membarrier: Provide register expedited private command
Mathieu Desnoyers
maintainerPATCH v5 1/3 membarrier: Provide register expedited private command
Provide a new command allowing processes to register their intent to use the private expedited command.
This allows PowerPC to skip the full memory barrier in switch_mm(), and only issue the barrier when scheduling into a task belonging to a process that has registered to use expedited private.
Processes are now required to register before using MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM.
Changes since v1:
- Use test_ti_thread_flag(next, ...) instead of test_thread_flag() in powerpc membarrier_arch_sched_in(), given that we want to specifically check the next thread state.
- Add missing ARCH_HAS_MEMBARRIER_HOOKS in Kconfig.
- Use task_thread_info() to pass thread_info from task to *_ti_thread_flag().
Changes since v2:
- Move membarrier_arch_sched_in() call to finish_task_switch().
- Check for NULL t->mm in membarrier_arch_fork().
- Use membarrier_sched_in() in generic code, which invokes the arch-specific membarrier_arch_sched_in(). This fixes allnoconfig build on PowerPC.
- Move asm/membarrier.h include under CONFIG_MEMBARRIER, fixing allnoconfig build on PowerPC.
- Build and runtime tested on PowerPC.
Changes since v3:
- Simply rely on copy_mm() to copy the membarrier_private_expedited mm field on fork.
- powerpc: test thread flag instead of reading membarrier_private_expedited in membarrier_arch_fork().
- powerpc: skip memory barrier in membarrier_arch_sched_in() if coming from kernel thread, since mmdrop() implies a full barrier.
- Set membarrier_private_expedited to 1 only after arch registration code, thus eliminating a race where concurrent commands could succeed when they should fail if issued concurrently with process registration.
- Use READ_ONCE() for membarrier_private_expedited field access in membarrier_private_expedited. Matches WRITE_ONCE() performed in process registration.
Changes since v4:
- Move powerpc hook from sched_in() to switch_mm(), based on feedback from Nicholas Piggin.
--- MAINTAINERS | 2 ++ arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/membarrier.h | 43 +++++++++++++++++++++++++++++ arch/powerpc/include/asm/thread_info.h | 3 ++ arch/powerpc/kernel/Makefile | 2 ++ arch/powerpc/kernel/membarrier.c | 45 ++++++++++++++++++++++++++++++ arch/powerpc/mm/mmu_context.c | 7 +++++ fs/exec.c | 1 + include/linux/mm_types.h | 3 ++ include/linux/sched/mm.h | 50 ++++++++++++++++++++++++++++++++++ include/uapi/linux/membarrier.h | 23 +++++++++++----- init/Kconfig | 3 ++ kernel/fork.c | 2 ++ kernel/sched/core.c | 10 ------- kernel/sched/membarrier.c | 25 ++++++++++++++--- 15 files changed, 199 insertions(+), 21 deletions(-) create mode 100644 arch/powerpc/include/asm/membarrier.h create mode 100644 arch/powerpc/kernel/membarrier.c
MAINTAINERS +2 -0
@@ -8816,6 +8816,8 @@ L: [email protected] S: Supported F: kernel/sched/membarrier.c F: include/uapi/linux/membarrier.h +F: arch/powerpc/kernel/membarrier.c +F: arch/powerpc/include/asm/membarrier.h MEMORY MANAGEMENT L: [email protected]
arch/powerpc/Kconfig +1 -0
@@ -138,6 +138,7 @@ config PPC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_MEMBARRIER_HOOKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
arch/powerpc/include/asm/membarrier.h new file +43 -0
43 lines not on this page · raw message
arch/powerpc/include/asm/thread_info.h +3 -0
@@ -100,6 +100,7 @@ static inline struct thread_info *current_thread_info(void)#if defined(CONFIG_PPC64 )#define TIF_ELF2ABI 18/* function descriptors must die! */ #endif +#define TIF_MEMBARRIER_PRIVATE_EXPEDITED 19/* membarrier */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
