debian-packaging
/
linux
8
0
Fork 0
Code Releases Activity

[rt] Update to 3.12.0-rt2 and reenable 

svn path=/dists/trunk/linux/; revision=20817
This commit is contained in:
Ben Hutchings 2013-11-22 01:00:09 +00:00
parent 33e439ff0f
commit 94bed1121b
283 changed files with 32235 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
debian/changelog vendored
View File

@ -1,3 +1,10 @@
linux (3.12-1~exp2) UNRELEASED; urgency=low
[ Ben Hutchings ]
* [rt] Update to 3.12.0-rt2 and reenable
-- Ben Hutchings <ben@decadent.org.uk> Fri, 22 Nov 2013 00:41:09 +0000
linux (3.12-1~exp1) experimental; urgency=low
* New upstream release: http://kernelnewbies.org/Linux_3.12

2
debian/config/defines vendored
View File

@ -29,7 +29,7 @@ featuresets:
rt
[featureset-rt_base]
enabled: false
enabled: true
[description]
part-long-up: This kernel is not suitable for SMP (multi-processor,

130
debian/patches/features/all/rt/0002-kernel-SRCU-provide-a-static-initializer.patch vendored Normal file
View File

@ -0,0 +1,130 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 19 Mar 2013 14:44:30 +0100
Subject: [PATCH] kernel/SRCU: provide a static initializer
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
There are macros for static initializer for the three out of four
possible notifier types, that are:
ATOMIC_NOTIFIER_HEAD()
BLOCKING_NOTIFIER_HEAD()
RAW_NOTIFIER_HEAD()
This patch provides a static initilizer for the forth type to make it
complete.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/notifier.h | 34 +++++++++++++++++++++++++---------
include/linux/srcu.h | 8 ++++----
2 files changed, 29 insertions(+), 13 deletions(-)
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -6,7 +6,7 @@
*
* Alan Cox <Alan.Cox@linux.org>
*/
-
+
#ifndef _LINUX_NOTIFIER_H
#define _LINUX_NOTIFIER_H
#include <linux/errno.h>
@@ -42,9 +42,7 @@
* in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
* As compensation, srcu_notifier_chain_unregister() is rather expensive.
* SRCU notifier chains should be used when the chain will be called very
- * often but notifier_blocks will seldom be removed. Also, SRCU notifier
- * chains are slightly more difficult to use because they require special
- * runtime initialization.
+ * often but notifier_blocks will seldom be removed.
*/
typedef int (*notifier_fn_t)(struct notifier_block *nb,
@@ -88,7 +86,7 @@ struct srcu_notifier_head {
(name)->head = NULL; \
} while (0)
-/* srcu_notifier_heads must be initialized and cleaned up dynamically */
+/* srcu_notifier_heads must be cleaned up dynamically */
extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
#define srcu_cleanup_notifier_head(name) \
cleanup_srcu_struct(&(name)->srcu);
@@ -101,7 +99,13 @@ extern void srcu_init_notifier_head(stru
.head = NULL }
#define RAW_NOTIFIER_INIT(name) { \
.head = NULL }
-/* srcu_notifier_heads cannot be initialized statically */
+
+#define SRCU_NOTIFIER_INIT(name, pcpu) \
+ { \
+ .mutex = __MUTEX_INITIALIZER(name.mutex), \
+ .head = NULL, \
+ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \
+ }
#define ATOMIC_NOTIFIER_HEAD(name) \
struct atomic_notifier_head name = \
@@ -113,6 +117,18 @@ extern void srcu_init_notifier_head(stru
struct raw_notifier_head name = \
RAW_NOTIFIER_INIT(name)
+#define _SRCU_NOTIFIER_HEAD(name, mod) \
+ static DEFINE_PER_CPU(struct srcu_struct_array, \
+ name##_head_srcu_array); \
+ mod struct srcu_notifier_head name = \
+ SRCU_NOTIFIER_INIT(name, name##_head_srcu_array)
+
+#define SRCU_NOTIFIER_HEAD(name) \
+ _SRCU_NOTIFIER_HEAD(name, )
+
+#define SRCU_NOTIFIER_HEAD_STATIC(name) \
+ _SRCU_NOTIFIER_HEAD(name, static)
+
#ifdef __KERNEL__
extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
@@ -182,12 +198,12 @@ static inline int notifier_to_errno(int
/*
* Declared notifiers so far. I can imagine quite a few more chains
- * over time (eg laptop power reset chains, reboot chain (to clean
+ * over time (eg laptop power reset chains, reboot chain (to clean
* device units up), device [un]mount chain, module load/unload chain,
- * low memory chain, screenblank chain (for plug in modular screenblankers)
+ * low memory chain, screenblank chain (for plug in modular screenblankers)
* VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
*/
-
+
/* CPU notfiers are defined in include/linux/cpu.h. */
/* netdevice notifiers are defined in include/linux/netdevice.h */
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct
void process_srcu(struct work_struct *work);
-#define __SRCU_STRUCT_INIT(name) \
+#define __SRCU_STRUCT_INIT(name, pcpu_name) \
{ \
.completed = -300, \
- .per_cpu_ref = &name##_srcu_array, \
+ .per_cpu_ref = &pcpu_name, \
.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
.running = false, \
.batch_queue = RCU_BATCH_INIT(name.batch_queue), \
@@ -104,11 +104,11 @@ void process_srcu(struct work_struct *wo
*/
#define DEFINE_SRCU(name) \
static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
- struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+ struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array);
#define DEFINE_STATIC_SRCU(name) \
static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
- static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+ static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array);
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period

24
debian/patches/features/all/rt/0002-x86-highmem-add-a-already-used-pte-check.patch vendored Normal file
View File

@ -0,0 +1,24 @@
From 65513f34449eedb6b84c24a3583266534c1627e4 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 11 Mar 2013 17:09:55 +0100
Subject: [PATCH 2/6] x86/highmem: add a "already used pte" check
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
This is a copy from kmap_atomic_prot().
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
arch/x86/mm/iomap_32.c | 2 ++
1 file changed, 2 insertions(+)
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -65,6 +65,8 @@ void *kmap_atomic_prot_pfn(unsigned long
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR * smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ WARN_ON(!pte_none(*(kmap_pte - idx)));
+
#ifdef CONFIG_PREEMPT_RT_FULL
current->kmap_pte[type] = pte;
#endif

29
debian/patches/features/all/rt/0003-arm-highmem-flush-tlb-on-unmap.patch vendored Normal file
View File

@ -0,0 +1,29 @@
From e2ca4d092d9c6e6b07b465b4d81da207bbcc7437 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 11 Mar 2013 21:37:27 +0100
Subject: [PATCH 3/6] arm/highmem: flush tlb on unmap
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The tlb should be flushed on unmap and thus make the mapping entry
invalid. This is only done in the non-debug case which does not look
right.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
arch/arm/mm/highmem.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -95,10 +95,10 @@ void __kunmap_atomic(void *kvaddr)
__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
- set_top_pte(vaddr, __pte(0));
#else
(void) idx; /* to kill a warning */
#endif
+ set_top_pte(vaddr, __pte(0));
kmap_atomic_idx_pop();
} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
/* this address was obtained through kmap_high_get() */

45
debian/patches/features/all/rt/0005-futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch vendored Normal file
View File

@ -0,0 +1,45 @@
From eef09918aff670a6162d2ae5fe87b393698ef57d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 1 Mar 2013 11:17:42 +0100
Subject: [PATCH 5/6] futex: Ensure lock/unlock symetry versus pi_lock and
hash bucket lock
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
In exit_pi_state_list() we have the following locking construct:
spin_lock(&hb->lock);
raw_spin_lock_irq(&curr->pi_lock);
...
spin_unlock(&hb->lock);
In !RT this works, but on RT the migrate_enable() function which is
called from spin_unlock() sees atomic context due to the held pi_lock
and just decrements the migrate_disable_atomic counter of the
task. Now the next call to migrate_disable() sees the counter being
negative and issues a warning. That check should be in
migrate_enable() already.
Fix this by dropping pi_lock before unlocking hb->lock and reaquire
pi_lock after that again. This is safe as the loop code reevaluates
head again under the pi_lock.
Reported-by: Yong Zhang <yong.zhang@windriver.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/futex.c | 2 ++
1 file changed, 2 insertions(+)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -572,7 +572,9 @@ void exit_pi_state_list(struct task_stru
* task still owns the PI-state:
*/
if (head->next != next) {
+ raw_spin_unlock_irq(&curr->pi_lock);
spin_unlock(&hb->lock);
+ raw_spin_lock_irq(&curr->pi_lock);
continue;
}

78
debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch vendored Normal file
View File

@ -0,0 +1,78 @@
From b72b514282ffad0d665ea94932b968f388304079 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 21 Mar 2013 19:01:05 +0100
Subject: [PATCH] HACK: printk: drop the logbuf_lock more often
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The lock is hold with irgs off. The latency drops 500us+ on my arm bugs
with a "full" buffer after executing "dmesg" on the shell.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/printk/printk.c | 27 ++++++++++++++++++++++++++-
1 file changed, 26 insertions(+), 1 deletion(-)
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1029,6 +1029,7 @@ static int syslog_print_all(char __user
{
char *text;
int len = 0;
+ int attempts = 0;
text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
if (!text)
@@ -1040,7 +1041,14 @@ static int syslog_print_all(char __user
u64 seq;
u32 idx;
enum log_flags prev;
-
+ int num_msg;
+try_again:
+ attempts++;
+ if (attempts > 10) {
+ len = -EBUSY;
+ goto out;
+ }
+ num_msg = 0;
if (clear_seq < log_first_seq) {
/* messages are gone, move to first available one */
clear_seq = log_first_seq;
@@ -1061,6 +1069,14 @@ static int syslog_print_all(char __user
prev = msg->flags;
idx = log_next(idx);
seq++;
+ num_msg++;
+ if (num_msg > 5) {
+ num_msg = 0;
+ raw_spin_unlock_irq(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
+ if (clear_seq < log_first_seq)
+ goto try_again;
+ }
}
/* move first record forward until length fits into the buffer */
@@ -1074,6 +1090,14 @@ static int syslog_print_all(char __user
prev = msg->flags;
idx = log_next(idx);
seq++;
+ num_msg++;
+ if (num_msg > 5) {
+ num_msg = 0;
+ raw_spin_unlock_irq(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
+ if (clear_seq < log_first_seq)
+ goto try_again;
+ }
}
/* last message fitting into this dump */
@@ -1115,6 +1139,7 @@ static int syslog_print_all(char __user
clear_seq = log_next_seq;
clear_idx = log_next_idx;
}
+out:
raw_spin_unlock_irq(&logbuf_lock);
kfree(text);

43
debian/patches/features/all/rt/Kind-of-revert-powerpc-52xx-provide-a-default-in-mpc.patch vendored Normal file
View File

@ -0,0 +1,43 @@
From 0939f949f9c72833e5b1a718bd5b4546873b0b38 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Fri, 4 Oct 2013 17:37:09 +0200
Subject: [PATCH] Kind of revert "powerpc: 52xx: provide a default in
mpc52xx_irqhost_map()"
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
This more or less reverts commit 6391f697d4892a6f233501beea553e13f7745a23.
Instead of adding an unneeded 'default', mark the variable to prevent
the false positive 'uninitialized var'. The other change (fixing the
printout) needs revert, too. We want to know WHICH critical irq failed,
not which level it had.
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Anatolij Gustschin <agust@denx.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
arch/powerpc/platforms/52xx/mpc52xx_pic.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -340,7 +340,7 @@ static int mpc52xx_irqhost_map(struct ir
{
int l1irq;
int l2irq;
- struct irq_chip *irqchip;
+ struct irq_chip *uninitialized_var(irqchip);
void *hndlr;
int type;
u32 reg;
@@ -373,9 +373,8 @@ static int mpc52xx_irqhost_map(struct ir
case MPC52xx_IRQ_L1_PERP: irqchip = &mpc52xx_periph_irqchip; break;
case MPC52xx_IRQ_L1_SDMA: irqchip = &mpc52xx_sdma_irqchip; break;
case MPC52xx_IRQ_L1_CRIT:
- default:
pr_warn("%s: Critical IRQ #%d is unsupported! Nopping it.\n",
- __func__, l1irq);
+ __func__, l2irq);
irq_set_chip(virq, &no_irq_chip);
return 0;
}

173
debian/patches/features/all/rt/acpi-rt-Convert-acpi_gbl_hardware-lock-back-to-a-raw.patch vendored Normal file
View File

@ -0,0 +1,173 @@
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 13 Feb 2013 09:26:05 -0500
Subject: [PATCH] acpi/rt: Convert acpi_gbl_hardware lock back to a raw_spinlock_t
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
We hit the following bug with 3.6-rt:
[ 5.898990] BUG: scheduling while atomic: swapper/3/0/0x00000002
[ 5.898991] no locks held by swapper/3/0.
[ 5.898993] Modules linked in:
[ 5.898996] Pid: 0, comm: swapper/3 Not tainted 3.6.11-rt28.19.el6rt.x86_64.debug #1
[ 5.898997] Call Trace:
[ 5.899011] [<ffffffff810804e7>] __schedule_bug+0x67/0x90
[ 5.899028] [<ffffffff81577923>] __schedule+0x793/0x7a0
[ 5.899032] [<ffffffff810b4e40>] ? debug_rt_mutex_print_deadlock+0x50/0x200
[ 5.899034] [<ffffffff81577b89>] schedule+0x29/0x70
[ 5.899036] BUG: scheduling while atomic: swapper/7/0/0x00000002
[ 5.899037] no locks held by swapper/7/0.
[ 5.899039] [<ffffffff81578525>] rt_spin_lock_slowlock+0xe5/0x2f0
[ 5.899040] Modules linked in:
[ 5.899041]
[ 5.899045] [<ffffffff81579a58>] ? _raw_spin_unlock_irqrestore+0x38/0x90
[ 5.899046] Pid: 0, comm: swapper/7 Not tainted 3.6.11-rt28.19.el6rt.x86_64.debug #1
[ 5.899047] Call Trace:
[ 5.899049] [<ffffffff81578bc6>] rt_spin_lock+0x16/0x40
[ 5.899052] [<ffffffff810804e7>] __schedule_bug+0x67/0x90
[ 5.899054] [<ffffffff8157d3f0>] ? notifier_call_chain+0x80/0x80
[ 5.899056] [<ffffffff81577923>] __schedule+0x793/0x7a0
[ 5.899059] [<ffffffff812f2034>] acpi_os_acquire_lock+0x1f/0x23
[ 5.899062] [<ffffffff810b4e40>] ? debug_rt_mutex_print_deadlock+0x50/0x200
[ 5.899068] [<ffffffff8130be64>] acpi_write_bit_register+0x33/0xb0
[ 5.899071] [<ffffffff81577b89>] schedule+0x29/0x70
[ 5.899072] [<ffffffff8130be13>] ? acpi_read_bit_register+0x33/0x51
[ 5.899074] [<ffffffff81578525>] rt_spin_lock_slowlock+0xe5/0x2f0
[ 5.899077] [<ffffffff8131d1fc>] acpi_idle_enter_bm+0x8a/0x28e
[ 5.899079] [<ffffffff81579a58>] ? _raw_spin_unlock_irqrestore+0x38/0x90
[ 5.899081] [<ffffffff8107e5da>] ? this_cpu_load+0x1a/0x30
[ 5.899083] [<ffffffff81578bc6>] rt_spin_lock+0x16/0x40
[ 5.899087] [<ffffffff8144c759>] cpuidle_enter+0x19/0x20
[ 5.899088] [<ffffffff8157d3f0>] ? notifier_call_chain+0x80/0x80
[ 5.899090] [<ffffffff8144c777>] cpuidle_enter_state+0x17/0x50
[ 5.899092] [<ffffffff812f2034>] acpi_os_acquire_lock+0x1f/0x23
[ 5.899094] [<ffffffff8144d1a1>] cpuidle899101] [<ffffffff8130be13>] ?
As the acpi code disables interrupts in acpi_idle_enter_bm, and calls
code that grabs the acpi lock, it causes issues as the lock is currently
in RT a sleeping lock.
The lock was converted from a raw to a sleeping lock due to some
previous issues, and tests that showed it didn't seem to matter.
Unfortunately, it did matter for one of our boxes.
This patch converts the lock back to a raw lock. I've run this code on a
few of my own machines, one being my laptop that uses the acpi quite
extensively. I've been able to suspend and resume without issues.
[ tglx: Made the change exclusive for acpi_gbl_hardware_lock ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: John Kacur <jkacur@gmail.com>
Cc: Clark Williams <clark@redhat.com>
Link: http://lkml.kernel.org/r/1360765565.23152.5.camel@gandalf.local.home
Cc: stable-rt@vger.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/acpi/acpica/acglobal.h | 2 +-
drivers/acpi/acpica/hwregs.c | 4 ++--
drivers/acpi/acpica/hwxface.c | 4 ++--
drivers/acpi/acpica/utmutex.c | 4 ++--
include/acpi/platform/aclinux.h | 14 ++++++++++++++
5 files changed, 21 insertions(+), 7 deletions(-)
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -235,7 +235,7 @@ ACPI_EXTERN u8 acpi_gbl_global_lock_pend
* interrupt level
*/
ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock; /* For GPE data structs and registers */
-ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */
+ACPI_EXTERN acpi_raw_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */
ACPI_EXTERN acpi_spinlock acpi_gbl_reference_count_lock;
/* Mutex for _OSI support */
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -269,14 +269,14 @@ acpi_status acpi_hw_clear_acpi_status(vo
ACPI_BITMASK_ALL_FIXED_STATUS,
ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
/* Clear the fixed events in PM1 A/B */
status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
ACPI_BITMASK_ALL_FIXED_STATUS);
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
if (ACPI_FAILURE(status))
goto exit;
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -365,7 +365,7 @@ acpi_status acpi_write_bit_register(u32
return_ACPI_STATUS(AE_BAD_PARAMETER);
}
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
/*
* At this point, we know that the parent register is one of the
@@ -426,7 +426,7 @@ acpi_status acpi_write_bit_register(u32
unlock_and_exit:
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
return_ACPI_STATUS(status);
}
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(voi
return_ACPI_STATUS (status);
}
- status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock);
if (ACPI_FAILURE (status)) {
return_ACPI_STATUS (status);
}
@@ -141,7 +141,7 @@ void acpi_ut_mutex_terminate(void)
/* Delete the spinlocks */
acpi_os_delete_lock(acpi_gbl_gpe_lock);
- acpi_os_delete_lock(acpi_gbl_hardware_lock);
+ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
acpi_os_delete_lock(acpi_gbl_reference_count_lock);
/* Delete the reader/writer lock */
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -72,6 +72,7 @@
#define acpi_cache_t struct kmem_cache
#define acpi_spinlock spinlock_t *
+#define acpi_raw_spinlock raw_spinlock_t *
#define acpi_cpu_flags unsigned long
#else /* !__KERNEL__ */
@@ -174,6 +175,19 @@ static inline void *acpi_os_acquire_obje
lock ? AE_OK : AE_NO_MEMORY; \
})
+#define acpi_os_create_raw_lock(__handle) \
+({ \
+ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
+ \
+ if (lock) { \
+ *(__handle) = lock; \
+ raw_spin_lock_init(*(__handle)); \
+ } \
+ lock ? AE_OK : AE_NO_MEMORY; \
+})
+
+#define acpi_os_delete_raw_lock(__handle) kfree(__handle)
+
#endif /* __KERNEL__ */
#endif /* __ACLINUX_H__ */

287
debian/patches/features/all/rt/arch-use-pagefault-disabled.patch vendored Normal file
View File

@ -0,0 +1,287 @@
Subject: mm: Fixup all fault handlers to check current->pagefault_disable
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 17 Mar 2011 11:32:28 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Necessary for decoupling pagefault disable from preempt count.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/alpha/mm/fault.c | 2 +-
arch/arm/mm/fault.c | 2 +-
arch/avr32/mm/fault.c | 3 ++-
arch/cris/mm/fault.c | 2 +-
arch/frv/mm/fault.c | 2 +-
arch/ia64/mm/fault.c | 2 +-
arch/m32r/mm/fault.c | 2 +-
arch/m68k/mm/fault.c | 2 +-
arch/microblaze/mm/fault.c | 2 +-
arch/mips/mm/fault.c | 2 +-
arch/mn10300/mm/fault.c | 2 +-
arch/parisc/mm/fault.c | 2 +-
arch/powerpc/mm/fault.c | 2 +-
arch/s390/mm/fault.c | 6 ++++--
arch/score/mm/fault.c | 2 +-
arch/sh/mm/fault.c | 2 +-
arch/sparc/mm/fault_32.c | 2 +-
arch/sparc/mm/fault_64.c | 2 +-
arch/tile/mm/fault.c | 2 +-
arch/um/kernel/trap.c | 2 +-
arch/x86/mm/fault.c | 2 +-
arch/xtensa/mm/fault.c | 2 +-
22 files changed, 26 insertions(+), 23 deletions(-)
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -107,7 +107,7 @@ do_page_fault(unsigned long address, uns
/* If we're in an interrupt context, or have no user context,
we must not take the fault. */
- if (!mm || in_atomic())
+ if (!mm || in_atomic() || current->pagefault_disabled)
goto no_context;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -277,7 +277,7 @@ do_page_fault(unsigned long addr, unsign
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
if (user_mode(regs))
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -81,7 +81,8 @@ asmlinkage void do_page_fault(unsigned l
* If we're in an interrupt or have no user context, we must
* not take the fault...
*/
- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+ if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM) ||
+ current->pagefault_disabled)
goto no_context;
local_irq_enable();
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -113,7 +113,7 @@ do_page_fault(unsigned long address, str
* user context, we must not take the fault.
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
if (user_mode(regs))
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datamm
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
if (user_mode(__frame))
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long addres
/*
* If we're in an interrupt or have no user context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
#ifdef CONFIG_VIRTUAL_MEM_MAP
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -114,7 +114,7 @@ asmlinkage void do_page_fault(struct pt_
* If we're in an interrupt or have no user context or are running in an
* atomic region then we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled
goto bad_area_nosemaphore;
if (error_code & ACE_USERMODE)
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -85,7 +85,7 @@ int do_page_fault(struct pt_regs *regs,
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
if (user_mode(regs))
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -107,7 +107,7 @@ void do_page_fault(struct pt_regs *regs,
if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
is_write = 0;
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(in_atomic() || !mm || current->pagefault_disabled)) {
if (kernel_mode(regs))
goto bad_area_nosemaphore;
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -89,7 +89,7 @@ static void __kprobes __do_page_fault(st
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto bad_area_nosemaphore;
if (user_mode(regs))
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -177,7 +177,7 @@ void do_page_fault(struct pt_regs *regs,
int fault;
unsigned int flags;
- if (in_atomic())
+ if (in_atomic() || current->pagefault_disabled)
goto no_context;
tsk = current;
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -261,7 +261,7 @@ int __kprobes do_page_fault(struct pt_re
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
- if (in_atomic() || mm == NULL) {
+ if (in_atomic() || mm == NULL || current->pagefault_disabled) {
if (!user_mode(regs)) {
rc = SIGSEGV;
goto bail;
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -296,7 +296,8 @@ static inline int do_exception(struct pt
* user context.
*/
fault = VM_FAULT_BADCONTEXT;
- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
+ if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm ||
+ tsk->pagefault_disabled))
goto out;
address = trans_exc_code & __FAIL_ADDR_MASK;
@@ -442,7 +443,8 @@ void __kprobes do_asce_exception(struct
clear_tsk_thread_flag(current, TIF_PER_TRAP);
trans_exc_code = regs->int_parm_long;
- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
+ if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm ||
+ current->pagefault_disabled()));
goto no_context;
down_read(&mm->mmap_sem);
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -73,7 +73,7 @@ asmlinkage void do_page_fault(struct pt_
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto bad_area_nosemaphore;
if (user_mode(regs))
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -438,7 +438,7 @@ asmlinkage void __kprobes do_page_fault(
* If we're in an interrupt, have no user context or are running
* in an atomic region then we must not take the fault:
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(in_atomic() || !mm || current->pagefault_disabled)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -199,7 +199,7 @@ asmlinkage void do_sparc_fault(struct pt
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_disabled)
goto no_context;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -322,7 +322,7 @@ asmlinkage void __kprobes do_sparc64_fau
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm)
+ if (in_atomic() || !mm || current->pagefault_enabled)
goto intr_or_no_mm;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -357,7 +357,7 @@ static int handle_page_fault(struct pt_r
* If we're in an interrupt, have no user context or are running in an
* atomic region then we must not take the fault.
*/
- if (in_atomic() || !mm) {
+ if (in_atomic() || !mm || current->pagefault_disabled) {
vma = NULL; /* happy compiler */
goto bad_area_nosemaphore;
}
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -38,7 +38,7 @@ int handle_page_fault(unsigned long addr
* If the fault was during atomic operation, don't take the fault, just
* fail.
*/
- if (in_atomic())
+ if (in_atomic() || current->pagefault_disabled)
goto out_nosemaphore;
if (is_user)
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1094,7 +1094,7 @@ static void __kprobes
* If we're in an interrupt, have no user context or are running
* in an atomic region then we must not take the fault:
*/
- if (unlikely(in_atomic() || !mm)) {
+ if (unlikely(in_atomic() || !mm || current->pagefault_disabled)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs)
/* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
- if (in_atomic() || !mm) {
+ if (in_atomic() || !mm || current->pagefault_disabled) {
bad_page_fault(regs, address, SIGSEGV);
return;
}

58
debian/patches/features/all/rt/arm-at91-pit-remove-irq-handler-when-clock-is-unused.patch vendored Normal file
View File

@ -0,0 +1,58 @@
From: Benedikt Spranger <b.spranger@linutronix.de>
Date: Sat, 6 Mar 2010 17:47:10 +0100
Subject: ARM: AT91: PIT: Remove irq handler when clock event is unused
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Setup and remove the interrupt handler in clock event mode selection.
This avoids calling the (shared) interrupt handler when the device is
not used.
Signed-off-by: Benedikt Spranger <b.spranger@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bigeasy: redo the patch with NR_IRQS_LEGACY which is probabyl required since
commit 8fe82a55 ("ARM: at91: sparse irq support") which is included since v3.6.
Patch based on what Sami Pietikäinen <Sami.Pietikainen@wapice.com> suggested].
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
arch/arm/mach-at91/at91rm9200_time.c | 1 +
arch/arm/mach-at91/at91sam926x_time.c | 5 ++++-
2 files changed, 5 insertions(+), 1 deletion(-)
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -134,6 +134,7 @@ clkevt32k_mode(enum clock_event_mode mod
break;
case CLOCK_EVT_MODE_SHUTDOWN:
case CLOCK_EVT_MODE_UNUSED:
+ remove_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq);
case CLOCK_EVT_MODE_RESUME:
irqmask = 0;
break;
--- a/arch/arm/mach-at91/at91sam926x_time.c
+++ b/arch/arm/mach-at91/at91sam926x_time.c
@@ -77,7 +77,7 @@ static struct clocksource pit_clk = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-
+static struct irqaction at91sam926x_pit_irq;
/*
* Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16)
*/
@@ -86,6 +86,8 @@ pit_clkevt_mode(enum clock_event_mode mo
{
switch (mode) {
case CLOCK_EVT_MODE_PERIODIC:
+ /* Set up irq handler */
+ setup_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq);
/* update clocksource counter */
pit_cnt += pit_cycle * PIT_PICNT(pit_read(AT91_PIT_PIVR));
pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN
@@ -98,6 +100,7 @@ pit_clkevt_mode(enum clock_event_mode mo
case CLOCK_EVT_MODE_UNUSED:
/* disable irq, leaving the clocksource active */
pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN);
+ remove_irq(at91sam926x_pit_irq.irq, &at91sam926x_pit_irq);
break;
case CLOCK_EVT_MODE_RESUME:
break;

33
debian/patches/features/all/rt/arm-at91-tclib-default-to-tclib-timer-for-rt.patch vendored Normal file
View File

@ -0,0 +1,33 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 1 May 2010 18:29:35 +0200
Subject: ARM: at91: tclib: Default to tclib timer for RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
RT is not too happy about the shared timer interrupt in AT91
devices. Default to tclib timer for RT.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/misc/Kconfig | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -63,6 +63,7 @@ config ATMEL_PWM
config ATMEL_TCLIB
bool "Atmel AT32/AT91 Timer/Counter Library"
depends on (AVR32 || ARCH_AT91)
+ default y if PREEMPT_RT_FULL
help
Select this if you want a library to allocate the Timer/Counter
blocks found on many Atmel processors. This facilitates using
@@ -95,7 +96,7 @@ config ATMEL_TCB_CLKSRC_BLOCK
config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
bool "TC Block use 32 KiHz clock"
depends on ATMEL_TCB_CLKSRC
- default y
+ default y if !PREEMPT_RT_FULL
help
Select this to use 32 KiHz base clock rate as TC block clock
source for clock events.

