May 2025 - Linux-stable-mirror

[PATCH] net: ch9200: fix uninitialised access during mii_nway_restart

by Qasim Ijaz

In mii_nway_restart() the code attempts to call mii->mdio_read which is ch9200_mdio_read(). ch9200_mdio_read() utilises a local buffer called "buff", which is initialised with control_read(). However "buff" is conditionally initialised inside control_read(): if (err == size) { memcpy(data, buf, size); } If the condition of "err == size" is not met, then "buff" remains uninitialised. Once this happens the uninitialised "buff" is accessed and returned during ch9200_mdio_read(): return (buff[0] | buff[1] << 8); The problem stems from the fact that ch9200_mdio_read() ignores the return value of control_read(), leading to uinit-access of "buff". To fix this we should check the return value of control_read() and return early on error. Reported-by: syzbot <syzbot+3361c2d6f78a3e0892f9(a)syzkaller.appspotmail.com> Closes: https://syzkaller.appspot.com/bug?extid=3361c2d6f78a3e0892f9 Tested-by: syzbot <syzbot+3361c2d6f78a3e0892f9(a)syzkaller.appspotmail.com> Fixes: 4a476bd6d1d9 ("usbnet: New driver for QinHeng CH9200 devices") Cc: stable(a)vger.kernel.org Signed-off-by: Qasim Ijaz <qasdev00(a)gmail.com> --- drivers/net/usb/ch9200.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c index f69d9b902da0..a206ffa76f1b 100644 --- a/drivers/net/usb/ch9200.c +++ b/drivers/net/usb/ch9200.c @@ -178,6 +178,7 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc) { struct usbnet *dev = netdev_priv(netdev); unsigned char buff[2]; + int ret; netdev_dbg(netdev, "%s phy_id:%02x loc:%02x\n", __func__, phy_id, loc); @@ -185,8 +186,10 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc) if (phy_id != 0) return -ENODEV; - control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02, - CONTROL_TIMEOUT_MS); + ret = control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02, + CONTROL_TIMEOUT_MS); + if (ret < 0) + return ret; return (buff[0] | buff[1] << 8); } -- 2.39.5

3 months, 2 weeks

2
1
0 0

[PATCH] net: af_key: Add error check in set_sadb_address()

by Wentao Liang

The function set_sadb_address() calls the function pfkey_sockaddr_fill(), but does not check its return value. A proper implementation can be found in set_sadb_kmaddress(). Add an error check for set_sadb_address(), return error code if the function fails. Fixes: e5b56652c11b ("key: Share common code path to fill sockaddr{}.") Cc: stable(a)vger.kernel.org # v2.6 Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- net/key/af_key.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index c56bb4f451e6..537c9604e356 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3474,15 +3474,17 @@ static int set_sadb_address(struct sk_buff *skb, int sasize, int type, switch (type) { case SADB_EXT_ADDRESS_SRC: addr->sadb_address_prefixlen = sel->prefixlen_s; - pfkey_sockaddr_fill(&sel->saddr, 0, - (struct sockaddr *)(addr + 1), - sel->family); + if (!pfkey_sockaddr_fill(&sel->saddr, 0, + (struct sockaddr *)(addr + 1), + sel->family)) + return -EINVAL; break; case SADB_EXT_ADDRESS_DST: addr->sadb_address_prefixlen = sel->prefixlen_d; - pfkey_sockaddr_fill(&sel->daddr, 0, - (struct sockaddr *)(addr + 1), - sel->family); + if (!pfkey_sockaddr_fill(&sel->daddr, 0, + (struct sockaddr *)(addr + 1), + sel->family)) + return -EINVAL; break; default: return -EINVAL; -- 2.42.0.windows.2

3 months, 2 weeks

3
2
0 0

[PATCH 2/5] LoongArch: KVM: Check interrupt route from physical cpu with eiointc

by Bibo Mao

With eiointc interrupt controller, physical cpu id is set for irq route. However function kvm_get_vcpu() is used to get destination vCPU when delivering irq. With API kvm_get_vcpu(), logical cpu is used. With API kvm_get_vcpu_by_cpuid(), vCPU can be searched from physical cpu id. Cc: stable(a)vger.kernel.org Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index d2c521b0e923..0b648c56b0c3 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -9,7 +9,8 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) { - int ipnum, cpu, irq_index, irq_mask, irq; + int ipnum, cpu, irq_index, irq_mask, irq, cpuid; + struct kvm_vcpu *vcpu; for (irq = 0; irq < EIOINTC_IRQS; irq++) { ipnum = s->ipmap.reg_u8[irq / 32]; @@ -20,7 +21,12 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) irq_index = irq / 32; irq_mask = BIT(irq & 0x1f); - cpu = s->coremap.reg_u8[irq]; + cpuid = s->coremap.reg_u8[irq]; + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (vcpu == NULL) + continue; + + cpu = vcpu->vcpu_id; if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask)) set_bit(irq, s->sw_coreisr[cpu][ipnum]); else @@ -68,17 +74,23 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, int irq, u64 val, u32 len, bool notify) { - int i, cpu; + int i, cpu, cpuid; + struct kvm_vcpu *vcpu; for (i = 0; i < len; i++) { - cpu = val & 0xff; + cpuid = val & 0xff; val = val >> 8; if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) { - cpu = ffs(cpu) - 1; - cpu = (cpu >= 4) ? 0 : cpu; + cpuid = ffs(cpuid) - 1; + cpuid = (cpuid >= 4) ? 0 : cpuid; } + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (vcpu == NULL) + continue; + + cpu = vcpu->vcpu_id; if (s->sw_coremap[irq + i] == cpu) continue; -- 2.39.3

3 months, 2 weeks

1
0
0 0

[PATCH 1/5] LoongArch: KVM: Fix interrupt route update with eiointc

by Bibo Mao

With function eiointc_update_sw_coremap(), there is forced assignment like val = *(u64 *)pvalue. Parameter pvalue may be pointer to char type or others, there is problem with forced assignment with u64 type. Here the detailed value is passed rather address pointer. Cc: stable(a)vger.kernel.org Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index f39929d7bf8a..d2c521b0e923 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -66,10 +66,9 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) } static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, - int irq, void *pvalue, u32 len, bool notify) + int irq, u64 val, u32 len, bool notify) { int i, cpu; - u64 val = *(u64 *)pvalue; for (i = 0; i < len; i++) { cpu = val & 0xff; @@ -398,7 +397,7 @@ static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq; s->coremap.reg_u8[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -484,7 +483,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 1; s->coremap.reg_u16[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -570,7 +569,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 2; s->coremap.reg_u32[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -656,7 +655,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 3; s->coremap.reg_u64[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -809,7 +808,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, for (i = 0; i < (EIOINTC_IRQS / 4); i++) { start_irq = i * 4; eiointc_update_sw_coremap(s, start_irq, - (void *)&s->coremap.reg_u32[i], sizeof(u32), false); + s->coremap.reg_u32[i], sizeof(u32), false); } break; default: -- 2.39.3

3 months, 2 weeks

1
0
0 0

[PATCH] net: ethernet: rtsn: Fix a null pointer dereference in rtsn_probe()

by Haoxiang Li

Add check for the return value of rcar_gen4_ptp_alloc() to prevent potential null pointer dereference. Fixes: b0d3969d2b4d ("net: ethernet: rtsn: Add support for Renesas Ethernet-TSN") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- drivers/net/ethernet/renesas/rtsn.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c index 6b3f7fca8d15..f5df3374d279 100644 --- a/drivers/net/ethernet/renesas/rtsn.c +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -1260,6 +1260,10 @@ static int rtsn_probe(struct platform_device *pdev) priv->pdev = pdev; priv->ndev = ndev; priv->ptp_priv = rcar_gen4_ptp_alloc(pdev); + if (!priv->ptp_priv) { + ret = -ENOMEM; + goto error_free; + } spin_lock_init(&priv->lock); platform_set_drvdata(pdev, priv); -- 2.25.1

