The value for some hwprobe keys, like MISALIGNED_VECTOR_PERF, is determined by an asynchronous kthread. This kthread can finish after the hwprobe vDSO data is populated, creating a race condition where userspace can read stale values.

A completion-based framework is introduced to synchronize the async probes with the vDSO population. The init_hwprobe_vdso_data() function is deferred to `late_initcall` and now blocks until all probes signal completion.

Reported-by: Tsukasa OI research_trasio@irq.a4lg.com Closes: https://lore.kernel.org/linux-riscv/760d637b-b13b-4518-b6bf-883d55d44e7f@irq... Fixes: e7c9d66e313b ("RISC-V: Report vector unaligned access speed hwprobe") Cc: Palmer Dabbelt palmer@dabbelt.com Cc: Alexandre Ghiti alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Jingwei Wang wangjingwei@iscas.ac.cn --- Changes in v4: - Reworked the synchronization mechanism based on feedback from Palmer and Alexandre. - Instead of a post-hoc refresh, this version introduces a robust completion-based framework using an atomic counter to ensure async probes are finished before populating the vDSO. - Moved the vdso data initialization to a late_initcall to avoid impacting boot time.

Changes in v3: - Retained existing blank line.

Changes in v2: - Addressed feedback from Yixun's regarding #ifdef CONFIG_MMU usage. - Updated commit message to provide a high-level summary. - Added Fixes tag for commit e7c9d66e313b.

v1: https://lore.kernel.org/linux-riscv/20250521052754.185231-1-wangjingwei@isca...

arch/riscv/include/asm/hwprobe.h | 8 +++++++- arch/riscv/kernel/sys_hwprobe.c | 20 +++++++++++++++++++- arch/riscv/kernel/unaligned_access_speed.c | 9 +++++++-- 3 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 7fe0a379474ae2c6..87af186d92e75ddb 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -40,5 +40,11 @@ static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,

return pair->value == other_pair->value; } - +#ifdef CONFIG_MMU +void riscv_hwprobe_register_async_probe(void); +void riscv_hwprobe_complete_async_probe(void); +#else +inline void riscv_hwprobe_register_async_probe(void) {} +inline void riscv_hwprobe_complete_async_probe(void) {} +#endif #endif diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 0b170e18a2beba57..8c50dcec2b754c30 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -5,6 +5,8 @@ * more details. */ #include <linux/syscalls.h> +#include <linux/completion.h> +#include <linux/atomic.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwprobe.h> @@ -467,6 +469,20 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,

#ifdef CONFIG_MMU

+static DECLARE_COMPLETION(boot_probes_done); +static atomic_t pending_boot_probes = ATOMIC_INIT(0); + +void riscv_hwprobe_register_async_probe(void) +{ + atomic_inc(&pending_boot_probes); +} + +void riscv_hwprobe_complete_async_probe(void) +{ + if (atomic_dec_and_test(&pending_boot_probes)) + complete(&boot_probes_done); +} + static int __init init_hwprobe_vdso_data(void) { struct vdso_arch_data *avd = vdso_k_arch_data; @@ -474,6 +490,8 @@ static int __init init_hwprobe_vdso_data(void) struct riscv_hwprobe pair; int key;

+ if (unlikely(atomic_read(&pending_boot_probes) > 0)) + wait_for_completion(&boot_probes_done); /* * Initialize vDSO data with the answers for the "all CPUs" case, to * save a syscall in the common case. @@ -504,7 +522,7 @@ static int __init init_hwprobe_vdso_data(void) return 0; }

-arch_initcall_sync(init_hwprobe_vdso_data); +late_initcall(init_hwprobe_vdso_data);

#endif /* CONFIG_MMU */

diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index ae2068425fbcd207..4b8ad2673b0f7470 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -379,6 +379,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) { schedule_on_each_cpu(check_vector_unaligned_access); + riscv_hwprobe_complete_async_probe();

return 0; } @@ -473,8 +474,12 @@ static int __init check_unaligned_access_all_cpus(void) per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; } else if (!check_vector_unaligned_access_emulated_all_cpus() && IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { - kthread_run(vec_check_unaligned_access_speed_all_cpus, - NULL, "vec_check_unaligned_access_speed_all_cpus"); + riscv_hwprobe_register_async_probe(); + if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus, + NULL, "vec_check_unaligned_access_speed_all_cpus"))) { + pr_warn("Failed to create vec_unalign_check kthread\n"); + riscv_hwprobe_complete_async_probe(); + } }

/*