From: Michael Neuling <mikey@neuling.org>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org, kexec@lists.infradead.org,
Anton Blanchard <anton@samba.org>,
jlarrew@linux.vnet.ibm.com
Subject: [PATCH 1/2] powerpc, kexec: Fix race in kexec shutdown
Date: Fri, 14 May 2010 13:57:00 +1000 [thread overview]
Message-ID: <20100514035700.8B6EDCED6E@localhost.localdomain> (raw)
In-Reply-To: <1273559307.55666.645438163872.qpush@pale>
In kexec_prepare_cpus, the primary CPU IPIs the secondary CPUs to
kexec_smp_down(). kexec_smp_down() calls kexec_smp_wait() which sets
the hw_cpu_id() to -1. The primary does this while leaving IRQs on
which means the primary can take a timer interrupt which can lead to
the IPIing one of the secondary CPUs (say, for a scheduler re-balance)
but since the secondary CPU now has a hw_cpu_id = -1, we IPI CPU
-1... Kaboom!
We are hitting this case regularly on POWER7 machines.
There is also a second race, where the primary will tear down the MMU
mappings before knowing the secondaries have entered real mode.
Also, the secondaries are clearing out any pending IPIs before
guaranteeing that no more will be received.
This changes kexec_prepare_cpus() so that we turn off IRQs in the
primary CPU much earlier. It adds a paca flag to say that the
secondaries have entered the kexec_smp_down() IPI and turned off IRQs,
rather than overloading hw_cpu_id with -1. This new paca flag is
again used to in indicate when the secondaries has entered real mode.
It also ensures that all CPUs have their IRQs off before we clear out
any pending IPI requests (in kexec_cpu_down()) to ensure there are no
trailing IPIs left unacknowledged.
Signed-off-by: Michael Neuling <mikey@neuling.org>
---
arch/powerpc/include/asm/kexec.h | 4 ++
arch/powerpc/include/asm/paca.h | 1
arch/powerpc/kernel/asm-offsets.c | 1
arch/powerpc/kernel/machine_kexec_64.c | 48 +++++++++++++++++++++++----------
arch/powerpc/kernel/misc_64.S | 8 +++--
arch/powerpc/kernel/paca.c | 2 +
6 files changed, 47 insertions(+), 17 deletions(-)
Index: linux-2.6-ozlabs/arch/powerpc/include/asm/kexec.h
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/include/asm/kexec.h
+++ linux-2.6-ozlabs/arch/powerpc/include/asm/kexec.h
@@ -31,6 +31,10 @@
#define KEXEC_ARCH KEXEC_ARCH_PPC
#endif
+#define KEXEC_STATE_NONE 0
+#define KEXEC_STATE_IRQS_OFF 1
+#define KEXEC_STATE_REAL_MODE 2
+
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
#include <asm/reg.h>
Index: linux-2.6-ozlabs/arch/powerpc/include/asm/paca.h
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/include/asm/paca.h
+++ linux-2.6-ozlabs/arch/powerpc/include/asm/paca.h
@@ -82,6 +82,7 @@ struct paca_struct {
s16 hw_cpu_id; /* Physical processor number */
u8 cpu_start; /* At startup, processor spins until */
/* this becomes non-zero. */
+ u8 kexec_state; /* set when kexec down has irqs off */
#ifdef CONFIG_PPC_STD_MMU_64
struct slb_shadow *slb_shadow_ptr;
Index: linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/asm-offsets.c
@@ -184,6 +184,7 @@ int main(void)
#endif /* CONFIG_PPC_STD_MMU_64 */
DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+ DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
Index: linux-2.6-ozlabs/arch/powerpc/kernel/machine_kexec_64.c
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/machine_kexec_64.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/machine_kexec_64.c
@@ -155,33 +155,38 @@ void kexec_copy_flush(struct kimage *ima
#ifdef CONFIG_SMP
-/* FIXME: we should schedule this function to be called on all cpus based
- * on calling the interrupts, but we would like to call it off irq level
- * so that the interrupt controller is clean.
- */
+static int kexec_all_irq_disabled = 0;
+
static void kexec_smp_down(void *arg)
{
+ local_irq_disable();
+ mb(); /* make sure our irqs are disabled before we say they are */
+ get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+ while(kexec_all_irq_disabled == 0)
+ cpu_relax();
+ mb(); /* make sure all irqs are disabled before this */
+ /*
+ * Now every CPU has IRQs off, we can clear out any pending
+ * IPIs and be sure that no more will come in after this.
+ */
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 1);
- local_irq_disable();
kexec_smp_wait();
/* NOTREACHED */
}
-static void kexec_prepare_cpus(void)
+static void kexec_prepare_cpus_wait(int wait_state)
{
int my_cpu, i, notified=-1;
- smp_call_function(kexec_smp_down, NULL, /* wait */0);
my_cpu = get_cpu();
-
- /* check the others cpus are now down (via paca hw cpu id == -1) */
+ /* check the others cpus are now down (via paca kexec_irqs_off == 1) */
for (i=0; i < NR_CPUS; i++) {
if (i == my_cpu)
continue;
- while (paca[i].hw_cpu_id != -1) {
+ while (paca[i].kexec_state < wait_state) {
barrier();
if (!cpu_possible(i)) {
printk("kexec: cpu %d hw_cpu_id %d is not"
@@ -201,20 +206,35 @@ static void kexec_prepare_cpus(void)
}
if (i != notified) {
printk( "kexec: waiting for cpu %d (physical"
- " %d) to go down\n",
- i, paca[i].hw_cpu_id);
+ " %d) to enter %i state\n",
+ i, paca[i].hw_cpu_id, wait_state);
notified = i;
}
}
}
+ mb();
+}
+
+static void kexec_prepare_cpus(void)
+{
+
+ smp_call_function(kexec_smp_down, NULL, /* wait */0);
+ local_irq_disable();
+ mb(); /* make sure IRQs are disabled before we say they are */
+ get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+
+ kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
+ /* we are sure every CPU has IRQs off at this point */
+ kexec_all_irq_disabled = 1;
/* after we tell the others to go down */
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 0);
- put_cpu();
+ /* Before removing MMU mapings make sure all CPUs have entered real mode */
+ kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
- local_irq_disable();
+ put_cpu();
}
#else /* ! SMP */
Index: linux-2.6-ozlabs/arch/powerpc/kernel/misc_64.S
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/misc_64.S
+++ linux-2.6-ozlabs/arch/powerpc/kernel/misc_64.S
@@ -24,6 +24,7 @@
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
#include <asm/thread_info.h>
+#include <asm/kexec.h>
.text
@@ -471,6 +472,10 @@ _GLOBAL(kexec_wait)
1: mflr r5
addi r5,r5,kexec_flag-1b
+ li r4,KEXEC_STATE_REAL_MODE
+ stb r4,PACAKEXECSTATE(r13)
+ SYNC
+
99: HMT_LOW
#ifdef CONFIG_KEXEC /* use no memory without kexec */
lwz r4,0(r5)
@@ -494,14 +499,11 @@ kexec_flag:
* note: this is a terminal routine, it does not save lr
*
* get phys id from paca
- * set paca id to -1 to say we got here
* switch to real mode
* join other cpus in kexec_wait(phys_id)
*/
_GLOBAL(kexec_smp_wait)
lhz r3,PACAHWCPUID(r13)
- li r4,-1
- sth r4,PACAHWCPUID(r13) /* let others know we left */
bl real_mode
b .kexec_wait
Index: linux-2.6-ozlabs/arch/powerpc/kernel/paca.c
===================================================================
--- linux-2.6-ozlabs.orig/arch/powerpc/kernel/paca.c
+++ linux-2.6-ozlabs/arch/powerpc/kernel/paca.c
@@ -18,6 +18,7 @@
#include <asm/pgtable.h>
#include <asm/iseries/lpar_map.h>
#include <asm/iseries/hv_types.h>
+#include <asm/kexec.h>
/* This symbol is provided by the linker - let it fill in the paca
* field correctly */
@@ -97,6 +98,7 @@ void __init initialise_paca(struct paca_
new_paca->kernelbase = (unsigned long) _stext;
new_paca->kernel_msr = MSR_KERNEL;
new_paca->hw_cpu_id = 0xffff;
+ new_paca->kexec_state = KEXEC_STATE_NONE;
new_paca->__current = &init_task;
#ifdef CONFIG_PPC_STD_MMU_64
new_paca->slb_shadow_ptr = &slb_shadow[cpu];
next prev parent reply other threads:[~2010-05-14 3:57 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-11 6:28 [PATCH] powerpc, kexec: Fix race in kexec shutdown Michael Neuling
2010-05-14 3:57 ` [PATCH 2/2] powerpc, kdump: Fix race in kdump shutdown Michael Neuling
2010-05-14 3:57 ` Michael Neuling [this message]
2010-05-14 5:40 ` Michael Neuling
2010-05-24 19:23 ` Kumar Gala
2010-05-24 19:29 ` Kumar Gala
2010-05-24 23:53 ` Michael Neuling
2010-05-14 5:40 ` [PATCH 1/2] powerpc, kexec: Fix race in kexec shutdown Michael Neuling
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=20100514035700.8B6EDCED6E@localhost.localdomain \
--to=mikey@neuling.org \
--cc=anton@samba.org \
--cc=benh@kernel.crashing.org \
--cc=jlarrew@linux.vnet.ibm.com \
--cc=kexec@lists.infradead.org \
--cc=linuxppc-dev@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).