320
debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch vendored Normal file
View File

@ -0,0 +1,320 @@
From: Frank Rowand <frank.rowand@am.sony.com>
Date: Mon, 19 Sep 2011 14:51:14 -0700
Subject: [PATCH] preempt-rt: Convert arm boot_lock to raw
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The arm boot_lock is used by the secondary processor startup code. The locking
task is the idle thread, which has idle->sched_class == &idle_sched_class.
idle_sched_class->enqueue_task == NULL, so if the idle task blocks on the
lock, the attempt to wake it when the lock becomes available will fail:
try_to_wake_up()
...
activate_task()
enqueue_task()
p->sched_class->enqueue_task(rq, p, flags)
Fix by converting boot_lock to a raw spin lock.
Signed-off-by: Frank Rowand <frank.rowand@am.sony.com>
Link: http://lkml.kernel.org/r/4E77B952.3010606@am.sony.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/arm/mach-exynos/platsmp.c | 12 ++++++------
arch/arm/mach-msm/platsmp.c | 10 +++++-----
arch/arm/mach-omap2/omap-smp.c | 10 +++++-----
arch/arm/mach-prima2/platsmp.c | 10 +++++-----
arch/arm/mach-spear/platsmp.c | 10 +++++-----
arch/arm/mach-ux500/platsmp.c | 10 +++++-----
arch/arm/plat-versatile/platsmp.c | 10 +++++-----
7 files changed, 36 insertions(+), 36 deletions(-)
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -73,7 +73,7 @@ static void __iomem *scu_base_addr(void)
return (void __iomem *)(S5P_VA_SCU);
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void exynos_secondary_init(unsigned int cpu)
{
@@ -86,8 +86,8 @@ static void exynos_secondary_init(unsign
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -99,7 +99,7 @@ static int exynos_boot_secondary(unsigne
* Set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
@@ -128,7 +128,7 @@ static int exynos_boot_secondary(unsigne
if (timeout == 0) {
printk(KERN_ERR "cpu1 power enable failed");
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return -ETIMEDOUT;
}
}
@@ -167,7 +167,7 @@ static int exynos_boot_secondary(unsigne
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -30,7 +30,7 @@
extern void msm_secondary_startup(void);
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static inline int get_core_count(void)
{
@@ -50,8 +50,8 @@ static void msm_secondary_init(unsigned
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static void prepare_cold_cpu(unsigned int cpu)
@@ -88,7 +88,7 @@ static int msm_boot_secondary(unsigned i
* set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
@@ -122,7 +122,7 @@ static int msm_boot_secondary(unsigned i
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -44,7 +44,7 @@ u16 pm44xx_errata;
/* SCU base address */
static void __iomem *scu_base;
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
void __iomem *omap4_get_scu_base(void)
{
@@ -68,8 +68,8 @@ static void omap4_secondary_init(unsigne
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -83,7 +83,7 @@ static int omap4_boot_secondary(unsigned
* Set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* Update the AuxCoreBoot0 with boot state for secondary core.
@@ -160,7 +160,7 @@ static int omap4_boot_secondary(unsigned
* Now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return 0;
}
--- a/arch/arm/mach-prima2/platsmp.c
+++ b/arch/arm/mach-prima2/platsmp.c
@@ -23,7 +23,7 @@
static void __iomem *scu_base;
static void __iomem *rsc_base;
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static struct map_desc scu_io_desc __initdata = {
.length = SZ_4K,
@@ -56,8 +56,8 @@ static void sirfsoc_secondary_init(unsig
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static struct of_device_id rsc_ids[] = {
@@ -95,7 +95,7 @@ static int sirfsoc_boot_secondary(unsign
/* make sure write buffer is drained */
mb();
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
@@ -128,7 +128,7 @@ static int sirfsoc_boot_secondary(unsign
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -20,7 +20,7 @@
#include <mach/spear.h>
#include "generic.h"
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
@@ -36,8 +36,8 @@ static void spear13xx_secondary_init(uns
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -48,7 +48,7 @@ static int spear13xx_boot_secondary(unsi
* set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
@@ -75,7 +75,7 @@ static int spear13xx_boot_secondary(unsi
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -52,7 +52,7 @@ static void __iomem *scu_base_addr(void)
return NULL;
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void ux500_secondary_init(unsigned int cpu)
{
@@ -65,8 +65,8 @@ static void ux500_secondary_init(unsigne
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
static int ux500_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -77,7 +77,7 @@ static int ux500_boot_secondary(unsigned
* set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
@@ -98,7 +98,7 @@ static int ux500_boot_secondary(unsigned
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -31,7 +31,7 @@ static void write_pen_release(int val)
outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
void versatile_secondary_init(unsigned int cpu)
{
@@ -44,8 +44,8 @@ void versatile_secondary_init(unsigned i
/*
* Synchronise with the boot thread.
*/
- spin_lock(&boot_lock);
- spin_unlock(&boot_lock);
+ raw_spin_lock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
}
int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -56,7 +56,7 @@ int versatile_boot_secondary(unsigned in
* Set synchronisation state between this boot processor
* and the secondary one
*/
- spin_lock(&boot_lock);
+ raw_spin_lock(&boot_lock);
/*
* This is really belt and braces; we hold unintended secondary
@@ -86,7 +86,7 @@ int versatile_boot_secondary(unsigned in
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}

21
debian/patches/features/all/rt/arm-disable-highmem-on-rt.patch vendored Normal file
View File

@ -0,0 +1,21 @@
Subject: arm-disable-highmem-on-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 18 Jul 2011 17:09:28 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/arm/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1759,7 +1759,7 @@ config HAVE_ARCH_PFN_VALID
config HIGHMEM
bool "High Memory Support"
- depends on MMU
+ depends on MMU && !PREEMPT_RT_FULL
help
The address space of ARM processors is only 4 Gigabytes large
and it has to accommodate user address space, kernel address

140
debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch vendored Normal file
View File

@ -0,0 +1,140 @@
Subject: arm-enable-highmem-for-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 13 Feb 2013 11:03:11 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/arm/Kconfig | 2 -
arch/arm/include/asm/switch_to.h | 8 +++++++
arch/arm/mm/highmem.c | 41 +++++++++++++++++++++++++++++++++++++--
include/linux/highmem.h | 1
4 files changed, 49 insertions(+), 3 deletions(-)
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1759,7 +1759,7 @@ config HAVE_ARCH_PFN_VALID
config HIGHMEM
bool "High Memory Support"
- depends on MMU && !PREEMPT_RT_FULL
+ depends on MMU
help
The address space of ARM processors is only 4 Gigabytes large
and it has to accommodate user address space, kernel address
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -3,6 +3,13 @@
#include <linux/thread_info.h>
+#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p);
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
/*
* For v7 SMP cores running a preemptible kernel we may be pre-empted
* during a TLB maintenance operation, so execute an inner-shareable dsb
@@ -22,6 +29,7 @@ extern struct task_struct *__switch_to(s
#define switch_to(prev,next,last) \
do { \
+ switch_kmaps(prev, next); \
last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \
} while (0)
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -38,6 +38,7 @@ EXPORT_SYMBOL(kunmap);
void *kmap_atomic(struct page *page)
{
+ pte_t pte = mk_pte(page, kmap_prot);
unsigned int idx;
unsigned long vaddr;
void *kmap;
@@ -76,7 +77,10 @@ void *kmap_atomic(struct page *page)
* in place, so the contained TLB flush ensures the TLB is updated
* with the new mapping.
*/
- set_top_pte(vaddr, mk_pte(page, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+ current->kmap_pte[type] = pte;
+#endif
+ set_top_pte(vaddr, pte);
return (void *)vaddr;
}
@@ -93,6 +97,9 @@ void __kunmap_atomic(void *kvaddr)
if (cache_is_vivt())
__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
+#ifdef CONFIG_PREEMPT_RT_FULL
+ current->kmap_pte[type] = __pte(0);
+#endif
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
#else
@@ -110,6 +117,7 @@ EXPORT_SYMBOL(__kunmap_atomic);
void *kmap_atomic_pfn(unsigned long pfn)
{
+ pte_t pte = pfn_pte(pfn, kmap_prot);
unsigned long vaddr;
int idx, type;
@@ -121,7 +129,10 @@ void *kmap_atomic_pfn(unsigned long pfn)
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(!pte_none(get_top_pte(vaddr)));
#endif
- set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+ current->kmap_pte[type] = pte;
+#endif
+ set_top_pte(vaddr, pte);
return (void *)vaddr;
}
@@ -135,3 +146,29 @@ struct page *kmap_atomic_to_page(const v
return pte_page(get_top_pte(vaddr));
}
+
+#if defined CONFIG_PREEMPT_RT_FULL
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+ int i;
+
+ /*
+ * Clear @prev's kmap_atomic mappings
+ */
+ for (i = 0; i < prev_p->kmap_idx; i++) {
+ int idx = i + KM_TYPE_NR * smp_processor_id();
+
+ set_top_pte(__fix_to_virt(FIX_KMAP_BEGIN + idx), __pte(0));
+ }
+ /*
+ * Restore @next_p's kmap_atomic mappings
+ */
+ for (i = 0; i < next_p->kmap_idx; i++) {
+ int idx = i + KM_TYPE_NR * smp_processor_id();
+
+ if (!pte_none(next_p->kmap_pte[i]))
+ set_top_pte(__fix_to_virt(FIX_KMAP_BEGIN + idx),
+ next_p->kmap_pte[i]);
+ }
+}
+#endif
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -7,6 +7,7 @@
#include <linux/mm.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
+#include <linux/sched.h>
#include <asm/cacheflush.h>

104
debian/patches/features/all/rt/arm-preempt-lazy-support.patch vendored Normal file
View File

@ -0,0 +1,104 @@
Subject: arm-preempt-lazy-support.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 31 Oct 2012 12:04:11 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/arm/Kconfig | 1 +
arch/arm/include/asm/thread_info.h | 3 +++
arch/arm/kernel/asm-offsets.c | 1 +
arch/arm/kernel/entry-armv.S | 13 +++++++++++--
arch/arm/kernel/signal.c | 3 ++-
5 files changed, 18 insertions(+), 3 deletions(-)
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -51,6 +51,7 @@ config ARM
select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
select HAVE_PERF_EVENTS
+ select HAVE_PREEMPT_LAZY
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UID16
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -60,6 +60,7 @@ struct arm_restart_block {
struct thread_info {
unsigned long flags; /* low level flags */
int preempt_count; /* 0 => preemptable, <0 => bug */
+ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */
mm_segment_t addr_limit; /* address limit */
struct task_struct *task; /* main task structure */
struct exec_domain *exec_domain; /* execution domain */
@@ -159,6 +160,7 @@ extern int vfp_restore_user_hwstate(stru
#define TIF_SIGPENDING 0
#define TIF_NEED_RESCHED 1
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
+#define TIF_NEED_RESCHED_LAZY 3
#define TIF_SYSCALL_TRACE 8
#define TIF_SYSCALL_AUDIT 9
#define TIF_SYSCALL_TRACEPOINT 10
@@ -171,6 +173,7 @@ extern int vfp_restore_user_hwstate(stru
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -54,6 +54,7 @@ int main(void)
BLANK();
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
+ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count));
DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit));
DEFINE(TI_TASK, offsetof(struct thread_info, task));
DEFINE(TI_EXEC_DOMAIN, offsetof(struct thread_info, exec_domain));
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -204,11 +204,18 @@ ENDPROC(__dabt_svc)
#ifdef CONFIG_PREEMPT
get_thread_info tsk
ldr r8, [tsk, #TI_PREEMPT] @ get preempt count
- ldr r0, [tsk, #TI_FLAGS] @ get flags
teq r8, #0 @ if preempt count != 0
+ bne 1f @ return from exeption
+ ldr r0, [tsk, #TI_FLAGS] @ get flags
+ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set
+ blne svc_preempt @ preempt!
+
+ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count
+ teq r8, #0 @ if preempt lazy count != 0
movne r0, #0 @ force flags to 0
- tst r0, #_TIF_NEED_RESCHED
+ tst r0, #_TIF_NEED_RESCHED_LAZY
blne svc_preempt
+1:
#endif
svc_exit r5, irq = 1 @ return from exception
@@ -223,6 +230,8 @@ ENDPROC(__irq_svc)
1: bl preempt_schedule_irq @ irq en/disable is done inside
ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS
tst r0, #_TIF_NEED_RESCHED
+ bne 1b
+ tst r0, #_TIF_NEED_RESCHED_LAZY
moveq pc, r8 @ go again
b 1b
#endif
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -589,7 +589,8 @@ asmlinkage int
do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
{
do {
- if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+ if (likely(thread_flags & (_TIF_NEED_RESCHED |
+ _TIF_NEED_RESCHED_LAZY))) {
schedule();
} else {
if (unlikely(!user_mode(regs)))

65
debian/patches/features/all/rt/ata-disable-interrupts-if-non-rt.patch vendored Normal file
View File

@ -0,0 +1,65 @@
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 3 Jul 2009 08:44:29 -0500
Subject: ata: Do not disable interrupts in ide code for preempt-rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Use the local_irq_*_nort variants.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/ata/libata-sff.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(str
unsigned long flags;
unsigned int consumed;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
consumed = ata_sff_data_xfer32(dev, buf, buflen, rw);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
return consumed;
}
@@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_qu
unsigned long flags;
/* FIXME: use a bounce buffer */
- local_irq_save(flags);
+ local_irq_save_nort(flags);
buf = kmap_atomic(page);
/* do the actual data transfer */
@@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_qu
do_write);
kunmap_atomic(buf);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
} else {
buf = page_address(page);
ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size,
@@ -864,7 +864,7 @@ static int __atapi_pio_bytes(struct ata_
unsigned long flags;
/* FIXME: use bounce buffer */
- local_irq_save(flags);
+ local_irq_save_nort(flags);
buf = kmap_atomic(page);
/* do the actual data transfer */
@@ -872,7 +872,7 @@ static int __atapi_pio_bytes(struct ata_
count, rw);
kunmap_atomic(buf);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
} else {
buf = page_address(page);
consumed = ap->ops->sff_data_xfer(dev, buf + offset,

98
debian/patches/features/all/rt/block-shorten-interrupt-disabled-regions.patch vendored Normal file
View File

@ -0,0 +1,98 @@
Subject: block: Shorten interrupt disabled regions
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Jun 2011 19:47:02 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Moving the blk_sched_flush_plug() call out of the interrupt/preempt
disabled region in the scheduler allows us to replace
local_irq_save/restore(flags) by local_irq_disable/enable() in
blk_flush_plug().
Now instead of doing this we disable interrupts explicitely when we
lock the request_queue and reenable them when we drop the lock. That
allows interrupts to be handled when the plug list contains requests
for more than one queue.
Aside of that this change makes the scope of the irq disabled region
more obvious. The current code confused the hell out of me when
looking at:
local_irq_save(flags);
spin_lock(q->queue_lock);
...
queue_unplugged(q...);
scsi_request_fn();
spin_unlock(q->queue_lock);
spin_lock(shost->host_lock);
spin_unlock_irq(shost->host_lock);
-------------------^^^ ????
spin_lock_irq(q->queue_lock);
spin_unlock(q->lock);
local_irq_restore(flags);
Also add a comment to __blk_run_queue() documenting that
q->request_fn() can drop q->queue_lock and reenable interrupts, but
must return with q->queue_lock held and interrupts disabled.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20110622174919.025446432@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
block/blk-core.c | 12 ++----------
1 file changed, 2 insertions(+), 10 deletions(-)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2914,7 +2914,7 @@ static void queue_unplugged(struct reque
blk_run_queue_async(q);
else
__blk_run_queue(q);
- spin_unlock(q->queue_lock);
+ spin_unlock_irq(q->queue_lock);
}
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -2962,7 +2962,6 @@ EXPORT_SYMBOL(blk_check_plugged);
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request_queue *q;
- unsigned long flags;
struct request *rq;
LIST_HEAD(list);
unsigned int depth;
@@ -2980,11 +2979,6 @@ void blk_flush_plug_list(struct blk_plug
q = NULL;
depth = 0;
- /*
- * Save and disable interrupts here, to avoid doing it for every
- * queue lock we have to take.
- */
- local_irq_save(flags);
while (!list_empty(&list)) {
rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
@@ -2997,7 +2991,7 @@ void blk_flush_plug_list(struct blk_plug
queue_unplugged(q, depth, from_schedule);
q = rq->q;
depth = 0;
- spin_lock(q->queue_lock);
+ spin_lock_irq(q->queue_lock);
}
/*
@@ -3024,8 +3018,6 @@ void blk_flush_plug_list(struct blk_plug
*/
if (q)
queue_unplugged(q, depth, from_schedule);
-
- local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)

46
debian/patches/features/all/rt/block-use-cpu-chill.patch vendored Normal file
View File

@ -0,0 +1,46 @@
Subject: block: Use cpu_chill() for retry loops
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 20 Dec 2012 18:28:26 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Retry loops on RT might loop forever when the modifying side was
preempted. Steven also observed a live lock when there was a
concurrent priority boosting going on.
Use cpu_chill() instead of cpu_relax() to let the system
make progress.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
block/blk-ioc.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -8,6 +8,7 @@
#include <linux/blkdev.h>
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
#include <linux/slab.h>
+#include <linux/delay.h>
#include "blk.h"
@@ -110,7 +111,7 @@ static void ioc_release_fn(struct work_s
spin_unlock(q->queue_lock);
} else {
spin_unlock_irqrestore(&ioc->lock, flags);
- cpu_relax();
+ cpu_chill();
spin_lock_irqsave_nested(&ioc->lock, flags, 1);
}
}
@@ -188,7 +189,7 @@ void put_io_context_active(struct io_con
spin_unlock(icq->q->queue_lock);
} else {
spin_unlock_irqrestore(&ioc->lock, flags);
- cpu_relax();
+ cpu_chill();
goto retry;
}
}

35
debian/patches/features/all/rt/bug-rt-dependend-variants.patch vendored Normal file
View File

@ -0,0 +1,35 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:58 -0500
Subject: bug: BUG_ON/WARN_ON variants dependend on RT/!RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/asm-generic/bug.h | 14 ++++++++++++++
1 file changed, 14 insertions(+)
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -202,6 +202,20 @@ extern void warn_slowpath_null(const cha
# define WARN_ON_SMP(x) ({0;})
#endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define BUG_ON_RT(c) BUG_ON(c)
+# define BUG_ON_NONRT(c) do { } while (0)
+# define WARN_ON_RT(condition) WARN_ON(condition)
+# define WARN_ON_NONRT(condition) do { } while (0)
+# define WARN_ON_ONCE_NONRT(condition) do { } while (0)
+#else
+# define BUG_ON_RT(c) do { } while (0)
+# define BUG_ON_NONRT(c) BUG_ON(c)
+# define WARN_ON_RT(condition) do { } while (0)
+# define WARN_ON_NONRT(condition) WARN_ON(condition)
+# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition)
+#endif
+
#endif /* __ASSEMBLY__ */
#endif

153
debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch vendored Normal file
View File

@ -0,0 +1,153 @@
From: Benedikt Spranger <b.spranger@linutronix.de>
Date: Mon, 8 Mar 2010 18:57:04 +0100
Subject: clocksource: TCLIB: Allow higher clock rates for clock events
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
As default the TCLIB uses the 32KiHz base clock rate for clock events.
Add a compile time selection to allow higher clock resulution.
Signed-off-by: Benedikt Spranger <b.spranger@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/clocksource/tcb_clksrc.c | 35 +++++++++++++++++++++--------------
drivers/misc/Kconfig | 12 ++++++++++--
2 files changed, 31 insertions(+), 16 deletions(-)
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -23,8 +23,7 @@
* this 32 bit free-running counter. the second channel is not used.
*
* - The third channel may be used to provide a 16-bit clockevent
- * source, used in either periodic or oneshot mode. This runs
- * at 32 KiHZ, and can handle delays of up to two seconds.
+ * source, used in either periodic or oneshot mode.
*
* A boot clocksource and clockevent source are also currently needed,
* unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
@@ -74,6 +73,7 @@ static struct clocksource clksrc = {
struct tc_clkevt_device {
struct clock_event_device clkevt;
struct clk *clk;
+ u32 freq;
void __iomem *regs;
};
@@ -82,13 +82,6 @@ static struct tc_clkevt_device *to_tc_cl
return container_of(clkevt, struct tc_clkevt_device, clkevt);
}
-/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
- * because using one of the divided clocks would usually mean the
- * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
- *
- * A divided clock could be good for high resolution timers, since
- * 30.5 usec resolution can seem "low".
- */
static u32 timer_clock;
static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
@@ -111,11 +104,12 @@ static void tc_mode(enum clock_event_mod
case CLOCK_EVT_MODE_PERIODIC:
clk_enable(tcd->clk);
- /* slow clock, count up to RC, then irq and restart */
+ /* count up to RC, then irq and restart */
__raw_writel(timer_clock
| ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
regs + ATMEL_TC_REG(2, CMR));
- __raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+ __raw_writel((tcd->freq + HZ/2)/HZ,
+ tcaddr + ATMEL_TC_REG(2, RC));
/* Enable clock and interrupts on RC compare */
__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -128,7 +122,7 @@ static void tc_mode(enum clock_event_mod
case CLOCK_EVT_MODE_ONESHOT:
clk_enable(tcd->clk);
- /* slow clock, count up to RC, then irq and stop */
+ /* count up to RC, then irq and stop */
__raw_writel(timer_clock | ATMEL_TC_CPCSTOP
| ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
regs + ATMEL_TC_REG(2, CMR));
@@ -157,8 +151,12 @@ static struct tc_clkevt_device clkevt =
.name = "tc_clkevt",
.features = CLOCK_EVT_FEAT_PERIODIC
| CLOCK_EVT_FEAT_ONESHOT,
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
/* Should be lower than at91rm9200's system timer */
.rating = 125,
+#else
+ .rating = 200,
+#endif
.set_next_event = tc_next_event,
.set_mode = tc_mode,
},
@@ -186,6 +184,8 @@ static struct irqaction tc_irqaction = {
static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
{
+ unsigned divisor = atmel_tc_divisors[clk32k_divisor_idx];
+ u32 freq;
struct clk *t2_clk = tc->clk[2];
int irq = tc->irq[2];
@@ -194,10 +194,14 @@ static void __init setup_clkevents(struc
tc_irqaction.dev_id = &clkevt;
timer_clock = clk32k_divisor_idx;
+ if (!divisor)
+ freq = 32768;
+ else
+ freq = clk_get_rate(t2_clk) / divisor;
clkevt.clkevt.cpumask = cpumask_of(0);
- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff);
+ clockevents_config_and_register(&clkevt.clkevt, freq, 1, 0xffff);
setup_irq(irq, &tc_irqaction);
}
@@ -322,8 +326,11 @@ static int __init tcb_clksrc_init(void)
clocksource_register_hz(&clksrc, divided_rate);
/* channel 2: periodic and oneshot timer support */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
setup_clkevents(tc, clk32k_divisor_idx);
-
+#else
+ setup_clkevents(tc, best_divisor_idx);
+#endif
return 0;
}
arch_initcall(tcb_clksrc_init);
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -78,8 +78,7 @@ config ATMEL_TCB_CLKSRC
are combined to make a single 32-bit timer.
When GENERIC_CLOCKEVENTS is defined, the third timer channel
- may be used as a clock event device supporting oneshot mode
- (delays of up to two seconds) based on the 32 KiHz clock.
+ may be used as a clock event device supporting oneshot mode.
config ATMEL_TCB_CLKSRC_BLOCK
int
@@ -93,6 +92,15 @@ config ATMEL_TCB_CLKSRC_BLOCK
TC can be used for other purposes, such as PWM generation and
interval timing.
+config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+ bool "TC Block use 32 KiHz clock"
+ depends on ATMEL_TCB_CLKSRC
+ default y
+ help
+ Select this to use 32 KiHz base clock rate as TC block clock
+ source for clock events.
+
+
config DUMMY_IRQ
tristate "Dummy IRQ handler"
default n

180
debian/patches/features/all/rt/completion-use-simple-wait-queues.patch vendored Normal file
View File

@ -0,0 +1,180 @@
Subject: completion: Use simple wait queues
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 11 Jan 2013 11:23:51 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Completions have no long lasting callbacks and therefor do not need
the complex waitqueue variant. Use simple waitqueues which reduces the
contention on the waitqueue lock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/completion.h | 8 ++++----
include/linux/uprobes.h | 1 +
kernel/sched/core.c | 44 +++++++++++++++++++++++++-------------------
3 files changed, 30 insertions(+), 23 deletions(-)
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -8,7 +8,7 @@
* See kernel/sched/core.c for details.
*/
-#include <linux/wait.h>
+#include <linux/wait-simple.h>
/*
* struct completion - structure used to maintain state for a "completion"
@@ -24,11 +24,11 @@
*/
struct completion {
unsigned int done;
- wait_queue_head_t wait;
+ struct swait_head wait;
};
#define COMPLETION_INITIALIZER(work) \
- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+ { 0, SWAIT_HEAD_INITIALIZER((work).wait) }
#define COMPLETION_INITIALIZER_ONSTACK(work) \
({ init_completion(&work); work; })
@@ -73,7 +73,7 @@ struct completion {
static inline void init_completion(struct completion *x)
{
x->done = 0;
- init_waitqueue_head(&x->wait);
+ init_swait_head(&x->wait);
}
extern void wait_for_completion(struct completion *);
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -26,6 +26,7 @@
#include <linux/errno.h>
#include <linux/rbtree.h>
+#include <linux/wait.h>
struct vm_area_struct;
struct mm_struct;
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2412,7 +2412,10 @@ void migrate_disable(void)
}
#ifdef CONFIG_SCHED_DEBUG
- WARN_ON_ONCE(p->migrate_disable_atomic);
+ if (unlikely(p->migrate_disable_atomic)) {
+ tracing_off();
+ WARN_ON_ONCE(1);
+ }
#endif
preempt_disable();
@@ -2444,7 +2447,10 @@ void migrate_enable(void)
}
#ifdef CONFIG_SCHED_DEBUG
- WARN_ON_ONCE(p->migrate_disable_atomic);
+ if (unlikely(p->migrate_disable_atomic)) {
+ tracing_off();
+ WARN_ON_ONCE(1);
+ }
#endif
WARN_ON_ONCE(p->migrate_disable <= 0);
@@ -2903,10 +2909,10 @@ void complete(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
x->done++;
- __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ __swait_wake_locked(&x->wait, TASK_NORMAL, 1);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);
@@ -2923,10 +2929,10 @@ void complete_all(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
x->done += UINT_MAX/2;
- __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ __swait_wake_locked(&x->wait, TASK_NORMAL, 0);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);
@@ -2935,20 +2941,20 @@ do_wait_for_common(struct completion *x,
long (*action)(long), long timeout, int state)
{
if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
+ DEFINE_SWAITER(wait);
- __add_wait_queue_tail_exclusive(&x->wait, &wait);
+ swait_prepare_locked(&x->wait, &wait);
do {
if (signal_pending_state(state, current)) {
timeout = -ERESTARTSYS;
break;
}
__set_current_state(state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
timeout = action(timeout);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
} while (!x->done && timeout);
- __remove_wait_queue(&x->wait, &wait);
+ swait_finish_locked(&x->wait, &wait);
if (!x->done)
return timeout;
}
@@ -2962,9 +2968,9 @@ static inline long __sched
{
might_sleep();
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
timeout = do_wait_for_common(x, action, timeout, state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
return timeout;
}
@@ -3140,12 +3146,12 @@ bool try_wait_for_completion(struct comp
unsigned long flags;
int ret = 1;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = 0;
else
x->done--;
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);
@@ -3163,10 +3169,10 @@ bool completion_done(struct completion *
unsigned long flags;
int ret = 1;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = 0;
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
}
EXPORT_SYMBOL(completion_done);

21
debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch vendored Normal file
View File

@ -0,0 +1,21 @@
Subject: cond-resched-lock-rt-tweak.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 17 Jul 2011 22:51:33 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/sched.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2482,7 +2482,7 @@ extern int _cond_resched(void);
extern int __cond_resched_lock(spinlock_t *lock);
-#ifdef CONFIG_PREEMPT_COUNT
+#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL)
#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
#else
#define PREEMPT_LOCK_OFFSET 0

48
debian/patches/features/all/rt/cond-resched-softirq-rt.patch vendored Normal file
View File

@ -0,0 +1,48 @@
Subject: cond-resched-softirq-fix.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 14 Jul 2011 09:56:44 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/sched.h | 4 ++++
kernel/sched/core.c | 2 ++
2 files changed, 6 insertions(+)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2493,12 +2493,16 @@ extern int __cond_resched_lock(spinlock_
__cond_resched_lock(lock); \
})
+#ifndef CONFIG_PREEMPT_RT_FULL
extern int __cond_resched_softirq(void);
#define cond_resched_softirq() ({ \
__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
__cond_resched_softirq(); \
})
+#else
+# define cond_resched_softirq() cond_resched()
+#endif
static inline void cond_resched_rcu(void)
{
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3941,6 +3941,7 @@ int __cond_resched_lock(spinlock_t *lock
}
EXPORT_SYMBOL(__cond_resched_lock);
+#ifndef CONFIG_PREEMPT_RT_FULL
int __sched __cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
@@ -3954,6 +3955,7 @@ int __sched __cond_resched_softirq(void)
return 0;
}
EXPORT_SYMBOL(__cond_resched_softirq);
+#endif
/**
* yield - yield the current processor to other threads.

