- Linux-stable-mirror - lists.linaro.org

[for-next][PATCH 2/2] atomic64: Use arch_spin_locks instead of raw_spin_locks

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> raw_spin_locks can be traced by lockdep or tracing itself. Atomic64 operations can be used in the tracing infrastructure. When an architecture does not have true atomic64 operations it can use the generic version that disables interrupts and uses spin_locks. The tracing ring buffer code uses atomic64 operations for the time keeping. But because some architectures use the default operations, the locking inside the atomic operations can cause an infinite recursion. As atomic64 is an architecture specific operation, it should not be using raw_spin_locks() but instead arch_spin_locks as that is the purpose of arch_spin_locks. To be used in architecture specific implementations of generic infrastructure like atomic64 operations. Cc: stable(a)vger.kernel.org Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Andreas Larsson <andreas(a)gaisler.com> Link: https://lore.kernel.org/20250120235721.574973242@goodmis.org Fixes: c84897c0ff592 ("ring-buffer: Remove 32bit timestamp logic") Closes: https://lore.kernel.org/all/86fb4f86-a0e4-45a2-a2df-3154acc4f086@gaisler.co… Reported-by: Ludwig Rydberg <ludwig.rydberg(a)gaisler.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- lib/atomic64.c | 78 +++++++++++++++++++++++++++++++------------------- 1 file changed, 48 insertions(+), 30 deletions(-) diff --git a/lib/atomic64.c b/lib/atomic64.c index caf895789a1e..1a72bba36d24 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -25,15 +25,15 @@ * Ensure each lock is in a separate cacheline. */ static union { - raw_spinlock_t lock; + arch_spinlock_t lock; char pad[L1_CACHE_BYTES]; } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = { [0 ... (NR_LOCKS - 1)] = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock), + .lock = __ARCH_SPIN_LOCK_UNLOCKED, }, }; -static inline raw_spinlock_t *lock_addr(const atomic64_t *v) +static inline arch_spinlock_t *lock_addr(const atomic64_t *v) { unsigned long addr = (unsigned long) v; @@ -45,12 +45,14 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v) s64 generic_atomic64_read(const atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_read); @@ -58,11 +60,13 @@ EXPORT_SYMBOL(generic_atomic64_read); void generic_atomic64_set(atomic64_t *v, s64 i) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); v->counter = i; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); } EXPORT_SYMBOL(generic_atomic64_set); @@ -70,11 +74,13 @@ EXPORT_SYMBOL(generic_atomic64_set); void generic_atomic64_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ } \ EXPORT_SYMBOL(generic_atomic64_##op); @@ -82,12 +88,14 @@ EXPORT_SYMBOL(generic_atomic64_##op); s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = (v->counter c_op a); \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_##op##_return); @@ -96,13 +104,15 @@ EXPORT_SYMBOL(generic_atomic64_##op##_return); s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = v->counter; \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_fetch_##op); @@ -131,14 +141,16 @@ ATOMIC64_OPS(xor, ^=) s64 generic_atomic64_dec_if_positive(atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter - 1; if (val >= 0) v->counter = val; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_dec_if_positive); @@ -146,14 +158,16 @@ EXPORT_SYMBOL(generic_atomic64_dec_if_positive); s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val == o) v->counter = n; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_cmpxchg); @@ -161,13 +175,15 @@ EXPORT_SYMBOL(generic_atomic64_cmpxchg); s64 generic_atomic64_xchg(atomic64_t *v, s64 new) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; v->counter = new; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_xchg); @@ -175,14 +191,16 @@ EXPORT_SYMBOL(generic_atomic64_xchg); s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val != u) v->counter += a; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } -- 2.45.2