@@ -119,6 +120,8 @@ static inline struct thread_info *current_thread_info(void)#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)#define _TIF_NOHZ (1<<TIF_NOHZ) +#define _TIF_MEMBARRIER_PRIVATE_EXPEDITED \ + (1<<TIF_MEMBARRIER_PRIVATE_EXPEDITED)#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ)
arch/powerpc/kernel/Makefile +2 -0
@@ -135,6 +135,8 @@ endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o +obj-$(CONFIG_MEMBARRIER) += membarrier.o + # Disable GCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n UBSAN_SANITIZE_prom_init.o := n
arch/powerpc/kernel/membarrier.c new file +45 -0
45 lines not on this page · raw message
arch/powerpc/mm/mmu_context.c +7 -0
@@ -12,6 +12,7 @@#include <linux/mm.h> #include <linux/cpu.h> +#include <linux/sched/mm.h> #include <asm/mmu_context.h>
@@ -67,6 +68,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,* * On the read side the barrier is in pte_xchg(), which orders * the store to the PTE vs the load of mm_cpumask. +* +* This full barrier is needed by membarrier when switching +* between processes after store to rq->curr, before user-space +* memory accesses. */ smp_mb ();
@@ -89,6 +94,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,if (new_on_cpu)radix_kvm_prefetch_workaround (next); +else +membarrier_arch_switch_mm (prev, next, tsk);/* * The actual HW switching method differs between the various
fs/exec.c +1 -0
@@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename,/* execve succeeded */ current->fs->in_exec =0 ; current->in_execve =0 ; +membarrier_execve (current);acct_update_integrals (current);task_numa_free (current);free_bprm (bprm);
include/linux/mm_types.h +3 -0
@@ -445,6 +445,9 @@ struct mm_struct {unsigned long flags;/* Must use atomic bitops to access the bits */ struct core_state *core_state;/* coredumping support */ +#ifdef CONFIG_MEMBARRIER +int membarrier_private_expedited; +#endif #ifdef CONFIG_AIO spinlock_t ioctx_lock;struct kioctx_table __rcu *ioctx_table;
include/linux/sched/mm.h +50 -0
54 lines not on this page · raw message
include/uapi/linux/membarrier.h +16 -7
@@ -52,21 +52,30 @@* (non-running threads are de facto in such a * state). This only covers threads from the * same processes as the caller thread. This -* command returns 0. The "expedited" commands -* complete faster than the non-expedited ones, -* they never block, but have the downside of -* causing extra overhead. +* command returns 0 on success. The +* "expedited" commands complete faster than +* the non-expedited ones, they never block, +* but have the downside of causing extra +* overhead. A process needs to register its +* intent to use the private expedited command +* prior to using it, otherwise this command +* returns -EPERM. +* @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: +* Register the process intent to use +* MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always +* returns 0. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { -MEMBARRIER_CMD_QUERY =0 , -MEMBARRIER_CMD_SHARED = (1 <<0 ), +MEMBARRIER_CMD_QUERY =0 , +MEMBARRIER_CMD_SHARED = (1 <<0 ),/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ -MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 <<3 ), +MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 <<3 ), +MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 <<4 ), };#endif /* _UAPI_LINUX_MEMBARRIER_H */
init/Kconfig +3 -0
@@ -1400,6 +1400,9 @@ config MEMBARRIER If unsure, say Y. +config ARCH_HAS_MEMBARRIER_HOOKS + bool + config EMBEDDED bool "Embedded system" option allnoconfig_y
kernel/fork.c +2 -0
@@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(*/ copy_seccomp (p); +membarrier_fork (p, clone_flags); +/* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the
kernel/sched/core.c +0 -10
@@ -2644,16 +2644,6 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state;vtime_task_switch (prev);perf_event_task_sched_in (prev, current); -/* -* The membarrier system call requires a full memory barrier -* after storing to rq->curr, before going back to user-space. -* -* TODO: This smp_mb__after_unlock_lock can go away if PPC end -* up adding a full barrier to switch_mm(), or we should figure -* out if a smp_mb__after_unlock_lock is really the proper API -* to use. -*/ -smp_mb__after_unlock_lock ();finish_lock_switch (rq, prev);finish_arch_post_lock_switch ();
kernel/sched/membarrier.c +21 -4
@@ -26,21 +26,25 @@* except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)static void ipi_mb (void *info) {smp_mb ();/* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited (void ) +static int membarrier_private_expedited (void ) {int cpu;bool fallback = false;cpumask_var_t tmpmask; +if (!READ_ONCE (current->mm->membarrier_private_expedited)) +return -EPERM ; +if (num_online_cpus () ==1 ) -return ; +return 0 ;/* * Matches memory barriers around rq->curr modification in
@@ -94,6 +98,17 @@ static void membarrier_private_expedited(void)* rq->curr modification in scheduler. */ smp_mb ();/* exit from system call is not a mb */ +return 0 ; +} + +static void membarrier_register_private_expedited (void ) +{ +struct task_struct *p = current; + +if (READ_ONCE (p->mm->membarrier_private_expedited)) +return ; +membarrier_arch_register_private_expedited (p); +WRITE_ONCE (p->mm->membarrier_private_expedited,1 ); }/**
@@ -144,7 +159,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)synchronize_sched ();return 0 ;case MEMBARRIER_CMD_PRIVATE_EXPEDITED : -membarrier_private_expedited (); +return membarrier_private_expedited (); +case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED : +membarrier_register_private_expedited ();return 0 ;default :return -EINVAL ;
Signature · 1 line
2.11.0
Mathieu Desnoyers
maintainerPATCH 2/3 membarrier: selftest: Test private expedited cmd
Test the new MEMBARRIER_CMD_PRIVATE_EXPEDITED and MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED commands.
Add checks expecting specific error values on system calls expected to fail.
--- .../testing/selftests/membarrier/membarrier_test.c | 109 ++++++++++++++++++--- 1 file changed, 94 insertions(+), 15 deletions(-)
tools/testing/selftests/membarrier/membarrier_test.c +94 -15
@@ -15,49 +15,119 @@ static int sys_membarrier(int cmd, int flags)static int test_membarrier_cmd_fail (void ) {int cmd =-1 , flags =0 ; +const char *test_name ="sys membarrier invalid command" ;if (sys_membarrier (cmd, flags) !=-1 ) {ksft_exit_fail_msg ( -"sys membarrier invalid command test: command = %d, flags = %d. Should fail, but passed\n" , - cmd, flags); +"%s test: command = %d, flags = %d. Should fail, but passed\n" , + test_name, cmd, flags); + } +if (errno !=EINVAL ) { +ksft_exit_fail_msg ( +"%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n" , + test_name, flags,EINVAL ,strerror (EINVAL ), + errno,strerror (errno)); }ksft_test_result_pass ( -"sys membarrier invalid command test: command = %d, flags = %d. Failed as expected\n" , - cmd, flags); +"%s test: command = %d, flags = %d, errno = %d. Failed as expected\n" , + test_name, cmd, flags, errno);return 0 ; }static int test_membarrier_flags_fail (void ) {int cmd =MEMBARRIER_CMD_QUERY , flags =1 ; +const char *test_name ="sys membarrier MEMBARRIER_CMD_QUERY invalid flags" ;if (sys_membarrier (cmd, flags) !=-1 ) {ksft_exit_fail_msg ( -"sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Should fail, but passed\n" , - flags); +"%s test: flags = %d. Should fail, but passed\n" , + test_name, flags); + } +if (errno !=EINVAL ) { +ksft_exit_fail_msg ( +"%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n" , + test_name, flags,EINVAL ,strerror (EINVAL ), + errno,strerror (errno)); }ksft_test_result_pass ( -"sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Failed as expected\n" , - flags); +"%s test: flags = %d, errno = %d. Failed as expected\n" , + test_name, flags, errno);return 0 ; } -static int test_membarrier_success (void ) +static int test_membarrier_shared_success (void ) {int cmd =MEMBARRIER_CMD_SHARED , flags =0 ; -const char *test_name ="sys membarrier MEMBARRIER_CMD_SHARED\n" ; +const char *test_name ="sys membarrier MEMBARRIER_CMD_SHARED" ; + +if (sys_membarrier (cmd, flags) !