126
debian/patches/features/all/rt/cpu-rt-make-hotplug-lock-a-sleeping-spinlock-on-rt.patch vendored Normal file
View File

@ -0,0 +1,126 @@
Subject: cpu: Make hotplug.lock a "sleeping" spinlock on RT
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 02 Mar 2012 10:36:57 -0500
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Tasks can block on hotplug.lock in pin_current_cpu(), but their state
might be != RUNNING. So the mutex wakeup will set the state
unconditionally to RUNNING. That might cause spurious unexpected
wakeups. We could provide a state preserving mutex_lock() function,
but this is semantically backwards. So instead we convert the
hotplug.lock() to a spinlock for RT, which has the state preserving
semantics already.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Carsten Emde <C.Emde@osadl.org>
Cc: John Kacur <jkacur@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Clark Williams <clark.williams@gmail.com>
Cc: stable-rt@vger.kernel.org
Link: http://lkml.kernel.org/r/1330702617.25686.265.camel@gandalf.stny.rr.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/cpu.c | 35 ++++++++++++++++++++++++++---------
1 file changed, 26 insertions(+), 9 deletions(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -51,7 +51,12 @@ static int cpu_hotplug_disabled;
static struct {
struct task_struct *active_writer;
+#ifdef CONFIG_PREEMPT_RT_FULL
+ /* Makes the lock keep the task's state */
+ spinlock_t lock;
+#else
struct mutex lock; /* Synchronizes accesses to refcount, */
+#endif
/*
* Also blocks the new readers during
* an ongoing cpu hotplug operation.
@@ -59,10 +64,22 @@ static struct {
int refcount;
} cpu_hotplug = {
.active_writer = NULL,
+#ifdef CONFIG_PREEMPT_RT_FULL
+ .lock = __SPIN_LOCK_UNLOCKED(cpu_hotplug.lock),
+#else
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
+#endif
.refcount = 0,
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define hotplug_lock() rt_spin_lock(&cpu_hotplug.lock)
+# define hotplug_unlock() rt_spin_unlock(&cpu_hotplug.lock)
+#else
+# define hotplug_lock() mutex_lock(&cpu_hotplug.lock)
+# define hotplug_unlock() mutex_unlock(&cpu_hotplug.lock)
+#endif
+
struct hotplug_pcp {
struct task_struct *unplug;
int refcount;
@@ -92,8 +109,8 @@ void pin_current_cpu(void)
return;
}
preempt_enable();
- mutex_lock(&cpu_hotplug.lock);
- mutex_unlock(&cpu_hotplug.lock);
+ hotplug_lock();
+ hotplug_unlock();
preempt_disable();
goto retry;
}
@@ -165,9 +182,9 @@ void get_online_cpus(void)
might_sleep();
if (cpu_hotplug.active_writer == current)
return;
- mutex_lock(&cpu_hotplug.lock);
+ hotplug_lock();
cpu_hotplug.refcount++;
- mutex_unlock(&cpu_hotplug.lock);
+ hotplug_unlock();
}
EXPORT_SYMBOL_GPL(get_online_cpus);
@@ -176,14 +193,14 @@ void put_online_cpus(void)
{
if (cpu_hotplug.active_writer == current)
return;
- mutex_lock(&cpu_hotplug.lock);
+ hotplug_lock();
if (WARN_ON(!cpu_hotplug.refcount))
cpu_hotplug.refcount++; /* try to fix things up */
if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
wake_up_process(cpu_hotplug.active_writer);
- mutex_unlock(&cpu_hotplug.lock);
+ hotplug_unlock();
}
EXPORT_SYMBOL_GPL(put_online_cpus);
@@ -215,11 +232,11 @@ void cpu_hotplug_begin(void)
cpu_hotplug.active_writer = current;
for (;;) {
- mutex_lock(&cpu_hotplug.lock);
+ hotplug_lock();
if (likely(!cpu_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
- mutex_unlock(&cpu_hotplug.lock);
+ hotplug_unlock();
schedule();
}
}
@@ -227,7 +244,7 @@ void cpu_hotplug_begin(void)
void cpu_hotplug_done(void)
{
cpu_hotplug.active_writer = NULL;
- mutex_unlock(&cpu_hotplug.lock);
+ hotplug_unlock();
}
/*

548
debian/patches/features/all/rt/cpu-rt-rework-cpu-down.patch vendored Normal file
View File

@ -0,0 +1,548 @@
From: Steven Rostedt <srostedt@redhat.com>
Date: Mon, 16 Jul 2012 08:07:43 +0000
Subject: cpu/rt: Rework cpu down for PREEMPT_RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Bringing a CPU down is a pain with the PREEMPT_RT kernel because
tasks can be preempted in many more places than in non-RT. In
order to handle per_cpu variables, tasks may be pinned to a CPU
for a while, and even sleep. But these tasks need to be off the CPU
if that CPU is going down.
Several synchronization methods have been tried, but when stressed
they failed. This is a new approach.
A sync_tsk thread is still created and tasks may still block on a
lock when the CPU is going down, but how that works is a bit different.
When cpu_down() starts, it will create the sync_tsk and wait on it
to inform that current tasks that are pinned on the CPU are no longer
pinned. But new tasks that are about to be pinned will still be allowed
to do so at this time.
Then the notifiers are called. Several notifiers will bring down tasks
that will enter these locations. Some of these tasks will take locks
of other tasks that are on the CPU. If we don't let those other tasks
continue, but make them block until CPU down is done, the tasks that
the notifiers are waiting on will never complete as they are waiting
for the locks held by the tasks that are blocked.
Thus we still let the task pin the CPU until the notifiers are done.
After the notifiers run, we then make new tasks entering the pinned
CPU sections grab a mutex and wait. This mutex is now a per CPU mutex
in the hotplug_pcp descriptor.
To help things along, a new function in the scheduler code is created
called migrate_me(). This function will try to migrate the current task
off the CPU this is going down if possible. When the sync_tsk is created,
all tasks will then try to migrate off the CPU going down. There are
several cases that this wont work, but it helps in most cases.
After the notifiers are called and if a task can't migrate off but enters
the pin CPU sections, it will be forced to wait on the hotplug_pcp mutex
until the CPU down is complete. Then the scheduler will force the migration
anyway.
Also, I found that THREAD_BOUND need to also be accounted for in the
pinned CPU, and the migrate_disable no longer treats them special.
This helps fix issues with ksoftirqd and workqueue that unbind on CPU down.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/sched.h | 7 +
kernel/cpu.c | 240 +++++++++++++++++++++++++++++++++++++++++---------
kernel/sched/core.c | 82 ++++++++++++++++-
3 files changed, 284 insertions(+), 45 deletions(-)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1807,6 +1807,10 @@ extern void do_set_cpus_allowed(struct t
extern int set_cpus_allowed_ptr(struct task_struct *p,
const struct cpumask *new_mask);
+int migrate_me(void);
+void tell_sched_cpu_down_begin(int cpu);
+void tell_sched_cpu_down_done(int cpu);
+
#else
static inline void do_set_cpus_allowed(struct task_struct *p,
const struct cpumask *new_mask)
@@ -1819,6 +1823,9 @@ static inline int set_cpus_allowed_ptr(s
return -EINVAL;
return 0;
}
+static inline int migrate_me(void) { return 0; }
+static inline void tell_sched_cpu_down_begin(int cpu) { }
+static inline void tell_sched_cpu_down_done(int cpu) { }
#endif
#ifdef CONFIG_NO_HZ_COMMON
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -51,12 +51,7 @@ static int cpu_hotplug_disabled;
static struct {
struct task_struct *active_writer;
-#ifdef CONFIG_PREEMPT_RT_FULL
- /* Makes the lock keep the task's state */
- spinlock_t lock;
-#else
struct mutex lock; /* Synchronizes accesses to refcount, */
-#endif
/*
* Also blocks the new readers during
* an ongoing cpu hotplug operation.
@@ -64,28 +59,46 @@ static struct {
int refcount;
} cpu_hotplug = {
.active_writer = NULL,
-#ifdef CONFIG_PREEMPT_RT_FULL
- .lock = __SPIN_LOCK_UNLOCKED(cpu_hotplug.lock),
-#else
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-#endif
.refcount = 0,
};
-#ifdef CONFIG_PREEMPT_RT_FULL
-# define hotplug_lock() rt_spin_lock(&cpu_hotplug.lock)
-# define hotplug_unlock() rt_spin_unlock(&cpu_hotplug.lock)
-#else
-# define hotplug_lock() mutex_lock(&cpu_hotplug.lock)
-# define hotplug_unlock() mutex_unlock(&cpu_hotplug.lock)
-#endif
-
+/**
+ * hotplug_pcp - per cpu hotplug descriptor
+ * @unplug: set when pin_current_cpu() needs to sync tasks
+ * @sync_tsk: the task that waits for tasks to finish pinned sections
+ * @refcount: counter of tasks in pinned sections
+ * @grab_lock: set when the tasks entering pinned sections should wait
+ * @synced: notifier for @sync_tsk to tell cpu_down it's finished
+ * @mutex: the mutex to make tasks wait (used when @grab_lock is true)
+ * @mutex_init: zero if the mutex hasn't been initialized yet.
+ *
+ * Although @unplug and @sync_tsk may point to the same task, the @unplug
+ * is used as a flag and still exists after @sync_tsk has exited and
+ * @sync_tsk set to NULL.
+ */
struct hotplug_pcp {
struct task_struct *unplug;
+ struct task_struct *sync_tsk;
int refcount;
+ int grab_lock;
struct completion synced;
+#ifdef CONFIG_PREEMPT_RT_FULL
+ spinlock_t lock;
+#else
+ struct mutex mutex;
+#endif
+ int mutex_init;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock)
+# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock)
+#else
+# define hotplug_lock(hp) mutex_lock(&(hp)->mutex)
+# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex)
+#endif
+
static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
/**
@@ -99,18 +112,39 @@ static DEFINE_PER_CPU(struct hotplug_pcp
void pin_current_cpu(void)
{
struct hotplug_pcp *hp;
+ int force = 0;
retry:
hp = &__get_cpu_var(hotplug_pcp);
- if (!hp->unplug || hp->refcount || preempt_count() > 1 ||
+ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 ||
hp->unplug == current) {
hp->refcount++;
return;
}
- preempt_enable();
- hotplug_lock();
- hotplug_unlock();
+ if (hp->grab_lock) {
+ preempt_enable();
+ hotplug_lock(hp);
+ hotplug_unlock(hp);
+ } else {
+ preempt_enable();
+ /*
+ * Try to push this task off of this CPU.
+ */
+ if (!migrate_me()) {
+ preempt_disable();
+ hp = &__get_cpu_var(hotplug_pcp);
+ if (!hp->grab_lock) {
+ /*
+ * Just let it continue it's already pinned
+ * or about to sleep.
+ */
+ force = 1;
+ goto retry;
+ }
+ preempt_enable();
+ }
+ }
preempt_disable();
goto retry;
}
@@ -131,26 +165,84 @@ void unpin_current_cpu(void)
wake_up_process(hp->unplug);
}
-/*
- * FIXME: Is this really correct under all circumstances ?
- */
+static void wait_for_pinned_cpus(struct hotplug_pcp *hp)
+{
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ while (hp->refcount) {
+ schedule_preempt_disabled();
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ }
+}
+
static int sync_unplug_thread(void *data)
{
struct hotplug_pcp *hp = data;
preempt_disable();
hp->unplug = current;
+ wait_for_pinned_cpus(hp);
+
+ /*
+ * This thread will synchronize the cpu_down() with threads
+ * that have pinned the CPU. When the pinned CPU count reaches
+ * zero, we inform the cpu_down code to continue to the next step.
+ */
set_current_state(TASK_UNINTERRUPTIBLE);
- while (hp->refcount) {
- schedule_preempt_disabled();
+ preempt_enable();
+ complete(&hp->synced);
+
+ /*
+ * If all succeeds, the next step will need tasks to wait till
+ * the CPU is offline before continuing. To do this, the grab_lock
+ * is set and tasks going into pin_current_cpu() will block on the
+ * mutex. But we still need to wait for those that are already in
+ * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop()
+ * will kick this thread out.
+ */
+ while (!hp->grab_lock && !kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ }
+
+ /* Make sure grab_lock is seen before we see a stale completion */
+ smp_mb();
+
+ /*
+ * Now just before cpu_down() enters stop machine, we need to make
+ * sure all tasks that are in pinned CPU sections are out, and new
+ * tasks will now grab the lock, keeping them from entering pinned
+ * CPU sections.
+ */
+ if (!kthread_should_stop()) {
+ preempt_disable();
+ wait_for_pinned_cpus(hp);
+ preempt_enable();
+ complete(&hp->synced);
+ }
+
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
set_current_state(TASK_UNINTERRUPTIBLE);
}
set_current_state(TASK_RUNNING);
- preempt_enable();
- complete(&hp->synced);
+
+ /*
+ * Force this thread off this CPU as it's going down and
+ * we don't want any more work on this CPU.
+ */
+ current->flags &= ~PF_NO_SETAFFINITY;
+ do_set_cpus_allowed(current, cpu_present_mask);
+ migrate_me();
return 0;
}
+static void __cpu_unplug_sync(struct hotplug_pcp *hp)
+{
+ wake_up_process(hp->sync_tsk);
+ wait_for_completion(&hp->synced);
+}
+
/*
* Start the sync_unplug_thread on the target cpu and wait for it to
* complete.
@@ -158,23 +250,83 @@ static int sync_unplug_thread(void *data
static int cpu_unplug_begin(unsigned int cpu)
{
struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
- struct task_struct *tsk;
+ int err;
+
+ /* Protected by cpu_hotplug.lock */
+ if (!hp->mutex_init) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+ spin_lock_init(&hp->lock);
+#else
+ mutex_init(&hp->mutex);
+#endif
+ hp->mutex_init = 1;
+ }
+
+ /* Inform the scheduler to migrate tasks off this CPU */
+ tell_sched_cpu_down_begin(cpu);
init_completion(&hp->synced);
- tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
- if (IS_ERR(tsk))
- return (PTR_ERR(tsk));
- kthread_bind(tsk, cpu);
- wake_up_process(tsk);
- wait_for_completion(&hp->synced);
+
+ hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
+ if (IS_ERR(hp->sync_tsk)) {
+ err = PTR_ERR(hp->sync_tsk);
+ hp->sync_tsk = NULL;
+ return err;
+ }
+ kthread_bind(hp->sync_tsk, cpu);
+
+ /*
+ * Wait for tasks to get out of the pinned sections,
+ * it's still OK if new tasks enter. Some CPU notifiers will
+ * wait for tasks that are going to enter these sections and
+ * we must not have them block.
+ */
+ __cpu_unplug_sync(hp);
+
return 0;
}
+static void cpu_unplug_sync(unsigned int cpu)
+{
+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+ init_completion(&hp->synced);
+ /* The completion needs to be initialzied before setting grab_lock */
+ smp_wmb();
+
+ /* Grab the mutex before setting grab_lock */
+ hotplug_lock(hp);
+ hp->grab_lock = 1;
+
+ /*
+ * The CPU notifiers have been completed.
+ * Wait for tasks to get out of pinned CPU sections and have new
+ * tasks block until the CPU is completely down.
+ */
+ __cpu_unplug_sync(hp);
+
+ /* All done with the sync thread */
+ kthread_stop(hp->sync_tsk);
+ hp->sync_tsk = NULL;
+}
+
static void cpu_unplug_done(unsigned int cpu)
{
struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
hp->unplug = NULL;
+ /* Let all tasks know cpu unplug is finished before cleaning up */
+ smp_wmb();
+
+ if (hp->sync_tsk)
+ kthread_stop(hp->sync_tsk);
+
+ if (hp->grab_lock) {
+ hotplug_unlock(hp);
+ /* protected by cpu_hotplug.lock */
+ hp->grab_lock = 0;
+ }
+ tell_sched_cpu_down_done(cpu);
}
void get_online_cpus(void)
@@ -182,9 +334,9 @@ void get_online_cpus(void)
might_sleep();
if (cpu_hotplug.active_writer == current)
return;
- hotplug_lock();
+ mutex_lock(&cpu_hotplug.lock);
cpu_hotplug.refcount++;
- hotplug_unlock();
+ mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(get_online_cpus);
@@ -194,14 +346,13 @@ void put_online_cpus(void)
if (cpu_hotplug.active_writer == current)
return;
- hotplug_lock();
+ mutex_lock(&cpu_hotplug.lock);
if (WARN_ON(!cpu_hotplug.refcount))
cpu_hotplug.refcount++; /* try to fix things up */
if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
wake_up_process(cpu_hotplug.active_writer);
- hotplug_unlock();
-
+ mutex_unlock(&cpu_hotplug.lock);
}
EXPORT_SYMBOL_GPL(put_online_cpus);
@@ -232,11 +383,11 @@ void cpu_hotplug_begin(void)
cpu_hotplug.active_writer = current;
for (;;) {
- hotplug_lock();
+ mutex_lock(&cpu_hotplug.lock);
if (likely(!cpu_hotplug.refcount))
break;
__set_current_state(TASK_UNINTERRUPTIBLE);
- hotplug_unlock();
+ mutex_unlock(&cpu_hotplug.lock);
schedule();
}
}
@@ -244,7 +395,7 @@ void cpu_hotplug_begin(void)
void cpu_hotplug_done(void)
{
cpu_hotplug.active_writer = NULL;
- hotplug_unlock();
+ mutex_unlock(&cpu_hotplug.lock);
}
/*
@@ -442,6 +593,9 @@ static int __ref _cpu_down(unsigned int
}
smpboot_park_threads(cpu);
+ /* Notifiers are done. Don't let any more tasks pin this CPU. */
+ cpu_unplug_sync(cpu);
+
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2359,7 +2359,7 @@ void migrate_disable(void)
{
struct task_struct *p = current;
- if (in_atomic() || p->flags & PF_NO_SETAFFINITY) {
+ if (in_atomic()) {
#ifdef CONFIG_SCHED_DEBUG
p->migrate_disable_atomic++;
#endif
@@ -2390,7 +2390,7 @@ void migrate_enable(void)
unsigned long flags;
struct rq *rq;
- if (in_atomic() || p->flags & PF_NO_SETAFFINITY) {
+ if (in_atomic()) {
#ifdef CONFIG_SCHED_DEBUG
p->migrate_disable_atomic--;
#endif
@@ -4430,6 +4430,84 @@ void do_set_cpus_allowed(struct task_str
cpumask_copy(&p->cpus_allowed, new_mask);
}
+static DEFINE_PER_CPU(struct cpumask, sched_cpumasks);
+static DEFINE_MUTEX(sched_down_mutex);
+static cpumask_t sched_down_cpumask;
+
+void tell_sched_cpu_down_begin(int cpu)
+{
+ mutex_lock(&sched_down_mutex);
+ cpumask_set_cpu(cpu, &sched_down_cpumask);
+ mutex_unlock(&sched_down_mutex);
+}
+
+void tell_sched_cpu_down_done(int cpu)
+{
+ mutex_lock(&sched_down_mutex);
+ cpumask_clear_cpu(cpu, &sched_down_cpumask);
+ mutex_unlock(&sched_down_mutex);
+}
+
+/**
+ * migrate_me - try to move the current task off this cpu
+ *
+ * Used by the pin_current_cpu() code to try to get tasks
+ * to move off the current CPU as it is going down.
+ * It will only move the task if the task isn't pinned to
+ * the CPU (with migrate_disable, affinity or NO_SETAFFINITY)
+ * and the task has to be in a RUNNING state. Otherwise the
+ * movement of the task will wake it up (change its state
+ * to running) when the task did not expect it.
+ *
+ * Returns 1 if it succeeded in moving the current task
+ * 0 otherwise.
+ */
+int migrate_me(void)
+{
+ struct task_struct *p = current;
+ struct migration_arg arg;
+ struct cpumask *cpumask;
+ struct cpumask *mask;
+ unsigned long flags;
+ unsigned int dest_cpu;
+ struct rq *rq;
+
+ /*
+ * We can not migrate tasks bounded to a CPU or tasks not
+ * running. The movement of the task will wake it up.
+ */
+ if (p->flags & PF_NO_SETAFFINITY || p->state)
+ return 0;
+
+ mutex_lock(&sched_down_mutex);
+ rq = task_rq_lock(p, &flags);
+
+ cpumask = &__get_cpu_var(sched_cpumasks);
+ mask = &p->cpus_allowed;
+
+ cpumask_andnot(cpumask, mask, &sched_down_cpumask);
+
+ if (!cpumask_weight(cpumask)) {
+ /* It's only on this CPU? */
+ task_rq_unlock(rq, p, &flags);
+ mutex_unlock(&sched_down_mutex);
+ return 0;
+ }
+
+ dest_cpu = cpumask_any_and(cpu_active_mask, cpumask);
+
+ arg.task = p;
+ arg.dest_cpu = dest_cpu;
+
+ task_rq_unlock(rq, p, &flags);
+
+ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+ tlb_migrate_finish(p->mm);
+ mutex_unlock(&sched_down_mutex);
+
+ return 1;
+}
+
/*
* This is how migration works:
*

27
debian/patches/features/all/rt/cpu-rt-variants.patch vendored Normal file
View File

@ -0,0 +1,27 @@
Subject: cpu-rt-variants.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 17 Jun 2011 15:42:38 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/smp.h | 8 ++++++++
1 file changed, 8 insertions(+)
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -188,6 +188,14 @@ static inline void __smp_call_function_s
#define get_cpu() ({ preempt_disable(); smp_processor_id(); })
#define put_cpu() preempt_enable()
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define get_cpu_light() get_cpu()
+# define put_cpu_light() put_cpu()
+#else
+# define get_cpu_light() ({ migrate_disable(); smp_processor_id(); })
+# define put_cpu_light() migrate_enable()
+#endif
+
/*
* Callback to arch code if there's nosmp or maxcpus=0 on the
* boot command line:

54
debian/patches/features/all/rt/cpu_down_move_migrate_enable_back.patch vendored Normal file
View File

@ -0,0 +1,54 @@
From linux-rt-users-owner@vger.kernel.org Thu Nov 7 03:07:12 2013
From: Tiejun Chen <tiejun.chen@windriver.com>
Subject: [v1][PATCH] cpu_down: move migrate_enable() back
Date: Thu, 7 Nov 2013 10:06:07 +0800
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Commit 08c1ab68, "hotplug-use-migrate-disable.patch", intends to
use migrate_enable()/migrate_disable() to replace that combination
of preempt_enable() and preempt_disable(), but actually in
!CONFIG_PREEMPT_RT_FULL case, migrate_enable()/migrate_disable()
are still equal to preempt_enable()/preempt_disable(). So that
followed cpu_hotplug_begin()/cpu_unplug_begin(cpu) would go schedule()
to trigger schedule_debug() like this:
_cpu_down()
|
+ migrate_disable() = preempt_disable()
|
+ cpu_hotplug_begin() or cpu_unplug_begin()
|
+ schedule()
|
+ __schedule()
|
+ preempt_disable();
|
+ __schedule_bug() is true!
So we should move migrate_enable() as the original scheme.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Tiejun Chen <tiejun.chen@windriver.com>
---
kernel/cpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -593,6 +593,7 @@ static int __ref _cpu_down(unsigned int
err = -EBUSY;
goto restore_cpus;
}
+ migrate_enable();
cpu_hotplug_begin();
err = cpu_unplug_begin(cpu);
@@ -646,7 +647,6 @@ static int __ref _cpu_down(unsigned int
out_release:
cpu_unplug_done(cpu);
out_cancel:
- migrate_enable();
cpu_hotplug_done();
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);

35
debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch vendored Normal file
View File

@ -0,0 +1,35 @@
Subject: cpumask: Disable CONFIG_CPUMASK_OFFSTACK for RT
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 14 Dec 2011 01:03:49 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
We can't deal with the cpumask allocations which happen in atomic
context (see arch/x86/kernel/apic/io_apic.c) on RT right now.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/Kconfig | 2 +-
lib/Kconfig | 1 +
2 files changed, 2 insertions(+), 1 deletion(-)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -820,7 +820,7 @@ config IOMMU_HELPER
config MAXSMP
bool "Enable Maximum number of SMP Processors and NUMA Nodes"
depends on X86_64 && SMP && DEBUG_KERNEL
- select CPUMASK_OFFSTACK
+ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL
---help---
Enable maximum number of CPUS and NUMA Nodes for this architecture.
If unsure, say N.
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -344,6 +344,7 @@ config CHECK_SIGNATURE
config CPUMASK_OFFSTACK
bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+ depends on !PREEMPT_RT_FULL
help
Use dynamic allocation for cpumask_var_t, instead of putting
them on the stack. This is a bit more expensive, but avoids

24
debian/patches/features/all/rt/debugobjects-rt.patch vendored Normal file
View File

@ -0,0 +1,24 @@
Subject: debugobjects-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 17 Jul 2011 21:41:35 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
lib/debugobjects.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -308,7 +308,10 @@ static void
struct debug_obj *obj;
unsigned long flags;
- fill_pool();
+#ifdef CONFIG_PREEMPT_RT_FULL
+ if (preempt_count() == 0 && !irqs_disabled())
+#endif
+ fill_pool();
db = get_bucket((unsigned long) addr);

35
debian/patches/features/all/rt/dm-make-rt-aware.patch vendored Normal file
View File

@ -0,0 +1,35 @@
Subject: dm: Make rt aware
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 14 Nov 2011 23:06:09 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Use the BUG_ON_NORT variant for the irq_disabled() checks. RT has
interrupts legitimately enabled here as we cant deadlock against the
irq thread due to the "sleeping spinlocks" conversion.
Reported-by: Luis Claudio R. Goncalves <lclaudio@uudg.org>
Cc: stable-rt@vger.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/md/dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1813,14 +1813,14 @@ static void dm_request_fn(struct request
if (map_request(ti, clone, md))
goto requeued;
- BUG_ON(!irqs_disabled());
+ BUG_ON_NONRT(!irqs_disabled());
spin_lock(q->queue_lock);
}
goto out;
requeued:
- BUG_ON(!irqs_disabled());
+ BUG_ON_NONRT(!irqs_disabled());
spin_lock(q->queue_lock);
delay_and_out:

26
debian/patches/features/all/rt/drivers-net-8139-disable-irq-nosync.patch vendored Normal file
View File

@ -0,0 +1,26 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:24 -0500
Subject: drivers/net: Use disable_irq_nosync() in 8139too
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Use disable_irq_nosync() instead of disable_irq() as this might be
called in atomic context with netpoll.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/net/ethernet/realtek/8139too.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2213,7 +2213,7 @@ static void rtl8139_poll_controller(stru
struct rtl8139_private *tp = netdev_priv(dev);
const int irq = tp->pci_dev->irq;
- disable_irq(irq);
+ disable_irq_nosync(irq);
rtl8139_interrupt(irq, dev);
enable_irq(irq);
}

127
debian/patches/features/all/rt/drivers-net-fix-livelock-issues.patch vendored Normal file
View File

