From 2f9f28b212a2bd4948c8ceaaec33ce0123632129 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 4 Apr 2011 15:19:25 +0200 Subject: netfilter: ipset: references are protected by rwlock instead of mutex The timeout variant of the list:set type must reference the member sets. However, its garbage collector runs at timer interrupt so the mutex protection of the references is a no go. Therefore the reference protection is converted to rwlock. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy --- include/linux/netfilter/ipset/ip_set.h | 2 +- include/linux/netfilter/ipset/ip_set_ahash.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ec333d83f3b4..5a262e3ae715 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -293,7 +293,7 @@ struct ip_set { /* Lock protecting the set data */ rwlock_t lock; /* References to the set */ - atomic_t ref; + u32 ref; /* The core set type */ struct ip_set_type *type; /* The type variant doing the real job */ diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index ec9d9bea1e37..a0196ac79051 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -515,8 +515,7 @@ type_pf_head(struct ip_set *set, struct sk_buff *skb) if (h->netmask != HOST_MASK) NLA_PUT_U8(skb, IPSET_ATTR_NETMASK, h->netmask); #endif - NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, - htonl(atomic_read(&set->ref) - 1)); + NLA_PUT_NET32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)); NLA_PUT_NET32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)); if (with_timeout(h->timeout)) NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)); -- cgit v1.2.3 From 31ad3dd64e689bc79dd819f8f134b9b025240eb8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 16:56:29 +0200 Subject: netfilter: af_info: add network namespace parameter to route hook This is required to eventually replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index eeec00abb664..20ed4528e850 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -270,7 +270,8 @@ struct nf_afinfo { unsigned int dataoff, unsigned int len, u_int8_t protocol); - int (*route)(struct dst_entry **dst, struct flowi *fl); + int (*route)(struct net *net, struct dst_entry **dst, + struct flowi *fl); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, -- cgit v1.2.3 From 0fae2e7740aca7e384c5f337f458897e7e337d58 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 4 Apr 2011 17:00:54 +0200 Subject: netfilter: af_info: add 'strict' parameter to limit lookup to .oif ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search to an interface, but this flag cannot be set via struct flowi. Also, it cannot be set via ip6_route_output: this function uses the passed sock struct to determine if this flag is required (by testing for nonzero sk_bound_dev_if). Work around this by passing in an artificial struct sk in case 'strict' argument is true. This is required to replace the rt6_lookup call in xt_addrtype.c with nf_afinfo->route(). Signed-off-by: Florian Westphal Acked-by: David S. Miller Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 20ed4528e850..7fa95df60146 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -271,7 +271,7 @@ struct nf_afinfo { unsigned int len, u_int8_t protocol); int (*route)(struct net *net, struct dst_entry **dst, - struct flowi *fl); + struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); int (*reroute)(struct sk_buff *skb, -- cgit v1.2.3 From 34206f267120c839a479d0237db907fa062e7b0f Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Tue, 5 Apr 2011 07:08:41 +0000 Subject: can: mcp251x: Allow pass IRQ flags through platform data. When an interrupt occurs, the INT pin is driven low by the MCP251x controller (falling edge) but in some cases the INT pin can be connected to the MPU through a transistor or level translator which inverts this signal. In this case interrupt should be configured in rising edge. This patch adds support to pass the IRQ flags via mcp251x_platform_data. Signed-off-by: Enric Balletbo i Serra Acked-by: Wolfgang Grandegger Acked-by: Marc Kleine-Budde Signed-off-by: David S. Miller --- include/linux/can/platform/mcp251x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h index 8e20540043f5..089fe43211a4 100644 --- a/include/linux/can/platform/mcp251x.h +++ b/include/linux/can/platform/mcp251x.h @@ -12,6 +12,7 @@ /** * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data * @oscillator_frequency: - oscillator frequency in Hz + * @irq_flags: - IRQF configuration flags * @board_specific_setup: - called before probing the chip (power,reset) * @transceiver_enable: - called to power on/off the transceiver * @power_enable: - called to power on/off the mcp *and* the @@ -24,6 +25,7 @@ struct mcp251x_platform_data { unsigned long oscillator_frequency; + unsigned long irq_flags; int (*board_specific_setup)(struct spi_device *spi); int (*transceiver_enable)(int enable); int (*power_enable) (int enable); -- cgit v1.2.3 From 1f112cee07b314e244ee9e71d9c1e6950dc13327 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 11 Apr 2011 22:54:42 +0200 Subject: PM / Hibernate: Introduce CONFIG_HIBERNATE_CALLBACKS Xen save/restore is going to use hibernate device callbacks for quiescing devices and putting them back to normal operations and it would need to select CONFIG_HIBERNATION for this purpose. However, that also would cause the hibernate interfaces for user space to be enabled, which might confuse user space, because the Xen kernels don't support hibernation. Moreover, it would be wasteful, as it would make the Xen kernels include a substantial amount of code that they would never use. To address this issue introduce new power management Kconfig option CONFIG_HIBERNATE_CALLBACKS, such that it will only select the code that is necessary for the hibernate device callbacks to work and make CONFIG_HIBERNATION select it. Then, Xen save/restore will be able to select CONFIG_HIBERNATE_CALLBACKS without dragging the entire hibernate code along with it. Signed-off-by: Rafael J. Wysocki Tested-by: Shriram Rajagopalan --- include/linux/suspend.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5a89e3612875..083ffea7ba18 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -249,6 +249,8 @@ extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); #else /* CONFIG_HIBERNATION */ +static inline void register_nosave_region(unsigned long b, unsigned long e) {} +static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} @@ -297,14 +299,7 @@ static inline bool pm_wakeup_pending(void) { return false; } extern struct mutex pm_mutex; -#ifndef CONFIG_HIBERNATION -static inline void register_nosave_region(unsigned long b, unsigned long e) -{ -} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) -{ -} - +#ifndef CONFIG_HIBERNATE_CALLBACKS static inline void lock_system_sleep(void) {} static inline void unlock_system_sleep(void) {} -- cgit v1.2.3 From e710d7d5a9cab1041b7a3cf9e655b75d92786857 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Fri, 8 Apr 2011 00:43:01 +0200 Subject: mfd: Fetch cell pointer from platform_device->mfd_cell In order for MFD drivers to fetch their cell pointer but also their platform data one, an mfd cell pointer is added to the platform_device structure. That allows all MFD sub devices drivers to be MFD agnostic, unless they really need to access their MFD cell data. Most of them don't, especially the ones for IPs used by both MFD and non MFD SoCs. Cc: Grant Likely Acked-by: Greg KH Signed-off-by: Samuel Ortiz --- include/linux/mfd/core.h | 13 +++++++++++-- include/linux/platform_device.h | 5 +++++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index ad1b19aa6508..aef23309a742 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -86,16 +86,25 @@ extern int mfd_clone_cell(const char *cell, const char **clones, */ static inline const struct mfd_cell *mfd_get_cell(struct platform_device *pdev) { - return pdev->dev.platform_data; + return pdev->mfd_cell; } /* * Given a platform device that's been created by mfd_add_devices(), fetch * the .mfd_data entry from the mfd_cell that created it. + * Otherwise just return the platform_data pointer. + * This maintains compatibility with platform drivers whose devices aren't + * created by the mfd layer, and expect platform_data to contain what would've + * otherwise been in mfd_data. */ static inline void *mfd_get_data(struct platform_device *pdev) { - return mfd_get_cell(pdev)->mfd_data; + const struct mfd_cell *cell = mfd_get_cell(pdev); + + if (cell) + return cell->mfd_data; + else + return pdev->dev.platform_data; } extern int mfd_add_devices(struct device *parent, int id, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index d96db9825708..744942c95fec 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -14,6 +14,8 @@ #include #include +struct mfd_cell; + struct platform_device { const char * name; int id; @@ -23,6 +25,9 @@ struct platform_device { const struct platform_device_id *id_entry; + /* MFD cell pointer */ + struct mfd_cell *mfd_cell; + /* arch specific additions */ struct pdev_archdata archdata; }; -- cgit v1.2.3 From be85bccaa5aa5a11dcaf85f9e945ffefd253f631 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 12 Apr 2011 13:35:56 -0700 Subject: Revert "vfs: Export file system uuid via /proc//mountinfo" This reverts commit 93f1c20bc8cdb757be50566eff88d65c3b26881f. It turns out that libmount misparses