=0 ) { +ksft_exit_fail_msg ( +"%s test: flags = %d, errno = %d\n" , + test_name, flags, errno); + } + +ksft_test_result_pass ( +"%s test: flags = %d\n" , test_name, flags); +return 0 ; +} + +static int test_membarrier_private_expedited_fail (void ) +{ +int cmd =MEMBARRIER_CMD_PRIVATE_EXPEDITED , flags =0 ; +const char *test_name ="sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED not registered failure" ; + +if (sys_membarrier (cmd, flags) !=-1 ) { +ksft_exit_fail_msg ( +"%s test: flags = %d. Should fail, but passed\n" , + test_name, flags); + } +if (errno !=EPERM ) { +ksft_exit_fail_msg ( +"%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n" , + test_name, flags,EPERM ,strerror (EPERM ), + errno,strerror (errno)); + } + +ksft_test_result_pass ( +"%s test: flags = %d, errno = %d\n" , + test_name, flags, errno); +return 0 ; +} + +static int test_membarrier_register_private_expedited_success (void ) +{ +int cmd =MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED , flags =0 ; +const char *test_name ="sys membarrier MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED" ;if (sys_membarrier (cmd, flags) !=0 ) {ksft_exit_fail_msg ( -"sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n" , - flags); +"%s test: flags = %d, errno = %d\n" , + test_name, flags, errno); }ksft_test_result_pass ( -"sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n" , - flags); +"%s test: flags = %d\n" , + test_name, flags); +return 0 ; +} + +static int test_membarrier_private_expedited_success (void ) +{ +int cmd =MEMBARRIER_CMD_PRIVATE_EXPEDITED , flags =0 ; +const char *test_name ="sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED" ; + +if (sys_membarrier (cmd, flags) !=0 ) { +ksft_exit_fail_msg ( +"%s test: flags = %d, errno = %d\n" , + test_name, flags, errno); + } + +ksft_test_result_pass ( +"%s test: flags = %d\n" , + test_name, flags);return 0 ; }
@@ -71,7 +141,16 @@ static int test_membarrier(void) status =test_membarrier_flags_fail ();if (status)return status; - status =test_membarrier_success (); + status =test_membarrier_shared_success (); +if (status) +return status; + status =test_membarrier_private_expedited_fail (); +if (status) +return status; + status =test_membarrier_register_private_expedited_success (); +if (status) +return status; + status =test_membarrier_private_expedited_success ();if (status)return status;return 0 ;
Signature · 1 line
2.11.0
Mathieu Desnoyers
maintainerPATCH v5 3/3 membarrier: Document scheduler barrier requirements
In reply to Mathieu DesnoyersDocument the membarrier requirement on having a full memory barrier in __schedule() after coming from user-space, before storing to rq->curr. It is provided by smp_mb__after_spinlock() in __schedule().
Document that membarrier requires a full barrier on transition from kernel thread to userspace thread. We currently have an implicit barrier from atomic_dec_and_test() in mmdrop() that ensures this.
The x86 switch_mm_irqs_off() full barrier is currently provided by many cpumask update operations as well as write_cr3(). Document that write_cr3() provides this barrier.
Changes since v1:
- Update comments to match reality for code paths which are after storing to rq->curr, before returning to user-space, based on feedback from Andrea Parri.
Changes since v2:
- Update changelog (smp_mb__before_spinlock -> smp_mb__after_spinlock). Based on feedback from Andrea Parri.
Changes since v3:
- Clarify comments following feeback from Peter Zijlstra. Changes since v4:
- Update comment regarding powerpc barrier.