@ -0,0 +1,127 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 20 Jun 2009 11:36:54 +0200
Subject: drivers/net: fix livelock issues
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Preempt-RT runs into a live lock issue with the NETDEV_TX_LOCKED micro
optimization. The reason is that the softirq thread is rescheduling
itself on that return value. Depending on priorities it starts to
monoplize the CPU and livelock on UP systems.
Remove it.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 6 +-----
drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 3 +--
drivers/net/ethernet/chelsio/cxgb/sge.c | 3 +--
drivers/net/ethernet/neterion/s2io.c | 7 +------
drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 6 ++----
drivers/net/ethernet/tehuti/tehuti.c | 9 ++-------
drivers/net/rionet.c | 6 +-----
7 files changed, 9 insertions(+), 31 deletions(-)
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2206,11 +2206,7 @@ static netdev_tx_t atl1c_xmit_frame(stru
}
tpd_req = atl1c_cal_tpd_req(skb);
- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) {
- if (netif_msg_pktdata(adapter))
- dev_info(&adapter->pdev->dev, "tx locked\n");
- return NETDEV_TX_LOCKED;
- }
+ spin_lock_irqsave(&adapter->tx_lock, flags);
if (atl1c_tpd_avail(adapter, type) < tpd_req) {
/* no enough descriptor, just stop queue */
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1838,8 +1838,7 @@ static netdev_tx_t atl1e_xmit_frame(stru
return NETDEV_TX_OK;
}
tpd_req = atl1e_cal_tdp_req(skb);
- if (!spin_trylock_irqsave(&adapter->tx_lock, flags))
- return NETDEV_TX_LOCKED;
+ spin_lock_irqsave(&adapter->tx_lock, flags);
if (atl1e_tpd_avail(adapter) < tpd_req) {
/* no enough descriptor, just stop queue */
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1665,8 +1665,7 @@ static int t1_sge_tx(struct sk_buff *skb
struct cmdQ *q = &sge->cmdQ[qid];
unsigned int credits, pidx, genbit, count, use_sched_skb = 0;
- if (!spin_trylock(&q->lock))
- return NETDEV_TX_LOCKED;
+ spin_lock(&q->lock);
reclaim_completed_tx(sge, q);
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4089,12 +4089,7 @@ static netdev_tx_t s2io_xmit(struct sk_b
[skb->priority & (MAX_TX_FIFOS - 1)];
fifo = &mac_control->fifos[queue];
- if (do_spin_lock)
- spin_lock_irqsave(&fifo->tx_lock, flags);
- else {
- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags)))
- return NETDEV_TX_LOCKED;
- }
+ spin_lock_irqsave(&fifo->tx_lock, flags);
if (sp->config.multiq) {
if (__netif_subqueue_stopped(dev, fifo->fifo_no)) {
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2148,10 +2148,8 @@ static int pch_gbe_xmit_frame(struct sk_
struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring;
unsigned long flags;
- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) {
- /* Collision - tell upper layer to requeue */
- return NETDEV_TX_LOCKED;
- }
+ spin_lock_irqsave(&tx_ring->tx_lock, flags);
+
if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) {
netif_stop_queue(netdev);
spin_unlock_irqrestore(&tx_ring->tx_lock, flags);
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1629,13 +1629,8 @@ static netdev_tx_t bdx_tx_transmit(struc
unsigned long flags;
ENTER;
- local_irq_save(flags);
- if (!spin_trylock(&priv->tx_lock)) {
- local_irq_restore(flags);
- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n",
- BDX_DRV_NAME, ndev->name);
- return NETDEV_TX_LOCKED;
- }
+
+ spin_lock_irqsave(&priv->tx_lock, flags);
/* build tx descriptor */
BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -174,11 +174,7 @@ static int rionet_start_xmit(struct sk_b
unsigned long flags;
int add_num = 1;
- local_irq_save(flags);
- if (!spin_trylock(&rnet->tx_lock)) {
- local_irq_restore(flags);
- return NETDEV_TX_LOCKED;
- }
+ spin_lock_irqsave(&rnet->tx_lock, flags);
if (is_multicast_ether_addr(eth->h_dest))
add_num = nets[rnet->mport->id].nact;

56
debian/patches/features/all/rt/drivers-net-gianfar-make-rt-aware.patch vendored Normal file
View File

@ -0,0 +1,56 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 1 Apr 2010 20:20:57 +0200
Subject: drivers: net: gianfar: Make RT aware
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The adjust_link() disables interrupts before taking the queue
locks. On RT those locks are converted to "sleeping" locks and
therefor the local_irq_save/restore must be converted to
local_irq_save/restore_nort.
Reported-by: Xianghua Xiao <xiaoxianghua@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Xianghua Xiao <xiaoxianghua@gmail.com>
---
drivers/net/ethernet/freescale/gianfar.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1701,7 +1701,7 @@ void stop_gfar(struct net_device *dev)
/* Lock it down */
- local_irq_save(flags);
+ local_irq_save_nort(flags);
lock_tx_qs(priv);
lock_rx_qs(priv);
@@ -1709,7 +1709,7 @@ void stop_gfar(struct net_device *dev)
unlock_rx_qs(priv);
unlock_tx_qs(priv);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
/* Free the IRQs */
if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) {
@@ -3101,7 +3101,7 @@ static void adjust_link(struct net_devic
struct phy_device *phydev = priv->phydev;
int new_state = 0;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
lock_tx_qs(priv);
if (phydev->link) {
@@ -3175,7 +3175,7 @@ static void adjust_link(struct net_devic
if (new_state && netif_msg_link(priv))
phy_print_status(phydev);
unlock_tx_qs(priv);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
/* Update the hash table based on the current list of multicast

24
debian/patches/features/all/rt/drivers-net-tulip-add-missing-pci-disable.patch vendored Normal file
View File

@ -0,0 +1,24 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:18 -0500
Subject: drivers/net: tulip_remove_one needs to call pci_disable_device()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Otherwise the device is not completely shut down.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/net/ethernet/dec/tulip/tulip_core.c | 1 +
1 file changed, 1 insertion(+)
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1939,6 +1939,7 @@ static void tulip_remove_one(struct pci_
pci_iounmap(pdev, tp->base_addr);
free_netdev (dev);
pci_release_regions (pdev);
+ pci_disable_device (pdev);
pci_set_drvdata (pdev, NULL);
/* pci_power_off (pdev, -1); */

49
debian/patches/features/all/rt/drivers-net-vortex-fix-locking-issues.patch vendored Normal file
View File

@ -0,0 +1,49 @@
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 3 Jul 2009 08:30:00 -0500
Subject: drivers/net: vortex fix locking issues
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Argh, cut and paste wasn't enough...
Use this patch instead. It needs an irq disable. But, believe it or not,
on SMP this is actually better. If the irq is shared (as it is in Mark's
case), we don't stop the irq of other devices from being handled on
another CPU (unfortunately for Mark, he pinned all interrupts to one CPU).
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
drivers/net/ethernet/3com/3c59x.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@ static void poll_vortex(struct net_devic
{
struct vortex_private *vp = netdev_priv(dev);
unsigned long flags;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
(vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
#endif
@@ -1917,12 +1917,12 @@ static void vortex_tx_timeout(struct net
* Block interrupts because vortex_interrupt does a bare spin_lock()
*/
unsigned long flags;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
if (vp->full_bus_master_tx)
boomerang_interrupt(dev->irq, dev);
else
vortex_interrupt(dev->irq, dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
}

40
debian/patches/features/all/rt/drivers-random-reduce-preempt-disabled-region.patch vendored Normal file
View File

@ -0,0 +1,40 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:30 -0500
Subject: drivers: random: Reduce preempt disabled region
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
No need to keep preemption disabled across the whole function.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/char/random.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -673,9 +673,12 @@ static void add_timer_randomness(struct
preempt_disable();
/* if over the trickle threshold, use only 1 in 4096 samples */
if (input_pool.entropy_count > trickle_thresh &&
- ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff))
- goto out;
+ ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) {
+ preempt_enable();
+ return;
+ }
+ preempt_enable();
sample.jiffies = jiffies;
sample.cycles = random_get_entropy();
sample.num = num;
@@ -716,8 +719,6 @@ static void add_timer_randomness(struct
credit_entropy_bits(&input_pool,
min_t(int, fls(delta>>1), 11));
}
-out:
- preempt_enable();
}
void add_input_randomness(unsigned int type, unsigned int code,

28
debian/patches/features/all/rt/drivers-serial-call-flush_to_ldisc-when-the-irq-is-t.patch vendored Normal file
View File

@ -0,0 +1,28 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:01 -0500
Subject: serial: 8250: Call flush_to_ldisc when the irq is threaded
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
drivers/tty/tty_buffer.c | 4 ++++
1 file changed, 4 insertions(+)
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -509,10 +509,14 @@ void tty_flip_buffer_push(struct tty_por
buf->tail->commit = buf->tail->used;
+#ifndef CONFIG_PREEMPT_RT_FULL
if (port->low_latency)
flush_to_ldisc(&buf->work);
else
schedule_work(&buf->work);
+#else
+ schedule_work(&buf->work);
+#endif
}
EXPORT_SYMBOL(tty_flip_buffer_push);

43
debian/patches/features/all/rt/drivers-serial-cleanup-locking-for-rt.patch vendored Normal file
View File

@ -0,0 +1,43 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:01 -0500
Subject: serial: 8250: Clean up the locking for -rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/tty/serial/8250/8250_core.c | 15 +++++----------
1 file changed, 5 insertions(+), 10 deletions(-)
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2860,14 +2860,10 @@ serial8250_console_write(struct console
touch_nmi_watchdog();
- local_irq_save(flags);
- if (port->sysrq) {
- /* serial8250_handle_irq() already took the lock */
- locked = 0;
- } else if (oops_in_progress) {
- locked = spin_trylock(&port->lock);
- } else
- spin_lock(&port->lock);
+ if (port->sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&port->lock, flags);
+ else
+ spin_lock_irqsave(&port->lock, flags);
/*
* First save the IER then disable the interrupts
@@ -2899,8 +2895,7 @@ serial8250_console_write(struct console
serial8250_modem_status(up);
if (locked)
- spin_unlock(&port->lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&port->lock, flags);
}
static int __init serial8250_console_setup(struct console *co, char *options)

39
debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch vendored Normal file
View File

@ -0,0 +1,39 @@
Subject: drivers-tty-fix-omap-lock-crap.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 28 Jul 2011 13:32:57 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/tty/serial/omap-serial.c | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1232,13 +1232,10 @@ serial_omap_console_write(struct console
pm_runtime_get_sync(up->dev);
- local_irq_save(flags);
- if (up->port.sysrq)
- locked = 0;
- else if (oops_in_progress)
- locked = spin_trylock(&up->port.lock);
+ if (up->port.sysrq || oops_in_progress)
+ locked = spin_trylock_irqsave(&up->port.lock, flags);
else
- spin_lock(&up->port.lock);
+ spin_lock_irqsave(&up->port.lock, flags);
/*
* First save the IER then disable the interrupts
@@ -1267,8 +1264,7 @@ serial_omap_console_write(struct console
pm_runtime_mark_last_busy(up->dev);
pm_runtime_put_autosuspend(up->dev);
if (locked)
- spin_unlock(&up->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
static int __init

45
debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch vendored Normal file
View File

@ -0,0 +1,45 @@
Subject: drivers-tty-pl011-irq-disable-madness.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 08 Jan 2013 21:36:51 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/tty/serial/amba-pl011.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1910,13 +1910,19 @@ pl011_console_write(struct console *co,
clk_enable(uap->clk);
- local_irq_save(flags);
+ /*
+ * local_irq_save(flags);
+ *
+ * This local_irq_save() is nonsense. If we come in via sysrq
+ * handling then interrupts are already disabled. Aside of
+ * that the port.sysrq check is racy on SMP regardless.
+ */
if (uap->port.sysrq)
locked = 0;
else if (oops_in_progress)
- locked = spin_trylock(&uap->port.lock);
+ locked = spin_trylock_irqsave(&uap->port.lock, flags);
else
- spin_lock(&uap->port.lock);
+ spin_lock_irqsave(&uap->port.lock, flags);
/*
* First save the CR then disable the interrupts
@@ -1938,8 +1944,7 @@ pl011_console_write(struct console *co,
writew(old_cr, uap->port.membase + UART011_CR);
if (locked)
- spin_unlock(&uap->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&uap->port.lock, flags);
clk_disable(uap->clk);
}

60
debian/patches/features/all/rt/drm-i915-drop-trace_i915_gem_ring_dispatch-onrt.patch vendored Normal file
View File

@ -0,0 +1,60 @@
From d841118ac80c5bfb18f47984bc40687eed08b714 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 25 Apr 2013 18:12:52 +0200
Subject: [PATCH] drm/i915: drop trace_i915_gem_ring_dispatch on rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
This tracepoint is responsible for:
|[<814cc358>] __schedule_bug+0x4d/0x59
|[<814d24cc>] __schedule+0x88c/0x930
|[<814d3b90>] ? _raw_spin_unlock_irqrestore+0x40/0x50
|[<814d3b95>] ? _raw_spin_unlock_irqrestore+0x45/0x50
|[<810b57b5>] ? task_blocks_on_rt_mutex+0x1f5/0x250
|[<814d27d9>] schedule+0x29/0x70
|[<814d3423>] rt_spin_lock_slowlock+0x15b/0x278
|[<814d3786>] rt_spin_lock+0x26/0x30
|[<a00dced9>] gen6_gt_force_wake_get+0x29/0x60 [i915]
|[<a00e183f>] gen6_ring_get_irq+0x5f/0x100 [i915]
|[<a00b2a33>] ftrace_raw_event_i915_gem_ring_dispatch+0xe3/0x100 [i915]
|[<a00ac1b3>] i915_gem_do_execbuffer.isra.13+0xbd3/0x1430 [i915]
|[<810f8943>] ? trace_buffer_unlock_commit+0x43/0x60
|[<8113e8d2>] ? ftrace_raw_event_kmem_alloc+0xd2/0x180
|[<8101d063>] ? native_sched_clock+0x13/0x80
|[<a00acf29>] i915_gem_execbuffer2+0x99/0x280 [i915]
|[<a00114a3>] drm_ioctl+0x4c3/0x570 [drm]
|[<8101d0d9>] ? sched_clock+0x9/0x10
|[<a00ace90>] ? i915_gem_execbuffer+0x480/0x480 [i915]
|[<810f1c18>] ? rb_commit+0x68/0xa0
|[<810f1c6c>] ? ring_buffer_unlock_commit+0x1c/0xa0
|[<81197467>] do_vfs_ioctl+0x97/0x540
|[<81021318>] ? ftrace_raw_event_sys_enter+0xd8/0x130
|[<811979a1>] sys_ioctl+0x91/0xb0
|[<814db931>] tracesys+0xe1/0xe6
Chris Wilson does not like to move i915_trace_irq_get() out of the macro
|No. This enables the IRQ, as well as making a number of
|very expensively serialised read, unconditionally.
so it is gone now on RT.
Cc: stable-rt@vger.kernel.org
Reported-by: Joakim Hernberg <jbh@alchemy.lu>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 ++
1 file changed, 2 insertions(+)
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1129,7 +1129,9 @@ i915_gem_do_execbuffer(struct drm_device
goto err;
}
+#ifndef CONFIG_PREEMPT_RT_BASE
trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags);
+#endif
i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring);
i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);

78
debian/patches/features/all/rt/drm-remove-preempt_disable-from-drm_calc_vbltimestam.patch vendored Normal file
View File

@ -0,0 +1,78 @@
From c17c11831778d5ed948858ef4bb32058f5013094 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 11 Oct 2013 17:14:31 +0200
Subject: [PATCH] drm: remove preempt_disable() from
drm_calc_vbltimestamp_from_scanoutpos()
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Luis captured the following:
| BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
| in_atomic(): 1, irqs_disabled(): 0, pid: 517, name: Xorg
| 2 locks held by Xorg/517:
| #0:
| (
| &dev->vbl_lock
| ){......}
| , at:
| [<ffffffffa0024c60>] drm_vblank_get+0x30/0x2b0 [drm]
| #1:
| (
| &dev->vblank_time_lock
| ){......}
| , at:
| [<ffffffffa0024ce1>] drm_vblank_get+0xb1/0x2b0 [drm]
| Preemption disabled at:
| [<ffffffffa008bc95>] i915_get_vblank_timestamp+0x45/0xa0 [i915]
| CPU: 3 PID: 517 Comm: Xorg Not tainted 3.10.10-rt7+ #5
| Call Trace:
| [<ffffffff8164b790>] dump_stack+0x19/0x1b
| [<ffffffff8107e62f>] __might_sleep+0xff/0x170
| [<ffffffff81651ac4>] rt_spin_lock+0x24/0x60
| [<ffffffffa0084e67>] i915_read32+0x27/0x170 [i915]
| [<ffffffffa008a591>] i915_pipe_enabled+0x31/0x40 [i915]
| [<ffffffffa008a6be>] i915_get_crtc_scanoutpos+0x3e/0x1b0 [i915]
| [<ffffffffa00245d4>] drm_calc_vbltimestamp_from_scanoutpos+0xf4/0x430 [drm]
| [<ffffffffa008bc95>] i915_get_vblank_timestamp+0x45/0xa0 [i915]
| [<ffffffffa0024998>] drm_get_last_vbltimestamp+0x48/0x70 [drm]
| [<ffffffffa0024db5>] drm_vblank_get+0x185/0x2b0 [drm]
| [<ffffffffa0025d03>] drm_wait_vblank+0x83/0x5d0 [drm]
| [<ffffffffa00212a2>] drm_ioctl+0x552/0x6a0 [drm]
| [<ffffffff811a0095>] do_vfs_ioctl+0x325/0x5b0
| [<ffffffff811a03a1>] SyS_ioctl+0x81/0xa0
| [<ffffffff8165a342>] tracesys+0xdd/0xe2
After a longer thread it was decided to drop the preempt_disable()/
enable() invocations which were meant for -RT and Mario Kleiner looks
for a replacement.
Cc: stable-rt@vger.kernel.org
Reported-By: Luis Claudio R. Goncalves <lclaudio@uudg.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/gpu/drm/drm_irq.c | 7 -------
1 file changed, 7 deletions(-)
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -628,11 +628,6 @@ int drm_calc_vbltimestamp_from_scanoutpo
* code gets preempted or delayed for some reason.
*/
for (i = 0; i < DRM_TIMESTAMP_MAXRETRIES; i++) {
- /* Disable preemption to make it very likely to
- * succeed in the first iteration even on PREEMPT_RT kernel.
- */
- preempt_disable();
-
/* Get system timestamp before query. */
stime = ktime_get();
@@ -644,8 +639,6 @@ int drm_calc_vbltimestamp_from_scanoutpo
if (!drm_timestamp_monotonic)
mono_time_offset = ktime_get_monotonic_offset();
- preempt_enable();
-
/* Return as no-op if scanout query unsupported or failed. */
if (!(vbl_status & DRM_SCANOUTPOS_VALID)) {
DRM_DEBUG("crtc %d : scanoutpos query failed [%d].\n",

45
debian/patches/features/all/rt/early-printk-consolidate.patch vendored Normal file
View File

@ -0,0 +1,45 @@
Subject: early-printk-consolidate.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 23 Jul 2011 11:04:08 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/sparc/kernel/setup_32.c | 1 +
arch/sparc/kernel/setup_64.c | 8 +++++++-
2 files changed, 8 insertions(+), 1 deletion(-)
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -309,6 +309,7 @@ void __init setup_arch(char **cmdline_p)
boot_flags_init(*cmdline_p);
+ early_console = &prom_early_console;
register_console(&prom_early_console);
printk("ARCH: ");
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -555,6 +555,12 @@ static void __init init_sparc64_elf_hwca
pause_patch();
}
+static inline void register_prom_console(void)
+{
+ early_console = &prom_early_console;
+ register_console(&prom_early_console);
+}
+
void __init setup_arch(char **cmdline_p)
{
/* Initialize PROM console and command line. */
@@ -566,7 +572,7 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_EARLYFB
if (btext_find_display())
#endif
- register_console(&prom_early_console);
+ register_prom_console();
if (tlb_type == hypervisor)
printk("ARCH: SUN4V\n");

27
debian/patches/features/all/rt/epoll-use-get-cpu-light.patch vendored Normal file
View File

@ -0,0 +1,27 @@
Subject: epoll.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 08 Jul 2011 16:35:35 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
fs/eventpoll.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -500,12 +500,12 @@ static int ep_poll_wakeup_proc(void *pri
*/
static void ep_poll_safewake(wait_queue_head_t *wq)
{
- int this_cpu = get_cpu();
+ int this_cpu = get_cpu_light();
ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
- put_cpu();
+ put_cpu_light();
}
static void ep_remove_wait_queue(struct eppoll_entry *pwq)

23
debian/patches/features/all/rt/filemap-fix-up.patch vendored Normal file
View File

@ -0,0 +1,23 @@
Subject: filemap-fix-up.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 17 Jun 2011 18:56:24 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Wrecked-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-m6yuzd6ul717hlnl2gj6p3ou@git.kernel.org
---
mm/filemap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1976,7 +1976,7 @@ size_t iov_iter_copy_from_user_atomic(st
char *kaddr;
size_t copied;
- BUG_ON(!in_atomic());
+ BUG_ON(!pagefault_disabled());
kaddr = kmap_atomic(page);
if (likely(i->nr_segs == 1)) {
int left;

113
debian/patches/features/all/rt/fix-rt-int3-x86_32-3.2-rt.patch vendored Normal file
View File

@ -0,0 +1,113 @@
From: Steven Rostedt <rostedt@goodmis.org>
Subject: x86: Do not disable preemption in int3 on 32bit
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Preemption must be disabled before enabling interrupts in do_trap
on x86_64 because the stack in use for int3 and debug is a per CPU
stack set by th IST. But 32bit does not have an IST and the stack
still belongs to the current task and there is no problem in scheduling
out the task.
Keep preemption enabled on X86_32 when enabling interrupts for
do_trap().
The name of the function is changed from preempt_conditional_sti/cli()
to conditional_sti/cli_ist(), to annotate that this function is used
when the stack is on the IST.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/kernel/traps.c | 32 +++++++++++++++++++++++---------
1 file changed, 23 insertions(+), 9 deletions(-)
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -86,9 +86,21 @@ static inline void conditional_sti(struc
local_irq_enable();
}
-static inline void preempt_conditional_sti(struct pt_regs *regs)
+static inline void conditional_sti_ist(struct pt_regs *regs)
{
+#ifdef CONFIG_X86_64
+ /*
+ * X86_64 uses a per CPU stack on the IST for certain traps
+ * like int3. The task can not be preempted when using one
+ * of these stacks, thus preemption must be disabled, otherwise
+ * the stack can be corrupted if the task is scheduled out,
+ * and another task comes in and uses this stack.
+ *
+ * On x86_32 the task keeps its own stack and it is OK if the
+ * task schedules out.
+ */
inc_preempt_count();
+#endif
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
}
@@ -99,11 +111,13 @@ static inline void conditional_cli(struc
local_irq_disable();
}
-static inline void preempt_conditional_cli(struct pt_regs *regs)
+static inline void conditional_cli_ist(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
local_irq_disable();
+#ifdef CONFIG_X86_64
dec_preempt_count();
+#endif
}
static int __kprobes
@@ -236,9 +250,9 @@ dotraplinkage void do_stack_segment(stru
prev_state = exception_enter();
if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
- preempt_conditional_sti(regs);
+ conditional_sti_ist(regs);
do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
+ conditional_cli_ist(regs);
}
exception_exit(prev_state);
}
@@ -347,9 +361,9 @@ dotraplinkage void __kprobes notrace do_
* as we may switch to the interrupt stack.
*/
debug_stack_usage_inc();
- preempt_conditional_sti(regs);
+ conditional_sti_ist(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
- preempt_conditional_cli(regs);
+ conditional_cli_ist(regs);
debug_stack_usage_dec();
exit:
exception_exit(prev_state);
@@ -455,12 +469,12 @@ dotraplinkage void __kprobes do_debug(st
debug_stack_usage_inc();
/* It's safe to allow irq's after DR6 has been saved */
- preempt_conditional_sti(regs);
+ conditional_sti_ist(regs);
if (regs->flags & X86_VM_MASK) {
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
X86_TRAP_DB);
- preempt_conditional_cli(regs);
+ conditional_cli_ist(regs);
debug_stack_usage_dec();
goto exit;
}
@@ -480,7 +494,7 @@ dotraplinkage void __kprobes do_debug(st
si_code = get_si_code(tsk->thread.debugreg6);
if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
- preempt_conditional_cli(regs);
+ conditional_cli_ist(regs);
debug_stack_usage_dec();
exit:

67
debian/patches/features/all/rt/fixup_opencoded_completions.patch vendored Normal file
View File

@ -0,0 +1,67 @@
From 53a9508f5983092928b0e6e12f400b686e1f04b1 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 28 Oct 2013 11:50:06 +0100
Subject: [PATCH] a few open coded completions
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/net/wireless/orinoco/orinoco_usb.c | 2 +-
drivers/usb/gadget/f_fs.c | 2 +-
drivers/usb/gadget/inode.c | 4 ++--
include/linux/netdevice.h | 2 +-
4 files changed, 5 insertions(+), 5 deletions(-)
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -714,7 +714,7 @@ static void ezusb_req_ctx_wait(struct ez
while (!ctx->done.done && msecs--)
udelay(1000);
} else {
- wait_event_interruptible(ctx->done.wait,
+ swait_event_interruptible(ctx->done.wait,
ctx->done.done);
}
break;
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1282,7 +1282,7 @@ static void ffs_data_put(struct ffs_data
pr_info("%s(): freeing\n", __func__);
ffs_data_clear(ffs);
BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
- waitqueue_active(&ffs->ep0req_completion.wait));
+ swaitqueue_active(&ffs->ep0req_completion.wait));
kfree(ffs->dev_name);
kfree(ffs);
}
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -340,7 +340,7 @@ ep_io (struct ep_data *epdata, void *buf
spin_unlock_irq (&epdata->dev->lock);
if (likely (value == 0)) {
- value = wait_event_interruptible (done.wait, done.done);
+ value = swait_event_interruptible (done.wait, done.done);
if (value != 0) {
spin_lock_irq (&epdata->dev->lock);
if (likely (epdata->ep != NULL)) {
@@ -349,7 +349,7 @@ ep_io (struct ep_data *epdata, void *buf
usb_ep_dequeue (epdata->ep, epdata->req);
spin_unlock_irq (&epdata->dev->lock);
- wait_event (done.wait, done.done);
+ swait_event (done.wait, done.done);
if (epdata->status == -ECONNRESET)
epdata->status = -EINTR;
} else {
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1214,7 +1214,7 @@ struct net_device {
unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
unsigned char addr_assign_type; /* hw address assignment type */
unsigned char addr_len; /* hardware address length */
- unsigned char neigh_priv_len;
+ unsigned short neigh_priv_len;
unsigned short dev_id; /* Used to differentiate devices
* that share the same link
* layer address

21
debian/patches/features/all/rt/fs-block-rt-support.patch vendored Normal file
View File

@ -0,0 +1,21 @@
Subject: fs-block-rt-support.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 14 Jun 2011 17:05:09 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
block/blk-core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -232,7 +232,7 @@ EXPORT_SYMBOL(blk_delay_queue);
**/
void blk_start_queue(struct request_queue *q)
{
- WARN_ON(!irqs_disabled());
+ WARN_ON_NONRT(!irqs_disabled());
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
__blk_run_queue(q);

86
debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch vendored Normal file
View File

@ -0,0 +1,86 @@
Subject: fs: dcache: Use cpu_chill() in trylock loops
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 07 Mar 2012 21:00:34 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Retry loops on RT might loop forever when the modifying side was
preempted. Use cpu_chill() instead of cpu_relax() to let the system
make progress.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
fs/autofs4/autofs_i.h | 1 +
fs/autofs4/expire.c | 2 +-
fs/dcache.c | 5 +++--
fs/namespace.c | 3 ++-
4 files changed, 7 insertions(+), 4 deletions(-)
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -34,6 +34,7 @@
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
+#include <linux/delay.h>
#include <asm/current.h>
#include <asm/uaccess.h>
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -157,7 +157,7 @@ static struct dentry *get_next_positive_
parent = p->d_parent;
if (!spin_trylock(&parent->d_lock)) {
spin_unlock(&p->d_lock);
- cpu_relax();
+ cpu_chill();
goto relock;
}
spin_unlock(&p->d_lock);
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -19,6 +19,7 @@
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
+#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
@@ -554,7 +555,7 @@ dentry_kill(struct dentry *dentry, int u
relock:
if (unlock_on_failure) {
spin_unlock(&dentry->d_lock);
- cpu_relax();
+ cpu_chill();
}
return dentry; /* try again with same dentry */
}
@@ -2391,7 +2392,7 @@ void d_delete(struct dentry * dentry)
if (dentry->d_lockref.count == 1) {
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
- cpu_relax();
+ cpu_chill();
goto again;
}
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -23,6 +23,7 @@
#include <linux/uaccess.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
+#include <linux/delay.h>
#include "pnode.h"
#include "internal.h"
@@ -317,7 +318,7 @@ int __mnt_want_write(struct vfsmount *m)
smp_mb();
while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
preempt_enable();
- cpu_relax();
+ cpu_chill();
preempt_disable();
}
/*

30
debian/patches/features/all/rt/fs-jbd-pull-plug-when-waiting-for-space.patch vendored Normal file
View File