3 months, 2 weeks

3
2
0 0

[alternative-merged] mm-contig_alloc-fix-alloc_contig_range-when-__gfp_comp-and-order-max_order.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/contig_alloc: fix alloc_contig_range when __GFP_COMP and order < MAX_ORDER has been removed from the -mm tree. Its filename was mm-contig_alloc-fix-alloc_contig_range-when-__gfp_comp-and-order-max_order.patch This patch was dropped because an alternative patch was or shall be merged ------------------------------------------------------ From: Jinjiang Tu <tujinjiang(a)huawei.com> Subject: mm/contig_alloc: fix alloc_contig_range when __GFP_COMP and order < MAX_ORDER Date: Mon, 21 Apr 2025 09:36:20 +0800 When calling alloc_contig_range() with __GFP_COMP and the order of requested pfn range is pageblock_order, less than MAX_ORDER, I triggered WARNING as follows: PFN range: requested [2150105088, 2150105600), allocated [2150105088, 2150106112) WARNING: CPU: 3 PID: 580 at mm/page_alloc.c:6877 alloc_contig_range+0x280/0x340 alloc_contig_range() marks pageblocks of the requested pfn range to be isolated, migrate these pages if they are in use and will be freed to MIGRATE_ISOLATED freelist. Suppose two alloc_contig_range() calls at the same time and the requested pfn range are [0x80280000, 0x80280200) and [0x80280200, 0x80280400) respectively. Suppose the two memory range are in use, then alloc_contig_range() will migrate and free these pages to MIGRATE_ISOLATED freelist. __free_one_page() will merge MIGRATE_ISOLATE buddy to larger buddy, resulting in a MAX_ORDER buddy. Finally, find_large_buddy() in alloc_contig_range() returns a MAX_ORDER buddy and results in WARNING. To fix it, call free_contig_range() to free the excess pfn range. Link: https://lkml.kernel.org/r/20250421013620.459740-1-tujinjiang@huawei.com Fixes: e98337d11bbd ("mm/contig_alloc: support __GFP_COMP") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) --- a/mm/page_alloc.c~mm-contig_alloc-fix-alloc_contig_range-when-__gfp_comp-and-order-max_order +++ a/mm/page_alloc.c @@ -6693,6 +6693,7 @@ int alloc_contig_range_noprof(unsigned l .alloc_contig = true, }; INIT_LIST_HEAD(&cc.migratepages); + bool is_range_aligned; gfp_mask = current_gfp_context(gfp_mask); if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask)) @@ -6781,7 +6782,14 @@ int alloc_contig_range_noprof(unsigned l goto done; } - if (!(gfp_mask & __GFP_COMP)) { + /* + * With __GFP_COMP and the requested order < MAX_PAGE_ORDER, + * isolated free pages can have higher order than the requested + * one. Use split_free_pages() to free out of range pages. + */ + is_range_aligned = is_power_of_2(end - start); + if (!(gfp_mask & __GFP_COMP) || + (is_range_aligned && ilog2(end - start) < MAX_PAGE_ORDER)) { split_free_pages(cc.freepages, gfp_mask); /* Free head and tail (if any) */ @@ -6789,7 +6797,15 @@ int alloc_contig_range_noprof(unsigned l free_contig_range(outer_start, start - outer_start); if (end != outer_end) free_contig_range(end, outer_end - end); - } else if (start == outer_start && end == outer_end && is_power_of_2(end - start)) { + + outer_start = start; + outer_end = end; + + if (!(gfp_mask & __GFP_COMP)) + goto done; + } + + if (start == outer_start && end == outer_end && is_range_aligned) { struct page *head = pfn_to_page(start); int order = ilog2(end - start); _ Patches currently in -mm which might be from tujinjiang(a)huawei.com are

3 months, 2 weeks

1
0
0 0

[for-next][PATCH 02/10] ring-buffer: Do not trigger WARN_ON() due to a commit_overrun

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> When reading a memory mapped buffer the reader page is just swapped out with the last page written in the write buffer. If the reader page is the same as the commit buffer (the buffer that is currently being written to) it was assumed that it should never have missed events. If it does, it triggers a WARN_ON_ONCE(). But there just happens to be one scenario where this can legitimately happen. That is on a commit_overrun. A commit overrun is when an interrupt preempts an event being written to the buffer and then the interrupt adds so many new events that it fills and wraps the buffer back to the commit. Any new events would then be dropped and be reported as "missed_events". In this case, the next page to read is the commit buffer and after the swap of the reader page, the reader page will be the commit buffer, but this time there will be missed events and this triggers the following warning: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 1127 at kernel/trace/ring_buffer.c:7357 ring_buffer_map_get_reader+0x49a/0x780 Modules linked in: kvm_intel kvm irqbypass CPU: 2 UID: 0 PID: 1127 Comm: trace-cmd Not tainted 6.15.0-rc7-test-00004-g478bc2824b45-dirty #564 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:ring_buffer_map_get_reader+0x49a/0x780 Code: 00 00 00 48 89 fe 48 c1 ee 03 80 3c 2e 00 0f 85 ec 01 00 00 4d 3b a6 a8 00 00 00 0f 85 8a fd ff ff 48 85 c0 0f 84 55 fe ff ff <0f> 0b e9 4e fe ff ff be 08 00 00 00 4c 89 54 24 58 48 89 54 24 50 RSP: 0018:ffff888121787dc0 EFLAGS: 00010002 RAX: 00000000000006a2 RBX: ffff888100062800 RCX: ffffffff8190cb49 RDX: ffff888126934c00 RSI: 1ffff11020200a15 RDI: ffff8881010050a8 RBP: dffffc0000000000 R08: 0000000000000000 R09: ffffed1024d26982 R10: ffff888126934c17 R11: ffff8881010050a8 R12: ffff888126934c00 R13: ffff8881010050b8 R14: ffff888101005000 R15: ffff888126930008 FS: 00007f95c8cd7540(0000) GS:ffff8882b576e000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f95c8de4dc0 CR3: 0000000128452002 CR4: 0000000000172ef0 Call Trace: <TASK> ? __pfx_ring_buffer_map_get_reader+0x10/0x10 tracing_buffers_ioctl+0x283/0x370 __x64_sys_ioctl+0x134/0x190 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f95c8de48db Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1c 48 8b 44 24 18 64 48 2b 04 25 28 00 00 RSP: 002b:00007ffe037ba110 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffe037bb2b0 RCX: 00007f95c8de48db RDX: 0000000000000000 RSI: 0000000000005220 RDI: 0000000000000006 RBP: 00007ffe037ba180 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe037bb6f8 R14: 00007f95c9065000 R15: 00005575c7492c90 </TASK> irq event stamp: 5080 hardirqs last enabled at (5079): [<ffffffff83e0adb0>] _raw_spin_unlock_irqrestore+0x50/0x70 hardirqs last disabled at (5080): [<ffffffff83e0aa83>] _raw_spin_lock_irqsave+0x63/0x70 softirqs last enabled at (4182): [<ffffffff81516122>] handle_softirqs+0x552/0x710 softirqs last disabled at (4159): [<ffffffff815163f7>] __irq_exit_rcu+0x107/0x210 ---[ end trace 0000000000000000 ]--- The above was triggered by running on a kernel with both lockdep and KASAN as well as kmemleak enabled and executing the following command: # perf record -o perf-test.dat -a -- trace-cmd record --nosplice -e all -p function hackbench 50 With perf interjecting a lot of interrupts and trace-cmd enabling all events as well as function tracing, with lockdep, KASAN and kmemleak enabled, it could cause an interrupt preempting an event being written to add enough events to wrap the buffer. trace-cmd was modified to have --nosplice use mmap instead of reading the buffer. The way to differentiate this case from the normal case of there only being one page written to where the swap of the reader page received that one page (which is the commit page), check if the tail page is on the reader page. The difference between the commit page and the tail page is that the tail page is where new writes go to, and the commit page holds the first write that hasn't been committed yet. In the case of an interrupt preempting the write of an event and filling the buffer, it would move the tail page but not the commit page. Have the warning only trigger if the tail page is also on the reader page, and also print out the number of events dropped by a commit overrun as that can not yet be safely added to the page so that the reader can see there were events dropped. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Vincent Donnefort <vdonnefort(a)google.com> Link: https://lore.kernel.org/20250528121555.2066527e@gandalf.local.home Fixes: fe832be05a8ee ("ring-buffer: Have mmapped ring buffer keep track of missed events") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ring_buffer.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ca1a8e706004..683aa57870fe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7285,8 +7285,8 @@ int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu) /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; - if (cpu_buffer->reader_page != cpu_buffer->commit_page) { - if (missed_events) { + if (missed_events) { + if (cpu_buffer->reader_page != cpu_buffer->commit_page) { struct buffer_data_page *bpage = reader->page; unsigned int commit; /* @@ -7307,13 +7307,23 @@ int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu) local_add(RB_MISSED_STORED, &bpage->commit); } local_add(RB_MISSED_EVENTS, &bpage->commit); + } else if (!WARN_ONCE(cpu_buffer->reader_page == cpu_buffer->tail_page, + "Reader on commit with %ld missed events", + missed_events)) { + /* + * There shouldn't be any missed events if the tail_page + * is on the reader page. But if the tail page is not on the + * reader page and the commit_page is, that would mean that + * there's a commit_overrun (an interrupt preempted an + * addition of an event and then filled the buffer + * with new events). In this case it's not an + * error, but it should still be reported. + * + * TODO: Add missed events to the page for user space to know. + */ + pr_info("Ring buffer [%d] commit overrun lost %ld events at timestamp:%lld\n", + cpu, missed_events, cpu_buffer->reader_page->page->time_stamp); } - } else { - /* - * There really shouldn't be any missed events if the commit - * is on the reader page. - */ - WARN_ON_ONCE(missed_events); } cpu_buffer->lost_events = 0; -- 2.47.2