--- arch/x86/mm/tlb.c | 5 +++++ include/linux/sched/mm.h | 5 +++++ kernel/sched/core.c | 37 ++++++++++++++++++++++++++----------- 3 files changed, 36 insertions(+), 11 deletions(-)
arch/x86/mm/tlb.c +5 -0
@@ -143,6 +143,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, }#endif +/* +* The membarrier system call requires a full memory barrier +* before returning to user-space, after storing to rq->curr. +* Writing to CR3 provides that full memory barrier. +*/ if (real_prev == next) {VM_BUG_ON (this_cpu_read (cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id);
include/linux/sched/mm.h +5 -0
@@ -38,6 +38,11 @@ static inline void mmgrab(struct mm_struct *mm)extern void __mmdrop (struct mm_struct *);static inline void mmdrop (struct mm_struct *mm) { +/* +* The implicit full barrier implied by atomic_dec_and_test is +* required by the membarrier system call before returning to +* user-space, after storing to rq->curr. +*/ if (unlikely (atomic_dec_and_test (&mm->mm_count)))__mmdrop (mm); }
kernel/sched/core.c +26 -11
@@ -2648,6 +2648,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)finish_arch_post_lock_switch ();fire_sched_in_preempt_notifiers (current); +/* +* When transitioning from a kernel thread to a userspace +* thread, mmdrop()'s implicit full barrier is required by the +* membarrier system call, because the current active_mm can +* become the current mm without going through switch_mm(). +*/ if (mm)mmdrop (mm);if (unlikely (prev_state ==TASK_DEAD )) {
@@ -2753,6 +2759,13 @@ context_switch(struct rq *rq, struct task_struct *prev,*/ arch_start_context_switch (prev); +/* +* If mm is non-NULL, we pass through switch_mm(). If mm is +* NULL, we will pass through mmdrop() in finish_task_switch(). +* Both of these contain the full memory barrier required by +* membarrier after storing to rq->curr, before returning to +* user-space. +*/ if (!mm) { next->active_mm = oldmm;mmgrab (oldmm);
@@ -3289,6 +3302,9 @@ static void __sched notrace __schedule(bool preempt)* Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). +* +* The membarrier system call requires a full memory barrier +* after coming from user-space, before storing to rq->curr. */ rq_lock (rq, &rf);smp_mb__after_spinlock ();
@@ -3336,17 +3352,16 @@ static void __sched notrace __schedule(bool preempt)/* * The membarrier system call requires each architecture * to have a full memory barrier after updating -* rq->curr, before returning to user-space. For TSO -* (e.g. x86), the architecture must provide its own -* barrier in switch_mm(). For weakly ordered machines -* for which spin_unlock() acts as a full memory -* barrier, finish_lock_switch() in common code takes -* care of this barrier. For weakly ordered machines for -* which spin_unlock() acts as a RELEASE barrier (only -* arm64 and PowerPC), arm64 has a full barrier in -* switch_to(), and PowerPC has -* smp_mb__after_unlock_lock() before -* finish_lock_switch(). +* rq->curr, before returning to user-space. +* +* Here are the schemes providing that barrier on the +* various architectures: +* - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. +* switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. +* - finish_lock_switch() for weakly-ordered +* architectures where spin_unlock is a full barrier, +* - switch_to() for arm64 (weakly-ordered, spin_unlock +* is a RELEASE barrier), */ ++*switch_count;
Signature · 1 line
2.11.0
Quoted 9 lines · Mathieu Desnoyers
Provide a new command allowing processes to register their intent to use the private expedited command.
This allows PowerPC to skip the full memory barrier in
switch_mm(), and only issue the barrier when scheduling into a task belonging to a process that has registered to use expedited private.Processes are now required to register before using
MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM.
Queued for further review and testing, replacing your two earlier commits. Will send a pull request if there are no objections in the next few days.
Thanx, Paul
Quoted 508 lines
Changes since v1:
- Usetest_ti_thread_flag(next, ...)instead oftest_thread_flag()in powerpcmembarrier_arch_sched_in(), given that we want to specifically check the next thread state.
- Add missingARCH_HAS_MEMBARRIER_HOOKSinKconfig.
- Usetask_thread_info()to passthread_infofrom task to*_ti_thread_flag().Changes since v2:
- Movemembarrier_arch_sched_in()call tofinish_task_switch().
- Check for NULLt->mminmembarrier_arch_fork().
- Usemembarrier_sched_in()in generic code, which invokes the arch-specificmembarrier_arch_sched_in(). This fixes allnoconfig build on PowerPC.
- Moveasm/membarrier.hinclude underCONFIG_MEMBARRIER, fixing allnoconfig build on PowerPC.
- Build and runtime tested on PowerPC.Changes since v3:
- Simply rely oncopy_mm()to copy themembarrier_private_expeditedmm field on fork.
- powerpc: test thread flag instead of readingmembarrier_private_expeditedinmembarrier_arch_fork().
- powerpc: skip memory barrier inmembarrier_arch_sched_in()if coming from kernel thread, sincemmdrop()implies a full barrier.
- Setmembarrier_private_expeditedto 1 only after arch registration code, thus eliminating a race where concurrent commands could succeed when they should fail if issued concurrently with process registration.
- UseREAD_ONCE()formembarrier_private_expeditedfield access inmembarrier_private_expedited. MatchesWRITE_ONCE()performed in process registration.Changes since v4:
- Move powerpc hook fromsched_in()toswitch_mm(), based on feedback from Nicholas Piggin.Signed-off-by Mathieu Desnoyers <[email protected]>CC Peter Zijlstra <[email protected]>CC Paul E. McKenney <[email protected]>CC Boqun Feng <[email protected]>CC Andrew Hunter <[email protected]>CC Maged Michael <[email protected]>CC Avi Kivity <[email protected]>CC Benjamin Herrenschmidt <[email protected]>CC Paul Mackerras <[email protected]>CC Michael Ellerman <[email protected]>CC Dave Watson <[email protected]>CC Alan Stern <[email protected]>CC Will Deacon <[email protected]>CC Andy Lutomirski <[email protected]>CC Ingo Molnar <[email protected]>CC Alexander Viro <[email protected]>CC Nicholas Piggin <[email protected]>--- MAINTAINERS | 2 ++ arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/membarrier.h | 43 +++++++++++++++++++++++++++++ arch/powerpc/include/asm/thread_info.h | 3 ++ arch/powerpc/kernel/Makefile | 2 ++ arch/powerpc/kernel/membarrier.c | 45 ++++++++++++++++++++++++++++++ arch/powerpc/mm/mmu_context.c | 7 +++++ fs/exec.c | 1 + include/linux/mm_types.h | 3 ++ include/linux/sched/mm.h | 50 ++++++++++++++++++++++++++++++++++ include/uapi/linux/membarrier.h | 23 +++++++++++----- init/Kconfig | 3 ++ kernel/fork.c | 2 ++ kernel/sched/core.c | 10 ------- kernel/sched/membarrier.c | 25 ++++++++++++++--- 15 files changed, 199 insertions(+), 21 deletions(-) create mode 100644 arch/powerpc/include/asm/membarrier.h create mode 100644 arch/powerpc/kernel/membarrier.cMAINTAINERS +2
-0@@ -8816,6 +8816,8 @@ L: [email protected] S: Supported F: kernel/sched/membarrier.c F: include/uapi/linux/membarrier.h +F: arch/powerpc/kernel/membarrier.c +F: arch/powerpc/include/asm/membarrier.h MEMORY MANAGEMENT L: [email protected]arch/powerpc/Kconfig +1
-0@@ -138,6 +138,7 @@ config PPC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_MEMBARRIER_HOOKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCASTarch/powerpc/include/asm/membarrier.h new file +43
-0@@ -0,0 +1,43 @@ +#ifndef _ASM_POWERPC_MEMBARRIER_H +#define _ASM_POWERPC_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm (struct mm_struct *prev, +struct mm_struct *next,struct task_struct *tsk) +{ +/* +* Only need the full barrier when switching between processes. +* Barrier when switching from kernel to userspace is not +* required here, given that it is implied by mmdrop(). Barrier +* when switching from userspace to kernel is not needed after +* store to rq->curr. +*/ +if (likely (!test_ti_thread_flag (task_thread_info (tsk), +TIF_MEMBARRIER_PRIVATE_EXPEDITED ) || !prev)) +return ; + +/* +* The membarrier system call requires a full memory barrier +* after storing to rq->curr, before going back to user-space. +*/ +smp_mb (); +} +static inline void membarrier_arch_fork (struct task_struct *t, +unsigned long clone_flags) +{ +/* +* Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread +* fork is protected by siglock. membarrier_arch_fork is called +* with siglock held. +*/ +if (test_thread_flag (TIF_MEMBARRIER_PRIVATE_EXPEDITED )) +set_ti_thread_flag (task_thread_info (t), +TIF_MEMBARRIER_PRIVATE_EXPEDITED ); +} +static inline void membarrier_arch_execve (struct task_struct *t) +{ +clear_ti_thread_flag (task_thread_info (t), +TIF_MEMBARRIER_PRIVATE_EXPEDITED ); +} +void membarrier_arch_register_private_expedited (struct task_struct *t); + +#endif /* _ASM_POWERPC_MEMBARRIER_H */ arch/powerpc/include/asm/thread_info.h +3
-0@@ -100,6 +100,7 @@ static inline struct thread_info *current_thread_info(void)#if defined(CONFIG_PPC64 )#define TIF_ELF2ABI 18/* function descriptors must die! */ #endif +#define TIF_MEMBARRIER_PRIVATE_EXPEDITED 19/* membarrier */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)@@ -119,6 +120,8 @@ static inline struct thread_info *current_thread_info(void)#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)#define _TIF_NOHZ (1<<TIF_NOHZ) +#define _TIF_MEMBARRIER_PRIVATE_EXPEDITED \ + (1<<TIF_MEMBARRIER_PRIVATE_EXPEDITED)#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ)arch/powerpc/kernel/Makefile +2
-0@@ -135,6 +135,8 @@ endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o +obj-$(CONFIG_MEMBARRIER) += membarrier.o + # Disable GCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n UBSAN_SANITIZE_prom_init.o := narch/powerpc/kernel/membarrier.c new file +45
-0@@ -0,0 +1,45 @@ +/* +* Copyright (C) 2010-2017 Mathieu Desnoyers <[email protected]> +* +* membarrier system call - PowerPC architecture code +* +* This program is free software; you can redistribute it and/or modify +* it under the terms of the GNU General Public License as published by +* the Free Software Foundation; either version 2 of the License, or +* (at your option) any later version. +* +* This program is distributed in the hope that it will be useful, +* but WITHOUT ANY WARRANTY; without even the implied warranty of +* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +* GNU General Public License for more details. +*/ + +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/thread_info.h> +#include <linux/spinlock.h> +#include <linux/rcupdate.h> + +void membarrier_arch_register_private_expedited (struct task_struct *p) +{ +struct task_struct *t; + +if (get_nr_threads (p) ==1 ) { +set_thread_flag (TIF_MEMBARRIER_PRIVATE_EXPEDITED ); +return ; + } +/* +* Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread +* fork is protected by siglock. +*/ +spin_lock (&p->sighand->siglock); +for_each_thread (p, t) +set_ti_thread_flag (task_thread_info (t), +TIF_MEMBARRIER_PRIVATE_EXPEDITED ); +spin_unlock (&p->sighand->siglock); +/* +* Ensure all future scheduler executions will observe the new +* thread flag state for this process. +*/ +synchronize_sched (); +}arch/powerpc/mm/mmu_context.c +7
-0@@ -12,6 +12,7 @@#include <linux/mm.h> #include <linux/cpu.h> +#include <linux/sched/mm.h> #include <asm/mmu_context.h> @@ -67,6 +68,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,* * On the read side the barrier is in pte_xchg(), which orders * the store to the PTE vs the load of mm_cpumask. +* +* This full barrier is needed by membarrier when switching +* between processes after store to rq->curr, before user-space +* memory accesses. */ smp_mb ();@@ -89,6 +94,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,if (new_on_cpu)radix_kvm_prefetch_workaround (next); +else +membarrier_arch_switch_mm (prev, next, tsk);/* * The actual HW switching method differs between the various fs/exec.c +1
-0@@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename,/* execve succeeded */ current->fs->in_exec =0 ; current->in_execve =0 ; +membarrier_execve (current);acct_update_integrals (current);task_numa_free (current);free_bprm (bprm);include/linux/mm_types.h +3
-0@@ -445,6 +445,9 @@ struct mm_struct {unsigned long flags;/* Must use atomic bitops to access the bits */ struct core_state *core_state;/* coredumping support */ +#ifdef CONFIG_MEMBARRIER +int membarrier_private_expedited; +#endif #ifdef CONFIG_AIO spinlock_t ioctx_lock;struct kioctx_table __rcu *ioctx_table;include/linux/sched/mm.h +50
-0@@ -205,4 +205,54 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC ) | flags; } +#ifdef CONFIG_MEMBARRIER + +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_HOOKS +#include <asm/membarrier.h> +#else +static inline void membarrier_arch_switch_mm (struct mm_struct *prev, +struct mm_struct *next,struct task_struct *tsk) +{ +} +static inline void membarrier_arch_fork (struct task_struct *t, +unsigned long clone_flags) +{ +} +static inline void membarrier_arch_execve (struct task_struct *t) +{ +} +static inline void membarrier_arch_register_private_expedited ( +struct task_struct *p) +{ +} +#endif + +static inline void membarrier_fork (struct task_struct *t, +unsigned long clone_flags) +{ +/* +* Prior copy_mm() copies the membarrier_private_expedited field +* from current->mm to t->mm. +*/ +membarrier_arch_fork (t, clone_flags); +} +static inline void membarrier_execve (struct task_struct *t) +{ + t->mm->membarrier_private_expedited =0 ; +membarrier_arch_execve (t); +} +#else +static inline void membarrier_arch_switch_mm (struct mm_struct *prev, +struct mm_struct *next,struct task_struct *tsk) +{ +} +static inline void membarrier_fork (struct task_struct *t, +unsigned long clone_flags) +{ +} +static inline void membarrier_execve (struct task_struct *t) +{ +} +#endif +#endif /* _LINUX_SCHED_MM_H */ include/uapi/linux/membarrier.h +16