@ -0,0 +1,30 @@
From: Mike Galbraith <mgalbraith@suse.de>
Date: Wed, 11 Jul 2012 22:05:20 +0000
Subject: fs, jbd: pull your plug when waiting for space
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
With an -rt kernel, and a heavy sync IO load, tasks can jam
up on journal locks without unplugging, which can lead to
terminal IO starvation. Unplug and schedule when waiting for space.
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Theodore Tso <tytso@mit.edu>
Link: http://lkml.kernel.org/r/1341812414.7370.73.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
fs/jbd/checkpoint.c | 2 ++
1 file changed, 2 insertions(+)
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *jou
if (journal->j_flags & JFS_ABORT)
return;
spin_unlock(&journal->j_state_lock);
+ if (current->plug)
+ io_schedule();
mutex_lock(&journal->j_checkpoint_mutex);
/*

101
debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch vendored Normal file
View File

@ -0,0 +1,101 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 18 Mar 2011 10:11:25 +0100
Subject: fs: jbd/jbd2: Make state lock and journal head lock rt safe
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
bit_spin_locks break under RT.
Based on a previous patch from Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
--
include/linux/buffer_head.h | 10 ++++++++++
include/linux/jbd_common.h | 24 ++++++++++++++++++++++++
2 files changed, 34 insertions(+)
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -77,6 +77,11 @@ struct buffer_head {
atomic_t b_count; /* users using this buffer_head */
#ifdef CONFIG_PREEMPT_RT_BASE
spinlock_t b_uptodate_lock;
+#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
+ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
+ spinlock_t b_state_lock;
+ spinlock_t b_journal_head_lock;
+#endif
#endif
};
@@ -108,6 +113,11 @@ static inline void buffer_head_init_lock
{
#ifdef CONFIG_PREEMPT_RT_BASE
spin_lock_init(&bh->b_uptodate_lock);
+#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
+ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
+ spin_lock_init(&bh->b_state_lock);
+ spin_lock_init(&bh->b_journal_head_lock);
+#endif
#endif
}
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -15,32 +15,56 @@ static inline struct journal_head *bh2jh
static inline void jbd_lock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(BH_State, &bh->b_state);
+#else
+ spin_lock(&bh->b_state_lock);
+#endif
}
static inline int jbd_trylock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
return bit_spin_trylock(BH_State, &bh->b_state);
+#else
+ return spin_trylock(&bh->b_state_lock);
+#endif
}
static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
return bit_spin_is_locked(BH_State, &bh->b_state);
+#else
+ return spin_is_locked(&bh->b_state_lock);
+#endif
}
static inline void jbd_unlock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_unlock(BH_State, &bh->b_state);
+#else
+ spin_unlock(&bh->b_state_lock);
+#endif
}
static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(BH_JournalHead, &bh->b_state);
+#else
+ spin_lock(&bh->b_journal_head_lock);
+#endif
}
static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_unlock(BH_JournalHead, &bh->b_state);
+#else
+ spin_unlock(&bh->b_journal_head_lock);
+#endif
}
#endif

31
debian/patches/features/all/rt/fs-namespace-preemption-fix.patch vendored Normal file
View File

@ -0,0 +1,31 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 19 Jul 2009 08:44:27 -0500
Subject: fs: namespace preemption fix
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
On RT we cannot loop with preemption disabled here as
mnt_make_readonly() might have been preempted. We can safely enable
preemption while waiting for MNT_WRITE_HOLD to be cleared. Safe on !RT
as well.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
fs/namespace.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -315,8 +315,11 @@ int __mnt_want_write(struct vfsmount *m)
* incremented count after it has set MNT_WRITE_HOLD.
*/
smp_mb();
- while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
+ while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
+ preempt_enable();
cpu_relax();
+ preempt_disable();
+ }
/*
* After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
* be set to match its requirements. So we must not load that until

60
debian/patches/features/all/rt/fs-ntfs-disable-interrupt-non-rt.patch vendored Normal file
View File

@ -0,0 +1,60 @@
From: Mike Galbraith <efault@gmx.de>
Date: Fri, 3 Jul 2009 08:44:12 -0500
Subject: fs: ntfs: disable interrupt only on !RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
On Sat, 2007-10-27 at 11:44 +0200, Ingo Molnar wrote:
> * Nick Piggin <nickpiggin@yahoo.com.au> wrote:
>
> > > [10138.175796] [<c0105de3>] show_trace+0x12/0x14
> > > [10138.180291] [<c0105dfb>] dump_stack+0x16/0x18
> > > [10138.184769] [<c011609f>] native_smp_call_function_mask+0x138/0x13d
> > > [10138.191117] [<c0117606>] smp_call_function+0x1e/0x24
> > > [10138.196210] [<c012f85c>] on_each_cpu+0x25/0x50
> > > [10138.200807] [<c0115c74>] flush_tlb_all+0x1e/0x20
> > > [10138.205553] [<c016caaf>] kmap_high+0x1b6/0x417
> > > [10138.210118] [<c011ec88>] kmap+0x4d/0x4f
> > > [10138.214102] [<c026a9d8>] ntfs_end_buffer_async_read+0x228/0x2f9
> > > [10138.220163] [<c01a0e9e>] end_bio_bh_io_sync+0x26/0x3f
> > > [10138.225352] [<c01a2b09>] bio_endio+0x42/0x6d
> > > [10138.229769] [<c02c2a08>] __end_that_request_first+0x115/0x4ac
> > > [10138.235682] [<c02c2da7>] end_that_request_chunk+0x8/0xa
> > > [10138.241052] [<c0365943>] ide_end_request+0x55/0x10a
> > > [10138.246058] [<c036dae3>] ide_dma_intr+0x6f/0xac
> > > [10138.250727] [<c0366d83>] ide_intr+0x93/0x1e0
> > > [10138.255125] [<c015afb4>] handle_IRQ_event+0x5c/0xc9
> >
> > Looks like ntfs is kmap()ing from interrupt context. Should be using
> > kmap_atomic instead, I think.
>
> it's not atomic interrupt context but irq thread context - and -rt
> remaps kmap_atomic() to kmap() internally.
Hm. Looking at the change to mm/bounce.c, perhaps I should do this
instead?
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
fs/ntfs/aops.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -144,13 +144,13 @@ static void ntfs_end_buffer_async_read(s
recs = PAGE_CACHE_SIZE / rec_size;
/* Should have been verified before we got here... */
BUG_ON(!recs);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
kaddr = kmap_atomic(page);
for (i = 0; i < recs; i++)
post_read_mst_fixup((NTFS_RECORD*)(kaddr +
i * rec_size), rec_size);
kunmap_atomic(kaddr);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
flush_dcache_page(page);
if (likely(page_uptodate && !PageError(page)))
SetPageUptodate(page);

162
debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch vendored Normal file
View File

@ -0,0 +1,162 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 18 Mar 2011 09:18:52 +0100
Subject: buffer_head: Replace bh_uptodate_lock for -rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Wrap the bit_spin_lock calls into a separate inline and add the RT
replacements with a real spinlock.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
fs/buffer.c | 21 +++++++--------------
fs/ntfs/aops.c | 10 +++-------
include/linux/buffer_head.h | 34 ++++++++++++++++++++++++++++++++++
3 files changed, 44 insertions(+), 21 deletions(-)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -322,8 +322,7 @@ static void end_buffer_async_read(struct
* decide that the page is now completely done.
*/
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ flags = bh_uptodate_lock_irqsave(first);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
@@ -336,8 +335,7 @@ static void end_buffer_async_read(struct
}
tmp = tmp->b_this_page;
} while (tmp != bh);
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ bh_uptodate_unlock_irqrestore(first, flags);
/*
* If none of the buffers had errors and they are all
@@ -349,9 +347,7 @@ static void end_buffer_async_read(struct
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
- return;
+ bh_uptodate_unlock_irqrestore(first, flags);
}
/*
@@ -385,8 +381,7 @@ void end_buffer_async_write(struct buffe
}
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ flags = bh_uptodate_lock_irqsave(first);
clear_buffer_async_write(bh);
unlock_buffer(bh);
@@ -398,15 +393,12 @@ void end_buffer_async_write(struct buffe
}
tmp = tmp->b_this_page;
}
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ bh_uptodate_unlock_irqrestore(first, flags);
end_page_writeback(page);
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
- return;
+ bh_uptodate_unlock_irqrestore(first, flags);
}
EXPORT_SYMBOL(end_buffer_async_write);
@@ -3334,6 +3326,7 @@ struct buffer_head *alloc_buffer_head(gf
struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
if (ret) {
INIT_LIST_HEAD(&ret->b_assoc_buffers);
+ buffer_head_init_locks(ret);
preempt_disable();
__this_cpu_inc(bh_accounting.nr);
recalc_bh_state();
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(s
"0x%llx.", (unsigned long long)bh->b_blocknr);
}
first = page_buffers(page);
- local_irq_save(flags);
- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+ flags = bh_uptodate_lock_irqsave(first);
clear_buffer_async_read(bh);
unlock_buffer(bh);
tmp = bh;
@@ -124,8 +123,7 @@ static void ntfs_end_buffer_async_read(s
}
tmp = tmp->b_this_page;
} while (tmp != bh);
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
+ bh_uptodate_unlock_irqrestore(first, flags);
/*
* If none of the buffers had errors then we can set the page uptodate,
* but we first have to perform the post read mst fixups, if the
@@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(s
unlock_page(page);
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
- return;
+ bh_uptodate_unlock_irqrestore(first, flags);
}
/**
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -75,8 +75,42 @@ struct buffer_head {
struct address_space *b_assoc_map; /* mapping this buffer is
associated with */
atomic_t b_count; /* users using this buffer_head */
+#ifdef CONFIG_PREEMPT_RT_BASE
+ spinlock_t b_uptodate_lock;
+#endif
};
+static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh)
+{
+ unsigned long flags;
+
+#ifndef CONFIG_PREEMPT_RT_BASE
+ local_irq_save(flags);
+ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state);
+#else
+ spin_lock_irqsave(&bh->b_uptodate_lock, flags);
+#endif
+ return flags;
+}
+
+static inline void
+bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags)
+{
+#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state);
+ local_irq_restore(flags);
+#else
+ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags);
+#endif
+}
+
+static inline void buffer_head_init_locks(struct buffer_head *bh)
+{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ spin_lock_init(&bh->b_uptodate_lock);
+#endif
+}
+
/*
* macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
* and buffer_foo() functions.

82
debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch vendored Normal file
View File

@ -0,0 +1,82 @@
Subject: ftrace-migrate-disable-tracing.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 17 Jul 2011 21:56:42 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/ftrace_event.h | 2 ++
kernel/trace/trace.c | 11 +++++++----
kernel/trace/trace_events.c | 1 +
kernel/trace/trace_output.c | 5 +++++
4 files changed, 15 insertions(+), 4 deletions(-)
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -56,6 +56,8 @@ struct trace_entry {
unsigned char flags;
unsigned char preempt_count;
int pid;
+ unsigned short migrate_disable;
+ unsigned short padding;
};
#define FTRACE_MAX_EVENT \
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -439,7 +439,7 @@ int __trace_puts(unsigned long ip, const
local_save_flags(irq_flags);
buffer = global_trace.trace_buffer.buffer;
- event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
+ event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
irq_flags, preempt_count());
if (!event)
return 0;
@@ -1510,6 +1510,8 @@ tracing_generic_entry_update(struct trac
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
+
+ entry->migrate_disable = (tsk) ? tsk->migrate_disable & 0xFF : 0;
}
EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
@@ -2404,9 +2406,10 @@ static void print_lat_help_header(struct
seq_puts(m, "# | / _----=> need-resched \n");
seq_puts(m, "# || / _---=> hardirq/softirq \n");
seq_puts(m, "# ||| / _--=> preempt-depth \n");
- seq_puts(m, "# |||| / delay \n");
- seq_puts(m, "# cmd pid ||||| time | caller \n");
- seq_puts(m, "# \\ / ||||| \\ | / \n");
+ seq_puts(m, "# |||| / _--=> migrate-disable\n");
+ seq_puts(m, "# ||||| / delay \n");
+ seq_puts(m, "# cmd pid |||||| time | caller \n");
+ seq_puts(m, "# \\ / ||||| \\ | / \n");
}
static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -166,6 +166,7 @@ static int trace_define_common_fields(vo
__common_field(unsigned char, flags);
__common_field(unsigned char, preempt_count);
__common_field(int, pid);
+ __common_field(unsigned short, migrate_disable);
return ret;
}
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -635,6 +635,11 @@ int trace_print_lat_fmt(struct trace_seq
else
ret = trace_seq_putc(s, '.');
+ if (entry->migrate_disable)
+ ret = trace_seq_printf(s, "%x", entry->migrate_disable);
+ else
+ ret = trace_seq_putc(s, '.');
+
return ret;
}

115
debian/patches/features/all/rt/futex-requeue-pi-fix.patch vendored Normal file
View File

@ -0,0 +1,115 @@
From: Steven Rostedt <rostedt@goodmis.org>
Subject: futex: Fix bug on when a requeued RT task times out
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Requeue with timeout causes a bug with PREEMPT_RT_FULL.
The bug comes from a timed out condition.
TASK 1 TASK 2
------ ------
futex_wait_requeue_pi()
futex_wait_queue_me()
<timed out>
double_lock_hb();
raw_spin_lock(pi_lock);
if (current->pi_blocked_on) {
} else {
current->pi_blocked_on = PI_WAKE_INPROGRESS;
run_spin_unlock(pi_lock);
spin_lock(hb->lock); <-- blocked!
plist_for_each_entry_safe(this) {
rt_mutex_start_proxy_lock();
task_blocks_on_rt_mutex();
BUG_ON(task->pi_blocked_on)!!!!
The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the
problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to
grab the hb->lock, which it fails to do so. As the hb->lock is a mutex,
it will block and set the "pi_blocked_on" to the hb->lock.
When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails
because the task1's pi_blocked_on is no longer set to that, but instead,
set to the hb->lock.
The fix:
When calling rt_mutex_start_proxy_lock() a check is made to see
if the proxy tasks pi_blocked_on is set. If so, exit out early.
Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies
the proxy task that it is being requeued, and will handle things
appropriately.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/rtmutex.c | 32 +++++++++++++++++++++++++++++++-
kernel/rtmutex_common.h | 1 +
2 files changed, 32 insertions(+), 1 deletion(-)
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -70,7 +70,8 @@ static void fixup_rt_mutex_waiters(struc
static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
{
- return waiter && waiter != PI_WAKEUP_INPROGRESS;
+ return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+ waiter != PI_REQUEUE_INPROGRESS;
}
/*
@@ -1007,6 +1008,35 @@ int rt_mutex_start_proxy_lock(struct rt_
return 1;
}
+#ifdef CONFIG_PREEMPT_RT_FULL
+ /*
+ * In PREEMPT_RT there's an added race.
+ * If the task, that we are about to requeue, times out,
+ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+ * to skip this task. But right after the task sets
+ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+ * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+ * This will replace the PI_WAKEUP_INPROGRESS with the actual
+ * lock that it blocks on. We *must not* place this task
+ * on this proxy lock in that case.
+ *
+ * To prevent this race, we first take the task's pi_lock
+ * and check if it has updated its pi_blocked_on. If it has,
+ * we assume that it woke up and we return -EAGAIN.
+ * Otherwise, we set the task's pi_blocked_on to
+ * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+ * it will know that we are in the process of requeuing it.
+ */
+ raw_spin_lock_irq(&task->pi_lock);
+ if (task->pi_blocked_on) {
+ raw_spin_unlock_irq(&task->pi_lock);
+ raw_spin_unlock(&lock->wait_lock);
+ return -EAGAIN;
+ }
+ task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+ raw_spin_unlock_irq(&task->pi_lock);
+#endif
+
ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
if (ret && !rt_mutex_owner(lock)) {
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -104,6 +104,7 @@ static inline struct task_struct *rt_mut
* PI-futex support (proxy locking functions, etc.):
*/
#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2)
extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,

39
debian/patches/features/all/rt/genirq-Set-the-irq-thread-policy-without-checking-CA.patch vendored Normal file
View File

@ -0,0 +1,39 @@
From 7f095a71d6bc49d7c33ed33ebc26daf4867ee4c8 Mon Sep 17 00:00:00 2001
From: Thomas Pfaff <tpfaff@pcs.com>
Date: Fri, 11 Oct 2013 12:42:49 +0200
Subject: [PATCH] genirq: Set the irq thread policy without checking
CAP_SYS_NICE
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
In commit ee23871389 ("genirq: Set irq thread to RT priority on
creation") we moved the assigment of the thread's priority from the
thread's function into __setup_irq(). That function may run in user
context for instance if the user opens an UART node and then driver
calls requests in the ->open() callback. That user may not have
CAP_SYS_NICE and so the irq thread won't run with the SCHED_OTHER
policy.
This patch uses sched_setscheduler_nocheck() so we omit the CAP_SYS_NICE
check which is otherwise required for the SCHED_OTHER policy.
Cc: Ivo Sieben <meltedpianoman@gmail.com>
Cc: stable@vger.kernel.org
Cc: stable-rt@vger.kernel.org
Signed-off-by: Thomas Pfaff <tpfaff@pcs.com>
[bigeasy: rewrite the changelog]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/irq/manage.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -956,7 +956,7 @@ static int
goto out_mput;
}
- sched_setscheduler(t, SCHED_FIFO, &param);
+ sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
/*
* We keep the reference to the task struct even if

40
debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch vendored Normal file
View File

@ -0,0 +1,40 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:57 -0500
Subject: genirq: disable irqpoll on -rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Creates long latencies for no value
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/irq/spurious.c | 10 ++++++++++
1 file changed, 10 insertions(+)
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -340,6 +340,11 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir
static int __init irqfixup_setup(char *str)
{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ printk(KERN_WARNING "irqfixup boot option not supported "
+ "w/ CONFIG_PREEMPT_RT_BASE\n");
+ return 1;
+#endif
irqfixup = 1;
printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
printk(KERN_WARNING "This may impact system performance.\n");
@@ -352,6 +357,11 @@ module_param(irqfixup, int, 0644);
static int __init irqpoll_setup(char *str)
{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ printk(KERN_WARNING "irqpoll boot option not supported "
+ "w/ CONFIG_PREEMPT_RT_BASE\n");
+ return 1;
+#endif
irqfixup = 2;
printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
"enabled\n");

146
debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch vendored Normal file
View File

@ -0,0 +1,146 @@
From 76666dbbdd40e963e7df84c123fc9aea4a2bcc69 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 21 Aug 2013 17:48:46 +0200
Subject: [PATCH] genirq: do not invoke the affinity callback via a workqueue
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Joe Korty reported, that __irq_set_affinity_locked() schedules a
workqueue while holding a rawlock which results in a might_sleep()
warning.
This patch moves the invokation into a process context so that we only
wakeup() a process while holding the lock.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/interrupt.h | 1
kernel/irq/manage.c | 79 ++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 77 insertions(+), 3 deletions(-)
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -220,6 +220,7 @@ struct irq_affinity_notify {
unsigned int irq;
struct kref kref;
struct work_struct work;
+ struct list_head list;
void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
void (*release)(struct kref *ref);
};
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -164,6 +164,62 @@ int irq_do_set_affinity(struct irq_data
return ret;
}
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void _irq_affinity_notify(struct irq_affinity_notify *notify);
+static struct task_struct *set_affinity_helper;
+static LIST_HEAD(affinity_list);
+static DEFINE_RAW_SPINLOCK(affinity_list_lock);
+
+static int set_affinity_thread(void *unused)
+{
+ while (1) {
+ struct irq_affinity_notify *notify;
+ int empty;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ raw_spin_lock_irq(&affinity_list_lock);
+ empty = list_empty(&affinity_list);
+ raw_spin_unlock_irq(&affinity_list_lock);
+
+ if (empty)
+ schedule();
+ if (kthread_should_stop())
+ break;
+ set_current_state(TASK_RUNNING);
+try_next:
+ notify = NULL;
+
+ raw_spin_lock_irq(&affinity_list_lock);
+ if (!list_empty(&affinity_list)) {
+ notify = list_first_entry(&affinity_list,
+ struct irq_affinity_notify, list);
+ list_del_init(&notify->list);
+ }
+ raw_spin_unlock_irq(&affinity_list_lock);
+
+ if (!notify)
+ continue;
+ _irq_affinity_notify(notify);
+ goto try_next;
+ }
+ return 0;
+}
+
+static void init_helper_thread(void)
+{
+ if (set_affinity_helper)
+ return;
+ set_affinity_helper = kthread_run(set_affinity_thread, NULL,
+ "affinity-cb");
+ WARN_ON(IS_ERR(set_affinity_helper));
+}
+#else
+
+static inline void init_helper_thread(void) { }
+
+#endif
+
int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -182,7 +238,17 @@ int __irq_set_affinity_locked(struct irq
if (desc->affinity_notify) {
kref_get(&desc->affinity_notify->kref);
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+ raw_spin_lock(&affinity_list_lock);
+ if (list_empty(&desc->affinity_notify->list))
+ list_add_tail(&affinity_list,
+ &desc->affinity_notify->list);
+ raw_spin_unlock(&affinity_list_lock);
+ wake_up_process(set_affinity_helper);
+#else
schedule_work(&desc->affinity_notify->work);
+#endif
}
irqd_set(data, IRQD_AFFINITY_SET);
@@ -223,10 +289,8 @@ int irq_set_affinity_hint(unsigned int i
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
-static void irq_affinity_notify(struct work_struct *work)
+static void _irq_affinity_notify(struct irq_affinity_notify *notify)
{
- struct irq_affinity_notify *notify =
- container_of(work, struct irq_affinity_notify, work);
struct irq_desc *desc = irq_to_desc(notify->irq);
cpumask_var_t cpumask;
unsigned long flags;
@@ -248,6 +312,13 @@ static void irq_affinity_notify(struct w
kref_put(&notify->kref, notify->release);
}
+static void irq_affinity_notify(struct work_struct *work)
+{
+ struct irq_affinity_notify *notify =
+ container_of(work, struct irq_affinity_notify, work);
+ _irq_affinity_notify(notify);
+}
+
/**
* irq_set_affinity_notifier - control notification of IRQ affinity changes
* @irq: Interrupt for which to enable/disable notification
@@ -277,6 +348,8 @@ irq_set_affinity_notifier(unsigned int i
notify->irq = irq;
kref_init(&notify->kref);
INIT_WORK(&notify->work, irq_affinity_notify);
+ INIT_LIST_HEAD(&notify->list);
+ init_helper_thread();
}
raw_spin_lock_irqsave(&desc->lock, flags);

47
debian/patches/features/all/rt/genirq-force-threading.patch vendored Normal file
View File

@ -0,0 +1,47 @@
Subject: genirq-force-threading.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 03 Apr 2011 11:57:29 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/interrupt.h | 8 ++++++--
kernel/irq/manage.c | 2 ++
2 files changed, 8 insertions(+), 2 deletions(-)
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -314,9 +314,13 @@ static inline int disable_irq_wake(unsig
#ifdef CONFIG_IRQ_FORCED_THREADING
-extern bool force_irqthreads;
+# ifndef CONFIG_PREEMPT_RT_BASE
+ extern bool force_irqthreads;
+# else
+# define force_irqthreads (true)
+# endif
#else
-#define force_irqthreads (0)
+#define force_irqthreads (false)
#endif
#ifndef __ARCH_SET_SOFTIRQ_PENDING
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -22,6 +22,7 @@
#include "internals.h"
#ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
__read_mostly bool force_irqthreads;
static int __init setup_forced_irqthreads(char *arg)
@@ -30,6 +31,7 @@ static int __init setup_forced_irqthread
return 0;
}
early_param("threadirqs", setup_forced_irqthreads);
+# endif
#endif
/**

21
debian/patches/features/all/rt/genirq-nodebug-shirq.patch vendored Normal file
View File

@ -0,0 +1,21 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 18 Mar 2011 10:22:04 +0100
Subject: genirq: Disable DEBUG_SHIRQ for rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
lib/Kconfig.debug | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -597,7 +597,7 @@ endmenu # "Memory Debugging"
config DEBUG_SHIRQ
bool "Debug shared IRQ handlers"
- depends on DEBUG_KERNEL
+ depends on DEBUG_KERNEL && !PREEMPT_RT_BASE
help
Enable this to generate a spurious interrupt as soon as a shared
interrupt handler is registered, and just before one is deregistered.

60
debian/patches/features/all/rt/hotplug-call-cpu_unplug_begin-a-little-early.patch vendored Normal file
View File

@ -0,0 +1,60 @@
Subject: hotplug: Call cpu_unplug_begin() before DOWN_PREPARE
From: Yong Zhang <yong.zhang0@gmail.com>
Date: Sun, 16 Oct 2011 18:56:44 +0800
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
cpu_unplug_begin() should be called before CPU_DOWN_PREPARE, because
at CPU_DOWN_PREPARE cpu_active is cleared and sched_domain is
rebuilt. Otherwise the 'sync_unplug' thread will be running on the cpu
on which it's created and not bound on the cpu which is about to go
down.
I found that by an incorrect warning on smp_processor_id() called by
sync_unplug/1, and trace shows below:
(echo 1 > /sys/device/system/cpu/cpu1/online)
bash-1664 [000] 83.136620: _cpu_down: Bind sync_unplug to cpu 1
bash-1664 [000] 83.136623: sched_wait_task: comm=sync_unplug/1 pid=1724 prio=120
bash-1664 [000] 83.136624: _cpu_down: Wake sync_unplug
bash-1664 [000] 83.136629: sched_wakeup: comm=sync_unplug/1 pid=1724 prio=120 success=1 target_cpu=000
Wants to be folded back....
Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Link: http://lkml.kernel.org/r/1318762607-2261-3-git-send-email-yong.zhang0@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/cpu.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -408,22 +408,20 @@ static int __ref _cpu_down(unsigned int
return -EBUSY;
}
- err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
+ cpu_hotplug_begin();
+ err = cpu_unplug_begin(cpu);
if (err) {
- nr_calls--;
- __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
- printk("%s: attempt to take down CPU %u failed\n",
- __func__, cpu);
+ printk("cpu_unplug_begin(%d) failed\n", cpu);
goto out_cancel;
}
- cpu_hotplug_begin();
- err = cpu_unplug_begin(cpu);
+ err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
if (err) {
nr_calls--;
__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
- printk("cpu_unplug_begin(%d) failed\n", cpu);
- goto out_cancel;
+ printk("%s: attempt to take down CPU %u failed\n",
+ __func__, cpu);
+ goto out_release;
}
smpboot_park_threads(cpu);

208
debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch vendored Normal file
View File