3 months, 2 weeks

1
0
0 0

[for-next][PATCH 01/10] ring-buffer: Move cpus_read_lock() outside of buffer->mutex

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Running a modified trace-cmd record --nosplice where it does a mmap of the ring buffer when '--nosplice' is set, caused the following lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.15.0-rc7-test-00002-gfb7d03d8a82f #551 Not tainted ------------------------------------------------------ trace-cmd/1113 is trying to acquire lock: ffff888100062888 (&buffer->mutex){+.+.}-{4:4}, at: ring_buffer_map+0x11c/0xe70 but task is already holding lock: ffff888100a5f9f8 (&cpu_buffer->mapping_lock){+.+.}-{4:4}, at: ring_buffer_map+0xcf/0xe70 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #5 (&cpu_buffer->mapping_lock){+.+.}-{4:4}: __mutex_lock+0x192/0x18c0 ring_buffer_map+0xcf/0xe70 tracing_buffers_mmap+0x1c4/0x3b0 __mmap_region+0xd8d/0x1f70 do_mmap+0x9d7/0x1010 vm_mmap_pgoff+0x20b/0x390 ksys_mmap_pgoff+0x2e9/0x440 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #4 (&mm->mmap_lock){++++}-{4:4}: __might_fault+0xa5/0x110 _copy_to_user+0x22/0x80 _perf_ioctl+0x61b/0x1b70 perf_ioctl+0x62/0x90 __x64_sys_ioctl+0x134/0x190 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #3 (&cpuctx_mutex){+.+.}-{4:4}: __mutex_lock+0x192/0x18c0 perf_event_init_cpu+0x325/0x7c0 perf_event_init+0x52a/0x5b0 start_kernel+0x263/0x3e0 x86_64_start_reservations+0x24/0x30 x86_64_start_kernel+0x95/0xa0 common_startup_64+0x13e/0x141 -> #2 (pmus_lock){+.+.}-{4:4}: __mutex_lock+0x192/0x18c0 perf_event_init_cpu+0xb7/0x7c0 cpuhp_invoke_callback+0x2c0/0x1030 __cpuhp_invoke_callback_range+0xbf/0x1f0 _cpu_up+0x2e7/0x690 cpu_up+0x117/0x170 cpuhp_bringup_mask+0xd5/0x120 bringup_nonboot_cpus+0x13d/0x170 smp_init+0x2b/0xf0 kernel_init_freeable+0x441/0x6d0 kernel_init+0x1e/0x160 ret_from_fork+0x34/0x70 ret_from_fork_asm+0x1a/0x30 -> #1 (cpu_hotplug_lock){++++}-{0:0}: cpus_read_lock+0x2a/0xd0 ring_buffer_resize+0x610/0x14e0 __tracing_resize_ring_buffer.part.0+0x42/0x120 tracing_set_tracer+0x7bd/0xa80 tracing_set_trace_write+0x132/0x1e0 vfs_write+0x21c/0xe80 ksys_write+0xf9/0x1c0 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #0 (&buffer->mutex){+.+.}-{4:4}: __lock_acquire+0x1405/0x2210 lock_acquire+0x174/0x310 __mutex_lock+0x192/0x18c0 ring_buffer_map+0x11c/0xe70 tracing_buffers_mmap+0x1c4/0x3b0 __mmap_region+0xd8d/0x1f70 do_mmap+0x9d7/0x1010 vm_mmap_pgoff+0x20b/0x390 ksys_mmap_pgoff+0x2e9/0x440 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: &buffer->mutex --> &mm->mmap_lock --> &cpu_buffer->mapping_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&cpu_buffer->mapping_lock); lock(&mm->mmap_lock); lock(&cpu_buffer->mapping_lock); lock(&buffer->mutex); *** DEADLOCK *** 2 locks held by trace-cmd/1113: #0: ffff888106b847e0 (&mm->mmap_lock){++++}-{4:4}, at: vm_mmap_pgoff+0x192/0x390 #1: ffff888100a5f9f8 (&cpu_buffer->mapping_lock){+.+.}-{4:4}, at: ring_buffer_map+0xcf/0xe70 stack backtrace: CPU: 5 UID: 0 PID: 1113 Comm: trace-cmd Not tainted 6.15.0-rc7-test-00002-gfb7d03d8a82f #551 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x6e/0xa0 print_circular_bug.cold+0x178/0x1be check_noncircular+0x146/0x160 __lock_acquire+0x1405/0x2210 lock_acquire+0x174/0x310 ? ring_buffer_map+0x11c/0xe70 ? ring_buffer_map+0x11c/0xe70 ? __mutex_lock+0x169/0x18c0 __mutex_lock+0x192/0x18c0 ? ring_buffer_map+0x11c/0xe70 ? ring_buffer_map+0x11c/0xe70 ? function_trace_call+0x296/0x370 ? __pfx___mutex_lock+0x10/0x10 ? __pfx_function_trace_call+0x10/0x10 ? __pfx___mutex_lock+0x10/0x10 ? _raw_spin_unlock+0x2d/0x50 ? ring_buffer_map+0x11c/0xe70 ? ring_buffer_map+0x11c/0xe70 ? __mutex_lock+0x5/0x18c0 ring_buffer_map+0x11c/0xe70 ? do_raw_spin_lock+0x12d/0x270 ? find_held_lock+0x2b/0x80 ? _raw_spin_unlock+0x2d/0x50 ? rcu_is_watching+0x15/0xb0 ? _raw_spin_unlock+0x2d/0x50 ? trace_preempt_on+0xd0/0x110 tracing_buffers_mmap+0x1c4/0x3b0 __mmap_region+0xd8d/0x1f70 ? ring_buffer_lock_reserve+0x99/0xff0 ? __pfx___mmap_region+0x10/0x10 ? ring_buffer_lock_reserve+0x99/0xff0 ? __pfx_ring_buffer_lock_reserve+0x10/0x10 ? __pfx_ring_buffer_lock_reserve+0x10/0x10 ? bpf_lsm_mmap_addr+0x4/0x10 ? security_mmap_addr+0x46/0xd0 ? lock_is_held_type+0xd9/0x130 do_mmap+0x9d7/0x1010 ? 0xffffffffc0370095 ? __pfx_do_mmap+0x10/0x10 vm_mmap_pgoff+0x20b/0x390 ? __pfx_vm_mmap_pgoff+0x10/0x10 ? 0xffffffffc0370095 ksys_mmap_pgoff+0x2e9/0x440 do_syscall_64+0x79/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fb0963a7de2 Code: 00 00 00 0f 1f 44 00 00 41 f7 c1 ff 0f 00 00 75 27 55 89 cd 53 48 89 fb 48 85 ff 74 3b 41 89 ea 48 89 df b8 09 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 76 5b 5d c3 0f 1f 00 48 8b 05 e1 9f 0d 00 64 RSP: 002b:00007ffdcc8fb878 EFLAGS: 00000246 ORIG_RAX: 0000000000000009 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb0963a7de2 RDX: 0000000000000001 RSI: 0000000000001000 RDI: 0000000000000000 RBP: 0000000000000001 R08: 0000000000000006 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffdcc8fbe68 R14: 00007fb096628000 R15: 00005633e01a5c90 </TASK> The issue is that cpus_read_lock() is taken within buffer->mutex. The memory mapped pages are taken with the mmap_lock held. The buffer->mutex is taken within the cpu_buffer->mapping_lock. There's quite a chain with all these locks, where the deadlock can be fixed by moving the cpus_read_lock() outside the taking of the buffer->mutex. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Vincent Donnefort <vdonnefort(a)google.com> Link: https://lore.kernel.org/20250527105820.0f45d045@gandalf.local.home Fixes: 117c39200d9d7 ("ring-buffer: Introducing ring-buffer mapping functions") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ring_buffer.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3f9bf562beea..ca1a8e706004 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2849,6 +2849,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, if (nr_pages < 2) nr_pages = 2; + /* + * Keep CPUs from coming online while resizing to synchronize + * with new per CPU buffers being created. + */ + guard(cpus_read_lock)(); + /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); atomic_inc(&buffer->resizing); @@ -2893,7 +2899,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, cond_resched(); } - cpus_read_lock(); /* * Fire off all the required work handlers * We can't schedule on offline CPUs, but it's not necessary @@ -2933,7 +2938,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, cpu_buffer->nr_pages_to_update = 0; } - cpus_read_unlock(); } else { cpu_buffer = buffer->buffers[cpu_id]; @@ -2961,8 +2965,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, goto out_err; } - cpus_read_lock(); - /* Can't run something on an offline CPU. */ if (!cpu_online(cpu_id)) rb_update_pages(cpu_buffer); @@ -2981,7 +2983,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } cpu_buffer->nr_pages_to_update = 0; - cpus_read_unlock(); } out: -- 2.47.2

