linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: linuxppc-dev@lists.ozlabs.org
Cc: Nicholas Piggin <npiggin@gmail.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>
Subject: [PATCH 01/11] powerpc/64: irq_work avoid interrupt when called with hardware irqs enabled
Date: Sat,  5 May 2018 03:19:25 +1000	[thread overview]
Message-ID: <20180504171935.25410-2-npiggin@gmail.com> (raw)
In-Reply-To: <20180504171935.25410-1-npiggin@gmail.com>

irq_work_raise should not cause a decrementer exception unless it is
called from NMI context. Doing so often just results in an immediate
masked decrementer interrupt:

   <...>-550    90d...    4us : update_curr_rt <-dequeue_task_rt
   <...>-550    90d...    5us : dbs_update_util_handler <-update_curr_rt
   <...>-550    90d...    6us : arch_irq_work_raise <-irq_work_queue
   <...>-550    90d...    7us : soft_nmi_interrupt <-soft_nmi_common
   <...>-550    90d...    7us : printk_nmi_enter <-soft_nmi_interrupt
   <...>-550    90d.Z.    8us : rcu_nmi_enter <-soft_nmi_interrupt
   <...>-550    90d.Z.    9us : rcu_nmi_exit <-soft_nmi_interrupt
   <...>-550    90d...    9us : printk_nmi_exit <-soft_nmi_interrupt
   <...>-550    90d...   10us : cpuacct_charge <-update_curr_rt

The soft_nmi_interrupt here is the call into the watchdog, due to the
decrementer interrupt firing with irqs soft-disabled. This is
harmless, but sub-optimal.

When it's not called from NMI context or with interrupts enabled, mark
the decrementer pending in the irq_happened mask directly, rather than
having the masked decrementer interupt handler do it. This will be
replayed at the next local_irq_enable. See the comment for details.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/time.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 360e71d455cc..e7e8611e8863 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -513,6 +513,35 @@ static inline void clear_irq_work_pending(void)
 		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
+void arch_irq_work_raise(void)
+{
+	preempt_disable();
+	set_irq_work_pending_flag();
+	/*
+	 * Non-nmi code running with interrupts disabled will replay
+	 * irq_happened before it re-enables interrupts, so setthe
+	 * decrementer there instead of causing a hardware exception
+	 * which would immediately hit the masked interrupt handler
+	 * and have the net effect of setting the decrementer in
+	 * irq_happened.
+	 *
+	 * NMI interrupts can not check this when they return, so the
+	 * decrementer hardware exception is raised, which will fire
+	 * when interrupts are next enabled.
+	 *
+	 * BookE does not support this yet, it must audit all NMI
+	 * interrupt handlers to ensure they call nmi_enter() so this
+	 * check would be correct.
+	 */
+	if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) {
+		set_dec(1);
+	} else {
+		hard_irq_disable();
+		local_paca->irq_happened |= PACA_IRQ_DEC;
+	}
+	preempt_enable();
+}
+
 #else /* 32-bit */
 
 DEFINE_PER_CPU(u8, irq_work_pending);
@@ -521,8 +550,6 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
 #define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
-#endif /* 32 vs 64 bit */
-
 void arch_irq_work_raise(void)
 {
 	preempt_disable();
@@ -531,6 +558,8 @@ void arch_irq_work_raise(void)
 	preempt_enable();
 }
 
+#endif /* 32 vs 64 bit */
+
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
-- 
2.17.0

  reply	other threads:[~2018-05-04 17:19 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-04 17:19 [PATCH 00/11] assortment of timer, watchdog, interrupt Nicholas Piggin
2018-05-04 17:19 ` Nicholas Piggin [this message]
2018-06-04 14:10   ` [01/11] powerpc/64: irq_work avoid interrupt when called with hardware irqs enabled Michael Ellerman
2018-05-04 17:19 ` [PATCH 02/11] powerpc/pseries: put cede MSR[EE] check under IRQ_SOFT_MASK_DEBUG Nicholas Piggin
2018-05-04 17:19 ` [PATCH 03/11] powerpc/64s: make PACA_IRQ_HARD_DIS track MSR[EE] closely Nicholas Piggin
2018-05-04 17:19 ` [PATCH 04/11] powerpc/64s: micro-optimise __hard_irq_enable() for mtmsrd L=1 support Nicholas Piggin
2018-05-04 17:19 ` [PATCH 05/11] powerpc/64: remove start_tb and accum_tb from thread_struct Nicholas Piggin
2018-05-04 17:19 ` [PATCH 06/11] powerpc/pseries: lparcfg calculate PURR on demand Nicholas Piggin
2018-05-04 17:19 ` [PATCH 07/11] powerpc: generic clockevents broadcast receiver call tick_receive_broadcast Nicholas Piggin
2018-05-05 14:38   ` kbuild test robot
2018-05-04 17:19 ` [PATCH 08/11] powerpc: allow soft-NMI watchdog to cover timer interrupts with large decrementers Nicholas Piggin
2018-05-04 17:19 ` [PATCH 09/11] powerpc: move timer broadcast code under GENERIC_CLOCKEVENTS_BROADCAST ifdef Nicholas Piggin
2018-05-04 17:19 ` [PATCH 10/11] powerpc: move a stray NMI IPI case under NMI_IPI ifdef Nicholas Piggin
2018-05-04 17:19 ` [PATCH 11/11] powerpc/time: account broadcast timer event interrupts separately Nicholas Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180504171935.25410-2-npiggin@gmail.com \
    --to=npiggin@gmail.com \
    --cc=benh@kernel.crashing.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).