From c58ea9adf7342508c6ac0b7ad79ef10d589f9c6e Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 15 Jul 2026 17:45:38 -0700 Subject: [PATCH 1/2] smp: Avoid invalid per-CPU CSD lookup with CSD lock debug Commit b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") made smp_call_function_single() use the destination CPU's csd_data when CSD lock debugging is enabled. That lets the debug code associate a stuck CSD lock with the target CPU, but it also means the CPU argument is used in per_cpu_ptr() before generic_exec_single() has a chance to validate it. This becomes unsafe when smp_call_function_any() cannot find an online CPU in the supplied mask. In that case the selected CPU can be nr_cpu_ids, and the !wait path calls get_single_csd_data(cpu) before generic_exec_single() returns -ENXIO. With csdlock_debug_enabled set, that indexes the per-CPU offset array with an invalid CPU number. Use the destination CPU's csd_data only when the CPU number is within nr_cpu_ids. For invalid CPU numbers, fall back to the local CPU's csd_data and let generic_exec_single() perform the existing validation and return -ENXIO. Fixes: b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") Signed-off-by: Chuyi Zhou Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Reviewed-by: Paul E. McKenney Acked-by: Muchun Song Link: https://patch.msgid.link/20260716004539.13983-1-paulmck@kernel.org --- kernel/smp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/smp.c b/kernel/smp.c index a0bb56bd8dda..dc6582bb35d0 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -380,7 +380,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static call_single_data_t *get_single_csd_data(int cpu) { - if (static_branch_unlikely(&csdlock_debug_enabled)) + if (static_branch_unlikely(&csdlock_debug_enabled) && + (unsigned int)cpu < nr_cpu_ids) return per_cpu_ptr(&csd_data, cpu); return this_cpu_ptr(&csd_data); } From 35551efb155e3b83445a6c3f66cb498d5efc182c Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 15 Jul 2026 17:45:39 -0700 Subject: [PATCH 2/2] smp: Make CSD lock acquisition atomic for debug mode Commit b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") changed smp_call_function_single() so that, when CSD lock debugging is enabled, async !wait calls use the destination CPU csd_data. That improves diagnostics, but it also removes the single-writer property that made the old csd_lock() safe: multiple CPUs can now prepare the same destination CPU CSD concurrently. csd_lock() currently waits for CSD_FLAG_LOCK to clear and then sets the bit with a non-atomic read-modify-write. Two senders can both see an unlocked CSD, set the bit, overwrite the callback fields, and enqueue the same llist node. Re-adding a node that is already the queue head can make node->next point to itself, leaving the target CPU stuck walking call_single_queue. Later synchronous work, such as a TLB shootdown, can then remain queued and trigger soft-lockup warnings or panics. Keep the single csd_lock() implementation, but when CSD lock debugging is enabled, acquire CSD_FLAG_LOCK with try_cmpxchg_acquire(). This makes the destination CPU CSD a real atomic lock in the only configuration where it can be shared by multiple remote senders, while preserving the existing non-debug fast path. Fixes: b0473dcd4b1d ("smp: Improve smp_call_function_single() CSD-lock diagnostics") Signed-off-by: Chuyi Zhou Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260716004539.13983-2-paulmck@kernel.org --- kernel/smp.c | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/kernel/smp.c b/kernel/smp.c index dc6582bb35d0..52dffc86555c 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -137,10 +137,10 @@ csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) trace_csd_function_exit(func, csd); } -#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG - static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); +#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG + /* * Parse the csdlock_debug= kernel boot parameter. * @@ -342,6 +342,10 @@ static __always_inline void csd_lock_wait(call_single_data_t *csd) smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else +static __always_inline void __csd_lock_wait(call_single_data_t *csd) +{ +} + static void csd_lock_record(call_single_data_t *csd) { } @@ -354,8 +358,23 @@ static __always_inline void csd_lock_wait(call_single_data_t *csd) static __always_inline void csd_lock(call_single_data_t *csd) { - csd_lock_wait(csd); - csd->node.u_flags |= CSD_FLAG_LOCK; + if (IS_ENABLED(CONFIG_CSD_LOCK_WAIT_DEBUG) && + static_branch_unlikely(&csdlock_debug_enabled)) { + + for (;;) { + unsigned int flags; + + __csd_lock_wait(csd); + flags = READ_ONCE(csd->node.u_flags); + + if (!(flags & CSD_FLAG_LOCK) && + try_cmpxchg_acquire(&csd->node.u_flags, &flags, flags | CSD_FLAG_LOCK)) + break; + } + } else { + csd_lock_wait(csd); + csd->node.u_flags |= CSD_FLAG_LOCK; + } /* * prevent CPU from reordering the above assignment