From: Greg Kroah-Hartman Date: Thu, 11 Apr 2024 07:50:13 +0000 (+0200) Subject: 5.4-stable patches X-Git-Tag: v4.19.312~37 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=5ad0546fad3f263e53c3fa3ffef39695c19d3ce1;p=thirdparty%2Fkernel%2Fstable-queue.git 5.4-stable patches added patches: drm-i915-gt-reset-queue_priority_hint-on-parking.patch drm-vkms-call-drm_atomic_helper_shutdown-before-drm_dev_put.patch virtio-reenable-config-if-freezing-device-failed.patch x86-alternative-don-t-call-text_poke-in-lazy-tlb-mode.patch x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch --- diff --git a/queue-5.4/drm-i915-gt-reset-queue_priority_hint-on-parking.patch b/queue-5.4/drm-i915-gt-reset-queue_priority_hint-on-parking.patch new file mode 100644 index 00000000000..71ced2a39db --- /dev/null +++ b/queue-5.4/drm-i915-gt-reset-queue_priority_hint-on-parking.patch @@ -0,0 +1,122 @@ +From 4a3859ea5240365d21f6053ee219bb240d520895 Mon Sep 17 00:00:00 2001 +From: Chris Wilson +Date: Mon, 18 Mar 2024 14:58:47 +0100 +Subject: drm/i915/gt: Reset queue_priority_hint on parking + +From: Chris Wilson + +commit 4a3859ea5240365d21f6053ee219bb240d520895 upstream. + +Originally, with strict in order execution, we could complete execution +only when the queue was empty. Preempt-to-busy allows replacement of an +active request that may complete before the preemption is processed by +HW. If that happens, the request is retired from the queue, but the +queue_priority_hint remains set, preventing direct submission until +after the next CS interrupt is processed. + +This preempt-to-busy race can be triggered by the heartbeat, which will +also act as the power-management barrier and upon completion allow us to +idle the HW. We may process the completion of the heartbeat, and begin +parking the engine before the CS event that restores the +queue_priority_hint, causing us to fail the assertion that it is MIN. + +<3>[ 166.210729] __engine_park:283 GEM_BUG_ON(engine->sched_engine->queue_priority_hint != (-((int)(~0U >> 1)) - 1)) +<0>[ 166.210781] Dumping ftrace buffer: +<0>[ 166.210795] --------------------------------- +... +<0>[ 167.302811] drm_fdin-1097 2..s1. 165741070us : trace_ports: 0000:00:02.0 rcs0: promote { ccid:20 1217:2 prio 0 } +<0>[ 167.302861] drm_fdin-1097 2d.s2. 165741072us : execlists_submission_tasklet: 0000:00:02.0 rcs0: preempting last=1217:2, prio=0, hint=2147483646 +<0>[ 167.302928] drm_fdin-1097 2d.s2. 165741072us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 1217:2, current 0 +<0>[ 167.302992] drm_fdin-1097 2d.s2. 165741073us : __i915_request_submit: 0000:00:02.0 rcs0: fence 3:4660, current 4659 +<0>[ 167.303044] drm_fdin-1097 2d.s1. 165741076us : execlists_submission_tasklet: 0000:00:02.0 rcs0: context:3 schedule-in, ccid:40 +<0>[ 167.303095] drm_fdin-1097 2d.s1. 165741077us : trace_ports: 0000:00:02.0 rcs0: submit { ccid:40 3:4660* prio 2147483646 } +<0>[ 167.303159] kworker/-89 11..... 165741139us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence c90:2, current 2 +<0>[ 167.303208] kworker/-89 11..... 165741148us : __intel_context_do_unpin: 0000:00:02.0 rcs0: context:c90 unpin +<0>[ 167.303272] kworker/-89 11..... 