From d7aacaddcac3971e33cf52d7e610c06696cb347f Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 8 Jul 2009 13:21:31 +0200 Subject: Driver Core: Add platform device arch data V3 Allow architecture specific data in struct platform_device V3. With this patch struct pdev_archdata is added to struct platform_device, similar to struct dev_archdata in found in struct device. Useful for architecture code that needs to keep extra data associated with each platform device. Struct pdev_archdata is different from dev.platform_data, the convention is that dev.platform_data points to driver-specific data. It may or may not be required by the driver. The format of this depends on driver but is the same across architectures. The structure pdev_archdata is a place for architecture specific data. This data is handled by architecture specific code (for example runtime PM), and since it is architecture specific it should _never_ be touched by device driver code. Exactly like struct dev_archdata but for platform devices. [rjw: This change is for power management mostly and that's why it goes through the suspend tree.] Signed-off-by: Magnus Damm Acked-by: Kevin Hilman Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/platform_device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 8dc5123b6305..672a69849735 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -22,6 +22,9 @@ struct platform_device { struct resource * resource; struct platform_device_id *id_entry; + + /* arch specific additions */ + struct pdev_archdata archdata; }; #define platform_get_device_id(pdev) ((pdev)->id_entry) -- cgit v1.2.3 From 511647ff58fd0f1c1f415d2c757d841650edac91 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 8 Jul 2009 13:23:07 +0200 Subject: PM: Remove platform device suspend_late()/resume_early() V2 This is V2 of the platform driver power management late/early callback removal patch. The callbacks ->suspend_late() and ->resume_early() are removed since all in-tree users now have been migrated to dev_pm_ops. Signed-off-by: Magnus Damm Acked-by: Greg Kroah-Hartman Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/platform_device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 672a69849735..3c6675c2444b 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -60,8 +60,6 @@ struct platform_driver { int (*remove)(struct platform_device *); void (*shutdown)(struct platform_device *); int (*suspend)(struct platform_device *, pm_message_t state); - int (*suspend_late)(struct platform_device *, pm_message_t state); - int (*resume_early)(struct platform_device *); int (*resume)(struct platform_device *); struct device_driver driver; struct platform_device_id *id_table; -- cgit v1.2.3 From d9ab77161d811ffb0bccf396f7155cc905c1b9e1 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 22 Jul 2009 00:37:25 +0200 Subject: Driver Core: Make PM operations a const pointer They are not supposed to be modified by drivers, so make them const. Signed-off-by: Dmitry Torokhov Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index aebb81036db2..a28642975053 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -62,7 +62,7 @@ struct bus_type { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); - struct dev_pm_ops *pm; + const struct dev_pm_ops *pm; struct bus_type_private *p; }; @@ -132,7 +132,7 @@ struct device_driver { int (*resume) (struct device *dev); struct attribute_group **groups; - struct dev_pm_ops *pm; + const struct dev_pm_ops *pm; struct driver_private *p; }; @@ -200,7 +200,8 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); - struct dev_pm_ops *pm; + const struct dev_pm_ops *pm; + struct class_private *p; }; @@ -291,7 +292,7 @@ struct device_type { char *(*nodename)(struct device *dev); void (*release)(struct device *dev); - struct dev_pm_ops *pm; + const struct dev_pm_ops *pm; }; /* interface for exporting device attributes */ -- cgit v1.2.3 From 9c0d90103c7e0eb6e638e5b649e9f6d8d9c1b4b3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:53:58 -0400 Subject: Capabilities: move cap_file_mmap to commoncap.c Currently we duplicate the mmap_min_addr test in cap_file_mmap and in security_file_mmap if !CONFIG_SECURITY. This patch moves cap_file_mmap into commoncap.c and then calls that function directly from security_file_mmap ifndef CONFIG_SECURITY like all of the other capability checks are done. Signed-off-by: Eric Paris Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/security.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 5eff459b3833..ac4bc3760b46 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -66,6 +66,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only); extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -2197,9 +2200,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { - if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) - return -EACCES; - return 0; + return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); } static inline int security_file_mprotect(struct vm_area_struct *vma, -- cgit v1.2.3 From 788084aba2ab7348257597496befcbccabdc98a3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:54:11 -0400 Subject: Security/SELinux: seperate lsm specific mmap_min_addr Currently SELinux enforcement of controls on the ability to map low memory is determined by the mmap_min_addr tunable. This patch causes SELinux to ignore the tunable and instead use a seperate Kconfig option specific to how much space the LSM should protect. The tunable will now only control the need for CAP_SYS_RAWIO and SELinux permissions will always protect the amount of low memory designated by CONFIG_LSM_MMAP_MIN_ADDR. This allows users who need to disable the mmap_min_addr controls (usual reason being they run WINE as a non-root user) to do so and still have SELinux controls preventing confined domains (like a web server) from being able to map some area of low memory. Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/mm.h | 15 --------------- include/linux/security.h | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ba3a7cb1eaa0..9a72cc78e6b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif -extern unsigned long mmap_min_addr; - #include #include #include @@ -574,19 +572,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, set_page_section(page, pfn_to_section_nr(pfn)); } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/security.h b/include/linux/security.h index ac4bc3760b46..dc3472c1f781 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -28,6 +28,7 @@ #include #include #include +#include /* PAGE_ALIGN */ #include #include #include @@ -95,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); extern int cap_netlink_recv(struct sk_buff *skb, int cap); extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; /* * Values used in the task_security_ops calls */ @@ -147,6 +149,21 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From 1d9959734a1949ea4f2427bd2d8b21ede6b2441c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 7 Aug 2009 14:53:57 -0400 Subject: security: define round_hint_to_min in !CONFIG_SECURITY Fix the header files to define round_hint_to_min() and to define mmap_min_addr_handler() in the !CONFIG_SECURITY case. Built and tested with !CONFIG_SECURITY Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index dc3472c1f781..1f16eea2017b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,6 +121,21 @@ struct request_sock; #define LSM_UNSAFE_PTRACE 2 #define LSM_UNSAFE_PTRACE_CAP 4 +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -149,21 +164,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From c1a8f1f1c8e01eab5862c8db39b49ace814e6c66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 Aug 2009 09:36:49 +0000 Subject: net: restore gnet_stats_basic to previous definition In 5e140dfc1fe87eae27846f193086724806b33c7d "net: reorder struct Qdisc for better SMP performance" the definition of struct gnet_stats_basic changed incompatibly, as copies of this struct are shipped to userland via netlink. Restoring old behavior is not welcome, for performance reason. Fix is to use a private structure for kernel, and teach gnet_stats_copy_basic() to convert from kernel to user land, using legacy structure (struct gnet_stats_basic) Based on a report and initial patch from Michael Spang. Reported-by: Michael Spang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/gen_stats.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h index 0ffa41df0ee8..710e901085d0 100644 --- a/include/linux/gen_stats.h +++ b/include/linux/gen_stats.h @@ -19,6 +19,11 @@ enum { * @packets: number of seen packets */ struct gnet_stats_basic +{ + __u64 bytes; + __u32 packets; +}; +struct gnet_stats_basic_packed { __u64 bytes; __u32 packets; -- cgit v1.2.3 From 0753ba01e126020bf0f8150934903b48935b697d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 18 Aug 2009 14:11:10 -0700 Subject: mm: revert "oom: move oom_adj value" The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit 2ff05b2b and related commit. Reverted commit list --------------------- - commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct) - commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit 8123681022 (oom: only oom kill exiting tasks with attached memory) - commit 933b787b57 (mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/sched.