From 17e8351a77397e8a83727eb17e3a3e9b8ab5257a Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 24 Jul 2015 08:12:54 +0200 Subject: thermal: consistently use int for temperatures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The thermal code uses int, long and unsigned long for temperatures in different places. Using an unsigned type limits the thermal framework to positive temperatures without need. Also several drivers currently will report temperatures near UINT_MAX for temperatures below 0°C. This will probably immediately shut the machine down due to overtemperature if started below 0°C. 'long' is 64bit on several architectures. This is not needed since INT_MAX °mC is above the melting point of all known materials. Consistently use a plain 'int' for temperatures throughout the thermal code and the drivers. This only changes the places in the drivers where the temperature is passed around as pointer, when drivers internally use another type this is not changed. Signed-off-by: Sascha Hauer Acked-by: Geert Uytterhoeven Reviewed-by: Jean Delvare Reviewed-by: Lukasz Majewski Reviewed-by: Darren Hart Reviewed-by: Heiko Stuebner Reviewed-by: Peter Feuerer Cc: Punit Agrawal Cc: Zhang Rui Cc: Eduardo Valentin Cc: linux-pm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Jean Delvare Cc: Peter Feuerer Cc: Heiko Stuebner Cc: Lukasz Majewski Cc: Stephen Warren Cc: Thierry Reding Cc: linux-acpi@vger.kernel.org Cc: platform-driver-x86@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-omap@vger.kernel.org Cc: linux-samsung-soc@vger.kernel.org Cc: Guenter Roeck Cc: Rafael J. Wysocki Cc: Maxime Ripard Cc: Darren Hart Cc: lm-sensors@lm-sensors.org Signed-off-by: Zhang Rui --- include/linux/thermal.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 037e9df2f610..17292fee8686 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -92,23 +92,19 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); - int (*get_temp) (struct thermal_zone_device *, unsigned long *); + int (*get_temp) (struct thermal_zone_device *, int *); int (*get_mode) (struct thermal_zone_device *, enum thermal_device_mode *); int (*set_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, enum thermal_trip_type *); - int (*get_trip_temp) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_temp) (struct thermal_zone_device *, int, - unsigned long); - int (*get_trip_hyst) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_hyst) (struct thermal_zone_device *, int, - unsigned long); - int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); - int (*set_emul_temp) (struct thermal_zone_device *, unsigned long); + int (*get_trip_temp) (struct thermal_zone_device *, int, int *); + int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*get_trip_hyst) (struct thermal_zone_device *, int, int *); + int (*set_trip_hyst) (struct thermal_zone_device *, int, int); + int (*get_crit_temp) (struct thermal_zone_device *, int *); + int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); int (*notify) (struct thermal_zone_device *, int, @@ -332,9 +328,9 @@ struct thermal_genl_event { * temperature. */ struct thermal_zone_of_device_ops { - int (*get_temp)(void *, long *); + int (*get_temp)(void *, int *); int (*get_trend)(void *, long *); - int (*set_emul_temp)(void *, unsigned long); + int (*set_emul_temp)(void *, int); }; /** @@ -406,7 +402,7 @@ thermal_of_cooling_device_register(struct device_node *np, char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); -int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); +int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, @@ -457,7 +453,7 @@ static inline struct thermal_zone_device *thermal_zone_get_zone_by_name( const char *name) { return ERR_PTR(-ENODEV); } static inline int thermal_zone_get_temp( - struct thermal_zone_device *tz, unsigned long *temp) + struct thermal_zone_device *tz, int *temp) { return -ENODEV; } static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) { return -ENODEV; } -- cgit v1.2.3 From 8025e5ddf9c1cac0e632dad49a63abf7848b78cb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Jul 2015 11:55:44 -0300 Subject: [media] mm: Provide new get_vaddr_frames() helper Provide new function get_vaddr_frames(). This function maps virtual addresses from given start and fills given array with page frame numbers of the corresponding pages. If given start belongs to a normal vma, the function grabs reference to each of the pages to pin them in memory. If start belongs to VM_IO | VM_PFNMAP vma, we don't touch page structures. Caller must make sure pfns aren't reused for anything else while he is using them. This function is created for various drivers to simplify handling of their buffers. Signed-off-by: Jan Kara Acked-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Andrew Morton Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/mm.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e872f92dbac..79ad29a8a60a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -20,6 +20,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -1198,6 +1199,49 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); + +/* Container for pinned pfns / pages */ +struct frame_vector { + unsigned int nr_allocated; /* Number of frames we have space for */ + unsigned int nr_frames; /* Number of frames stored in ptrs array */ + bool got_ref; /* Did we pin pages by getting page ref? */ + bool is_pfns; /* Does array contain pages or pfns? */ + void *ptrs[0]; /* Array of pinned pfns / pages. Use + * pfns_vector_pages() or pfns_vector_pfns() + * for access */ +}; + +struct frame_vector *frame_vector_create(unsigned int nr_frames); +void frame_vector_destroy(struct frame_vector *vec); +int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, + bool write, bool force, struct frame_vector *vec); +void put_vaddr_frames(struct frame_vector *vec); +int frame_vector_to_pages(struct frame_vector *vec); +void frame_vector_to_pfns(struct frame_vector *vec); + +static inline unsigned int frame_vector_count(struct frame_vector *vec) +{ + return vec->nr_frames; +} + +static inline struct page **frame_vector_pages(struct frame_vector *vec) +{ + if (vec->is_pfns) { + int err = frame_vector_to_pages(vec); + + if (err) + return ERR_PTR(err); + } + return (struct page **)(vec->ptrs); +} + +static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) +{ + if (!vec->is_pfns) + frame_vector_to_pfns(vec); + return (unsigned long *)(vec->ptrs); +} + struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); -- cgit v1.2.3 From 9642d18eee2cd169b60c6ac0f20bda745b5a3d1e Mon Sep 17 00:00:00 2001 From: Vatika Harlalka Date: Tue, 1 Sep 2015 16:50:59 +0200 Subject: nohz: Affine unpinned timers to housekeepers The problem addressed in this patch is about affining unpinned timers. Adaptive or Full Dynticks CPUs are currently disturbed by unnecessary jitter due to firing of such timers on them. This patch will affine timers to online CPUs which are not full dynticks in NOHZ_FULL configured systems. It should not introduce overhead in nohz full off case due to static keys. Signed-off-by: Vatika Harlalka Signed-off-by: Frederic Weisbecker Reviewed-by: Preeti U Murthy Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1441119060-2230-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/tick.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 48d901f83f92..e312219ff823 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -147,11 +147,20 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(void); #else +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } -- cgit v1.2.3 From 5e7c4274a70aa2d6f485996d0ca1dad52d0039ca Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 3 Sep 2015 19:28:20 +0300 Subject: block: Check for gaps on front and back merges We are checking for gaps to previous bio_vec, which can only detect back merges gaps. Moreover, at the point where we check for a gap, we don't know if we will attempt a back or a front merge. Thus, check for gap to prev in a back merge attempt and check for a gap to next in a front merge attempt. Signed-off-by: Jens Axboe [sagig: Minor rename change] Signed-off-by: Sagi Grimberg --- include/linux/blkdev.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a622f270f09e..2ff94def041e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1368,6 +1368,26 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } +static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, + struct bio *next) +{ + if (!bio_has_data(prev)) + return false; + + return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); +} + +static inline bool req_gap_back_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, req->biotail, bio); +} + +static inline bool req_gap_front_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, bio, req->bio); +} + struct work_struct; int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From e74bfeedad08180b968d8613dcde141ffb0720c3 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 13 Jul 2015 08:07:17 -0400 Subject: NTB: Add flow control to the ntb_netdev Right now if we push the NTB really hard, we start dropping packets due to not able to process the packets fast enough. We need to st:qop the upper layer from flooding us when that happens. A timer is necessary in order to restart the queue once the resource has been processed on the receive side. Due to the way NTB is setup, the resources on the tx side are tied to the processing of the rx side and there's no async way to know when the rx side has released those resources. Signed-off-by: Dave Jiang Signed-off-by: Jon Mason --- include/linux/ntb_transport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h index 2862861366a5..7243eb98a722 100644 --- a/include/linux/ntb_transport.h +++ b/include/linux/ntb_transport.h @@ -83,3 +83,4 @@ void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); void ntb_transport_link_up(struct ntb_transport_qp *qp); void ntb_transport_link_down(struct ntb_transport_qp *qp); bool ntb_transport_link_query(struct ntb_transport_qp *qp); +unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp); -- cgit v1.2.3 From a7c23237481782fbea3c2230e362b72863e144b0 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Wed, 15 Jul 2015 04:15:28 -0400 Subject: NTB: Fix documentation for ntb_link_is_up There was a copy and paste error in the documentation for ntb_link_is_up. The long description was mistakenly copied from ntb_link_set_trans. This adds the appropriate long description for ntb_link_is_up. Reported-by: Dave Jiang Signed-off-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index b02f72bb8e32..e3d3299c6052 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -522,10 +522,9 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * @speed: OUT - The link speed expressed as PCIe generation number. * @width: OUT - The link width expressed as the number of PCIe lanes. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Get the current state of the ntb link. It is recommended to query the link + * state once after every link event. It is safe to query the link state in + * the context of the link event callback. * * Return: One if the link is up, zero if the link is down, otherwise a * negative value indicating the error number. -- cgit v1.2.3 From 86663c91866ae85c219f1a80ef2c9460b7ca5cd8 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Wed, 15 Jul 2015 12:43:21 -0400 Subject: NTB: Fix documentation for ntb_peer_db_clear. The documentation should say "peer" not "local" when referring to the peer doorbell register. Reported-by: Dave Jiang Signed-off-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index e3d3299c6052..f798e2afba88 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -794,7 +794,7 @@ static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) } /** - * ntb_peer_db_clear() - clear bits in the local doorbell register + * ntb_peer_db_clear() - clear bits in the peer doorbell register * @ntb: NTB device context. * @db_bits: Doorbell bits to clear. * -- cgit v1.2.3 From edcd591c77a48da753456f92daf8bb50fe9bac93 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 7 Sep 2015 13:18:03 -0600 Subject: locking/static_keys: Fix a silly typo Commit: 412758cb2670 ("jump label, locking/static_keys: Update docs") introduced a typo that might as well get fixed. Signed-off-by: Jonathan Corbet Cc: Andrew Morton Cc: Jason Baron Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150907131803.54c027e1@lwn.net Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 7f653e8f6690..0684bd3a48fc 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -22,7 +22,7 @@ * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * static_key_likely() - * statick_key_unlikely() + * static_key_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we -- cgit v1.2.3 From 8b9558aab853e98ba6e3fee0dd8545544966958c Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 1 Sep 2015 17:19:38 +0800 Subject: libceph: use keepalive2 to verify the mon session is alive Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 2 ++ include/linux/ceph/messenger.h | 4 ++++ include/linux/ceph/msgr.h | 4 +++- 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9ebee53d3bf5..397c5cd09794 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -46,6 +46,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long monc_ping_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -66,6 +67,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_MONC_PING_TIMEOUT_DEFAULT msecs_to_jiffies(30 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 37753278987a..7e1252e97a30 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -248,6 +248,8 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ + struct timespec last_keepalive_ack; + struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ }; @@ -285,6 +287,8 @@ extern void ceph_msg_revoke(struct ceph_msg *msg); extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval); extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 1c1887206ffa..0fe2656ac415 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -84,10 +84,12 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_MSG 7 /* message */ #define CEPH_MSGR_TAG_ACK 8 /* message ack */ #define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ -#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ +#define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ +#define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ /* -- cgit v1.2.3 From 4eafbd15b6c84cd3f6c76022c8a6c27f7cc076e1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 8 Sep 2015 18:41:01 +0200 Subject: PM / OPP: add dev_pm_opp_get_suspend_opp() helper Add dev_pm_opp_get_suspend_opp() helper to obtain suspend opp. Acked-by: Viresh Kumar Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index cab7ba55bedb..e817722ee3f0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,7 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -80,6 +81,11 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + return NULL; +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { -- cgit v1.2.3 From 08e75e754a6d9838e490b74551d19fc04d0fd6f9 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Fri, 14 Aug 2015 18:56:56 +0100 Subject: PM / devfreq: cache the last call to get_dev_status() The return value of get_dev_status() can be reused. Cache it so that other parts of the kernel can reuse it instead of having to call the same function again. Cc: Kyungmin Park Signed-off-by: Javi Merino Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index ce447f0f1bad..70a1c60ddda4 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -161,6 +161,7 @@ struct devfreq { struct delayed_work work; unsigned long previous_freq; + struct devfreq_dev_status last_status; void *data; /* private data for governors */ @@ -204,6 +205,15 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev, extern void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +/** + * devfreq_update_stats() - update the last_status pointer in struct devfreq + * @df: the devfreq instance whose status needs updating + */ +static inline int devfreq_update_stats(struct devfreq *df) +{ + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} + #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq @@ -289,6 +299,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { } + +static inline int devfreq_update_stats(struct devfreq *df) +{ + return -EINVAL; +} #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ -- cgit v1.2.3 From d54cdf3fc91aae3780433471d15d73413a845bc0 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Tue, 18 Aug 2015 13:45:49 +0900 Subject: PM / devfreq: comments for get_dev_status usage updated With the introduction of devfreq_update_stats(), governors are not recommended to use get_dev_status() directly. Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 70a1c60ddda4..68030e22af35 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -65,7 +65,10 @@ struct devfreq_dev_status { * The "flags" parameter's possible values are * explained above with "DEVFREQ_FLAG_*" macros. * @get_dev_status: The device should provide the current performance - * status to devfreq, which is used by governors. + * status to devfreq. Governors are recommended not to + * use this directly. Instead, governors are recommended + * to use devfreq_update_stats() along with + * devfreq.last_status. * @get_cur_freq: The device should provide the current frequency * at which it is operating. * @exit: An optional callback that is called when devfreq @@ -208,6 +211,10 @@ extern void devm_devfreq_unregister_opp_notifier(struct device *dev, /** * devfreq_update_stats() - update the last_status pointer in struct devfreq * @df: the devfreq instance whose status needs updating + * + * Governors are recommended to use this function along with last_status, + * which allows other entities to reuse the last_status without affecting + * the values fetched later by governors. */ static inline int devfreq_update_stats(struct devfreq *df) { -- cgit v1.2.3 From 7f39add3b08cbbdb99abe50e6d7c342e6800d684 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 11 Sep 2015 09:03:04 -0600 Subject: block: Refuse request/bio merges with gaps in the integrity payload If a driver sets the block queue virtual boundary mask, it means that it cannot handle gaps so we must not allow those in the integrity payload as well. Signed-off-by: Sagi Grimberg Fixed up by me to have duplicate integrity merge functions, depending on whether block integrity is enabled or not. Fixes a compilations issue with CONFIG_BLK_DEV_INTEGRITY unset. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2ff94def041e..1aac7316a4b5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1514,6 +1514,26 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + struct bio_integrity_payload *bip = bio_integrity(req->bio); + struct bio_integrity_payload *bip_next = bio_integrity(next); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_integrity_payload *bip_next = bio_integrity(req->bio); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1580,6 +1600,16 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) { return 0; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + return false; +} +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + return false; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From 5b25b13ab08f616efd566347d809b4ece54570d1 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 11 Sep 2015 13:07:39 -0700 Subject: sys_membarrier(): system-wide memory barrier (generic, x86) Here is an implementation of a new system call, sys_membarrier(), which executes a memory barrier on all threads running on the system. It is implemented by calling synchronize_sched(). It can be used to distribute the cost of user-space memory barriers asymmetrically by transforming pairs of memory barriers into pairs consisting of sys_membarrier() and a compiler barrier. For synchronization primitives that distinguish between read-side and write-side (e.g. userspace RCU [1], rwlocks), the read-side can be accelerated significantly by moving the bulk of the memory barrier overhead to the write-side. The existing applications of which I am aware that would be improved by this system call are as follows: * Through Userspace RCU library (http://urcu.so) - DNS server (Knot DNS) https://www.knot-dns.cz/ - Network sniffer (http://netsniff-ng.org/) - Distributed object storage (https://sheepdog.github.io/sheepdog/) - User-space tracing (http://lttng.org) - Network storage system (https://www.gluster.org/) - Virtual routers (https://events.linuxfoundation.org/sites/events/files/slides/DPDK_RCU_0MQ.pdf) - Financial software (https://lkml.org/lkml/2015/3/23/189) Those projects use RCU in userspace to increase read-side speed and scalability compared to locking. Especially in the case of RCU used by libraries, sys_membarrier can speed up the read-side by moving the bulk of the memory barrier cost to synchronize_rcu(). * Direct users of sys_membarrier - core dotnet garbage collector (https://github.com/dotnet/coreclr/issues/198) Microsoft core dotnet GC developers are planning to use the mprotect() side-effect of issuing memory barriers through IPIs as a way to implement Windows FlushProcessWriteBuffers() on Linux. They are referring to sys_membarrier in their github thread, specifically stating that sys_membarrier() is what they are looking for. To explain the benefit of this scheme, let's introduce two example threads: Thread A (non-frequent, e.g. executing liburcu synchronize_rcu()) Thread B (frequent, e.g. executing liburcu rcu_read_lock()/rcu_read_unlock()) In a scheme where all smp_mb() in thread A are ordering memory accesses with respect to smp_mb() present in Thread B, we can change each smp_mb() within Thread A into calls to sys_membarrier() and each smp_mb() within Thread B into compiler barriers "barrier()". Before the change, we had, for each smp_mb() pairs: Thread A Thread B previous mem accesses previous mem accesses smp_mb() smp_mb() following mem accesses following mem accesses After the change, these pairs become: Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses As we can see, there are two possible scenarios: either Thread B memory accesses do not happen concurrently with Thread A accesses (1), or they do (2). 1) Non-concurrent Thread A vs Thread B accesses: Thread A Thread B prev mem accesses sys_membarrier() follow mem accesses prev mem accesses barrier() follow mem accesses In this case, thread B accesses will be weakly ordered. This is OK, because at that point, thread A is not particularly interested in ordering them with respect to its own accesses. 2) Concurrent Thread A vs Thread B accesses Thread A Thread B prev mem accesses prev mem accesses sys_membarrier() barrier() follow mem accesses follow mem accesses In this case, thread B accesses, which are ensured to be in program order thanks to the compiler barrier, will be "upgraded" to full smp_mb() by synchronize_sched(). * Benchmarks On Intel Xeon E5405 (8 cores) (one thread is calling sys_membarrier, the other 7 threads are busy looping) 1000 non-expedited sys_membarrier calls in 33s =3D 33 milliseconds/call. * User-space user of this system call: Userspace RCU library Both the signal-based and the sys_membarrier userspace RCU schemes permit us to remove the memory barrier from the userspace RCU rcu_read_lock() and rcu_read_unlock() primitives, thus significantly accelerating them. These memory barriers are replaced by compiler barriers on the read-side, and all matching memory barriers on the write-side are turned into an invocation of a memory barrier on all active threads in the process. By letting the kernel perform this synchronization rather than dumbly sending a signal to every process threads (as we currently do), we diminish the number of unnecessary wake ups and only issue the memory barriers on active threads. Non-running threads do not need to execute such barrier anyway, because these are implied by the scheduler context switches. Results in liburcu: Operations in 10s, 6 readers, 2 writers: memory barriers in reader: 1701557485 reads, 2202847 writes signal-based scheme: 9830061167 reads, 6700 writes sys_membarrier: 9952759104 reads, 425 writes sys_membarrier (dyn. check): 7970328887 reads, 425 writes The dynamic sys_membarrier availability check adds some overhead to the read-side compared to the signal-based scheme, but besides that, sys_membarrier slightly outperforms the signal-based scheme. However, this non-expedited sys_membarrier implementation has a much slower grace period than signal and memory barrier schemes. Besides diminishing the number of wake-ups, one major advantage of the membarrier system call over the signal-based scheme is that it does not need to reserve a signal. This plays much more nicely with libraries, and with processes injected into for tracing purposes, for which we cannot expect that signals will be unused by the application. An expedited version of this system call can be added later on to speed up the grace period. Its implementation will likely depend on reading the cpu_curr()->mm without holding each CPU's rq lock. This patch adds the system call to x86 and to asm-generic. [1] http://urcu.so membarrier(2) man page: MEMBARRIER(2) Linux Programmer's Manual MEMBARRIER(2) NAME membarrier - issue memory barriers on a set of threads SYNOPSIS #include int membarrier(int cmd, int flags); DESCRIPTION The cmd argument is one of the following: MEMBARRIER_CMD_QUERY Query the set of supported commands. It returns a bitmask of supported commands. MEMBARRIER_CMD_SHARED Execute a memory barrier on all threads running on the system. Upon return from system call, the caller thread is ensured that all running threads have passed through a state where all memory accesses to user-space addresses match program order between entry to and return from the system call (non-running threads are de facto in such a state). This covers threads from all pro=E2=80=90 cesses running on the system. This command returns 0. The flags argument needs to be 0. For future extensions. All memory accesses performed in program order from each targeted thread is guaranteed to be ordered with respect to sys_membarrier(). If we use the semantic "barrier()" to represent a compiler barrier forcing memory accesses to be performed in program order across the barrier, and smp_mb() to represent explicit memory barriers forcing full memory ordering across the barrier, we have the following ordering table for each pair of barrier(), sys_membarrier() and smp_mb(): The pair ordering is detailed as (O: ordered, X: not ordered): barrier() smp_mb() sys_membarrier() barrier() X X O smp_mb() X O O sys_membarrier() O O O RETURN VALUE On success, these system calls return zero. On error, -1 is returned, and errno is set appropriately. For a given command, with flags argument set to 0, this system call is guaranteed to always return the same value until reboot. ERRORS ENOSYS System call is not implemented. EINVAL Invalid arguments. Linux 2015-04-15 MEMBARRIER(2) Signed-off-by: Mathieu Desnoyers Reviewed-by: Paul E. McKenney Reviewed-by: Josh Triplett Cc: KOSAKI Motohiro Cc: Steven Rostedt Cc: Nicholas Miell Cc: Ingo Molnar Cc: Alan Cox Cc: Lai Jiangshan Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Pranith Kumar Cc: Michael Kerrisk Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 08001317aee7..a460e2ef2843 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -885,4 +885,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); +asmlinkage long sys_membarrier(int cmd, int flags); + #endif -- cgit v1.2.3 From 6798a8caaf64fa68b9ab2044e070fe4545034e03 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 11 Sep 2015 13:07:48 -0700 Subject: fs/seq_file: convert int seq_vprint/seq_printf/etc... returns to void The seq_ function return values were frequently misused. See: commit 1f33c41c03da ("seq_file: Rename seq_overflow() to seq_has_overflowed() and make public") All uses of these return values have been removed, so convert the return types to void. Miscellanea: o Move seq_put_decimal_ and seq_escape prototypes closer the other seq_vprintf prototypes o Reorder seq_putc and seq_puts to return early on overflow o Add argument names to seq_vprintf and seq_printf o Update the seq_escape kernel-doc o Convert a couple of leading spaces to tabs in seq_escape Signed-off-by: Joe Perches Cc: Al Viro Cc: Steven Rostedt Cc: Mark Brown Cc: Stephen Rothwell Cc: Joerg Roedel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index adeadbd6d7bf..dde00defbaa5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -114,13 +114,18 @@ int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); -int seq_escape(struct seq_file *, const char *, const char *); -int seq_putc(struct seq_file *m, char c); -int seq_puts(struct seq_file *m, const char *s); int seq_write(struct seq_file *seq, const void *data, size_t len); -__printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); -__printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args); +__printf(2, 0) +void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); +__printf(2, 3) +void seq_printf(struct seq_file *m, const char *fmt, ...); +void seq_putc(struct seq_file *m, char c); +void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull(struct seq_file *m, char delimiter, + unsigned long long num); +void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, @@ -138,10 +143,6 @@ int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); -int seq_put_decimal_ull(struct seq_file *m, char delimiter, - unsigned long long num); -int seq_put_decimal_ll(struct seq_file *m, char delimiter, - long long num); static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { -- cgit v1.2.3 From 10fbd36e362a0f367e34a7cd876a81295d8fc5ca Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 27 May 2015 15:32:15 -0700 Subject: blk: rq_data_dir() should not return a boolean MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rq_data_dir() returns either READ or WRITE (0 == READ, 1 == WRITE), not a boolean value. Now, admittedly the "!= 0" doesn't really change the value (0 stays as zero, 1 stays as one), but it's not only redundant, it confuses gcc, and causes gcc to warn about the construct switch (rq_data_dir(req)) { case READ: ... case WRITE: ... that we have in a few drivers. Now, the gcc warning is silly and stupid (it seems to warn not about the switch value having a different type from the case statements, but about _any_ boolean switch value), but in this case the code itself is silly and stupid too, so let's just change it, and get rid of warnings like this: drivers/block/hd.c: In function ‘hd_request’: drivers/block/hd.c:630:11: warning: switch condition has boolean value [-Wswitch-bool] switch (rq_data_dir(req)) { The odd '!= 0' came in when "cmd_flags" got turned into a "u64" in commit 5953316dbf90 ("block: make rq->cmd_flags be 64-bit") and is presumably because the old code (that just did a logical 'and' with 1) would then end up making the type of rq_data_dir() be u64 too. But if we want to retain the old regular integer type, let's just cast the result to 'int' rather than use that rather odd '!= 0'. Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 708923b9b623..38a5ff772a37 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -584,7 +584,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) +#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1)) /* * Driver can handle struct request, if it either has an old style -- cgit v1.2.3 From cd33dc9ac2977ebe30cecbf39d2992190fbac5b4 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 8 Sep 2015 14:51:12 +0100 Subject: thermal: Fix thermal_zone_of_sensor_register to match documentation thermal_zone_of_sensor_register is documented as returning a pointer to either a valid thermal_zone_device on success, or a corresponding ERR_PTR() value. In contrast, the function returns NULL when THERMAL_OF is configured off. Fix this. Signed-off-by: Punit Agrawal Acked-by: Guenter Roeck Cc: Eduardo Valentin Cc: Zhang Rui Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 17292fee8686..0c5518e13584 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -360,7 +360,7 @@ static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops) { - return NULL; + return ERR_PTR(-ENODEV); } static inline -- cgit v1.2.3 From eef7635a22f6b144206b5ca2f1398f637acffc4d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 11 Sep 2015 09:34:26 +0530 Subject: clockevents: Remove unused set_mode() callback All users are migrated to the per-state callbacks, get rid of the unused interface and the core support code. Signed-off-by: Viresh Kumar Signed-off-by: Thomas Gleixner Cc: linaro-kernel@lists.linaro.org Cc: John Stultz Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/fd60de14cf6d125489c031207567bb255ad946f6.1441943991.git.viresh.kumar@linaro.org Signed-off-by: Ingo Molnar --- include/linux/clockchips.h | 29 +++++------------------------ 1 file changed, 5 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 31ce435981fe..bdcf358dfce2 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -18,15 +18,6 @@ struct clock_event_device; struct module; -/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ -enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED, - CLOCK_EVT_MODE_SHUTDOWN, - CLOCK_EVT_MODE_PERIODIC, - CLOCK_EVT_MODE_ONESHOT, - CLOCK_EVT_MODE_RESUME, -}; - /* * Possible states of a clock event device. * @@ -86,16 +77,14 @@ enum clock_event_state { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE * @state_use_accessors:current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries - * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. - * @set_state_periodic: switch state to periodic, if !set_mode - * @set_state_oneshot: switch state to oneshot, if !set_mode - * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode - * @set_state_shutdown: switch state to shutdown, if !set_mode - * @tick_resume: resume clkevt device, if !set_mode + * @set_state_periodic: switch state to periodic + * @set_state_oneshot: switch state to oneshot + * @set_state_oneshot_stopped: switch state to oneshot_stopped + * @set_state_shutdown: switch state to shutdown + * @tick_resume: resume clkevt device * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -116,18 +105,10 @@ struct clock_event_device { u64 min_delta_ns; u32 mult; u32 shift; - enum clock_event_mode mode; enum clock_event_state state_use_accessors; unsigned int features; unsigned long retries; - /* - * State transition callback(s): Only one of the two groups should be - * defined: - * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume(). - */ - void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); int (*set_state_oneshot_stopped)(struct clock_event_device *); -- cgit v1.2.3 From c973c3bcec3752455c4d7545edd42935cd7942d9 Mon Sep 17 00:00:00 2001 From: Javi Merino Date: Mon, 14 Sep 2015 14:23:50 +0100 Subject: thermal: Add a function to get the minimum power The thermal core already has a function to get the maximum power of a cooling device: power_actor_get_max_power(). Add a function to get the minimum power of a cooling device. Cc: Zhang Rui Cc: Eduardo Valentin Reviewed-by: Daniel Kurtz Signed-off-by: Javi Merino Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 0c5518e13584..157d366e761b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -380,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) int power_actor_get_max_power(struct thermal_cooling_device *, struct thermal_zone_device *tz, u32 *max_power); +int power_actor_get_min_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *min_power); int power_actor_set_power(struct thermal_cooling_device *, struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, @@ -415,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 *max_power) { return 0; } +static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, + u32 *min_power) +{ return -ENODEV; } static inline int power_actor_set_power(struct thermal_cooling_device *cdev, struct thermal_instance *tz, u32 power) { return 0; } -- cgit v1.2.3 From 63cdbc06b357dcb3a7104a421ee4a4550d7fadfd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Sep 