@ -0,0 +1,208 @@
Subject: hotplug: Lightweight get online cpus
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Jun 2011 12:36:06 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
get_online_cpus() is a heavy weight function which involves a global
mutex. migrate_disable() wants a simpler construct which prevents only
a CPU from going doing while a task is in a migrate disabled section.
Implement a per cpu lockless mechanism, which serializes only in the
real unplug case on a global mutex. That serialization affects only
tasks on the cpu which should be brought down.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/cpu.h | 4 +
kernel/cpu.c | 126 ++++++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 127 insertions(+), 3 deletions(-)
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -179,6 +179,8 @@ extern void get_online_cpus(void);
extern void put_online_cpus(void);
extern void cpu_hotplug_disable(void);
extern void cpu_hotplug_enable(void);
+extern void pin_current_cpu(void);
+extern void unpin_current_cpu(void);
#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
@@ -206,6 +208,8 @@ static inline void cpu_hotplug_done(void
#define put_online_cpus() do { } while (0)
#define cpu_hotplug_disable() do { } while (0)
#define cpu_hotplug_enable() do { } while (0)
+static inline void pin_current_cpu(void) { }
+static inline void unpin_current_cpu(void) { }
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -63,6 +63,101 @@ static struct {
.refcount = 0,
};
+struct hotplug_pcp {
+ struct task_struct *unplug;
+ int refcount;
+ struct completion synced;
+};
+
+static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
+
+/**
+ * pin_current_cpu - Prevent the current cpu from being unplugged
+ *
+ * Lightweight version of get_online_cpus() to prevent cpu from being
+ * unplugged when code runs in a migration disabled region.
+ *
+ * Must be called with preemption disabled (preempt_count = 1)!
+ */
+void pin_current_cpu(void)
+{
+ struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp);
+
+retry:
+ if (!hp->unplug || hp->refcount || preempt_count() > 1 ||
+ hp->unplug == current) {
+ hp->refcount++;
+ return;
+ }
+ preempt_enable();
+ mutex_lock(&cpu_hotplug.lock);
+ mutex_unlock(&cpu_hotplug.lock);
+ preempt_disable();
+ goto retry;
+}
+
+/**
+ * unpin_current_cpu - Allow unplug of current cpu
+ *
+ * Must be called with preemption or interrupts disabled!
+ */
+void unpin_current_cpu(void)
+{
+ struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp);
+
+ WARN_ON(hp->refcount <= 0);
+
+ /* This is safe. sync_unplug_thread is pinned to this cpu */
+ if (!--hp->refcount && hp->unplug && hp->unplug != current)
+ wake_up_process(hp->unplug);
+}
+
+/*
+ * FIXME: Is this really correct under all circumstances ?
+ */
+static int sync_unplug_thread(void *data)
+{
+ struct hotplug_pcp *hp = data;
+
+ preempt_disable();
+ hp->unplug = current;
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ while (hp->refcount) {
+ schedule_preempt_disabled();
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ }
+ set_current_state(TASK_RUNNING);
+ preempt_enable();
+ complete(&hp->synced);
+ return 0;
+}
+
+/*
+ * Start the sync_unplug_thread on the target cpu and wait for it to
+ * complete.
+ */
+static int cpu_unplug_begin(unsigned int cpu)
+{
+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+ struct task_struct *tsk;
+
+ init_completion(&hp->synced);
+ tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu);
+ if (IS_ERR(tsk))
+ return (PTR_ERR(tsk));
+ kthread_bind(tsk, cpu);
+ wake_up_process(tsk);
+ wait_for_completion(&hp->synced);
+ return 0;
+}
+
+static void cpu_unplug_done(unsigned int cpu)
+{
+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+ hp->unplug = NULL;
+}
+
void get_online_cpus(void)
{
might_sleep();
@@ -282,13 +377,14 @@ static int __ref take_cpu_down(void *_pa
/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
{
- int err, nr_calls = 0;
+ int mycpu, err, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
struct take_cpu_down_param tcd_param = {
.mod = mod,
.hcpu = hcpu,
};
+ cpumask_var_t cpumask;
if (num_online_cpus() == 1)
return -EBUSY;
@@ -296,7 +392,20 @@ static int __ref _cpu_down(unsigned int
if (!cpu_online(cpu))
return -EINVAL;
- cpu_hotplug_begin();
+ /* Move the downtaker off the unplug cpu */
+ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+ return -ENOMEM;
+ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
+ set_cpus_allowed_ptr(current, cpumask);
+ free_cpumask_var(cpumask);
+ preempt_disable();
+ mycpu = smp_processor_id();
+ if (mycpu == cpu) {
+ printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
+ preempt_enable();
+ return -EBUSY;
+ }
+ preempt_enable();
err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
if (err) {
@@ -304,7 +413,16 @@ static int __ref _cpu_down(unsigned int
__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
printk("%s: attempt to take down CPU %u failed\n",
__func__, cpu);
- goto out_release;
+ goto out_cancel;
+ }
+
+ cpu_hotplug_begin();
+ err = cpu_unplug_begin(cpu);
+ if (err) {
+ nr_calls--;
+ __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
+ printk("cpu_unplug_begin(%d) failed\n", cpu);
+ goto out_cancel;
}
smpboot_park_threads(cpu);
@@ -336,6 +454,8 @@ static int __ref _cpu_down(unsigned int
check_for_tasks(cpu);
out_release:
+ cpu_unplug_done(cpu);
+out_cancel:
cpu_hotplug_done();
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);

25
debian/patches/features/all/rt/hotplug-sync_unplug-no-27-5cn-27-in-task-name.patch vendored Normal file
View File

@ -0,0 +1,25 @@
Subject: hotplug: sync_unplug: No "\n" in task name
From: Yong Zhang <yong.zhang0@gmail.com>
Date: Sun, 16 Oct 2011 18:56:43 +0800
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Otherwise the output will look a little odd.
Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Link: http://lkml.kernel.org/r/1318762607-2261-2-git-send-email-yong.zhang0@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/cpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -142,7 +142,7 @@ static int cpu_unplug_begin(unsigned int
struct task_struct *tsk;
init_completion(&hp->synced);
- tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d\n", cpu);
+ tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
if (IS_ERR(tsk))
return (PTR_ERR(tsk));
kthread_bind(tsk, cpu);

37
debian/patches/features/all/rt/hotplug-use-migrate-disable.patch vendored Normal file
View File

@ -0,0 +1,37 @@
Subject: hotplug-use-migrate-disable.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 17 Jul 2011 19:35:29 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/cpu.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -400,14 +400,13 @@ static int __ref _cpu_down(unsigned int
cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
set_cpus_allowed_ptr(current, cpumask);
free_cpumask_var(cpumask);
- preempt_disable();
+ migrate_disable();
mycpu = smp_processor_id();
if (mycpu == cpu) {
printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
- preempt_enable();
+ migrate_enable();
return -EBUSY;
}
- preempt_enable();
err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
if (err) {
@@ -458,6 +457,7 @@ static int __ref _cpu_down(unsigned int
out_release:
cpu_unplug_done(cpu);
out_cancel:
+ migrate_enable();
cpu_hotplug_done();
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);

119
debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch vendored Normal file
View File

@ -0,0 +1,119 @@
From 180cdb93d796bf52c919f5e3df30af83aa6d46ca Mon Sep 17 00:00:00 2001
From: Yang Shi <yang.shi@windriver.com>
Date: Mon, 16 Sep 2013 14:09:19 -0700
Subject: [PATCH] hrtimer: Move schedule_work call to helper thread
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
When run ltp leapsec_timer test, the following call trace is caught:
BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1
Preemption disabled at:[<ffffffff810857f3>] cpu_startup_entry+0x133/0x310
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.10-rt3 #2
Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010
ffffffff81c2f800 ffff880076843e40 ffffffff8169918d ffff880076843e58
ffffffff8106db31 ffff88007684b4a0 ffff880076843e70 ffffffff8169d9c0
ffff88007684b4a0 ffff880076843eb0 ffffffff81059da1 0000001876851200
Call Trace:
<IRQ> [<ffffffff8169918d>] dump_stack+0x19/0x1b
[<ffffffff8106db31>] __might_sleep+0xf1/0x170
[<ffffffff8169d9c0>] rt_spin_lock+0x20/0x50
[<ffffffff81059da1>] queue_work_on+0x61/0x100
[<ffffffff81065aa1>] clock_was_set_delayed+0x21/0x30
[<ffffffff810883be>] do_timer+0x40e/0x660
[<ffffffff8108f487>] tick_do_update_jiffies64+0xf7/0x140
[<ffffffff8108fe42>] tick_check_idle+0x92/0xc0
[<ffffffff81044327>] irq_enter+0x57/0x70
[<ffffffff816a040e>] smp_apic_timer_interrupt+0x3e/0x9b
[<ffffffff8169f80a>] apic_timer_interrupt+0x6a/0x70
<EOI> [<ffffffff8155ea1c>] ? cpuidle_enter_state+0x4c/0xc0
[<ffffffff8155eb68>] cpuidle_idle_call+0xd8/0x2d0
[<ffffffff8100b59e>] arch_cpu_idle+0xe/0x30
[<ffffffff8108585e>] cpu_startup_entry+0x19e/0x310
[<ffffffff8168efa2>] start_secondary+0x1ad/0x1b0
The clock_was_set_delayed is called in hard IRQ handler (timer interrupt), which
calls schedule_work.
Under PREEMPT_RT_FULL, schedule_work calls spinlocks which could sleep, so it's
not safe to call schedule_work in interrupt context.
Reference upstream commit b68d61c705ef02384c0538b8d9374545097899ca
(rt,ntp: Move call to schedule_delayed_work() to helper thread)
from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git, which
makes a similar change.
add a helper thread which does the call to schedule_work and wake up that
thread instead of calling schedule_work directly.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Yang Shi <yang.shi@windriver.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/hrtimer.c | 40 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -47,6 +47,7 @@
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/timer.h>
+#include <linux/kthread.h>
#include <linux/freezer.h>
#include <asm/uaccess.h>
@@ -741,6 +742,44 @@ static void clock_was_set_work(struct wo
static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * RT can not call schedule_work from real interrupt context.
+ * Need to make a thread to do the real work.
+ */
+static struct task_struct *clock_set_delay_thread;
+static bool do_clock_set_delay;
+
+static int run_clock_set_delay(void *ignore)
+{
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (do_clock_set_delay) {
+ do_clock_set_delay = false;
+ schedule_work(&hrtimer_work);
+ }
+ schedule();
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+void clock_was_set_delayed(void)
+{
+ do_clock_set_delay = true;
+ /* Make visible before waking up process */
+ smp_wmb();
+ wake_up_process(clock_set_delay_thread);
+}
+
+static __init int create_clock_set_delay_thread(void)
+{
+ clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd");
+ BUG_ON(!clock_set_delay_thread);
+ return 0;
+}
+early_initcall(create_clock_set_delay_thread);
+#else /* PREEMPT_RT_FULL */
/*
* Called from timekeeping and resume code to reprogramm the hrtimer
* interrupt device on all cpus.
@@ -749,6 +788,7 @@ void clock_was_set_delayed(void)
{
schedule_work(&hrtimer_work);
}
+#endif
#else

453
debian/patches/features/all/rt/hrtimer-fixup-hrtimer-callback-changes-for-preempt-r.patch vendored Normal file
View File

@ -0,0 +1,453 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 3 Jul 2009 08:44:31 -0500
Subject: hrtimer: fixup hrtimer callback changes for preempt-rt
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
In preempt-rt we can not call the callbacks which take sleeping locks
from the timer interrupt context.
Bring back the softirq split for now, until we fixed the signal
delivery problem for real.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
include/linux/hrtimer.h | 3
kernel/hrtimer.c | 216 ++++++++++++++++++++++++++++++++++++++++-------
kernel/sched/core.c | 1
kernel/sched/rt.c | 1
kernel/time/tick-sched.c | 1
kernel/watchdog.c | 1
6 files changed, 195 insertions(+), 28 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -111,6 +111,8 @@ struct hrtimer {
enum hrtimer_restart (*function)(struct hrtimer *);
struct hrtimer_clock_base *base;
unsigned long state;
+ struct list_head cb_entry;
+ int irqsafe;
#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
ktime_t praecox;
#endif
@@ -150,6 +152,7 @@ struct hrtimer_clock_base {
int index;
clockid_t clockid;
struct timerqueue_head active;
+ struct list_head expired;
ktime_t resolution;
ktime_t (*get_time)(void);
ktime_t softirq_time;
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -608,8 +608,7 @@ static int hrtimer_reprogram(struct hrti
* When the callback is running, we do not reprogram the clock event
* device. The timer callback is either running on a different CPU or
* the callback is executed in the hrtimer_interrupt context. The
- * reprogramming is handled either by the softirq, which called the
- * callback or at the end of the hrtimer_interrupt.
+ * reprogramming is handled at the end of the hrtimer_interrupt.
*/
if (hrtimer_callback_running(timer))
return 0;
@@ -644,6 +643,9 @@ static int hrtimer_reprogram(struct hrti
return res;
}
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now);
+static int hrtimer_rt_defer(struct hrtimer *timer);
+
/*
* Initialize the high resolution related parts of cpu_base
*/
@@ -660,9 +662,18 @@ static inline void hrtimer_init_hres(str
* and expiry check is done in the hrtimer_interrupt or in the softirq.
*/
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
- return base->cpu_base->hres_active && hrtimer_reprogram(timer, base);
+ if (!(base->cpu_base->hres_active && hrtimer_reprogram(timer, base)))
+ return 0;
+ if (!wakeup)
+ return -ETIME;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ if (!hrtimer_rt_defer(timer))
+ return -ETIME;
+#endif
+ return 1;
}
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
@@ -747,12 +758,18 @@ static inline int hrtimer_switch_to_hres
static inline void
hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void retrigger_next_event(void *arg) { }
+static inline int hrtimer_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ return 0;
+}
#endif /* CONFIG_HIGH_RES_TIMERS */
@@ -888,9 +905,9 @@ void hrtimer_wait_for_timer(const struct
{
struct hrtimer_clock_base *base = timer->base;
- if (base && base->cpu_base && !hrtimer_hres_active(base->cpu_base))
+ if (base && base->cpu_base && !timer->irqsafe)
wait_event(base->cpu_base->wait,
- !(timer->state & HRTIMER_STATE_CALLBACK));
+ !(timer->state & HRTIMER_STATE_CALLBACK));
}
#else
@@ -940,6 +957,11 @@ static void __remove_hrtimer(struct hrti
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
+ if (unlikely(!list_empty(&timer->cb_entry))) {
+ list_del_init(&timer->cb_entry);
+ goto out;
+ }
+
next_timer = timerqueue_getnext(&base->active);
timerqueue_del(&base->active, &timer->node);
if (&timer->node == next_timer) {
@@ -1047,9 +1069,19 @@ int __hrtimer_start_range_ns(struct hrti
*
* XXX send_remote_softirq() ?
*/
- if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
- && hrtimer_enqueue_reprogram(timer, new_base)) {
- if (wakeup) {
+ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) {
+ ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup);
+ if (ret < 0) {
+ /*
+ * In case we failed to reprogram the timer (mostly
+ * because out current timer is already elapsed),
+ * remove it again and report a failure. This avoids
+ * stale base->first entries.
+ */
+ debug_deactivate(timer);
+ __remove_hrtimer(timer, new_base,
+ timer->state & HRTIMER_STATE_CALLBACK, 0);
+ } else if (ret > 0) {
/*
* We need to drop cpu_base->lock to avoid a
* lock ordering issue vs. rq->lock.
@@ -1057,9 +1089,7 @@ int __hrtimer_start_range_ns(struct hrti
raw_spin_unlock(&new_base->cpu_base->lock);
raise_softirq_irqoff(HRTIMER_SOFTIRQ);
local_irq_restore(flags);
- return ret;
- } else {
- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ return 0;
}
}
@@ -1228,6 +1258,7 @@ static void __hrtimer_init(struct hrtime
base = hrtimer_clockid_to_base(clock_id);
timer->base = &cpu_base->clock_base[base];
+ INIT_LIST_HEAD(&timer->cb_entry);
timerqueue_init(&timer->node);
#ifdef CONFIG_TIMER_STATS
@@ -1311,10 +1342,128 @@ static void __run_hrtimer(struct hrtimer
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
-#ifdef CONFIG_HIGH_RES_TIMERS
-
static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ /*
+ * Note, we clear the callback flag before we requeue the
+ * timer otherwise we trigger the callback_running() check
+ * in hrtimer_reprogram().
+ */
+ timer->state &= ~HRTIMER_STATE_CALLBACK;
+
+ if (restart != HRTIMER_NORESTART) {
+ BUG_ON(hrtimer_active(timer));
+ /*
+ * Enqueue the timer, if it's the leftmost timer then
+ * we need to reprogram it.
+ */
+ if (!enqueue_hrtimer(timer, base))
+ return;
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+ }
+#else
+ if (base->cpu_base->hres_active &&
+ hrtimer_reprogram(timer, base))
+ goto requeue;
+
+ } else if (hrtimer_active(timer)) {
+ /*
+ * If the timer was rearmed on another CPU, reprogram
+ * the event device.
+ */
+ if (&timer->node == base->active.next &&
+ base->cpu_base->hres_active &&
+ hrtimer_reprogram(timer, base))
+ goto requeue;
+ }
+ return;
+
+requeue:
+ /*
+ * Timer is expired. Thus move it from tree to pending list
+ * again.
+ */
+ __remove_hrtimer(timer, base, timer->state, 0);
+ list_add_tail(&timer->cb_entry, &base->expired);
+#endif
+}
+
+/*
+ * The changes in mainline which removed the callback modes from
+ * hrtimer are not yet working with -rt. The non wakeup_process()
+ * based callbacks which involve sleeping locks need to be treated
+ * seperately.
+ */
+static void hrtimer_rt_run_pending(void)
+{
+ enum hrtimer_restart (*fn)(struct hrtimer *);
+ struct hrtimer_cpu_base *cpu_base;
+ struct hrtimer_clock_base *base;
+ struct hrtimer *timer;
+ int index, restart;
+
+ local_irq_disable();
+ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());
+
+ raw_spin_lock(&cpu_base->lock);
+
+ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+ base = &cpu_base->clock_base[index];
+
+ while (!list_empty(&base->expired)) {
+ timer = list_first_entry(&base->expired,
+ struct hrtimer, cb_entry);
+
+ /*
+ * Same as the above __run_hrtimer function
+ * just we run with interrupts enabled.
+ */
+ debug_hrtimer_deactivate(timer);
+ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+ timer_stats_account_hrtimer(timer);
+ fn = timer->function;
+
+ raw_spin_unlock_irq(&cpu_base->lock);
+ restart = fn(timer);
+ raw_spin_lock_irq(&cpu_base->lock);
+
+ hrtimer_rt_reprogram(restart, timer, base);
+ }
+ }
+
+ raw_spin_unlock_irq(&cpu_base->lock);
+
+ wake_up_timer_waiters(cpu_base);
+}
+
+static int hrtimer_rt_defer(struct hrtimer *timer)
+{
+ if (timer->irqsafe)
+ return 0;
+
+ __remove_hrtimer(timer, timer->base, timer->state, 0);
+ list_add_tail(&timer->cb_entry, &timer->base->expired);
+ return 1;
+}
+
+#else
+
+static inline void hrtimer_rt_run_pending(void)
+{
+ hrtimer_peek_ahead_timers();
+}
+
+static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
+
+#endif
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
/*
* High resolution timer interrupt
* Called with interrupts disabled
@@ -1323,7 +1472,7 @@ void hrtimer_interrupt(struct clock_even
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
- int i, retries = 0;
+ int i, retries = 0, raise = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
@@ -1392,7 +1541,10 @@ void hrtimer_interrupt(struct clock_even
break;
}
- __run_hrtimer(timer, &basenow);
+ if (!hrtimer_rt_defer(timer))
+ __run_hrtimer(timer, &basenow);
+ else
+ raise = 1;
}
}
@@ -1407,6 +1559,10 @@ void hrtimer_interrupt(struct clock_even
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
+
+ if (raise)
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+
return;
}
@@ -1486,18 +1642,18 @@ void hrtimer_peek_ahead_timers(void)
__hrtimer_peek_ahead_timers();
local_irq_restore(flags);
}
-
-static void run_hrtimer_softirq(struct softirq_action *h)
-{
- hrtimer_peek_ahead_timers();
-}
-
#else /* CONFIG_HIGH_RES_TIMERS */
static inline void __hrtimer_peek_ahead_timers(void) { }
#endif /* !CONFIG_HIGH_RES_TIMERS */
+
+static void run_hrtimer_softirq(struct softirq_action *h)
+{
+ hrtimer_rt_run_pending();
+}
+
/*
* Called from timer softirq every jiffy, expire hrtimers:
*
@@ -1530,7 +1686,7 @@ void hrtimer_run_queues(void)
struct timerqueue_node *node;
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
- int index, gettime = 1;
+ int index, gettime = 1, raise = 0;
if (hrtimer_hres_active())
return;
@@ -1555,12 +1711,16 @@ void hrtimer_run_queues(void)
hrtimer_get_expires_tv64(timer))
break;
- __run_hrtimer(timer, &base->softirq_time);
+ if (!hrtimer_rt_defer(timer))
+ __run_hrtimer(timer, &base->softirq_time);
+ else
+ raise = 1;
}
raw_spin_unlock(&cpu_base->lock);
}
- wake_up_timer_waiters(cpu_base);
+ if (raise)
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}
/*
@@ -1582,6 +1742,7 @@ static enum hrtimer_restart hrtimer_wake
void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
{
sl->timer.function = hrtimer_wakeup;
+ sl->timer.irqsafe = 1;
sl->task = task;
}
EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
@@ -1718,6 +1879,7 @@ static void init_hrtimers_cpu(int cpu)
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
cpu_base->clock_base[i].cpu_base = cpu_base;
timerqueue_init_head(&cpu_base->clock_base[i].active);
+ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
}
hrtimer_init_hres(cpu_base);
@@ -1836,9 +1998,7 @@ void __init hrtimers_init(void)
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
}
/**
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -491,6 +491,7 @@ static void init_rq_hrtick(struct rq *rq
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rq->hrtick_timer.function = hrtick;
+ rq->hrtick_timer.irqsafe = 1;
}
#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -43,6 +43,7 @@ void init_rt_bandwidth(struct rt_bandwid
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ rt_b->rt_period_timer.irqsafe = 1;
rt_b->rt_period_timer.function = sched_rt_period_timer;
}
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1119,6 +1119,7 @@ void tick_setup_sched_timer(void)
* Emulate tick processing via per-CPU hrtimers:
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ ts->sched_timer.irqsafe = 1;
ts->sched_timer.function = tick_sched_timer;
/* Get the next period (per cpu) */
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -357,6 +357,7 @@ static void watchdog_enable(unsigned int
/* kick off the timer for the hardlockup detector */
hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hrtimer->function = watchdog_timer_fn;
+ hrtimer->irqsafe = 1;
/* Enable the perf event */
watchdog_nmi_enable(cpu);

38
debian/patches/features/all/rt/hrtimer-raise-softirq-if-hrtimer-irq-stalled.patch vendored Normal file
View File

@ -0,0 +1,38 @@
Subject: hrtimer: Raise softirq if hrtimer irq stalled
From: Watanabe <shunsuke.watanabe@tel.com>
Date: Sun, 28 Oct 2012 11:13:44 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
When the hrtimer stall detection hits the softirq is not raised.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
kernel/hrtimer.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1559,11 +1559,7 @@ void hrtimer_interrupt(struct clock_even
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
-
- if (raise)
- raise_softirq_irqoff(HRTIMER_SOFTIRQ);
-
- return;
+ goto out;
}
/*
@@ -1607,6 +1603,9 @@ void hrtimer_interrupt(struct clock_even
tick_program_event(expires_next, 1);
printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
ktime_to_ns(delta));
+out:
+ if (raise)
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}
/*

196
debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch vendored Normal file
View File

@ -0,0 +1,196 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:34 -0500
Subject: hrtimers: prepare full preemption
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Make cancellation of a running callback in softirq context safe
against preemption.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/hrtimer.h | 10 ++++++++++
kernel/hrtimer.c | 33 ++++++++++++++++++++++++++++++++-
kernel/itimer.c | 1 +
kernel/posix-timers.c | 33 +++++++++++++++++++++++++++++++++
4 files changed, 76 insertions(+), 1 deletion(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -193,6 +193,9 @@ struct hrtimer_cpu_base {
unsigned long nr_hangs;
ktime_t max_hang_time;
#endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+ wait_queue_head_t wait;
+#endif
struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
};
@@ -388,6 +391,13 @@ static inline int hrtimer_restart(struct
return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
+/* Softirq preemption could deadlock timer removal */
+#ifdef CONFIG_PREEMPT_RT_BASE
+ extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
+#else
+# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0)
+#endif
+
/* Query timers: */
extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -871,6 +871,32 @@ u64 hrtimer_forward(struct hrtimer *time
}
EXPORT_SYMBOL_GPL(hrtimer_forward);
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define wake_up_timer_waiters(b) wake_up(&(b)->wait)
+
+/**
+ * hrtimer_wait_for_timer - Wait for a running timer
+ *
+ * @timer: timer to wait for
+ *
+ * The function waits in case the timers callback function is
+ * currently executed on the waitqueue of the timer base. The
+ * waitqueue is woken up after the timer callback function has
+ * finished execution.
+ */
+void hrtimer_wait_for_timer(const struct hrtimer *timer)
+{
+ struct hrtimer_clock_base *base = timer->base;
+
+ if (base && base->cpu_base && !hrtimer_hres_active(base->cpu_base))
+ wait_event(base->cpu_base->wait,
+ !(timer->state & HRTIMER_STATE_CALLBACK));
+}
+
+#else
+# define wake_up_timer_waiters(b) do { } while (0)
+#endif
+
/*
* enqueue_hrtimer - internal function to (re)start a timer
*
@@ -1123,7 +1149,7 @@ int hrtimer_cancel(struct hrtimer *timer
if (ret >= 0)
return ret;
- cpu_relax();
+ hrtimer_wait_for_timer(timer);
}
}
EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1533,6 +1559,8 @@ void hrtimer_run_queues(void)
}
raw_spin_unlock(&cpu_base->lock);
}
+
+ wake_up_timer_waiters(cpu_base);
}
/*
@@ -1693,6 +1721,9 @@ static void init_hrtimers_cpu(int cpu)
}
hrtimer_init_hres(cpu_base);
+#ifdef CONFIG_PREEMPT_RT_BASE
+ init_waitqueue_head(&cpu_base->wait);
+#endif
}
#ifdef CONFIG_HOTPLUG_CPU
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -213,6 +213,7 @@ int do_setitimer(int which, struct itime
/* We are sharing ->siglock with it_real_fn() */
if (hrtimer_try_to_cancel(timer) < 0) {
spin_unlock_irq(&tsk->sighand->siglock);
+ hrtimer_wait_for_timer(&tsk->signal->real_timer);
goto again;
}
expires = timeval_to_ktime(value->it_value);
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -818,6 +818,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_
return overrun;
}
+/*
+ * Protected by RCU!
+ */
+static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+ if (kc->timer_set == common_timer_set)
+ hrtimer_wait_for_timer(&timr->it.real.timer);
+ else
+ /* FIXME: Whacky hack for posix-cpu-timers */
+ schedule_timeout(1);
+#endif
+}
+
/* Set a POSIX.1b interval timer. */
/* timr->it_lock is taken. */
static int
@@ -895,6 +909,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t,
if (!timr)
return -EINVAL;
+ rcu_read_lock();
kc = clockid_to_kclock(timr->it_clock);
if (WARN_ON_ONCE(!kc || !kc->timer_set))
error = -EINVAL;
@@ -903,9 +918,12 @@ SYSCALL_DEFINE4(timer_settime, timer_t,
unlock_timer(timr, flag);
if (error == TIMER_RETRY) {
+ timer_wait_for_callback(kc, timr);
rtn = NULL; // We already got the old time...
+ rcu_read_unlock();
goto retry;
}
+ rcu_read_unlock();
if (old_setting && !error &&
copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
@@ -943,10 +961,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, t
if (!timer)
return -EINVAL;
+ rcu_read_lock();
if (timer_delete_hook(timer) == TIMER_RETRY) {
unlock_timer(timer, flags);
+ timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+ timer);
+ rcu_read_unlock();
goto retry_delete;
}
+ rcu_read_unlock();
spin_lock(&current->sighand->siglock);
list_del(&timer->list);
@@ -972,8 +995,18 @@ static void itimer_delete(struct k_itime
retry_delete:
spin_lock_irqsave(&timer->it_lock, flags);
+ /* On RT we can race with a deletion */
+ if (!timer->it_signal) {
+ unlock_timer(timer, flags);
+ return;
+ }
+
if (timer_delete_hook(timer) == TIMER_RETRY) {
+ rcu_read_lock();
unlock_timer(timer, flags);
+ timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+ timer);
+ rcu_read_unlock();
goto retry_delete;
}
list_del(&timer->list);

27
debian/patches/features/all/rt/hwlat-detector-Don-t-ignore-threshold-module-paramet.patch vendored Normal file
View File

@ -0,0 +1,27 @@
From c19bf3baaa55918486b868ab17aae0c0c220e51f Mon Sep 17 00:00:00 2001
From: Mike Galbraith <bitbucket@online.de>
Date: Fri, 30 Aug 2013 07:57:25 +0200
Subject: [PATCH] hwlat-detector: Don't ignore threshold module parameter
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
If the user specified a threshold at module load time, use it.
Cc: stable-rt@vger.kernel.org
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/misc/hwlat_detector.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/misc/hwlat_detector.c
+++ b/drivers/misc/hwlat_detector.c
@@ -413,7 +413,7 @@ static int init_stats(void)
goto out;
__reset_stats();
- data.threshold = DEFAULT_LAT_THRESHOLD; /* threshold us */
+ data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */
data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */
data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */

128
debian/patches/features/all/rt/hwlat-detector-Update-hwlat_detector-to-add-outer-lo.patch vendored Normal file
View File

@ -0,0 +1,128 @@
From 7a036d4dfcf3f2d3247ff7f739284f4b5056bdcb Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 19 Aug 2013 17:33:25 -0400
Subject: [PATCH 1/3] hwlat-detector: Update hwlat_detector to add outer loop
detection
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The hwlat_detector reads two timestamps in a row, then reports any
gap between those calls. The problem is, it misses everything between
the second reading of the time stamp to the first reading of the time stamp
in the next loop. That's were most of the time is spent, which means,
chances are likely that it will miss all hardware latencies. This
defeats the purpose.
By also testing the first time stamp from the previous loop second
time stamp (the outer loop), we are more likely to find a latency.
Setting the threshold to 1, here's what the report now looks like:
1347415723.0232202770 0 2
1347415725.0234202822 0 2
1347415727.0236202875 0 2
1347415729.0238202928 0 2
1347415731.0240202980 0 2
1347415734.0243203061 0 2
1347415736.0245203113 0 2
1347415738.0247203166 2 0
1347415740.0249203219 0 3
1347415742.0251203272 0 3
1347415743.0252203299 0 3
1347415745.0254203351 0 2
1347415747.0256203404 0 2
1347415749.0258203457 0 2
1347415751.0260203510 0 2
1347415754.0263203589 0 2
1347415756.0265203642 0 2
1347415758.0267203695 0 2
1347415760.0269203748 0 2
1347415762.0271203801 0 2
1347415764.0273203853 2 0
There's some hardware latency that takes 2 microseconds to run.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/misc/hwlat_detector.c | 32 ++++++++++++++++++++++++++------
1 file changed, 26 insertions(+), 6 deletions(-)
--- a/drivers/misc/hwlat_detector.c
+++ b/drivers/misc/hwlat_detector.c
@@ -143,6 +143,7 @@ static void detector_exit(void);
struct sample {
u64 seqnum; /* unique sequence */
u64 duration; /* ktime delta */
+ u64 outer_duration; /* ktime delta (outer loop) */
struct timespec timestamp; /* wall time */
unsigned long lost;
};
@@ -219,11 +220,13 @@ static struct sample *buffer_get_sample(
*/
static int get_sample(void *unused)
{
- ktime_t start, t1, t2;
+ ktime_t start, t1, t2, last_t2;
s64 diff, total = 0;
u64 sample = 0;
+ u64 outer_sample = 0;
int ret = 1;
+ last_t2.tv64 = 0;
start = ktime_get(); /* start timestamp */
do {
@@ -231,7 +234,22 @@ static int get_sample(void *unused)
t1 = ktime_get(); /* we'll look for a discontinuity */
t2 = ktime_get();
+ if (last_t2.tv64) {
+ /* Check the delta from the outer loop (t2 to next t1) */
+ diff = ktime_to_us(ktime_sub(t1, last_t2));
+ /* This shouldn't happen */
+ if (diff < 0) {
+ printk(KERN_ERR BANNER "time running backwards\n");
+ goto out;
+ }
+ if (diff > outer_sample)
+ outer_sample = diff;
+ }
+ last_t2 = t2;
+
total = ktime_to_us(ktime_sub(t2, start)); /* sample width */
+
+ /* This checks the inner loop (t1 to t2) */
diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */
/* This shouldn't happen */
@@ -246,12 +264,13 @@ static int get_sample(void *unused)
} while (total <= data.sample_width);
/* If we exceed the threshold value, we have found a hardware latency */
- if (sample > data.threshold) {
+ if (sample > data.threshold || outer_sample > data.threshold) {
struct sample s;
data.count++;
s.seqnum = data.count;
s.duration = sample;
+ s.outer_duration = outer_sample;
s.timestamp = CURRENT_TIME;
__buffer_add_sample(&s);
@@ -738,10 +757,11 @@ static ssize_t debug_sample_fread(struct
}
}
- len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\n",
- sample->timestamp.tv_sec,
- sample->timestamp.tv_nsec,
- sample->duration);
+ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n",
+ sample->timestamp.tv_sec,
+ sample->timestamp.tv_nsec,
+ sample->duration,
+ sample->outer_duration);
/* handling partial reads is more trouble than it's worth */

184
debian/patches/features/all/rt/hwlat-detector-Use-thread-instead-of-stop-machine.patch vendored Normal file
View File

@ -0,0 +1,184 @@
From 42b3963c5d3dcdb54226fc6bbb6b5fbcf3f2ddee Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 19 Aug 2013 17:33:27 -0400
Subject: [PATCH 3/3] hwlat-detector: Use thread instead of stop machine
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
There's no reason to use stop machine to search for hardware latency.
Simply disabling interrupts while running the loop will do enough to
check if something comes in that wasn't disabled by interrupts being
off, which is exactly what stop machine does.
Instead of using stop machine, just have the thread disable interrupts
while it checks for hardware latency.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/misc/hwlat_detector.c | 59 +++++++++++++++++-------------------------
1 file changed, 25 insertions(+), 34 deletions(-)
--- a/drivers/misc/hwlat_detector.c
+++ b/drivers/misc/hwlat_detector.c
@@ -41,7 +41,6 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/ring_buffer.h>
-#include <linux/stop_machine.h>
#include <linux/time.h>
#include <linux/hrtimer.h>
#include <linux/kthread.h>
@@ -107,7 +106,6 @@ struct data; /* Global state */
/* Sampling functions */
static int __buffer_add_sample(struct sample *sample);
static struct sample *buffer_get_sample(struct sample *sample);
-static int get_sample(void *unused);
/* Threading and state */
static int kthread_fn(void *unused);
@@ -149,7 +147,7 @@ struct sample {
unsigned long lost;
};
-/* keep the global state somewhere. Mostly used under stop_machine. */
+/* keep the global state somewhere. */
static struct data {
struct mutex lock; /* protect changes */
@@ -172,7 +170,7 @@ static struct data {
* @sample: The new latency sample value
*
* This receives a new latency sample and records it in a global ring buffer.
- * No additional locking is used in this case - suited for stop_machine use.
+ * No additional locking is used in this case.
*/
static int __buffer_add_sample(struct sample *sample)
{
@@ -229,18 +227,17 @@ static struct sample *buffer_get_sample(
#endif
/**
* get_sample - sample the CPU TSC and look for likely hardware latencies
- * @unused: This is not used but is a part of the stop_machine API
*
* Used to repeatedly capture the CPU TSC (or similar), looking for potential
- * hardware-induced latency. Called under stop_machine, with data.lock held.
+ * hardware-induced latency. Called with interrupts disabled and with data.lock held.
*/
-static int get_sample(void *unused)
+static int get_sample(void)
{
time_type start, t1, t2, last_t2;
s64 diff, total = 0;
u64 sample = 0;
u64 outer_sample = 0;
- int ret = 1;
+ int ret = -1;
init_time(last_t2, 0);
start = time_get(); /* start timestamp */
@@ -279,10 +276,14 @@ static int get_sample(void *unused)
} while (total <= data.sample_width);
+ ret = 0;
+
/* If we exceed the threshold value, we have found a hardware latency */
if (sample > data.threshold || outer_sample > data.threshold) {
struct sample s;
+ ret = 1;
+
data.count++;
s.seqnum = data.count;
s.duration = sample;
@@ -295,7 +296,6 @@ static int get_sample(void *unused)
data.max_sample = sample;
}
- ret = 0;
out:
return ret;
}
@@ -305,32 +305,30 @@ static int get_sample(void *unused)
* @unused: A required part of the kthread API.
*
* Used to periodically sample the CPU TSC via a call to get_sample. We
- * use stop_machine, whith does (intentionally) introduce latency since we
+ * disable interrupts, which does (intentionally) introduce latency since we
* need to ensure nothing else might be running (and thus pre-empting).
* Obviously this should never be used in production environments.
*
- * stop_machine will schedule us typically only on CPU0 which is fine for
- * almost every real-world hardware latency situation - but we might later
- * generalize this if we find there are any actualy systems with alternate
- * SMI delivery or other non CPU0 hardware latencies.
+ * Currently this runs on which ever CPU it was scheduled on, but most
+ * real-worald hardware latency situations occur across several CPUs,
+ * but we might later generalize this if we find there are any actualy
+ * systems with alternate SMI delivery or other hardware latencies.
*/
static int kthread_fn(void *unused)
{
- int err = 0;
- u64 interval = 0;
+ int ret;
+ u64 interval;
while (!kthread_should_stop()) {
mutex_lock(&data.lock);
- err = stop_machine(get_sample, unused, 0);
- if (err) {
- /* Houston, we have a problem */
- mutex_unlock(&data.lock);
- goto err_out;
- }
+ local_irq_disable();
+ ret = get_sample();
+ local_irq_enable();
- wake_up(&data.wq); /* wake up reader(s) */
+ if (ret > 0)
+ wake_up(&data.wq); /* wake up reader(s) */
interval = data.sample_window - data.sample_width;
do_div(interval, USEC_PER_MSEC); /* modifies interval value */
@@ -338,15 +336,10 @@ static int kthread_fn(void *unused)
mutex_unlock(&data.lock);
if (msleep_interruptible(interval))
- goto out;
+ break;
}
- goto out;
-err_out:
- printk(KERN_ERR BANNER "could not call stop_machine, disabling\n");
- enabled = 0;
-out:
- return err;
+ return 0;
}
/**
@@ -442,8 +435,7 @@ static int init_stats(void)
* This function provides a generic read implementation for the global state
* "data" structure debugfs filesystem entries. It would be nice to use
* simple_attr_read directly, but we need to make sure that the data.lock
- * spinlock is held during the actual read (even though we likely won't ever
- * actually race here as the updater runs under a stop_machine context).
+ * is held during the actual read.
*/
static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos, const u64 *entry)
@@ -478,8 +470,7 @@ static ssize_t simple_data_read(struct f
* This function provides a generic write implementation for the global state
* "data" structure debugfs filesystem entries. It would be nice to use
* simple_attr_write directly, but we need to make sure that the data.lock
- * spinlock is held during the actual write (even though we likely won't ever
- * actually race here as the updater runs under a stop_machine context).
+ * is held during the actual write.
*/
static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos, u64 *entry)

94
debian/patches/features/all/rt/hwlat-detector-Use-trace_clock_local-if-available.patch vendored Normal file
View File

@ -0,0 +1,94 @@
From 4aaca90c0255caee9a55371afaecb32365123762 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 19 Aug 2013 17:33:26 -0400
Subject: [PATCH 2/3] hwlat-detector: Use trace_clock_local if available
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
As ktime_get() calls into the timing code which does a read_seq(), it
may be affected by other CPUS that touch that lock. To remove this
dependency, use the trace_clock_local() which is already exported
for module use. If CONFIG_TRACING is enabled, use that as the clock,
otherwise use ktime_get().
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/misc/hwlat_detector.c | 34 +++++++++++++++++++++++++---------
1 file changed, 25 insertions(+), 9 deletions(-)
--- a/drivers/misc/hwlat_detector.c
+++ b/drivers/misc/hwlat_detector.c
@@ -51,6 +51,7 @@
#include <linux/version.h>
#include <linux/delay.h>
#include <linux/slab.h>
+#include <linux/trace_clock.h>
#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */
#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */
@@ -211,6 +212,21 @@ static struct sample *buffer_get_sample(
return sample;
}
+#ifndef CONFIG_TRACING
+#define time_type ktime_t
+#define time_get() ktime_get()
+#define time_to_us(x) ktime_to_us(x)
+#define time_sub(a, b) ktime_sub(a, b)
+#define init_time(a, b) (a).tv64 = b
+#define time_u64(a) (a).tv64
+#else
+#define time_type u64
+#define time_get() trace_clock_local()
+#define time_to_us(x) div_u64(x, 1000)
+#define time_sub(a, b) ((a) - (b))
+#define init_time(a, b) a = b
+#define time_u64(a) a
+#endif
/**
* get_sample - sample the CPU TSC and look for likely hardware latencies
* @unused: This is not used but is a part of the stop_machine API
@@ -220,23 +236,23 @@ static struct sample *buffer_get_sample(
*/
static int get_sample(void *unused)
{
- ktime_t start, t1, t2, last_t2;
+ time_type start, t1, t2, last_t2;
s64 diff, total = 0;
u64 sample = 0;
u64 outer_sample = 0;
int ret = 1;
- last_t2.tv64 = 0;
- start = ktime_get(); /* start timestamp */
+ init_time(last_t2, 0);
+ start = time_get(); /* start timestamp */
do {
- t1 = ktime_get(); /* we'll look for a discontinuity */
- t2 = ktime_get();
+ t1 = time_get(); /* we'll look for a discontinuity */
+ t2 = time_get();
- if (last_t2.tv64) {
+ if (time_u64(last_t2)) {
/* Check the delta from the outer loop (t2 to next t1) */
- diff = ktime_to_us(ktime_sub(t1, last_t2));
+ diff = time_to_us(time_sub(t1, last_t2));
/* This shouldn't happen */
if (diff < 0) {
printk(KERN_ERR BANNER "time running backwards\n");
@@ -247,10 +263,10 @@ static int get_sample(void *unused)
}
last_t2 = t2;
- total = ktime_to_us(ktime_sub(t2, start)); /* sample width */
+ total = time_to_us(time_sub(t2, start)); /* sample width */
/* This checks the inner loop (t1 to t2) */
- diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */
+ diff = time_to_us(time_sub(t2, t1)); /* current diff */
/* This shouldn't happen */
if (diff < 0) {

1345
debian/patches/features/all/rt/hwlatdetect.patch vendored Normal file
View File

File diff suppressed because it is too large Load Diff

35
debian/patches/features/all/rt/i2c-omap-drop-the-lock-hard-irq-context.patch vendored Normal file
View File

@ -0,0 +1,35 @@
From 5145351047b216cca13aaca99f939a9a594c6c4d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 21 Mar 2013 11:35:49 +0100
Subject: [PATCH 2/3] i2c/omap: drop the lock hard irq context
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The lock is taken while reading two registers. On RT the first lock is
taken in hard irq where it might sleep and in the threaded irq.
The threaded irq runs in oneshot mode so the hard irq does not run until
the thread the completes so there is no reason to grab the lock.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/i2c/busses/i2c-omap.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -879,15 +879,12 @@ omap_i2c_isr(int irq, void *dev_id)
u16 mask;
u16 stat;
- spin_lock(&dev->lock);
- mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG);
stat = omap_i2c_read_reg(dev, OMAP_I2C_STAT_REG);
+ mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG);
if (stat & mask)
ret = IRQ_WAKE_THREAD;
- spin_unlock(&dev->lock);
-
return ret;
}

23
debian/patches/features/all/rt/i915_compile_fix.patch vendored Normal file
View File

@ -0,0 +1,23 @@
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Subject: gpu/i915: don't open code these things
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The opencode part is gone in 1f83fee0 ("drm/i915: clear up wedged transitions")
the owner check is still there.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
drivers/gpu/drm/i915/i915_gem.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4778,7 +4778,7 @@ static bool mutex_is_locked_by(struct mu
if (!mutex_is_locked(mutex))
return false;
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if (defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)) && !defined(CONFIG_PREEMPT_RT_BASE)
return mutex->owner == task;
#else
/* Since UP may be pre-empted, we cannot assume that we own the lock */

170
debian/patches/features/all/rt/ide-use-nort-local-irq-variants.patch vendored Normal file
View File

@ -0,0 +1,170 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:16 -0500
Subject: ide: Do not disable interrupts for PREEMPT-RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Use the local_irq_*_nort variants.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/ide/alim15x3.c | 4 ++--
drivers/ide/hpt366.c | 4 ++--
drivers/ide/ide-io-std.c | 8 ++++----
drivers/ide/ide-io.c | 2 +-
drivers/ide/ide-iops.c | 4 ++--
drivers/ide/ide-probe.c | 4 ++--
drivers/ide/ide-taskfile.c | 6 +++---
7 files changed, 16 insertions(+), 16 deletions(-)
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct p
isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
if (m5229_revision < 0xC2) {
/*
@@ -325,7 +325,7 @@ static int init_chipset_ali15x3(struct p
}
pci_dev_put(north);
pci_dev_put(isa_dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
return 0;
}
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -1241,7 +1241,7 @@ static int init_dma_hpt366(ide_hwif_t *h
dma_old = inb(base + 2);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
dma_new = dma_old;
pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
@@ -1252,7 +1252,7 @@ static int init_dma_hpt366(ide_hwif_t *h
if (dma_new != dma_old)
outb(dma_new, base + 2);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n",
hwif->name, base, base + 7);
--- a/drivers/ide/ide-io-std.c
+++ b/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive,
unsigned long uninitialized_var(flags);
if ((io_32bit & 2) && !mmio) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
ata_vlb_sync(io_ports->nsect_addr);
}
@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive,
insl(data_addr, buf, words);
if ((io_32bit & 2) && !mmio)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
if (((len + 1) & 3) < 2)
return;
@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive,
unsigned long uninitialized_var(flags);
if ((io_32bit & 2) && !mmio) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
ata_vlb_sync(io_ports->nsect_addr);
}
@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive,
outsl(data_addr, buf, words);
if ((io_32bit & 2) && !mmio)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
if (((len + 1) & 3) < 2)
return;
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long dat
/* disable_irq_nosync ?? */
disable_irq(hwif->irq);
/* local CPU only, as if we were handling an interrupt */
- local_irq_disable();
+ local_irq_disable_nort();
if (hwif->polling) {
startstop = handler(drive);
} else if (drive_is_ready(drive)) {
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive,
if ((stat & ATA_BUSY) == 0)
break;
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
*rstat = stat;
return -EBUSY;
}
}
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
/*
* Allow status to settle, then read it again.
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *dri
int bswap = 1;
/* local CPU only; some systems need this */
- local_irq_save(flags);
+ local_irq_save_nort(flags);
/* read 512 bytes of id info */
hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
drive->dev_flags |= IDE_DFLAG_ID_READ;
#ifdef DEBUG
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -250,7 +250,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
page_is_high = PageHighMem(page);
if (page_is_high)
- local_irq_save(flags);
+ local_irq_save_nort(flags);
buf = kmap_atomic(page) + offset;
@@ -271,7 +271,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
kunmap_atomic(buf);
if (page_is_high)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
len -= nr_bytes;
}
@@ -414,7 +414,7 @@ static ide_startstop_t pre_task_out_intr
}
if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
- local_irq_disable();
+ local_irq_disable_nort();
ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);

20
debian/patches/features/all/rt/idle-state.patch vendored Normal file
View File

@ -0,0 +1,20 @@
Subject: sched: Init idle->on_rq in init_idle()
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 09 Jan 2013 23:03:29 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/sched/core.c | 1 +
1 file changed, 1 insertion(+)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4206,6 +4206,7 @@ void init_idle(struct task_struct *idle,
rcu_read_unlock();
rq->curr = rq->idle = idle;
+ idle->on_rq = 1;
#if defined(CONFIG_SMP)
idle->on_cpu = 1;
#endif

97
debian/patches/features/all/rt/idr-use-local-lock-for-protection.patch vendored Normal file
View File

@ -0,0 +1,97 @@
From: Thomas Gleixner <tglx@linutronix.de>
Subject: idr: Use local lock instead of preempt enable/disable
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
We need to protect the per cpu variable and prevent migration.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/idr.h | 4 ++++
lib/idr.c | 37 ++++++++++++++++++++++++++++++++++---
2 files changed, 38 insertions(+), 3 deletions(-)
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -92,10 +92,14 @@ void idr_init(struct idr *idp);
* Each idr_preload() should be matched with an invocation of this
* function. See idr_preload() for details.
*/
+#ifdef CONFIG_PREEMPT_RT_FULL
+void idr_preload_end(void);
+#else
static inline void idr_preload_end(void)
{
preempt_enable();
}
+#endif
/**
* idr_find - return pointer for given id
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -37,6 +37,7 @@
#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
+#include <linux/locallock.h>
#define MAX_IDR_SHIFT (sizeof(int) * 8 - 1)
#define MAX_IDR_BIT (1U << MAX_IDR_SHIFT)
@@ -389,6 +390,36 @@ int __idr_get_new_above(struct idr *idp,
}
EXPORT_SYMBOL(__idr_get_new_above);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static DEFINE_LOCAL_IRQ_LOCK(idr_lock);
+
+static inline void idr_preload_lock(void)
+{
+ local_lock(idr_lock);
+}
+
+static inline void idr_preload_unlock(void)
+{
+ local_unlock(idr_lock);
+}
+
+void idr_preload_end(void)
+{
+ idr_preload_unlock();
+}
+EXPORT_SYMBOL(idr_preload_end);
+#else
+static inline void idr_preload_lock(void)
+{
+ preempt_disable();
+}
+
+static inline void idr_preload_unlock(void)
+{
+ preempt_enable();
+}
+#endif
+
/**
* idr_preload - preload for idr_alloc()
* @gfp_mask: allocation mask to use for preloading
@@ -423,7 +454,7 @@ void idr_preload(gfp_t gfp_mask)
WARN_ON_ONCE(in_interrupt());
might_sleep_if(gfp_mask & __GFP_WAIT);
- preempt_disable();
+ idr_preload_lock();
/*
* idr_alloc() is likely to succeed w/o full idr_layer buffer and
@@ -435,9 +466,9 @@ void idr_preload(gfp_t gfp_mask)
while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) {
struct idr_layer *new;
- preempt_enable();
+ idr_preload_unlock();
new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
- preempt_disable();
+ idr_preload_lock();
if (!new)
break;

41
debian/patches/features/all/rt/infiniband-mellanox-ib-use-nort-irq.patch vendored Normal file
View File

@ -0,0 +1,41 @@
From: Sven-Thorsten Dietrich <sdietrich@novell.com>
Date: Fri, 3 Jul 2009 08:30:35 -0500
Subject: infiniband: Mellanox IB driver patch use _nort() primitives
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Fixes in_atomic stack-dump, when Mellanox module is loaded into the RT
Kernel.
Michael S. Tsirkin <mst@dev.mellanox.co.il> sayeth:
"Basically, if you just make spin_lock_irqsave (and spin_lock_irq) not disable
interrupts for non-raw spinlocks, I think all of infiniband will be fine without
changes."
Signed-off-by: Sven-Thorsten Dietrich <sven@thebigcorporation.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -783,7 +783,7 @@ void ipoib_mcast_restart_task(struct wor
ipoib_mcast_stop_thread(dev, 0);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
netif_addr_lock(dev);
spin_lock(&priv->lock);
@@ -865,7 +865,7 @@ void ipoib_mcast_restart_task(struct wor
spin_unlock(&priv->lock);
netif_addr_unlock(dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
/* We have to cancel outside of the spinlock */
list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {

45
debian/patches/features/all/rt/inpt-gameport-use-local-irq-nort.patch vendored Normal file
View File

@ -0,0 +1,45 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:16 -0500
Subject: input: gameport: Do not disable interrupts on PREEMPT_RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Use the _nort() primitives.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
drivers/input/gameport/gameport.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -87,12 +87,12 @@ static int gameport_measure_speed(struct
tx = 1 << 30;
for(i = 0; i < 50; i++) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
GET_TIME(t1);
for (t = 0; t < 50; t++) gameport_read(gameport);
GET_TIME(t2);
GET_TIME(t3);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
udelay(i * 10);
if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
}
@@ -111,11 +111,11 @@ static int gameport_measure_speed(struct
tx = 1 << 30;
for(i = 0; i < 50; i++) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
rdtscl(t1);
for (t = 0; t < 50; t++) gameport_read(gameport);
rdtscl(t2);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
udelay(i * 10);
if (t2 - t1 < tx) tx = t2 - t1;
}

84
debian/patches/features/all/rt/ipc-make-rt-aware.patch vendored Normal file
View File

@ -0,0 +1,84 @@
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:30:12 -0500
Subject: ipc: Make the ipc code -rt aware
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
RT serializes the code with the (rt)spinlock but keeps preemption
enabled. Some parts of the code need to be atomic nevertheless.
Protect it with preempt_disable/enable_rt pairts.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
ipc/mqueue.c | 5 +++++
ipc/msg.c | 16 ++++++++++++++++
2 files changed, 21 insertions(+)
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -923,12 +923,17 @@ static inline void pipelined_send(struct
struct msg_msg *message,
struct ext_wait_queue *receiver)
{
+ /*
+ * Keep them in one critical section for PREEMPT_RT:
+ */
+ preempt_disable_rt();
receiver->msg = message;
list_del(&receiver->list);
receiver->state = STATE_PENDING;
wake_up_process(receiver->task);
smp_wmb();
receiver->state = STATE_READY;
+ preempt_enable_rt();
}
/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -253,10 +253,18 @@ static void expunge_all(struct msg_queue
struct msg_receiver *msr, *t;
list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
+ /*
+ * Make sure that the wakeup doesnt preempt
+ * this CPU prematurely. (on PREEMPT_RT)
+ */
+ preempt_disable_rt();
+
msr->r_msg = NULL;
wake_up_process(msr->r_tsk);
smp_mb();
msr->r_msg = ERR_PTR(res);
+
+ preempt_enable_rt();
}
}
@@ -636,6 +644,12 @@ static inline int pipelined_send(struct
!security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
msr->r_msgtype, msr->r_mode)) {
+ /*
+ * Make sure that the wakeup doesnt preempt
+ * this CPU prematurely. (on PREEMPT_RT)
+ */
+ preempt_disable_rt();
+
list_del(&msr->r_list);
if (msr->r_maxsize < msg->m_ts) {
msr->r_msg = NULL;
@@ -649,9 +663,11 @@ static inline int pipelined_send(struct
wake_up_process(msr->r_tsk);
smp_mb();
msr->r_msg = msg;
+ preempt_enable_rt();
return 1;
}
+ preempt_enable_rt();
}
}
return 0;

65
debian/patches/features/all/rt/ipc-mqueue-add-a-critical-section-to-avoid-a-deadlock.patch vendored Normal file
View File

@ -0,0 +1,65 @@
Subject: ipc/mqueue: Add a critical section to avoid a deadlock
From: KOBAYASHI Yoshitake <yoshitake.kobayashi@toshiba.co.jp>
Date: Sat, 23 Jul 2011 11:57:36 +0900
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
(Repost for v3.0-rt1 and changed the distination addreses)
I have tested the following patch on v3.0-rt1 with PREEMPT_RT_FULL.
In POSIX message queue, if a sender process uses SCHED_FIFO and
has a higher priority than a receiver process, the sender will
be stuck at ipc/mqueue.c:452
452 while (ewp->state == STATE_PENDING)
453 cpu_relax();
Description of the problem
(receiver process)
1. receiver changes sender's state to STATE_PENDING (mqueue.c:846)
2. wake up sender process and "switch to sender" (mqueue.c:847)
Note: This context switch only happens in PREEMPT_RT_FULL kernel.
(sender process)
3. sender check the own state in above loop (mqueue.c:452-453)
*. receiver will never wake up and cannot change sender's state to
STATE_READY because sender has higher priority
Signed-off-by: Yoshitake Kobayashi <yoshitake.kobayashi@toshiba.co.jp>
Cc: viro@zeniv.linux.org.uk
Cc: dchinner@redhat.com
Cc: npiggin@kernel.dk
Cc: hch@lst.de
Cc: arnd@arndb.de
Link: http://lkml.kernel.org/r/4E2A38A0.1090601@toshiba.co.jp
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
ipc/mqueue.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -947,13 +947,18 @@ static inline void pipelined_receive(str
wake_up_interruptible(&info->wait_q);
return;
}
- if (msg_insert(sender->msg, info))
- return;
- list_del(&sender->list);
- sender->state = STATE_PENDING;
- wake_up_process(sender->task);
- smp_wmb();
- sender->state = STATE_READY;
+ /*
+ * Keep them in one critical section for PREEMPT_RT:
+ */
+ preempt_disable_rt();
+ if (!msg_insert(sender->msg, info)) {
+ list_del(&sender->list);
+ sender->state = STATE_PENDING;
+ wake_up_process(sender->task);
+ smp_wmb();
+ sender->state = STATE_READY;
+ }
+ preempt_enable_rt();
}
SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,

70
debian/patches/features/all/rt/ipc-sem-rework-semaphore-wakeups.patch vendored Normal file
View File

@ -0,0 +1,70 @@
Subject: ipc/sem: Rework semaphore wakeups
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Sep 2011 11:57:04 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Current sysv sems have a weird ass wakeup scheme that involves keeping
preemption disabled over a potential O(n^2) loop and busy waiting on
that on other CPUs.
Kill this and simply wake the task directly from under the sem_lock.
This was discovered by a migrate_disable() debug feature that
disallows:
spin_lock();
preempt_disable();
spin_unlock()
preempt_enable();
Cc: Manfred Spraul <manfred@colorfullife.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Manfred Spraul <manfred@colorfullife.com>
Link: http://lkml.kernel.org/r/1315994224.5040.1.camel@twins
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
ipc/sem.c | 10 ++++++++++
1 file changed, 10 insertions(+)
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -666,6 +666,13 @@ static int perform_atomic_semop(struct s
static void wake_up_sem_queue_prepare(struct list_head *pt,
struct sem_queue *q, int error)
{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ struct task_struct *p = q->sleeper;
+ get_task_struct(p);
+ q->status = error;
+ wake_up_process(p);
+ put_task_struct(p);
+#else
if (list_empty(pt)) {
/*
* Hold preempt off so that we don't get preempted and have the
@@ -677,6 +684,7 @@ static void wake_up_sem_queue_prepare(st
q->pid = error;
list_add_tail(&q->list, pt);
+#endif
}
/**
@@ -690,6 +698,7 @@ static void wake_up_sem_queue_prepare(st
*/
static void wake_up_sem_queue_do(struct list_head *pt)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
struct sem_queue *q, *t;
int did_something;
@@ -702,6 +711,7 @@ static void wake_up_sem_queue_do(struct
}
if (did_something)
preempt_enable();
+#endif
}
static void unlink_queue(struct sem_array *sma, struct sem_queue *q)

145
debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch vendored Normal file
View File