9 months, 4 weeks

2
4
0 0

[REGRESSION] vsocket timeout with kata containers agent 3.10.1 and kernel 6.6.70

by Simon Kaegi

#regzbot introduced v6.6.69..v6.6.70 #regzbot introduced: ad91a2dacbf8c26a446658cdd55e8324dfeff1e7 We hit this regression when updating our guest vm kernel from 6.6.69 to 6.6.70 -- bisecting, this problem was introduced in ad91a2dacbf8c26a446658cdd55e8324dfeff1e7 -- net: restrict SO_REUSEPORT to inet sockets We're getting a timeout when trying to connect to the vsocket in the guest VM when launching a kata containers 3.10.1 agent which unsurprisingly ... uses a vsocket to communicate back to the host. We updated this commit and added an additional sk_is_vsock check and recompiled and this works correctly for us. - if (valbool && !sk_is_inet(sk)) + if (valbool && !(sk_is_inet(sk) || sk_is_vsock(sk))) My understanding is limited here so I've added Stefano as he is likely to better understand what makes sense here. This commit was backported from v6.13 to v6.12.8..6.12.9. -Simon

9 months, 4 weeks

2
6
0 0

[PATCH 5.4.y] signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die

by Finn Thain

From: "Eric W. Biederman" <ebiederm(a)xmission.com> [ Upstream commit a3616a3c02722d1edb95acc7fceade242f6553ba ] In the fpsp040 code when copyin or copyout fails call force_sigsegv(SIGSEGV) instead of do_exit(SIGSEGV). This solves a couple of problems. Because do_exit embeds the ptrace stop PTRACE_EVENT_EXIT a complete stack frame needs to be present for that to work correctly. There is always the information needed for a ptrace stop where get_signal is called. So exiting with a signal solves the ptrace issue. Further exiting with a signal ensures that all of the threads in a process are killed not just the thread that malfunctioned. Which avoids confusing userspace. To make force_sigsegv(SIGSEGV) work in fpsp040_die modify the code to save all of the registers and jump to ret_from_exception (which ultimately calls get_signal) after fpsp040_die returns. v2: Updated the branches to use gas's pseudo ops that automatically calculate the best branch instruction to use for the purpose. v1: https://lkml.kernel.org/r/87a6m8kgtx.fsf_-_@disp2133 Link: https://lkml.kernel.org/r/87tukghjfs.fsf_-_@disp2133 Acked-by: Geert Uytterhoeven <geert(a)linux-m68k.org> Signed-off-by: "Eric W. Biederman" <ebiederm(a)xmission.com> Signed-off-by: Finn Thain <fthain(a)linux-m68k.org> --- arch/m68k/fpsp040/skeleton.S | 3 ++- arch/m68k/kernel/traps.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/m68k/fpsp040/skeleton.S b/arch/m68k/fpsp040/skeleton.S index 31a9c634c81e..081922c72daa 100644 --- a/arch/m68k/fpsp040/skeleton.S +++ b/arch/m68k/fpsp040/skeleton.S @@ -502,7 +502,8 @@ in_ea: .section .fixup,"ax" .even 1: - jbra fpsp040_die + jbsr fpsp040_die + jbra .Lnotkern .section __ex_table,"a" .align 4 diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 35f706d836c5..c6f18dc5884b 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1155,7 +1155,7 @@ asmlinkage void set_esp0(unsigned long ssp) */ asmlinkage void fpsp040_die(void) { - do_exit(SIGSEGV); + force_sigsegv(SIGSEGV); } #ifdef CONFIG_M68KFPU_EMU

9 months, 4 weeks

2
1
0 0

[PATCH 5.4.y] m68k: Add missing mmap_read_lock() to sys_cacheflush()

by Finn Thain

From: Liam Howlett <liam.howlett(a)oracle.com> [ Upstream commit f829b4b212a315b912cb23fd10aaf30534bb5ce9 ] When the superuser flushes the entire cache, the mmap_read_lock() is not taken, but mmap_read_unlock() is called. Add the missing mmap_read_lock() call. Fixes: cd2567b6850b1648 ("m68k: call find_vma with the mmap_sem held in sys_cacheflush()") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Reviewed-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Link: https://lore.kernel.org/r/20210407200032.764445-1-Liam.Howlett@Oracle.com Signed-off-by: Geert Uytterhoeven <geert(a)linux-m68k.org> [ mmap_read_lock() open-coded using down_read() as was done prior to v5.8 ] Signed-off-by: Finn Thain <fthain(a)linux-m68k.org> --- arch/m68k/kernel/sys_m68k.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 6363ec83a290..38dcc1a2097d 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -388,6 +388,8 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; + + down_read(&current->mm->mmap_sem); } else { struct vm_area_struct *vma;

9 months, 4 weeks

2
1
0 0

Re: [PATCH] KVM: x86: switch hugepage recovery thread to vhost_task

by Sasha Levin

[ Sasha's backport helper bot ] Hi, Found matching upstream commit: d96c77bd4eeba469bddbbb14323d2191684da82a WARNING: Author mismatch between patch and found commit: Backport author: Keith Busch<kbusch(a)kernel.org> Commit author: Paolo Bonzini<pbonzini(a)redhat.com> Status in newer kernel trees: 6.12.y | Present (different SHA1: 91248a2e4101) Note: The patch differs from the upstream commit: --- 1: d96c77bd4eeba < -: ------------- KVM: x86: switch hugepage recovery thread to vhost_task -: ------------- > 1: d7ca669c0cbba KVM: x86: switch hugepage recovery thread to vhost_task --- Results of testing on various branches: | Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | stable/linux-6.12.y | Success | Success | | stable/linux-6.6.y | Failed | N/A | | stable/linux-6.1.y | Failed | N/A | | stable/linux-5.15.y | Failed | N/A | | stable/linux-5.10.y | Failed | N/A | | stable/linux-5.4.y | Failed | N/A |

9 months, 4 weeks

1
0
0 0

Re: [PATCH] KVM: x86: switch hugepage recovery thread to vhost_task

by Sasha Levin

[ Sasha's backport helper bot ] Hi, Found matching upstream commit: d96c77bd4eeba469bddbbb14323d2191684da82a WARNING: Author mismatch between patch and found commit: Backport author: Keith Busch<kbusch(a)kernel.org> Commit author: Paolo Bonzini<pbonzini(a)redhat.com> Status in newer kernel trees: 6.12.y | Present (different SHA1: 91248a2e4101) Note: The patch differs from the upstream commit: --- 1: d96c77bd4eeba < -: ------------- KVM: x86: switch hugepage recovery thread to vhost_task -: ------------- > 1: e24606748e041 KVM: x86: switch hugepage recovery thread to vhost_task --- Results of testing on various branches: | Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | stable/linux-6.12.y | Success | Success | | stable/linux-6.6.y | Failed | N/A | | stable/linux-6.1.y | Failed | N/A | | stable/linux-5.15.y | Failed | N/A | | stable/linux-5.10.y | Failed | N/A | | stable/linux-5.4.y | Failed | N/A |

9 months, 4 weeks

1
0
0 0

FAILED: patch "[PATCH] mptcp: don't always assume copied data in" 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 551844f26da2a9f76c0a698baaffa631d1178645 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010605-obscurity-buckshot-fc5f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 551844f26da2a9f76c0a698baaffa631d1178645 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Mon, 30 Dec 2024 19:12:31 +0100 Subject: [PATCH] mptcp: don't always assume copied data in mptcp_cleanup_rbuf() Under some corner cases the MPTCP protocol can end-up invoking mptcp_cleanup_rbuf() when no data has been copied, but such helper assumes the opposite condition. Explicitly drop such assumption and performs the costly call only when strictly needed - before releasing the msk socket lock. Fixes: fd8976790a6c ("mptcp: be careful on MPTCP-level ack.") Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-2-8608af434ceb@ke… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 27afdb7e2071..5307fff9d995 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -528,13 +528,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +551,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +559,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -2220,9 +2220,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2271,6 +2268,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2278,6 +2276,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } + mptcp_cleanup_rbuf(msk, copied); + out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS)

9 months, 4 weeks

3
2
0 0

[PATCH 6.1.y] ipv6: Fix soft lockups in fib6_select_path under high next hop churn

by Rajani kantha

From: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi(a)menlosecurity.com> [ Upstream commit d9ccb18f83ea2bb654289b6ecf014fd267cc988b ] Soft lockups have been observed on a cluster of Linux-based edge routers located in a highly dynamic environment. Using the `bird` service, these routers continuously update BGP-advertised routes due to frequently changing nexthop destinations, while also managing significant IPv6 traffic. The lockups occur during the traversal of the multipath circular linked-list in the `fib6_select_path` function, particularly while iterating through the siblings in the list. The issue typically arises when the nodes of the linked list are unexpectedly deleted concurrently on a different core—indicated by their 'next' and 'previous' elements pointing back to the node itself and their reference count dropping to zero. This results in an infinite loop, leading to a soft lockup that triggers a system panic via the watchdog timer. Apply RCU primitives in the problematic code sections to resolve the issue. Where necessary, update the references to fib6_siblings to annotate or use the RCU APIs. Include a test script that reproduces the issue. The script periodically updates the routing table while generating a heavy load of outgoing IPv6 traffic through multiple iperf3 clients. It consistently induces infinite soft lockups within a couple of minutes. Kernel log: 0 [ffffbd13003e8d30] machine_kexec at ffffffff8ceaf3eb 1 [ffffbd13003e8d90] __crash_kexec at ffffffff8d0120e3 2 [ffffbd13003e8e58] panic at ffffffff8cef65d4 3 [ffffbd13003e8ed8] watchdog_timer_fn at ffffffff8d05cb03 4 [ffffbd13003e8f08] __hrtimer_run_queues at ffffffff8cfec62f 5 [ffffbd13003e8f70] hrtimer_interrupt at ffffffff8cfed756 6 [ffffbd13003e8fd0] __sysvec_apic_timer_interrupt at ffffffff8cea01af 7 [ffffbd13003e8ff0] sysvec_apic_timer_interrupt at ffffffff8df1b83d -- <IRQ stack> -- 8 [ffffbd13003d3708] asm_sysvec_apic_timer_interrupt at ffffffff8e000ecb [exception RIP: fib6_select_path+299] RIP: ffffffff8ddafe7b RSP: ffffbd13003d37b8 RFLAGS: 00000287 RAX: ffff975850b43600 RBX: ffff975850b40200 RCX: 0000000000000000 RDX: 000000003fffffff RSI: 0000000051d383e4 RDI: ffff975850b43618 RBP: ffffbd13003d3800 R8: 0000000000000000 R9: ffff975850b40200 R10: 0000000000000000 R11: 0000000000000000 R12: ffffbd13003d3830 R13: ffff975850b436a8 R14: ffff975850b43600 R15: 0000000000000007 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 9 [ffffbd13003d3808] ip6_pol_route at ffffffff8ddb030c 10 [ffffbd13003d3888] ip6_pol_route_input at ffffffff8ddb068c 11 [ffffbd13003d3898] fib6_rule_lookup at ffffffff8ddf02b5 12 [ffffbd13003d3928] ip6_route_input at ffffffff8ddb0f47 13 [ffffbd13003d3a18] ip6_rcv_finish_core.constprop.0 at ffffffff8dd950d0 14 [ffffbd13003d3a30] ip6_list_rcv_finish.constprop.0 at ffffffff8dd96274 15 [ffffbd13003d3a98] ip6_sublist_rcv at ffffffff8dd96474 16 [ffffbd13003d3af8] ipv6_list_rcv at ffffffff8dd96615 17 [ffffbd13003d3b60] __netif_receive_skb_list_core at ffffffff8dc16fec 18 [ffffbd13003d3be0] netif_receive_skb_list_internal at ffffffff8dc176b3 19 [ffffbd13003d3c50] napi_gro_receive at ffffffff8dc565b9 20 [ffffbd13003d3c80] ice_receive_skb at ffffffffc087e4f5 [ice] 21 [ffffbd13003d3c90] ice_clean_rx_irq at ffffffffc0881b80 [ice] 22 [ffffbd13003d3d20] ice_napi_poll at ffffffffc088232f [ice] 23 [ffffbd13003d3d80] __napi_poll at ffffffff8dc18000 24 [ffffbd13003d3db8] net_rx_action at ffffffff8dc18581 25 [ffffbd13003d3e40] __do_softirq at ffffffff8df352e9 26 [ffffbd13003d3eb0] run_ksoftirqd at ffffffff8ceffe47 27 [ffffbd13003d3ec0] smpboot_thread_fn at ffffffff8cf36a30 28 [ffffbd13003d3ee8] kthread at ffffffff8cf2b39f 29 [ffffbd13003d3f28] ret_from_fork at ffffffff8ce5fa64 30 [ffffbd13003d3f50] ret_from_fork_asm at ffffffff8ce03cbb Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Adrian Oliver <kernel(a)aoliver.ca> Signed-off-by: Omid Ehtemam-Haghighi <omid.ehtemamhaghighi(a)menlosecurity.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Ido Schimmel <idosch(a)idosch.org> Cc: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: Simon Horman <horms(a)kernel.org> Reviewed-by: David Ahern <dsahern(a)kernel.org> Link: https://patch.msgid.link/20241106010236.1239299-1-omid.ehtemamhaghighi@menl… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Rajani Kantha <rajanikantha(a)engineer.com> --- net/ipv6/ip6_fib.c | 8 +- net/ipv6/route.c | 45 ++- tools/testing/selftests/net/Makefile | 1 + .../net/ipv6_route_update_soft_lockup.sh | 262 ++++++++++++++++++ 4 files changed, 297 insertions(+), 19 deletions(-) create mode 100755 tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0b45ef8b7ee2..b6a7cbd6bee0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1180,8 +1180,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->fib6_siblings, - &sibling->fib6_siblings); + list_add_tail_rcu(&rt->fib6_siblings, + &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, @@ -1242,7 +1242,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } @@ -1955,7 +1955,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5ae3ff6ffb7e..f3268bac9f19 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -420,8 +420,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; + struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -447,8 +447,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; - list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, - fib6_siblings) { + list_for_each_entry_rcu(sibling, &match->fib6_siblings, + fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; @@ -5189,14 +5189,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ + rcu_read_lock(); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { - rt = list_first_entry(&rt_last->fib6_siblings, - struct fib6_info, - fib6_siblings); + rt = list_first_or_null_rcu(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); + + rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) @@ -5541,17 +5545,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { - struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; + struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } + + rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } @@ -5715,7 +5723,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); @@ -5727,14 +5735,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, 0) < 0) goto nla_put_failure; - list_for_each_entry_safe(sibling, next_sibling, - &rt->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &rt->fib6_siblings, + fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6, 0) < 0) + AF_INET6, 0) < 0) { + rcu_read_unlock(); + goto nla_put_failure; + } } + rcu_read_unlock(); + nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) @@ -6171,7 +6186,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; @@ -6184,7 +6199,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, - info->nlh, gfp_any()); + info->nlh, GFP_ATOMIC); return; errout: if (err < 0) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 48d1a68be1d5..080860a8826b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -72,6 +72,7 @@ TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_PROGS += test_ingress_egress_chaining.sh TEST_GEN_FILES += nat6to4.o +TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh new file mode 100755 index 000000000000..a6b2b1f9c641 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh @@ -0,0 +1,262 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Testing for potential kernel soft lockup during IPv6 routing table +# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup +# occurs, a kernel panic will be triggered to prevent associated issues. +# +# +# Test Environment Layout +# +# ┌----------------┐ ┌----------------┐ +# | SOURCE_NS | | SINK_NS | +# | NAMESPACE | | NAMESPACE | +# |(iperf3 clients)| |(iperf3 servers)| +# | | | | +# | | | | +# | ┌-----------| nexthops |---------┐ | +# | |veth_source|<--------------------------------------->|veth_sink|<┐ | +# | └-----------|2001:0DB8:1::0:1/96 2001:0DB8:1::1:1/96 |---------┘ | | +# | | ^ 2001:0DB8:1::1:2/96 | | | +# | | . . | fwd | | +# | ┌---------┐ | . . | | | +# | | IPv6 | | . . | V | +# | | routing | | . 