From 8eb4b09e0bbd30981305643229fe7640ad41b667 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:11 -0500 Subject: [PATCH 01/16] ftrace: Do not add duplicate entries in subops manager ops Check if a function is already in the manager ops of a subops. A manager ops contains multiple subops, and if two or more subops are tracing the same function, the manager ops only needs a single entry in its hash. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.226762894@goodmis.org Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function") Tested-by: Heiko Carstens Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ftrace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index bec54dc27204..6b0c25761ccb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5718,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); -- 2.51.0 From ded9140622358a154efb3a777025fa7f7ae2c2d9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:12 -0500 Subject: [PATCH 02/16] fprobe: Always unregister fgraph function from ops When the last fprobe is removed, it calls unregister_ftrace_graph() to remove the graph_ops from function graph. The issue is when it does so, it calls return before removing the function from its graph ops via ftrace_set_filter_ips(). This leaves the last function lingering in the fprobe's fgraph ops and if a probe is added it also enables that last function (even though the callback will just drop it, it does add unneeded overhead to make that call). # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions # echo "f:myevent3 kmem_cache_free" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kmem_cache_free (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 schedule_timeout (1) tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 The above enabled a fprobe on kernel_clone, and then on schedule_timeout. The content of the enabled_functions shows the functions that have a callback attached to them. The fprobe attached to those functions properly. Then the fprobes were cleared, and enabled_functions was empty after that. But after adding a fprobe on kmem_cache_free, the enabled_functions shows that the schedule_timeout was attached again. This is because it was still left in the fprobe ops that is used to tell function graph what functions it wants callbacks from. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.393254452@goodmis.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Tested-by: Heiko Carstens Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fprobe.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2560b312ad57..62e8f7d56602 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -403,11 +403,9 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_graph_active--; - if (!fprobe_graph_active) { - /* Q: should we unregister it ? */ + /* Q: should we unregister it ? */ + if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - return; - } ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } -- 2.51.0 From ca26554a1498bc905c4a39fb42d55d93f3ae8df2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:13 -0500 Subject: [PATCH 03/16] fprobe: Fix accounting of when to unregister from function graph When adding a new fprobe, it will update the function hash to the functions the fprobe is attached to and register with function graph to have it call the registered functions. The fprobe_graph_active variable keeps track of the number of fprobes that are using function graph. If two fprobes attach to the same function, it increments the fprobe_graph_active for each of them. But when they are removed, the first fprobe to be removed will see that the function it is attached to is also used by another fprobe and it will not remove that function from function_graph. The logic will skip decrementing the fprobe_graph_active variable. This causes the fprobe_graph_active variable to not go to zero when all fprobes are removed, and in doing so it does not unregister from function graph. As the fgraph ops hash will now be empty, and an empty filter hash means all functions are enabled, this triggers function graph to add a callback to the fprobe infrastructure for every function! # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events # echo "f:myevent2 kernel_clone%return" >> /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions kernel_clone (1) tramp: 0xffffffffc0024000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60 # > /sys/kernel/tracing/dynamic_events # cat /sys/kernel/tracing/enabled_functions trace_initcall_start_cb (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 try_to_run_init_process (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 x86_pmu_show_pmu_cap (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 cleanup_rapl_pmus (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_free_pcibus_map (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_types_exit (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 uncore_pci_exit.part.0 (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 kvm_shutdown (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 vmx_dump_msrs (1) tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170 [..] # cat /sys/kernel/tracing/enabled_functions | wc -l 54702 If a fprobe is being removed and all its functions are also traced by other fprobes, still decrement the fprobe_graph_active counter. Cc: stable@vger.kernel.org Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.565129766@goodmis.org Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer") Closes: https://lore.kernel.org/all/20250217114918.10397-A-hca@linux.ibm.com/ Reported-by: Heiko Carstens Tested-by: Heiko Carstens Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/fprobe.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 62e8f7d56602..33082c4e8154 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -407,7 +407,8 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); + if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } static int symbols_cmp(const void *a, const void *b) @@ -677,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - if (count) - fprobe_graph_remove_ips(addrs, count); + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; -- 2.51.0 From e85c5e9792b942381ad92ccd0ff745b6d408a91f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 20 Feb 2025 15:20:14 -0500 Subject: [PATCH 04/16] selftests/ftrace: Update fprobe test to check enabled_functions file A few bugs were found in the fprobe accounting logic along with it using the function graph infrastructure. Update the fprobe selftest to catch those bugs in case they or something similar shows up in the future. The test now checks the enabled_functions file which shows all the functions attached to ftrace or fgraph. When enabling a fprobe, make sure that its corresponding function is also added to that file. Also add two more fprobes to enable to make sure that the fprobe logic works properly with multiple probes. Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Alexander Gordeev Link: https://lore.kernel.org/20250220202055.733001756@goodmis.org Acked-by: Masami Hiramatsu (Google) Tested-by: Heiko Carstens Signed-off-by: Steven Rostedt (Google) --- .../test.d/dynevent/add_remove_fprobe.tc | 54 +++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc index dc25bcf4f9e2..449f9d8be746 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc @@ -7,12 +7,38 @@ echo 0 > events/enable echo > dynamic_events PLACE=$FUNCTION_FORK +PLACE2="kmem_cache_free" +PLACE3="schedule_timeout" echo "f:myevent1 $PLACE" >> dynamic_events + +# Make sure the event is attached and is the only one +grep -q $PLACE enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + echo "f:myevent2 $PLACE%return" >> dynamic_events +# It should till be the only attached function +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + +# add another event +echo "f:myevent3 $PLACE2" >> dynamic_events + +grep -q $PLACE2 enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 2 ]; then + exit_fail +fi + grep -q myevent1 dynamic_events grep -q myevent2 dynamic_events +grep -q myevent3 dynamic_events test -d events/fprobes/myevent1 test -d events/fprobes/myevent2 @@ -21,6 +47,34 @@ echo "-:myevent2" >> dynamic_events grep -q myevent1 dynamic_events ! grep -q myevent2 dynamic_events +# should still have 2 left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 2 ]; then + exit_fail +fi + echo > dynamic_events +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo "f:myevent4 $PLACE" >> dynamic_events + +# Should only have one enabled +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + +echo > dynamic_events + +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 0 ]; then + exit_fail +fi + clear_trace -- 2.51.0 From 57b76bedc5c52c66968183b5ef57234894c25ce7 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 20 Feb 2025 15:07:49 +0100 Subject: [PATCH 05/16] ftrace: Correct preemption accounting for function tracing. The function tracer should record the preemption level at the point when the function is invoked. If the tracing subsystem decrement the preemption counter it needs to correct this before feeding the data into the trace buffer. This was broken in the commit cited below while shifting the preempt-disabled section. Use tracing_gen_ctx_dec() which properly subtracts one from the preemption counter on a preemptible kernel. Cc: stable@vger.kernel.org Cc: Wander Lairson Costa Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Thomas Gleixner Link: https://lore.kernel.org/20250220140749.pfw8qoNZ@linutronix.de Fixes: ce5e48036c9e7 ("ftrace: disable preemption when recursion locked") Signed-off-by: Sebastian Andrzej Siewior Tested-by: Wander Lairson Costa Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index d358c9935164..df56f9b76010 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, parent_ip = function_get_true_parent_ip(parent_ip, fregs); - trace_ctx = tracing_gen_ctx(); + trace_ctx = tracing_gen_ctx_dec(); data = this_cpu_ptr(tr->array_buffer.data); if (!atomic_read(&data->disabled)) @@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned int trace_ctx; - unsigned long flags; int bit; if (unlikely(!tr->function_enabled)) @@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (is_repeat_check(tr, last_info, ip, parent_ip)) goto out; - local_save_flags(flags); - trace_ctx = tracing_gen_ctx_flags(flags); + trace_ctx = tracing_gen_ctx_dec(); process_repeats(tr, ip, parent_ip, last_info, trace_ctx); trace_function(tr, ip, parent_ip, trace_ctx); -- 2.51.0 From 2fa6a01345b538faa7b0fae8f723bb6977312428 Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Thu, 20 Feb 2025 11:15:28 +0800 Subject: [PATCH 06/16] tracing: Fix memory leak when reading set_event file kmemleak reports the following memory leak after reading set_event file: # cat /sys/kernel/tracing/set_event # cat /sys/kernel/debug/kmemleak unreferenced object 0xff110001234449e0 (size 16): comm "cat", pid 13645, jiffies 4294981880 hex dump (first 16 bytes): 01 00 00 00 00 00 00 00 a8 71 e7 84 ff ff ff ff .........q...... backtrace (crc c43abbc): __kmalloc_cache_noprof+0x3ca/0x4b0 s_start+0x72/0x2d0 seq_read_iter+0x265/0x1080 seq_read+0x2c9/0x420 vfs_read+0x166/0xc30 ksys_read+0xf4/0x1d0 do_syscall_64+0x79/0x150 entry_SYSCALL_64_after_hwframe+0x76/0x7e The issue can be reproduced regardless of whether set_event is empty or not. Here is an example about the valid content of set_event. # cat /sys/kernel/tracing/set_event sched:sched_process_fork sched:sched_switch sched:sched_wakeup *:*:mod:trace_events_sample The root cause is that s_next() returns NULL when nothing is found. This results in s_stop() attempting to free a NULL pointer because its parameter is NULL. Fix the issue by freeing the memory appropriately when s_next() fails to find anything. Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250220031528.7373-1-ahuang12@lenovo.com Fixes: b355247df104 ("tracing: Cache ":mod:" events for modules not loaded yet") Signed-off-by: Adrian Huang Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4cb275316e51..513de9ceb80e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos) return iter; #endif + /* + * The iter is allocated in s_start() and passed via the 'v' + * parameter. To stop the iterator, NULL must be returned. But + * the return value is what the 'v' parameter in s_stop() receives + * and frees. Free iter here as it will no longer be used. + */ + kfree(iter); return NULL; } @@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v) } #endif -static void s_stop(struct seq_file *m, void *p) +static void s_stop(struct seq_file *m, void *v) { - kfree(p); + kfree(v); t_stop(m, NULL); } -- 2.51.0 From 781813db7909d945c33d3b035822225f3598774d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 20 Feb 2025 16:12:12 +0100 Subject: [PATCH 07/16] i2c: core: Allocate temporary client dynamically MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit drivers/i2c/i2c-core-base.c: In function ‘i2c_detect.isra’: drivers/i2c/i2c-core-base.c:2544:1: warning: the frame size of 1312 bytes is larger than 1024 bytes [-Wframe-larger-than=] 2544 | } | ^ Fix this by allocating the temporary client structure dynamically, as it is a rather large structure (1216 bytes, depending on kernel config). This is basically a revert of the to-be-fixed commit with some checkpatch improvements. Fixes: 735668f8e5c9 ("i2c: core: Allocate temp client on the stack in i2c_detect") Signed-off-by: Geert Uytterhoeven Reviewed-by: Su Hui Reviewed-by: Guenter Roeck [wsa: updated commit message, merged tags from similar patch] Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 35a221e2c11c..7ad1ad5c8c3f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2506,7 +2506,7 @@ static int i2c_detect_address(struct i2c_client *temp_client, static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver) { const unsigned short *address_list; - struct i2c_client temp_client; + struct i2c_client *temp_client; int i, err = 0; address_list = driver->address_list; @@ -2527,19 +2527,24 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver) return 0; /* Set up a temporary client to help detect callback */ - memset(&temp_client, 0, sizeof(temp_client)); - temp_client.adapter = adapter; + temp_client = kzalloc(sizeof(*temp_client), GFP_KERNEL); + if (!temp_client) + return -ENOMEM; + + temp_client->adapter = adapter; for (i = 0; address_list[i] != I2C_CLIENT_END; i += 1) { dev_dbg(&adapter->dev, "found normal entry for adapter %d, addr 0x%02x\n", i2c_adapter_id(adapter), address_list[i]); - temp_client.addr = address_list[i]; - err = i2c_detect_address(&temp_client, driver); + temp_client->addr = address_list[i]; + err = i2c_detect_address(temp_client, driver); if (unlikely(err)) break; } + kfree(temp_client); + return err; } -- 2.51.0 From d082ecbc71e9e0bf49883ee4afd435a77a5101b6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 23 Feb 2025 12:32:57 -0800 Subject: [PATCH 08/16] Linux 6.14-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 96407c1d6be1..30dab4c8b012 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From 3ff6c8707c9a0116d00982851ec1216a42053ace Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 26 Feb 2025 17:18:31 +1100 Subject: [PATCH 09/16] nfs/vfs: discard d_exact_alias() d_exact_alias() is a descendent of d_add_unique() which was introduced 20 years ago mostly likely to work around problems with NFS servers of the time. It is now not used in several situations were it was originally needed and there have been no reports of problems - presumably the old NFS servers have been improved. This only place it is now use is in NFSv4 code and the old problematic servers are thought to have been v2/v3 only. There is no clear benefit in reusing a unhashed() dentry which happens to have the same name as the dentry we are adding. So this patch removes d_exact_alias() and the one place that it is used. Cc: Trond Myklebust Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250226062135.2043651-2-neilb@suse.de Signed-off-by: Christian Brauner --- fs/dcache.c | 46 ------------------------------------------ fs/nfs/nfs4proc.c | 4 +--- include/linux/dcache.h | 1 - 3 files changed, 1 insertion(+), 50 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index e3634916ffb9..726a5be2747b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2687,52 +2687,6 @@ void d_add(struct dentry *entry, struct inode *inode) } EXPORT_SYMBOL(d_add); -/** - * d_exact_alias - find and hash an exact unhashed alias - * @entry: dentry to add - * @inode: The inode to go with this dentry - * - * If an unhashed dentry with the same name/parent and desired - * inode already exists, hash and return it. Otherwise, return - * NULL. - * - * Parent directory should be locked. - */ -struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) -{ - struct dentry *alias; - unsigned int hash = entry->d_name.hash; - - spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - /* - * Don't need alias->d_lock here, because aliases with - * d_parent == entry->d_parent are not subject to name or - * parent changes, because the parent inode i_mutex is held. - */ - if (alias->d_name.hash != hash) - continue; - if (alias->d_parent != entry->d_parent) - continue; - if (!d_same_name(alias, entry->d_parent, &entry->d_name)) - continue; - spin_lock(&alias->d_lock); - if (!d_unhashed(alias)) { - spin_unlock(&alias->d_lock); - alias = NULL; - } else { - dget_dlock(alias); - __d_rehash(alias); - spin_unlock(&alias->d_lock); - } - spin_unlock(&inode->i_lock); - return alias; - } - spin_unlock(&inode->i_lock); - return NULL; -} -EXPORT_SYMBOL(d_exact_alias); - static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index df9669d4ded7..0a46b193f18e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3153,9 +3153,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, if (d_really_is_negative(dentry)) { struct dentry *alias; d_drop(dentry); - alias = d_exact_alias(dentry, state->inode); - if (!alias) - alias = d_splice_alias(igrab(state->inode), dentry); + alias = d_splice_alias(igrab(state->inode), dentry); /* d_splice_alias() can't fail here - it's a non-directory */ if (alias) { dput(ctx->dentry); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4afb60365675..8a63978187a4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -253,7 +253,6 @@ extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); -extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); -- 2.51.0 From 4cf006b739958942ee8b59b22c057681c65a9be6 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 26 Feb 2025 17:18:32 +1100 Subject: [PATCH 10/16] nfsd: drop fh_update() from S_IFDIR branch of nfsd_create_locked() nfsd_create_locked() doesn't need to explicitly call fh_update(). On success (which is the only time that fh_update() matters at all), nfsd_create_setattr() will be called and it will call fh_update(). This extra call is not harmful, but is not necessary. Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250226062135.2043651-3-neilb@suse.de Signed-off-by: Christian Brauner --- fs/nfsd/vfs.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 29cb7b812d71..1035010f1198 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1505,11 +1505,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, } dput(resfhp->fh_dentry); resfhp->fh_dentry = dget(d); - err = fh_update(resfhp); dput(dchild); dchild = d; - if (err) - goto out; } break; case S_IFCHR: -- 2.51.0 From 88d5baf69082e5b410296435008329676b687549 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 27 Feb 2025 12:32:53 +1100 Subject: [PATCH 11/16] Change inode_operations.mkdir to return struct dentry * Some filesystems, such as NFS, cifs, ceph, and fuse, do not have complete control of sequencing on the actual filesystem (e.g. on a different server) and may find that the inode created for a mkdir request already exists in the icache and dcache by the time the mkdir request returns. For example, if the filesystem is mounted twice the directory could be visible on the other mount before it is on the original mount, and a pair of name_to_handle_at(), open_by_handle_at() calls could instantiate the directory inode with an IS_ROOT() dentry before the first mkdir returns. This means that the dentry passed to ->mkdir() may not be the one that is associated with the inode after the ->mkdir() completes. Some callers need to interact with the inode after the ->mkdir completes and they currently need to perform a lookup in the (rare) case that the dentry is no longer hashed. This lookup-after-mkdir requires that the directory remains locked to avoid races. Planned future patches to lock the dentry rather than the directory will mean that this lookup cannot be performed atomically with the mkdir. To remove this barrier, this patch changes ->mkdir to return the resulting dentry if it is different from the one passed in. Possible returns are: NULL - the directory was created and no other dentry was used ERR_PTR() - an error occurred non-NULL - this other dentry was spliced in This patch only changes file-systems to return "ERR_PTR(err)" instead of "err" or equivalent transformations. Subsequent patches will make further changes to some file-systems to return a correct dentry. Not all filesystems reliably result in a positive hashed dentry: - NFS, cifs, hostfs will sometimes need to perform a lookup of the name to get inode information. Races could result in this returning something different. Note that this lookup is non-atomic which is what we are trying to avoid. Placing the lookup in filesystem code means it only happens when the filesystem has no other option. - kernfs and tracefs leave the dentry negative and the ->revalidate operation ensures that lookup will be called to correctly populate the dentry. This could be fixed but I don't think it is important to any of the users of vfs_mkdir() which look at the dentry. The recommendation to use d_drop();d_splice_alias() is ugly but fits with current practice. A planned future patch will change this. Reviewed-by: Jeff Layton Reviewed-by: Jan Kara Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250227013949.536172-2-neilb@suse.de Signed-off-by: Christian Brauner --- Documentation/filesystems/locking.rst | 2 +- Documentation/filesystems/porting.rst | 19 +++++++++++++++++++ Documentation/filesystems/vfs.rst | 23 +++++++++++++++++++++-- fs/9p/vfs_inode.c | 7 +++---- fs/9p/vfs_inode_dotl.c | 8 ++++---- fs/affs/affs.h | 2 +- fs/affs/namei.c | 8 ++++---- fs/afs/dir.c | 12 ++++++------ fs/autofs/root.c | 14 +++++++------- fs/bad_inode.c | 6 +++--- fs/bcachefs/fs.c | 6 +++--- fs/btrfs/inode.c | 8 ++++---- fs/ceph/dir.c | 8 ++++---- fs/coda/dir.c | 14 +++++++------- fs/configfs/dir.c | 6 +++--- fs/ecryptfs/inode.c | 6 +++--- fs/exfat/namei.c | 8 ++++---- fs/ext2/namei.c | 9 +++++---- fs/ext4/namei.c | 10 +++++----- fs/f2fs/namei.c | 14 +++++++------- fs/fat/namei_msdos.c | 8 ++++---- fs/fat/namei_vfat.c | 8 ++++---- fs/fuse/dir.c | 6 +++--- fs/gfs2/inode.c | 9 +++++---- fs/hfs/dir.c | 10 +++++----- fs/hfsplus/dir.c | 6 +++--- fs/hostfs/hostfs_kern.c | 8 ++++---- fs/hpfs/namei.c | 10 +++++----- fs/hugetlbfs/inode.c | 6 +++--- fs/jffs2/dir.c | 18 +++++++++--------- fs/jfs/namei.c | 8 ++++---- fs/kernfs/dir.c | 12 ++++++------ fs/minix/namei.c | 8 ++++---- fs/namei.c | 15 ++++++++++++--- fs/nfs/dir.c | 8 ++++---- fs/nfs/internal.h | 4 ++-- fs/nilfs2/namei.c | 8 ++++---- fs/ntfs3/namei.c | 8 ++++---- fs/ocfs2/dlmfs/dlmfs.c | 10 +++++----- fs/ocfs2/namei.c | 10 +++++----- fs/omfs/dir.c | 6 +++--- fs/orangefs/namei.c | 8 ++++---- fs/overlayfs/dir.c | 9 +++++---- fs/ramfs/inode.c | 6 +++--- fs/smb/client/cifsfs.h | 4 ++-- fs/smb/client/inode.c | 10 +++++----- fs/sysv/namei.c | 6 +++--- fs/tracefs/inode.c | 10 +++++----- fs/ubifs/dir.c | 10 +++++----- fs/udf/namei.c | 12 ++++++------ fs/ufs/namei.c | 8 ++++---- fs/vboxsf/dir.c | 8 ++++---- fs/xfs/xfs_iops.c | 4 ++-- include/linux/fs.h | 4 ++-- kernel/bpf/inode.c | 8 ++++---- mm/shmem.c | 8 ++++---- security/apparmor/apparmorfs.c | 8 ++++---- 57 files changed, 274 insertions(+), 225 deletions(-) diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index d20a32b77b60..0ec0bb6eb0fb 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -66,7 +66,7 @@ prototypes:: int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 3ed3f39ecf71..fe0581271d5b 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1178,3 +1178,22 @@ these conditions don't require explicit checks: LOOKUP_EXCL now means "target must not exist". It can be combined with LOOK_CREATE or LOOKUP_RENAME_TARGET. + +--- + +** mandatory** + +->mkdir() now returns a 'struct dentry *'. If the created inode is +found to already be in cache and have a dentry (often IS_ROOT()), it will +need to be spliced into the given name in place of the given dentry. +That dentry now needs to be returned. If the original dentry is used, +NULL should be returned. Any error should be returned with +ERR_PTR(). + +In general, filesystems which use d_instantiate_new() to install the new +inode can safely return NULL. Filesystems which may not have an I_NEW inode +should use d_drop();d_splice_alias() and return the result of the latter. + +If a positive dentry cannot be returned for some reason, in-kernel +clients such as cachefiles, nfsd, smb/server may not perform ideally but +will fail-safe. diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 31eea688609a..ae79c30b6c0c 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -495,7 +495,7 @@ As of kernel 2.6.22, the following members are defined: int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, @@ -562,7 +562,26 @@ otherwise noted. ``mkdir`` called by the mkdir(2) system call. Only required if you want to support creating subdirectories. You will probably need to - call d_instantiate() just as you would in the create() method + call d_instantiate_new() just as you would in the create() method. + + If d_instantiate_new() is not used and if the fh_to_dentry() + export operation is provided, or if the storage might be + accessible by another path (e.g. with a network filesystem) + then more care may be needed. Importantly d_instantate() + should not be used with an inode that is no longer I_NEW if there + any chance that the inode could already be attached to a dentry. + This is because of a hard rule in the VFS that a directory must + only ever have one dentry. + + For example, if an NFS filesystem is mounted twice the new directory + could be visible on the other mount before it is on the original + mount, and a pair of name_to_handle_at(), open_by_handle_at() + calls could instantiate the directory inode with an IS_ROOT() + dentry before the first mkdir returns. + + If there is any chance this could happen, then the new inode + should be d_drop()ed and attached with d_splice_alias(). The + returned dentry (if any) should be returned by ->mkdir(). ``rmdir`` called by the rmdir(2) system call. Only required if you want diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 3e68521f4e2f..399d455d50d6 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -669,8 +669,8 @@ v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir, * */ -static int v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int err; u32 perm; @@ -692,8 +692,7 @@ static int v9fs_vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (fid) p9_fid_put(fid); - - return err; + return ERR_PTR(err); } /** diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 143ac03b7425..cc2007be2173 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -350,9 +350,9 @@ out: * */ -static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, - struct inode *dir, struct dentry *dentry, - umode_t omode) +static struct dentry *v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, + struct inode *dir, struct dentry *dentry, + umode_t omode) { int err; struct v9fs_session_info *v9ses; @@ -417,7 +417,7 @@ error: p9_fid_put(fid); v9fs_put_acl(dacl, pacl); p9_fid_put(dfid); - return err; + return ERR_PTR(err); } static int diff --git a/fs/affs/affs.h b/fs/affs/affs.h index e8c2c4535cb3..ac4e9a02910b 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -168,7 +168,7 @@ extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsi extern int affs_unlink(struct inode *dir, struct dentry *dentry); extern int affs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool); -extern int affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, +extern struct dentry *affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 8c154490a2d6..f883be50db12 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -273,7 +273,7 @@ affs_create(struct mnt_idmap *idmap, struct inode *dir, return 0; } -int +struct dentry * affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { @@ -285,7 +285,7 @@ affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, inode = affs_new_inode(dir); if (!inode) - return -ENOSPC; + return ERR_PTR(-ENOSPC); inode->i_mode = S_IFDIR | mode; affs_mode_to_prot(inode); @@ -298,9 +298,9 @@ affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, clear_nlink(inode); mark_inode_dirty(inode); iput(inode); - return error; + return ERR_PTR(error); } - return 0; + return NULL; } int diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 02cbf38e1a77..5bddcc20786e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -33,8 +33,8 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nl loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl); -static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode); +static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); static int afs_unlink(struct inode *dir, struct dentry *dentry); static int afs_link(struct dentry *from, struct inode *dir, @@ -1315,8 +1315,8 @@ static const struct afs_operation_ops afs_mkdir_operation = { /* * create a directory on an AFS filesystem */ -static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); @@ -1328,7 +1328,7 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, op = afs_alloc_operation(NULL, dvnode->volume); if (IS_ERR(op)) { d_drop(dentry); - return PTR_ERR(op); + return ERR_CAST(op); } fscache_use_cookie(afs_vnode_cache(dvnode), true); @@ -1344,7 +1344,7 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, op->ops = &afs_mkdir_operation; ret = afs_do_sync_operation(op); afs_dir_unuse_cookie(dvnode, ret); - return ret; + return ERR_PTR(ret); } /* diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 530d18827e35..174c7205fee4 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -15,8 +15,8 @@ static int autofs_dir_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); static int autofs_dir_unlink(struct inode *, struct dentry *); static int autofs_dir_rmdir(struct inode *, struct dentry *); -static int autofs_dir_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +static struct dentry *autofs_dir_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); static long autofs_root_ioctl(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT static long autofs_root_compat_ioctl(struct file *, @@ -720,9 +720,9 @@ static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) return 0; } -static int autofs_dir_mkdir(struct mnt_idmap *idmap, - struct inode *dir, struct dentry *dentry, - umode_t mode) +static struct dentry *autofs_dir_mkdir(struct mnt_idmap *idmap, + struct inode *dir, struct dentry *dentry, + umode_t mode) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); @@ -739,7 +739,7 @@ static int autofs_dir_mkdir(struct mnt_idmap *idmap, inode = autofs_get_inode(dir->i_sb, S_IFDIR | mode); if (!inode) - return -ENOMEM; + return ERR_PTR(-ENOMEM); d_add(dentry, inode); if (sbi->version < 5) @@ -751,7 +751,7 @@ static int autofs_dir_mkdir(struct mnt_idmap *idmap, inc_nlink(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); - return 0; + return NULL; } /* Get/set timeout ioctl() operation */ diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 316d88da2ce1..0ef9bcb744dd 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -58,10 +58,10 @@ static int bad_inode_symlink(struct mnt_idmap *idmap, return -EIO; } -static int bad_inode_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *bad_inode_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return -EIO; + return ERR_PTR(-EIO); } static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 90ade8f648d9..1c94a680fcce 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -858,10 +858,10 @@ err: return bch2_err_class(ret); } -static int bch2_mkdir(struct mnt_idmap *idmap, - struct inode *vdir, struct dentry *dentry, umode_t mode) +static struct dentry *bch2_mkdir(struct mnt_idmap *idmap, + struct inode *vdir, struct dentry *dentry, umode_t mode) { - return bch2_mknod(idmap, vdir, dentry, mode|S_IFDIR, 0); + return ERR_PTR(bch2_mknod(idmap, vdir, dentry, mode|S_IFDIR, 0)); } static int bch2_rename2(struct mnt_idmap *idmap, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a9322601ab5c..851d3e8a06a7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6739,18 +6739,18 @@ fail: return err; } -static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; inode = new_inode(dir->i_sb); if (!inode) - return -ENOMEM; + return ERR_PTR(-ENOMEM); inode_init_owner(idmap, inode, dir, S_IFDIR | mode); inode->i_op = &btrfs_dir_inode_operations; inode->i_fop = &btrfs_dir_file_operations; - return btrfs_create_common(dir, dentry, inode); + return ERR_PTR(btrfs_create_common(dir, dentry, inode)); } static noinline int uncompress_inline(struct btrfs_path *path, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 62e99e65250d..39e0f240de06 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1092,8 +1092,8 @@ out: return err; } -static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_client *cl = mdsc->fsc->client; @@ -1104,7 +1104,7 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, err = ceph_wait_on_conflict_unlink(dentry); if (err) - return err; + return ERR_PTR(err); if (ceph_snap(dir) == CEPH_SNAPDIR) { /* mkdir .snap/foo is a MKSNAP */ @@ -1173,7 +1173,7 @@ out: else d_drop(dentry); ceph_release_acl_sec_ctx(&as_ctx); - return err; + return ERR_PTR(err); } static int ceph_link(struct dentry *old_dentry, struct inode *dir, diff --git a/fs/coda/dir.c b/fs/coda/dir.c index a3e2dfeedfbf..ab69d8f0cec2 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -166,8 +166,8 @@ err_out: return error; } -static int coda_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *de, umode_t mode) +static struct dentry *coda_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *de, umode_t mode) { struct inode *inode; struct coda_vattr attrs; @@ -177,14 +177,14 @@ static int coda_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct CodaFid newfid; if (is_root_inode(dir) && coda_iscontrol(name, len)) - return -EPERM; + return ERR_PTR(-EPERM); attrs.va_mode = mode; - error = venus_mkdir(dir->i_sb, coda_i2f(dir), + error = venus_mkdir(dir->i_sb, coda_i2f(dir), name, len, &newfid, &attrs); if (error) goto err_out; - + inode = coda_iget(dir->i_sb, &newfid, &attrs); if (IS_ERR(inode)) { error = PTR_ERR(inode); @@ -195,10 +195,10 @@ static int coda_mkdir(struct mnt_idmap *idmap, struct inode *dir, coda_dir_inc_nlink(dir); coda_dir_update_mtime(dir); d_instantiate(de, inode); - return 0; + return NULL; err_out: d_drop(de); - return error; + return ERR_PTR(error); } /* try to make de an entry in dir_inodde linked to source_de */ diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 7d10278db30d..5568cb74b322 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1280,8 +1280,8 @@ out_root_unlock: } EXPORT_SYMBOL(configfs_depend_item_unlocked); -static int configfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *configfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int ret = 0; int module_got = 0; @@ -1461,7 +1461,7 @@ out_put: put_fragment(frag); out: - return ret; + return ERR_PTR(ret); } static int configfs_rmdir(struct inode *dir, struct dentry *dentry) diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index a9819ddb1ab8..6315dd194228 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -503,8 +503,8 @@ out_lock: return rc; } -static int ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int rc; struct dentry *lower_dentry; @@ -526,7 +526,7 @@ out: inode_unlock(lower_dir); if (d_really_is_negative(dentry)) d_drop(dentry); - return rc; + return ERR_PTR(rc); } static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 691dd77b6ab5..1660c9bbcfa9 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -835,8 +835,8 @@ unlock: return err; } -static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -846,7 +846,7 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, loff_t size = i_size_read(dir); if (unlikely(exfat_forced_shutdown(sb))) - return -EIO; + return ERR_PTR(-EIO); mutex_lock(&EXFAT_SB(sb)->s_lock); exfat_set_volume_dirty(sb); @@ -877,7 +877,7 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); - return err; + return ERR_PTR(err); } static int exfat_check_dir_empty(struct super_block *sb, diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 8346ab9534c1..bde617a66cec 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -225,15 +225,16 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, return err; } -static int ext2_mkdir(struct mnt_idmap * idmap, - struct inode * dir, struct dentry * dentry, umode_t mode) +static struct dentry *ext2_mkdir(struct mnt_idmap * idmap, + struct inode * dir, struct dentry * dentry, + umode_t mode) { struct inode * inode; int err; err = dquot_initialize(dir); if (err) - return err; + return ERR_PTR(err); inode_inc_link_count(dir); @@ -258,7 +259,7 @@ static int ext2_mkdir(struct mnt_idmap * idmap, d_instantiate_new(dentry, inode); out: - return err; + return ERR_PTR(err); out_fail: inode_dec_link_count(inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 536d56d15072..716cc6096870 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3004,19 +3004,19 @@ out: return err; } -static int ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { handle_t *handle; struct inode *inode; int err, err2 = 0, credits, retries = 0; if (EXT4_DIR_LINK_MAX(dir)) - return -EMLINK; + return ERR_PTR(-EMLINK); err = dquot_initialize(dir); if (err) - return err; + return ERR_PTR(err); credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3); @@ -3066,7 +3066,7 @@ out_stop: out_retry: if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; - return err; + return ERR_PTR(err); } /* diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a278c7da8177..24dca4dc85a9 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -684,23 +684,23 @@ out_free_encrypted_link: return err; } -static int f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; int err; if (unlikely(f2fs_cp_error(sbi))) - return -EIO; + return ERR_PTR(-EIO); err = f2fs_dquot_initialize(dir); if (err) - return err; + return ERR_PTR(err); inode = f2fs_new_inode(idmap, dir, S_IFDIR | mode, NULL); if (IS_ERR(inode)) - return PTR_ERR(inode); + return ERR_CAST(inode); inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; @@ -722,12 +722,12 @@ static int f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir, f2fs_sync_fs(sbi->sb, 1); f2fs_balance_fs(sbi, true); - return 0; + return NULL; out_fail: clear_inode_flag(inode, FI_INC_LINK); f2fs_handle_failed_inode(inode); - return err; + return ERR_PTR(err); } static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index f06f6ba643cc..23e9b9371ec3 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -339,8 +339,8 @@ out: } /***** Make a directory */ -static int msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -389,13 +389,13 @@ static int msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir, mutex_unlock(&MSDOS_SB(sb)->s_lock); fat_flush_inodes(sb, dir, inode); - return 0; + return NULL; out_free: fat_free_clusters(dir, cluster); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); - return err; + return ERR_PTR(err); } /***** Unlink a file */ diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 926c26e90ef8..dd910edd2404 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -841,8 +841,8 @@ out: return err; } -static int vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; @@ -877,13 +877,13 @@ static int vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); mutex_unlock(&MSDOS_SB(sb)->s_lock); - return 0; + return NULL; out_free: fat_free_clusters(dir, cluster); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); - return err; + return ERR_PTR(err); } static int vfat_get_dotdot_de(struct inode *inode, struct buffer_head **bh, diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 198862b086ff..5bb65f38bfb8 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -898,8 +898,8 @@ static int fuse_tmpfile(struct mnt_idmap *idmap, struct inode *dir, return err; } -static int fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *entry, umode_t mode) +static struct dentry *fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *entry, umode_t mode) { struct fuse_mkdir_in inarg; struct fuse_mount *fm = get_fuse_mount(dir); @@ -917,7 +917,7 @@ static int fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir, args.in_args[0].value = &inarg; args.in_args[1].size = entry->d_name.len + 1; args.in_args[1].value = entry->d_name.name; - return create_new_entry(idmap, fm, &args, dir, entry, S_IFDIR); + return ERR_PTR(create_new_entry(idmap, fm, &args, dir, entry, S_IFDIR)); } static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6fbbaaad1cd0..198a8cbaf5e5 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1248,14 +1248,15 @@ static int gfs2_symlink(struct mnt_idmap *idmap, struct inode *dir, * @dentry: The dentry of the new directory * @mode: The mode of the new directory * - * Returns: errno + * Returns: the dentry, or ERR_PTR(errno) */ -static int gfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *gfs2_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir)); - return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0); + + return ERR_PTR(gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0)); } /** diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index b75c26045df4..86a6b317b474 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -219,26 +219,26 @@ static int hfs_create(struct mnt_idmap *idmap, struct inode *dir, * in a directory, given the inode for the parent directory and the * name (and its length) of the new directory. */ -static int hfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *hfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; int res; inode = hfs_new_inode(dir, &dentry->d_name, S_IFDIR | mode); if (!inode) - return -ENOMEM; + return ERR_PTR(-ENOMEM); res = hfs_cat_create(inode->i_ino, dir, &dentry->d_name, inode); if (res) { clear_nlink(inode); hfs_delete_inode(inode); iput(inode); - return res; + return ERR_PTR(res); } d_instantiate(dentry, inode); mark_inode_dirty(inode); - return 0; + return NULL; } /* diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index f5c4b3e31a1c..876bbb80fb4d 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -523,10 +523,10 @@ static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir, return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } -static int hfsplus_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *hfsplus_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); + return ERR_PTR(hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0)); } static int hfsplus_rename(struct mnt_idmap *idmap, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index e0741e468956..ccbb48fe830d 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -679,17 +679,17 @@ static int hostfs_symlink(struct mnt_idmap *idmap, struct inode *ino, return err; } -static int hostfs_mkdir(struct mnt_idmap *idmap, struct inode *ino, - struct dentry *dentry, umode_t mode) +static struct dentry *hostfs_mkdir(struct mnt_idmap *idmap, struct inode *ino, + struct dentry *dentry, umode_t mode) { char *file; int err; if ((file = dentry_name(dentry)) == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); err = do_mkdir(file, mode); __putname(file); - return err; + return ERR_PTR(err); } static int hostfs_rmdir(struct inode *ino, struct dentry *dentry) diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index d0edf9ed33b6..e3cdc421dfba 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -19,8 +19,8 @@ static void hpfs_update_directory_times(struct inode *dir) hpfs_write_inode_nolock(dir); } -static int hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; @@ -35,7 +35,7 @@ static int hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, int r; struct hpfs_dirent dee; int err; - if ((err = hpfs_chk_name(name, &len))) return err==-ENOENT ? -EINVAL : err; + if ((err = hpfs_chk_name(name, &len))) return ERR_PTR(err==-ENOENT ? -EINVAL : err); hpfs_lock(dir->i_sb); err = -ENOSPC; fnode = hpfs_alloc_fnode(dir->i_sb, hpfs_i(dir)->i_dno, &fno, &bh); @@ -112,7 +112,7 @@ static int hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); - return 0; + return NULL; bail3: iput(result); bail2: @@ -123,7 +123,7 @@ bail1: hpfs_free_sectors(dir->i_sb, fno, 1); bail: hpfs_unlock(dir->i_sb); - return err; + return ERR_PTR(err); } static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0fc179a59830..d98caedbb723 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -991,14 +991,14 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, return 0; } -static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int retval = hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); - return retval; + return ERR_PTR(retval); } static int hugetlbfs_create(struct mnt_idmap *idmap, diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 2b2938970da3..dd91f725ded6 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -32,8 +32,8 @@ static int jffs2_link (struct dentry *,struct inode *,struct dentry *); static int jffs2_unlink (struct inode *,struct dentry *); static int jffs2_symlink (struct mnt_idmap *, struct inode *, struct dentry *, const char *); -static int jffs2_mkdir (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); +static struct dentry *jffs2_mkdir (struct mnt_idmap *, struct inode *,struct dentry *, + umode_t); static int jffs2_rmdir (struct inode *,struct dentry *); static int jffs2_mknod (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); @@ -446,8 +446,8 @@ static int jffs2_symlink (struct mnt_idmap *idmap, struct inode *dir_i, } -static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, - struct dentry *dentry, umode_t mode) +static struct dentry *jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, + struct dentry *dentry, umode_t mode) { struct jffs2_inode_info *f, *dir_f; struct jffs2_sb_info *c; @@ -464,7 +464,7 @@ static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, ri = jffs2_alloc_raw_inode(); if (!ri) - return -ENOMEM; + return ERR_PTR(-ENOMEM); c = JFFS2_SB_INFO(dir_i->i_sb); @@ -477,7 +477,7 @@ static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, if (ret) { jffs2_free_raw_inode(ri); - return ret; + return ERR_PTR(ret); } inode = jffs2_new_inode(dir_i, mode, ri); @@ -485,7 +485,7 @@ static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, if (IS_ERR(inode)) { jffs2_free_raw_inode(ri); jffs2_complete_reservation(c); - return PTR_ERR(inode); + return ERR_CAST(inode); } inode->i_op = &jffs2_dir_inode_operations; @@ -584,11 +584,11 @@ static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, jffs2_complete_reservation(c); d_instantiate_new(dentry, inode); - return 0; + return NULL; fail: iget_failed(inode); - return ret; + return ERR_PTR(ret); } static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index fc8ede43afde..65a218eba8fa 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -187,13 +187,13 @@ static int jfs_create(struct mnt_idmap *idmap, struct inode *dip, * dentry - dentry of child directory * mode - create mode (rwxrwxrwx). * - * RETURN: Errors from subroutines + * RETURN: ERR_PTR() of errors from subroutines. * * note: * EACCES: user needs search+write permission on the parent directory */ -static int jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, - struct dentry *dentry, umode_t mode) +static struct dentry *jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, + struct dentry *dentry, umode_t mode) { int rc = 0; tid_t tid; /* transaction id */ @@ -308,7 +308,7 @@ static int jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, out1: jfs_info("jfs_mkdir: rc:%d", rc); - return rc; + return ERR_PTR(rc); } /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 5f0f8b95f44c..d296aad70800 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1230,24 +1230,24 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, return d_splice_alias(inode, dentry); } -static int kernfs_iop_mkdir(struct mnt_idmap *idmap, - struct inode *dir, struct dentry *dentry, - umode_t mode) +static struct dentry *kernfs_iop_mkdir(struct mnt_idmap *idmap, + struct inode *dir, struct dentry *dentry, + umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) - return -EPERM; + return ERR_PTR(-EPERM); if (!kernfs_get_active(parent)) - return -ENODEV; + return ERR_PTR(-ENODEV); ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); - return ret; + return ERR_PTR(ret); } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 5d9c1406fe27..8938536d8d3c 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -104,15 +104,15 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int minix_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *minix_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode * inode; int err; inode = minix_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) - return PTR_ERR(inode); + return ERR_CAST(inode); inode_inc_link_count(dir); minix_set_inode(inode, 0); @@ -128,7 +128,7 @@ static int minix_mkdir(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); out: - return err; + return ERR_PTR(err); out_fail: inode_dec_link_count(inode); diff --git a/fs/namei.c b/fs/namei.c index b7cdca902803..48880fc38d1b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4293,6 +4293,7 @@ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, { int error; unsigned max_links = dir->i_sb->s_max_links; + struct dentry *de; error = may_create(idmap, dir, dentry); if (error) @@ -4309,10 +4310,18 @@ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (max_links && dir->i_nlink >= max_links) return -EMLINK; - error = dir->i_op->mkdir(idmap, dir, dentry, mode); - if (!error) + de = dir->i_op->mkdir(idmap, dir, dentry, mode); + if (IS_ERR(de)) + return PTR_ERR(de); + if (de) { + fsnotify_mkdir(dir, de); + /* Cannot return de yet */ + dput(de); + } else { fsnotify_mkdir(dir, dentry); - return error; + } + + return 0; } EXPORT_SYMBOL(vfs_mkdir); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 56cf16a72334..101b1098e87b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2422,8 +2422,8 @@ EXPORT_SYMBOL_GPL(nfs_mknod); /* * See comments for nfs_proc_create regarding failed operations. */ -int nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +struct dentry *nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct iattr attr; int error; @@ -2439,10 +2439,10 @@ int nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, trace_nfs_mkdir_exit(dir, dentry, error); if (error != 0) goto out_err; - return 0; + return NULL; out_err: d_drop(dentry); - return error; + return ERR_PTR(error); } EXPORT_SYMBOL_GPL(nfs_mkdir); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index fae2c7ae4acc..1ac1d3eec517 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -400,8 +400,8 @@ struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, - umode_t); +struct dentry *nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, + umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 953fbd5f0851..40f4b1a28705 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -218,8 +218,8 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, return err; } -static int nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct nilfs_transaction_info ti; @@ -227,7 +227,7 @@ static int nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) - return err; + return ERR_PTR(err); inc_nlink(dir); @@ -258,7 +258,7 @@ out: else nilfs_transaction_abort(dir->i_sb); - return err; + return ERR_PTR(err); out_fail: drop_nlink(inode); diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index abf7e81584a9..652735a0b0c4 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -201,11 +201,11 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, /* * ntfs_mkdir- inode_operations::mkdir */ -static int ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, - NULL, 0, NULL); + return ERR_PTR(ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, + NULL, 0, NULL)); } /* diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 2a7f36643895..5130ec44e5e1 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -402,10 +402,10 @@ static struct inode *dlmfs_get_inode(struct inode *parent, * File creation. Allocate an inode, and we're done.. */ /* SMP-safe */ -static int dlmfs_mkdir(struct mnt_idmap * idmap, - struct inode * dir, - struct dentry * dentry, - umode_t mode) +static struct dentry *dlmfs_mkdir(struct mnt_idmap * idmap, + struct inode * dir, + struct dentry * dentry, + umode_t mode) { int status; struct inode *inode = NULL; @@ -448,7 +448,7 @@ static int dlmfs_mkdir(struct mnt_idmap * idmap, bail: if (status < 0) iput(inode); - return status; + return ERR_PTR(status); } static int dlmfs_create(struct mnt_idmap *idmap, diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 0ec63a1a94b8..99278c8f0e24 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -644,10 +644,10 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, suballoc_loc, suballoc_bit); } -static int ocfs2_mkdir(struct mnt_idmap *idmap, - struct inode *dir, - struct dentry *dentry, - umode_t mode) +static struct dentry *ocfs2_mkdir(struct mnt_idmap *idmap, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { int ret; @@ -657,7 +657,7 @@ static int ocfs2_mkdir(struct mnt_idmap *idmap, if (ret) mlog_errno(ret); - return ret; + return ERR_PTR(ret); } static int ocfs2_create(struct mnt_idmap *idmap, diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index 6bda275826d6..2ed541fccf33 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -279,10 +279,10 @@ out_free_inode: return err; } -static int omfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *omfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return omfs_add_node(dir, dentry, mode | S_IFDIR); + return ERR_PTR(omfs_add_node(dir, dentry, mode | S_IFDIR)); } static int omfs_create(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index 200558ec72f0..82395fe2b956 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -300,8 +300,8 @@ out: return ret; } -static int orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct orangefs_inode_s *parent = ORANGEFS_I(dir); struct orangefs_kernel_op_s *new_op; @@ -312,7 +312,7 @@ static int orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, new_op = op_alloc(ORANGEFS_VFS_OP_MKDIR); if (!new_op) - return -ENOMEM; + return ERR_PTR(-ENOMEM); new_op->upcall.req.mkdir.parent_refn = parent->refn; @@ -366,7 +366,7 @@ static int orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, __orangefs_setattr(dir, &iattr); out: op_release(new_op); - return ret; + return ERR_PTR(ret); } static int orangefs_rename(struct mnt_idmap *idmap, diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index c9993ff66fc2..21c3aaf7b274 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -282,7 +282,8 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode, * XXX: if we ever use ovl_obtain_alias() to decode directory * file handles, need to use ovl_get_inode_locked() and * d_instantiate_new() here to prevent from creating two - * hashed directory inode aliases. + * hashed directory inode aliases. We then need to return + * the obtained alias to ovl_mkdir(). */ inode = ovl_get_inode(dentry->d_sb, &oip); if (IS_ERR(inode)) @@ -687,10 +688,10 @@ static int ovl_create(struct mnt_idmap *idmap, struct inode *dir, return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); } -static int ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { - return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); + return ERR_PTR(ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL)); } static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 8006faaaf0ec..775fa905fda0 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -119,13 +119,13 @@ out: return error; } -static int ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); - return retval; + return ERR_PTR(retval); } static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 831fee962c4d..8dea0cf3a8de 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -59,8 +59,8 @@ extern int cifs_unlink(struct inode *dir, struct dentry *dentry); extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *); extern int cifs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); -extern int cifs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, - umode_t); +extern struct dentry *cifs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, + umode_t); extern int cifs_rmdir(struct inode *, struct dentry *); extern int cifs_rename2(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 616149c7f0a5..3bb21aa58474 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2207,8 +2207,8 @@ posix_mkdir_get_info: } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -int cifs_mkdir(struct mnt_idmap *idmap, struct inode *inode, - struct dentry *direntry, umode_t mode) +struct dentry *cifs_mkdir(struct mnt_idmap *idmap, struct inode *inode, + struct dentry *direntry, umode_t mode) { int rc = 0; unsigned int xid; @@ -2224,10 +2224,10 @@ int cifs_mkdir(struct mnt_idmap *idmap, struct inode *inode, cifs_sb = CIFS_SB(inode->i_sb); if (unlikely(cifs_forced_shutdown(cifs_sb))) - return -EIO; + return ERR_PTR(-EIO); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) - return PTR_ERR(tlink); + return ERR_CAST(tlink); tcon = tlink_tcon(tlink); xid = get_xid(); @@ -2283,7 +2283,7 @@ mkdir_out: free_dentry_path(page); free_xid(xid); cifs_put_tlink(tlink); - return rc; + return ERR_PTR(rc); } int cifs_rmdir(struct inode *inode, struct dentry *direntry) diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index fb8bd8437872..ec02378bb361 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -110,8 +110,8 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, return add_nondir(dentry, inode); } -static int sysv_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *sysv_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode * inode; int err; @@ -137,7 +137,7 @@ static int sysv_mkdir(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); out: - return err; + return ERR_PTR(err); out_fail: inode_dec_link_count(inode); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 53214499e384..cb1af30b49f5 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -109,9 +109,9 @@ static char *get_dname(struct dentry *dentry) return name; } -static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, - struct inode *inode, struct dentry *dentry, - umode_t mode) +static struct dentry *tracefs_syscall_mkdir(struct mnt_idmap *idmap, + struct inode *inode, struct dentry *dentry, + umode_t mode) { struct tracefs_inode *ti; char *name; @@ -119,7 +119,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, name = get_dname(dentry); if (!name) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* * This is a new directory that does not take the default of @@ -141,7 +141,7 @@ static int tracefs_syscall_mkdir(struct mnt_idmap *idmap, kfree(name); - return ret; + return ERR_PTR(ret); } static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index fda82f3e16e8..3c3d3ad4fa6c 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1002,8 +1002,8 @@ out_fname: return err; } -static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct ubifs_inode *dir_ui = ubifs_inode(dir); @@ -1023,7 +1023,7 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, err = ubifs_budget_space(c, &req); if (err) - return err; + return ERR_PTR(err); err = ubifs_prepare_create(dir, dentry, &nm); if (err) @@ -1060,7 +1060,7 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, ubifs_release_budget(c, &req); d_instantiate(dentry, inode); fscrypt_free_filename(&nm); - return 0; + return NULL; out_cancel: dir->i_size -= sz_change; @@ -1074,7 +1074,7 @@ out_fname: fscrypt_free_filename(&nm); out_budg: ubifs_release_budget(c, &req); - return err; + return ERR_PTR(err); } static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir, diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 2cb49b6b0716..5f2e9a892bff 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -419,8 +419,8 @@ static int udf_mknod(struct mnt_idmap *idmap, struct inode *dir, return udf_add_nondir(dentry, inode); } -static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; struct udf_fileident_iter iter; @@ -430,7 +430,7 @@ static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, inode = udf_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) - return PTR_ERR(inode); + return ERR_CAST(inode); iinfo = UDF_I(inode); inode->i_op = &udf_dir_inode_operations; @@ -439,7 +439,7 @@ static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (err) { clear_nlink(inode); discard_new_inode(inode); - return err; + return ERR_PTR(err); } set_nlink(inode, 2); iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); @@ -456,7 +456,7 @@ static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, if (err) { clear_nlink(inode); discard_new_inode(inode); - return err; + return ERR_PTR(err); } iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); @@ -471,7 +471,7 @@ static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, mark_inode_dirty(dir); d_instantiate_new(dentry, inode); - return 0; + return NULL; } static int empty_dir(struct inode *dir) diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 38a024c8cccd..5b3c85c93242 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -166,8 +166,8 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, return error; } -static int ufs_mkdir(struct mnt_idmap * idmap, struct inode * dir, - struct dentry * dentry, umode_t mode) +static struct dentry *ufs_mkdir(struct mnt_idmap * idmap, struct inode * dir, + struct dentry * dentry, umode_t mode) { struct inode * inode; int err; @@ -194,7 +194,7 @@ static int ufs_mkdir(struct mnt_idmap * idmap, struct inode * dir, goto out_fail; d_instantiate_new(dentry, inode); - return 0; + return NULL; out_fail: inode_dec_link_count(inode); @@ -202,7 +202,7 @@ out_fail: discard_new_inode(inode); out_dir: inode_dec_link_count(dir); - return err; + return ERR_PTR(err); } static int ufs_unlink(struct inode *dir, struct dentry *dentry) diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index a859ac9b74ba..770e29ec3557 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -303,11 +303,11 @@ static int vboxsf_dir_mkfile(struct mnt_idmap *idmap, return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL); } -static int vboxsf_dir_mkdir(struct mnt_idmap *idmap, - struct inode *parent, struct dentry *dentry, - umode_t mode) +static struct dentry *vboxsf_dir_mkdir(struct mnt_idmap *idmap, + struct inode *parent, struct dentry *dentry, + umode_t mode) { - return vboxsf_dir_create(parent, dentry, mode, true, true, NULL); + return ERR_PTR(vboxsf_dir_create(parent, dentry, mode, true, true, NULL)); } static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry, diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 40289fe6f5b2..a4480098d2bf 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -298,14 +298,14 @@ xfs_vn_create( return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL); } -STATIC int +STATIC struct dentry * xfs_vn_mkdir( struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - return xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL); + return ERR_PTR(xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL)); } STATIC struct dentry * diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c3b2f8a621f..45269608ee23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2211,8 +2211,8 @@ struct inode_operations { int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9aaf5124648b..dc3aa91a6ba0 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -150,14 +150,14 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } -static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct inode *inode; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) - return PTR_ERR(inode); + return ERR_CAST(inode); inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; @@ -166,7 +166,7 @@ static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, inc_nlink(dir); bpf_dentry_finalize(dentry, inode, dir); - return 0; + return NULL; } struct map_iter { diff --git a/mm/shmem.c b/mm/shmem.c index 4ea6109a8043..00ae0146e768 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3889,16 +3889,16 @@ out_iput: return error; } -static int shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int error; error = shmem_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (error) - return error; + return ERR_PTR(error); inc_nlink(dir); - return 0; + return NULL; } static int shmem_create(struct mnt_idmap *idmap, struct inode *dir, diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index c07d150685d7..6039afae4bfc 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1795,8 +1795,8 @@ fail2: return error; } -static int ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct aa_ns *ns, *parent; /* TODO: improve permission check */ @@ -1808,7 +1808,7 @@ static int ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, AA_MAY_LOAD_POLICY); end_current_label_crit_section(label); if (error) - return error; + return ERR_PTR(error); parent = aa_get_ns(dir->i_private); AA_BUG(d_inode(ns_subns_dir(parent)) != dir); @@ -1843,7 +1843,7 @@ out: mutex_unlock(&parent->lock); aa_put_ns(parent); - return error; + return ERR_PTR(error); } static int ns_rmdir_op(struct inode *dir, struct dentry *dentry) -- 2.51.0 From 3f90030e121201cb274cc4754d7be23099180d25 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 27 Feb 2025 12:32:54 +1100 Subject: [PATCH 12/16] hostfs: store inode in dentry after mkdir if possible. After handling a mkdir, get the inode for the name and use d_splice_alias() to store the correct dentry in the dcache. Reviewed-by: Jeff Layton Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250227013949.536172-3-neilb@suse.de Signed-off-by: Christian Brauner --- fs/hostfs/hostfs_kern.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index ccbb48fe830d..a2c6b9051c5b 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -682,14 +682,22 @@ static int hostfs_symlink(struct mnt_idmap *idmap, struct inode *ino, static struct dentry *hostfs_mkdir(struct mnt_idmap *idmap, struct inode *ino, struct dentry *dentry, umode_t mode) { + struct inode *inode; char *file; int err; if ((file = dentry_name(dentry)) == NULL) return ERR_PTR(-ENOMEM); err = do_mkdir(file, mode); + if (err) { + dentry = ERR_PTR(err); + } else { + inode = hostfs_iget(dentry->d_sb, file); + d_drop(dentry); + dentry = d_splice_alias(inode, dentry); + } __putname(file); - return ERR_PTR(err); + return dentry; } static int hostfs_rmdir(struct inode *ino, struct dentry *dentry) -- 2.51.0 From 3f92c7b57687fb24da46487d91dba7aa58aed75b Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 27 Feb 2025 12:32:55 +1100 Subject: [PATCH 13/16] ceph: return the correct dentry on mkdir ceph already splices the correct dentry (in splice_dentry()) from the result of mkdir but does nothing more with it. Now that ->mkdir can return a dentry, return the correct dentry. Note that previously ceph_mkdir() could call ceph_init_inode_acls() on the inode from the wrong dentry, which would be NULL. This is safe as ceph_init_inode_acls() checks for NULL, but is not strictly correct. With this patch, the inode for the returned dentry is passed to ceph_init_inode_acls(). Reviewed-by: Viacheslav Dubeyko Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250227013949.536172-4-neilb@suse.de Signed-off-by: Christian Brauner --- fs/ceph/dir.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 39e0f240de06..153ea9bf05b9 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1099,6 +1099,7 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct ceph_client *cl = mdsc->fsc->client; struct ceph_mds_request *req; struct ceph_acl_sec_ctx as_ctx = {}; + struct dentry *ret; int err; int op; @@ -1116,32 +1117,32 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, ceph_vinop(dir), dentry, dentry, mode); op = CEPH_MDS_OP_MKDIR; } else { - err = -EROFS; + ret = ERR_PTR(-EROFS); goto out; } if (op == CEPH_MDS_OP_MKDIR && ceph_quota_is_max_files_exceeded(dir)) { - err = -EDQUOT; + ret = ERR_PTR(-EDQUOT); goto out; } if ((op == CEPH_MDS_OP_MKSNAP) && IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir)) { - err = -ENOKEY; + ret = ERR_PTR(-ENOKEY); goto out; } req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); if (IS_ERR(req)) { - err = PTR_ERR(req); + ret = ERR_CAST(req); goto out; } mode |= S_IFDIR; req->r_new_inode = ceph_new_inode(dir, dentry, &mode, &as_ctx); if (IS_ERR(req->r_new_inode)) { - err = PTR_ERR(req->r_new_inode); + ret = ERR_CAST(req->r_new_inode); req->r_new_inode = NULL; goto out_req; } @@ -1165,15 +1166,22 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, !req->r_reply_info.head->is_target && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); + ret = ERR_PTR(err); out_req: + if (!IS_ERR(ret) && req->r_dentry != dentry) + /* Some other dentry was spliced in */ + ret = dget(req->r_dentry); ceph_mdsc_put_request(req); out: - if (!err) + if (!IS_ERR(ret)) { + if (ret) + dentry = ret; ceph_init_inode_acls(d_inode(dentry), &as_ctx); - else + } else { d_drop(dentry); + } ceph_release_acl_sec_ctx(&as_ctx); - return ERR_PTR(err); + return ret; } static int ceph_link(struct dentry *old_dentry, struct inode *dir, -- 2.51.0 From d701902c13dfc40b83b52e41155824c038ac19d2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Mar 2025 08:48:20 +1100 Subject: [PATCH 14/16] fuse: return correct dentry for ->mkdir fuse already uses d_splice_alias() to ensure an appropriate dentry is found for a newly created dentry. Now that ->mkdir can return that dentry we do so. This requires changing create_new_entry() to return a dentry and handling that change in all callers. Note that when create_new_entry() is asked to create anything other than a directory we can be sure it will NOT return an alternate dentry as d_splice_alias() only returns an alternate dentry for directories. So we don't need to check for that case when passing one the result. Reviewed-by: Jeff Layton Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/174112490070.33508.15852253149143067890@noble.neil.brown.name Signed-off-by: Christian Brauner --- fs/fuse/dir.c | 48 +++++++++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 17 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5bb65f38bfb8..a130b8bbdeb7 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -781,9 +781,9 @@ no_open: /* * Code shared between mknod, mkdir, symlink and link */ -static int create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm, - struct fuse_args *args, struct inode *dir, - struct dentry *entry, umode_t mode) +static struct dentry *create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm, + struct fuse_args *args, struct inode *dir, + struct dentry *entry, umode_t mode) { struct fuse_entry_out outarg; struct inode *inode; @@ -792,11 +792,11 @@ static int create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm, struct fuse_forget_link *forget; if (fuse_is_bad(dir)) - return -EIO; + return ERR_PTR(-EIO); forget = fuse_alloc_forget(); if (!forget) - return -ENOMEM; + return ERR_PTR(-ENOMEM); memset(&outarg, 0, sizeof(outarg)); args->nodeid = get_node_id(dir); @@ -826,29 +826,43 @@ static int create_new_entry(struct mnt_idmap *idmap, struct fuse_mount *fm, &outarg.attr, ATTR_TIMEOUT(&outarg), 0, 0); if (!inode) { fuse_queue_forget(fm->fc, forget, outarg.nodeid, 1); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } kfree(forget); d_drop(entry); d = d_splice_alias(inode, entry); if (IS_ERR(d)) - return PTR_ERR(d); + return d; - if (d) { + if (d) fuse_change_entry_timeout(d, &outarg); - dput(d); - } else { + else fuse_change_entry_timeout(entry, &outarg); - } fuse_dir_changed(dir); - return 0; + return d; out_put_forget_req: if (err == -EEXIST) fuse_invalidate_entry(entry); kfree(forget); - return err; + return ERR_PTR(err); +} + +static int create_new_nondir(struct mnt_idmap *idmap, struct fuse_mount *fm, + struct fuse_args *args, struct inode *dir, + struct dentry *entry, umode_t mode) +{ + /* + * Note that when creating anything other than a directory we + * can be sure create_new_entry() will NOT return an alternate + * dentry as d_splice_alias() only returns an alternate dentry + * for directories. So we don't need to check for that case + * when passing back the result. + */ + WARN_ON_ONCE(S_ISDIR(mode)); + + return PTR_ERR(create_new_entry(idmap, fm, args, dir, entry, mode)); } static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir, @@ -871,7 +885,7 @@ static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir, args.in_args[0].value = &inarg; args.in_args[1].size = entry->d_name.len + 1; args.in_args[1].value = entry->d_name.name; - return create_new_entry(idmap, fm, &args, dir, entry, mode); + return create_new_nondir(idmap, fm, &args, dir, entry, mode); } static int fuse_create(struct mnt_idmap *idmap, struct inode *dir, @@ -917,7 +931,7 @@ static struct dentry *fuse_mkdir(struct mnt_idmap *idmap, struct inode *dir, args.in_args[0].value = &inarg; args.in_args[1].size = entry->d_name.len + 1; args.in_args[1].value = entry->d_name.name; - return ERR_PTR(create_new_entry(idmap, fm, &args, dir, entry, S_IFDIR)); + return create_new_entry(idmap, fm, &args, dir, entry, S_IFDIR); } static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, @@ -934,7 +948,7 @@ static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, args.in_args[1].value = entry->d_name.name; args.in_args[2].size = len; args.in_args[2].value = link; - return create_new_entry(idmap, fm, &args, dir, entry, S_IFLNK); + return create_new_nondir(idmap, fm, &args, dir, entry, S_IFLNK); } void fuse_flush_time_update(struct inode *inode) @@ -1131,7 +1145,7 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, args.in_args[0].value = &inarg; args.in_args[1].size = newent->d_name.len + 1; args.in_args[1].value = newent->d_name.name; - err = create_new_entry(&invalid_mnt_idmap, fm, &args, newdir, newent, inode->i_mode); + err = create_new_nondir(&invalid_mnt_idmap, fm, &args, newdir, newent, inode->i_mode); if (!err) fuse_update_ctime_in_cache(inode); else if (err == -EINTR) -- 2.51.0 From 8376583b84a1937196514dbe380917d61af29978 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 27 Feb 2025 12:32:57 +1100 Subject: [PATCH 15/16] nfs: change mkdir inode_operation to return alternate dentry if needed. mkdir now allows a different dentry to be returned which is sometimes relevant for nfs. This patch changes the nfs_rpc_ops mkdir op to return a dentry, and passes that back to the caller. The mkdir nfs_rpc_op will return NULL if the original dentry should be used. This matches the mkdir inode_operation. nfs4_do_create() is duplicated to nfs4_do_mkdir() which is changed to handle the specifics of directories. Consequently the current special handling for directories is removed from nfs4_do_create() Reviewed-by: Jeff Layton Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250227013949.536172-6-neilb@suse.de Signed-off-by: Christian Brauner --- fs/nfs/dir.c | 13 ++++--------- fs/nfs/nfs3proc.c | 29 ++++++++++++++------------- fs/nfs/nfs4proc.c | 43 +++++++++++++++++++++++++++++------------ fs/nfs/proc.c | 12 ++++++++---- include/linux/nfs_xdr.h | 2 +- 5 files changed, 60 insertions(+), 39 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 101b1098e87b..bc957487f6ec 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2426,7 +2426,7 @@ struct dentry *nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct iattr attr; - int error; + struct dentry *ret; dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n", dir->i_sb->s_id, dir->i_ino, dentry); @@ -2435,14 +2435,9 @@ struct dentry *nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, attr.ia_mode = mode | S_IFDIR; trace_nfs_mkdir_enter(dir, dentry); - error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); - trace_nfs_mkdir_exit(dir, dentry, error); - if (error != 0) - goto out_err; - return NULL; -out_err: - d_drop(dentry); - return ERR_PTR(error); + ret = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); + trace_nfs_mkdir_exit(dir, dentry, PTR_ERR_OR_ZERO(ret)); + return ret; } EXPORT_SYMBOL_GPL(nfs_mkdir); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0c3bc98cd999..755ed3c37051 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -578,13 +578,13 @@ out: return status; } -static int +static struct dentry * nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct posix_acl *default_acl, *acl; struct nfs3_createdata *data; - struct dentry *d_alias; - int status = -ENOMEM; + struct dentry *ret = ERR_PTR(-ENOMEM); + int status; dprintk("NFS call mkdir %pd\n", dentry); @@ -592,8 +592,9 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) if (data == NULL) goto out; - status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl); - if (status) + ret = ERR_PTR(posix_acl_create(dir, &sattr->ia_mode, + &default_acl, &acl)); + if (IS_ERR(ret)) goto out; data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR]; @@ -602,25 +603,27 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) data->arg.mkdir.len = dentry->d_name.len; data->arg.mkdir.sattr = sattr; - d_alias = nfs3_do_create(dir, dentry, data); - status = PTR_ERR_OR_ZERO(d_alias); + ret = nfs3_do_create(dir, dentry, data); - if (status != 0) + if (IS_ERR(ret)) goto out_release_acls; - if (d_alias) - dentry = d_alias; + if (ret) + dentry = ret; status = nfs3_proc_setacls(d_inode(dentry), acl, default_acl); + if (status) { + dput(ret); + ret = ERR_PTR(status); + } - dput(d_alias); out_release_acls: posix_acl_release(acl); posix_acl_release(default_acl); out: nfs3_free_createdata(data); - dprintk("NFS reply mkdir: %d\n", status); - return status; + dprintk("NFS reply mkdir: %d\n", PTR_ERR_OR_ZERO(ret)); + return ret; } static int diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0a46b193f18e..d5ce5256b47a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5133,9 +5133,6 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { spin_lock(&dir->i_lock); - /* Creating a directory bumps nlink in the parent */ - if (data->arg.ftype == NF4DIR) - nfs4_inc_nlink_locked(dir); nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo, data->res.fattr->time_start, NFS_INO_INVALID_DATA); @@ -5145,6 +5142,25 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ return status; } +static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry, + struct nfs4_createdata *data) +{ + int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg, + &data->arg.seq_args, &data->res.seq_res, 1); + + if (status) + return ERR_PTR(status); + + spin_lock(&dir->i_lock); + /* Creating a directory bumps nlink in the parent */ + nfs4_inc_nlink_locked(dir); + nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo, + data->res.fattr->time_start, + NFS_INO_INVALID_DATA); + spin_unlock(&dir->i_lock); + return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr); +} + static void nfs4_free_createdata(struct nfs4_createdata *data) { nfs4_label_free(data->fattr.label); @@ -5201,32 +5217,34 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry, return err; } -static int _nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, - struct iattr *sattr, struct nfs4_label *label) +static struct dentry *_nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, + struct iattr *sattr, + struct nfs4_label *label) { struct nfs4_createdata *data; - int status = -ENOMEM; + struct dentry *ret = ERR_PTR(-ENOMEM); data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR); if (data == NULL) goto out; data->arg.label = label; - status = nfs4_do_create(dir, dentry, data); + ret = nfs4_do_mkdir(dir, dentry, data); nfs4_free_createdata(data); out: - return status; + return ret; } -static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, - struct iattr *sattr) +static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, + struct iattr *sattr) { struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { .interruptible = true, }; struct nfs4_label l, *label; + struct dentry *alias; int err; label = nfs4_label_init_security(dir, dentry, sattr, &l); @@ -5234,14 +5252,15 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK)) sattr->ia_mode &= ~current_umask(); do { - err = _nfs4_proc_mkdir(dir, dentry, sattr, label); + alias = _nfs4_proc_mkdir(dir, dentry, sattr, label); + err = PTR_ERR_OR_ZERO(alias); trace_nfs4_mkdir(dir, &dentry->d_name, err); err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } while (exception.retry); nfs4_label_release_security(label); - return err; + return alias; } static int _nfs4_proc_readdir(struct nfs_readdir_arg *nr_arg, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 77920a2e3cef..63e71310b9f6 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -446,13 +446,14 @@ out: return status; } -static int +static struct dentry * nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) { struct nfs_createdata *data; struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_MKDIR], }; + struct dentry *alias = NULL; int status = -ENOMEM; dprintk("NFS call mkdir %pd\n", dentry); @@ -464,12 +465,15 @@ nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); nfs_mark_for_revalidate(dir); - if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); + if (status == 0) { + alias = nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr); + status = PTR_ERR_OR_ZERO(alias); + } else + alias = ERR_PTR(status); nfs_free_createdata(data); out: dprintk("NFS reply mkdir: %d\n", status); - return status; + return alias; } static int diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9155a6ffc370..d66c61cbbd1d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1802,7 +1802,7 @@ struct nfs_rpc_ops { int (*link) (struct inode *, struct inode *, const struct qstr *); int (*symlink) (struct inode *, struct dentry *, struct folio *, unsigned int, struct iattr *); - int (*mkdir) (struct inode *, struct dentry *, struct iattr *); + struct dentry *(*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *); int (*mknod) (struct inode *, struct dentry *, struct iattr *, -- 2.51.0 From c54b386969a58151765a9ffaaa0438e7b580283f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 27 Feb 2025 12:32:58 +1100 Subject: [PATCH 16/16] VFS: Change vfs_mkdir() to return the dentry. vfs_mkdir() does not guarantee to leave the child dentry hashed or make it positive on success, and in many such cases the filesystem had to use a different dentry which it can now return. This patch changes vfs_mkdir() to return the dentry provided by the filesystems which is hashed and positive when provided. This reduces the number of cases where the resulting dentry is not positive to a handful which don't deserve extra efforts. The only callers of vfs_mkdir() which are interested in the resulting inode are in-kernel filesystem clients: cachefiles, nfsd, smb/server. The only filesystems that don't reliably provide the inode are: - kernfs, tracefs which these clients are unlikely to be interested in - cifs in some configurations would need to do a lookup to find the created inode, but doesn't. cifs cannot be exported via NFS, is unlikely to be used by cachefiles, and smb/server only has a soft requirement for the inode, so this is unlikely to be a problem in practice. - hostfs, nfs, cifs may need to do a lookup (rarely for NFS) and it is possible for a race to make that lookup fail. Actual failure is unlikely and providing callers handle negative dentries graceful they will fail-safe. So this patch removes the lookup code in nfsd and smb/server and adjusts them to fail safe if a negative dentry is provided: - cache-files already fails safe by restarting the task from the top - it still does with this change, though it no longer calls cachefiles_put_directory() as that will crash if the dentry is negative. - nfsd reports "Server-fault" which it what it used to do if the lookup failed. This will never happen on any file-systems that it can actually export, so this is of no consequence. I removed the fh_update() call as that is not needed and out-of-place. A subsequent nfsd_create_setattr() call will call fh_update() when needed. - smb/server only wants the inode to call ksmbd_smb_inherit_owner() which updates ->i_uid (without calling notify_change() or similar) which can be safely skipping on cifs (I hope). If a different dentry is returned, the first one is put. If necessary the fact that it is new can be determined by comparing pointers. A new dentry will certainly have a new pointer (as the old is put after the new is obtained). Similarly if an error is returned (via ERR_PTR()) the original dentry is put. Reviewed-by: Jeff Layton Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/20250227013949.536172-7-neilb@suse.de Signed-off-by: Christian Brauner --- drivers/base/devtmpfs.c | 7 +++---- fs/cachefiles/namei.c | 16 +++++++------- fs/ecryptfs/inode.c | 14 +++++++++---- fs/init.c | 7 +++++-- fs/namei.c | 45 ++++++++++++++++++++++++++-------------- fs/nfsd/nfs4recover.c | 7 +++++-- fs/nfsd/vfs.c | 31 ++++++++++----------------- fs/overlayfs/dir.c | 37 ++++----------------------------- fs/overlayfs/overlayfs.h | 15 +++++++------- fs/overlayfs/super.c | 7 ++++--- fs/smb/server/vfs.c | 32 +++++++++------------------- fs/xfs/scrub/orphanage.c | 9 ++++---- include/linux/fs.h | 4 ++-- 13 files changed, 104 insertions(+), 127 deletions(-) diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index c9e34842139f..8ec756b5dec4 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -160,18 +160,17 @@ static int dev_mkdir(const char *name, umode_t mode) { struct dentry *dentry; struct path path; - int err; dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY); if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode); - if (!err) + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode); + if (!IS_ERR(dentry)) /* mark as kernel-created inode */ d_inode(dentry)->i_private = &thread; done_path_create(&path, dentry); - return err; + return PTR_ERR_OR_ZERO(dentry); } static int create_path(const char *nodepath) diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 7cf59713f0f7..83a60126de0f 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -128,18 +128,19 @@ retry: ret = security_path_mkdir(&path, subdir, 0700); if (ret < 0) goto mkdir_error; - ret = cachefiles_inject_write_error(); - if (ret == 0) - ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); - if (ret < 0) { + subdir = ERR_PTR(cachefiles_inject_write_error()); + if (!IS_ERR(subdir)) + subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); + ret = PTR_ERR(subdir); + if (IS_ERR(subdir)) { trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, cachefiles_trace_mkdir_error); goto mkdir_error; } trace_cachefiles_mkdir(dir, subdir); - if (unlikely(d_unhashed(subdir))) { - cachefiles_put_directory(subdir); + if (unlikely(d_unhashed(subdir) || d_is_negative(subdir))) { + dput(subdir); goto retry; } ASSERT(d_backing_inode(subdir)); @@ -195,7 +196,8 @@ mark_error: mkdir_error: inode_unlock(d_inode(dir)); - dput(subdir); + if (!IS_ERR(subdir)) + dput(subdir); pr_err("mkdir %s failed with error %d\n", dirname, ret); return ERR_PTR(ret); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 6315dd194228..51a5c54eb740 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -511,10 +511,16 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct inode *lower_dir; rc = lock_parent(dentry, &lower_dentry, &lower_dir); - if (!rc) - rc = vfs_mkdir(&nop_mnt_idmap, lower_dir, - lower_dentry, mode); - if (rc || d_really_is_negative(lower_dentry)) + if (rc) + goto out; + + lower_dentry = vfs_mkdir(&nop_mnt_idmap, lower_dir, + lower_dentry, mode); + rc = PTR_ERR(lower_dentry); + if (IS_ERR(lower_dentry)) + goto out; + rc = 0; + if (d_unhashed(lower_dentry)) goto out; rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb); if (rc) diff --git a/fs/init.c b/fs/init.c index e9387b6c4f30..eef5124885e3 100644 --- a/fs/init.c +++ b/fs/init.c @@ -230,9 +230,12 @@ int __init init_mkdir(const char *pathname, umode_t mode) return PTR_ERR(dentry); mode = mode_strip_umask(d_inode(path.dentry), mode); error = security_path_mkdir(&path, dentry, mode); - if (!error) - error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, + if (!error) { + dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode); + if (IS_ERR(dentry)) + error = PTR_ERR(dentry); + } done_path_create(&path, dentry); return error; } diff --git a/fs/namei.c b/fs/namei.c index 48880fc38d1b..b5abf456c5f4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4128,7 +4128,8 @@ EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { - dput(dentry); + if (!IS_ERR(dentry)) + dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); @@ -4274,7 +4275,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d } /** - * vfs_mkdir - create directory + * vfs_mkdir - create directory returning correct dentry if possible * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory @@ -4287,9 +4288,15 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. + * + * In the event that the filesystem does not use the *@dentry but leaves it + * negative or unhashes it and possibly splices a different one returning it, + * the original dentry is dput() and the alternate is returned. + * + * In case of an error the dentry is dput() and an ERR_PTR() is returned. */ -int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode) +struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { int error; unsigned max_links = dir->i_sb->s_max_links; @@ -4297,31 +4304,35 @@ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, error = may_create(idmap, dir, dentry); if (error) - return error; + goto err; + error = -EPERM; if (!dir->i_op->mkdir) - return -EPERM; + goto err; mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) - return error; + goto err; + error = -EMLINK; if (max_links && dir->i_nlink >= max_links) - return -EMLINK; + goto err; de = dir->i_op->mkdir(idmap, dir, dentry, mode); + error = PTR_ERR(de); if (IS_ERR(de)) - return PTR_ERR(de); + goto err; if (de) { - fsnotify_mkdir(dir, de); - /* Cannot return de yet */ - dput(de); - } else { - fsnotify_mkdir(dir, dentry); + dput(dentry); + dentry = de; } + fsnotify_mkdir(dir, dentry); + return dentry; - return 0; +err: + dput(dentry); + return ERR_PTR(error); } EXPORT_SYMBOL(vfs_mkdir); @@ -4341,8 +4352,10 @@ retry: error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { - error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, + dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry, mode); + if (IS_ERR(dentry)) + error = PTR_ERR(dentry); } done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 28f4d5311c40..c1d9bd07285f 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -233,9 +233,12 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - status = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); + dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); + if (IS_ERR(dentry)) + status = PTR_ERR(dentry); out_put: - dput(dentry); + if (!status) + dput(dentry); out_unlock: inode_unlock(d_inode(dir)); if (status == 0) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 1035010f1198..34d7aa531662 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1461,7 +1461,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, struct inode *dirp; struct iattr *iap = attrs->na_iattr; __be32 err; - int host_err; + int host_err = 0; dentry = fhp->fh_dentry; dirp = d_inode(dentry); @@ -1488,25 +1488,15 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); - if (!host_err && unlikely(d_unhashed(dchild))) { - struct dentry *d; - d = lookup_one_len(dchild->d_name.name, - dchild->d_parent, - dchild->d_name.len); - if (IS_ERR(d)) { - host_err = PTR_ERR(d); - break; - } - if (unlikely(d_is_negative(d))) { - dput(d); - err = nfserr_serverfault; - goto out; - } + dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); + if (IS_ERR(dchild)) { + host_err = PTR_ERR(dchild); + } else if (d_is_negative(dchild)) { + err = nfserr_serverfault; + goto out; + } else if (unlikely(dchild != resfhp->fh_dentry)) { dput(resfhp->fh_dentry); - resfhp->fh_dentry = dget(d); - dput(dchild); - dchild = d; + resfhp->fh_dentry = dget(dchild); } break; case S_IFCHR: @@ -1527,7 +1517,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs); out: - dput(dchild); + if (!IS_ERR(dchild)) + dput(dchild); return err; out_nfserr: diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 21c3aaf7b274..fe493f3ed6b6 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -138,37 +138,6 @@ kill_whiteout: goto out; } -int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir, - struct dentry **newdentry, umode_t mode) -{ - int err; - struct dentry *d, *dentry = *newdentry; - - err = ovl_do_mkdir(ofs, dir, dentry, mode); - if (err) - return err; - - if (likely(!d_unhashed(dentry))) - return 0; - - /* - * vfs_mkdir() may succeed and leave the dentry passed - * to it unhashed and negative. If that happens, try to - * lookup a new hashed and positive dentry. - */ - d = ovl_lookup_upper(ofs, dentry->d_name.name, dentry->d_parent, - dentry->d_name.len); - if (IS_ERR(d)) { - pr_warn("failed lookup after mkdir (%pd2, err=%i).\n", - dentry, err); - return PTR_ERR(d); - } - dput(dentry); - *newdentry = d; - - return 0; -} - struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr) { @@ -191,7 +160,8 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir, case S_IFDIR: /* mkdir is special... */ - err = ovl_mkdir_real(ofs, dir, &newdentry, attr->mode); + newdentry = ovl_do_mkdir(ofs, dir, newdentry, attr->mode); + err = PTR_ERR_OR_ZERO(newdentry); break; case S_IFCHR: @@ -219,7 +189,8 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir, } out: if (err) { - dput(newdentry); + if (!IS_ERR(newdentry)) + dput(newdentry); return ERR_PTR(err); } return newdentry; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0021e2025020..6f2f8f4cfbbc 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -241,13 +241,14 @@ static inline int ovl_do_create(struct ovl_fs *ofs, return err; } -static inline int ovl_do_mkdir(struct ovl_fs *ofs, - struct inode *dir, struct dentry *dentry, - umode_t mode) +static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs, + struct inode *dir, + struct dentry *dentry, + umode_t mode) { - int err = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); - pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err); - return err; + dentry = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode); + pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(dentry)); + return dentry; } static inline int ovl_do_mknod(struct ovl_fs *ofs, @@ -838,8 +839,6 @@ struct ovl_cattr { #define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) }) -int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir, - struct dentry **newdentry, umode_t mode); struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 86ae6f6da36b..a381765802e9 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -327,9 +327,10 @@ retry: goto retry; } - err = ovl_mkdir_real(ofs, dir, &work, attr.ia_mode); - if (err) - goto out_dput; + work = ovl_do_mkdir(ofs, dir, work, attr.ia_mode); + err = PTR_ERR(work); + if (IS_ERR(work)) + goto out_err; /* Weird filesystem returning with hashed negative (kernfs)? */ err = -EINVAL; diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index fe29acef5872..8554aa5a1059 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -206,8 +206,8 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) { struct mnt_idmap *idmap; struct path path; - struct dentry *dentry; - int err; + struct dentry *dentry, *d; + int err = 0; dentry = ksmbd_vfs_kern_path_create(work, name, LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, @@ -222,27 +222,15 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; - err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); - if (!err && d_unhashed(dentry)) { - struct dentry *d; - - d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent, - dentry->d_name.len); - if (IS_ERR(d)) { - err = PTR_ERR(d); - goto out_err; - } - if (unlikely(d_is_negative(d))) { - dput(d); - err = -ENOENT; - goto out_err; - } - - ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d)); - dput(d); - } + d = dentry; + dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); + if (IS_ERR(dentry)) + err = PTR_ERR(dentry); + else if (d_is_negative(dentry)) + err = -ENOENT; + if (!err && dentry != d) + ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(dentry)); -out_err: done_path_create(&path, dentry); if (err) pr_err("mkdir(%s): creation failed (err:%d)\n", name, err); diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c index c287c755f2c5..3537f3cca6d5 100644 --- a/fs/xfs/scrub/orphanage.c +++ b/fs/xfs/scrub/orphanage.c @@ -167,10 +167,11 @@ xrep_orphanage_create( * directory to control access to a file we put in here. */ if (d_really_is_negative(orphanage_dentry)) { - error = vfs_mkdir(&nop_mnt_idmap, root_inode, orphanage_dentry, - 0750); - if (error) - goto out_dput_orphanage; + orphanage_dentry = vfs_mkdir(&nop_mnt_idmap, root_inode, + orphanage_dentry, 0750); + error = PTR_ERR(orphanage_dentry); + if (IS_ERR(orphanage_dentry)) + goto out_unlock_root; } /* Not a directory? Bail out. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 45269608ee23..beae24bc990d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1981,8 +1981,8 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap, */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, -- 2.51.0