summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAndy Lutomirski <luto@kernel.org>2020-12-03 21:07:03 -0800
committerThomas Gleixner <tglx@linutronix.de>2020-12-09 09:37:42 +0100
commita493d1ca1a03b532871f1da27f8dbda2b28b04c4 (patch)
tree61407e37eea602bd636baf5cc44105c85dcb8bf6
parent0477e92881850d44910a7e94fc2c46f96faa131f (diff)
downloadlinux-stable-a493d1ca1a03b532871f1da27f8dbda2b28b04c4.tar.gz
linux-stable-a493d1ca1a03b532871f1da27f8dbda2b28b04c4.tar.bz2
linux-stable-a493d1ca1a03b532871f1da27f8dbda2b28b04c4.zip
x86/membarrier: Get rid of a dubious optimization
sync_core_before_usermode() had an incorrect optimization. If the kernel returns from an interrupt, it can get to usermode without IRET. It just has to schedule to a different task in the same mm and do SYSRET. Fortunately, there were no callers of sync_core_before_usermode() that could have had in_irq() or in_nmi() equal to true, because it's only ever called from the scheduler. While at it, clarify a related comment. Fixes: 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") Signed-off-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/5afc7632be1422f91eaf7611aaaa1b5b8580a086.1607058304.git.luto@kernel.org
-rw-r--r--arch/x86/include/asm/sync_core.h9
-rw-r--r--arch/x86/mm/tlb.c10
2 files changed, 13 insertions, 6 deletions
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index 0fd4a9dfb29c..ab7382f92aff 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -98,12 +98,13 @@ static inline void sync_core_before_usermode(void)
/* With PTI, we unconditionally serialize before running user code. */
if (static_cpu_has(X86_FEATURE_PTI))
return;
+
/*
- * Return from interrupt and NMI is done through iret, which is core
- * serializing.
+ * Even if we're in an interrupt, we might reschedule before returning,
+ * in which case we could switch to a different thread in the same mm
+ * and return using SYSRET or SYSEXIT. Instead of trying to keep
+ * track of our need to sync the core, just sync right away.
*/
- if (in_irq() || in_nmi())
- return;
sync_core();
}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 11666ba19b62..569ac1d57f55 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -474,8 +474,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
/*
* The membarrier system call requires a full memory barrier and
* core serialization before returning to user-space, after
- * storing to rq->curr. Writing to CR3 provides that full
- * memory barrier and core serializing instruction.
+ * storing to rq->curr, when changing mm. This is because
+ * membarrier() sends IPIs to all CPUs that are in the target mm
+ * to make them issue memory barriers. However, if another CPU
+ * switches to/from the target mm concurrently with
+ * membarrier(), it can cause that CPU not to receive an IPI
+ * when it really should issue a memory barrier. Writing to CR3
+ * provides that full memory barrier and core serializing
+ * instruction.
*/
if (real_prev == next) {
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=