache)memcpy (cache, ioucmd->sqe,uring_sqe_size (req->ctx));
io_uring/uring_cmd.h +0 -4
@@ -1,9 +1,5 @@// SPDX-License-Identifier: GPL-2.0 -struct uring_cache { -struct io_uring_sqe sqes[2 ]; -}; -int io_uring_cmd (struct io_kiocb *req,unsigned int issue_flags);int io_uring_cmd_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe);
Signature · 1 line
2.45.2
PATCH 2/4 io_uring: use sizeof for io_issue_defs[IORING_OP_URING_CMD].async_size
Correct the value of io_issue_defs[IORING_OP_URING_CMD].async_size so that it is derived from the size of the struct rather than being calculated.
--- io_uring/opdef.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
io_uring/opdef.c +2 -1
@@ -7,6 +7,7 @@#include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> +#include <linux/io_uring/cmd.h> #include "io_uring.h" #include "opdef.h"
@@ -414,7 +415,7 @@ const struct io_issue_def io_issue_defs[] = { .plug = 1, .iopoll = 1, .iopoll_queue = 1, - .async_size = 2 * sizeof(struct io_uring_sqe), + .async_size = sizeof(struct io_uring_cmd_data), .prep = io_uring_cmd_prep, .issue = io_uring_cmd, },
Signature · 1 line
2.45.2
Jens Axboe
maintainerRe: [PATCH 2/4] io_uring: use sizeof for io_issue_defs[IORING_OP_URING_CMD].async_size
Quoted 3 lines · Mark Harmstone
Correct the value of io_issue_defs[IORING_OP_URING_CMD].async_size so that it is derived from the size of the struct rather than being calculated.
You should probably just fold this with patch 1, where the type is changed.
Signature · 1 line
Jens Axboe
PATCH 3/4 io_uring/cmd: add per-op data to struct io_uring_cmd_data
In reply to Mark HarmstoneFrom: Jens Axboe <[email protected]>
In case an op handler for ->uring_cmd() needs stable storage for user data, it can allocate io_uring_cmd_data->op_data and use it for the duration of the request. When the request gets cleaned up, uring_cmd will free it automatically.
--- include/linux/io_uring/cmd.h | 1 + io_uring/uring_cmd.c | 13 +++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-)
include/linux/io_uring/cmd.h +1 -0
@@ -20,6 +20,7 @@ struct io_uring_cmd {struct io_uring_cmd_data {struct io_uring_sqe sqes[2 ]; +void *op_data; };static inline const void *io_uring_sqe_cmd (const struct io_uring_sqe *sqe)
io_uring/uring_cmd.c +11 -2
@@ -23,12 +23,16 @@ static struct io_uring_cmd_data *io_uring_async_get(struct io_kiocb *req) cache =io_alloc_cache_get (&ctx->uring_cache);if (cache) { + cache->op_data =NULL ; req->flags |=REQ_F_ASYNC_DATA ; req->async_data = cache;return cache; } -if (!io_alloc_async_data (req)) -return req->async_data; +if (!io_alloc_async_data (req)) { + cache = req->async_data; + cache->op_data =NULL ; +return cache; + }return NULL ; }
@@ -37,6 +41,11 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);struct io_uring_cmd_data *cache = req->async_data; +if (cache->op_data) { +kfree (cache->op_data); + cache->op_data =NULL ; + } +if (issue_flags &IO_URING_F_UNLOCKED )return ;if (io_alloc_cache_put (&req->ctx->uring_cache, cache)) {
Signature · 1 line
2.45.2
PATCH 4/4 btrfs: don't read from userspace twice in btrfs_uring_encoded_read()
In reply to Mark HarmstoneIf we return -EAGAIN the first time because we need to block, btrfs_uring_encoded_read() will get called twice. Take a copy of args the first time, to prevent userspace from messing around with it.
--- fs/btrfs/ioctl.c | 74 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 25 deletions(-)
fs/btrfs/ioctl.c +49 -25
@@ -4873,7 +4873,7 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags);size_t copy_end; -struct btrfs_ioctl_encoded_io_args args = {0 }; +struct btrfs_ioctl_encoded_io_args *args;int ret;u64 disk_bytenr, disk_io_size;struct file *file;
@@ -4888,6 +4888,9 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issuestruct extent_state *cached_state =NULL ;u64 start, lockend;void __user *sqe_addr; +struct io_kiocb *req =cmd_to_io_kiocb (cmd); +struct io_uring_cmd_data *data = req->async_data; +bool need_copy = false;if (!capable (CAP_SYS_ADMIN )) { ret = -EPERM ;
@@ -4899,34 +4902,55 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue io_tree = &inode->io_tree; sqe_addr =u64_to_user_ptr (READ_ONCE (cmd->sqe->addr)); +if (!data->op_data) { + data->op_data =kzalloc (sizeof (*args),GFP_NOFS ); +if (!data->op_data) { + ret = -ENOMEM ; + goto out_acct; + } + + need_copy = true; + } + + args = data->op_data; +if (issue_flags &IO_URING_F_COMPAT ) {#if defined(CONFIG_64BIT ) && defined(CONFIG_COMPAT ) -struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); -if (copy_from_user (&args32, sqe_addr, copy_end)) { - ret = -EFAULT ; - goto out_acct; + +if (need_copy) { +struct btrfs_ioctl_encoded_io_args_32 args32; + +if (copy_from_user (&args32, sqe_addr, copy_end)) { + ret = -EFAULT ; + goto out_acct; + } + + args->iov =compat_ptr (args32.iov); + args->iovcnt = args32.iovcnt; + args->offset = args32.offset; + args->flags = args32.flags; } - args.iov =compat_ptr (args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags;#else return -ENOTTY ;#endif }else { copy_end = copy_end_kernel; -if (copy_from_user (&args, sqe_addr, copy_end)) { - ret = -EFAULT ; - goto out_acct; + +if (need_copy) { +if (copy_from_user (args, sqe_addr, copy_end)) { + ret = -EFAULT ; + goto out_acct; + } } } -if (args.flags !=0 ) -return -EINVAL ; +if (args->flags !=0 ) { + ret = -EINVAL ; + goto out_acct; + } - ret =import_iovec (ITER_DEST , args.iov, args.iovcnt,ARRAY_SIZE (iovstack), + ret =import_iovec (ITER_DEST , args->iov, args->iovcnt,ARRAY_SIZE (iovstack), &iov, &iter);if (ret <0 ) goto out_acct;
@@ -4936,8 +4960,8 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue goto out_free; } - pos = args.offset; - ret =rw_verify_area (READ , file, &pos, args.len); + pos = args->offset; + ret =rw_verify_area (READ , file, &pos, args->len);if (ret <0 ) goto out_free;
@@ -4950,15 +4974,15 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start =ALIGN_DOWN (pos, fs_info->sectorsize); lockend = start +BTRFS_MAX_UNCOMPRESSED -1 ; - ret =btrfs_encoded_read (&kiocb, &iter, &args, &cached_state, + ret =btrfs_encoded_read (&kiocb, &iter, args, &cached_state, &disk_bytenr, &disk_io_size);if (ret <0 && ret != -EIOCBQUEUED ) goto out_free;file_accessed (file); -if (copy_to_user (sqe_addr + copy_end, (const char *)&args + copy_end_kernel, -sizeof (args) - copy_end_kernel)) { +if (copy_to_user (sqe_addr + copy_end, (const char *)args + copy_end_kernel, +sizeof (*args) - copy_end_kernel)) {if (ret == -EIOCBQUEUED ) {unlock_extent (io_tree, start, lockend, &cached_state);btrfs_inode_unlock (inode,BTRFS_ILOCK_SHARED );
@@ -4975,7 +4999,7 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue* undo this. */ if (!iov) { - iov =kmemdup (iovstack,sizeof (struct iovec ) * args.iovcnt, + iov =kmemdup (iovstack,sizeof (struct iovec ) * args->iovcnt,GFP_NOFS );if (!iov) {unlock_extent (io_tree, start, lockend, &cached_state);
@@ -4988,13 +5012,13 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue count =min_t (u64,iov_iter_count (&iter), disk_io_size);/* Match ioctl by not returning past EOF if uncompressed. */ -if (!args.compression) - count =min_t (u64, count, args.len); +if (!args->compression) + count =min_t (u64, count, args->len); ret =btrfs_uring_read_extent (&kiocb, &iter, start, lockend, cached_state, disk_bytenr, disk_io_size, count, - args.compression, iov, cmd); + args->compression, iov, cmd); goto out_acct; }
Signature · 1 line
2.45.2
Re: [PATCH 4/4] btrfs: don't read from userspace twice in btrfs_uring_encoded_read()
Could someone please apply my kmemdup patch from last week so that this applies cleanly? "btrfs: use kmemdup in btrfs_uring_encoded_read"
Quoted 159 lines · Mark Harmstone
If we return
-EAGAINthe first time because we need to block,btrfs_uring_encoded_read()will get called twice. Take a copy of args the first time, to prevent userspace from messing around with it.Signed-off-by Mark Harmstone <[email protected]>--- fs/btrfs/ioctl.c | 74 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 25 deletions(-)fs/btrfs/ioctl.c +49
-25@@ -4873,7 +4873,7 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags);size_t copy_end; -struct btrfs_ioctl_encoded_io_args args = {0 }; +struct btrfs_ioctl_encoded_io_args *args;int ret;u64 disk_bytenr, disk_io_size;struct file *file;@@ -4888,6 +4888,9 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issuestruct extent_state *cached_state =NULL ;u64 start, lockend;void __user *sqe_addr; +struct io_kiocb *req =cmd_to_io_kiocb (cmd); +struct io_uring_cmd_data *data = req->async_data; +bool need_copy = false;if (!capable (CAP_SYS_ADMIN )) { ret = -EPERM ;@@ -4899,34 +4902,55 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue io_tree = &inode->io_tree; sqe_addr =u64_to_user_ptr (READ_ONCE (cmd->sqe->addr)); +if (!data->op_data) { + data->op_data =kzalloc (sizeof (*args),GFP_NOFS ); +if (!data->op_data) { + ret = -ENOMEM ; + goto out_acct; + } + + need_copy = true; + } + + args = data->op_data; +if (issue_flags &IO_URING_F_COMPAT ) {#if defined(CONFIG_64BIT ) && defined(CONFIG_COMPAT ) -struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); -if (copy_from_user (&args32, sqe_addr, copy_end)) { - ret = -EFAULT ; - goto out_acct; + +if (need_copy) { +struct btrfs_ioctl_encoded_io_args_32 args32; + +if (copy_from_user (&args32, sqe_addr, copy_end)) { + ret = -EFAULT ; + goto out_acct; + } + + args->iov =compat_ptr (args32.iov); + args->iovcnt = args32.iovcnt; + args->offset = args32.offset; + args->flags = args32.flags; } - args.iov =compat_ptr (args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags;#else return -ENOTTY ;#endif }else { copy_end = copy_end_kernel; -if (copy_from_user (&args, sqe_addr, copy_end)) { - ret = -EFAULT ; - goto out_acct; + +if (need_copy) { +if (copy_from_user (args, sqe_addr, copy_end)) { + ret = -EFAULT ; + goto out_acct; + } } } -if (args.flags !=0 ) -return -EINVAL ; +if (args->flags !=0 ) { + ret = -EINVAL ; + goto out_acct; + } - ret =import_iovec (ITER_DEST , args.iov, args.iovcnt,ARRAY_SIZE (iovstack), + ret =import_iovec (ITER_DEST , args->iov, args->iovcnt,ARRAY_SIZE (iovstack), &iov, &iter);if (ret <0 ) goto out_acct;@@ -4936,8 +4960,8 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue goto out_free; } - pos = args.offset; - ret =rw_verify_area (READ , file, &pos, args.len); + pos = args->offset; + ret =rw_verify_area (READ , file, &pos, args->len);if (ret <0 ) goto out_free;@@ -4950,15 +4974,15 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start =ALIGN_DOWN (pos, fs_info->sectorsize); lockend = start +BTRFS_MAX_UNCOMPRESSED -1 ; - ret =btrfs_encoded_read (&kiocb, &iter, &args, &cached_state, + ret =btrfs_encoded_read (&kiocb, &iter, args, &cached_state, &disk_bytenr, &disk_io_size);if (ret <0 && ret != -EIOCBQUEUED ) goto out_free;file_accessed (file); -if (copy_to_user (sqe_addr + copy_end, (const char *)&args + copy_end_kernel, -sizeof (args) - copy_end_kernel)) { +if (copy_to_user (sqe_addr + copy_end, (const char *)args + copy_end_kernel, +sizeof (*args) - copy_end_kernel)) {if (ret == -EIOCBQUEUED ) {unlock_extent (io_tree, start, lockend, &cached_state);btrfs_inode_unlock (inode,BTRFS_ILOCK_SHARED );@@ -4975,7 +4999,7 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue* undo this. */ if (!iov) { - iov =kmemdup (iovstack,sizeof (struct iovec ) * args.iovcnt, + iov =kmemdup (iovstack,sizeof (struct iovec ) * args->iovcnt,GFP_NOFS );if (!iov) {unlock_extent (io_tree, start, lockend, &cached_state);@@ -4988,13 +5012,13 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue count =min_t (u64,iov_iter_count (&iter), disk_io_size);/* Match ioctl by not returning past EOF if uncompressed. */ -if (!args.compression) - count =min_t (u64, count, args.len); +if (!args->compression) + count =min_t (u64, count, args->len); ret =btrfs_uring_read_extent (&kiocb, &iter, start, lockend, cached_state, disk_bytenr, disk_io_size, count, - args.compression, iov, cmd); + args->compression, iov, cmd); goto out_acct; }
Jens Axboe
maintainerRe: [PATCH 4/4] btrfs: don't read from userspace twice in btrfs_uring_encoded_read()
In reply to Mark HarmstoneQuoted 35 lines · Mark Harmstone
If we return
-EAGAINthe first time because we need to block,btrfs_uring_encoded_read()will get called twice. Take a copy of args the first time, to prevent userspace from messing around with it.Signed-off-by Mark Harmstone <[email protected]>--- fs/btrfs/ioctl.c | 74 ++++++++++++++++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 25 deletions(-)fs/btrfs/ioctl.c +4
-1@@ -4873,7 +4873,7 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags);size_t copy_end; -struct btrfs_ioctl_encoded_io_args args = {0 }; +struct btrfs_ioctl_encoded_io_args *args;int ret;u64 disk_bytenr, disk_io_size;struct file *file;@@ -4888,6 +4888,9 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issuestruct extent_state *cached_state =NULL ;u64 start, lockend;void __user *sqe_addr; +struct io_kiocb *req =cmd_to_io_kiocb (cmd); +struct io_uring_cmd_data *data = req->async_data; +bool need_copy = false;if (!capable (CAP_SYS_ADMIN )) { ret = -EPERM ;@@ -4899,34 +4902,55 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue io_tree = &inode->io_tree; sqe_addr =u64_to_user_ptr (READ_ONCE (cmd->sqe->addr));
fs/btrfs/ioctl.c static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue · line 4913
Quoted 10 lines
fs/btrfs/ioctl.c +9
-0+if (!data->op_data) { + data->op_data =kzalloc (sizeof (*args),GFP_NOFS ); +if (!data->op_data) { + ret = -ENOMEM ; + goto out_acct; + } + + need_copy = true; + }
I'd probably get rid of this need_copy variable and just do the copy here? Might look cleaner with an btrfs_alloc_copy_foo() helper, as you could just do:
ret = btrfs_alloc_copy_foo(...);
if (unlikely(ret))
return ret;
and hide all that ugly compat business outside the meat of this function.
More of a style thing, the change itself looks fine.
Signature · 1 line
Jens Axboe