diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-21 04:41:08 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-21 04:41:08 +0300 |
commit | 1f2d9ffc7a5f916935749ffc6e93fb33bfe94d2f (patch) | |
tree | a5dabaa924d50867cbe347e20a7643b2850f11c0 /tools/testing/selftests/rseq/rseq.h | |
parent | a2f0e7eee1344eb9f91b22bc72d9eb0a52b849c9 (diff) | |
parent | 7c4a5b89a0b5a57a64b601775b296abf77a9fe97 (diff) | |
download | linux-1f2d9ffc7a5f916935749ffc6e93fb33bfe94d2f.tar.xz |
Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Improve the scalability of the CFS bandwidth unthrottling logic with
large number of CPUs.
- Fix & rework various cpuidle routines, simplify interaction with the
generic scheduler code. Add __cpuidle methods as noinstr to objtool's
noinstr detection and fix boatloads of cpuidle bugs & quirks.
- Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
previously issued registrations.
- Limit scheduler slice duration to the sysctl_sched_latency period, to
improve scheduling granularity with a large number of SCHED_IDLE
tasks.
- Debuggability enhancement on sys_exit(): warn about disabled IRQs,
but also enable them to prevent a cascade of followup problems and
repeat warnings.
- Fix the rescheduling logic in prio_changed_dl().
- Micro-optimize cpufreq and sched-util methods.
- Micro-optimize ttwu_runnable()
- Micro-optimize the idle-scanning in update_numa_stats(),
select_idle_capacity() and steal_cookie_task().
- Update the RSEQ code & self-tests
- Constify various scheduler methods
- Remove unused methods
- Refine __init tags
- Documentation updates
- Misc other cleanups, fixes
* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
sched/rt: pick_next_rt_entity(): check list_entry
sched/deadline: Add more reschedule cases to prio_changed_dl()
sched/fair: sanitize vruntime of entity being placed
sched/fair: Remove capacity inversion detection
sched/fair: unlink misfit task from cpu overutilized
objtool: mem*() are not uaccess safe
cpuidle: Fix poll_idle() noinstr annotation
sched/clock: Make local_clock() noinstr
sched/clock/x86: Mark sched_clock() noinstr
x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
x86/atomics: Always inline arch_atomic64*()
cpuidle: tracing, preempt: Squash _rcuidle tracing
cpuidle: tracing: Warn about !rcu_is_watching()
cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
cpuidle: drivers: firmware: psci: Dont instrument suspend code
KVM: selftests: Fix build of rseq test
exit: Detect and fix irq disabled state in oops
cpuidle, arm64: Fix the ARM64 cpuidle logic
cpuidle: mvebu: Fix duplicate flags assignment
sched/fair: Limit sched slice duration
...
Diffstat (limited to 'tools/testing/selftests/rseq/rseq.h')
-rw-r--r-- | tools/testing/selftests/rseq/rseq.h | 215 |
1 files changed, 211 insertions, 4 deletions
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 6f7513384bf5..d7364ea4d201 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -20,6 +20,15 @@ #include "rseq-abi.h" #include "compiler.h" +#ifndef rseq_sizeof_field +#define rseq_sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +#ifndef rseq_offsetofend +#define rseq_offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + rseq_sizeof_field(TYPE, MEMBER)) +#endif + /* * Empty code injection macros, override when testing. * It is important to consider that the ASM injection macros need to be @@ -47,14 +56,38 @@ #include "rseq-thread-pointer.h" -/* Offset from the thread pointer to the rseq area. */ +/* Offset from the thread pointer to the rseq area. */ extern ptrdiff_t rseq_offset; -/* Size of the registered rseq area. 0 if the registration was - unsuccessful. */ + +/* + * Size of the registered rseq area. 0 if the registration was + * unsuccessful. + */ extern unsigned int rseq_size; -/* Flags used during rseq registration. */ + +/* Flags used during rseq registration. */ extern unsigned int rseq_flags; +/* + * rseq feature size supported by the kernel. 