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7acc8439d9b3..0042090a4d70 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,8 +240,6 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - s8 oom_adj; /* OOM kill score adjustment (bit shift) */ - cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3ab08e4bb6b8..0f1ea4a66957 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1198,6 +1198,7 @@ struct task_struct { * a short time */ unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif -- cgit v1.2.3 From f4b0373b26567cafd421d91101852ed7a34e9e94 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 21 Aug 2009 09:26:15 -0700 Subject: Make bitmask 'and' operators return a result code When 'and'ing two bitmasks (where 'andnot' is a variation on it), some cases want to know whether the result is the empty set or not. In particular, the TLB IPI sending code wants to do cpumask operations and determine if there are any CPU's left in the final set. So this just makes the bitmask (and cpumask) functions return a boolean for whether the result has any bits set. Cc: stable@kernel.org (2.6.30, needed by TLB shootdown fix) Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 18 ++++++++---------- include/linux/cpumask.h | 20 ++++++++++---------- 2 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 2878811c6134..756d78b8c1c5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -94,13 +94,13 @@ extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, int shift, int bits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, int shift, int bits); -extern void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); -extern void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); @@ -171,13 +171,12 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, } } -static inline void bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & *src2; - else - __bitmap_and(dst, src1, src2, nbits); + return (*dst = *src1 & *src2) != 0; + return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, @@ -198,13 +197,12 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1, +static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, int nbits) { if (small_const_nbits(nbits)) - *dst = *src1 & ~(*src2); - else - __bitmap_andnot(dst, src1, src2, nbits); + return (*dst = *src1 & ~(*src2)) != 0; + return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c5ac87ca7bc6..796df12091b7 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -43,10 +43,10 @@ * int cpu_isset(cpu, mask) true iff bit 'cpu' set in mask * int cpu_test_and_set(cpu, mask) test and set bit 'cpu' in mask * - * void cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] + * int cpus_and(dst, src1, src2) dst = src1 & src2 [intersection] * void cpus_or(dst, src1, src2) dst = src1 | src2 [union] * void cpus_xor(dst, src1, src2) dst = src1 ^ src2 - * void cpus_andnot(dst, src1, src2) dst = src1 & ~src2 + * int cpus_andnot(dst, src1, src2) dst = src1 & ~src2 * void cpus_complement(dst, src) dst = ~src * * int cpus_equal(mask1, mask2) Does mask1 == mask2? @@ -179,10 +179,10 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) } #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) @@ -201,10 +201,10 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, #define cpus_andnot(dst, src1, src2) \ __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) -static inline void __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, +static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, const cpumask_t *src2p, int nbits) { - bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); + return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS) @@ -738,11 +738,11 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_and(struct cpumask *dstp, +static inline int cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } @@ -779,11 +779,11 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_andnot(struct cpumask *dstp, +static inline int cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { - bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), + return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } -- cgit v1.2.3 From 5e928f77a09a07f9dd595bb8a489965d69a83458 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 18 Aug 2009 23:38:32 +0200 Subject: PM: Introduce core framework for run-time PM of I/O devices (rev. 17) Introduce a core framework for run-time power management of I/O devices. Add device run-time PM fields to 'struct dev_pm_info' and device run-time PM callbacks to 'struct dev_pm_ops'. Introduce a run-time PM workqueue and define some device run-time PM helper functions at the core level. Document all these things. Special thanks to Alan Stern for his help with the design and multiple detailed reviews of the pereceding versions of this patch and to Magnus Damm for testing feedback. Signed-off-by: Rafael J. Wysocki Acked-by: Magnus Damm --- include/linux/pm.h | 101 +++++++++++++++++++++++++++++++++++++-- include/linux/pm_runtime.h | 114 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 212 insertions(+), 3 deletions(-) create mode 100644 include/linux/pm_runtime.h (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index b3f74764a586..2b6e20df0e52 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -22,6 +22,10 @@ #define _LINUX_PM_H #include +#include +#include +#include +#include /* * Callbacks for platform drivers to implement. @@ -165,6 +169,28 @@ typedef struct pm_message { * It is allowed to unregister devices while the above callbacks are being * executed. However, it is not allowed to unregister a device from within any * of its own callbacks. + * + * There also are the following callbacks related to run-time power management + * of devices: + * + * @runtime_suspend: Prepare the device for a condition in which it won't be + * able to communicate with the CPU(s) and RAM due to power management. + * This need not mean that the device should be put into a low power state. + * For example, if the device is behind a link which is about to be turned + * off, the device may remain at full power. If the device does go to low + * power and if device_may_wakeup(dev) is true, remote wake-up (i.e., a + * hardware mechanism allowing the device to request a change of its power + * state, such as PCI PME) should be enabled for it. + * + * @runtime_resume: Put the device into the fully active state in response to a + * wake-up event generated by hardware or at the request of software. If + * necessary, put the device into the full power state and restore its + * registers, so that it is fully operational. + * + * @runtime_idle: Device appears to be inactive and it might be put into a low + * power state if all of the necessary conditions are satisfied. Check + * these conditions and handle the device as appropriate, possibly queueing + * a suspend request for it. The return value is ignored by the PM core. */ struct dev_pm_ops { @@ -182,6 +208,9 @@ struct dev_pm_ops { int (*thaw_noirq)(struct device *dev); int (*poweroff_noirq)(struct device *dev); int (*restore_noirq)(struct device *dev); + int (*runtime_suspend)(struct device *dev); + int (*runtime_resume)(struct device *dev); + int (*runtime_idle)(struct device *dev); }; /** @@ -315,14 +344,80 @@ enum dpm_state { DPM_OFF_IRQ, }; +/** + * Device run-time power management status. + * + * These status labels are used internally by the PM core to indicate the + * current status of a device with respect to the PM core operations. They do + * not reflect the actual power state of the device or its status as seen by the + * driver. + * + * RPM_ACTIVE Device is fully operational. Indicates that the device + * bus type's ->runtime_resume() callback has completed + * successfully. + * + * RPM_SUSPENDED Device bus type's ->runtime_suspend() callback has + * completed successfully. The device is regarded as + * suspended. + * + * RPM_RESUMING Device bus type's ->runtime_resume() callback is being + * executed. + * + * RPM_SUSPENDING Device bus type's ->runtime_suspend() callback is being + * executed. + */ + +enum rpm_status { + RPM_ACTIVE = 0, + RPM_RESUMING, + RPM_SUSPENDED, + RPM_SUSPENDING, +}; + +/** + * Device run-time power management request types. + * + * RPM_REQ_NONE Do nothing. + * + * RPM_REQ_IDLE Run the device bus type's ->runtime_idle() callback + * + * RPM_REQ_SUSPEND Run the device bus type's ->runtime_suspend() callback + * + * RPM_REQ_RESUME Run the device bus type's ->runtime_resume() callback + */ + +enum rpm_request { + RPM_REQ_NONE = 0, + RPM_REQ_IDLE, + RPM_REQ_SUSPEND, + RPM_REQ_RESUME, +}; + struct dev_pm_info { pm_message_t power_state; - unsigned can_wakeup:1; - unsigned should_wakeup:1; + unsigned int can_wakeup:1; + unsigned int should_wakeup:1; enum dpm_state status; /* Owned by the PM core */ -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM_SLEEP struct list_head entry; #endif +#ifdef CONFIG_PM_RUNTIME + struct timer_list suspend_timer; + unsigned long timer_expires; + struct work_struct work; + wait_queue_head_t wait_queue; + spinlock_t lock; + atomic_t usage_count; + atomic_t child_count; + unsigned int disable_depth:3; + unsigned int ignore_children:1; + unsigned int idle_notification:1; + unsigned int request_pending:1; + unsigned int deferred_resume:1; + enum rpm_request request; + enum rpm_status runtime_status; + int runtime_error; +#endif }; /* diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h new file mode 100644 index 000000000000..44087044910f --- /dev/null +++ b/include/linux/pm_runtime.h @@ -0,0 +1,114 @@ +/* + * pm_runtime.h - Device run-time power management helper functions. + * + * Copyright (C) 2009 Rafael J. Wysocki + * + * This file is released under the GPLv2. + */ + +#ifndef _LINUX_PM_RUNTIME_H +#define _LINUX_PM_RUNTIME_H + +#include +#include + +#ifdef CONFIG_PM_RUNTIME + +extern struct workqueue_struct *pm_wq; + +extern int pm_runtime_idle(struct device *dev); +extern int pm_runtime_suspend(struct device *dev); +extern int pm_runtime_resume(struct device *dev); +extern int pm_request_idle(struct device *dev); +extern int pm_schedule_suspend(struct device *dev, unsigned int delay); +extern int pm_request_resume(struct device *dev); +extern int __pm_runtime_get(struct device *dev, bool sync); +extern int __pm_runtime_put(struct device *dev, bool sync); +extern int __pm_runtime_set_status(struct device *dev, unsigned int status); +extern int pm_runtime_barrier(struct device *dev); +extern void pm_runtime_enable(struct device *dev); +extern void __pm_runtime_disable(struct device *dev, bool check_resume); + +static inline bool pm_children_suspended(struct device *dev) +{ + return dev->power.ignore_children + || !atomic_read(&dev->power.child_count); +} + +static inline void pm_suspend_ignore_children(struct device *dev, bool enable) +{ + dev->power.ignore_children = enable; +} + +static inline void pm_runtime_get_noresume(struct device *dev) +{ + atomic_inc(&dev->power.usage_count); +} + +static inline void pm_runtime_put_noidle(struct device *dev) +{ + atomic_add_unless(&dev->power.usage_count, -1, 0); +} + +#else /* !CONFIG_PM_RUNTIME */ + +static inline int pm_runtime_idle(struct device *dev) { return -ENOSYS; } +static inline int pm_runtime_suspend(struct device *dev) { return -ENOSYS; } +static inline int pm_runtime_resume(struct device *dev) { return 0; } +static inline int pm_request_idle(struct device *dev) { return -ENOSYS; } +static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) +{ + return -ENOSYS; +} +static inline int pm_request_resume(struct device *dev) { return 0; } +static inline int __pm_runtime_get(struct device *dev, bool sync) { return 1; } +static inline int __pm_runtime_put(struct device *dev, bool sync) { return 0; } +static inline int __pm_runtime_set_status(struct device *dev, + unsigned int status) { return 0; } +static inline int pm_runtime_barrier(struct device *dev) { return 0; } +static inline void pm_runtime_enable(struct device *dev) {} +static inline void __pm_runtime_disable(struct device *dev, bool c) {} + +static inline bool pm_children_suspended(struct device *dev) { return false; } +static inline void pm_suspend_ignore_children(struct device *dev, bool en) {} +static inline void pm_runtime_get_noresume(struct device *dev) {} +static inline void pm_runtime_put_noidle(struct device *dev) {} + +#endif /* !CONFIG_PM_RUNTIME */ + +static inline int pm_runtime_get(struct device *dev) +{ + return __pm_runtime_get(dev, false); +} + +static inline int pm_runtime_get_sync(struct device *dev) +{ + return __pm_runtime_get(dev, true); +} + +static inline int pm_runtime_put(struct device *dev) +{ + return __pm_runtime_put(dev, false); +} + +static inline int pm_runtime_put_sync(struct device *dev) +{ + return __pm_runtime_put(dev, true); +} + +static inline int pm_runtime_set_active(struct device *dev) +{ + return __pm_runtime_set_status(dev, RPM_ACTIVE); +} + +static inline void pm_runtime_set_suspended(struct device *dev) +{ + __pm_runtime_set_status(dev, RPM_SUSPENDED); +} + +static inline void pm_runtime_disable(struct device *dev) +{ + __pm_runtime_disable(dev, true); +} + +#endif -- cgit v1.2.3