2001:0DB8:1::1:80/96| ┌-----┐ | +# | | table | | . | | lo | | +# | | nexthop | | . └--------┴-----┴-┘ +# | | update | | ............................> 2001:0DB8:2::1:1/128 +# | └-------- ┘ | +# └----------------┘ +# +# The test script sets up two network namespaces, source_ns and sink_ns, +# connected via a veth link. Within source_ns, it continuously updates the +# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop +# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a +# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds. +# +# Simultaneously, multiple iperf3 clients within source_ns generate heavy +# outgoing IPv6 traffic. Each client is assigned a unique port number starting +# at 5000 and incrementing sequentially. Each client targets a unique iperf3 +# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface +# using the same port number. +# +# The number of iperf3 servers and clients is set to half of the total +# available cores on each machine. +# +# NOTE: We have tested this script on machines with various CPU specifications, +# ranging from lower to higher performance as listed below. The test script +# effectively triggered a kernel soft lockup on machines running an unpatched +# kernel in under a minute: +# +# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz +# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz +# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz +# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz +# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz +# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz +# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz +# +# On less performant machines, you may need to increase the TEST_DURATION +# parameter to enhance the likelihood of encountering a race condition leading +# to a kernel soft lockup and avoid a false negative result. +# +# NOTE: The test may not produce the expected result in virtualized +# environments (e.g., qemu) due to differences in timing and CPU handling, +# which can affect the conditions needed to trigger a soft lockup. + +source lib.sh +source net_helper.sh + +TEST_DURATION=300 +ROUTING_TABLE_REFRESH_PERIOD=0.01 + +IPERF3_BITRATE="300m" + + +IPV6_NEXTHOP_ADDR_COUNT="128" +IPV6_NEXTHOP_ADDR_MASK="96" +IPV6_NEXTHOP_PREFIX="2001:0DB8:1" + + +SOURCE_TEST_IFACE="veth_source" +SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96" + +SINK_TEST_IFACE="veth_sink" +# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses: +# 2001:0DB8:1::1:1 to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT} +SINK_LOOPBACK_IFACE="lo" +SINK_LOOPBACK_IP_MASK="128" +SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1" + +nexthop_ip_list="" +termination_signal="" +kernel_softlokup_panic_prev_val="" + +terminate_ns_processes_by_pattern() { + local ns=$1 + local pattern=$2 + + for pid in $(ip netns pids ${ns}); do + [ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid + done +} + +cleanup() { + echo "info: cleaning up namespaces and terminating all processes within them..." + + + # Terminate iperf3 instances running in the source_ns. To avoid race + # conditions, first iterate over the PIDs and terminate those + # associated with the bash shells running the + # `while true; do iperf3 -c ...; done` loops. In a second iteration, + # terminate the individual `iperf3 -c ...