summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2015-01-28 15:32:03 +0100
committerIngo Molnar <mingo@kernel.org>2015-01-28 15:33:26 +0100
commit772a9aca12567badb5b9caf2af249a5991f47ea8 (patch)
tree82515ae74c4f3a0740aeec13dd671f18f58d5c96 /kernel
parent41ca5d4e9be11ea6ae040b51d9628a189fd82896 (diff)
parentf6f64681d9d87ded48a90b644b2991c6ee05da2d (diff)
downloadtalos-op-linux-772a9aca12567badb5b9caf2af249a5991f47ea8.tar.gz
talos-op-linux-772a9aca12567badb5b9caf2af249a5991f47ea8.zip
Merge tag 'pr-20150114-x86-entry' of git://git.kernel.org/pub/scm/linux/kernel/git/luto/linux into x86/asm
Pull x86/entry enhancements from Andy Lutomirski: " This is my accumulated x86 entry work, part 1, for 3.20. The meat of this is an IST rework. When an IST exception interrupts user space, we will handle it on the per-thread kernel stack instead of on the IST stack. This sounds messy, but it actually simplifies the IST entry/exit code, because it eliminates some ugly games we used to play in order to handle rescheduling, signal delivery, etc on the way out of an IST exception. The IST rework introduces proper context tracking to IST exception handlers. I haven't seen any bug reports, but the old code could have incorrectly treated an IST exception handler as an RCU extended quiescent state. The memory failure change (included in this pull request with Borislav and Tony's permission) eliminates a bunch of code that is no longer needed now that user memory failure handlers are called in process context. Finally, this includes a few on Denys' uncontroversial and Obviously Correct (tm) cleanups. The IST and memory failure changes have been in -next for a while. LKML references: IST rework: http://lkml.kernel.org/r/cover.1416604491.git.luto@amacapital.net Memory failure change: http://lkml.kernel.org/r/54ab2ffa301102cd6e@agluck-desk.sc.intel.com Denys' cleanups: http://lkml.kernel.org/r/1420927210-19738-1-git-send-email-dvlasenk@redhat.com " This tree semantically depends on and is based on the following RCU commit: 734d16801349 ("rcu: Make rcu_nmi_enter() handle nesting") ... and for that reason won't be pushed upstream before the RCU bits hit Linus's tree. Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/rcu/tree.c66
1 files changed, 49 insertions, 17 deletions
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7680fc275036..4c106fcc0d54 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -759,39 +759,71 @@ void rcu_irq_enter(void)
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
*
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is active.
+ * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and
+ * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know
+ * that the CPU is active. This implementation permits nested NMIs, as
+ * long as the nesting level does not overflow an int. (You will probably
+ * run out of stack space first.)
*/
void rcu_nmi_enter(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+ int incby = 2;
- if (rdtp->dynticks_nmi_nesting == 0 &&
- (atomic_read(&rdtp->dynticks) & 0x1))
- return;
- rdtp->dynticks_nmi_nesting++;
- smp_mb__before_atomic(); /* Force delay from prior write. */
- atomic_inc(&rdtp->dynticks);
- /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
- smp_mb__after_atomic(); /* See above. */
- WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+ /* Complain about underflow. */
+ WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0);
+
+ /*
+ * If idle from RCU viewpoint, atomically increment ->dynticks
+ * to mark non-idle and increment ->dynticks_nmi_nesting by one.
+ * Otherwise, increment ->dynticks_nmi_nesting by two. This means
+ * if ->dynticks_nmi_nesting is equal to one, we are guaranteed
+ * to be in the outermost NMI handler that interrupted an RCU-idle
+ * period (observation due to Andy Lutomirski).
+ */
+ if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
+ smp_mb__before_atomic(); /* Force delay from prior write. */
+ atomic_inc(&rdtp->dynticks);
+ /* atomic_inc() before later RCU read-side crit sects */
+ smp_mb__after_atomic(); /* See above. */
+ WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+ incby = 1;
+ }
+ rdtp->dynticks_nmi_nesting += incby;
+ barrier();
}
/**
* rcu_nmi_exit - inform RCU of exit from NMI context
*
- * If the CPU was idle with dynamic ticks active, and there is no
- * irq handler running, this updates rdtp->dynticks_nmi to let the
- * RCU grace-period handling know that the CPU is no longer active.
+ * If we are returning from the outermost NMI handler that interrupted an
+ * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
+ * to let the RCU grace-period handling know that the CPU is back to
+ * being RCU-idle.
*/
void rcu_nmi_exit(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- if (rdtp->dynticks_nmi_nesting == 0 ||
- --rdtp->dynticks_nmi_nesting != 0)
+ /*
+ * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
+ * (We are exiting an NMI handler, so RCU better be paying attention
+ * to us!)
+ */
+ WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
+ WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+
+ /*
+ * If the nesting level is not 1, the CPU wasn't RCU-idle, so
+ * leave it in non-RCU-idle state.
+ */
+ if (rdtp->dynticks_nmi_nesting != 1) {
+ rdtp->dynticks_nmi_nesting -= 2;
return;
+ }
+
+ /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
+ rdtp->dynticks_nmi_nesting = 0;
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
OpenPOWER on IntegriCloud