November 2023 - Linux-stable-mirror

[PATCH AUTOSEL 4.14 1/4] clocksource/drivers/timer-imx-gpt: Fix potential memory leak

by Sasha Levin

From: Jacky Bai <ping.bai(a)nxp.com> [ Upstream commit 8051a993ce222a5158bccc6ac22ace9253dd71cb ] Fix coverity Issue CID 250382: Resource leak (RESOURCE_LEAK). Add kfree when error return. Signed-off-by: Jacky Bai <ping.bai(a)nxp.com> Reviewed-by: Peng Fan <peng.fan(a)nxp.com> Signed-off-by: Daniel Lezcano <daniel.lezcano(a)linaro.org> Link: https://lore.kernel.org/r/20231009083922.1942971-1-ping.bai@nxp.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/clocksource/timer-imx-gpt.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index 6ec6d79b237ce..fcc12f72e907f 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -489,12 +489,16 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t return -ENOMEM; imxtm->base = of_iomap(np, 0); - if (!imxtm->base) - return -ENXIO; + if (!imxtm->base) { + ret = -ENXIO; + goto err_kfree; + } imxtm->irq = irq_of_parse_and_map(np, 0); - if (imxtm->irq <= 0) - return -EINVAL; + if (imxtm->irq <= 0) { + ret = -EINVAL; + goto err_kfree; + } imxtm->clk_ipg = of_clk_get_by_name(np, "ipg"); @@ -507,11 +511,15 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t ret = _mxc_timer_init(imxtm); if (ret) - return ret; + goto err_kfree; initialized = 1; return 0; + +err_kfree: + kfree(imxtm); + return ret; } static int __init imx1_timer_init_dt(struct device_node *np) -- 2.42.0

2 years

2
5
0 0

[PATCH AUTOSEL 6.6 01/40] drm/gma500: Fix call trace when psb_gem_mm_init() fails

