3.0-git19 snapshot
Add epoll patch until it gets upstreamed Add trial patch to fix the scheduling while atomic issues around pidmap_init
This commit is contained in:
Josh Boyer
parent
1aa2339b01
commit
8e3ae989b3
|
|
@ -153,7 +153,8 @@ CONFIG_ACPI_PROCESSOR_AGGREGATOR=m
|
|||
CONFIG_ACPI_HED=m
|
||||
CONFIG_ACPI_APEI=y
|
||||
CONFIG_ACPI_APEI_PCIEAER=y
|
||||
CONFIG_ACPI_APEI_GHES=m
|
||||
CONFIG_ACPI_APEI_GHES=y
|
||||
CONFIG_ACPI_APEI_MEMORY_FAILURE=y
|
||||
# CONFIG_ACPI_APEI_EINJ is not set
|
||||
CONFIG_ACPI_IPMI=m
|
||||
CONFIG_ACPI_CUSTOM_METHOD=m
|
||||
|
|
|
|||
|
|
@ -87,7 +87,8 @@ CONFIG_ACPI_PROCESSOR_AGGREGATOR=m
|
|||
CONFIG_ACPI_HED=m
|
||||
CONFIG_ACPI_APEI=y
|
||||
CONFIG_ACPI_APEI_PCIEAER=y
|
||||
CONFIG_ACPI_APEI_GHES=m
|
||||
CONFIG_ACPI_APEI_GHES=y
|
||||
CONFIG_ACPI_APEI_MEMORY_FAILURE=y
|
||||
# CONFIG_ACPI_APEI_EINJ is not set
|
||||
CONFIG_ACPI_IPMI=m
|
||||
CONFIG_ACPI_CUSTOM_METHOD=m
|
||||
|
|
|
|||
|
|
@ -0,0 +1,116 @@
|
|||
epoll can acquire multiple ep->mutex on multiple "struct eventpoll"s
|
||||
at once in the case where one epoll fd is monitoring another epoll
|
||||
fd. This is perfectly OK, since we're careful about the lock ordering,
|
||||
but causes spurious lockdep warnings. Annotate the recursion using
|
||||
mutex_lock_nested, and add a comment explaining the nesting rules for
|
||||
good measure.
|
||||
|
||||
Reported-by: Paul Bolle <pebolle@tiscali.nl>
|
||||
Signed-off-by: Nelson Elhage <nelhage@nelhage.com>
|
||||
---
|
||||
I've tested this on a synthetic epoll test case, that just adds e1 to
|
||||
e2 and then does an epoll_wait(). I verified that it caused lockdep
|
||||
problems on 3.0 and that this patch fixed it, but I haven't done more
|
||||
extensive testing. Paul, are you able to test systemd against this?
|
||||
|
||||
fs/eventpoll.c | 25 ++++++++++++++++++-------
|
||||
1 files changed, 18 insertions(+), 7 deletions(-)
|
||||
|
||||
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
|
||||
index f9cfd16..0cb7bc6 100644
|
||||
--- a/fs/eventpoll.c
|
||||
+++ b/fs/eventpoll.c
|
||||
@@ -76,6 +76,15 @@
|
||||
* Events that require holding "epmutex" are very rare, while for
|
||||
* normal operations the epoll private "ep->mtx" will guarantee
|
||||
* a better scalability.
|
||||
+ * It is possible to acquire multiple "ep->mtx"es at once in the case
|
||||
+ * when one epoll fd is added to another. In this case, we always
|
||||
+ * acquire the locks in the order of nesting (i.e. after epoll_ctl(e1,
|
||||
+ * EPOLL_CTL_ADD, e2), e1->mtx will always be acquired before
|
||||
+ * e2->mtx). Since we disallow cycles of epoll file descriptors, this
|
||||
+ * ensures that the mutexes are well-ordered. In order to communicate
|
||||
+ * this nesting to lockdep, when walking a tree of epoll file
|
||||
+ * descriptors, we use the current recursion depth as the lockdep
|
||||
+ * subkey.
|
||||
*/
|
||||
|
||||
/* Epoll private bits inside the event mask */
|
||||
@@ -464,13 +473,15 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
|
||||
* @ep: Pointer to the epoll private data structure.
|
||||
* @sproc: Pointer to the scan callback.
|
||||
* @priv: Private opaque data passed to the @sproc callback.
|
||||
+ * @depth: The current depth of recursive f_op->poll calls.
|
||||
*
|
||||
* Returns: The same integer error code returned by the @sproc callback.
|
||||
*/
|
||||
static int ep_scan_ready_list(struct eventpoll *ep,
|
||||
int (*sproc)(struct eventpoll *,
|
||||
struct list_head *, void *),
|
||||
- void *priv)
|
||||
+ void *priv,
|
||||
+ int depth)
|
||||
{
|
||||
int error, pwake = 0;
|
||||
unsigned long flags;
|
||||
@@ -481,7 +492,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
|
||||
* We need to lock this because we could be hit by
|
||||
* eventpoll_release_file() and epoll_ctl().
|
||||
*/
|
||||
- mutex_lock(&ep->mtx);
|
||||
+ mutex_lock_nested(&ep->mtx, depth);
|
||||
|
||||
/*
|
||||
* Steal the ready list, and re-init the original one to the
|
||||
@@ -670,7 +681,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
|
||||
|
||||
static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
|
||||
{
|
||||
- return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
|
||||
+ return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
|
||||
}
|
||||
|
||||
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
|
||||
@@ -737,7 +748,7 @@ void eventpoll_release_file(struct file *file)
|
||||
|
||||
ep = epi->ep;
|
||||
list_del_init(&epi->fllink);
|
||||
- mutex_lock(&ep->mtx);
|
||||
+ mutex_lock_nested(&ep->mtx, 0);
|
||||
ep_remove(ep, epi);
|
||||
mutex_unlock(&ep->mtx);
|
||||
}
|
||||
@@ -1134,7 +1145,7 @@ static int ep_send_events(struct eventpoll *ep,
|
||||
esed.maxevents = maxevents;
|
||||
esed.events = events;
|
||||
|
||||
- return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
|
||||
+ return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
|
||||
}
|
||||
|
||||
static inline struct timespec ep_set_mstimeout(long ms)
|
||||
@@ -1267,7 +1278,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
|
||||
struct rb_node *rbp;
|
||||
struct epitem *epi;
|
||||
|
||||
- mutex_lock(&ep->mtx);
|
||||
+ mutex_lock_nested(&ep->mtx, call_nests + 1);
|
||||
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
|
||||
epi = rb_entry(rbp, struct epitem, rbn);
|
||||
if (unlikely(is_file_epoll(epi->ffd.file))) {
|
||||
@@ -1409,7 +1420,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
|
||||
}
|
||||
|
||||
|
||||
- mutex_lock(&ep->mtx);
|
||||
+ mutex_lock_nested(&ep->mtx, 0);
|
||||
|
||||
/*
|
||||
* Try to lookup the file inside our RB tree, Since we grabbed "mtx"
|
||||
--
|
||||
1.7.4.1
|
||||
|
||||
--
|
||||
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
|
||||
the body of a message to majordomo@vger.kernel.org
|
||||
More majordomo info at http://vger.kernel.org/majordomo-info.html
|
||||
11
kernel.spec
11
kernel.spec
|
|
@ -84,7 +84,7 @@ Summary: The Linux kernel
|
|||
# The rc snapshot level
|
||||
%define rcrev 0
|
||||
# The git snapshot level
|
||||
%define gitrev 17
|
||||
%define gitrev 19
|
||||
# Set rpm version accordingly
|
||||
%define rpmversion 3.%{upstream_sublevel}.0
|
||||
%endif
|
||||
|
|
@ -683,6 +683,8 @@ Patch12021: udlfb-bind-framebuffer-to-interface.patch
|
|||
|
||||
Patch12022: fix-cdc-ncm-dma-stack-vars.patch
|
||||
Patch12023: ums-realtek-driver-uses-stack-memory-for-DMA.patch
|
||||
Patch12024: epoll-fix-spurious-lockdep-warnings.patch
|
||||
Patch12025: rcu-prevent-early-schedule.patch
|
||||
|
||||
# Runtime power management
|
||||
Patch12203: linux-2.6-usb-pci-autosuspend.patch
|
||||
|
|
@ -1260,6 +1262,8 @@ ApplyPatch neuter_intel_microcode_load.patch
|
|||
ApplyPatch udlfb-bind-framebuffer-to-interface.patch
|
||||
ApplyPatch fix-cdc-ncm-dma-stack-vars.patch
|
||||
ApplyPatch ums-realtek-driver-uses-stack-memory-for-DMA.patch
|
||||
ApplyPatch epoll-fix-spurious-lockdep-warnings.patch
|
||||
ApplyPatch rcu-prevent-early-schedule.patch
|
||||
|
||||
# Runtime PM
|
||||
#ApplyPatch linux-2.6-usb-pci-autosuspend.patch
|
||||
|
|
@ -1891,6 +1895,11 @@ fi
|
|||
# ||----w |
|
||||
# || ||
|
||||
%changelog
|
||||
* Thu Aug 04 2011 Josh Boyer <jwboyer@redhat.com>
|
||||
- Linux 3.0-git19
|
||||
- Add patch to fix epoll backtrace (rhbz 722472)
|
||||
- Add trial patch to fix rhbz 726877
|
||||
|
||||
* Wed Aug 03 2011 Dave Jones <davej@redhat.com>
|
||||
- Re-apply the rebased utrace
|
||||
|
||||
|
|
|
|||
|
|
@ -1,17 +1,17 @@
|
|||
From df42d15cd28f468ecd4c30465b98a53cce90617c Mon Sep 17 00:00:00 2001
|
||||
From f72d640713d01b3b704c6e84ab49b62f19fc9c22 Mon Sep 17 00:00:00 2001
|
||||
From: Kyle McMartin <kyle@phobos.i.jkkm.org>
|
||||
Date: Tue, 30 Mar 2010 00:16:25 -0400
|
||||
Subject: dev-crash-driver.patch
|
||||
Subject: [PATCH] dev-crash-driver.patch
|
||||
|
||||
---
|
||||
arch/ia64/include/asm/crash.h | 90 +++++++++++++++++++++++++++++
|
||||
arch/ia64/kernel/ia64_ksyms.c | 3 +
|
||||
arch/x86/include/asm/crash.h | 75 ++++++++++++++++++++++++
|
||||
arch/x86/mm/ioremap.c | 2 +
|
||||
drivers/char/Kconfig | 2 +
|
||||
drivers/char/Kconfig | 3 +
|
||||
drivers/char/Makefile | 2 +
|
||||
drivers/char/crash.c | 128 +++++++++++++++++++++++++++++++++++++++++
|
||||
7 files changed, 302 insertions(+), 0 deletions(-)
|
||||
7 files changed, 303 insertions(+), 0 deletions(-)
|
||||
create mode 100644 arch/ia64/include/asm/crash.h
|
||||
create mode 100644 arch/x86/include/asm/crash.h
|
||||
create mode 100644 drivers/char/crash.c
|
||||
|
|
@ -208,7 +208,7 @@ index 0000000..dfcc006
|
|||
+
|
||||
+#endif /* _ASM_I386_CRASH_H */
|
||||
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
|
||||
index 5eb1ba7..3e525d2 100644
|
||||
index be1ef57..ac659f7 100644
|
||||
--- a/arch/x86/mm/ioremap.c
|
||||
+++ b/arch/x86/mm/ioremap.c
|
||||
@@ -24,6 +24,8 @@
|
||||
|
|
@ -220,6 +220,30 @@ index 5eb1ba7..3e525d2 100644
|
|||
/*
|
||||
* Fix up the linear direct mapping of the kernel to avoid cache attribute
|
||||
* conflicts.
|
||||
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
|
||||
index 423fd56..e04a561 100644
|
||||
--- a/drivers/char/Kconfig
|
||||
+++ b/drivers/char/Kconfig
|
||||
@@ -4,6 +4,9 @@
|
||||
|
||||
menu "Character devices"
|
||||
|
||||
+config CRASH
|
||||
+ tristate "Crash Utility memory driver"
|
||||
+
|
||||
source "drivers/tty/Kconfig"
|
||||
|
||||
config DEVKMEM
|
||||
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
|
||||
index 32762ba..3d5d525 100644
|
||||
--- a/drivers/char/Makefile
|
||||
+++ b/drivers/char/Makefile
|
||||
@@ -65,3 +65,5 @@ obj-$(CONFIG_JS_RTC) += js-rtc.o
|
||||
js-rtc-y = rtc.o
|
||||
|
||||
obj-$(CONFIG_TILE_SROM) += tile-srom.o
|
||||
+
|
||||
+obj-$(CONFIG_CRASH) += crash.o
|
||||
diff --git a/drivers/char/crash.c b/drivers/char/crash.c
|
||||
new file mode 100644
|
||||
index 0000000..e5437de
|
||||
|
|
@ -354,29 +378,6 @@ index 0000000..e5437de
|
|||
+module_exit(crash_cleanup_module);
|
||||
+
|
||||
+MODULE_LICENSE("GPL");
|
||||
--
|
||||
1.7.6
|
||||
|
||||
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
|
||||
index ba53ec9..6588b33 100644
|
||||
--- a/drivers/char/Makefile
|
||||
+++ b/drivers/char/Makefile
|
||||
@@ -98,3 +98,5 @@ obj-$(CONFIG_RAMOOPS) += ramoops.o
|
||||
|
||||
obj-$(CONFIG_JS_RTC) += js-rtc.o
|
||||
js-rtc-y = rtc.o
|
||||
+
|
||||
+obj-$(CONFIG_CRASH) += crash.o
|
||||
|
||||
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
|
||||
index 04f8b2d..e8fb997 100644
|
||||
--- a/drivers/char/Kconfig
|
||||
+++ b/drivers/char/Kconfig
|
||||
@@ -4,6 +4,9 @@
|
||||
|
||||
menu "Character devices"
|
||||
|
||||
+config CRASH
|
||||
+ tristate "Crash Utility memory driver"
|
||||
+
|
||||
source "drivers/tty/Kconfig"
|
||||
|
||||
config DEVKMEM
|
||||
|
|
|
|||
|
|
@ -0,0 +1,34 @@
|
|||
From 05b0c3b7b05471a6d53300cf6d7d88ee66eff7ed Mon Sep 17 00:00:00 2001
|
||||
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
|
||||
Date: Thu, 4 Aug 2011 11:10:24 -0400
|
||||
Subject: [PATCH] rcu: Prevent early boot set_need_resched() from
|
||||
__rcu_pending()
|
||||
|
||||
There isn't a whole lot of point in poking the scheduler before there
|
||||
are other tasks to switch to. This commit therefore adds a check
|
||||
for rcu_scheduler_fully_active in __rcu_pending() to suppress any
|
||||
pre-scheduler calls to set_need_resched(). The downside of this approach
|
||||
is additional runtime overhead in a reasonably hot code path.
|
||||
|
||||
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
|
||||
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
||||
---
|
||||
kernel/rcutree.c | 2 +-
|
||||
1 files changed, 1 insertions(+), 1 deletions(-)
|
||||
|
||||
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
|
||||
index ba06207..9c8a3f9 100644
|
||||
--- a/kernel/rcutree.c
|
||||
+++ b/kernel/rcutree.c
|
||||
@@ -1671,7 +1671,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
|
||||
check_cpu_stall(rsp, rdp);
|
||||
|
||||
/* Is the RCU core waiting for a quiescent state from this CPU? */
|
||||
- if (rdp->qs_pending && !rdp->passed_quiesc) {
|
||||
+ if (rcu_scheduler_fully_active && rdp->qs_pending && !rdp->passed_quiesc) {
|
||||
|
||||
/*
|
||||
* If force_quiescent_state() coming soon and this CPU
|
||||
--
|
||||
1.7.6
|
||||
|
||||
Loading…
Reference in New Issue