165741159us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence 1217:2, current 2 +<0>[ 167.303321] kworker/-89 11..... 165741166us : __intel_context_do_unpin: 0000:00:02.0 rcs0: context:1217 unpin +<0>[ 167.303384] kworker/-89 11..... 165741170us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence 3:4660, current 4660 +<0>[ 167.303434] kworker/-89 11d..1. 165741172us : __intel_context_retire: 0000:00:02.0 rcs0: context:1216 retire runtime: { total:56028ns, avg:56028ns } +<0>[ 167.303484] kworker/-89 11..... 165741198us : __engine_park: 0000:00:02.0 rcs0: parked +<0>[ 167.303534] -0 5d.H3. 165741207us : execlists_irq_handler: 0000:00:02.0 rcs0: semaphore yield: 00000040 +<0>[ 167.303583] kworker/-89 11..... 165741397us : __intel_context_retire: 0000:00:02.0 rcs0: context:1217 retire runtime: { total:325575ns, avg:0ns } +<0>[ 167.303756] kworker/-89 11..... 165741777us : __intel_context_retire: 0000:00:02.0 rcs0: context:c90 retire runtime: { total:0ns, avg:0ns } +<0>[ 167.303806] kworker/-89 11..... 165742017us : __engine_park: __engine_park:283 GEM_BUG_ON(engine->sched_engine->queue_priority_hint != (-((int)(~0U >> 1)) - 1)) +<0>[ 167.303811] --------------------------------- +<4>[ 167.304722] ------------[ cut here ]------------ +<2>[ 167.304725] kernel BUG at drivers/gpu/drm/i915/gt/intel_engine_pm.c:283! +<4>[ 167.304731] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI +<4>[ 167.304734] CPU: 11 PID: 89 Comm: kworker/11:1 Tainted: G W 6.8.0-rc2-CI_DRM_14193-gc655e0fd2804+ #1 +<4>[ 167.304736] Hardware name: Intel Corporation Rocket Lake Client Platform/RocketLake S UDIMM 6L RVP, BIOS RKLSFWI1.R00.3173.A03.2204210138 04/21/2022 +<4>[ 167.304738] Workqueue: i915-unordered retire_work_handler [i915] +<4>[ 167.304839] RIP: 0010:__engine_park+0x3fd/0x680 [i915] +<4>[ 167.304937] Code: 00 48 c7 c2 b0 e5 86 a0 48 8d 3d 00 00 00 00 e8 79 48 d4 e0 bf 01 00 00 00 e8 ef 0a d4 e0 31 f6 bf 09 00 00 00 e8 03 49 c0 e0 <0f> 0b 0f 0b be 01 00 00 00 e8 f5 61 fd ff 31 c0 e9 34 fd ff ff 48 +<4>[ 167.304940] RSP: 0018:ffffc9000059fce0 EFLAGS: 00010246 +<4>[ 167.304942] RAX: 0000000000000200 RBX: 0000000000000000 RCX: 0000000000000006 +<4>[ 167.304944] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000009 +<4>[ 167.304946] RBP: ffff8881330ca1b0 R08: 0000000000000001 R09: 0000000000000001 +<4>[ 167.304947] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8881330ca000 +<4>[ 167.304948] R13: ffff888110f02aa0 R14: ffff88812d1d0205 R15: ffff88811277d4f0 +<4>[ 167.304950] FS: 0000000000000000(0000) GS:ffff88844f780000(0000) knlGS:0000000000000000 +<4>[ 167.304952] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +<4>[ 167.304953] CR2: 00007fc362200c40 CR3: 000000013306e003 CR4: 0000000000770ef0 +<4>[ 167.304955] PKRU: 55555554 +<4>[ 167.304957] Call Trace: +<4>[ 167.304958] +<4>[ 167.305573] ____intel_wakeref_put_last+0x1d/0x80 [i915] +<4>[ 167.305685] i915_request_retire.part.0+0x34f/0x600 [i915] +<4>[ 167.305800] retire_requests+0x51/0x80 [i915] +<4>[ 167.305892] intel_gt_retire_requests_timeout+0x27f/0x700 [i915] +<4>[ 167.305985] process_scheduled_works+0x2db/0x530 +<4>[ 167.305990] worker_thread+0x18c/0x350 +<4>[ 167.305993] kthread+0xfe/0x130 +<4>[ 167.305997] ret_from_fork+0x2c/0x50 +<4>[ 167.306001] ret_from_fork_asm+0x1b/0x30 +<4>[ 167.306004] + +It is necessary for the queue_priority_hint to be lower than the next +request submission upon waking up, as we rely on the hint to decide when +to kick the tasklet to submit that first request. + +Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy") +Closes: https://gitlab.freedesktop.org/drm/intel/issues/10154 +Signed-off-by: Chris Wilson +Signed-off-by: Janusz Krzysztofik +Cc: Mika Kuoppala +Cc: # v5.4+ +Reviewed-by: Rodrigo Vivi +Reviewed-by: Andi Shyti +Signed-off-by: Andi Shyti +Link: https://patchwork.freedesktop.org/patch/msgid/20240318135906.716055-2-janusz.krzysztofik@linux.intel.com +(cherry picked from commit 98850e96cf811dc2d0a7d0af491caff9f5d49c1e) +Signed-off-by: Rodrigo Vivi +Signed-off-by: Janusz Krzysztofik +Signed-off-by: Greg Kroah-Hartman +--- + drivers/gpu/drm/i915/gt/intel_engine_pm.c | 3 --- + drivers/gpu/drm/i915/gt/intel_lrc.c | 3 +++ + 2 files changed, 3 insertions(+), 3 deletions(-) + +--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c ++++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c +@@ -145,9 +145,6 @@ static int __engine_park(struct intel_wa + intel_engine_disarm_breadcrumbs(engine); + intel_engine_pool_park(&engine->pool); + +- /* Must be reset upon idling, or we may miss the busy wakeup. */ +- GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN); +- + if (engine->park) + engine->park(engine); + +--- a/drivers/gpu/drm/i915/gt/intel_lrc.c ++++ b/drivers/gpu/drm/i915/gt/intel_lrc.c +@@ -2992,6 +2992,9 @@ static u32 *gen11_emit_fini_breadcrumb_r + static void execlists_park(struct intel_engine_cs *engine) + { + del_timer(&engine->execlists.timer); ++ ++ /* Reset upon idling, or we may delay the busy wakeup. */ ++ WRITE_ONCE(engine->execlists.queue_priority_hint, INT_MIN); + } + + void intel_execlists_set_default_submission(struct intel_engine_cs *engine) diff --git a/queue-5.4/drm-vkms-call-drm_atomic_helper_shutdown-before-drm_dev_put.patch b/queue-5.4/drm-vkms-call-drm_atomic_helper_shutdown-before-drm_dev_put.patch new file mode 100644 index 00000000000..3a9e3892120 --- /dev/null +++ b/queue-5.4/drm-vkms-call-drm_atomic_helper_shutdown-before-drm_dev_put.patch @@ -0,0 +1,98 @@ +From guomengqi3@huawei.com Thu Apr 11 09:41:35 2024 +From: Guo Mengqi +Date: Tue, 9 Apr 2024 10:26:47 +0800 +Subject: drm/vkms: call drm_atomic_helper_shutdown before drm_dev_put() +To: , , , , , +Cc: +Message-ID: <20240409022647.1821-1-guomengqi3@huawei.com> + +From: Guo Mengqi + +commit 73a82b22963d ("drm/atomic: Fix potential use-after-free +in nonblocking commits") introduced drm_dev_get/put() to +drm_atomic_helper_shutdown(). And this cause problem in vkms driver exit +process. + +vkms_exit() + drm_dev_put() + vkms_release() + drm_atomic_helper_shutdown() + drm_dev_get() + drm_dev_put() + vkms_release() ------ use after free + +Using 5.4 stable x86 image on qemu, below stacktrace can be triggered by +load and unload vkms.ko. + +root:~ # insmod vkms.ko +[ 76.957802] [drm] Supports vblank timestamp caching Rev 2 (21.10.2013). +[ 76.961490] [drm] Driver supports precise vblank timestamp query. +[ 76.964416] [drm] Initialized vkms 1.0.0 20180514 for vkms on minor 