Commit 10bcc80e authored by Mathieu Desnoyers's avatar Mathieu Desnoyers Committed by Ingo Molnar

membarrier/x86: Provide core serializing command

There are two places where core serialization is needed by membarrier:

1) When returning from the membarrier IPI,
2) After scheduler updates curr to a thread with a different mm, before
   going back to user-space, since the curr->mm is used by membarrier to
   check whether it needs to send an IPI to that CPU.

x86-32 uses IRET as return from interrupt, and both IRET and SYSEXIT to go
back to user-space. The IRET instruction is core serializing, but not
SYSEXIT.

x86-64 uses IRET as return from interrupt, which takes care of the IPI.
However, it can return to user-space through either SYSRETL (compat
code), SYSRETQ, or IRET. Given that SYSRET{L,Q} is not core serializing,
we rely instead on write_cr3() performed by switch_mm() to provide core
serialization after changing the current mm, and deal with the special
case of kthread -> uthread (temporarily keeping current mm into
active_mm) by adding a sync_core() in that specific case.

Use the new sync_core_before_usermode() to guarantee this.
Signed-off-by: default avatarMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: default avatarThomas Gleixner <tglx@linutronix.de>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrea Parri <parri.andrea@gmail.com>
Cc: Andrew Hunter <ahh@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Avi Kivity <avi@scylladb.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: David Sehr <sehr@google.com>
Cc: Greg Hackmann <ghackmann@google.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Maged Michael <maged.michael@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/20180129202020.8515-10-mathieu.desnoyers@efficios.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 70216e18
...@@ -54,6 +54,7 @@ config X86 ...@@ -54,6 +54,7 @@ config X86
select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_KCOV if X86_64
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_REFCOUNT select ARCH_HAS_REFCOUNT
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
......
...@@ -566,6 +566,11 @@ restore_all: ...@@ -566,6 +566,11 @@ restore_all:
.Lrestore_nocheck: .Lrestore_nocheck:
RESTORE_REGS 4 # skip orig_eax/error_code RESTORE_REGS 4 # skip orig_eax/error_code
.Lirq_return: .Lirq_return:
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
* when returning from IPI handler and when returning from
* scheduler to user-space.
*/
INTERRUPT_RETURN INTERRUPT_RETURN
.section .fixup, "ax" .section .fixup, "ax"
......
...@@ -804,6 +804,10 @@ GLOBAL(restore_regs_and_return_to_kernel) ...@@ -804,6 +804,10 @@ GLOBAL(restore_regs_and_return_to_kernel)
POP_EXTRA_REGS POP_EXTRA_REGS
POP_C_REGS POP_C_REGS
addq $8, %rsp /* skip regs->orig_ax */ addq $8, %rsp /* skip regs->orig_ax */
/*
* ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
* when returning from IPI handler.
*/
INTERRUPT_RETURN INTERRUPT_RETURN
ENTRY(native_iret) ENTRY(native_iret)
......
...@@ -229,9 +229,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, ...@@ -229,9 +229,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
this_cpu_write(cpu_tlbstate.is_lazy, false); this_cpu_write(cpu_tlbstate.is_lazy, false);
/* /*
* The membarrier system call requires a full memory barrier * The membarrier system call requires a full memory barrier and
* before returning to user-space, after storing to rq->curr. * core serialization before returning to user-space, after
* Writing to CR3 provides that full memory barrier. * storing to rq->curr. Writing to CR3 provides that full
* memory barrier and core serializing instruction.
*/ */
if (real_prev == next) { if (real_prev == next) {
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment