From dd935f44a40f8fb02aff2cc0df2269c92422df1c Mon Sep 17 00:00:00 2001 From: Josh Durgin Date: Wed, 28 Aug 2013 21:43:09 -0700 Subject: libceph: add function to ensure notifies are complete Without a way to flush the osd client's notify workqueue, a watch event that is unregistered could continue receiving callbacks indefinitely. Unregistering the event simply means no new notifies are added to the queue, but there may still be events in the queue that will call the watch callback for the event. If the queue is flushed after the event is unregistered, the caller can be sure no more watch callbacks will occur for the canceled watch. Signed-off-by: Josh Durgin Reviewed-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ce6df39f60ff..8f47625a0661 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -335,6 +335,8 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); extern void ceph_osdc_sync(struct ceph_osd_client *osdc); +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc); + extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_vino vino, struct ceph_file_layout *layout, -- cgit v1.2.3 From 7bd36014460f793c19e7d6c94dab67b0afcfcb7f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Sep 2013 16:50:56 -0700 Subject: timekeeping: Fix HRTICK related deadlock from ntp lock changes Gerlando Falauto reported that when HRTICK is enabled, it is possible to trigger system deadlocks. These were hard to reproduce, as HRTICK has been broken in the past, but seemed to be connected to the timekeeping_seq lock. Since seqlock/seqcount's aren't supported w/ lockdep, I added some extra spinlock based locking and triggered the following lockdep output: [ 15.849182] ntpd/4062 is trying to acquire lock: [ 15.849765] (&(&pool->lock)->rlock){..-...}, at: [] __queue_work+0x145/0x480 [ 15.850051] [ 15.850051] but task is already holding lock: [ 15.850051] (timekeeper_lock){-.-.-.}, at: [] do_adjtimex+0x7f/0x100 [ 15.850051] Chain exists of: &(&pool->lock)->rlock --> &p->pi_lock --> timekeeper_lock [ 15.850051] Possible unsafe locking scenario: [ 15.850051] [ 15.850051] CPU0 CPU1 [ 15.850051] ---- ---- [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&p->pi_lock); [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&(&pool->lock)->rlock); [ 15.850051] [ 15.850051] *** DEADLOCK *** The deadlock was introduced by 06c017fdd4dc48451a ("timekeeping: Hold timekeepering locks in do_adjtimex and hardpps") in 3.10 This patch avoids this deadlock, by moving the call to schedule_delayed_work() outside of the timekeeper lock critical section. Reported-by: Gerlando Falauto Tested-by: Lin Ming Signed-off-by: John Stultz Cc: Mathieu Desnoyers Cc: stable #3.11, 3.10 Link: http://lkml.kernel.org/r/1378943457-27314-1-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- include/linux/timex.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b3726e61368e..dd3edd7dfc94 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -141,6 +141,7 @@ extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); int read_current_timer(unsigned long *timer_val); +void ntp_notify_cmos_timer(void); /* The clock frequency of the i8253/i8254 PIT */ #define PIT_TICK_RATE 1193182ul -- cgit v1.2.3 From 331415ff16a12147d57d5c953f3a961b7ede348b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 11 Sep 2013 21:56:50 +0200 Subject: HID: provide a helper for validating hid reports Many drivers need to validate the characteristics of their HID report during initialization to avoid misusing the reports. This adds a common helper to perform validation of the report exisitng, the field existing, and the expected number of values within the field. Signed-off-by: Kees Cook Cc: stable@vger.kernel.org Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ee1ffc5e19c9..31b9d299ef6c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -756,6 +756,10 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +struct hid_report *hid_validate_values(struct hid_device *hid, + unsigned int type, unsigned int id, + unsigned int field_index, + unsigned int report_counts); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); -- cgit v1.2.3 From 35e4237973665c8a1ad4e3f7a7cb87573deaa24a Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 13 Sep 2013 07:34:13 -0700 Subject: vxlan: Fix sparse warnings This patch fixes sparse warnings when incorrectly handling the port number and using int instead of unsigned int iterating through &vn->sock_list[]. Keeping the port as __be16 also makes things clearer wrt endianess. Also, it was pointed out that vxlan_get_rx_port() had unnecessary checks which got removed. Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 041b42a305f6..3de49aca4519 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -950,14 +950,14 @@ struct netdev_phys_port_id { * multiple net devices on single physical port. * * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notiy a driver about the UDP port and socket * address family that vxlan is listnening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. @@ -1093,10 +1093,10 @@ struct net_device_ops { struct netdev_phys_port_id *ppid); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); }; /* -- cgit v1.2.3 From 0f1799ba1a5db4c48b72ac2da2dc70d8c190a73d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:04:53 +0200 Subject: netfilter: ipset: Consistent userspace testing with nomatch flag The "nomatch" commandline flag should invert the matching at testing, similarly to the --return-nomatch flag of the "set" match of iptables. Until now it worked with the elements with "nomatch" flag only. From now on it works with elements without the flag too, i.e: # ipset n test hash:net # ipset a test 10.0.0.0/24 nomatch # ipset t test 10.0.0.1 10.0.0.1 is NOT in set test. # ipset t test 10.0.0.1 nomatch 10.0.0.1 is in set test. # ipset a test 192.168.0.0/24 # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is NOT in set test. Before the patch the results were ... # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is in set test. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index d80e2753847c..9ac9fbde7b61 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -296,10 +296,12 @@ ip_set_eexist(int ret, u32 flags) /* Match elements marked with nomatch */ static inline bool -ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && - ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); + (set->type->features & IPSET_TYPE_NOMATCH) && + ((flags >> 16) & IPSET_FLAG_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ -- cgit v1.2.3 From ba6a3541545542721ce821d1e7e5ce35752e6fdf Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Sep 2013 13:52:33 +0200 Subject: KVM: mmu: allow page tables to be in read-only slots Page tables in a read-only memory slot will currently cause a triple fault because the page walker uses gfn_to_hva and it fails on such a slot. OVMF uses such a page table; however, real hardware seems to be fine with that as long as the accessed/dirty bits are set. Save whether the slot is readonly, and later check it when updating the accessed and dirty bits. Reviewed-by: Xiao Guangrong Reviewed-by: Gleb Natapov Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ca645a01d37a..0fbbc7aa02cb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -533,6 +533,7 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); -- cgit v1.2.3 From f84cb8a46a771f36a04a02c61ea635c968ed5f6a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 19 Sep 2013 12:13:58 -0400 Subject: dm mpath: disable WRITE SAME if it fails Workaround the SCSI layer's problematic WRITE SAME heuristics by disabling WRITE SAME in the DM multipath device's queue_limits if an underlying device disabled it. The WRITE SAME heuristics, with both the original commit 5db44863b6eb ("[SCSI] sd: Implement support for WRITE SAME") and the updated commit 66c28f971 ("[SCSI] sd: Update WRITE SAME heuristics"), default to enabling WRITE SAME(10) even without successfully determining it is supported. After the first failed WRITE SAME the SCSI layer will disable WRITE SAME for the device (by setting sdkp->device->no_write_same which results in 'max_write_same_sectors' in device's queue_limits to be set to 0). When a device is stacked ontop of such a SCSI device any changes to that SCSI device's queue_limits do not automatically propagate up the stack. As such, a DM multipath device will not have its WRITE SAME support disabled. This causes the block layer to continue to issue WRITE SAME requests to the mpath device which causes paths to fail and (if mpath IO isn't configured to queue when no paths are available) it will result in actual IO errors to the upper layers. This fix doesn't help configurations that have additional devices stacked ontop of the mpath device (e.g. LVM created linear DM devices ontop). A proper fix that restacks all the queue_limits from the bottom of the device stack up will need to be explored if SCSI will continue to use this model of optimistically allowing op codes and then disabling them after they fail for the first time. Before this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: failing WRITE SAME IO with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. device-mapper: multipath: Failing path 8:112. end_request: I/O error, dev dm-6, sector 4616 dm-6: WRITE SAME failed. Manually zeroing. end_request: I/O error, dev dm-6, sector 4616 end_request: I/O error, dev dm-6, sector 5640 end_request: I/O error, dev dm-6, sector 6664 end_request: I/O error, dev dm-6, sector 7688 end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. end_request: I/O error, dev dm-6, sector 524296 Aborting journal on device dm-6-8. end_request: I/O error, dev dm-6, sector 524288 Buffer I/O error on device dm-6, logical block 65536 lost page write due to I/O error on dm-6 JBD2: Error -5 detected when updating journal superblock for dm-6-8. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 33553920 After this patch: EXT4-fs (dm-6): mounted filesystem with ordered data mode. Opts: (null) device-mapper: multipath: XXX snitm debugging: got -EREMOTEIO (-121) device-mapper: multipath: XXX snitm debugging: WRITE SAME I/O failed with error=-121 end_request: critical target error, dev dm-6, sector 528 dm-6: WRITE SAME failed. Manually zeroing. # cat /sys/block/sdh/queue/write_same_max_bytes 0 # cat /sys/block/dm-6/queue/write_same_max_bytes 0 It should be noted that WRITE SAME support wasn't enabled in DM multipath until v3.10. Signed-off-by: Mike Snitzer Cc: Martin K. Petersen Cc: Hannes Reinecke Cc: stable@vger.kernel.org # 3.10+ --- include/linux/device-mapper.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 653073de09e3..ed419c62dde1 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -406,13 +406,14 @@ int dm_noflush_suspending(struct dm_target *ti); union map_info *dm_get_mapinfo(struct bio *bio); union map_info *dm_get_rq_mapinfo(struct request *rq); +struct queue_limits *dm_get_queue_limits(struct mapped_device *md); + /* * Geometry functions. */ int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo); int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); - /*----------------------------------------------------------------- * Functions for manipulating device-mapper tables. *---------------------------------------------------------------*/ -- cgit v1.2.3 From 75afb352991ff1cd3cf5955bfe611de6d83a0c87 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Sat, 21 Sep 2013 13:57:47 -0600 Subject: block: Add nr_bios to block_rq_remap tracepoint Adding the number of bios in a remapped request to 'block_rq_remap' tracepoint. Request remapper clones bios in a request to track the completion status of each bio. So the number of bios can be useful information for investigation. Related discussions: http://www.redhat.com/archives/dm-devel/2013-August/msg00084.html http://www.redhat.com/archives/dm-devel/2013-September/msg00024.html Signed-off-by: Jun'ichi Nomura Acked-by: Mike Snitzer Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2fdb4a451b49..0e6f765aa1f5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -862,6 +862,17 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) return blk_queue_get_max_sectors(q, rq->cmd_flags); } +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + /* * Request issue related functions. */ -- cgit v1.2.3 From 9809b18fcf6b8d8ec4d3643677345907e6b50eca Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 24 Sep 2013 15:27:30 -0700 Subject: watchdog: update watchdog_thresh properly watchdog_tresh controls how often nmi perf event counter checks per-cpu hrtimer_interrupts counter and blows up if the counter hasn't changed since the last check. The counter is updated by per-cpu watchdog_hrtimer hrtimer which is scheduled with 2/5 watchdog_thresh period which guarantees that hrtimer is scheduled 2 times per the main period. Both hrtimer and perf event are started together when the watchdog is enabled. So far so good. But... But what happens when watchdog_thresh is updated from sysctl handler? proc_dowatchdog will set a new sampling period and hrtimer callback (watchdog_timer_fn) will use the new value in the next round. The problem, however, is that nobody tells the perf event that the sampling period has changed so it is ticking with the period configured when it has been set up. This might result in an ear ripping dissonance between perf and hrtimer parts if the watchdog_thresh is increased. And even worse it might lead to KABOOM if the watchdog is configured to panic on such a spurious lockup. This patch fixes the issue by updating both nmi perf even counter and hrtimers if the threshold value has changed. The nmi one is disabled and then reinitialized from scratch. This has an unpleasant side effect that the allocation of the new event might fail theoretically so the hard lockup detector would be disabled for such cpus. On the other hand such a memory allocation failure is very unlikely because the original event is deallocated right before. It would be much nicer if we just changed perf event period but there doesn't seem to be any API to do that right now. It is also