0 +root:~ # rmmod vkms.ko +[ 79.650202] refcount_t: addition on 0; use-after-free. +[ 79.650249] WARNING: CPU: 2 PID: 3533 at ../lib/refcount.c:25 refcount_warn_saturate+0xcf/0xf0 +[ 79.654241] Modules linked in: vkms(-) +[ 79.654249] CPU: 2 PID: 3533 Comm: rmmod Not tainted 5.4.273 #4 +[ 79.654251] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 +[ 79.654262] RIP: 0010:refcount_warn_saturate+0xcf/0xf0 +... +[ 79.654296] Call Trace: +[ 79.654462] ? __warn+0x80/0xd0 +[ 79.654473] ? refcount_warn_saturate+0xcf/0xf0 +[ 79.654481] ? report_bug+0xb6/0x130 +[ 79.654484] ? refcount_warn_saturate+0xcf/0xf0 +[ 79.654489] ? fixup_bug.part.12+0x13/0x30 +[ 79.654492] ? do_error_trap+0x90/0xb0 +[ 79.654495] ? do_invalid_op+0x31/0x40 +[ 79.654497] ? refcount_warn_saturate+0xcf/0xf0 +[ 79.654504] ? invalid_op+0x1e/0x30 +[ 79.654508] ? refcount_warn_saturate+0xcf/0xf0 +[ 79.654516] drm_atomic_state_init+0x68/0xb0 +[ 79.654543] drm_atomic_state_alloc+0x43/0x60 +[ 79.654551] drm_atomic_helper_disable_all+0x13/0x180 +[ 79.654562] drm_atomic_helper_shutdown+0x5f/0xb0 +[ 79.654571] vkms_release+0x18/0x40 [vkms] +[ 79.654575] vkms_exit+0x29/0xc00 [vkms] +[ 79.654582] __x64_sys_delete_module+0x155/0x220 +[ 79.654592] do_syscall_64+0x43/0x120 +[ 79.654603] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 +[ 79.654619] ---[ end trace ce0c02f57ea6bf73 ]--- + +It seems that the proper unload sequence is: + drm_atomic_helper_shutdown(); + drm_dev_put(); + +Just put drm_atomic_helper_shutdown() before drm_dev_put() +should solve the problem. + +Note that vkms exit code is refactored by commit 53d77aaa3f76 +("drm/vkms: Use devm_drm_dev_alloc") in tags/v5.10-rc1. + +So this bug only exists on 4.19 and 5.4. + +Fixes: 380c7ceabdde ("drm/atomic: Fix potential use-after-free in nonblocking commits") +Fixes: 2ead1be54b22 ("drm/vkms: Fix connector leak at the module removal") +Signed-off-by: Guo Mengqi +Signed-off-by: Greg Kroah-Hartman +--- + drivers/gpu/drm/vkms/vkms_drv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/gpu/drm/vkms/vkms_drv.c ++++ b/drivers/gpu/drm/vkms/vkms_drv.c +@@ -60,7 +60,6 @@ static void vkms_release(struct drm_devi + struct vkms_device *vkms = container_of(dev, struct vkms_device, drm); + + platform_device_unregister(vkms->platform); +- drm_atomic_helper_shutdown(&vkms->drm); + drm_mode_config_cleanup(&vkms->drm); + drm_dev_fini(&vkms->drm); + destroy_workqueue(vkms->output.composer_workq); +@@ -194,6 +193,7 @@ static void __exit vkms_exit(void) + } + + drm_dev_unregister(&vkms_device->drm); ++ drm_atomic_helper_shutdown(&vkms_device->drm); + drm_dev_put(&vkms_device->drm); + + kfree(vkms_device); diff --git a/queue-5.4/series b/queue-5.4/series index cf1da9471e0..b0cbe88d89a 100644 --- a/queue-5.4/series +++ b/queue-5.4/series @@ -203,3 +203,8 @@ netfilter-nf_tables-release-batch-on-table-validatio.patch netfilter-nf_tables-release-mutex-after-nft_gc_seq_e.patch netfilter-nf_tables-discard-table-flag-update-with-p.patch tty-n_gsm-require-cap_net_admin-to-attach-n_gsm0710-ldisc.patch +drm-vkms-call-drm_atomic_helper_shutdown-before-drm_dev_put.patch +virtio-reenable-config-if-freezing-device-failed.patch +x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch +drm-i915-gt-reset-queue_priority_hint-on-parking.patch +x86-alternative-don-t-call-text_poke-in-lazy-tlb-mode.patch diff --git a/queue-5.4/virtio-reenable-config-if-freezing-device-failed.patch b/queue-5.4/virtio-reenable-config-if-freezing-device-failed.patch new file mode 100644 index 00000000000..b37e18f1955 --- /dev/null +++ b/queue-5.4/virtio-reenable-config-if-freezing-device-failed.patch @@ -0,0 +1,55 @@ +From 310227f42882c52356b523e2f4e11690eebcd2ab Mon Sep 17 00:00:00 2001 +From: David Hildenbrand +Date: Tue, 13 Feb 2024 14:54:25 +0100 +Subject: virtio: reenable config if freezing device failed + +From: David Hildenbrand + +commit 310227f42882c52356b523e2f4e11690eebcd2ab upstream. + +Currently, we don't reenable the config if freezing the device failed. + +For example, virtio-mem currently doesn't support suspend+resume, and +trying to freeze the device will always fail. Afterwards, the device +will no longer respond to resize requests, because it won't get notified +about config changes. + +Let's fix this by re-enabling the config if freezing fails. + +Fixes: 22b7050a024d ("virtio: defer config changed notifications") +Cc: +Cc: "Michael S. Tsirkin" +Cc: Jason Wang +Cc: Xuan Zhuo +Signed-off-by: David Hildenbrand +Message-Id: <20240213135425.795001-1-david@redhat.com> +Signed-off-by: Michael S. Tsirkin +Signed-off-by: Greg Kroah-Hartman +--- + drivers/virtio/virtio.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +--- a/drivers/virtio/virtio.c ++++ b/drivers/virtio/virtio.c +@@ -381,13 +381,19 @@ EXPORT_SYMBOL_GPL(unregister_virtio_devi + int virtio_device_freeze(struct virtio_device *dev) + { + struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); ++ int ret; + + virtio_config_disable(dev); + + dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; + +- if (drv && drv->freeze) +- return drv->freeze(dev); ++ if (drv && drv->freeze) { ++ ret = drv->freeze(dev); ++ if (ret) { ++ virtio_config_enable(dev); ++ return ret; ++ } ++ } + + return 0; + } diff --git a/queue-5.4/x86-alternative-don-t-call-text_poke-in-lazy-tlb-mode.patch b/queue-5.4/x86-alternative-don-t-call-text_poke-in-lazy-tlb-mode.patch new file mode 100644 index 00000000000..810d7cbdc67 --- /dev/null +++ b/queue-5.4/x86-alternative-don-t-call-text_poke-in-lazy-tlb-mode.patch @@ -0,0 +1,55 @@ +From abee7c494d8c41bb388839bccc47e06247f0d7de Mon Sep 17 00:00:00 2001 +From: Juergen Gross +Date: Fri, 9 Oct 2020 16:42:25 +0200 +Subject: x86/alternative: Don't call text_poke() in lazy TLB mode + +From: Juergen Gross + +commit abee7c494d8c41bb388839bccc47e06247f0d7de upstream. + +When running in lazy TLB mode the currently active page tables might +be the ones of a previous process, e.g. when running a kernel thread. + +This can be problematic in case kernel code is being modified via +text_poke() in a kernel thread, and on another processor exit_mmap() +is active for the process which was running on the first cpu before +the kernel thread. + +As text_poke() is using a temporary address space and the former +address space (obtained via cpu_tlbstate.loaded_mm) is restored +afterwards, there is a race possible in case the cpu on which +exit_mmap() is running wants to make sure there are no stale +references to that address space on any cpu active (this e.g. is +required when running as a Xen PV guest, where this problem has been +observed and analyzed). + +In order to avoid that, drop off TLB lazy mode before switching to the +temporary address space. + +Fixes: cefa929c034eb5d ("x86/mm: Introduce temporary mm structs") +Signed-off-by: Juergen Gross +Signed-off-by: Peter Zijlstra (Intel) +Link: https://lkml.kernel.org/r/20201009144225.12019-1-jgross@suse.com +Signed-off-by: Greg Kroah-Hartman +--- + arch/x86/include/asm/mmu_context.h | 9 +++++++++ + 1 file changed, 9 insertions(+) + +--- a/arch/x86/include/asm/mmu_context.h ++++ b/arch/x86/include/asm/mmu_context.h +@@ -379,6 +379,15 @@ static inline temp_mm_state_t use_tempor + temp_mm_state_t temp_state; + + lockdep_assert_irqs_disabled(); ++ ++ /* ++ * Make sure not to be in TLB lazy mode, as otherwise we'll end up ++ * with a stale address space WITHOUT being in lazy mode after ++ * restoring the previous mm. ++ */ ++ if (this_cpu_read(cpu_tlbstate.is_lazy)) ++ leave_mm(smp_processor_id()); ++ + temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); + switch_mm_irqs_off(NULL, mm, current); + diff --git a/queue-5.4/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch b/queue-5.4/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch new file mode 100644 index 00000000000..8f65853e330 --- /dev/null +++ b/queue-5.4/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch @@ -0,0 +1,239 @@ +From 04c35ab3bdae7fefbd7c7a7355f29fa03a035221 Mon Sep 17 00:00:00 2001 +From: David Hildenbrand +Date: Wed, 3 Apr 2024 23:21:30 +0200 +Subject: x86/mm/pat: fix VM_PAT handling in COW mappings + +From: David Hildenbrand + +commit 04c35ab3bdae7fefbd7c7a7355f29fa03a035221 upstream. + +PAT handling won't do the right thing in COW mappings: the first PTE (or, +in fact, all PTEs) can be replaced during write faults to point at anon +folios. Reliably recovering the correct PFN and cachemode using +follow_phys() from PTEs will not work in COW mappings. + +Using follow_phys(), we might just get the address+protection of the anon +folio (which is very wrong), or fail on swap/nonswap entries, failing +follow_phys() and triggering a WARN_ON_ONCE() in untrack_pfn() and +track_pfn_copy(), not properly calling free_pfn_range(). + +In free_pfn_range(), we either wouldn't call memtype_free() or would call +it with the wrong range, possibly leaking memory. + +To fix that, let's update follow_phys() to refuse returning anon folios, +and fallback to using the stored PFN inside vma->vm_pgoff for COW mappings +if we run into that. + +We will now properly handle untrack_pfn() with COW mappings, where we +don't need the cachemode. We'll have to fail fork()->track_pfn_copy() if +the first page was replaced by an anon folio, though: we'd have to store +the cachemode in the VMA to make this work, likely growing the VMA size. + +For now, lets keep it simple and let track_pfn_copy() just fail in that +case: it would have failed in the past with swap/nonswap entries already, +and it would have done the wrong thing with anon folios. + +Simple reproducer to trigger the WARN_ON_ONCE() in untrack_pfn(): + +<--- C reproducer ---> + #include + #include + #include + #include + + int main(void) + { + struct io_uring_params p = {}; + int ring_fd; + size_t size; + char *map; + + ring_fd = io_uring_setup(1, &p); + if (ring_fd < 0) { + perror("io_uring_setup"); + return 1; + } + size = p.sq_off.array + p.sq_entries * sizeof(unsigned); + + /* Map the submission queue ring MAP_PRIVATE */ + map = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, + ring_fd, IORING_OFF_SQ_RING); + if (map == MAP_FAILED) { + perror("mmap"); + return 1; + } + + /* We have at least one page. Let's COW it. */ + *map = 0; + pause(); + return 0; + } +<--- C reproducer ---> + +On a system with 16 GiB RAM and swap configured: + # ./iouring & + # memhog 16G + # killall iouring +[ 301.552930] ------------[ cut here ]------------ +[ 301.553285] WARNING: CPU: 7 PID: 1402 at arch/x86/mm/pat/memtype.c:1060 untrack_pfn+0xf4/0x100 +[ 301.553989] Modules linked in: binfmt_misc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_g +[ 301.558232] CPU: 7 PID: 1402 Comm: iouring Not tainted 6.7.5-100.fc38.x86_64 #1 +[ 301.558772] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebu4 +[ 301.559569] RIP: 0010:untrack_pfn+0xf4/0x100 +[ 301.559893] Code: 75 c4 eb cf 48 8b 43 10 8b a8 e8 00 00 00 3b 6b 28 74 b8 48 8b 7b 30 e8 ea 1a f7 000 +[ 301.561189] RSP: 0018:ffffba2c0377fab8 EFLAGS: 00010282 +[ 301.561590] RAX: 00000000ffffffea RBX: ffff9208c8ce9cc0 RCX: 000000010455e047 +[ 301.562105] RDX: 07fffffff0eb1e0a RSI: 0000000000000000 RDI: ffff9208c391d200 +[ 301.562628] RBP: 0000000000000000 R08: ffffba2c0377fab8 R09: 0000000000000000 +[ 301.563145] R10: ffff9208d2292d50 R11: 0000000000000002 R12: 00007fea890e0000 +[ 301.563669] R13: 0000000000000000 R14: ffffba2c0377fc08 R15: 0000000000000000 +[ 301.564186] FS: 0000000000000000(0000) GS:ffff920c2fbc0000(0000) knlGS:0000000000000000 +[ 301.564773] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 301.565197] CR2: 00007fea88ee8a20 CR3: 00000001033a8000 CR4: 0000000000750ef0 +[ 301.565725] PKRU: 55555554 +[ 301.565944] Call Trace: +[ 301.566148] +[ 301.566325] ? untrack_pfn+0xf4/0x100 +[ 301.566618] ? __warn+0x81/0x130 +[ 301.566876] ? untrack_pfn+0xf4/0x100 +[ 301.567163] ? report_bug+0x171/0x1a0 +[ 301.567466] ? handle_bug+0x3c/0x80 +[ 301.567743] ? exc_invalid_op+0x17/0x70 +[ 301.568038] ? asm_exc_invalid_op+0x1a/0x20 +[ 301.568363] ? untrack_pfn+0xf4/0x100 +[ 301.568660] ? untrack_pfn+0x65/0x100 +[ 301.568947] unmap_single_vma+0xa6/0xe0 +[ 301.569247] unmap_vmas+0xb5/0x190 +[ 301.569532] exit_mmap+0xec/0x340 +[ 301.569801] __mmput+0x3e/0x130 +[ 301.570051] do_exit+0x305/0xaf0 +... + +Link: https://lkml.kernel.org/r/20240403212131.929421-3-david@redhat.com +Signed-off-by: David Hildenbrand +Reported-by: Wupeng Ma +Closes: https://lkml.kernel.org/r/20240227122814.3781907-1-mawupeng1@huawei.com +Fixes: b1a86e15dc03 ("x86, pat: remove the dependency on 'vm_pgoff' in track/untrack pfn vma routines") +Fixes: 5899329b1910 ("x86: PAT: implement track/untrack of pfnmap regions for x86 - v3") +Acked-by: Ingo Molnar +Cc: Dave Hansen +Cc: Andy Lutomirski +Cc: Peter Zijlstra +Cc: Thomas Gleixner +Cc: Borislav Petkov +Cc: "H. Peter Anvin" +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: David Hildenbrand +Signed-off-by: Greg Kroah-Hartman +--- + arch/x86/mm/pat.c | 50 ++++++++++++++++++++++++++++++++++++-------------- + mm/memory.c | 4 ++++ + 2 files changed, 40 insertions(+), 14 deletions(-) + +--- a/arch/x86/mm/pat.c ++++ b/arch/x86/mm/pat.c +@@ -34,6 +34,7 @@ + + #include "pat_internal.h" + #include "mm_internal.h" ++#include "../../mm/internal.h" /* is_cow_mapping() */ + + #undef pr_fmt + #define pr_fmt(fmt) "" fmt +@@ -955,6 +956,38 @@ static void free_pfn_range(u64 paddr, un + free_memtype(paddr, paddr + size); + } + ++static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, ++ pgprot_t *pgprot) ++{ ++ unsigned long prot; ++ ++ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); ++ ++ /* ++ * We need the starting PFN and cachemode used for track_pfn_remap() ++ * that covered the whole VMA. For most mappings, we can obtain that ++ * information from the page tables. For COW mappings, we might now ++ * suddenly have anon folios mapped and follow_phys() will fail. ++ * ++ * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to ++ * detect the PFN. If we need the cachemode as well, we're out of luck ++ * for now and have to fail fork(). ++ */ ++ if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { ++ if (pgprot) ++ *pgprot = __pgprot(prot); ++ return 0; ++ } ++ if (is_cow_mapping(vma->vm_flags)) { ++ if (pgprot) ++ return -EINVAL; ++ *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; ++ return 0; ++ } ++ WARN_ON_ONCE(1); ++ return -EINVAL; ++} ++ + /* + * track_pfn_copy is called when vma that is covering the pfnmap gets + * copied through copy_page_range(). +@@ -965,20 +998,13 @@ static void free_pfn_range(u64 paddr, un + int track_pfn_copy(struct vm_area_struct *vma) + { + resource_size_t paddr; +- unsigned long prot; + unsigned long vma_size = vma->vm_end - vma->vm_start; + pgprot_t pgprot; + + if (vma->vm_flags & VM_PAT) { +- /* +- * reserve the whole chunk covered by vma. We need the +- * starting address and protection from pte. +- */ +- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { +- WARN_ON_ONCE(1); ++ if (get_pat_info(vma, &paddr, &pgprot)) + return -EINVAL; +- } +- pgprot = __pgprot(prot); ++ /* reserve the whole chunk covered by vma. */ + return reserve_pfn_range(paddr, vma_size, &pgprot, 1); + } + +@@ -1053,7 +1079,6 @@ void untrack_pfn(struct vm_area_struct * + unsigned long size) + { + resource_size_t paddr; +- unsigned long prot; + + if (vma && !(vma->vm_flags & VM_PAT)) + return; +@@ -1061,11 +1086,8 @@ void untrack_pfn(struct vm_area_struct * + /* free the chunk starting from pfn or the whole chunk */ + paddr = (resource_size_t)pfn << PAGE_SHIFT; + if (!paddr && !size) { +- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { +- WARN_ON_ONCE(1); ++ if (get_pat_info(vma, &paddr, NULL)) + return; +- } +- + size = vma->vm_end - vma->vm_start; + } + free_pfn_range(paddr, size); +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -4428,6 +4428,10 @@ int follow_phys(struct vm_area_struct *v + goto out; + pte = *ptep; + ++ /* Never return PFNs of anon folios in COW mappings. */ ++ if (vm_normal_page(vma, address, pte)) ++ goto unlock; ++ + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; +