` instances. + terminate_ns_processes_by_pattern ${source_ns} while + terminate_ns_processes_by_pattern ${source_ns} iperf3 + + # Repeat the same process for sink_ns + terminate_ns_processes_by_pattern ${sink_ns} while + terminate_ns_processes_by_pattern ${sink_ns} iperf3 + + # Check if any iperf3 instances are still running. This could happen + # if a core has entered an infinite loop and the timeout for detecting + # the soft lockup has not expired, but either the test interval has + # already elapsed or the test was terminated manually (e.g., with ^C) + for pid in $(ip netns pids ${source_ns}); do + if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then + echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!" + exit ${ksft_fail} + fi + done + + if [ "$termination_signal" == "SIGINT" ]; then + echo "SKIP: Termination due to ^C (SIGINT)" + elif [ "$termination_signal" == "SIGALRM" ]; then + echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test" + fi + + cleanup_ns ${source_ns} ${sink_ns} + + sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val} +} + +setup_prepare() { + setup_ns source_ns sink_ns + + ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns} + + # Setting up the Source namespace + ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE} + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000 + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up + ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1 + + # Setting up the Sink namespace + ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE} + ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1 + + ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1 + + + # Populate nexthop IPv6 addresses on the test interface in the sink_ns + echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..." + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE}; + done + + # Preparing list of nexthops + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1" + done +} + + +test_soft_lockup_during_routing_table_refresh() { + # Start num_of_iperf_servers iperf3 servers in the sink_ns namespace, + # each listening on ports starting at 5001 and incrementing + # sequentially. Since iperf3 instances may terminate unexpectedly, a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null" + ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + # Wait for the iperf3 servers to be ready + for i in $(seq ${num_of_iperf_servers}); do + port=$(printf '5%03d' ${i}); + wait_local_port_listen ${sink_ns} ${port} tcp + done + + # Continuously refresh the routing table in the background within + # the source_ns namespace + ip netns exec ${source_ns} bash -c " + while \$(ip netns list | grep -q ${source_ns}); do + ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list}; + sleep ${ROUTING_TABLE_REFRESH_PERIOD}; + ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK}; + done &" + + # Start num_of_iperf_servers iperf3 clients in the source_ns namespace, + # each sending TCP traffic on sequential ports starting at 5001. + # Since iperf3 instances may terminate unexpectedly (e.g., if the route + # to the server is deleted in the background during a route refresh), a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null" + ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..." + echo "info: A kernel soft lockup, if detected, results in a kernel panic!" + + wait +} + +# Make sure 'iperf3' is installed, skip the test otherwise +if [ ! -x "$(command -v "iperf3")" ]; then + echo "SKIP: 'iperf3' is not installed. Skipping the test." + exit ${ksft_skip} +fi + +# Determine the number of cores on the machine +num_of_iperf_servers=$(( $(nproc)/2 )) + +# Check if we are running on a multi-core machine, skip the test otherwise +if [ "${num_of_iperf_servers}" -eq 0 ]; then + echo "SKIP: This test is not valid on a single core machine!" + exit ${ksft_skip} +fi + +# Since the kernel soft lockup we're testing causes at least one core to enter +# an infinite loop, destabilizing the host and likely affecting subsequent +# tests, we trigger a kernel panic instead of reporting a failure and +# continuing +kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic) +sysctl -qw kernel.softlockup_panic=1 + +handle_sigint() { + termination_signal="SIGINT" + cleanup + exit ${ksft_skip} +} + +handle_sigalrm() { + termination_signal="SIGALRM" + cleanup + exit ${ksft_pass} +} + +trap handle_sigint SIGINT +trap handle_sigalrm SIGALRM + +(sleep ${TEST_DURATION} && kill -s SIGALRM $$)& + +setup_prepare +test_soft_lockup_during_routing_table_refresh -- 2.35.3