unfortunate that perf_event_alloc uses GFP_KERNEL allocation unconditionally so we cannot use on_each_cpu() and do the same thing from the per-cpu context. The update from the current CPU should be safe because perf_event_disable removes the event atomically before it clears the per-cpu watchdog_ev so it cannot change anything under running handler feet. The hrtimer is simply restarted (thanks to Don Zickus who has pointed this out) if it is queued because we cannot rely it will fire&adopt to the new sampling period before a new nmi event triggers (when the treshold is decreased). [akpm@linux-foundation.org: the UP version of __smp_call_function_single ended up in the wrong place] Signed-off-by: Michal Hocko Acked-by: Don Zickus Cc: Frederic Weisbecker Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Fabio Estevam Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index cfb7ca094b38..731f5237d5f4 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } +static inline void __smp_call_function_single(int cpuid, + struct call_single_data *data, int wait) +{ + on_each_cpu(data->func, data->info, wait); +} + #endif /* !SMP */ /* -- cgit v1.2.3 From 694fbc0fe78518d06efa63910bf4ecee660e7852 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:37 -0700 Subject: revert "memcg: enhance memcg iterator to support predicates" Revert commit de57780dc659 ("memcg: enhance memcg iterator to support predicates") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 49 ++++++---------------------------------------- 1 file changed, 6 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 60e95872da29..ef2b9bd7fafa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -enum mem_cgroup_filter_t { - VISIT, /* visit current node */ - SKIP, /* skip the current node and continue traversal */ - SKIP_TREE, /* skip the whole subtree and continue traversal */ -}; - -/* - * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to - * iterate through the hierarchy tree. Each tree element is checked by the - * predicate before it is returned by the iterator. If a filter returns - * SKIP or SKIP_TREE then the iterator code continues traversal (with the - * next node down the hierarchy or the next node that doesn't belong under the - * memcg's subtree). - */ -typedef enum mem_cgroup_filter_t -(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); - #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond); - -static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim) -{ - return mem_cgroup_iter_cond(root, prev, reclaim, NULL); -} - +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -260,8 +234,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); @@ -376,15 +349,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } -static inline struct mem_cgroup * -mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) -{ - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; -} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -471,11 +435,10 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, struct mem_cgroup *root) { - return VISIT; + return false; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From b1aff7fcf86c88472b0a70f15d89d7a4adba07bb Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:38 -0700 Subject: revert "vmscan, memcg: do softlimit reclaim also for targeted reclaim" Revert commit a5b7c87f9207 ("vmscan, memcg: do softlimit reclaim also for targeted reclaim") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ef2b9bd7fafa..6054c9f3a5e8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -234,8 +234,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root); +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -435,8 +434,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) { return false; } -- cgit v1.2.3 From 0608f43da64a1f1c42507304b5f25bc8b1227aa4 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 24 Sep 2013 15:27:41 -0700 Subject: revert "memcg, vmscan: integrate soft reclaim tighter with zone shrinking code" Revert commit 3b38722efd9f ("memcg, vmscan: integrate soft reclaim tighter with zone shrinking code") I merged this prematurely - Michal and Johannes still disagree about the overall design direction and the future remains unclear. Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6054c9f3a5e8..ecc82b37c4cc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -234,7 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -434,9 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -bool mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg) +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { - return false; + return 0; } static inline void mem_cgroup_split_huge_fixup(struct page *head) -- cgit v1.2.3 From b0b8c960ffcc5bfc82d1a09ad931673e3a36c15a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 4 Sep 2013 10:52:57 -0500 Subject: of: clean-up ifdefs in of_irq.h Much of of_irq.h is needlessly ifdef'ed. Clean this up and minimize the amount ifdef'ed code. This fixes some build warnings when CONFIG_OF is not enabled (seen on i386 and x86_64): include/linux/of_irq.h:82:7: warning: 'struct device_node' declared inside parameter list [enabled by default] include/linux/of_irq.h:82:7: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] include/linux/of_irq.h:87:47: warning: 'struct device_node' declared inside parameter list [enabled by default] Compile tested on i386, sparc and arm. Reported-by: Randy Dunlap Cc: Grant Likely Signed-off-by: Rob Herring --- include/linux/of_irq.h | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 535cecf1e02f..fcd63baee5f2 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -1,8 +1,6 @@ #ifndef __OF_IRQ_H #define __OF_IRQ_H -#if defined(CONFIG_OF) -struct of_irq; #include #include #include @@ -10,14 +8,6 @@ struct of_irq; #include #include -/* - * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC - * implements it differently. However, the prototype is the same for all, - * so declare it here regardless of the CONFIG_OF_IRQ setting. - */ -extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); - -#if defined(CONFIG_OF_IRQ) /** * of_irq - container for device_node/irq_specifier pair for an irq controller * @controller: pointer to interrupt controller device tree node @@ -71,11 +61,17 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern int of_irq_count(struct device_node *dev); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); -extern struct device_node *of_irq_find_parent(struct device_node *child); extern void of_irq_init(const struct of_device_id *matches); -#endif /* CONFIG_OF_IRQ */ +#if defined(CONFIG_OF) +/* + * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC + * implements it differently. However, the prototype is the same for all, + * so declare it here regardless of the CONFIG_OF_IRQ setting. + */ +extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); +extern struct device_node *of_irq_find_parent(struct device_node *child); #else /* !CONFIG_OF */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, -- cgit v1.2.3 From 3a4916050ba2e0f1d114ef540abdf02b2b173e61 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 6 Sep 2013 11:49:56 -0700 Subject: Drivers: hv: util: Correctly support ws2008R2 and earlier The current code does not correctly negotiate the version numbers for the util driver when hosted on earlier hosts. The version numbers presented by this driver were not compatible with the version numbers supported by Windows Server 2008. Fix this problem. I would like to thank Olaf Hering (ohering@suse.com) for identifying the problem. Reported-by: Olaf Hering Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a3b8b2e2d244..d98503bde7e9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -30,10 +30,13 @@ /* * Framework version for util services. */ +#define UTIL_FW_MINOR 0 + +#define UTIL_WS2K8_FW_MAJOR 1 +#define UTIL_WS2K8_FW_VERSION (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR) #define UTIL_FW_MAJOR 3 -#define UTIL_FW_MINOR 0 -#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) +#define UTIL_FW_VERSION (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) /* -- cgit v1.2.3 From 083986e8248d978b6c961d3da6beb0c921c68220 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 28 Sep 2013 11:23:59 +0200 Subject: mutex: replace CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX with simple ifdef Linus suggested to replace #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX #define arch_mutex_cpu_relax() cpu_relax() #endif with just a simple #ifndef arch_mutex_cpu_relax # define arch_mutex_cpu_relax() cpu_relax() #endif to get rid of CONFIG_HAVE_CPU_RELAX_SIMPLE. So architectures can simply define arch_mutex_cpu_relax if they want an architecture specific function instead of having to add a select statement in their Kconfig in addition. Suggested-by: Linus Torvalds Signed-off-by: Heiko Carstens --- include/linux/mutex.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index ccd4260834c5..bab49da8a0f0 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -15,8 +15,8 @@ #include #include #include - #include +#include /* * Simple, straightforward mutexes with strict semantics: @@ -175,8 +175,8 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); -#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX -#define arch_mutex_cpu_relax() cpu_relax() +#ifndef arch_mutex_cpu_relax +# define arch_mutex_cpu_relax() cpu_relax() #endif #endif -- cgit v1.2.3