#include #include #include #include #include #include #include #include #include int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, const char *name, struct lock_class_key *rwsem_key) { sem->read_count = alloc_percpu(int); if (unlikely(!sem->read_count)) return -ENOMEM; /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ rcu_sync_init(&sem->rss, RCU_SCHED_SYNC); __init_rwsem(&sem->rw_sem, name, rwsem_key); init_waitqueue_head(&sem->writer); sem->readers_block = 0; return 0; } EXPORT_SYMBOL_GPL(__percpu_init_rwsem); void percpu_free_rwsem(struct percpu_rw_semaphore *sem) { /* * XXX: temporary kludge. The error path in alloc_super() * assumes that percpu_free_rwsem() is safe after kzalloc(). */ if (!sem->read_count) return; rcu_sync_dtor(&sem->rss); free_percpu(sem->read_count); sem->read_count = NULL; /* catch use after free bugs */ } EXPORT_SYMBOL_GPL(percpu_free_rwsem); int __percpu_down_read(struct percpu_rw_semaphore *sem, int try) { /* * Due to having preemption disabled the decrement happens on * the same CPU as the increment, avoiding the * increment-on-one-CPU-and-decrement-on-another problem. * * If the reader misses the writer's assignment of readers_block, then * the writer is guaranteed to see the reader's increment. * * Conversely, any readers that increment their sem->read_count after * the writer looks are guaranteed to see the readers_block value, * which in turn means that they are guaranteed to immediately * decrement their sem->read_count, so that it doesn't matter that the * writer missed them. */ smp_mb(); /* A matches D */ /* * If !readers_block the critical section starts here, matched by the * release in percpu_up_write(). */ if (likely(!smp_load_acquire(&sem->readers_block))) return 1; /* * Per the above comment; we still have preemption disabled and * will thus decrement on the same CPU as we incremented. */ __percpu_up_read(sem); if (try) return 0; /* * We either call schedule() in the wait, or we'll fall through * and reschedule on the preempt_enable() in percpu_down_read(). */ preempt_enable_no_resched(); /* * Avoid lockdep for the down/up_read() we already have them. */ __down_read(&sem->rw_sem); this_cpu_inc(*sem->read_count); __up_read(&sem->rw_sem); preempt_disable(); return 1; } EXPORT_SYMBOL_GPL(__percpu_down_read); void __percpu_up_read(struct percpu_rw_semaphore *sem) { smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to aggregate * zero, as that is the only time it matters) they will also see our * critical section. */ __this_cpu_dec(*sem->read_count); /* Prod writer to recheck readers_active */ wake_up(&sem->writer); } EXPORT_SYMBOL_GPL(__percpu_up_read); #define per_cpu_sum(var) \ ({ \ typeof(var) __sum = 0; \ int cpu; \ compiletime_assert_atomic_type(__sum); \ for_each_possible_cpu(cpu) \ __sum += per_cpu(var, cpu); \ __sum; \ }) /* * Return true if the modular sum of the sem->read_count per-CPU variable is * zero. If this sum is zero, then it is stable due to the fact that if any * newly arriving readers increment a given counter, they will immediately * decrement that same counter. */ static bool readers_active_check(struct percpu_rw_semaphore *sem) { if (per_cpu_sum(*sem->read_count) != 0) return false; /* * If we observed the decrement; ensure we see the entire critical * section. */ smp_mb(); /* C matches B */ return true; } void percpu_down_write(struct percpu_rw_semaphore *sem) { /* Notify readers to take the slow path. */ rcu_sync_enter(&sem->rss); down_write(&sem->rw_sem); /* * Notify new readers to block; up until now, and thus throughout the * longish rcu_sync_enter() above, new readers could still come in. */ WRITE_ONCE(sem->readers_block, 1); smp_mb(); /* D matches A */ /* * If they don't see our writer of readers_block, then we are * guaranteed to see their sem->read_count increment, and therefore * will wait for them. */ /* Wait for all now active readers to complete. */ wait_event(sem->writer, readers_active_check(sem)); } EXPORT_SYMBOL_GPL(percpu_down_write); void percpu_up_write(struct percpu_rw_semaphore *sem) { /* * Signal the writer is done, no fast path yet. * * One reason that we cannot just immediately flip to readers_fast is * that new readers might fail to see the results of this writer's * critical section. * * Therefore we force it through the slow path which guarantees an * acquire and thereby guarantees the critical section's consistency. */ smp_store_release(&sem->readers_block, 0); /* * Release the write lock, this will allow readers back in the game. */ up_write(&sem->rw_sem); /* * Once this completes (at least one RCU-sched grace period hence) the * reader fast path will be available again. Safe to use outside the * exclusive write lock because its counting. */ rcu_sync_exit(&sem->rss); } EXPORT_SYMBOL_GPL(percpu_up_write); d> tree9bf9f9b4971df55a46e0a6750d3f6cd37bf1d9f0 /drivers/usb/usbip/vudc.h parent49def1853334396f948dcb4cedb9347abb318df5 (diff)
firmware: fix NULL pointer dereference in __fw_load_abort()
Since commit 5d47ec02c37ea6 ("firmware: Correct handling of fw_state_wait() return value") fw_load_abort() could be called twice and lead us to a kernel crash. This happens only when the firmware fallback mechanism (regular or custom) is used. The fallback mechanism exposes a sysfs interface for userspace to upload a file and notify the kernel when the file is loaded and ready, or to cancel an upload by echo'ing -1 into on the loading file: echo -n "-1" > /sys/$DEVPATH/loading This will call fw_load_abort(). Some distributions actually have a udev rule in place to *always* immediately cancel all firmware fallback mechanism requests (Debian), they have: $ cat /lib/udev/rules.d/50-firmware.rules # stub for immediately telling the kernel that userspace firmware loading # failed; necessary to avoid long timeouts with CONFIG_FW_LOADER_USER_HELPER=y SUBSYSTEM=="firmware", ACTION=="add", ATTR{loading}="-1 Distributions with this udev rule would run into this crash only if the fallback mechanism is used. Since most distributions disable by default using the fallback mechanism (CONFIG_FW_LOADER_USER_HELPER_FALLBACK), this would typicaly mean only 2 drivers which *require* the fallback mechanism could typically incur a crash: drivers/firmware/dell_rbu.c and the drivers/leds/leds-lp55xx-common.c driver. Distributions enabling CONFIG_FW_LOADER_USER_HELPER_FALLBACK by default are obviously more exposed to this crash. The crash happens because after commit 5b029624948d ("firmware: do not use fw_lock for fw_state protection") and subsequent fix commit 5d47ec02c37ea6 ("firmware: Correct handling of fw_state_wait() return value") a race can happen between this cancelation and the firmware fw_state_wait_timeout() being woken up after a state change with which fw_load_abort() as that calls swake_up(). Upon error fw_state_wait_timeout() will also again call fw_load_abort() and trigger a null reference. At first glance we could just fix this with a !buf check on fw_load_abort() before accessing buf->fw_st, however there is a logical issue in having a state machine used for the fallback mechanism and preventing access from it once we abort as its inside the buf (buf->fw_st). The firmware_class.c code is setting the buf to NULL to annotate an abort has occurred. Replace this mechanism by simply using the state check instead. All the other code in place already uses similar checks for aborting as well so no further changes are needed. An oops can be reproduced with the new fw_fallback.sh fallback mechanism cancellation test. Either cancelling the fallback mechanism or the custom fallback mechanism triggers a crash. mcgrof@piggy ~/linux-next/tools/testing/selftests/firmware (git::20170111-fw-fixes)$ sudo ./fw_fallback.sh ./fw_fallback.sh: timeout works ./fw_fallback.sh: firmware comparison works ./fw_fallback.sh: fallback mechanism works [ this then sits here when it is trying the cancellation test ] Kernel log: test_firmware: loading 'nope-test-firmware.bin' misc test_firmware: Direct firmware load for nope-test-firmware.bin failed with error -2 misc test_firmware: Falling back to user helper BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: _request_firmware+0xa27/0xad0 PGD 0 Oops: 0000 [#1] SMP Modules linked in: test_firmware(E) ... etc ... CPU: 1 PID: 1396 Comm: fw_fallback.sh Tainted: G W E 4.10.0-rc3-next-20170111+ #30 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.1-0-g8891697-prebuilt.qemu-project.org 04/01/2014 task: ffff9740b27f4340 task.stack: ffffbb15c0bc8000 RIP: 0010:_request_firmware+0xa27/0xad0 RSP: 0018:ffffbb15c0bcbd10 EFLAGS: 00010246 RAX: 00000000fffffffe RBX: ffff9740afe5aa80 RCX: 0000000000000000 RDX: ffff9740b27f4340 RSI: 0000000000000283 RDI: 0000000000000000 RBP: ffffbb15c0bcbd90 R08: ffffbb15c0bcbcd8 R09: 0000000000000000 R10: 0000000894a0d4b1 R11: 000000000000008c R12: ffffffffc0312480 R13: 0000000000000005 R14: ffff9740b1c32400 R15: 00000000000003e8 FS: 00007f8604422700(0000) GS:ffff9740bfc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 000000012164c000 CR4: 00000000000006e0 Call Trace: request_firmware+0x37/0x50 trigger_request_store+0x79/0xd0 [test_firmware] dev_attr_store+0x18/0x30 sysfs_kf_write+0x37/0x40 kernfs_fop_write+0x110/0x1a0 __vfs_write+0x37/0x160 ? _cond_resched+0x1a/0x50 vfs_write+0xb5/0x1a0 SyS_write+0x55/0xc0 ? trace_do_page_fault+0x37/0xd0 entry_SYSCALL_64_fastpath+0x1e/0xad RIP: 0033:0x7f8603f49620 RSP: 002b:00007fff6287b788 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000055c307b110a0 RCX: 00007f8603f49620 RDX: 0000000000000016 RSI: 000055c3084d8a90 RDI: 0000000000000001 RBP: 0000000000000016 R08: 000000000000c0ff R09: 000055c3084d6336 R10: 000055c307b108b0 R11: 0000000000000246 R12: 000055c307b13c80 R13: 000055c3084d6320 R14: 0000000000000000 R15: 00007fff6287b950 Code: 9f 64 84 e8 9c 61 fe ff b8 f4 ff ff ff e9 6b f9 ff ff 48 c7 c7 40 6b 8d 84 89 45 a8 e8 43 84 18 00 49 8b be 00 03 00 00 8b 45 a8 <83> 7f 38 02 74 08 e8 6e ec ff ff 8b 45 a8 49 c7 86 00 03 00 00 RIP: _request_firmware+0xa27/0xad0 RSP: ffffbb15c0bcbd10 CR2: 0000000000000038 ---[ end trace 6d94ac339c133e6f ]--- Fixes: 5d47ec02c37e ("firmware: Correct handling of fw_state_wait() return value") Reported-and-Tested-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reported-and-Tested-by: Patrick Bruenn <p.bruenn@beckhoff.com> Reported-by: Chris Wilson <chris@chris-wilson.co.uk> CC: <stable@vger.kernel.org> [3.10+] Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/usb/usbip/vudc.h')