3 months, 2 weeks

1
0
0 0

[PATCH AUTOSEL 5.4] fs/filesystems: Fix potential unsigned integer underflow in fs_name()

by Sasha Levin

From: Zijun Hu <quic_zijuhu(a)quicinc.com> [ Upstream commit 1363c134ade81e425873b410566e957fecebb261 ] fs_name() has @index as unsigned int, so there is underflow risk for operation '@index--'. Fix by breaking the for loop when '@index == 0' which is also more proper than '@index <= 0' for unsigned integer comparison. Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> Link: https://lore.kernel.org/20250410-fix_fs-v1-1-7c14ccc8ebaa@quicinc.com Signed-off-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- **YES** This commit should be backported to stable kernel trees. **Detailed Analysis:** **The Bug:** The `fs_name()` function at `fs/filesystems.c:156-174` has a critical unsigned integer underflow vulnerability. When the function receives `index=0` as a parameter, the loop `for (tmp = file_systems; tmp; tmp = tmp->next, index--)` decrements `index` from 0 to `UINT_MAX` (4294967295 on 32-bit systems), causing the condition `if (index <= 0 && try_module_get(tmp->owner))` to evaluate incorrectly. **The Fix:** The commit changes the logic from: - Old: `if (index <= 0 && try_module_get(tmp->owner))` - New: `if (index == 0) { if (try_module_get(tmp->owner)) res = 0; break; }` This prevents the unsigned integer from wrapping around and provides proper bounds checking. **Impact and Severity:** 1. **User-accessible vulnerability**: The `fs_name()` function is called through the `sysfs` system call (syscall #139) with option 2, making it directly accessible to userspace applications. 2. **Potential for exploitation**: An attacker could call `sysfs(2, 0, buffer)` to trigger the underflow, potentially causing: - Infinite loops in the filesystem list traversal - Unintended module reference acquisition - System instability or denial of service 3. **Core filesystem subsystem**: This affects the fundamental filesystem registration mechanism in the kernel. **Comparison with Similar Commits:** This follows the same pattern as the **accepted backport examples**: - **Similar to Commit #1 (ntfs3)**: Both fix integer overflow/underflow issues that could cause system instability - **Similar to Commit #3 (f2fs)**: Both prevent integer arithmetic issues in filesystem code - **Similar to Commit #5 (f2fs)**: Both add bounds checking to prevent corruption **Stable Tree Criteria:** ✅ **Fixes important bug**: Prevents potential system instability and undefined behavior ✅ **Small and contained**: Minimal code change, only affects one function ✅ **Clear side effects**: No architectural changes, just safer bounds checking ✅ **Low regression risk**: The fix makes the function more robust without changing expected behavior ✅ **Critical subsystem**: Filesystem management is fundamental to kernel operation **Conclusion:** This is a textbook example of a commit suitable for stable backporting: it fixes a clear bug with security implications in core kernel infrastructure, uses a minimal and safe approach, and has no risk of introducing regressions. The unsigned integer underflow could lead to system instability when triggered through the accessible `sysfs` syscall. fs/filesystems.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/filesystems.c b/fs/filesystems.c index 5e1a190133738..148073e372acd 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -155,15 +155,19 @@ static int fs_index(const char __user * __name) static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; - int len, res; + int len, res = -EINVAL; read_lock(&file_systems_lock); - for (tmp = file_systems; tmp; tmp = tmp->next, index--) - if (index <= 0 && try_module_get(tmp->owner)) + for (tmp = file_systems; tmp; tmp = tmp->next, index--) { + if (index == 0) { + if (try_module_get(tmp->owner)) + res = 0; break; + } + } read_unlock(&file_systems_lock); - if (!tmp) - return -EINVAL; + if (res) + return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; -- 2.39.5

3 months, 2 weeks

1
0
0 0

[PATCH AUTOSEL 5.10] fs/filesystems: Fix potential unsigned integer underflow in fs_name()

by Sasha Levin

From: Zijun Hu <quic_zijuhu(a)quicinc.com> [ Upstream commit 1363c134ade81e425873b410566e957fecebb261 ] fs_name() has @index as unsigned int, so there is underflow risk for operation '@index--'. Fix by breaking the for loop when '@index == 0' which is also more proper than '@index <= 0' for unsigned integer comparison. Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> Link: https://lore.kernel.org/20250410-fix_fs-v1-1-7c14ccc8ebaa@quicinc.com Signed-off-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- **YES** This commit should be backported to stable kernel trees. **Detailed Analysis:** **The Bug:** The `fs_name()` function at `fs/filesystems.c:156-174` has a critical unsigned integer underflow vulnerability. When the function receives `index=0` as a parameter, the loop `for (tmp = file_systems; tmp; tmp = tmp->next, index--)` decrements `index` from 0 to `UINT_MAX` (4294967295 on 32-bit systems), causing the condition `if (index <= 0 && try_module_get(tmp->owner))` to evaluate incorrectly. **The Fix:** The commit changes the logic from: - Old: `if (index <= 0 && try_module_get(tmp->owner))` - New: `if (index == 0) { if (try_module_get(tmp->owner)) res = 0; break; }` This prevents the unsigned integer from wrapping around and provides proper bounds checking. **Impact and Severity:** 1. **User-accessible vulnerability**: The `fs_name()` function is called through the `sysfs` system call (syscall #139) with option 2, making it directly accessible to userspace applications. 2. **Potential for exploitation**: An attacker could call `sysfs(2, 0, buffer)` to trigger the underflow, potentially causing: - Infinite loops in the filesystem list traversal - Unintended module reference acquisition - System instability or denial of service 3. **Core filesystem subsystem**: This affects the fundamental filesystem registration mechanism in the kernel. **Comparison with Similar Commits:** This follows the same pattern as the **accepted backport examples**: - **Similar to Commit #1 (ntfs3)**: Both fix integer overflow/underflow issues that could cause system instability - **Similar to Commit #3 (f2fs)**: Both prevent integer arithmetic issues in filesystem code - **Similar to Commit #5 (f2fs)**: Both add bounds checking to prevent corruption **Stable Tree Criteria:** ✅ **Fixes important bug**: Prevents potential system instability and undefined behavior ✅ **Small and contained**: Minimal code change, only affects one function ✅ **Clear side effects**: No architectural changes, just safer bounds checking ✅ **Low regression risk**: The fix makes the function more robust without changing expected behavior ✅ **Critical subsystem**: Filesystem management is fundamental to kernel operation **Conclusion:** This is a textbook example of a commit suitable for stable backporting: it fixes a clear bug with security implications in core kernel infrastructure, uses a minimal and safe approach, and has no risk of introducing regressions. The unsigned integer underflow could lead to system instability when triggered through the accessible `sysfs` syscall. fs/filesystems.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/filesystems.c b/fs/filesystems.c index 90b8d879fbaf3..1ab8eb5edf28e 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -156,15 +156,19 @@ static int fs_index(const char __user * __name) static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; - int len, res; + int len, res = -EINVAL; read_lock(&file_systems_lock); - for (tmp = file_systems; tmp; tmp = tmp->next, index--) - if (index <= 0 && try_module_get(tmp->owner)) + for (tmp = file_systems; tmp; tmp = tmp->next, index--) { + if (index == 0) { + if (try_module_get(tmp->owner)) + res = 0; break; + } + } read_unlock(&file_systems_lock); - if (!tmp) - return -EINVAL; + if (res) + return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; -- 2.39.5

3 months, 2 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025