0 if the registration was + * unsuccessful. + */ +extern unsigned int rseq_feature_size; + +enum rseq_mo { + RSEQ_MO_RELAXED = 0, + RSEQ_MO_CONSUME = 1, /* Unused */ + RSEQ_MO_ACQUIRE = 2, /* Unused */ + RSEQ_MO_RELEASE = 3, + RSEQ_MO_ACQ_REL = 4, /* Unused */ + RSEQ_MO_SEQ_CST = 5, /* Unused */ +}; + +enum rseq_percpu_mode { + RSEQ_PERCPU_CPU_ID = 0, + RSEQ_PERCPU_MM_CID = 1, +}; + static inline struct rseq_abi *rseq_get_abi(void) { return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); @@ -119,6 +152,11 @@ int rseq_unregister_current_thread(void); int32_t rseq_fallback_current_cpu(void); /* + * Restartable sequence fallback for reading the current node number. + */ +int32_t rseq_fallback_current_node(void); + +/* * Values returned can be either the current CPU number, -1 (rseq is * uninitialized), or -2 (rseq initialization has failed). */ @@ -153,6 +191,30 @@ static inline uint32_t rseq_current_cpu(void) return cpu; } +static inline bool rseq_node_id_available(void) +{ + return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, node_id); +} + +/* + * Current NUMA node number. + */ +static inline uint32_t rseq_current_node_id(void) +{ + assert(rseq_node_id_available()); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->node_id); +} + +static inline bool rseq_mm_cid_available(void) +{ + return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, mm_cid); +} + +static inline uint32_t rseq_current_mm_cid(void) +{ + return RSEQ_ACCESS_ONCE(rseq_get_abi()->mm_cid); +} + static inline void rseq_clear_rseq_cs(void) { RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); @@ -174,4 +236,149 @@ static inline void rseq_prepare_unload(void) rseq_clear_rseq_cs(); } +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t newv, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_storev_relaxed_cpu_id(v, expect, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_storev_relaxed_mm_cid(v, expect, newv, cpu); + } + return -1; +} + +/* + * Compare @v against @expectnot. When it does _not_ match, load @v + * into @load, and store the content of *@v + voffp into @v. + */ +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expectnot, long voffp, intptr_t *load, + int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpnev_storeoffp_load_relaxed_cpu_id(v, expectnot, voffp, load, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpnev_storeoffp_load_relaxed_mm_cid(v, expectnot, voffp, load, cpu); + } + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t count, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_addv_relaxed_cpu_id(v, count, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_addv_relaxed_mm_cid(v, count, cpu); + } + return -1; +} + +#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV +/* + * pval = *(ptr+off) + * *pval += inc; + */ +static inline __attribute__((always_inline)) +int rseq_offset_deref_addv(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *ptr, long off, intptr_t inc, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_offset_deref_addv_relaxed_cpu_id(ptr, off, inc, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_offset_deref_addv_relaxed_mm_cid(ptr, off, inc, cpu); + } + return -1; +} +#endif + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + switch (rseq_mo) { + case RSEQ_MO_RELAXED: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trystorev_storev_relaxed_cpu_id(v, expect, v2, newv2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trystorev_storev_relaxed_mm_cid(v, expect, v2, newv2, newv, cpu); + } + return -1; + case RSEQ_MO_RELEASE: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trystorev_storev_release_cpu_id(v, expect, v2, newv2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trystorev_storev_release_mm_cid(v, expect, v2, newv2, newv, cpu); + } + return -1; + default: + return -1; + } +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_cmpeqv_storev_relaxed_cpu_id(v, expect, v2, expect2, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_cmpeqv_storev_relaxed_mm_cid(v, expect, v2, expect2, newv, cpu); + } + return -1; +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode percpu_mode, + intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + switch (rseq_mo) { + case RSEQ_MO_RELAXED: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trymemcpy_storev_relaxed_cpu_id(v, expect, dst, src, len, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trymemcpy_storev_relaxed_mm_cid(v, expect, dst, src, len, newv, cpu); + } + return -1; + case RSEQ_MO_RELEASE: + switch (percpu_mode) { + case RSEQ_PERCPU_CPU_ID: + return rseq_cmpeqv_trymemcpy_storev_release_cpu_id(v, expect, dst, src, len, newv, cpu); + case RSEQ_PERCPU_MM_CID: + return rseq_cmpeqv_trymemcpy_storev_release_mm_cid(v, expect, dst, src, len, newv, cpu); + } + return -1; + default: + return -1; + } +} + #endif /* RSEQ_H_ */ |