9 months, 4 weeks

2
1
0 0

[PATCH 6.6.y] RDMA/bnxt_re: Avoid CPU lockups due fifo occupancy check loop

by alvalan9＠foxmail.com

From: Selvin Xavier <selvin.xavier(a)broadcom.com> [ Upstream commit 8be3e5b0c96beeefe9d5486b96575d104d3e7d17 ] Driver waits indefinitely for the fifo occupancy to go below a threshold as soon as the pacing interrupt is received. This can cause soft lockup on one of the processors, if the rate of DB is very high. Add a loop count for FPGA and exit the __wait_for_fifo_occupancy_below_th if the loop is taking more time. Pacing will be continuing until the occupancy is below the threshold. This is ensured by the checks in bnxt_re_pacing_timer_exp and further scheduling the work for pacing based on the fifo occupancy. Fixes: 2ad4e6303a6d ("RDMA/bnxt_re: Implement doorbell pacing algorithm") Link: https://patch.msgid.link/r/1728373302-19530-7-git-send-email-selvin.xavier@… Reviewed-by: Kalesh AP <kalesh-anakkur.purayil(a)broadcom.com> Reviewed-by: Chandramohan Akula <chandramohan.akula(a)broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier(a)broadcom.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> [ Add the declaration of variable pacing_data to make it work on 6.6.y ] Signed-off-by: Alva Lan <alvalan9(a)foxmail.com> --- drivers/infiniband/hw/bnxt_re/main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index c7e51cc2ea26..082a383c4913 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -485,6 +485,8 @@ static void bnxt_re_set_default_pacing_data(struct bnxt_re_dev *rdev) static void __wait_for_fifo_occupancy_below_th(struct bnxt_re_dev *rdev) { u32 read_val, fifo_occup; + struct bnxt_qplib_db_pacing_data *pacing_data = rdev->qplib_res.pacing_data; + u32 retry_fifo_check = 1000; /* loop shouldn't run infintely as the occupancy usually goes * below pacing algo threshold as soon as pacing kicks in. @@ -500,6 +502,14 @@ static void __wait_for_fifo_occupancy_below_th(struct bnxt_re_dev *rdev) if (fifo_occup < rdev->qplib_res.pacing_data->pacing_th) break; + if (!retry_fifo_check--) { + dev_info_once(rdev_to_dev(rdev), + "%s: fifo_occup = 0x%xfifo_max_depth = 0x%x pacing_th = 0x%x\n", + __func__, fifo_occup, pacing_data->fifo_max_depth, + pacing_data->pacing_th); + break; + } + } } -- 2.43.0

9 months, 4 weeks

2
1
0 0

[PATCH 5.10.y] m68k: Update ->thread.esp0 before calling syscall_trace() in ret_from_signal

by Finn Thain

From: Al Viro <viro(a)zeniv.linux.org.uk> [ Upstream commit 50e43a57334400668952f8e551c9d87d3ed2dfef ] We get there when sigreturn has performed obscene acts on kernel stack; in particular, the location of pt_regs has shifted. We are about to call syscall_trace(), which might stop for tracer. If that happens, we'd better have task_pt_regs() returning correct result... Fucked-up-by: Al Viro <viro(a)zeniv.linux.org.uk> Fixes: bd6f56a75bb2 ("m68k: Missing syscall_trace() on sigreturn") Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Tested-by: Michael Schmitz <schmitzmic(a)gmail.com> Reviewed-by: Michael Schmitz <schmitzmic(a)gmail.com> Tested-by: Finn Thain <fthain(a)linux-m68k.org> Link: https://lore.kernel.org/r/YP2dMWeV1LkHiOpr@zeniv-ca.linux.org.uk Signed-off-by: Geert Uytterhoeven <geert(a)linux-m68k.org> Signed-off-by: Finn Thain <fthain(a)linux-m68k.org> --- arch/m68k/kernel/entry.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 417d8f0e8962..0d03b4f2077b 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -182,6 +182,8 @@ ENTRY(ret_from_signal) movel %curptr@(TASK_STACK),%a1 tstb %a1@(TINFO_FLAGS+2) jge 1f + lea %sp@(SWITCH_STACK_SIZE),%a1 + movel %a1,%curptr@(TASK_THREAD+THREAD_ESP0) jbsr syscall_trace 1: RESTORE_SWITCH_STACK addql #4,%sp

9 months, 4 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror