diff options
| -rw-r--r-- | Documentation/userspace-api/rseq.rst | 94 | ||||
| -rw-r--r-- | kernel/rseq.c | 144 |
2 files changed, 178 insertions, 60 deletions
diff --git a/Documentation/userspace-api/rseq.rst b/Documentation/userspace-api/rseq.rst index 3cd27a3c7c7e..8549a6c61531 100644 --- a/Documentation/userspace-api/rseq.rst +++ b/Documentation/userspace-api/rseq.rst @@ -24,6 +24,97 @@ Quick access to CPU number, node ID Allows to implement per CPU data efficiently. Documentation is in code and selftests. :( +Optimized RSEQ V2 +----------------- + +On architectures which utilize the generic entry code and generic TIF bits +the kernel supports runtime optimizations for RSEQ, which also enable +enhanced features like scheduler time slice extensions. + +To enable them a task has to register the RSEQ region with at least the +length advertised by getauxval(AT_RSEQ_FEATURE_SIZE). + +If existing binaries register with RSEQ_ORIG_SIZE (32 bytes), the kernel +keeps the legacy low performance mode enabled to fulfil the expectations +of existing users regarding the original RSEQ implementation behaviour. + +The following table documents the ABI and behavioral guarantees of the +legacy and the optimized V2 mode. + +.. list-table:: RSEQ modes + :header-rows: 1 + + * - Nr + - What + + - Legacy + - Optimized V2 + + * - 1 + - The cpu_id_start, cpu_id, node_id and mm_cid fields (User mode read + only) + .. Legacy + - Updated by the kernel unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Updated by the kernel if and only if they change, i.e. if the task + is migrated or mm_cid changes + + * - 2 + - The rseq_cs critical section field + .. Legacy + - Evaluated and handled unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Evaluated and handled conditionally only when user space was + interrupted and was scheduled out or before delivering a signal in + the interrupted context. + + * - 3 + - Read only fields + .. Legacy + - No strict enforcement except in debug mode + .. Optimized V2 + - Strict enforcement + + * - 4 + - membarrier(...RSEQ) + .. Legacy + - All running threads of the process are interrupted and the ID fields + are rewritten and eventually active critical sections are aborted + before they return to user space. All threads which are scheduled + out whether voluntary or not are covered by #1/#2 above. + .. Optimized V2 + - All running threads of the process are interrupted and eventually + active critical sections are aborted before these threads return to + user space. The ID fields are only updated if changed as a + consequence of the interrupt. All threads which are scheduled out + whether voluntary or not are covered by #1/#2 above. + + * - 5 + - Time slice extensions + .. Legacy + - Not supported + .. Optimized V2 + - Supported + +The legacy mode is obviously less performant as it does unconditional +updates and critical section checks even if not strictly required by the +ABI contract. That can't be changed anymore as some users depend on that +observed behavior, which in turn enables them to violate the ABI and +overwrite the cpu_id_start field for their own purposes. This is obviously +discouraged as it renders RSEQ incompatible with the intended usage and +breaks the expectation of other libraries in the same application. + +The ABI compliant optimized v2 mode, which respects the read only fields, +does not require unconditional updates and therefore is way more +performant. The kernel validates the read only fields for compliance. If +user space modifies them, the process is killed. Compliant usage allows +multiple libraries in the same application to benefit from the RSEQ +functionality without disturbing each other. The ABI compliant optimized v2 +mode also enables extended RSEQ features like time slice extensions. + + Scheduler time slice extensions ------------------------------- @@ -37,7 +128,8 @@ The prerequisites for this functionality are: * Enabled at boot time (default is enabled) - * A rseq userspace pointer has been registered for the thread + * A rseq userspace pointer has been registered for the thread in + optimized V2 mode The thread has to enable the functionality via prctl(2):: diff --git a/kernel/rseq.c b/kernel/rseq.c index 101612027f6a..e75e3a5e312c 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -412,70 +412,23 @@ efault: /* The original rseq structure size (including padding) is 32 bytes. */ #define ORIG_RSEQ_SIZE 32 -/* - * sys_rseq - setup restartable sequences for caller thread. - */ -SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +static long rseq_register(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) { u32 rseqfl = 0; u8 version = 1; - if (flags & RSEQ_FLAG_UNREGISTER) { - if (flags & ~RSEQ_FLAG_UNREGISTER) - return -EINVAL; - /* Unregister rseq for current thread. */ - if (current->rseq.usrptr != rseq || !current->rseq.usrptr) - return -EINVAL; - if (rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - if (!rseq_reset_ids()) - return -EFAULT; - rseq_reset(current); - return 0; - } - - if (unlikely(flags & ~(RSEQ_FLAG_SLICE_EXT_DEFAULT_ON))) - return -EINVAL; - - if (current->rseq.usrptr) { - /* - * If rseq is already registered, check whether - * the provided address differs from the prior - * one. - */ - if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - /* Already registered. */ - return -EBUSY; - } - - /* - * If there was no rseq previously registered, ensure the provided rseq - * is properly aligned, as communcated to user-space through the ELF - * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq - * size, the required alignment is the original struct rseq alignment. - * - * The rseq_len is required to be greater or equal to the original rseq - * size. In order to be valid, rseq_len is either the original rseq size, - * or large enough to contain all supported fields, as communicated to - * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. - */ - if (rseq_len < ORIG_RSEQ_SIZE || - (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || - rseq_len < offsetof(struct rseq, end)))) - return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; /* - * The version check effectivly disables time slice extensions until the - * RSEQ ABI V2 registration are implemented. + * Architectures, which use the generic IRQ entry code (at least) enable + * registrations with a size greater than the original v1 fixed sized + * @rseq_len, which has been validated already to utilize the optimized + * v2 ABI mode which also enables extended RSEQ features beyond MMCID. */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_len > ORIG_RSEQ_SIZE) + version = 2; + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && version > 1) { if (rseq_slice_extension_enabled()) { rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; @@ -523,11 +476,10 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 #endif /* - * If rseq was previously inactive, and has just been - * registered, ensure the cpu_id_start and cpu_id fields - * are updated before returning to user-space. + * Ensure the cpu_id_start and cpu_id fields are updated before + * returning to user-space. */ - current->rseq.event.has_rseq = true; + current->rseq.event.has_rseq = version; rseq_force_update(); return 0; @@ -535,6 +487,80 @@ efault: return -EFAULT; } +static long rseq_unregister(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) +{ + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; + if (current->rseq.usrptr != rseq || !current->rseq.usrptr) + return -EINVAL; + if (rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + if (!rseq_reset_ids()) + return -EFAULT; + rseq_reset(current); + return 0; +} + +static long rseq_reregister(struct rseq __user * rseq, u32 rseq_len, u32 sig) +{ + /* + * If rseq is already registered, check whether the provided address + * differs from the prior one. + */ + if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + /* Already registered. */ + return -EBUSY; +} + +static bool rseq_length_valid(struct rseq __user *rseq, unsigned int rseq_len) +{ + /* + * Ensure the provided rseq is properly aligned, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_ALIGN. If + * rseq_len is the original rseq size, the required alignment is the + * original struct rseq alignment. + * + * In order to be valid, rseq_len is either the original rseq size, or + * large enough to contain all supported fields, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. + */ + if (rseq_len < ORIG_RSEQ_SIZE) + return false; + + if (rseq_len == ORIG_RSEQ_SIZE) + return IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE); + + return IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) && + rseq_len >= offsetof(struct rseq, end); +} + +#define RSEQ_FLAGS_SUPPORTED (RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) + +/* + * sys_rseq - Register or unregister restartable sequences for the caller thread. + */ +SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +{ + if (flags & RSEQ_FLAG_UNREGISTER) + return rseq_unregister(rseq, rseq_len, flags, sig); + + if (unlikely(flags & ~RSEQ_FLAGS_SUPPORTED)) + return -EINVAL; + + if (current->rseq.usrptr) + return rseq_reregister(rseq, rseq_len, sig); + + if (!rseq_length_valid(rseq, rseq_len)) + return -EINVAL; + + return rseq_register(rseq, rseq_len, flags, sig); +} + #ifdef CONFIG_RSEQ_SLICE_EXTENSION struct slice_timer { struct hrtimer timer; |