by Sasha Levin

From: Sui Jingfeng <suijingfeng(a)loongson.cn> [ Upstream commit da596080b2b400c50fe9f8f237bcaf09fed06af8 ] Because the gma_irq_install() is call after psb_gem_mm_init() function, when psb_gem_mm_init() fails, the interrupt line haven't been allocated. Yet the gma_irq_uninstall() is called in the psb_driver_unload() function without checking if checking the irq is registered or not. The calltrace is appended as following: [ 20.539253] ioremap memtype_reserve failed -16 [ 20.543895] gma500 0000:00:02.0: Failure to map stolen base. [ 20.565049] ------------[ cut here ]------------ [ 20.565066] Trying to free already-free IRQ 16 [ 20.565087] WARNING: CPU: 1 PID: 381 at kernel/irq/manage.c:1893 free_irq+0x209/0x370 [ 20.565316] CPU: 1 PID: 381 Comm: systemd-udevd Tainted: G C 6.5.0-rc1+ #368 [ 20.565329] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./IMB-140D Plus, BIOS P1.10 11/18/2013 [ 20.565338] RIP: 0010:free_irq+0x209/0x370 [ 20.565357] Code: 41 5d 41 5e 41 5f 5d 31 d2 89 d1 89 d6 89 d7 41 89 d1 c3 cc cc cc cc 8b 75 d0 48 c7 c7 e0 77 12 9f 4c 89 4d c8 e8 57 fe f4 ff <0f> 0b 48 8b 75 c8 4c 89 f7 e8 29 f3 f1 00 49 8b 47 40 48 8b 40 78 [ 20.565369] RSP: 0018:ffffae3b40733808 EFLAGS: 00010046 [ 20.565382] RAX: 0000000000000000 RBX: ffff9f8082bfe000 RCX: 0000000000000000 [ 20.565390] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 20.565397] RBP: ffffae3b40733840 R08: 0000000000000000 R09: 0000000000000000 [ 20.565405] R10: 0000000000000000 R11: 0000000000000000 R12: ffff9f80871c3100 [ 20.565413] R13: ffff9f80835d3360 R14: ffff9f80835d32a4 R15: ffff9f80835d3200 [ 20.565424] FS: 00007f13d36458c0(0000) GS:ffff9f8138880000(0000) knlGS:0000000000000000 [ 20.565434] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 20.565441] CR2: 00007f0d046f3f20 CR3: 0000000006c8c000 CR4: 00000000000006e0 [ 20.565450] Call Trace: [ 20.565458] <TASK> [ 20.565470] ? show_regs+0x72/0x90 [ 20.565488] ? free_irq+0x209/0x370 [ 20.565504] ? __warn+0x8d/0x160 [ 20.565520] ? free_irq+0x209/0x370 [ 20.565536] ? report_bug+0x1bb/0x1d0 [ 20.565555] ? handle_bug+0x46/0x90 [ 20.565572] ? exc_invalid_op+0x19/0x80 [ 20.565587] ? asm_exc_invalid_op+0x1b/0x20 [ 20.565607] ? free_irq+0x209/0x370 [ 20.565625] ? free_irq+0x209/0x370 [ 20.565644] gma_irq_uninstall+0x15b/0x1e0 [gma500_gfx] [ 20.565728] psb_driver_unload+0x27/0x190 [gma500_gfx] [ 20.565800] psb_pci_probe+0x5d2/0x790 [gma500_gfx] [ 20.565873] local_pci_probe+0x48/0xb0 [ 20.565892] pci_device_probe+0xc8/0x280 [ 20.565912] really_probe+0x1d2/0x440 [ 20.565929] __driver_probe_device+0x8a/0x190 [ 20.565944] driver_probe_device+0x23/0xd0 [ 20.565957] __driver_attach+0x10f/0x220 [ 20.565971] ? __pfx___driver_attach+0x10/0x10 [ 20.565984] bus_for_each_dev+0x7a/0xe0 [ 20.566002] driver_attach+0x1e/0x30 [ 20.566014] bus_add_driver+0x127/0x240 [ 20.566029] driver_register+0x64/0x140 [ 20.566043] ? __pfx_psb_init+0x10/0x10 [gma500_gfx] [ 20.566111] __pci_register_driver+0x68/0x80 [ 20.566128] psb_init+0x2c/0xff0 [gma500_gfx] [ 20.566194] do_one_initcall+0x46/0x330 [ 20.566214] ? kmalloc_trace+0x2a/0xb0 [ 20.566233] do_init_module+0x6a/0x270 [ 20.566250] load_module+0x207f/0x23a0 [ 20.566278] init_module_from_file+0x9c/0xf0 [ 20.566293] ? init_module_from_file+0x9c/0xf0 [ 20.566315] idempotent_init_module+0x184/0x240 [ 20.566335] __x64_sys_finit_module+0x64/0xd0 [ 20.566352] do_syscall_64+0x59/0x90 [ 20.566366] ? ksys_mmap_pgoff+0x123/0x270 [ 20.566378] ? __secure_computing+0x9b/0x110 [ 20.566392] ? exit_to_user_mode_prepare+0x39/0x190 [ 20.566406] ? syscall_exit_to_user_mode+0x2a/0x50 [ 20.566420] ? do_syscall_64+0x69/0x90 [ 20.566433] ? do_syscall_64+0x69/0x90 [ 20.566445] ? do_syscall_64+0x69/0x90 [ 20.566458] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 20.566472] RIP: 0033:0x7f13d351ea3d [ 20.566485] Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 a3 0f 00 f7 d8 64 89 01 48 [ 20.566496] RSP: 002b:00007ffe566c1fd8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [ 20.566510] RAX: ffffffffffffffda RBX: 000055e66806eec0 RCX: 00007f13d351ea3d [ 20.566519] RDX: 0000000000000000 RSI: 00007f13d36d9441 RDI: 0000000000000010 [ 20.566527] RBP: 0000000000020000 R08: 0000000000000000 R09: 0000000000000002 [ 20.566535] R10: 0000000000000010 R11: 0000000000000246 R12: 00007f13d36d9441 [ 20.566543] R13: 000055e6681108c0 R14: 000055e66805ba70 R15: 000055e66819a9c0 [ 20.566559] </TASK> [ 20.566566] ---[ end trace 0000000000000000 ]--- Signed-off-by: Sui Jingfeng <suijingfeng(a)loongson.cn> Signed-off-by: Patrik Jakobsson <patrik.r.jakobsson(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230727185855.713318-1-suiji… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/gma500/psb_drv.h | 1 + drivers/gpu/drm/gma500/psb_irq.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index f7f709df99b49..70d9adafa2333 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -424,6 +424,7 @@ struct drm_psb_private { uint32_t pipestat[PSB_NUM_PIPE]; spinlock_t irqmask_lock; + bool irq_enabled; /* Power */ bool pm_initialized; diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 343c51250207d..7bbb79b0497d8 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -327,6 +327,8 @@ int gma_irq_install(struct drm_device *dev) gma_irq_postinstall(dev); + dev_priv->irq_enabled = true; + return 0; } @@ -337,6 +339,9 @@ void gma_irq_uninstall(struct drm_device *dev) unsigned long irqflags; unsigned int i; + if (!dev_priv->irq_enabled) + return; + spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); if (dev_priv->ops->hotplug_enable) -- 2.42.0

2 years

3
42
0 0

[PATCH] mm: kmem: properly initialize local objcg variable in current_obj_cgroup()

by Roman Gushchin

Erhard reported that the 6.7-rc1 kernel panics on boot if being built with clang-16. The problem was not reproducible with gcc. [ 5.975049] general protection fault, probably for non-canonical address 0xf555515555555557: 0000 [#1] SMP KASAN PTI [ 5.976422] KASAN: maybe wild-memory-access in range [0xaaaaaaaaaaaaaab8-0xaaaaaaaaaaaaaabf] [ 5.977475] CPU: 3 PID: 1 Comm: systemd Not tainted 6.7.0-rc1-Zen3 #77 [ 5.977860] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 5.977860] RIP: 0010:obj_cgroup_charge_pages+0x27/0x2d5 [ 5.977860] Code: 90 90 90 55 41 57 41 56 41 55 41 54 53 89 d5 41 89 f6 49 89 ff 48 b8 00 00 00 00 00 fc ff df 49 83 c7 10 4d3 [ 5.977860] RSP: 0018:ffffc9000001fb18 EFLAGS: 00010a02 [ 5.977860] RAX: dffffc0000000000 RBX: aaaaaaaaaaaaaaaa RCX: ffff8883eb9a8b08 [ 5.977860] RDX: 0000000000000005 RSI: 0000000000400cc0 RDI: aaaaaaaaaaaaaaaa [ 5.977860] RBP: 0000000000000005 R08: 3333333333333333 R09: 0000000000000000 [ 5.977860] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8883eb9a8b18 [ 5.977860] R13: 1555555555555557 R14: 0000000000400cc0 R15: aaaaaaaaaaaaaaba [ 5.977860] FS: 00007f2976438b40(0000) GS:ffff8883eb980000(0000) knlGS:0000000000000000 [ 5.977860] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5.977860] CR2: 00007f29769e0060 CR3: 0000000107222003 CR4: 0000000000370eb0 [ 5.977860] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5.977860] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5.977860] Call Trace: [ 5.977860] <TASK> [ 5.977860] ? __die_body+0x16/0x75 [ 5.977860] ? die_addr+0x4a/0x70 [ 5.977860] ? exc_general_protection+0x1c9/0x2d0 [ 5.977860] ? cgroup_mkdir+0x455/0x9fb [ 5.977860] ? __x64_sys_mkdir+0x69/0x80 [ 5.977860] ? asm_exc_general_protection+0x26/0x30 [ 5.977860] ? obj_cgroup_charge_pages+0x27/0x2d5 [ 5.977860] obj_cgroup_charge+0x114/0x1ab [ 5.977860] pcpu_alloc+0x1a6/0xa65 [ 5.977860] ? mem_cgroup_css_alloc+0x1eb/0x1140 [ 5.977860] ? cgroup_apply_control_enable+0x26b/0x7c0 [ 5.977860] mem_cgroup_css_alloc+0x23f/0x1140 [ 5.977860] cgroup_apply_control_enable+0x26b/0x7c0 [ 5.977860] ? cgroup_kn_set_ugid+0x2d/0x1a0 [ 5.977860] cgroup_mkdir+0x455/0x9fb [ 5.977860] ? __cfi_cgroup_mkdir+0x10/0x10 [ 5.977860] kernfs_iop_mkdir+0x130/0x170 [ 5.977860] vfs_mkdir+0x405/0x530 [ 5.977860] do_mkdirat+0x188/0x1f0 [ 5.977860] __x64_sys_mkdir+0x69/0x80 [ 5.977860] do_syscall_64+0x7d/0x100 [ 5.977860] ? do_syscall_64+0x89/0x100 [ 5.977860] ? do_syscall_64+0x89/0x100 [ 5.977860] ? do_syscall_64+0x89/0x100 [ 5.977860] ? do_syscall_64+0x89/0x100 [ 5.977860] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 5.977860] RIP: 0033:0x7f297671defb [ 5.977860] Code: 8b 05 39 7f 0d 00 bb ff ff ff ff 64 c7 00 16 00 00 00 e9 61 ff ff ff e8 23 0c 02 00 0f 1f 00 f3 0f 1e fa b88 [ 5.977860] RSP: 002b:00007ffee6242bb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000053 [ 5.977860] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f297671defb [ 5.977860] RDX: 0000000000000000 RSI: 00000000000001ed RDI: 000055c6b449f0e0 [ 5.977860] RBP: 00007ffee6242bf0 R08: 000000000000000e R09: 0000000000000000 [ 5.977860] R10: 0000000000000000 R11: 0000000000000246 R12: 000055c6b445db80 [ 5.977860] R13: 00000000000003a0 R14: 00007f2976a68651 R15: 00000000000003a0 [ 5.977860] </TASK> [ 5.977860] Modules linked in: [ 6.014095] ---[ end trace 0000000000000000 ]--- [ 6.014701] RIP: 0010:obj_cgroup_charge_pages+0x27/0x2d5 [ 6.015348] Code: 90 90 90 55 41 57 41 56 41 55 41 54 53 89 d5 41 89 f6 49 89 ff 48 b8 00 00 00 00 00 fc ff df 49 83 c7 10 4d3 [ 6.017575] RSP: 0018:ffffc9000001fb18 EFLAGS: 00010a02 [ 6.018255] RAX: dffffc0000000000 RBX: aaaaaaaaaaaaaaaa RCX: ffff8883eb9a8b08 [ 6.019120] RDX: 0000000000000005 RSI: 0000000000400cc0 RDI: aaaaaaaaaaaaaaaa [ 6.019983] RBP: 0000000000000005 R08: 3333333333333333 R09: 0000000000000000 [ 6.020849] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8883eb9a8b18 [ 6.021747] R13: 1555555555555557 R14: 0000000000400cc0 R15: aaaaaaaaaaaaaaba [ 6.022609] FS: 00007f2976438b40(0000) GS:ffff8883eb980000(0000) knlGS:0000000000000000 [ 6.023593] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6.024296] CR2: 00007f29769e0060 CR3: 0000000107222003 CR4: 0000000000370eb0 [ 6.025279] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 6.026139] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 6.027000] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Actually the problem is caused by uninitialized local variable in current_obj_cgroup(). If the root memory cgroup is set as an active memory cgroup for a charging scope (as in the trace, where systemd tries to create the first non-root cgroup, so the parent cgroup is the root cgroup), the "for" loop is skipped and uninitialized objcg is returned, causing a panic down the accounting stack. The fix is trivial: initialize the objcg variable to NULL unconditionally before the "for" loop. Fixes: e86828e5446d ("mm: kmem: scoped objcg protection") Reported-by: Erhard Furtner <erhard_f(a)mailbox.org> Closes: https://github.com/ClangBuiltLinux/linux/issues/1959 Signed-off-by: Roman Gushchin (Cruise) <roman.gushchin(a)linux.dev> Cc: Shakeel Butt <shakeelb(a)google.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: David Rientjes <rientjes(a)google.com> Cc: Dennis Zhou <dennis(a)kernel.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: stable(a)vger.kernel.org --- mm/memcontrol.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 774bd6e21e27..b138501e6489 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3165,6 +3165,7 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void) return NULL; from_memcg: + objcg = NULL; for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) { /* * Memcg pointer is protected by scope (see set_active_memcg()) -- 2.42.0

2 years

4
5
0 0

FAILED: patch "[PATCH] tracing: Have trace_event_file have ref counters" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023110612-tribute-salvage-1b7f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Tue, 31 Oct 2023 12:24:53 -0400 Subject: [PATCH] tracing: Have trace_event_file have ref counters The following can crash the kernel: # cd /sys/kernel/tracing # echo 'p:sched schedule' > kprobe_events # exec 5>>events/kprobes/sched/enable # > kprobe_events # exec 5>&- The above commands: 1. Change directory to the tracefs directory 2. Create a kprobe event (doesn't matter what one) 3. Open bash file descriptor 5 on the enable file of the kprobe event 4. Delete the kprobe event (removes the files too) 5. Close the bash file descriptor 5 The above causes a crash! BUG: kernel NULL pointer dereference, address: 0000000000000028 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 6 PID: 877 Comm: bash Not tainted 6.5.0-rc4-test-00008-g2c6b6b1029d4-dirty #186 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:tracing_release_file_tr+0xc/0x50 What happens here is that the kprobe event creates a trace_event_file "file" descriptor that represents the file in tracefs to the event. It maintains state of the event (is it enabled for the given instance?). Opening the "enable" file gets a reference to the event "file" descriptor via the open file descriptor. When the kprobe event is deleted, the file is also deleted from the tracefs system which also frees the event "file" descriptor. But as the tracefs file is still opened by user space, it will not be totally removed until the final dput() is called on it. But this is not true with the event "file" descriptor that is already freed. If the user does a write to or simply closes the file descriptor it will reference the event "file" descriptor that was just freed, causing a use-after-free bug. To solve this, add a ref count to the event "file" descriptor as well as a new flag called "FREED". The "file" will not be freed until the last reference is released. But the FREE flag will be set when the event is removed to prevent any more modifications to that event from happening, even if there's still a reference to the event "file" descriptor. Link: https://lore.kernel.org/linux-trace-kernel/20231031000031.1e705592@gandalf.… Link: https://lore.kernel.org/linux-trace-kernel/20231031122453.7a48b923@gandalf.… Cc: stable(a)vger.kernel.org Cc: Mark Rutland <mark.rutland(a)arm.com> Fixes: f5ca233e2e66d ("tracing: Increase trace array ref count on enable and filter files") Reported-by: Beau Belgrave <beaub(a)linux.microsoft.com> Tested-by: Beau Belgrave <beaub(a)linux.microsoft.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 12207dc6722d..696f8dc4aa53 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -492,6 +492,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, EVENT_FILE_FL_WAS_ENABLED_BIT, + EVENT_FILE_FL_FREED_BIT, }; extern struct trace_event_file *trace_get_event_file(const char *instance, @@ -630,6 +631,7 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid * WAS_ENABLED - Set when enabled to know to clear trace on module removal + * FREED - File descriptor is freed, all fields should be considered invalid */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), @@ -643,6 +645,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), + EVENT_FILE_FL_FREED = (1 << EVENT_FILE_FL_FREED_BIT), }; struct trace_event_file { @@ -671,6 +674,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2539cfc20a97..9aebf904ff97 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4978,6 +4978,20 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp) if (ret) return ret; + mutex_lock(&event_mutex); + + /* Fail if the file is marked for removal */ + if (file->flags & EVENT_FILE_FL_FREED) { + trace_array_put(file->tr); + ret = -ENODEV; + } else { + event_file_get(file); + } + + mutex_unlock(&event_mutex); + if (ret) + return ret; + filp->private_data = inode->i_private; return 0; @@ -4988,6 +5002,7 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); + event_file_put(file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0e1405abf4f7..b7f4ea25a194 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1669,6 +1669,9 @@ extern void event_trigger_unregister(struct event_command *cmd_ops, char *glob, struct event_trigger_data *trigger_data); +extern void event_file_get(struct trace_event_file *file); +extern void event_file_put(struct trace_event_file *file); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f9e3e24d8796..f29e815ca5b2 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -990,13 +990,35 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) } } +void event_file_get(struct trace_event_file *file) +{ + atomic_inc(&file->ref); +} + +void event_file_put(struct trace_event_file *file) +{ + if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (file->flags & EVENT_FILE_FL_FREED) + kmem_cache_free(file_cachep, file); + return; + } + + if (atomic_dec_and_test(&file->ref)) { + /* Count should only go to zero when it is freed */ + if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) + return; + kmem_cache_free(file_cachep, file); + } +} + static void remove_event_file_dir(struct trace_event_file *file) { eventfs_remove_dir(file->ei); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); - kmem_cache_free(file_cachep, file); + file->flags |= EVENT_FILE_FL_FREED; + event_file_put(file); } /* @@ -1369,7 +1391,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, flags = file->flags; mutex_unlock(&event_mutex); - if (!file) + if (!file || flags & EVENT_FILE_FL_FREED) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && @@ -1403,7 +1425,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_data(filp); - if (likely(file)) { + if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) { ret = tracing_update_buffers(file->tr); if (ret < 0) { mutex_unlock(&event_mutex); @@ -1683,7 +1705,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); file = event_file_data(filp); - if (file) + if (file && !(file->flags & EVENT_FILE_FL_FREED)) print_event_filter(file, s); mutex_unlock(&event_mutex); @@ -2902,6 +2924,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); + event_file_get(file); return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 33264e510d16..0c611b281a5b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2349,6 +2349,9 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) struct event_filter *filter = NULL; int err; + if (file->flags & EVENT_FILE_FL_FREED) + return -ENODEV; + if (!strcmp(strstrip(filter_string), "0")) { filter_disable(file); filter = event_filter(file);

2 years

2
1
0 0

FAILED: patch "[PATCH] tracing: Have trace_event_file have ref counters" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023110609-mulled-exes-50b1@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Tue, 31 Oct 2023 12:24:53 -0400 Subject: [PATCH] tracing: Have trace_event_file have ref counters The following can crash the kernel: # cd /sys/kernel/tracing # echo 'p:sched schedule' > kprobe_events # exec 5>>events/kprobes/sched/enable # > kprobe_events # exec 5>&- The above commands: 1. Change directory to the tracefs directory 2. Create a kprobe event (doesn't matter what one) 3. Open bash file descriptor 5 on the enable file of the kprobe event 4. Delete the kprobe event (removes the files too) 5. Close the bash file descriptor 5 The above causes a crash! BUG: kernel NULL pointer dereference, address: 0000000000000028 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 6 PID: 877 Comm: bash Not tainted 6.5.0-rc4-test-00008-g2c6b6b1029d4-dirty #186 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:tracing_release_file_tr+0xc/0x50 What happens here is that the kprobe event creates a trace_event_file "file" descriptor that represents the file in tracefs to the event. It maintains state of the event (is it enabled for the given instance?). Opening the "enable" file gets a reference to the event "file" descriptor via the open file descriptor. When the kprobe event is deleted, the file is also deleted from the tracefs system which also frees the event "file" descriptor. But as the tracefs file is still opened by user space, it will not be totally removed until the final dput() is called on it. But this is not true with the event "file" descriptor that is already freed. If the user does a write to or simply closes the file descriptor it will reference the event "file" descriptor that was just freed, causing a use-after-free bug. To solve this, add a ref count to the event "file" descriptor as well as a new flag called "FREED". The "file" will not be freed until the last reference is released. But the FREE flag will be set when the event is removed to prevent any more modifications to that event from happening, even if there's still a reference to the event "file" descriptor. Link: https://lore.kernel.org/linux-trace-kernel/20231031000031.1e705592@gandalf.… Link: https://lore.kernel.org/linux-trace-kernel/20231031122453.7a48b923@gandalf.… Cc: stable(a)vger.kernel.org Cc: Mark Rutland <mark.rutland(a)arm.com> Fixes: f5ca233e2e66d ("tracing: Increase trace array ref count on enable and filter files") Reported-by: Beau Belgrave <beaub(a)linux.microsoft.com> Tested-by: Beau Belgrave <beaub(a)linux.microsoft.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 12207dc6722d..696f8dc4aa53 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -492,6 +492,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, EVENT_FILE_FL_WAS_ENABLED_BIT, + EVENT_FILE_FL_FREED_BIT, }; extern struct trace_event_file *trace_get_event_file(const char *instance, @@ -630,6 +631,7 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid * WAS_ENABLED - Set when enabled to know to clear trace on module removal + * FREED - File descriptor is freed, all fields should be considered invalid */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), @@ -643,6 +645,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), + EVENT_FILE_FL_FREED = (1 << EVENT_FILE_FL_FREED_BIT), }; struct trace_event_file { @@ -671,6 +674,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2539cfc20a97..9aebf904ff97 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4978,6 +4978,20 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp) if (ret) return ret; + mutex_lock(&event_mutex); + + /* Fail if the file is marked for removal */ + if (file->flags & EVENT_FILE_FL_FREED) { + trace_array_put(file->tr); + ret = -ENODEV; + } else { + event_file_get(file); + } + + mutex_unlock(&event_mutex); + if (ret) + return ret; + filp->private_data = inode->i_private; return 0; @@ -4988,6 +5002,7 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); + event_file_put(file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0e1405abf4f7..b7f4ea25a194 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1669,6 +1669,9 @@ extern void event_trigger_unregister(struct event_command *cmd_ops, char *glob, struct event_trigger_data *trigger_data); +extern void event_file_get(struct trace_event_file *file); +extern void event_file_put(struct trace_event_file *file); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f9e3e24d8796..f29e815ca5b2 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -990,13 +990,35 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) } } +void event_file_get(struct trace_event_file *file) +{ + atomic_inc(&file->ref); +} + +void event_file_put(struct trace_event_file *file) +{ + if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (file->flags & EVENT_FILE_FL_FREED) + kmem_cache_free(file_cachep, file); + return; + } + + if (atomic_dec_and_test(&file->ref)) { + /* Count should only go to zero when it is freed */ + if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) + return; + kmem_cache_free(file_cachep, file); + } +} + static void remove_event_file_dir(struct trace_event_file *file) { eventfs_remove_dir(file->ei); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); - kmem_cache_free(file_cachep, file); + file->flags |= EVENT_FILE_FL_FREED; + event_file_put(file); } /* @@ -1369,7 +1391,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, flags = file->flags; mutex_unlock(&event_mutex); - if (!file) + if (!file || flags & EVENT_FILE_FL_FREED) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && @@ -1403,7 +1425,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_data(filp); - if (likely(file)) { + if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) { ret = tracing_update_buffers(file->tr); if (ret < 0) { mutex_unlock(&event_mutex); @@ -1683,7 +1705,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); file = event_file_data(filp); - if (file) + if (file && !(file->flags & EVENT_FILE_FL_FREED)) print_event_filter(file, s); mutex_unlock(&event_mutex); @@ -2902,6 +2924,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); + event_file_get(file); return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 33264e510d16..0c611b281a5b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2349,6 +2349,9 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) struct event_filter *filter = NULL; int err; + if (file->flags & EVENT_FILE_FL_FREED) + return -ENODEV; + if (!strcmp(strstrip(filter_string), "0")) { filter_disable(file); filter = event_filter(file);

2 years

2
2
0 0

FAILED: patch "[PATCH] tracing: Have trace_event_file have ref counters" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023110607-destruct-footsore-9353@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Tue, 31 Oct 2023 12:24:53 -0400 Subject: [PATCH] tracing: Have trace_event_file have ref counters The following can crash the kernel: # cd /sys/kernel/tracing # echo 'p:sched schedule' > kprobe_events # exec 5>>events/kprobes/sched/enable # > kprobe_events # exec 5>&- The above commands: 1. Change directory to the tracefs directory 2. Create a kprobe event (doesn't matter what one) 3. Open bash file descriptor 5 on the enable file of the kprobe event 4. Delete the kprobe event (removes the files too) 5. Close the bash file descriptor 5 The above causes a crash! BUG: kernel NULL pointer dereference, address: 0000000000000028 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 6 PID: 877 Comm: bash Not tainted 6.5.0-rc4-test-00008-g2c6b6b1029d4-dirty #186 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:tracing_release_file_tr+0xc/0x50 What happens here is that the kprobe event creates a trace_event_file "file" descriptor that represents the file in tracefs to the event. It maintains state of the event (is it enabled for the given instance?). Opening the "enable" file gets a reference to the event "file" descriptor via the open file descriptor. When the kprobe event is deleted, the file is also deleted from the tracefs system which also frees the event "file" descriptor. But as the tracefs file is still opened by user space, it will not be totally removed until the final dput() is called on it. But this is not true with the event "file" descriptor that is already freed. If the user does a write to or simply closes the file descriptor it will reference the event "file" descriptor that was just freed, causing a use-after-free bug. To solve this, add a ref count to the event "file" descriptor as well as a new flag called "FREED". The "file" will not be freed until the last reference is released. But the FREE flag will be set when the event is removed to prevent any more modifications to that event from happening, even if there's still a reference to the event "file" descriptor. Link: https://lore.kernel.org/linux-trace-kernel/20231031000031.1e705592@gandalf.… Link: https://lore.kernel.org/linux-trace-kernel/20231031122453.7a48b923@gandalf.… Cc: stable(a)vger.kernel.org Cc: Mark Rutland <mark.rutland(a)arm.com> Fixes: f5ca233e2e66d ("tracing: Increase trace array ref count on enable and filter files") Reported-by: Beau Belgrave <beaub(a)linux.microsoft.com> Tested-by: Beau Belgrave <beaub(a)linux.microsoft.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 12207dc6722d..696f8dc4aa53 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -492,6 +492,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, EVENT_FILE_FL_WAS_ENABLED_BIT, + EVENT_FILE_FL_FREED_BIT, }; extern struct trace_event_file *trace_get_event_file(const char *instance, @@ -630,6 +631,7 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid * WAS_ENABLED - Set when enabled to know to clear trace on module removal + * FREED - File descriptor is freed, all fields should be considered invalid */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), @@ -643,6 +645,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), + EVENT_FILE_FL_FREED = (1 << EVENT_FILE_FL_FREED_BIT), }; struct trace_event_file { @@ -671,6 +674,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2539cfc20a97..9aebf904ff97 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4978,6 +4978,20 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp) if (ret) return ret; + mutex_lock(&event_mutex); + + /* Fail if the file is marked for removal */ + if (file->flags & EVENT_FILE_FL_FREED) { + trace_array_put(file->tr); + ret = -ENODEV; + } else { + event_file_get(file); + } + + mutex_unlock(&event_mutex); + if (ret) + return ret; + filp->private_data = inode->i_private; return 0; @@ -4988,6 +5002,7 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); + event_file_put(file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0e1405abf4f7..b7f4ea25a194 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1669,6 +1669,9 @@ extern void event_trigger_unregister(struct event_command *cmd_ops, char *glob, struct event_trigger_data *trigger_data); +extern void event_file_get(struct trace_event_file *file); +extern void event_file_put(struct trace_event_file *file); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f9e3e24d8796..f29e815ca5b2 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -990,13 +990,35 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) } } +void event_file_get(struct trace_event_file *file) +{ + atomic_inc(&file->ref); +} + +void event_file_put(struct trace_event_file *file) +{ + if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (file->flags & EVENT_FILE_FL_FREED) + kmem_cache_free(file_cachep, file); + return; + } + + if (atomic_dec_and_test(&file->ref)) { + /* Count should only go to zero when it is freed */ + if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) + return; + kmem_cache_free(file_cachep, file); + } +} + static void remove_event_file_dir(struct trace_event_file *file) { eventfs_remove_dir(file->ei); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); - kmem_cache_free(file_cachep, file); + file->flags |= EVENT_FILE_FL_FREED; + event_file_put(file); } /* @@ -1369,7 +1391,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, flags = file->flags; mutex_unlock(&event_mutex); - if (!file) + if (!file || flags & EVENT_FILE_FL_FREED) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && @@ -1403,7 +1425,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_data(filp); - if (likely(file)) { + if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) { ret = tracing_update_buffers(file->tr); if (ret < 0) { mutex_unlock(&event_mutex); @@ -1683,7 +1705,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); file = event_file_data(filp); - if (file) + if (file && !(file->flags & EVENT_FILE_FL_FREED)) print_event_filter(file, s); mutex_unlock(&event_mutex); @@ -2902,6 +2924,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); + event_file_get(file); return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 33264e510d16..0c611b281a5b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2349,6 +2349,9 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) struct event_filter *filter = NULL; int err; + if (file->flags & EVENT_FILE_FL_FREED) + return -ENODEV; + if (!strcmp(strstrip(filter_string), "0")) { filter_disable(file); filter = event_filter(file);

2 years

2
1
0 0

FAILED: patch "[PATCH] tracing: Have trace_event_file have ref counters" failed to apply to 6.5-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.5-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.5.y git checkout FETCH_HEAD git cherry-pick -x bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023110605-thirty-account-3d1a@gregkh' --subject-prefix 'PATCH 6.5.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bb32500fb9b78215e4ef6ee8b4345c5f5d7eafb4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Tue, 31 Oct 2023 12:24:53 -0400 Subject: [PATCH] tracing: Have trace_event_file have ref counters The following can crash the kernel: # cd /sys/kernel/tracing # echo 'p:sched schedule' > kprobe_events # exec 5>>events/kprobes/sched/enable # > kprobe_events # exec 5>&- The above commands: 1. Change directory to the tracefs directory 2. Create a kprobe event (doesn't matter what one) 3. Open bash file descriptor 5 on the enable file of the kprobe event 4. Delete the kprobe event (removes the files too) 5. Close the bash file descriptor 5 The above causes a crash! BUG: kernel NULL pointer dereference, address: 0000000000000028 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 6 PID: 877 Comm: bash Not tainted 6.5.0-rc4-test-00008-g2c6b6b1029d4-dirty #186 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:tracing_release_file_tr+0xc/0x50 What happens here is that the kprobe event creates a trace_event_file "file" descriptor that represents the file in tracefs to the event. It maintains state of the event (is it enabled for the given instance?). Opening the "enable" file gets a reference to the event "file" descriptor via the open file descriptor. When the kprobe event is deleted, the file is also deleted from the tracefs system which also frees the event "file" descriptor. But as the tracefs file is still opened by user space, it will not be totally removed until the final dput() is called on it. But this is not true with the event "file" descriptor that is already freed. If the user does a write to or simply closes the file descriptor it will reference the event "file" descriptor that was just freed, causing a use-after-free bug. To solve this, add a ref count to the event "file" descriptor as well as a new flag called "FREED". The "file" will not be freed until the last reference is released. But the FREE flag will be set when the event is removed to prevent any more modifications to that event from happening, even if there's still a reference to the event "file" descriptor. Link: https://lore.kernel.org/linux-trace-kernel/20231031000031.1e705592@gandalf.… Link: https://lore.kernel.org/linux-trace-kernel/20231031122453.7a48b923@gandalf.… Cc: stable(a)vger.kernel.org Cc: Mark Rutland <mark.rutland(a)arm.com> Fixes: f5ca233e2e66d ("tracing: Increase trace array ref count on enable and filter files") Reported-by: Beau Belgrave <beaub(a)linux.microsoft.com> Tested-by: Beau Belgrave <beaub(a)linux.microsoft.com> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 12207dc6722d..696f8dc4aa53 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -492,6 +492,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, EVENT_FILE_FL_WAS_ENABLED_BIT, + EVENT_FILE_FL_FREED_BIT, }; extern struct trace_event_file *trace_get_event_file(const char *instance, @@ -630,6 +631,7 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid * WAS_ENABLED - Set when enabled to know to clear trace on module removal + * FREED - File descriptor is freed, all fields should be considered invalid */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), @@ -643,6 +645,7 @@ enum { EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), + EVENT_FILE_FL_FREED = (1 << EVENT_FILE_FL_FREED_BIT), }; struct trace_event_file { @@ -671,6 +674,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2539cfc20a97..9aebf904ff97 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4978,6 +4978,20 @@ int tracing_open_file_tr(struct inode *inode, struct file *filp) if (ret) return ret; + mutex_lock(&event_mutex); + + /* Fail if the file is marked for removal */ + if (file->flags & EVENT_FILE_FL_FREED) { + trace_array_put(file->tr); + ret = -ENODEV; + } else { + event_file_get(file); + } + + mutex_unlock(&event_mutex); + if (ret) + return ret; + filp->private_data = inode->i_private; return 0; @@ -4988,6 +5002,7 @@ int tracing_release_file_tr(struct inode *inode, struct file *filp) struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); + event_file_put(file); return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0e1405abf4f7..b7f4ea25a194 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1669,6 +1669,9 @@ extern void event_trigger_unregister(struct event_command *cmd_ops, char *glob, struct event_trigger_data *trigger_data); +extern void event_file_get(struct trace_event_file *file); +extern void event_file_put(struct trace_event_file *file); + /** * struct event_trigger_ops - callbacks for trace event triggers * diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f9e3e24d8796..f29e815ca5b2 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -990,13 +990,35 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) } } +void event_file_get(struct trace_event_file *file) +{ + atomic_inc(&file->ref); +} + +void event_file_put(struct trace_event_file *file) +{ + if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (file->flags & EVENT_FILE_FL_FREED) + kmem_cache_free(file_cachep, file); + return; + } + + if (atomic_dec_and_test(&file->ref)) { + /* Count should only go to zero when it is freed */ + if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) + return; + kmem_cache_free(file_cachep, file); + } +} + static void remove_event_file_dir(struct trace_event_file *file) { eventfs_remove_dir(file->ei); list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); - kmem_cache_free(file_cachep, file); + file->flags |= EVENT_FILE_FL_FREED; + event_file_put(file); } /* @@ -1369,7 +1391,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, flags = file->flags; mutex_unlock(&event_mutex); - if (!file) + if (!file || flags & EVENT_FILE_FL_FREED) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && @@ -1403,7 +1425,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_data(filp); - if (likely(file)) { + if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) { ret = tracing_update_buffers(file->tr); if (ret < 0) { mutex_unlock(&event_mutex); @@ -1683,7 +1705,7 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); file = event_file_data(filp); - if (file) + if (file && !(file->flags & EVENT_FILE_FL_FREED)) print_event_filter(file, s); mutex_unlock(&event_mutex); @@ -2902,6 +2924,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); + event_file_get(file); return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 33264e510d16..0c611b281a5b 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2349,6 +2349,9 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) struct event_filter *filter = NULL; int err; + if (file->flags & EVENT_FILE_FL_FREED) + return -ENODEV; + if (!strcmp(strstrip(filter_string), "0")) { filter_disable(file); filter = event_filter(file);

2 years

2
2
0 0

We Can Finance Your Business / Projects

by Amir Aziz

Greetings, We are a consultancy firm situated in Bahrain currently looking to finance new or existing projects in any industry. Currently we are sourcing for opportunities for our review and consideration and would be delighted to discuss further. Please feel free to contact us if you wish to proceed via our email : amiraziz(a)wealthconsultantmanagers.com Regards, Amir Aziz N:B We will never charge or ask for any upfront fees of any sort.

2 years

1
0
0 0

[PATCH net 1/2] net: ti: am65-cpsw-nuss: Fix devlink warning on module removal

by Roger Quadros

devlink_port_unregister() should be called after unregister_netdev() so that the devlink_port->type is set to DEVLINK_PORT_TYPE_NOTSET and avoids the below warning. [ 48.511030] WARNING: CPU: 2 PID: 683 at net/devlink/port.c:1077 devl_port_unregister+0x80/0xa8 CC: stable(a)vger.kernel.org # v6.6+ Fixes: 58356eb31d60 ("net: ti: am65-cpsw-nuss: Add devlink support") Signed-off-by: Roger Quadros <rogerq(a)kernel.org> --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index ece9f8df98ae..cbbede094b2c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -3011,13 +3011,13 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) if (ret < 0) return ret; - am65_cpsw_unregister_devlink(common); am65_cpsw_unregister_notifiers(common); /* must unregister ndevs here because DD release_driver routine calls * dma_deconfigure(dev) before devres_release_all(dev) */ am65_cpsw_nuss_cleanup_ndev(common); + am65_cpsw_unregister_devlink(common); am65_cpsw_nuss_phylink_cleanup(common); am65_cpts_release(common->cpts); am65_cpsw_disable_serdes_phy(common); -- 2.34.1

2 years, 1 month

1
0
0 0

[PATCH 01/32] fbdev/acornfb: Fix name of fb_ops initializer macro

by Thomas Zimmermann

Fix build by using the correct name for the initializer macro for struct fb_ops. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: 9037afde8b9d ("fbdev/acornfb: Use fbdev I/O helpers") Cc: Thomas Zimmermann <tzimmermann(a)suse.de> Cc: Sam Ravnborg <sam(a)ravnborg.org> Cc: Helge Deller <deller(a)gmx.de> Cc: Javier Martinez Canillas <javierm(a)redhat.com> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: <stable(a)vger.kernel.org> # v6.6+ --- drivers/video/fbdev/acornfb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c index 163d2c9f951c3..f0600f6ca2548 100644 --- a/drivers/video/fbdev/acornfb.c +++ b/drivers/video/fbdev/acornfb.c @@ -605,7 +605,7 @@ acornfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) static const struct fb_ops acornfb_ops = { .owner = THIS_MODULE, - FB_IOMEM_DEFAULT_OPS, + FB_DEFAULT_IOMEM_OPS, .fb_check_var = acornfb_check_var, .fb_set_par = acornfb_set_par, .fb_setcolreg = acornfb_setcolreg, -- 2.42.0

2 years, 1 month

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2023