2015 17:06:27 +0200 Subject: netfilter: bridge: fix routing of bridge frames with call-iptables=1 We can't re-use the physoutdev storage area. 1. When using NFQUEUE in PREROUTING, we attempt to bump a bogus refcnt since nf_bridge->physoutdev is garbage (ipv4/ipv6 address) 2. for same reason, we crash in physdev match in FORWARD or later if skb is routed instead of bridged. This increases nf_bridge_info to 40 bytes, but we have no other choice. Fixes: 72b1e5e4cac7 ("netfilter: bridge: reduce nf_bridge_info to 32 bytes again") Reported-by: Sander Eikelenboom Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2738d355cdf9..9987af080fa0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -179,6 +179,9 @@ struct nf_bridge_info { u8 bridged_dnat:1; __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; @@ -189,9 +192,6 @@ struct nf_bridge_info { * skb is out in neigh layer. */ char neigh_header[8]; - - /* always valid & non-NULL from FORWARD on, for physdev match */ - struct net_device *physoutdev; }; }; #endif -- cgit v1.2.3 From 1975dbc276c6ab62230cf4f9df5ddc9ff0e0e473 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Mon, 14 Sep 2015 17:11:05 -0600 Subject: locking/static_keys: Fix up the static keys documentation Fix a few small mistakes in the static key documentation and delete an unneeded sentence. Suggested-by: Jason Baron Signed-off-by: Jonathan Corbet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20150914171105.511e1e21@lwn.net Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0684bd3a48fc..f1094238ab2a 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -21,8 +21,8 @@ * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); - * static_key_likely() - * static_key_unlikely() + * static_branch_likely() + * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we @@ -45,12 +45,10 @@ * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * - * In addtion to static_branch_{enable,disable}, we can also reference count + * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and - * static_branch_dec() as a 'make more false'. The inc()/dec() - * interface is meant to be used exclusively from the inc()/dec() for a given - * key. + * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). -- cgit v1.2.3 From 3829c664b1eec243f2a355829efa40f0f414de8d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Sep 2015 13:47:24 +0200 Subject: genirq: Remove stale comment Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 6f8b34066442..72a6b2feb7bf 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -151,10 +151,6 @@ struct irq_common_data { * methods, to allow shared chip implementations * @msi_desc: MSI descriptor * @affinity: IRQ affinity on SMP - * - * The fields here need to overlay the ones in irq_desc until we - * cleaned up the direct references and switched everything over to - * irq_data. */ struct irq_data { u32 mask; -- cgit v1.2.3 From 6584d84c3e504c76ad291cc2e381bbeed59798ab Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Tue, 1 Sep 2015 10:35:50 +0800 Subject: genirq: Update the comment for generic_handle_irq_desc __do_IRQ() was removed by commit 1c77ff2 "genirq: Remove __do_IRQ", but the comment referring to __do_IRQ() was left. Update the comment for generic_handle_irq_desc(). Signed-off-by: Huang Shijie Cc: jiang.liu@linux.intel.com Cc: peterz@infradead.org Cc: rafael.j.wysocki@intel.com Cc: jason@lakedaemon.net Cc: marc.zyngier@arm.com Link: http://lkml.kernel.org/r/1441074950-3893-1-git-send-email-shijie.huang@arm.com Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 5acfa26602e1..0593c691d091 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -137,9 +137,7 @@ static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) /* * Architectures call this to let the generic IRQ layer - * handle an interrupt. If the descriptor is attached to an - * irqchip-style controller then we call the ->handle_irq() handler, - * and it calls __do_IRQ() if it's attached to an irqtype-style controller. + * handle an interrupt. */ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) { -- cgit v1.2.3 From 1f0bd44e937468446d080b98b5669844744c24a1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Sep 2015 02:17:49 +0200 Subject: cpufreq: acpi-cpufreq: Use cpufreq_cpu_get_raw() in ->get() cpufreq_cpu_get() called by get_cur_freq_on_cpu() is overkill, because the ->get() callback is always invoked in a context in which all of the conditions checked by cpufreq_cpu_get() are guaranteed to be satisfied. Use cpufreq_cpu_get_raw() instead of it and drop the corresponding cpufreq_cpu_put() from get_cur_freq_on_cpu(). Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 430efcbea48e..dca22de98d94 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,9 +127,14 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu); struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); void cpufreq_cpu_put(struct cpufreq_policy *policy); #else +static inline struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +{ + return NULL; +} static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { return NULL; -- cgit v1.2.3 From e902e14549e04c040fb6e15785efd35f810a223a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 12:36:04 +0200 Subject: genirq: Remove __irq_set_chip_handler_name_locked() All users converted to irq_set_chip_handler_name_locked() Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 0593c691d091..29741382593c 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -184,19 +184,6 @@ static inline void __irq_set_handler_locked(unsigned int irq, desc->handle_irq = handler; } -/* caller has locked the irq_desc and both params are valid */ -static inline void -__irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handler, const char *name) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - irq_desc_get_irq_data(desc)->chip = chip; - desc->handle_irq = handler; - desc->name = name; -} - /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq -- cgit v1.2.3 From 123236ccacc933daac3b39c5eb1f0011c70d41d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 12:54:23 +0200 Subject: genirq: Remove __irq_set_handler_locked() All users converted to irq_set_handler_locked() Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 29741382593c..dce395cd67de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -174,16 +174,6 @@ static inline int irq_has_action(unsigned int irq) return irq_desc_has_action(irq_to_desc(irq)); } -/* caller has locked the irq_desc and both params are valid */ -static inline void __irq_set_handler_locked(unsigned int irq, - irq_flow_handler_t handler) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - desc->handle_irq = handler; -} - /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq -- cgit v1.2.3 From 755d119a6204974b2005a98549a48a75a7f5010b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2015 14:37:12 +0200 Subject: genirq: Simplify irq_data_to_desc() Avoid the lookup of irq_desc and use the same mechanism for hierarchical and flat irqdomains. Based-on-a-patch-from: Jiang Liu Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index dce395cd67de..1fc5304641a1 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -98,11 +98,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) { -#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY - return irq_to_desc(data->irq); -#else - return container_of(data, struct irq_desc, irq_data); -#endif + return container_of(data->common, struct irq_desc, irq_common_data); } static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) -- cgit v1.2.3 From fc5697126aa074c289df5e8baae28e115963023f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Sep 2015 12:33:42 +0200 Subject: genirq: Provide IRQD_FORWARDED_TO_VCPU status flag Provide a irq data flag to mark an irq forwarded to a VCPU along with the accessor functions. Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier --- include/linux/irq.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 72a6b2feb7bf..e54ae8295460 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -186,6 +186,7 @@ struct irq_data { * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed + * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -200,6 +201,7 @@ enum { IRQD_IRQ_MASKED = (1 << 17), IRQD_IRQ_INPROGRESS = (1 << 18), IRQD_WAKEUP_ARMED = (1 << 19), + IRQD_FORWARDED_TO_VCPU = (1 << 20), }; #define __irqd_to_state(d) ((d)->common->state_use_accessors) @@ -278,6 +280,20 @@ static inline bool irqd_is_wakeup_armed(struct irq_data *d) return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } +static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; +} /* * Functions for chained handlers which can be enabled/disabled by the -- cgit v1.2.3 From 449e9cae58b06be1293858ec8e5d8cb728238baa Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:16 +0800 Subject: genirq: Move field 'node' from irq_data into irq_common_data NUMA node information is per-irq instead of per-irqchip, so move it into struct irq_common_data. Also use CONFIG_NUMA to guard irq_common_data.node. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Link: http://lkml.kernel.org/r/1433145945-789-8-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index e54ae8295460..ebcc5c6745eb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -129,9 +129,13 @@ struct irq_domain; * struct irq_common_data - per irq data shared by all irqchips * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it + * @node: node index useful for balancing */ struct irq_common_data { unsigned int state_use_accessors; +#ifdef CONFIG_NUMA + unsigned int node; +#endif }; /** @@ -139,7 +143,6 @@ struct irq_common_data { * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain - * @node: node index useful for balancing * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping @@ -156,7 +159,6 @@ struct irq_data { u32 mask; unsigned int irq; unsigned long hwirq; - unsigned int node; struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; @@ -664,9 +666,18 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } -static inline int irq_data_get_node(struct irq_data *d) +static inline int irq_common_data_get_node(struct irq_common_data *d) { +#ifdef CONFIG_NUMA return d->node; +#else + return 0; +#endif +} + +static inline int irq_data_get_node(struct irq_data *d) +{ + return irq_common_data_get_node(d->common); } static inline struct cpumask *irq_get_affinity_mask(int irq) -- cgit v1.2.3 From af7080e040d223b5e7d0a8de28f7cea24ef017c4 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:21 +0800 Subject: genirq: Move field 'handler_data' from irq_data into irq_common_data Handler data (handler_data) is per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1433145945-789-13-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 8 ++++---- include/linux/irqdesc.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index ebcc5c6745eb..516aadbfc072 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -130,12 +130,14 @@ struct irq_domain; * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it * @node: node index useful for balancing + * @handler_data: per-IRQ data for the irq_chip methods */ struct irq_common_data { unsigned int state_use_accessors; #ifdef CONFIG_NUMA unsigned int node; #endif + void *handler_data; }; /** @@ -149,7 +151,6 @@ struct irq_common_data { * between hwirq number and linux irq number. * @parent_data: pointer to parent struct irq_data to support hierarchy * irq_domain - * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations * @msi_desc: MSI descriptor @@ -165,7 +166,6 @@ struct irq_data { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data *parent_data; #endif - void *handler_data; void *chip_data; struct msi_desc *msi_desc; cpumask_var_t affinity; @@ -641,12 +641,12 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d) static inline void *irq_get_handler_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->handler_data : NULL; + return d ? d->common->handler_data : NULL; } static inline void *irq_data_get_irq_handler_data(struct irq_data *d) { - return d->handler_data; + return d->common->handler_data; } static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1fc5304641a1..c7b3e1cc6d59 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -123,7 +123,7 @@ static inline void *irq_desc_get_chip_data(struct irq_desc *desc) static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { - return desc->irq_data.handler_data; + return desc->irq_common_data.handler_data; } static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) -- cgit v1.2.3 From 9df872faa7e1619e9278bec00ceaed2236533530 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jun 2015 11:47:50 +0800 Subject: genirq: Move field 'affinity' from irq_data into irq_common_data Irq affinity mask is per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Link: http://lkml.kernel.org/r/1433303281-27688-1-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 516aadbfc072..75d50544a18f 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -110,8 +110,8 @@ enum { /* * Return value for chip->irq_set_affinity() * - * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity + * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity + * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendent irqchips. @@ -131,6 +131,7 @@ struct irq_domain; * Use accessor functions to deal with it * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods + * @affinity: IRQ affinity on SMP */ struct irq_common_data { unsigned int state_use_accessors; @@ -138,6 +139,7 @@ struct irq_common_data { unsigned int node; #endif void *handler_data; + cpumask_var_t affinity; }; /** @@ -154,7 +156,6 @@ struct irq_common_data { * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations * @msi_desc: MSI descriptor - * @affinity: IRQ affinity on SMP */ struct irq_data { u32 mask; @@ -168,7 +169,6 @@ struct irq_data { #endif void *chip_data; struct msi_desc *msi_desc; - cpumask_var_t affinity; }; /* @@ -684,12 +684,12 @@ static inline struct cpumask *irq_get_affinity_mask(int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->affinity : NULL; + return d ? d->common->affinity : NULL; } static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) { - return d->affinity; + return d->common->affinity; } unsigned int arch_dynirq_lower_bound(unsigned int from); -- cgit v1.2.3 From b237721c5d95082a803c0be686f56d2dd1de995b Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 1 Jun 2015 16:05:43 +0800 Subject: genirq: Move field 'msi_desc' from irq_data into irq_common_data MSI descriptors are per-irq instead of per irqchip, so move it into struct irq_common_data. Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Bjorn Helgaas Cc: Benjamin Herrenschmidt Cc: Randy Dunlap Cc: Yinghai Lu Cc: Borislav Petkov Cc: Jason Cooper Cc: Kevin Cernekee Cc: Arnd Bergmann Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1433145945-789-35-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 8 ++++---- include/linux/irqdesc.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 75d50544a18f..4913c32db942 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -132,6 +132,7 @@ struct irq_domain; * @node: node index useful for balancing * @handler_data: per-IRQ data for the irq_chip methods * @affinity: IRQ affinity on SMP + * @msi_desc: MSI descriptor */ struct irq_common_data { unsigned int state_use_accessors; @@ -139,6 +140,7 @@ struct irq_common_data { unsigned int node; #endif void *handler_data; + struct msi_desc *msi_desc; cpumask_var_t affinity; }; @@ -155,7 +157,6 @@ struct irq_common_data { * irq_domain * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations - * @msi_desc: MSI descriptor */ struct irq_data { u32 mask; @@ -168,7 +169,6 @@ struct irq_data { struct irq_data *parent_data; #endif void *chip_data; - struct msi_desc *msi_desc; }; /* @@ -652,12 +652,12 @@ static inline void *irq_data_get_irq_handler_data(struct irq_data *d) static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->msi_desc : NULL; + return d ? d->common->msi_desc : NULL; } static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d) { - return d->msi_desc; + return d->common->msi_desc; } static inline u32 irq_get_trigger_type(unsigned int irq) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c7b3e1cc6d59..fbb4d5afc32b 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -128,7 +128,7 @@ static inline void *irq_desc_get_handler_data(struct irq_desc *desc) static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) { - return desc->irq_data.msi_desc; + return desc->irq_common_data.msi_desc; } /* -- cgit v1.2.3 From bd0b9ac405e1794d72533c3d487aa65b6b955a0c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 14 Sep 2015 10:42:37 +0200 Subject: genirq: Remove irq argument from irq flow handlers Most interrupt flow handlers do not use the irq argument. Those few which use it can retrieve the irq number from the irq descriptor. Remove the argument. Search and replace was done with coccinelle and some extra helper scripts around it. Thanks to Julia for her help! Signed-off-by: Thomas Gleixner Cc: Julia Lawall Cc: Jiang Liu --- include/linux/irq.h | 16 ++++++++-------- include/linux/irqdesc.h | 4 ++-- include/linux/irqhandler.h | 2 +- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4913c32db942..11bf09288ddb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -475,14 +475,14 @@ static inline int irq_set_parent(int irq, int parent_irq) * Built-in IRQ handlers for various IRQ types, * callable via desc->handle_irq() */ -extern void handle_level_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_level_irq(struct irq_desc *desc); +extern void handle_fasteoi_irq(struct irq_desc *desc); +extern void handle_edge_irq(struct irq_desc *desc); +extern void handle_edge_eoi_irq(struct irq_desc *desc); +extern void handle_simple_irq(struct irq_desc *desc); +extern void handle_percpu_irq(struct irq_desc *desc); +extern void handle_percpu_devid_irq(struct irq_desc *desc); +extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index fbb4d5afc32b..a587a33363c7 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -135,9 +135,9 @@ static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) * Architectures call this to let the generic IRQ layer * handle an interrupt. */ -static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) +static inline void generic_handle_irq_desc(struct irq_desc *desc) { - desc->handle_irq(irq, desc); + desc->handle_irq(desc); } int generic_handle_irq(unsigned int irq); diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h index 62d543004197..661bed0ed1f3 100644 --- a/include/linux/irqhandler.h +++ b/include/linux/irqhandler.h @@ -8,7 +8,7 @@ struct irq_desc; struct irq_data; -typedef void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc); +typedef void (*irq_flow_handler_t)(struct irq_desc *desc); typedef void (*irq_preflow_handler_t)(struct irq_data *data); #endif -- cgit v1.2.3 From 0c986253b939cc14c69d4adbe2b4121bdf4aa220 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 16 Sep 2015 11:51:12 -0400 Subject: Revert "sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem" This reverts commit d59cfc09c32a2ae31f1c3bc2983a0cd79afb3f14. d59cfc09c32a ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") and b5ba75b5fc0e ("cgroup: simplify threadgroup locking") changed how cgroup synchronizes against task fork and exits so that it uses global percpu_rwsem instead of per-process rwsem; unfortunately, the write [un]lock paths of percpu_rwsem always involve synchronize_rcu_expedited() which turned out to be too expensive. Improvements for percpu_rwsem are scheduled to be merged in the coming v4.4-rc1 merge window which alleviates this issue. For now, revert the two commits to restore per-process rwsem. They will be re-applied for the v4.4-rc1 merge window. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/55F8097A.7000206@de.ibm.com Reported-by: Christian Borntraeger Cc: Oleg Nesterov Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Paolo Bonzini Cc: stable@vger.kernel.org # v4.2+ --- include/linux/cgroup-defs.h | 27 ++------------------------- include/linux/init_task.h | 8 ++++++++ include/linux/sched.h | 12 ++++++++++++ 3 files changed, 22 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4d8fcf2187dc..8492721b39be 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -473,31 +473,8 @@ struct cgroup_subsys { unsigned int depends_on; }; -extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - -/** - * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_begin() and allows cgroup operations to - * synchronize against threadgroup changes using a percpu_rw_semaphore. - */ -static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) -{ - percpu_down_read(&cgroup_threadgroup_rwsem); -} - -/** - * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_end(). Counterpart of - * cgroup_threadcgroup_change_begin(). - */ -static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) -{ - percpu_up_read(&cgroup_threadgroup_rwsem); -} +void cgroup_threadgroup_change_begin(struct task_struct *tsk); +void cgroup_threadgroup_change_end(struct task_struct *tsk); #else /* CONFIG_CGROUPS */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d0b380ee7d67..e38681f4912d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,6 +25,13 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +#ifdef CONFIG_CGROUPS +#define INIT_GROUP_RWSEM(sig) \ + .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), +#else +#define INIT_GROUP_RWSEM(sig) +#endif + #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -57,6 +64,7 @@ extern struct fs_struct init_fs; INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ + INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index a4ab9daa387c..b7b9501b41af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -762,6 +762,18 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + /* + * group_rwsem prevents new tasks from entering the threadgroup and + * member tasks from exiting,a more specifically, setting of + * PF_EXITING. fork and exit paths are protected with this rwsem + * using threadgroup_change_begin/end(). Users which require + * threadgroup to remain stable should use threadgroup_[un]lock() + * which also takes care of exec path. Currently, cgroup is the + * only user. + */ + struct rw_semaphore group_rwsem; +#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ -- cgit v1.2.3 From 0243ed44ad4a25dbd2e92ad97e5e12a1a6c72d6c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 15 Sep 2015 04:59:21 -0700 Subject: spi: fix kernel-doc warnings in spi.h Fix the following 'make htmldocs' warnings: .//include/linux/spi/spi.h:71: warning: No description found for parameter 'lock' .//include/linux/spi/spi.h:71: warning: Excess struct/union/enum/typedef member 'clock' description in 'spi_statistics' Signed-off-by: Geliang Tang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 269e8afd3e2a..6b00f18f5e6b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers - * @clock: lock protecting this structure + * @lock: lock protecting this structure * * @messages: number of spi-messages handled * @transfers: number of spi_transfers handled -- cgit v1.2.3 From 7f61f545657281a3a1b0faf68993165ebdecc51b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 14 Sep 2015 16:01:05 +0300 Subject: libceph: don't access invalid memory in keepalive2 path This struct ceph_timespec ceph_ts; ... con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); wraps ceph_ts into a kvec and adds it to con->out_kvec array, yet ceph_ts becomes invalid on return from prepare_write_keepalive(). As a result, we send out bogus keepalive2 stamps. Fix this by encoding into a ceph_timespec member, similar to how acks are read and written. Signed-off-by: Ilya Dryomov Reviewed-by: Yan, Zheng --- include/linux/ceph/messenger.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 7e1252e97a30..b2371d9b51fa 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -238,6 +238,8 @@ struct ceph_connection { bool out_kvec_is_msg; /* kvec refers to out_msg */ int out_more; /* there is more data after the kvecs */ __le64 out_temp_ack; /* for writing an ack */ + struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2 + stamp */ /* message in temps */ struct ceph_msg_header in_hdr; @@ -248,7 +250,7 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ - struct timespec last_keepalive_ack; + struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ -- cgit v1.2.3 From 335c25858218e76ef47f92ecb9d22e919d36140d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 14 Sep 2015 12:44:22 +0300 Subject: libceph: advertise support for keepalive2 We are the client, but advertise keepalive2 anyway - for consistency, if nothing else. In the future the server might want to know whether its clients support keepalive2. Signed-off-by: Ilya Dryomov Reviewed-by: Yan, Zheng --- include/linux/ceph/ceph_features.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 4763ad64e832..f89b31d45cc8 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -107,6 +107,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSDMAP_ENC | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ + CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4) #define CEPH_FEATURES_REQUIRED_DEFAULT \ -- cgit v1.2.3 From 0fdea1e8a2853f79d39b8555cc9de16a7e0ab26f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Sep 2015 23:43:17 -0400 Subject: SUNRPC: Ensure that we wait for connections to complete before retrying Commit 718ba5b87343, moved the responsibility for unlocking the socket to xs_tcp_setup_socket, meaning that the socket will be unlocked before we know that it has finished trying to connect. The following patch is based on an initial patch by Russell King to ensure that we delay clearing the XPRT_CONNECTING flag until we either know that we failed to initiate a connection attempt, or the connection attempt itself failed. Fixes: 718ba5b87343 ("SUNRPC: Add helpers to prevent socket create from racing") Reported-by: Russell King Reported-by: Russell King Tested-by: Russell King Tested-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7591788e9fbf..357e44c1a46b 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,7 @@ struct sock_xprt { /* * Connection of transports */ + unsigned long sock_state; struct delayed_work connect_worker; struct sockaddr_storage srcaddr; unsigned short srcport; @@ -76,6 +77,8 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +#define XPRT_SOCK_CONNECTING 1U + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From b7f76ea2ef6739ee484a165ffbac98deb855d3d3 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 18 Sep 2015 23:41:23 +0200 Subject: security: fix typo in security_task_prctl Signed-off-by: Jann Horn Reviewed-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 79d85ddf8093..2f4c1f7aa7db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg4, unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5); + return cap_task_prctl(option, arg2, arg3, arg4, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) -- cgit v1.2.3 From ac5be6b47e8bd25b62bed2c82cda7398999f59e9 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 22 Sep 2015 14:58:49 -0700 Subject: userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key" This reverts commit 51360155eccb907ff8635bd10fc7de876408c2e0 and adapts fs/userfaultfd.c to use the old version of that function. It didn't look robust to call __wake_up_common with "nr == 1" when we absolutely require wakeall semantics, but we've full control of what we insert in the two waitqueue heads of the blocked userfaults. No exclusive waitqueue risks to be inserted into those two waitqueue heads so we can as well stick to "nr == 1" of the old code and we can rely purely on the fact no waitqueue inserted in one of the two waitqueue heads we must enforce as wakeall, has wait->flags WQ_FLAG_EXCLUSIVE set. Signed-off-by: Andrea Arcangeli Cc: Dr. David Alan Gilbert Cc: Michael Ellerman Cc: Shuah Khan Cc: Thierry Reding Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index d3d077228d4c..1e1bf9f963a9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key); +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); @@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) #define wake_up_locked_poll(x, m) \ - __wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m)) + __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) #define wake_up_interruptible_sync_poll(x, m) \ -- cgit v1.2.3 From 2d8bff12699abc3a9bf886bb0b79f44d94d81496 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Wed, 23 Sep 2015 14:57:58 -0400 Subject: netpoll: Close race condition between poll_one_napi and napi_disable Drivers might call napi_disable while not holding the napi instance poll_lock. In those instances, its possible for a race condition to exist between poll_one_napi and napi_disable. That is to say, poll_one_napi only tests the NAPI_STATE_SCHED bit to see if there is work to do during a poll, and as such the following may happen: CPU0 CPU1 ndo_tx_timeout napi_poll_dev napi_disable poll_one_napi test_and_set_bit (ret 0) test_bit (ret 1) reset adapter napi_poll_routine If the adapter gets a tx timeout without a napi instance scheduled, its possible for the adapter to think it has exclusive access to the hardware (as the napi instance is now scheduled via the napi_disable call), while the netpoll code thinks there is simply work to do. The result is parallel hardware access leading to corrupt data structures in the driver, and a crash. Additionaly, there is another, more critical race between netpoll and napi_disable. The disabled napi state is actually identical to the scheduled state for a given napi instance. The implication being that, if a napi instance is disabled, a netconsole instance would see the napi state of the device as having been scheduled, and poll it, likely while the driver was dong something requiring exclusive access. In the case above, its fairly clear that not having the rings in a state ready to be polled will cause any number of crashes. The fix should be pretty easy. netpoll uses its own bit to indicate that that the napi instance is in a state of being serviced by netpoll (NAPI_STATE_NPSVC). We can just gate disabling on that bit as well as the sched bit. That should prevent netpoll from conducting a napi poll if we convert its set bit to a test_and_set_bit operation to provide mutual exclusion Change notes: V2) Remove a trailing whtiespace Resubmit with proper subject prefix V3) Clean up spacing nits Signed-off-by: Neil Horman CC: "David S. Miller" CC: jmaxwell@redhat.com Tested-by: jmaxwell@redhat.com Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88a00694eda5..2d15e3831440 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP -- cgit v1.2.3 From 9badce000e2ce68ba74838a3cd356dde58221c2f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 23 Sep 2015 17:07:29 -0400 Subject: cgroup, writeback: don't enable cgroup writeback on traditional hierarchies inode_cgwb_enabled() gates cgroup writeback support. If it returns true, each inode is attached to the corresponding memory domain which gets mapped to io domain. It currently only tests whether the filesystem and bdi support cgroup writeback; however, cgroup writeback support doesn't work on traditional hierarchies and thus it should also test whether memcg and iocg are on the default hierarchy. This caused traditional hierarchy setups to hit the cgroup writeback path inadvertently and ended up creating separate writeback domains for each memcg and mapping them all to the root iocg uncovering a couple issues in the cgroup writeback path. cgroup writeback was never meant to be enabled on traditional hierarchies. Make inode_cgwb_enabled() test whether both memcg and iocg are on the default hierarchy. Signed-off-by: Tejun Heo Reported-by: Artem Bityutskiy Reported-by: Dexuan Cui Link: http://lkml.kernel.org/g/1443012552.19983.209.camel@gmail.com Link: http://lkml.kernel.org/g/f30d4a6aa8a546ff88f73021d026a453@SIXPR30MB031.064d.mgd.msft.net --- include/linux/backing-dev.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5a5d79ee256f..d5eb4ad1c534 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits); * @inode: inode of interest * * cgroup writeback requires support from both the bdi and filesystem. - * Test whether @inode has both. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); - return bdi_cap_account_dirty(bdi) && + return cgroup_on_dfl(mem_cgroup_root_css->cgroup) && + cgroup_on_dfl(blkcg_root_css->cgroup) && + bdi_cap_account_dirty(bdi) && (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } -- cgit v1.2.3 From 6ae459bdaaeebc632b16e54dcbabb490c6931d61 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Tue, 22 Sep 2015 12:57:53 -0700 Subject: skbuff: Fix skb checksum flag on skb pull VXLAN device can receive skb with checksum partial. But the checksum offset could be in outer header which is pulled on receive. This results in negative checksum offset for the skb. Such skb can cause the assert failure in skb_checksum_help(). Following patch fixes the bug by setting checksum-none while pulling outer header. Following is the kernel panic msg from old kernel hitting the bug. ------------[ cut here ]------------ kernel BUG at net/core/dev.c:1906! RIP: 0010:[] skb_checksum_help+0x144/0x150 Call Trace: [] queue_userspace_packet+0x408/0x470 [openvswitch] [] ovs_dp_upcall+0x5d/0x60 [openvswitch] [] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch] [] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch] [] ovs_vport_receive+0x2a/0x30 [openvswitch] [] vxlan_rcv+0x53/0x60 [openvswitch] [] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch] [] udp_queue_rcv_skb+0x2dc/0x3b0 [] __udp4_lib_rcv+0x1cf/0x6c0 [] udp_rcv+0x1a/0x20 [] ip_local_deliver_finish+0xdd/0x280 [] ip_local_deliver+0x88/0x90 [] ip_rcv_finish+0x10d/0x370 [] ip_rcv+0x235/0x300 [] __netif_receive_skb+0x55d/0x620 [] netif_receive_skb+0x80/0x90 [] virtnet_poll+0x555/0x6f0 [] net_rx_action+0x134/0x290 [] __do_softirq+0xa8/0x210 [] call_softirq+0x1c/0x30 [] do_softirq+0x65/0xa0 [] irq_exit+0x8e/0xb0 [] do_IRQ+0x63/0xe0 [] common_interrupt+0x6e/0x6e Reported-by: Anupam Chanda Signed-off-by: Pravin B Shelar Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9987af080fa0..2b0a30a6e31c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) <= len) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); -- cgit v1.2.3 From 3e3aaf649416988ca8be4ad2c52dc24d8be7b46e Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:02 +0100 Subject: phy: fix mdiobus module safety Re-implement the mdiobus module refcounting to ensure that we actually ensure that the mdiobus module code does not go away while we might call into it. The old scheme using bus->dev.driver was buggy, because bus->dev is a class device which never has a struct device_driver associated with it, and hence the associated code trying to obtain a refcount did nothing useful. Instead, take the approach that other subsystems do: pass the module when calling mdiobus_register(), and record that in the mii_bus struct. When we need to increment the module use count in the phy code, use this stored pointer. When the phy is deteched, drop the module refcount, remembering that the phy device might go away at that point. This doesn't stop the mii_bus going away while there are in-use phys - it merely stops the underlying code vanishing. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 962387a192f1..11bce44f6d65 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); -- cgit v1.2.3 From 38737e490d4ea91660d3cec83ef88c4e6d360ae4 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 24 Sep 2015 20:36:28 +0100 Subject: phy: add phy_device_remove() Add a phy_device_remove() function to complement phy_device_register(), which undoes the effects of phy_device_register() by removing the phy device from visibility, but not freeing it. This allows these details to be moved out of the mdio bus code into the phy code where this action belongs. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 11bce44f6d65..4a4e3a092337 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -745,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); -- cgit v1.2.3