it because it adds a '-' character in the uuid string, which libmount then incorrectly confuses with the separator string (" - ") at the end of all the optional arguments. Upstream libmount (in the util-linux tree) has been fixed, but until that fix actually percolates up to users, we'd better not expose this change in the kernel. Let's revisit this later (possibly by exposing the UUID without any '-' characters in it, avoiding the user-space bug). Reported-by: Dave Jones Cc: Aneesh Kumar K.V Cc: Al Viro Cc: Karel Zak Cc: Ram Pai Cc: Miklos Szeredi Cc: Eric Sandeen Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dbd860af0804..5b14843af9f9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1403,7 +1403,6 @@ struct super_block { wait_queue_head_t s_wait_unfrozen; char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ void *s_fs_info; /* Filesystem private info */ fmode_t s_mode; -- cgit v1.2.3 From 0bba01695b74fdd2f9286243bb39f88544d81401 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 12 Apr 2011 15:21:04 -0700 Subject: vfs: Re-introduce s_uuid in the superblock Gaah. When commit be85bccaa5aa reverted the export of file system uuid via /proc//mountinfo, it also unintentionally removed the s_uuid field in struct super_block. I didn't mean to do that, since filesystems have been taught to fill it in (and we want to keep it for future re-introduction in the mountinfo file). Stupid of me. This adds it back in. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5b14843af9f9..dbd860af0804 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1403,6 +1403,7 @@ struct super_block { wait_queue_head_t s_wait_unfrozen; char s_id[32]; /* Informational name */ + u8 s_uuid[16]; /* UUID */ void *s_fs_info; /* Filesystem private info */ fmode_t s_mode; -- cgit v1.2.3 From 184748cc50b2dceb8287f9fb657eda48ff8fcfe7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:39 +0200 Subject: sched: Provide scheduler_ipi() callback in response to smp_send_reschedule() For future rework of try_to_wake_up() we'd like to push part of that function onto the CPU the task is actually going to run on. In order to do so we need a generic callback from the existing scheduler IPI. This patch introduces such a generic callback: scheduler_ipi() and implements it as a NOP. BenH notes: PowerPC might use this IPI on offline CPUs under rare conditions! Acked-by: Russell King Acked-by: Martin Schwidefsky Acked-by: Chris Metcalf Acked-by: Jesper Nilsson Acked-by: Benjamin Herrenschmidt Signed-off-by: Ralf Baechle Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.744338123@chello.nl --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ec2c027e92c..758e27afcda5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2189,8 +2189,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP +static inline void scheduler_ipi(void) { } extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else +static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) { -- cgit v1.2.3 From 3ca7a440da394808571dad32d33d3bc0389982e6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:40 +0200 Subject: sched: Always provide p->on_cpu Always provide p->on_cpu so that we can determine if its on a cpu without having to lock the rq. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152728.785452014@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 758e27afcda5..3435837e89ff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1200,9 +1200,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP -#ifdef __ARCH_WANT_UNLOCKED_CTXSW - int oncpu; -#endif + int on_cpu; #endif int prio, static_prio, normal_prio; -- cgit v1.2.3 From c6eb3dda25892f1f974f5420f63e6721aab02f6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:41 +0200 Subject: mutex: Use p->on_cpu for the adaptive spin Since we now have p->on_cpu unconditionally available, use it to re-implement mutex_spin_on_owner. Requested-by: Thomas Gleixner Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.826338173@chello.nl --- include/linux/mutex.h | 2 +- include/linux/sched.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 94b48bd40dd7..c75471db576e 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -51,7 +51,7 @@ struct mutex { spinlock_t wait_lock; struct list_head wait_list; #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) - struct thread_info *owner; + struct task_struct *owner; #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/sched.h b/include/linux/sched.h index 3435837e89ff..173850479e2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -360,7 +360,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); +extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; -- cgit v1.2.3 From fd2f4419b4cbe8fe90796df9617c355762afd6a4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:44 +0200 Subject: sched: Provide p->on_rq Provide a generic p->on_rq because the p->se.on_rq semantics are unfavourable for lockless wakeups but needed for sched_fair. In particular, p->on_rq is only cleared when we actually dequeue the task in schedule() and not on any random dequeue as done by things like __migrate_task() and __sched_setscheduler(). This also allows us to remove p->se usage from !sched_fair code. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152728.949545047@chello.nl --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 173850479e2c..b33a700652dc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1202,6 +1202,7 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; #endif + int on_rq; int prio, static_prio, normal_prio; unsigned int rt_priority; -- cgit v1.2.3 From 7608dec2ce2004c234339bef8c8074e5e601d0e9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:46 +0200 Subject: sched: Drop the rq argument to sched_class::select_task_rq() In preparation of calling select_task_rq() without rq->lock held, drop the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.031077745@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b33a700652dc..ff4e2f9c24a7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1067,8 +1067,7 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct rq *rq, struct task_struct *p, - int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); -- cgit v1.2.3 From 74f8e4b2335de45485b8d5b31a504747f13c8070 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:47 +0200 Subject: sched: Remove rq argument to sched_class::task_waking() In preparation of calling this without rq->lock held, remove the dependency on the rq argument. Reviewed-by: Frank Rowand Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110405152729.071474242@chello.nl Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff4e2f9c24a7..7f5732f8c618 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1048,8 +1048,12 @@ struct sched_domain; #define WF_FORK 0x02 /* child wakeup after fork */ #define ENQUEUE_WAKEUP 1 -#define ENQUEUE_WAKING 2 -#define ENQUEUE_HEAD 4 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif #define DEQUEUE_SLEEP 1 @@ -1071,7 +1075,7 @@ struct sched_class { void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct rq *this_rq, struct task_struct *task); + void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, -- cgit v1.2.3 From a8e4f2eaecc9bfa4954adf79a04f4f22fddd829c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:49 +0200 Subject: sched: Delay task_contributes_to_load() In prepratation of having to call task_contributes_to_load() without holding rq->lock, we need to store the result until we do and can update the rq accounting accordingly. Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.151523907@chello.nl --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7f5732f8c618..25c50317ddc1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1273,6 +1273,7 @@ struct task_struct { /* Revert to default priority/policy when forking */ unsigned sched_reset_on_fork:1; + unsigned sched_contributes_to_load:1; pid_t pid; pid_t tgid; -- cgit v1.2.3 From 317f394160e9beb97d19a84c39b7e5eb3d7815a8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 5 Apr 2011 17:23:58 +0200 Subject: sched: Move the second half of ttwu() to the remote cpu Now that we've removed the rq->lock requirement from the first part of ttwu() and can compute placement without holding any rq->lock, ensure we execute the second half of ttwu() on the actual cpu we want the task to run on. This avoids having to take rq->lock and doing the task enqueue remotely, saving lots on cacheline transfers. As measured using: http://oss.oracle.com/~mason/sembench.c $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 unpatched: run time 30 seconds 647278 worker burns per second patched: run time 30 seconds 816715 worker burns per second Reviewed-by: Frank Rowand Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110405152729.515897185@chello.nl --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 25c50317ddc1..e09dafa6e149 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1203,6 +1203,7 @@ struct task_struct { int lock_depth; /* BKL lock depth */ #ifdef CONFIG_SMP + struct task_struct *wake_entry; int on_cpu; #endif int on_rq; @@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -static inline void scheduler_ipi(void) { } +void scheduler_ipi(void); extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else static inline void scheduler_ipi(void) { } -- cgit v1.2.3