-7@@ -52,21 +52,30 @@* (non-running threads are de facto in such a * state). This only covers threads from the * same processes as the caller thread. This -* command returns 0. The "expedited" commands -* complete faster than the non-expedited ones, -* they never block, but have the downside of -* causing extra overhead. +* command returns 0 on success. The +* "expedited" commands complete faster than +* the non-expedited ones, they never block, +* but have the downside of causing extra +* overhead. A process needs to register its +* intent to use the private expedited command +* prior to using it, otherwise this command +* returns -EPERM. +* @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: +* Register the process intent to use +* MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always +* returns 0. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { -MEMBARRIER_CMD_QUERY =0 , -MEMBARRIER_CMD_SHARED = (1 <<0 ), +MEMBARRIER_CMD_QUERY =0 , +MEMBARRIER_CMD_SHARED = (1 <<0 ),/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ -MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 <<3 ), +MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 <<3 ), +MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 <<4 ), };#endif /* _UAPI_LINUX_MEMBARRIER_H */ init/Kconfig +3
-0@@ -1400,6 +1400,9 @@ config MEMBARRIER If unsure, say Y. +config ARCH_HAS_MEMBARRIER_HOOKS + bool + config EMBEDDED bool "Embedded system" option allnoconfig_ykernel/fork.c +2
-0@@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(*/ copy_seccomp (p); +membarrier_fork (p, clone_flags); +/* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the kernel/sched/core.c +0
-10@@ -2644,16 +2644,6 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state;vtime_task_switch (prev);perf_event_task_sched_in (prev, current); -/* -* The membarrier system call requires a full memory barrier -* after storing to rq->curr, before going back to user-space. -* -* TODO: This smp_mb__after_unlock_lock can go away if PPC end -* up adding a full barrier to switch_mm(), or we should figure -* out if a smp_mb__after_unlock_lock is really the proper API -* to use. -*/ -smp_mb__after_unlock_lock ();finish_lock_switch (rq, prev);finish_arch_post_lock_switch ();kernel/sched/membarrier.c +21
-4@@ -26,21 +26,25 @@* except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)static void ipi_mb (void *info) {smp_mb ();/* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited (void ) +static int membarrier_private_expedited (void ) {int cpu;bool fallback = false;cpumask_var_t tmpmask; +if (!READ_ONCE (current->mm->membarrier_private_expedited)) +return -EPERM ; +if (num_online_cpus () ==1 ) -return ; +return 0 ;/* * Matches memory barriers around rq->curr modification in @@ -94,6 +98,17 @@ static void membarrier_private_expedited(void)* rq->curr modification in scheduler. */ smp_mb ();/* exit from system call is not a mb */ +return 0 ; +} + +static void membarrier_register_private_expedited (void ) +{ +struct task_struct *p = current; + +if (READ_ONCE (p->mm->membarrier_private_expedited)) +return ; +membarrier_arch_register_private_expedited (p); +WRITE_ONCE (p->mm->membarrier_private_expedited,1 ); }/** @@ -144,7 +159,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)synchronize_sched ();return 0 ;case MEMBARRIER_CMD_PRIVATE_EXPEDITED : -membarrier_private_expedited (); +return membarrier_private_expedited (); +case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED : +membarrier_register_private_expedited ();return 0 ;default :return -EINVAL ;Signature · 1 line
2.11.0