From: Greg Kroah-Hartman Date: Thu, 11 Apr 2024 07:50:49 +0000 (+0200) Subject: 5.15-stable patches X-Git-Tag: v4.19.312~35 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=1a8ab94f67377e875965c523fca1f9562a090f5e;p=thirdparty%2Fkernel%2Fstable-queue.git 5.15-stable patches added patches: virtio-reenable-config-if-freezing-device-failed.patch x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch --- diff --git a/queue-5.15/series b/queue-5.15/series index 854ad0c53d..148a6c325e 100644 --- a/queue-5.15/series +++ b/queue-5.15/series @@ -49,3 +49,5 @@ netfilter-nf_tables-discard-table-flag-update-with-p.patch tty-n_gsm-require-cap_net_admin-to-attach-n_gsm0710-ldisc.patch gcc-plugins-stackleak-ignore-.noinstr.text-and-.entry.text.patch gcc-plugins-stackleak-avoid-.head.text-section.patch +virtio-reenable-config-if-freezing-device-failed.patch +x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch diff --git a/queue-5.15/virtio-reenable-config-if-freezing-device-failed.patch b/queue-5.15/virtio-reenable-config-if-freezing-device-failed.patch new file mode 100644 index 0000000000..cf9d7bd556 --- /dev/null +++ b/queue-5.15/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 +@@ -455,13 +455,19 @@ 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-5.15/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch b/queue-5.15/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch new file mode 100644 index 0000000000..fea4faf540 --- /dev/null +++ b/queue-5.15/x86-mm-pat-fix-vm_pat-handling-in-cow-mappings.patch @@ -0,0 +1,231 @@ +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/memtype.c | 49 ++++++++++++++++++++++++++++++++-------------- + mm/memory.c | 4 +++ + 2 files changed, 39 insertions(+), 14 deletions(-) + +--- a/arch/x86/mm/pat/memtype.c ++++ b/arch/x86/mm/pat/memtype.c +@@ -989,6 +989,38 @@ static void free_pfn_range(u64 paddr, un + memtype_free(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(). +@@ -999,20 +1031,13 @@ 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); + } + +@@ -1087,7 +1112,6 @@ 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; +@@ -1095,11 +1119,8 @@ 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 +@@ -5086,6 +5086,10 @@ 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; +