@ -0,0 +1,145 @@
Subject: genirq: Allow disabling of softirq processing in irq thread context
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 31 Jan 2012 13:01:27 +0100
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
The processing of softirqs in irq thread context is a performance gain
for the non-rt workloads of a system, but it's counterproductive for
interrupts which are explicitely related to the realtime
workload. Allow such interrupts to prevent softirq processing in their
thread context.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
include/linux/interrupt.h | 2 ++
include/linux/irq.h | 5 ++++-
kernel/irq/manage.c | 13 ++++++++++++-
kernel/irq/settings.h | 12 ++++++++++++
kernel/softirq.c | 7 +++++++
5 files changed, 37 insertions(+), 2 deletions(-)
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -58,6 +58,7 @@
* IRQF_NO_THREAD - Interrupt cannot be threaded
* IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device
* resume time.
+ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT)
*/
#define IRQF_DISABLED 0x00000020
#define IRQF_SHARED 0x00000080
@@ -71,6 +72,7 @@
#define IRQF_FORCE_RESUME 0x00008000
#define IRQF_NO_THREAD 0x00010000
#define IRQF_EARLY_RESUME 0x00020000
+#define IRQF_NO_SOFTIRQ_CALL 0x00040000
#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -70,6 +70,7 @@ typedef void (*irq_preflow_handler_t)(st
* IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context
* IRQ_NESTED_TRHEAD - Interrupt nests into another thread
* IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable
+ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT)
*/
enum {
IRQ_TYPE_NONE = 0x00000000,
@@ -94,12 +95,14 @@ enum {
IRQ_NESTED_THREAD = (1 << 15),
IRQ_NOTHREAD = (1 << 16),
IRQ_PER_CPU_DEVID = (1 << 17),
+ IRQ_NO_SOFTIRQ_CALL = (1 << 18),
};
#define IRQF_MODIFY_MASK \
(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
- IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID)
+ IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
+ IRQ_NO_SOFTIRQ_CALL)
#define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING)
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -856,7 +856,15 @@ irq_forced_thread_fn(struct irq_desc *de
local_bh_disable();
ret = action->thread_fn(action->irq, action->dev_id);
irq_finalize_oneshot(desc, action);
- local_bh_enable();
+ /*
+ * Interrupts which have real time requirements can be set up
+ * to avoid softirq processing in the thread handler. This is
+ * safe as these interrupts do not raise soft interrupts.
+ */
+ if (irq_settings_no_softirq_call(desc))
+ _local_bh_enable();
+ else
+ local_bh_enable();
return ret;
}
@@ -1202,6 +1210,9 @@ static int
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
+ if (new->flags & IRQF_NO_SOFTIRQ_CALL)
+ irq_settings_set_no_softirq_call(desc);
+
/* Set default affinity mask once everything is setup */
setup_affinity(irq, desc, mask);
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,6 +14,7 @@ enum {
_IRQ_NO_BALANCING = IRQ_NO_BALANCING,
_IRQ_NESTED_THREAD = IRQ_NESTED_THREAD,
_IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID,
+ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL,
_IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
};
@@ -26,6 +27,7 @@ enum {
#define IRQ_NOAUTOEN GOT_YOU_MORON
#define IRQ_NESTED_THREAD GOT_YOU_MORON
#define IRQ_PER_CPU_DEVID GOT_YOU_MORON
+#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON
#undef IRQF_MODIFY_MASK
#define IRQF_MODIFY_MASK GOT_YOU_MORON
@@ -36,6 +38,16 @@ irq_settings_clr_and_set(struct irq_desc
desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
}
+static inline bool irq_settings_no_softirq_call(struct irq_desc *desc)
+{
+ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL;
+}
+
+static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc)
+{
+ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL;
+}
+
static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_PER_CPU;
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -423,6 +423,13 @@ void local_bh_enable_ip(unsigned long ip
}
EXPORT_SYMBOL(local_bh_enable_ip);
+void _local_bh_enable(void)
+{
+ current->softirq_nestcnt--;
+ migrate_enable();
+}
+EXPORT_SYMBOL(_local_bh_enable);
+
/* For tracing */
int notrace __in_softirq(void)
{

22
debian/patches/features/all/rt/jump-label-rt.patch vendored Normal file
View File

@ -0,0 +1,22 @@
Subject: jump-label-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 13 Jul 2011 11:03:16 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/jump_label.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -49,7 +49,8 @@
#include <linux/types.h>
#include <linux/compiler.h>
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && \
+ !defined(CONFIG_PREEMPT_BASE)
struct static_key {
atomic_t enabled;

45
debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch vendored Normal file
View File

@ -0,0 +1,45 @@
Subject: kconfig-disable-a-few-options-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 24 Jul 2011 12:11:43 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Disable stuff which is known to have issues on RT
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/Kconfig | 1 +
drivers/net/Kconfig | 1 +
mm/Kconfig | 2 +-
3 files changed, 3 insertions(+), 1 deletion(-)
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -6,6 +6,7 @@ config OPROFILE
tristate "OProfile system profiling"
depends on PROFILING
depends on HAVE_OPROFILE
+ depends on !PREEMPT_RT_FULL
select RING_BUFFER
select RING_BUFFER_ALLOW_SWAP
help
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -160,6 +160,7 @@ config VXLAN
config NETCONSOLE
tristate "Network console logging support"
+ depends on !PREEMPT_RT_FULL
---help---
If you want to log kernel messages over the network, enable this.
See <file:Documentation/networking/netconsole.txt> for details.
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -384,7 +384,7 @@ config NOMMU_INITIAL_TRIM_EXCESS
config TRANSPARENT_HUGEPAGE
bool "Transparent Hugepage Support"
- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL
select COMPACTION
help
Transparent Hugepages allows the kernel to use huge pages and

57
debian/patches/features/all/rt/kconfig-preempt-rt-full.patch vendored Normal file
View File

@ -0,0 +1,57 @@
Subject: kconfig-preempt-rt-full.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 29 Jun 2011 14:58:57 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
init/Makefile | 2 +-
kernel/Kconfig.preempt | 8 ++++++++
scripts/mkcompile_h | 4 +++-
3 files changed, 12 insertions(+), 2 deletions(-)
--- a/init/Makefile
+++ b/init/Makefile
@@ -33,4 +33,4 @@ mounts-$(CONFIG_BLK_DEV_MD) += do_mounts
include/generated/compile.h: FORCE
@$($(quiet)chk_compile.h)
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
+ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -67,6 +67,14 @@ config PREEMPT_RTB
enables changes which are preliminary for the full preemptible
RT kernel.
+config PREEMPT_RT_FULL
+ bool "Fully Preemptible Kernel (RT)"
+ depends on IRQ_FORCED_THREADING
+ select PREEMPT_RT_BASE
+ select PREEMPT_RCU
+ help
+ All and everything
+
endchoice
config PREEMPT_COUNT
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -4,7 +4,8 @@ TARGET=$1
ARCH=$2
SMP=$3
PREEMPT=$4
-CC=$5
+RT=$5
+CC=$6
vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
@@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION"
CONFIG_FLAGS=""
if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
+if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi
UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP"
# Truncate to maximum length

89
debian/patches/features/all/rt/kernel-cpu-fix-cpu-down-problem-if-kthread-s-cpu-is-.patch vendored Normal file
View File

@ -0,0 +1,89 @@
From 24136a819693ae36039d6b4286bf1f775e062bcc Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 7 Jun 2013 22:37:06 +0200
Subject: [PATCH] kernel/cpu: fix cpu down problem if kthread's cpu is
going down
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
If kthread is pinned to CPUx and CPUx is going down then we get into
trouble:
- first the unplug thread is created
- it will set itself to hp->unplug. As a result, every task that is
going to take a lock, has to leave the CPU.
- the CPU_DOWN_PREPARE notifier are started. The worker thread will
start a new process for the "high priority worker".
Now kthread would like to take a lock but since it can't leave the CPU
it will never complete its task.
We could fire the unplug thread after the notifier but then the cpu is
no longer marked "online" and the unplug thread will run on CPU0 which
was fixed before :)
So instead the unplug thread is started and kept waiting until the
notfier complete their work.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/cpu.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -83,6 +83,7 @@ struct hotplug_pcp {
int refcount;
int grab_lock;
struct completion synced;
+ struct completion unplug_wait;
#ifdef CONFIG_PREEMPT_RT_FULL
spinlock_t lock;
#else
@@ -178,6 +179,7 @@ static int sync_unplug_thread(void *data
{
struct hotplug_pcp *hp = data;
+ wait_for_completion(&hp->unplug_wait);
preempt_disable();
hp->unplug = current;
wait_for_pinned_cpus(hp);
@@ -243,6 +245,14 @@ static void __cpu_unplug_sync(struct hot
wait_for_completion(&hp->synced);
}
+static void __cpu_unplug_wait(unsigned int cpu)
+{
+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+ complete(&hp->unplug_wait);
+ wait_for_completion(&hp->synced);
+}
+
/*
* Start the sync_unplug_thread on the target cpu and wait for it to
* complete.
@@ -266,6 +276,7 @@ static int cpu_unplug_begin(unsigned int
tell_sched_cpu_down_begin(cpu);
init_completion(&hp->synced);
+ init_completion(&hp->unplug_wait);
hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
if (IS_ERR(hp->sync_tsk)) {
@@ -281,8 +292,7 @@ static int cpu_unplug_begin(unsigned int
* wait for tasks that are going to enter these sections and
* we must not have them block.
*/
- __cpu_unplug_sync(hp);
-
+ wake_up_process(hp->sync_tsk);
return 0;
}
@@ -591,6 +601,8 @@ static int __ref _cpu_down(unsigned int
__func__, cpu);
goto out_release;
}
+
+ __cpu_unplug_wait(cpu);
smpboot_park_threads(cpu);
/* Notifiers are done. Don't let any more tasks pin this CPU. */

60
debian/patches/features/all/rt/kernel-hotplug-restore-original-cpu-mask-oncpu-down.patch vendored Normal file
View File

@ -0,0 +1,60 @@
From 4c6df3d78817c20a147c0291f6600d002c0910d3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 14 Jun 2013 17:16:35 +0200
Subject: [PATCH] kernel/hotplug: restore original cpu mask oncpu/down
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
If a task which is allowed to run only on CPU X puts CPU Y down then it
will be allowed on all CPUs but the on CPU Y after it comes back from
kernel. This patch ensures that we don't lose the initial setting unless
the CPU the task is running is going down.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
kernel/cpu.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -565,6 +565,7 @@ static int __ref _cpu_down(unsigned int
.hcpu = hcpu,
};
cpumask_var_t cpumask;
+ cpumask_var_t cpumask_org;
if (num_online_cpus() == 1)
return -EBUSY;
@@ -575,6 +576,12 @@ static int __ref _cpu_down(unsigned int
/* Move the downtaker off the unplug cpu */
if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
return -ENOMEM;
+ if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) {
+ free_cpumask_var(cpumask);
+ return -ENOMEM;
+ }
+
+ cpumask_copy(cpumask_org, tsk_cpus_allowed(current));
cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
set_cpus_allowed_ptr(current, cpumask);
free_cpumask_var(cpumask);
@@ -583,7 +590,8 @@ static int __ref _cpu_down(unsigned int
if (mycpu == cpu) {
printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
migrate_enable();
- return -EBUSY;
+ err = -EBUSY;
+ goto restore_cpus;
}
cpu_hotplug_begin();
@@ -642,6 +650,9 @@ static int __ref _cpu_down(unsigned int
cpu_hotplug_done();
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
+restore_cpus:
+ set_cpus_allowed_ptr(current, cpumask_org);
+ free_cpumask_var(cpumask_org);
return err;
}

103
debian/patches/features/all/rt/kgb-serial-hackaround.patch vendored Normal file
View File

@ -0,0 +1,103 @@
From: Jason Wessel <jason.wessel@windriver.com>
Date: Thu, 28 Jul 2011 12:42:23 -0500
Subject: kgdb/serial: Short term workaround
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
On 07/27/2011 04:37 PM, Thomas Gleixner wrote:
> - KGDB (not yet disabled) is reportedly unusable on -rt right now due
> to missing hacks in the console locking which I dropped on purpose.
>
To work around this in the short term you can use this patch, in
addition to the clocksource watchdog patch that Thomas brewed up.
Comments are welcome of course. Ultimately the right solution is to
change separation between the console and the HW to have a polled mode
+ work queue so as not to introduce any kind of latency.
Thanks,
Jason.
---
drivers/tty/serial/8250/8250_core.c | 3 ++-
include/linux/kdb.h | 3 ++-
kernel/debug/kdb/kdb_io.c | 6 ++----
3 files changed, 6 insertions(+), 6 deletions(-)
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -38,6 +38,7 @@
#include <linux/nmi.h>
#include <linux/mutex.h>
#include <linux/slab.h>
+#include <linux/kdb.h>
#ifdef CONFIG_SPARC
#include <linux/sunserialcore.h>
#endif
@@ -2869,7 +2870,7 @@ serial8250_console_write(struct console
touch_nmi_watchdog();
- if (port->sysrq || oops_in_progress)
+ if (port->sysrq || oops_in_progress || in_kdb_printk())
locked = spin_trylock_irqsave(&port->lock, flags);
else
spin_lock_irqsave(&port->lock, flags);
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -115,7 +115,7 @@ extern int kdb_trap_printk;
extern __printf(1, 0) int vkdb_printf(const char *fmt, va_list args);
extern __printf(1, 2) int kdb_printf(const char *, ...);
typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...);
-
+#define in_kdb_printk() (kdb_trap_printk)
extern void kdb_init(int level);
/* Access to kdb specific polling devices */
@@ -150,6 +150,7 @@ extern int kdb_register_repeat(char *, k
extern int kdb_unregister(char *);
#else /* ! CONFIG_KGDB_KDB */
static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
+#define in_kdb_printk() (0)
static inline void kdb_init(int level) {}
static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
char *help, short minlen) { return 0; }
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -554,7 +554,6 @@ int vkdb_printf(const char *fmt, va_list
int linecount;
int colcount;
int logging, saved_loglevel = 0;
- int saved_trap_printk;
int got_printf_lock = 0;
int retlen = 0;
int fnd, len;
@@ -565,8 +564,6 @@ int vkdb_printf(const char *fmt, va_list
unsigned long uninitialized_var(flags);
preempt_disable();
- saved_trap_printk = kdb_trap_printk;
- kdb_trap_printk = 0;
/* Serialize kdb_printf if multiple cpus try to write at once.
* But if any cpu goes recursive in kdb, just print the output,
@@ -833,7 +830,6 @@ int vkdb_printf(const char *fmt, va_list
} else {
__release(kdb_printf_lock);
}
- kdb_trap_printk = saved_trap_printk;
preempt_enable();
return retlen;
}
@@ -843,9 +839,11 @@ int kdb_printf(const char *fmt, ...)
va_list ap;
int r;
+ kdb_trap_printk++;
va_start(ap, fmt);
r = vkdb_printf(fmt, ap);
va_end(ap);
+ kdb_trap_printk--;
return r;
}

1806
debian/patches/features/all/rt/latency-hist.patch vendored Normal file
View File

File diff suppressed because it is too large Load Diff

174
debian/patches/features/all/rt/lglocks-rt.patch vendored Normal file
View File

@ -0,0 +1,174 @@
Subject: lglocks-rt.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Jun 2011 11:02:21 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/lglock.h | 19 +++++++++++++++--
kernel/lglock.c | 54 ++++++++++++++++++++++++++++++++-----------------
2 files changed, 53 insertions(+), 20 deletions(-)
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -42,22 +42,37 @@
#endif
struct lglock {
+#ifndef CONFIG_PREEMPT_RT_FULL
arch_spinlock_t __percpu *lock;
+#else
+ struct rt_mutex __percpu *lock;
+#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lock_class_key lock_key;
struct lockdep_map lock_dep_map;
#endif
};
-#define DEFINE_LGLOCK(name) \
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define DEFINE_LGLOCK(name) \
static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \
= __ARCH_SPIN_LOCK_UNLOCKED; \
struct lglock name = { .lock = &name ## _lock }
-#define DEFINE_STATIC_LGLOCK(name) \
+# define DEFINE_STATIC_LGLOCK(name) \
static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \
= __ARCH_SPIN_LOCK_UNLOCKED; \
static struct lglock name = { .lock = &name ## _lock }
+#else
+
+# define DEFINE_LGLOCK(name) \
+ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock); \
+ struct lglock name = { .lock = &name ## _lock }
+
+# define DEFINE_STATIC_LGLOCK(name) \
+ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock); \
+ static struct lglock name = { .lock = &name ## _lock }
+#endif
void lg_lock_init(struct lglock *lg, char *name);
void lg_local_lock(struct lglock *lg);
--- a/kernel/lglock.c
+++ b/kernel/lglock.c
@@ -4,6 +4,15 @@
#include <linux/cpu.h>
#include <linux/string.h>
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define lg_lock_ptr arch_spinlock_t
+# define lg_do_lock(l) arch_spin_lock(l)
+# define lg_do_unlock(l) arch_spin_unlock(l)
+#else
+# define lg_lock_ptr struct rt_mutex
+# define lg_do_lock(l) __rt_spin_lock(l)
+# define lg_do_unlock(l) __rt_spin_unlock(l)
+#endif
/*
* Note there is no uninit, so lglocks cannot be defined in
* modules (but it's fine to use them from there)
@@ -12,51 +21,60 @@
void lg_lock_init(struct lglock *lg, char *name)
{
+#ifdef CONFIG_PREEMPT_RT_FULL
+ int i;
+
+ for_each_possible_cpu(i) {
+ struct rt_mutex *lock = per_cpu_ptr(lg->lock, i);
+
+ rt_mutex_init(lock);
+ }
+#endif
LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0);
}
EXPORT_SYMBOL(lg_lock_init);
void lg_local_lock(struct lglock *lg)
{
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
- preempt_disable();
+ migrate_disable();
lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
lock = this_cpu_ptr(lg->lock);
- arch_spin_lock(lock);
+ lg_do_lock(lock);
}
EXPORT_SYMBOL(lg_local_lock);
void lg_local_unlock(struct lglock *lg)
{
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
lock_release(&lg->lock_dep_map, 1, _RET_IP_);
lock = this_cpu_ptr(lg->lock);
- arch_spin_unlock(lock);
- preempt_enable();
+ lg_do_unlock(lock);
+ migrate_enable();
}
EXPORT_SYMBOL(lg_local_unlock);
void lg_local_lock_cpu(struct lglock *lg, int cpu)
{
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
- preempt_disable();
+ preempt_disable_nort();
lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
lock = per_cpu_ptr(lg->lock, cpu);
- arch_spin_lock(lock);
+ lg_do_lock(lock);
}
EXPORT_SYMBOL(lg_local_lock_cpu);
void lg_local_unlock_cpu(struct lglock *lg, int cpu)
{
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
lock_release(&lg->lock_dep_map, 1, _RET_IP_);
lock = per_cpu_ptr(lg->lock, cpu);
- arch_spin_unlock(lock);
- preempt_enable();
+ lg_do_unlock(lock);
+ preempt_enable_nort();
}
EXPORT_SYMBOL(lg_local_unlock_cpu);
@@ -64,12 +82,12 @@ void lg_global_lock(struct lglock *lg)
{
int i;
- preempt_disable();
+ preempt_disable_nort();
lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
for_each_possible_cpu(i) {
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
lock = per_cpu_ptr(lg->lock, i);
- arch_spin_lock(lock);
+ lg_do_lock(lock);
}
}
EXPORT_SYMBOL(lg_global_lock);
@@ -80,10 +98,10 @@ void lg_global_unlock(struct lglock *lg)
lock_release(&lg->lock_dep_map, 1, _RET_IP_);
for_each_possible_cpu(i) {
- arch_spinlock_t *lock;
+ lg_lock_ptr *lock;
lock = per_cpu_ptr(lg->lock, i);
- arch_spin_unlock(lock);
+ lg_do_unlock(lock);
}
- preempt_enable();
+ preempt_enable_nort();
}
EXPORT_SYMBOL(lg_global_unlock);

30
debian/patches/features/all/rt/list-add-list-last-entry.patch vendored Normal file
View File

@ -0,0 +1,30 @@
Subject: list-add-list-last-entry.patch
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 21 Jun 2011 11:22:36 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/list.h | 11 +++++++++++
1 file changed, 11 insertions(+)
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -373,6 +373,17 @@ static inline void list_splice_tail_init
(!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
/**
+ * list_last_entry - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+/**
* list_for_each - iterate over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.

115
debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch vendored Normal file
View File

@ -0,0 +1,115 @@
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Fri, 21 Jun 2013 15:07:25 -0400
Subject: [PATCH] list_bl.h: make list head locking RT safe
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
As per changes in include/linux/jbd_common.h for avoiding the
bit_spin_locks on RT ("fs: jbd/jbd2: Make state lock and journal
head lock rt safe") we do the same thing here.
We use the non atomic __set_bit and __clear_bit inside the scope of
the lock to preserve the ability of the existing LIST_DEBUG code to
use the zero'th bit in the sanity checks.
As a bit spinlock, we had no lockdep visibility into the usage
of the list head locking. Now, if we were to implement it as a
standard non-raw spinlock, we would see:
BUG: sleeping function called from invalid context at kernel/rtmutex.c:658
in_atomic(): 1, irqs_disabled(): 0, pid: 122, name: udevd
5 locks held by udevd/122:
#0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [<ffffffff811967e8>] lock_rename+0xe8/0xf0
#1: (rename_lock){+.+...}, at: [<ffffffff811a277c>] d_move+0x2c/0x60
#2: (&dentry->d_lock){+.+...}, at: [<ffffffff811a0763>] dentry_lock_for_move+0xf3/0x130
#3: (&dentry->d_lock/2){+.+...}, at: [<ffffffff811a0734>] dentry_lock_for_move+0xc4/0x130
#4: (&dentry->d_lock/3){+.+...}, at: [<ffffffff811a0747>] dentry_lock_for_move+0xd7/0x130
Pid: 122, comm: udevd Not tainted 3.4.47-rt62 #7
Call Trace:
[<ffffffff810b9624>] __might_sleep+0x134/0x1f0
[<ffffffff817a24d4>] rt_spin_lock+0x24/0x60
[<ffffffff811a0c4c>] __d_shrink+0x5c/0xa0
[<ffffffff811a1b2d>] __d_drop+0x1d/0x40
[<ffffffff811a24be>] __d_move+0x8e/0x320
[<ffffffff811a278e>] d_move+0x3e/0x60
[<ffffffff81199598>] vfs_rename+0x198/0x4c0
[<ffffffff8119b093>] sys_renameat+0x213/0x240
[<ffffffff817a2de5>] ? _raw_spin_unlock+0x35/0x60
[<ffffffff8107781c>] ? do_page_fault+0x1ec/0x4b0
[<ffffffff817a32ca>] ? retint_swapgs+0xe/0x13
[<ffffffff813eb0e6>] ? trace_hardirqs_on_thunk+0x3a/0x3f
[<ffffffff8119b0db>] sys_rename+0x1b/0x20
[<ffffffff817a3b96>] system_call_fastpath+0x1a/0x1f
Since we are only taking the lock during short lived list operations,
lets assume for now that it being raw won't be a significant latency
concern.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/list_bl.h | 28 ++++++++++++++++++++++++++--
1 file changed, 26 insertions(+), 2 deletions(-)
--- a/include/linux/list_bl.h
+++ b/include/linux/list_bl.h
@@ -2,6 +2,7 @@
#define _LINUX_LIST_BL_H
#include <linux/list.h>
+#include <linux/spinlock.h>
#include <linux/bit_spinlock.h>
/*
@@ -32,13 +33,22 @@
struct hlist_bl_head {
struct hlist_bl_node *first;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ raw_spinlock_t lock;
+#endif
};
struct hlist_bl_node {
struct hlist_bl_node *next, **pprev;
};
-#define INIT_HLIST_BL_HEAD(ptr) \
- ((ptr)->first = NULL)
+
+static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h)
+{
+ h->first = NULL;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ raw_spin_lock_init(&h->lock);
+#endif
+}
static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
{
@@ -117,12 +127,26 @@ static inline void hlist_bl_del_init(str
static inline void hlist_bl_lock(struct hlist_bl_head *b)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(0, (unsigned long *)b);
+#else
+ raw_spin_lock(&b->lock);
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+ __set_bit(0, (unsigned long *)b);
+#endif
+#endif
}
static inline void hlist_bl_unlock(struct hlist_bl_head *b)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
__bit_spin_unlock(0, (unsigned long *)b);
+#else
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+ __clear_bit(0, (unsigned long *)b);
+#endif
+ raw_spin_unlock(&b->lock);
+#endif
}
static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)

53
debian/patches/features/all/rt/local-irq-rt-depending-variants.patch vendored Normal file
View File

@ -0,0 +1,53 @@
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 21 Jul 2009 22:34:14 +0200
Subject: rt: local_irq_* variants depending on RT/!RT
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Add local_irq_*_(no)rt variant which are mainly used to break
interrupt disabled sections on PREEMPT_RT or to explicitely disable
interrupts on PREEMPT_RT.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/interrupt.h | 2 +-
include/linux/irqflags.h | 19 +++++++++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -176,7 +176,7 @@ extern void devm_free_irq(struct device
#ifdef CONFIG_LOCKDEP
# define local_irq_enable_in_hardirq() do { } while (0)
#else
-# define local_irq_enable_in_hardirq() local_irq_enable()
+# define local_irq_enable_in_hardirq() local_irq_enable_nort()
#endif
extern void disable_irq_nosync(unsigned int irq);
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -147,4 +147,23 @@
#endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
+/*
+ * local_irq* variants depending on RT/!RT
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define local_irq_disable_nort() do { } while (0)
+# define local_irq_enable_nort() do { } while (0)
+# define local_irq_save_nort(flags) do { local_save_flags(flags); } while (0)
+# define local_irq_restore_nort(flags) do { (void)(flags); } while (0)
+# define local_irq_disable_rt() local_irq_disable()
+# define local_irq_enable_rt() local_irq_enable()
+#else
+# define local_irq_disable_nort() local_irq_disable()
+# define local_irq_enable_nort() local_irq_enable()
+# define local_irq_save_nort(flags) local_irq_save(flags)
+# define local_irq_restore_nort(flags) local_irq_restore(flags)
+# define local_irq_disable_rt() do { } while (0)
+# define local_irq_enable_rt() do { } while (0)
+#endif
+
#endif

24
debian/patches/features/all/rt/local-var.patch vendored Normal file
View File

@ -0,0 +1,24 @@
Subject: local-var.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 24 Jun 2011 18:40:37 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/percpu.h | 5 +++++
1 file changed, 5 insertions(+)
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,6 +48,11 @@
preempt_enable(); \
} while (0)
+#define get_local_var(var) get_cpu_var(var)
+#define put_local_var(var) put_cpu_var(var)
+#define get_local_ptr(var) get_cpu_ptr(var)
+#define put_local_ptr(var) put_cpu_ptr(var)
+
/* minimum unit size, also is the maximum supported allocation size */
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)

47
debian/patches/features/all/rt/local-vars-migrate-disable.patch vendored Normal file
View File

@ -0,0 +1,47 @@
Subject: local-vars-migrate-disable.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 28 Jun 2011 20:42:16 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/percpu.h | 28 ++++++++++++++++++++++++----
1 file changed, 24 insertions(+), 4 deletions(-)
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,10 +48,30 @@
preempt_enable(); \
} while (0)
-#define get_local_var(var) get_cpu_var(var)
-#define put_local_var(var) put_cpu_var(var)
-#define get_local_ptr(var) get_cpu_ptr(var)
-#define put_local_ptr(var) put_cpu_ptr(var)
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define get_local_var(var) get_cpu_var(var)
+# define put_local_var(var) put_cpu_var(var)
+# define get_local_ptr(var) get_cpu_ptr(var)
+# define put_local_ptr(var) put_cpu_ptr(var)
+#else
+# define get_local_var(var) (*({ \
+ migrate_disable(); \
+ &__get_cpu_var(var); }))
+
+# define put_local_var(var) do { \
+ (void)&(var); \
+ migrate_enable(); \
+} while (0)
+
+# define get_local_ptr(var) ({ \
+ migrate_disable(); \
+ this_cpu_ptr(var); })
+
+# define put_local_ptr(var) do { \
+ (void)(var); \
+ migrate_enable(); \
+} while (0)
+#endif
/* minimum unit size, also is the maximum supported allocation size */
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)

16
debian/patches/features/all/rt/localversion.patch vendored Normal file
View File

@ -0,0 +1,16 @@
Subject: localversion.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 08 Jul 2011 20:25:16 +0200
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.12/patches-3.12.0-rt2.tar.xz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-8vdw4bfcsds27cvox6rpb334@git.kernel.org
---
localversion-rt | 1 +
1 file changed, 1 insertion(+)
--- /dev/null
+++ b/localversion-rt
@@ -0,0 +1 @@
+-rt2

Some files were not shown because too many files have changed in this diff Show More