diff --git a/include/linux/sched.h b/include/linux/sched.h index d380bffee2ef..b5916be49f62 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1367,6 +1367,15 @@ struct task_struct { * with respect to preemption. */ unsigned long rseq_event_mask; +# ifdef CONFIG_DEBUG_RSEQ + /* + * This is a place holder to save a copy of the rseq fields for + * validation of read-only fields. The struct rseq has a + * variable-length array at the end, so it cannot be used + * directly. Reserve a size large enough for the known fields. + */ + char rseq_fields[sizeof(struct rseq)]; +# endif #endif #ifdef CONFIG_SCHED_MM_CID diff --git a/kernel/rseq.c b/kernel/rseq.c index 9de6e35fe679..e04bb30a2eb8 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -25,6 +26,78 @@ RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) +#ifdef CONFIG_DEBUG_RSEQ +static struct rseq *rseq_kernel_fields(struct task_struct *t) +{ + return (struct rseq *) t->rseq_fields; +} + +static int rseq_validate_ro_fields(struct task_struct *t) +{ + static DEFINE_RATELIMIT_STATE(_rs, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + u32 cpu_id_start, cpu_id, node_id, mm_cid; + struct rseq __user *rseq = t->rseq; + + /* + * Validate fields which are required to be read-only by + * user-space. + */ + if (!user_read_access_begin(rseq, t->rseq_len)) + goto efault; + unsafe_get_user(cpu_id_start, &rseq->cpu_id_start, efault_end); + unsafe_get_user(cpu_id, &rseq->cpu_id, efault_end); + unsafe_get_user(node_id, &rseq->node_id, efault_end); + unsafe_get_user(mm_cid, &rseq->mm_cid, efault_end); + user_read_access_end(); + + if ((cpu_id_start != rseq_kernel_fields(t)->cpu_id_start || + cpu_id != rseq_kernel_fields(t)->cpu_id || + node_id != rseq_kernel_fields(t)->node_id || + mm_cid != rseq_kernel_fields(t)->mm_cid) && __ratelimit(&_rs)) { + + pr_warn("Detected rseq corruption for pid: %d, name: %s\n" + "\tcpu_id_start: %u ?= %u\n" + "\tcpu_id: %u ?= %u\n" + "\tnode_id: %u ?= %u\n" + "\tmm_cid: %u ?= %u\n", + t->pid, t->comm, + cpu_id_start, rseq_kernel_fields(t)->cpu_id_start, + cpu_id, rseq_kernel_fields(t)->cpu_id, + node_id, rseq_kernel_fields(t)->node_id, + mm_cid, rseq_kernel_fields(t)->mm_cid); + } + + /* For now, only print a console warning on mismatch. */ + return 0; + +efault_end: + user_read_access_end(); +efault: + return -EFAULT; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ + rseq_kernel_fields(t)->cpu_id_start = cpu_id; + rseq_kernel_fields(t)->cpu_id = cpu_id; + rseq_kernel_fields(t)->node_id = node_id; + rseq_kernel_fields(t)->mm_cid = mm_cid; +} +#else +static int rseq_validate_ro_fields(struct task_struct *t) +{ + return 0; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ +} +#endif + /* * * Restartable sequences are a lightweight interface that allows @@ -92,6 +165,11 @@ static int rseq_update_cpu_node_id(struct task_struct *t) u32 node_id = cpu_to_node(cpu_id); u32 mm_cid = task_mm_cid(t); + /* + * Validate read-only rseq fields. + */ + if (rseq_validate_ro_fields(t)) + goto efault; WARN_ON_ONCE((int) mm_cid < 0); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; @@ -105,6 +183,7 @@ static int rseq_update_cpu_node_id(struct task_struct *t) * t->rseq_len != ORIG_RSEQ_SIZE. */ user_write_access_end(); + rseq_set_ro_fields(t, cpu_id, cpu_id, node_id, mm_cid); trace_rseq_update(t); return 0; @@ -119,6 +198,11 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, mm_cid = 0; + /* + * Validate read-only rseq fields. + */ + if (!rseq_validate_ro_fields(t)) + return -EFAULT; /* * Reset cpu_id_start to its initial state (0). */ @@ -141,6 +225,9 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) */ if (put_user(mm_cid, &t->rseq->mm_cid)) return -EFAULT; + + rseq_set_ro_fields(t, cpu_id_start, cpu_id, node_id, mm_cid); + /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if @@ -423,6 +510,17 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, current->rseq = rseq; current->rseq_len = rseq_len; current->rseq_sig = sig; +#ifdef CONFIG_DEBUG_RSEQ + /* + * Initialize the in-kernel rseq fields copy for validation of + * read-only fields. + */ + if (get_user(rseq_kernel_fields(current)->cpu_id_start, &rseq->cpu_id_start) || + get_user(rseq_kernel_fields(current)->cpu_id, &rseq->cpu_id) || + get_user(rseq_kernel_fields(current)->node_id, &rseq->node_id) || + get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid)) + return -EFAULT; +#endif /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields