OpenCloudOS-Kernel/fs/kernfs/file.c

1038 lines
26 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/kernfs/file.c - kernfs file implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
*/
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>
#include "kernfs-internal.h"
/*
* There's one kernfs_open_file for each open file and one kernfs_open_node
* for each kernfs_node with one or more open files.
*
* kernfs_node->attr.open points to kernfs_open_node. attr.open is
* protected by kernfs_open_node_lock.
*
* filp->private_data points to seq_file whose ->private points to
* kernfs_open_file. kernfs_open_files are chained at
* kernfs_open_node->files, which is protected by kernfs_open_file_mutex.
*/
static DEFINE_SPINLOCK(kernfs_open_node_lock);
static DEFINE_MUTEX(kernfs_open_file_mutex);
struct kernfs_open_node {
atomic_t refcnt;
atomic_t event;
wait_queue_head_t poll;
struct list_head files; /* goes through kernfs_open_file.list */
};
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
/*
* kernfs_notify() may be called from any context and bounces notifications
* through a work item. To minimize space overhead in kernfs_node, the
* pending queue is implemented as a singly linked list of kernfs_nodes.
* The list is terminated with the self pointer so that whether a
* kernfs_node is on the list or not can be determined by testing the next
* pointer for NULL.
*/
#define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list)
static DEFINE_SPINLOCK(kernfs_notify_lock);
static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;
static struct kernfs_open_file *kernfs_of(struct file *file)
{
return ((struct seq_file *)file->private_data)->private;
}
/*
* Determine the kernfs_ops for the given kernfs_node. This function must
* be called while holding an active reference.
*/
static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
{
if (kn->flags & KERNFS_LOCKDEP)
lockdep_assert_held(kn);
return kn->attr.ops;
}
/*
* As kernfs_seq_stop() is also called after kernfs_seq_start() or
* kernfs_seq_next() failure, it needs to distinguish whether it's stopping
* a seq_file iteration which is fully initialized with an active reference
* or an aborted kernfs_seq_start() due to get_active failure. The
* position pointer is the only context for each seq_file iteration and
* thus the stop condition should be encoded in it. As the return value is
* directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
* choice to indicate get_active failure.
*
* Unfortunately, this is complicated due to the optional custom seq_file
* operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop()
* can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
* custom seq_file operations and thus can't decide whether put_active
* should be performed or not only on ERR_PTR(-ENODEV).
*
* This is worked around by factoring out the custom seq_stop() and
* put_active part into kernfs_seq_stop_active(), skipping it from
* kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
* custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
* that kernfs_seq_stop_active() is skipped only after get_active failure.
*/
static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
{
struct kernfs_open_file *of = sf->private;
const struct kernfs_ops *ops = kernfs_ops(of->kn);
if (ops->seq_stop)
ops->seq_stop(sf, v);
kernfs_put_active(of->kn);
}
static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
{
struct kernfs_open_file *of = sf->private;
const struct kernfs_ops *ops;
/*
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
* @of->mutex nests outside active ref and is primarily to ensure that
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
if (!kernfs_get_active(of->kn))
return ERR_PTR(-ENODEV);
ops = kernfs_ops(of->kn);
if (ops->seq_start) {
void *next = ops->seq_start(sf, ppos);
/* see the comment above kernfs_seq_stop_active() */
if (next == ERR_PTR(-ENODEV))
kernfs_seq_stop_active(sf, next);
return next;
} else {
/*
* The same behavior and code as single_open(). Returns
* !NULL if pos is at the beginning; otherwise, NULL.
*/
return NULL + !*ppos;
}
}
static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
{
struct kernfs_open_file *of = sf->private;
const struct kernfs_ops *ops = kernfs_ops(of->kn);
if (ops->seq_next) {
void *next = ops->seq_next(sf, v, ppos);
/* see the comment above kernfs_seq_stop_active() */
if (next == ERR_PTR(-ENODEV))
kernfs_seq_stop_active(sf, next);
return next;
} else {
/*
* The same behavior and code as single_open(), always
* terminate after the initial read.
*/
++*ppos;
return NULL;
}
}
static void kernfs_seq_stop(struct seq_file *sf, void *v)
{
struct kernfs_open_file *of = sf->private;
if (v != ERR_PTR(-ENODEV))
kernfs_seq_stop_active(sf, v);
mutex_unlock(&of->mutex);
}
static int kernfs_seq_show(struct seq_file *sf, void *v)
{
struct kernfs_open_file *of = sf->private;
of->event = atomic_read(&of->kn->attr.open->event);
return of->kn->attr.ops->seq_show(sf, v);
}
static const struct seq_operations kernfs_seq_ops = {
.start = kernfs_seq_start,
.next = kernfs_seq_next,
.stop = kernfs_seq_stop,
.show = kernfs_seq_show,
};
/*
* As reading a bin file can have side-effects, the exact offset and bytes
* specified in read(2) call should be passed to the read callback making
* it difficult to use seq_file. Implement simplistic custom buffering for
* bin files.
*/
static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
char __user *user_buf, size_t count,
loff_t *ppos)
{
ssize_t len = min_t(size_t, count, PAGE_SIZE);
const struct kernfs_ops *ops;
char *buf;
buf = of->prealloc_buf;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
if (buf)
mutex_lock(&of->prealloc_mutex);
else
buf = kmalloc(len, GFP_KERNEL);
if (!buf)
return -ENOMEM;
/*
* @of->mutex nests outside active ref and is used both to ensure that
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
if (!kernfs_get_active(of->kn)) {
len = -ENODEV;
mutex_unlock(&of->mutex);
goto out_free;
}
of->event = atomic_read(&of->kn->attr.open->event);
ops = kernfs_ops(of->kn);
if (ops->read)
len = ops->read(of, buf, len, *ppos);
else
len = -EINVAL;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
kernfs_put_active(of->kn);
mutex_unlock(&of->mutex);
if (len < 0)
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
goto out_free;
if (copy_to_user(user_buf, buf, len)) {
len = -EFAULT;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
goto out_free;
}
*ppos += len;
out_free:
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
if (buf == of->prealloc_buf)
mutex_unlock(&of->prealloc_mutex);
else
kfree(buf);
return len;
}
/**
* kernfs_fop_read - kernfs vfs read callback
* @file: file pointer
* @user_buf: data to write
* @count: number of bytes
* @ppos: starting offset
*/
static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
struct kernfs_open_file *of = kernfs_of(file);
if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
return seq_read(file, user_buf, count, ppos);
else
return kernfs_file_direct_read(of, user_buf, count, ppos);
}
/**
* kernfs_fop_write - kernfs vfs write callback
* @file: file pointer
* @user_buf: data to write
* @count: number of bytes
* @ppos: starting offset
*
* Copy data in from userland and pass it to the matching kernfs write
* operation.
*
* There is no easy way for us to know if userspace is only doing a partial
* write, so we don't support them. We expect the entire buffer to come on
* the first write. Hint: if you're writing a value, first read the file,
* modify only the the value you're changing, then write entire buffer
* back.
*/
static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
size_t count, loff_t *ppos)
{
struct kernfs_open_file *of = kernfs_of(file);
const struct kernfs_ops *ops;
ssize_t len;
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
char *buf;
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
if (of->atomic_write_len) {
len = count;
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
if (len > of->atomic_write_len)
return -E2BIG;
} else {
len = min_t(size_t, count, PAGE_SIZE);
}
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
buf = of->prealloc_buf;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
if (buf)
mutex_lock(&of->prealloc_mutex);
else
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
buf = kmalloc(len + 1, GFP_KERNEL);
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
if (!buf)
return -ENOMEM;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
if (copy_from_user(buf, user_buf, len)) {
len = -EFAULT;
goto out_free;
}
buf[len] = '\0'; /* guarantee string termination */
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
/*
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
* @of->mutex nests outside active ref and is used both to ensure that
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
* the ops aren't called concurrently for the same open file.
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
*/
mutex_lock(&of->mutex);
if (!kernfs_get_active(of->kn)) {
mutex_unlock(&of->mutex);
len = -ENODEV;
goto out_free;
}
ops = kernfs_ops(of->kn);
if (ops->write)
len = ops->write(of, buf, len, *ppos);
else
len = -EINVAL;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
kernfs_put_active(of->kn);
mutex_unlock(&of->mutex);
if (len > 0)
*ppos += len;
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
out_free:
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
if (buf == of->prealloc_buf)
mutex_unlock(&of->prealloc_mutex);
else
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
kfree(buf);
return len;
}
static void kernfs_vma_open(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
if (!of->vm_ops)
return;
if (!kernfs_get_active(of->kn))
return;
if (of->vm_ops->open)
of->vm_ops->open(vma);
kernfs_put_active(of->kn);
}
static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
vm_fault_t ret;
if (!of->vm_ops)
return VM_FAULT_SIGBUS;
if (!kernfs_get_active(of->kn))
return VM_FAULT_SIGBUS;
ret = VM_FAULT_SIGBUS;
if (of->vm_ops->fault)
ret = of->vm_ops->fault(vmf);
kernfs_put_active(of->kn);
return ret;
}
static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
vm_fault_t ret;
if (!of->vm_ops)
return VM_FAULT_SIGBUS;
if (!kernfs_get_active(of->kn))
return VM_FAULT_SIGBUS;
ret = 0;
if (of->vm_ops->page_mkwrite)
ret = of->vm_ops->page_mkwrite(vmf);
else
file_update_time(file);
kernfs_put_active(of->kn);
return ret;
}
static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write)
{
struct file *file = vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
int ret;
if (!of->vm_ops)
return -EINVAL;
if (!kernfs_get_active(of->kn))
return -EINVAL;
ret = -EINVAL;
if (of->vm_ops->access)
ret = of->vm_ops->access(vma, addr, buf, len, write);
kernfs_put_active(of->kn);
return ret;
}
#ifdef CONFIG_NUMA
static int kernfs_vma_set_policy(struct vm_area_struct *vma,
struct mempolicy *new)
{
struct file *file = vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
int ret;
if (!of->vm_ops)
return 0;
if (!kernfs_get_active(of->kn))
return -EINVAL;
ret = 0;
if (of->vm_ops->set_policy)
ret = of->vm_ops->set_policy(vma, new);
kernfs_put_active(of->kn);
return ret;
}
static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
unsigned long addr)
{
struct file *file = vma->vm_file;
struct kernfs_open_file *of = kernfs_of(file);
struct mempolicy *pol;
if (!of->vm_ops)
return vma->vm_policy;
if (!kernfs_get_active(of->kn))
return vma->vm_policy;
pol = vma->vm_policy;
if (of->vm_ops->get_policy)
pol = of->vm_ops->get_policy(vma, addr);
kernfs_put_active(of->kn);
return pol;
}
#endif
static const struct vm_operations_struct kernfs_vm_ops = {
.open = kernfs_vma_open,
.fault = kernfs_vma_fault,
.page_mkwrite = kernfs_vma_page_mkwrite,
.access = kernfs_vma_access,
#ifdef CONFIG_NUMA
.set_policy = kernfs_vma_set_policy,
.get_policy = kernfs_vma_get_policy,
#endif
};
static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
{
struct kernfs_open_file *of = kernfs_of(file);
const struct kernfs_ops *ops;
int rc;
sysfs: bail early from kernfs_file_mmap() to avoid spurious lockdep warning This is v3.14 fix for the same issue that a8b14744429f ("sysfs: give different locking key to regular and bin files") addresses for v3.13. Due to the extensive kernfs reorganization in v3.14 branch, the same fix couldn't be ported as-is. The v3.13 fix was ignored while merging it into v3.14 branch. 027a485d12e0 ("sysfs: use a separate locking class for open files depending on mmap") assigned different lockdep key to sysfs_open_file->mutex depending on whether the file implements mmap or not in an attempt to avoid spurious lockdep warning caused by merging of regular and bin file paths. While this restored some of the original behavior of using different locks (at least lockdep is concerned) for the different clases of files. The restoration wasn't full because now the lockdep key assignment depends on whether the file has mmap or not instead of whether it's a regular file or not. This means that bin files which don't implement mmap will get assigned the same lockdep class as regular files. This is problematic because file_operations for bin files still implements the mmap file operation and checking whether the sysfs file actually implements mmap happens in the file operation after grabbing @sysfs_open_file->mutex. We still end up adding locking dependency from mmap locking to sysfs_open_file->mutex to the regular file mutex which triggers spurious circular locking warning. For v3.13, a8b14744429f ("sysfs: give different locking key to regular and bin files") fixed it by giving sysfs_open_file->mutex different lockdep keys depending on whether the file is regular or bin instead of whether mmap exists or not; however, due to the way sysfs is now layered behind kernfs, this approach is no longer viable. kernfs can tell whether a sysfs node has mmap implemented or not but can't tell whether a bin file from a regular one. This patch updates kernfs such that kernfs_file_mmap() checks SYSFS_FLAG_HAS_MMAP and bail before grabbing sysfs_open_file->mutex so that it doesn't add spurious locking dependency from mmap to sysfs_open_file->mutex and changes sysfs so that it specifies kernfs_ops->mmap iff the sysfs file implements mmap. Combined, this ensures that sysfs_open_file->mutex is grabbed under mmap path iff the sysfs file actually implements mmap. As sysfs_open_file->mutex is already given a different lockdep key if mmap is implemented, this removes the spurious locking dependency. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Dave Jones <davej@redhat.com> Link: http://lkml.kernel.org/g/20131203184324.GA11320@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-12-10 22:29:17 +08:00
/*
* mmap path and of->mutex are prone to triggering spurious lockdep
* warnings and we don't want to add spurious locking dependency
* between the two. Check whether mmap is actually implemented
* without grabbing @of->mutex by testing HAS_MMAP flag. See the
* comment in kernfs_file_open() for more details.
*/
if (!(of->kn->flags & KERNFS_HAS_MMAP))
sysfs: bail early from kernfs_file_mmap() to avoid spurious lockdep warning This is v3.14 fix for the same issue that a8b14744429f ("sysfs: give different locking key to regular and bin files") addresses for v3.13. Due to the extensive kernfs reorganization in v3.14 branch, the same fix couldn't be ported as-is. The v3.13 fix was ignored while merging it into v3.14 branch. 027a485d12e0 ("sysfs: use a separate locking class for open files depending on mmap") assigned different lockdep key to sysfs_open_file->mutex depending on whether the file implements mmap or not in an attempt to avoid spurious lockdep warning caused by merging of regular and bin file paths. While this restored some of the original behavior of using different locks (at least lockdep is concerned) for the different clases of files. The restoration wasn't full because now the lockdep key assignment depends on whether the file has mmap or not instead of whether it's a regular file or not. This means that bin files which don't implement mmap will get assigned the same lockdep class as regular files. This is problematic because file_operations for bin files still implements the mmap file operation and checking whether the sysfs file actually implements mmap happens in the file operation after grabbing @sysfs_open_file->mutex. We still end up adding locking dependency from mmap locking to sysfs_open_file->mutex to the regular file mutex which triggers spurious circular locking warning. For v3.13, a8b14744429f ("sysfs: give different locking key to regular and bin files") fixed it by giving sysfs_open_file->mutex different lockdep keys depending on whether the file is regular or bin instead of whether mmap exists or not; however, due to the way sysfs is now layered behind kernfs, this approach is no longer viable. kernfs can tell whether a sysfs node has mmap implemented or not but can't tell whether a bin file from a regular one. This patch updates kernfs such that kernfs_file_mmap() checks SYSFS_FLAG_HAS_MMAP and bail before grabbing sysfs_open_file->mutex so that it doesn't add spurious locking dependency from mmap to sysfs_open_file->mutex and changes sysfs so that it specifies kernfs_ops->mmap iff the sysfs file implements mmap. Combined, this ensures that sysfs_open_file->mutex is grabbed under mmap path iff the sysfs file actually implements mmap. As sysfs_open_file->mutex is already given a different lockdep key if mmap is implemented, this removes the spurious locking dependency. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Dave Jones <davej@redhat.com> Link: http://lkml.kernel.org/g/20131203184324.GA11320@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-12-10 22:29:17 +08:00
return -ENODEV;
mutex_lock(&of->mutex);
rc = -ENODEV;
if (!kernfs_get_active(of->kn))
goto out_unlock;
ops = kernfs_ops(of->kn);
sysfs: bail early from kernfs_file_mmap() to avoid spurious lockdep warning This is v3.14 fix for the same issue that a8b14744429f ("sysfs: give different locking key to regular and bin files") addresses for v3.13. Due to the extensive kernfs reorganization in v3.14 branch, the same fix couldn't be ported as-is. The v3.13 fix was ignored while merging it into v3.14 branch. 027a485d12e0 ("sysfs: use a separate locking class for open files depending on mmap") assigned different lockdep key to sysfs_open_file->mutex depending on whether the file implements mmap or not in an attempt to avoid spurious lockdep warning caused by merging of regular and bin file paths. While this restored some of the original behavior of using different locks (at least lockdep is concerned) for the different clases of files. The restoration wasn't full because now the lockdep key assignment depends on whether the file has mmap or not instead of whether it's a regular file or not. This means that bin files which don't implement mmap will get assigned the same lockdep class as regular files. This is problematic because file_operations for bin files still implements the mmap file operation and checking whether the sysfs file actually implements mmap happens in the file operation after grabbing @sysfs_open_file->mutex. We still end up adding locking dependency from mmap locking to sysfs_open_file->mutex to the regular file mutex which triggers spurious circular locking warning. For v3.13, a8b14744429f ("sysfs: give different locking key to regular and bin files") fixed it by giving sysfs_open_file->mutex different lockdep keys depending on whether the file is regular or bin instead of whether mmap exists or not; however, due to the way sysfs is now layered behind kernfs, this approach is no longer viable. kernfs can tell whether a sysfs node has mmap implemented or not but can't tell whether a bin file from a regular one. This patch updates kernfs such that kernfs_file_mmap() checks SYSFS_FLAG_HAS_MMAP and bail before grabbing sysfs_open_file->mutex so that it doesn't add spurious locking dependency from mmap to sysfs_open_file->mutex and changes sysfs so that it specifies kernfs_ops->mmap iff the sysfs file implements mmap. Combined, this ensures that sysfs_open_file->mutex is grabbed under mmap path iff the sysfs file actually implements mmap. As sysfs_open_file->mutex is already given a different lockdep key if mmap is implemented, this removes the spurious locking dependency. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Dave Jones <davej@redhat.com> Link: http://lkml.kernel.org/g/20131203184324.GA11320@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-12-10 22:29:17 +08:00
rc = ops->mmap(of, vma);
if (rc)
goto out_put;
/*
* PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
* to satisfy versions of X which crash if the mmap fails: that
* substitutes a new vm_file, and we don't then want bin_vm_ops.
*/
if (vma->vm_file != file)
goto out_put;
rc = -EINVAL;
if (of->mmapped && of->vm_ops != vma->vm_ops)
goto out_put;
/*
* It is not possible to successfully wrap close.
* So error if someone is trying to use close.
*/
rc = -EINVAL;
if (vma->vm_ops && vma->vm_ops->close)
goto out_put;
rc = 0;
of->mmapped = true;
of->vm_ops = vma->vm_ops;
vma->vm_ops = &kernfs_vm_ops;
out_put:
kernfs_put_active(of->kn);
out_unlock:
mutex_unlock(&of->mutex);
return rc;
}
/**
* kernfs_get_open_node - get or create kernfs_open_node
* @kn: target kernfs_node
* @of: kernfs_open_file for this instance of open
*
* If @kn->attr.open exists, increment its reference count; otherwise,
* create one. @of is chained to the files list.
*
* LOCKING:
* Kernel thread context (may sleep).
*
* RETURNS:
* 0 on success, -errno on failure.
*/
static int kernfs_get_open_node(struct kernfs_node *kn,
struct kernfs_open_file *of)
{
struct kernfs_open_node *on, *new_on = NULL;
retry:
mutex_lock(&kernfs_open_file_mutex);
spin_lock_irq(&kernfs_open_node_lock);
if (!kn->attr.open && new_on) {
kn->attr.open = new_on;
new_on = NULL;
}
on = kn->attr.open;
if (on) {
atomic_inc(&on->refcnt);
list_add_tail(&of->list, &on->files);
}
spin_unlock_irq(&kernfs_open_node_lock);
mutex_unlock(&kernfs_open_file_mutex);
if (on) {
kfree(new_on);
return 0;
}
/* not there, initialize a new one and retry */
new_on = kmalloc(sizeof(*new_on), GFP_KERNEL);
if (!new_on)
return -ENOMEM;
atomic_set(&new_on->refcnt, 0);
atomic_set(&new_on->event, 1);
init_waitqueue_head(&new_on->poll);
INIT_LIST_HEAD(&new_on->files);
goto retry;
}
/**
* kernfs_put_open_node - put kernfs_open_node
* @kn: target kernfs_nodet
* @of: associated kernfs_open_file
*
* Put @kn->attr.open and unlink @of from the files list. If
* reference count reaches zero, disassociate and free it.
*
* LOCKING:
* None.
*/
static void kernfs_put_open_node(struct kernfs_node *kn,
struct kernfs_open_file *of)
{
struct kernfs_open_node *on = kn->attr.open;
unsigned long flags;
mutex_lock(&kernfs_open_file_mutex);
spin_lock_irqsave(&kernfs_open_node_lock, flags);
if (of)
list_del(&of->list);
if (atomic_dec_and_test(&on->refcnt))
kn->attr.open = NULL;
else
on = NULL;
spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
mutex_unlock(&kernfs_open_file_mutex);
kfree(on);
}
static int kernfs_fop_open(struct inode *inode, struct file *file)
{
struct kernfs_node *kn = inode->i_private;
2014-05-13 01:56:27 +08:00
struct kernfs_root *root = kernfs_root(kn);
const struct kernfs_ops *ops;
struct kernfs_open_file *of;
bool has_read, has_write, has_mmap;
int error = -EACCES;
if (!kernfs_get_active(kn))
return -ENODEV;
ops = kernfs_ops(kn);
has_read = ops->seq_show || ops->read || ops->mmap;
has_write = ops->write || ops->mmap;
has_mmap = ops->mmap;
2014-05-13 01:56:27 +08:00
/* see the flag definition for details */
if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) {
if ((file->f_mode & FMODE_WRITE) &&
(!(inode->i_mode & S_IWUGO) || !has_write))
goto err_out;
2014-05-13 01:56:27 +08:00
if ((file->f_mode & FMODE_READ) &&
(!(inode->i_mode & S_IRUGO) || !has_read))
goto err_out;
}
/* allocate a kernfs_open_file for the file */
error = -ENOMEM;
of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL);
if (!of)
goto err_out;
/*
* The following is done to give a different lockdep key to
* @of->mutex for files which implement mmap. This is a rather
* crude way to avoid false positive lockdep warning around
* mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and
* reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
* which mm->mmap_lock nests, while holding @of->mutex. As each
* open file has a separate mutex, it's okay as long as those don't
* happen on the same file. At this point, we can't easily give
* each file a separate locking class. Let's differentiate on
* whether the file has mmap or not for now.
sysfs: bail early from kernfs_file_mmap() to avoid spurious lockdep warning This is v3.14 fix for the same issue that a8b14744429f ("sysfs: give different locking key to regular and bin files") addresses for v3.13. Due to the extensive kernfs reorganization in v3.14 branch, the same fix couldn't be ported as-is. The v3.13 fix was ignored while merging it into v3.14 branch. 027a485d12e0 ("sysfs: use a separate locking class for open files depending on mmap") assigned different lockdep key to sysfs_open_file->mutex depending on whether the file implements mmap or not in an attempt to avoid spurious lockdep warning caused by merging of regular and bin file paths. While this restored some of the original behavior of using different locks (at least lockdep is concerned) for the different clases of files. The restoration wasn't full because now the lockdep key assignment depends on whether the file has mmap or not instead of whether it's a regular file or not. This means that bin files which don't implement mmap will get assigned the same lockdep class as regular files. This is problematic because file_operations for bin files still implements the mmap file operation and checking whether the sysfs file actually implements mmap happens in the file operation after grabbing @sysfs_open_file->mutex. We still end up adding locking dependency from mmap locking to sysfs_open_file->mutex to the regular file mutex which triggers spurious circular locking warning. For v3.13, a8b14744429f ("sysfs: give different locking key to regular and bin files") fixed it by giving sysfs_open_file->mutex different lockdep keys depending on whether the file is regular or bin instead of whether mmap exists or not; however, due to the way sysfs is now layered behind kernfs, this approach is no longer viable. kernfs can tell whether a sysfs node has mmap implemented or not but can't tell whether a bin file from a regular one. This patch updates kernfs such that kernfs_file_mmap() checks SYSFS_FLAG_HAS_MMAP and bail before grabbing sysfs_open_file->mutex so that it doesn't add spurious locking dependency from mmap to sysfs_open_file->mutex and changes sysfs so that it specifies kernfs_ops->mmap iff the sysfs file implements mmap. Combined, this ensures that sysfs_open_file->mutex is grabbed under mmap path iff the sysfs file actually implements mmap. As sysfs_open_file->mutex is already given a different lockdep key if mmap is implemented, this removes the spurious locking dependency. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Dave Jones <davej@redhat.com> Link: http://lkml.kernel.org/g/20131203184324.GA11320@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-12-10 22:29:17 +08:00
*
* Both paths of the branch look the same. They're supposed to
* look that way and give @of->mutex different static lockdep keys.
*/
if (has_mmap)
mutex_init(&of->mutex);
else
mutex_init(&of->mutex);
of->kn = kn;
of->file = file;
kernfs: cache atomic_write_len in kernfs_open_file While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement kernfs_ops->atomic_write_len") moved data copy from userland inside kernfs_get_active() and kernfs_open_file->mutex so that kernfs_ops->atomic_write_len can be accessed before copying buffer from userland; unfortunately, this could lead to locking order inversion involving mmap_sem if copy_from_user() takes a page fault. ====================================================== [ INFO: possible circular locking dependency detected ] 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G W ------------------------------------------------------- trinity-c236/10658 is trying to acquire lock: (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<mm/memory.c:4188>] might_fault+0x7e/0xb0 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 -> #0 (&of->mutex#2){+.+.+.}: [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&of->mutex#2); lock(&mm->mmap_sem); lock(&of->mutex#2); *** DEADLOCK *** 1 lock held by trinity-c236/10658: #0: (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0 stack backtrace: CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000 0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8 ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8 Call Trace: [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560 [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0 [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50 [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430 [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0 [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0 [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2 Fix it by caching atomic_write_len in kernfs_open_file during open so that it can be determined without accessing kernfs_ops in kernfs_fop_write(). This restores the structure of kernfs_fop_write() before 4d3773c4bb41 with updated @len determination logic. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Sasha Levin <sasha.levin@oracle.com> References: http://lkml.kernel.org/g/53113485.2090407@oracle.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-03-05 04:38:46 +08:00
/*
* Write path needs to atomic_write_len outside active reference.
* Cache it in open_file. See kernfs_fop_write() for details.
*/
of->atomic_write_len = ops->atomic_write_len;
error = -EINVAL;
/*
* ->seq_show is incompatible with ->prealloc,
* as seq_read does its own allocation.
* ->read must be used instead.
*/
if (ops->prealloc && ops->seq_show)
goto err_free;
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
if (ops->prealloc) {
int len = of->atomic_write_len ?: PAGE_SIZE;
of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL);
error = -ENOMEM;
if (!of->prealloc_buf)
goto err_free;
kernfs: Move faulting copy_user operations outside of the mutex A fault in a user provided buffer may lead anywhere, and lockdep warns that we have a potential deadlock between the mm->mmap_sem and the kernfs file mutex: [ 82.811702] ====================================================== [ 82.811705] [ INFO: possible circular locking dependency detected ] [ 82.811709] 4.5.0-rc4-gfxbench+ #1 Not tainted [ 82.811711] ------------------------------------------------------- [ 82.811714] kms_setmode/5859 is trying to acquire lock: [ 82.811717] (&dev->struct_mutex){+.+.+.}, at: [<ffffffff8150d9c1>] drm_gem_mmap+0x1a1/0x270 [ 82.811731] but task is already holding lock: [ 82.811734] (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.811745] which lock already depends on the new lock. [ 82.811749] the existing dependency chain (in reverse order) is: [ 82.811752] -> #3 (&mm->mmap_sem){++++++}: [ 82.811761] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811766] [<ffffffff8118bc65>] __might_fault+0x75/0xa0 [ 82.811771] [<ffffffff8124da4a>] kernfs_fop_write+0x8a/0x180 [ 82.811787] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811792] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811797] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811801] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811807] -> #2 (s_active#6){++++.+}: [ 82.811814] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811819] [<ffffffff8124c070>] __kernfs_remove+0x210/0x2f0 [ 82.811823] [<ffffffff8124d040>] kernfs_remove_by_name_ns+0x40/0xa0 [ 82.811828] [<ffffffff8124e9e0>] sysfs_remove_file_ns+0x10/0x20 [ 82.811832] [<ffffffff815318d4>] device_del+0x124/0x250 [ 82.811837] [<ffffffff81531a19>] device_unregister+0x19/0x60 [ 82.811841] [<ffffffff8153c051>] cpu_cache_sysfs_exit+0x51/0xb0 [ 82.811846] [<ffffffff8153c628>] cacheinfo_cpu_callback+0x38/0x70 [ 82.811851] [<ffffffff8109ae89>] notifier_call_chain+0x39/0xa0 [ 82.811856] [<ffffffff8109aef9>] __raw_notifier_call_chain+0x9/0x10 [ 82.811860] [<ffffffff810786de>] cpu_notify+0x1e/0x40 [ 82.811865] [<ffffffff81078779>] cpu_notify_nofail+0x9/0x20 [ 82.811869] [<ffffffff81078ac3>] _cpu_down+0x233/0x340 [ 82.811874] [<ffffffff81079019>] disable_nonboot_cpus+0xc9/0x350 [ 82.811878] [<ffffffff810d2e11>] suspend_devices_and_enter+0x5a1/0xb50 [ 82.811883] [<ffffffff810d3903>] pm_suspend+0x543/0x8d0 [ 82.811888] [<ffffffff810d1b77>] state_store+0x77/0xe0 [ 82.811892] [<ffffffff813fa68f>] kobj_attr_store+0xf/0x20 [ 82.811897] [<ffffffff8124e740>] sysfs_kf_write+0x40/0x50 [ 82.811902] [<ffffffff8124dafc>] kernfs_fop_write+0x13c/0x180 [ 82.811906] [<ffffffff811d1023>] __vfs_write+0x23/0xe0 [ 82.811910] [<ffffffff811d1d74>] vfs_write+0xa4/0x190 [ 82.811914] [<ffffffff811d2c14>] SyS_write+0x44/0xb0 [ 82.811918] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.811923] -> #1 (cpu_hotplug.lock){+.+.+.}: [ 82.811929] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.811933] [<ffffffff817b6f72>] mutex_lock_nested+0x62/0x3b0 [ 82.811940] [<ffffffff810784c1>] get_online_cpus+0x61/0x80 [ 82.811944] [<ffffffff811170eb>] stop_machine+0x1b/0xe0 [ 82.811949] [<ffffffffa0178edd>] gen8_ggtt_insert_entries__BKL+0x2d/0x30 [i915] [ 82.812009] [<ffffffffa017d3a6>] ggtt_bind_vma+0x46/0x70 [i915] [ 82.812045] [<ffffffffa017eb70>] i915_vma_bind+0x140/0x290 [i915] [ 82.812081] [<ffffffffa01862b9>] i915_gem_object_do_pin+0x899/0xb00 [i915] [ 82.812117] [<ffffffffa0186555>] i915_gem_object_pin+0x35/0x40 [i915] [ 82.812154] [<ffffffffa019a23e>] intel_init_pipe_control+0xbe/0x210 [i915] [ 82.812192] [<ffffffffa0197312>] intel_logical_rings_init+0xe2/0xde0 [i915] [ 82.812232] [<ffffffffa0186fe3>] i915_gem_init+0xf3/0x130 [i915] [ 82.812278] [<ffffffffa02097ed>] i915_driver_load+0xf2d/0x1770 [i915] [ 82.812318] [<ffffffff81512474>] drm_dev_register+0xa4/0xb0 [ 82.812323] [<ffffffff8151467e>] drm_get_pci_dev+0xce/0x1e0 [ 82.812328] [<ffffffffa01472cf>] i915_pci_probe+0x2f/0x50 [i915] [ 82.812360] [<ffffffff8143f907>] pci_device_probe+0x87/0xf0 [ 82.812366] [<ffffffff81535f89>] driver_probe_device+0x229/0x450 [ 82.812371] [<ffffffff81536233>] __driver_attach+0x83/0x90 [ 82.812375] [<ffffffff81533c61>] bus_for_each_dev+0x61/0xa0 [ 82.812380] [<ffffffff81535879>] driver_attach+0x19/0x20 [ 82.812384] [<ffffffff8153535f>] bus_add_driver+0x1ef/0x290 [ 82.812388] [<ffffffff81536e9b>] driver_register+0x5b/0xe0 [ 82.812393] [<ffffffff8143e83b>] __pci_register_driver+0x5b/0x60 [ 82.812398] [<ffffffff81514866>] drm_pci_init+0xd6/0x100 [ 82.812402] [<ffffffffa027c094>] 0xffffffffa027c094 [ 82.812406] [<ffffffff810003de>] do_one_initcall+0xae/0x1d0 [ 82.812412] [<ffffffff811595a0>] do_init_module+0x5b/0x1cb [ 82.812417] [<ffffffff81106160>] load_module+0x1c20/0x2480 [ 82.812422] [<ffffffff81106bae>] SyS_finit_module+0x7e/0xa0 [ 82.812428] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812433] -> #0 (&dev->struct_mutex){+.+.+.}: [ 82.812439] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812443] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812456] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812460] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812466] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812470] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812474] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812479] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812484] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 [ 82.812489] other info that might help us debug this: [ 82.812493] Chain exists of: &dev->struct_mutex --> s_active#6 --> &mm->mmap_sem [ 82.812502] Possible unsafe locking scenario: [ 82.812506] CPU0 CPU1 [ 82.812508] ---- ---- [ 82.812510] lock(&mm->mmap_sem); [ 82.812514] lock(s_active#6); [ 82.812519] lock(&mm->mmap_sem); [ 82.812522] lock(&dev->struct_mutex); [ 82.812526] *** DEADLOCK *** [ 82.812531] 1 lock held by kms_setmode/5859: [ 82.812533] #0: (&mm->mmap_sem){++++++}, at: [<ffffffff8117b364>] vm_mmap_pgoff+0x44/0xa0 [ 82.812541] stack backtrace: [ 82.812547] CPU: 0 PID: 5859 Comm: kms_setmode Not tainted 4.5.0-rc4-gfxbench+ #1 [ 82.812550] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0040.2015.0814.1353 08/14/2015 [ 82.812553] 0000000000000000 ffff880079407bf0 ffffffff813f8505 ffffffff825fb270 [ 82.812560] ffffffff825c4190 ffff880079407c30 ffffffff810c84ac ffff880079407c90 [ 82.812566] ffff8800797ed328 ffff8800797ecb00 0000000000000001 ffff8800797ed350 [ 82.812573] Call Trace: [ 82.812578] [<ffffffff813f8505>] dump_stack+0x67/0x92 [ 82.812582] [<ffffffff810c84ac>] print_circular_bug+0x1fc/0x310 [ 82.812586] [<ffffffff810cbe59>] __lock_acquire+0x1fc9/0x20f0 [ 82.812590] [<ffffffff810cc883>] lock_acquire+0xc3/0x1d0 [ 82.812594] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812599] [<ffffffff8150d9e7>] drm_gem_mmap+0x1c7/0x270 [ 82.812603] [<ffffffff8150d9c1>] ? drm_gem_mmap+0x1a1/0x270 [ 82.812608] [<ffffffff81196a14>] mmap_region+0x334/0x580 [ 82.812612] [<ffffffff81196fc4>] do_mmap+0x364/0x410 [ 82.812616] [<ffffffff8117b38d>] vm_mmap_pgoff+0x6d/0xa0 [ 82.812629] [<ffffffff811950f4>] SyS_mmap_pgoff+0x184/0x220 [ 82.812633] [<ffffffff8100a0fd>] SyS_mmap+0x1d/0x20 [ 82.812637] [<ffffffff817bb81b>] entry_SYSCALL_64_fastpath+0x16/0x73 Highly unlikely though this scenario is, we can avoid the issue entirely by moving the copy operation from out under the kernfs_get_active() tracking by assigning the preallocated buffer its own mutex. The temporary buffer allocation doesn't require mutex locking as it is entirely local. The locked section was extended by the addition of the preallocated buf to speed up md user operations in commit 2b75869bba676c248d8d25ae6d2bd9221dfffdb6 Author: NeilBrown <neilb@suse.de> Date: Mon Oct 13 16:41:28 2014 +1100 sysfs/kernfs: allow attributes to request write buffer be pre-allocated. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94350 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-03-31 18:45:06 +08:00
mutex_init(&of->prealloc_mutex);
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
}
/*
* Always instantiate seq_file even if read access doesn't use
* seq_file or is not requested. This unifies private data access
* and readable regular files are the vast majority anyway.
*/
if (ops->seq_show)
error = seq_open(file, &kernfs_seq_ops);
else
error = seq_open(file, NULL);
if (error)
goto err_free;
of->seq_file = file->private_data;
of->seq_file->private = of;
/* seq_file clears PWRITE unconditionally, restore it if WRITE */
if (file->f_mode & FMODE_WRITE)
file->f_mode |= FMODE_PWRITE;
/* make sure we have open node struct */
error = kernfs_get_open_node(kn, of);
if (error)
goto err_seq_release;
if (ops->open) {
/* nobody has access to @of yet, skip @of->mutex */
error = ops->open(of);
if (error)
goto err_put_node;
}
/* open succeeded, put active references */
kernfs_put_active(kn);
return 0;
err_put_node:
kernfs_put_open_node(kn, of);
err_seq_release:
seq_release(inode, file);
err_free:
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
kfree(of->prealloc_buf);
kfree(of);
err_out:
kernfs_put_active(kn);
return error;
}
/* used from release/drain to ensure that ->release() is called exactly once */
static void kernfs_release_file(struct kernfs_node *kn,
struct kernfs_open_file *of)
{
/*
* @of is guaranteed to have no other file operations in flight and
* we just want to synchronize release and drain paths.
* @kernfs_open_file_mutex is enough. @of->mutex can't be used
* here because drain path may be called from places which can
* cause circular dependency.
*/
lockdep_assert_held(&kernfs_open_file_mutex);
if (!of->released) {
/*
* A file is never detached without being released and we
* need to be able to release files which are deactivated
* and being drained. Don't use kernfs_ops().
*/
kn->attr.ops->release(of);
of->released = true;
}
}
static int kernfs_fop_release(struct inode *inode, struct file *filp)
{
struct kernfs_node *kn = inode->i_private;
struct kernfs_open_file *of = kernfs_of(filp);
if (kn->flags & KERNFS_HAS_RELEASE) {
mutex_lock(&kernfs_open_file_mutex);
kernfs_release_file(kn, of);
mutex_unlock(&kernfs_open_file_mutex);
}
kernfs_put_open_node(kn, of);
seq_release(inode, filp);
sysfs/kernfs: allow attributes to request write buffer be pre-allocated. md/raid allows metadata management to be performed in user-space. A various times, particularly on device failure, the metadata needs to be updated before further writes can be permitted. This means that the user-space program which updates metadata much not block on writeout, and so must not allocate memory. mlockall(MCL_CURRENT|MCL_FUTURE) and pre-allocation can avoid all memory allocation issues for user-memory, but that does not help kernel memory. Several kernel objects can be pre-allocated. e.g. files opened before any writes to the array are permitted. However some kernel allocation happens in places that cannot be pre-allocated. In particular, writes to sysfs files (to tell md that it can now allow writes to the array) allocate a buffer using GFP_KERNEL. This patch allows attributes to be marked as "PREALLOC". In that case the maximal buffer is allocated when the file is opened, and then used on each write instead of allocating a new buffer. As the same buffer is now shared for all writes on the same file description, the mutex is extended to cover full use of the buffer including the copy_from_user(). The new __ATTR_PREALLOC() 'or's a new flag in to the 'mode', which is inspected by sysfs_add_file_mode_ns() to determine if the file should be marked as requiring prealloc. Despite the comment, we *do* use ->seq_show together with ->prealloc in this patch. The next patch fixes that. Signed-off-by: NeilBrown <neilb@suse.de> Reviewed-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-13 13:41:28 +08:00
kfree(of->prealloc_buf);
kfree(of);
return 0;
}
void kernfs_drain_open_files(struct kernfs_node *kn)
{
struct kernfs_open_node *on;
struct kernfs_open_file *of;
if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
return;
spin_lock_irq(&kernfs_open_node_lock);
on = kn->attr.open;
if (on)
atomic_inc(&on->refcnt);
spin_unlock_irq(&kernfs_open_node_lock);
if (!on)
return;
mutex_lock(&kernfs_open_file_mutex);
list_for_each_entry(of, &on->files, list) {
struct inode *inode = file_inode(of->file);
if (kn->flags & KERNFS_HAS_MMAP)
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
kernfs: Check KERNFS_HAS_RELEASE before calling kernfs_release_file() Recently started seeing a kernel oops when a module tries removing a memory mapped sysfs bin_attribute. On closer investigation the root cause seems to be kernfs_release_file() trying to call kernfs_op.release() callback that's NULL for such sysfs bin_attributes. The oops occurs when kernfs_release_file() is called from kernfs_drain_open_files() to cleanup any open handles with active memory mappings. The patch fixes this by checking for flag KERNFS_HAS_RELEASE before calling kernfs_release_file() in function kernfs_drain_open_files(). On ppc64-le arch with cxl module the oops back-trace is of the form below: [ 861.381126] Unable to handle kernel paging request for instruction fetch [ 861.381360] Faulting instruction address: 0x00000000 [ 861.381428] Oops: Kernel access of bad area, sig: 11 [#1] .... [ 861.382481] NIP: 0000000000000000 LR: c000000000362c60 CTR: 0000000000000000 .... Call Trace: [c000000f1680b750] [c000000000362c34] kernfs_drain_open_files+0x104/0x1d0 (unreliable) [c000000f1680b790] [c00000000035fa00] __kernfs_remove+0x260/0x2c0 [c000000f1680b820] [c000000000360da0] kernfs_remove_by_name_ns+0x60/0xe0 [c000000f1680b8b0] [c0000000003638f4] sysfs_remove_bin_file+0x24/0x40 [c000000f1680b8d0] [c00000000062a164] device_remove_bin_file+0x24/0x40 [c000000f1680b8f0] [d000000009b7b22c] cxl_sysfs_afu_remove+0x144/0x170 [cxl] [c000000f1680b940] [d000000009b7c7e4] cxl_remove+0x6c/0x1a0 [cxl] [c000000f1680b990] [c00000000052f694] pci_device_remove+0x64/0x110 [c000000f1680b9d0] [c0000000006321d4] device_release_driver_internal+0x1f4/0x2b0 [c000000f1680ba20] [c000000000525cb0] pci_stop_bus_device+0xa0/0xd0 [c000000f1680ba60] [c000000000525e80] pci_stop_and_remove_bus_device+0x20/0x40 [c000000f1680ba90] [c00000000004a6c4] pci_hp_remove_devices+0x84/0xc0 [c000000f1680bad0] [c00000000004a688] pci_hp_remove_devices+0x48/0xc0 [c000000f1680bb10] [c0000000009dfda4] eeh_reset_device+0xb0/0x290 [c000000f1680bbb0] [c000000000032b4c] eeh_handle_normal_event+0x47c/0x530 [c000000f1680bc60] [c000000000032e64] eeh_handle_event+0x174/0x350 [c000000f1680bd10] [c000000000033228] eeh_event_handler+0x1e8/0x1f0 [c000000f1680bdc0] [c0000000000d384c] kthread+0x14c/0x190 [c000000f1680be30] [c00000000000b5a0] ret_from_kernel_thread+0x5c/0xbc Fixes: f83f3c515654 ("kernfs: fix locking around kernfs_ops->release() callback") Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-03-14 10:47:00 +08:00
if (kn->flags & KERNFS_HAS_RELEASE)
kernfs_release_file(kn, of);
}
mutex_unlock(&kernfs_open_file_mutex);
kernfs_put_open_node(kn, NULL);
}
/*
* Kernfs attribute files are pollable. The idea is that you read
* the content and then you use 'poll' or 'select' to wait for
* the content to change. When the content changes (assuming the
* manager for the kobject supports notification), poll will
* return EPOLLERR|EPOLLPRI, and select will return the fd whether
* it is waiting for read, write, or exceptions.
* Once poll/select indicates that the value has changed, you
* need to close and re-open the file, or seek to 0 and read again.
* Reminder: this only works for attributes which actively support
* it, and it is not possible to test an attribute from userspace
* to see if it supports poll (Neither 'poll' nor 'select' return
* an appropriate error code). When in doubt, set a suitable timeout value.
*/
fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:45:45 +08:00
__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
{
struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry);
struct kernfs_open_node *on = kn->attr.open;
poll_wait(of->file, &on->poll, wait);
if (of->event != atomic_read(&on->event))
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
return DEFAULT_POLLMASK;
}
static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
{
struct kernfs_open_file *of = kernfs_of(filp);
struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:45:45 +08:00
__poll_t ret;
if (!kernfs_get_active(kn))
fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:45:45 +08:00
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:45:45 +08:00
if (kn->attr.ops->poll)
ret = kn->attr.ops->poll(of, wait);
else
ret = kernfs_generic_poll(of, wait);
kernfs_put_active(kn);
fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 07:45:45 +08:00
return ret;
}
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
static void kernfs_notify_workfn(struct work_struct *work)
{
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
struct kernfs_node *kn;
struct kernfs_super_info *info;
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
repeat:
/* pop one off the notify_list */
spin_lock_irq(&kernfs_notify_lock);
kn = kernfs_notify_list;
if (kn == KERNFS_NOTIFY_EOL) {
spin_unlock_irq(&kernfs_notify_lock);
return;
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
}
kernfs_notify_list = kn->attr.notify_next;
kn->attr.notify_next = NULL;
spin_unlock_irq(&kernfs_notify_lock);
/* kick fsnotify */
mutex_lock(&kernfs_mutex);
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Eric Paris <eparis@parisplace.org> Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-18 05:51:17 +08:00
struct kernfs_node *parent;
struct inode *p_inode = NULL;
struct inode *inode;
struct qstr name;
kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Eric Paris <eparis@parisplace.org> Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-18 05:51:17 +08:00
/*
* We want fsnotify_modify() on @kn but as the
* modifications aren't originating from userland don't
* have the matching @file available. Look up the inodes
* and generate the events manually.
*/
inode = ilookup(info->sb, kernfs_ino(kn));
if (!inode)
continue;
name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Eric Paris <eparis@parisplace.org> Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-18 05:51:17 +08:00
parent = kernfs_get_parent(kn);
if (parent) {
p_inode = ilookup(info->sb, kernfs_ino(parent));
kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Eric Paris <eparis@parisplace.org> Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-18 05:51:17 +08:00
if (p_inode) {
fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD,
inode, FSNOTIFY_EVENT_INODE,
p_inode, &name, inode, 0);
kernfs: don't depend on d_find_any_alias() when generating notifications kernfs_notify_workfn() sends out file modified events for the scheduled kernfs_nodes. Because the modifications aren't from userland, it doesn't have the matching file struct at hand and can't use fsnotify_modify(). Instead, it looked up the inode and then used d_find_any_alias() to find the dentry and used fsnotify_parent() and fsnotify() directly to generate notifications. The assumption was that the relevant dentries would have been pinned if there are listeners, which isn't true as inotify doesn't pin dentries at all and watching the parent doesn't pin the child dentries even for dnotify. This led to, for example, inotify watchers not getting notifications if the system is under memory pressure and the matching dentries got reclaimed. It can also be triggered through /proc/sys/vm/drop_caches or a remount attempt which involves shrinking dcache. fsnotify_parent() only uses the dentry to access the parent inode, which kernfs can do easily. Update kernfs_notify_workfn() so that it uses fsnotify() directly for both the parent and target inodes without going through d_find_any_alias(). While at it, supply the target file name to fsnotify() from kernfs_node->name. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Evgeny Vereshchagin <evvers@ya.ru> Fixes: d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Eric Paris <eparis@parisplace.org> Cc: stable@vger.kernel.org # v3.16+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-18 05:51:17 +08:00
iput(p_inode);
}
kernfs_put(parent);
}
if (!p_inode)
fsnotify_inode(inode, FS_MODIFY);
iput(inode);
}
mutex_unlock(&kernfs_mutex);
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
kernfs_put(kn);
goto repeat;
}
/**
* kernfs_notify - notify a kernfs file
* @kn: file to notify
*
* Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any
* context.
*/
void kernfs_notify(struct kernfs_node *kn)
{
static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
unsigned long flags;
struct kernfs_open_node *on;
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
return;
/* kick poll immediately */
spin_lock_irqsave(&kernfs_open_node_lock, flags);
on = kn->attr.open;
if (on) {
atomic_inc(&on->event);
wake_up_interruptible(&on->poll);
}
spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
/* schedule work to kick fsnotify */
kernfs: kernfs_notify() must be useable from non-sleepable contexts d911d9874801 ("kernfs: make kernfs_notify() trigger inotify events too") added fsnotify triggering to kernfs_notify() which requires a sleepable context. There are already existing users of kernfs_notify() which invoke it from an atomic context and in general it's silly to require a sleepable context for triggering a notification. The following is an invalid context bug triggerd by md invoking sysfs_notify() from IO completion path. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 2 locks held by swapper/1/0: #0: (&(&vblk->vq_lock)->rlock){-.-...}, at: [<ffffffffa0039042>] virtblk_done+0x42/0xe0 [virtio_blk] #1: (&(&bitmap->counts.lock)->rlock){-.....}, at: [<ffffffff81633718>] bitmap_endwrite+0x68/0x240 irq event stamp: 33518 hardirqs last enabled at (33515): [<ffffffff8102544f>] default_idle+0x1f/0x230 hardirqs last disabled at (33516): [<ffffffff818122ed>] common_interrupt+0x6d/0x72 softirqs last enabled at (33518): [<ffffffff810a1272>] _local_bh_enable+0x22/0x50 softirqs last disabled at (33517): [<ffffffff810a29e0>] irq_enter+0x60/0x80 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.16.0-0.rc2.git2.1.fc21.x86_64 #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 0000000000000000 f90db13964f4ee05 ffff88007d403b80 ffffffff81807b4c 0000000000000000 ffff88007d403ba8 ffffffff810d4f14 0000000000000000 0000000000441800 ffff880078fa1780 ffff88007d403c38 ffffffff8180caf2 Call Trace: <IRQ> [<ffffffff81807b4c>] dump_stack+0x4d/0x66 [<ffffffff810d4f14>] __might_sleep+0x184/0x240 [<ffffffff8180caf2>] mutex_lock_nested+0x42/0x440 [<ffffffff812d76a0>] kernfs_notify+0x90/0x150 [<ffffffff8163377c>] bitmap_endwrite+0xcc/0x240 [<ffffffffa00de863>] close_write+0x93/0xb0 [raid1] [<ffffffffa00df029>] r1_bio_write_done+0x29/0x50 [raid1] [<ffffffffa00e0474>] raid1_end_write_request+0xe4/0x260 [raid1] [<ffffffff813acb8b>] bio_endio+0x6b/0xa0 [<ffffffff813b46c4>] blk_update_request+0x94/0x420 [<ffffffff813bf0ea>] blk_mq_end_io+0x1a/0x70 [<ffffffffa00392c2>] virtblk_request_done+0x32/0x80 [virtio_blk] [<ffffffff813c0648>] __blk_mq_complete_request+0x88/0x120 [<ffffffff813c070a>] blk_mq_complete_request+0x2a/0x30 [<ffffffffa0039066>] virtblk_done+0x66/0xe0 [virtio_blk] [<ffffffffa002535a>] vring_interrupt+0x3a/0xa0 [virtio_ring] [<ffffffff81116177>] handle_irq_event_percpu+0x77/0x340 [<ffffffff8111647d>] handle_irq_event+0x3d/0x60 [<ffffffff81119436>] handle_edge_irq+0x66/0x130 [<ffffffff8101c3e4>] handle_irq+0x84/0x150 [<ffffffff818146ad>] do_IRQ+0x4d/0xe0 [<ffffffff818122f2>] common_interrupt+0x72/0x72 <EOI> [<ffffffff8105f706>] ? native_safe_halt+0x6/0x10 [<ffffffff81025454>] default_idle+0x24/0x230 [<ffffffff81025f9f>] arch_cpu_idle+0xf/0x20 [<ffffffff810f5adc>] cpu_startup_entry+0x37c/0x7b0 [<ffffffff8104df1b>] start_secondary+0x25b/0x300 This patch fixes it by punting the notification delivery through a work item. This ends up adding an extra pointer to kernfs_elem_attr enlarging kernfs_node by a pointer, which is not ideal but not a very big deal either. If this turns out to be an actual issue, we can move kernfs_elem_attr->size to kernfs_node->iattr later. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Josh Boyer <jwboyer@fedoraproject.org> Cc: Jens Axboe <axboe@kernel.dk> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-07-02 04:41:03 +08:00
spin_lock_irqsave(&kernfs_notify_lock, flags);
if (!kn->attr.notify_next) {
kernfs_get(kn);
kn->attr.notify_next = kernfs_notify_list;
kernfs_notify_list = kn;
schedule_work(&kernfs_notify_work);
}
spin_unlock_irqrestore(&kernfs_notify_lock, flags);
}
EXPORT_SYMBOL_GPL(kernfs_notify);
const struct file_operations kernfs_file_fops = {
.read = kernfs_fop_read,
.write = kernfs_fop_write,
.llseek = generic_file_llseek,
.mmap = kernfs_fop_mmap,
.open = kernfs_fop_open,
.release = kernfs_fop_release,
.poll = kernfs_fop_poll,
.fsync = noop_fsync,
};
/**
* __kernfs_create_file - kernfs internal function to create a file
* @parent: directory to create the file in
* @name: name of the file
* @mode: mode of the file
* @uid: uid of the file
* @gid: gid of the file
* @size: size of the file
* @ops: kernfs operations for the file
* @priv: private data for the file
* @ns: optional namespace tag of the file
* @key: lockdep key for the file's active_ref, %NULL to disable lockdep
*
* Returns the created node on success, ERR_PTR() value on error.
*/
struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
const char *name,
umode_t mode, kuid_t uid, kgid_t gid,
loff_t size,
const struct kernfs_ops *ops,
void *priv, const void *ns,
struct lock_class_key *key)
{
struct kernfs_node *kn;
unsigned flags;
int rc;
flags = KERNFS_FILE;
kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG,
uid, gid, flags);
if (!kn)
return ERR_PTR(-ENOMEM);
kn->attr.ops = ops;
kn->attr.size = size;
kn->ns = ns;
kn->priv = priv;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (key) {
lockdep_init_map(&kn->dep_map, "kn->active", key, 0);
kn->flags |= KERNFS_LOCKDEP;
}
#endif
/*
* kn->attr.ops is accesible only while holding active ref. We
* need to know whether some ops are implemented outside active
* ref. Cache their existence in flags.
*/
if (ops->seq_show)
kn->flags |= KERNFS_HAS_SEQ_SHOW;
if (ops->mmap)
kn->flags |= KERNFS_HAS_MMAP;
if (ops->release)
kn->flags |= KERNFS_HAS_RELEASE;
rc = kernfs_add_one(kn);
if (rc) {
kernfs_put(kn);
return ERR_PTR(rc);
}
return kn;
}