From 45cd0faae3715e305bc46e23b34c5ed4d185ceb8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Aug 2018 15:56:02 +0300 Subject: vfs: add the fadvise() file operation This is going to be used by overlayfs and possibly useful for other filesystems. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ -- cgit v1.2.3-71-gd317 From 6b06546206868f723f2061d703a3c3c378dcbf4c Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:42 -0400 Subject: Revert "blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()" This reverts commit 4c6994806f708559c2812b73501406e21ae5dcd0. Destroying blkgs is tricky because of the nature of the relationship. A blkg should go away when either a blkcg or a request_queue goes away. However, blkg's pin the blkcg to ensure they remain valid. To break this cycle, when a blkcg is offlined, blkgs put back their css ref. This eventually lets css_free() get called which frees the blkcg. The above commit (4c6994806f70) breaks this order of events by trying to destroy blkgs in css_free(). As the blkgs still hold references to the blkcg, css_free() is never called. The race between blkcg_bio_issue_check() and cgroup_rmdir() will be addressed in the following patch by delaying destruction of a blkg until all writeback associated with the blkcg has been finished. Fixes: 4c6994806f70 ("blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Jens Axboe Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 78 ++++++++++------------------------------------ include/linux/blk-cgroup.h | 1 - 2 files changed, 16 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 694595b29b8f..2998e4f095d1 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, } } -static void blkg_pd_offline(struct blkcg_gq *blkg) -{ - int i; - - lockdep_assert_held(blkg->q->queue_lock); - lockdep_assert_held(&blkg->blkcg->lock); - - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; - - if (blkg->pd[i] && !blkg->pd[i]->offline && - pol->pd_offline_fn) { - pol->pd_offline_fn(blkg->pd[i]); - blkg->pd[i]->offline = true; - } - } -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; struct blkcg_gq *parent = blkg->parent; + int i; lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); @@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg) WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (blkg->pd[i] && pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + } + if (parent) { blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); @@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q) struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); - blkg_pd_offline(blkg); blkg_destroy(blkg); spin_unlock(&blkcg->lock); } @@ -1058,54 +1047,21 @@ static struct cftype blkcg_legacy_files[] = { * @css: css of interest * * This function is called when @css is about to go away and responsible - * for offlining all blkgs pd and killing all wbs associated with @css. - * blkgs pd offline should be done while holding both q and blkcg locks. - * As blkcg lock is nested inside q lock, this function performs reverse - * double lock dancing. + * for shooting down all blkgs associated with @css. blkgs should be + * removed while holding both q and blkcg locks. As blkcg lock is nested + * inside q lock, this function performs reverse double lock dancing. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg_gq *blkg; spin_lock_irq(&blkcg->lock); - hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - struct request_queue *q = blkg->q; - - if (spin_trylock(q->queue_lock)) { - blkg_pd_offline(blkg); - spin_unlock(q->queue_lock); - } else { - spin_unlock_irq(&blkcg->lock); - cpu_relax(); - spin_lock_irq(&blkcg->lock); - } - } - - spin_unlock_irq(&blkcg->lock); - - wb_blkcg_offline(blkcg); -} - -/** - * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg - * @blkcg: blkcg of interest - * - * This function is called when blkcg css is about to free and responsible for - * destroying all blkgs associated with @blkcg. - * blkgs should be removed while holding both q and blkcg locks. As blkcg lock - * is nested inside q lock, this function performs reverse double lock dancing. - */ -static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) -{ - spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, - struct blkcg_gq, - blkcg_node); + struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (spin_trylock(q->queue_lock)) { @@ -1117,7 +1073,10 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) spin_lock_irq(&blkcg->lock); } } + spin_unlock_irq(&blkcg->lock); + + wb_blkcg_offline(blkcg); } static void blkcg_css_free(struct cgroup_subsys_state *css) @@ -1125,8 +1084,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) struct blkcg *blkcg = css_to_blkcg(css); int i; - blkcg_destroy_all_blkgs(blkcg); - mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); @@ -1480,11 +1437,8 @@ void blkcg_deactivate_policy(struct request_queue *q, list_for_each_entry(blkg, &q->blkg_list, q_node) { if (blkg->pd[pol->plid]) { - if (!blkg->pd[pol->plid]->offline && - pol->pd_offline_fn) { + if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); - blkg->pd[pol->plid]->offline = true; - } pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..1615cdd4c797 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -89,7 +89,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* -- cgit v1.2.3-71-gd317 From 59b57717fff8b562825d9d25e0180ad7e8048ca9 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:43 -0400 Subject: blkcg: delay blkg destruction until after writeback has finished Currently, blkcg destruction relies on a sequence of events: 1. Destruction starts. blkcg_css_offline() is called and blkgs release their reference to the blkcg. This immediately destroys the cgwbs (writeback). 2. With blkgs giving up their reference, the blkcg ref count should become zero and eventually call blkcg_css_free() which finally frees the blkcg. Jiufei Xue reported that there is a race between blkcg_bio_issue_check() and cgroup_rmdir(). To remedy this, blkg destruction becomes contingent on the completion of all writeback associated with the blkcg. A count of the number of cgwbs is maintained and once that goes to zero, blkg destruction can follow. This should prevent premature blkg destruction related to writeback. The new process for blkcg cleanup is as follows: 1. Destruction starts. blkcg_css_offline() is called which offlines writeback. Blkg destruction is delayed on the cgwb_refcnt count to avoid punting potentially large amounts of outstanding writeback to root while maintaining any ongoing policies. Here, the base cgwb_refcnt is put back. 2. When the cgwb_refcnt becomes zero, blkcg_destroy_blkgs() is called and handles destruction of blkgs. This is where the css reference held by each blkg is released. 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. This finally frees the blkg. It seems in the past blk-throttle didn't do the most understandable things with taking data from a blkg while associating with current. So, the simplification and unification of what blk-throttle is doing caused this. Fixes: 08e18eab0c579 ("block: add bi_blkg to the bio for cgroups") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Josef Bacik Cc: Jens Axboe Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 53 +++++++++++++++++++++++++++++++++++++++------- include/linux/blk-cgroup.h | 44 ++++++++++++++++++++++++++++++++++++++ mm/backing-dev.c | 5 +++++ 3 files changed, 94 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 2998e4f095d1..c19f9078da1e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1042,21 +1042,59 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +/* + * blkcg destruction is a three-stage process. + * + * 1. Destruction starts. The blkcg_css_offline() callback is invoked + * which offlines writeback. Here we tie the next stage of blkg destruction + * to the completion of writeback associated with the blkcg. This lets us + * avoid punting potentially large amounts of outstanding writeback to root + * while maintaining any ongoing policies. The next stage is triggered when + * the nr_cgwbs count goes to zero. + * + * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called + * and handles the destruction of blkgs. Here the css reference held by + * the blkg is put back eventually allowing blkcg_css_free() to be called. + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. Any submitted ios that fail to get the blkg ref will be + * punted to the root_blkg. + * + * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. + * This finally frees the blkcg. + */ + /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * - * This function is called when @css is about to go away and responsible - * for shooting down all blkgs associated with @css. blkgs should be - * removed while holding both q and blkcg locks. As blkcg lock is nested - * inside q lock, this function performs reverse double lock dancing. - * - * This is the blkcg counterpart of ioc_release_fn(). + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); + /* this prevents anyone from attaching or migrating to this blkcg */ + wb_blkcg_offline(blkcg); + + /* put the base cgwb reference allowing step 2 to be triggered */ + blkcg_cgwb_put(blkcg); +} + +/** + * blkcg_destroy_blkgs - responsible for shooting down blkgs + * @blkcg: blkcg of interest + * + * blkgs should be removed while holding both q and blkcg locks. As blkcg lock + * is nested inside q lock, this function performs reverse double lock dancing. + * Destroying the blkgs releases the reference held on the blkcg's css allowing + * blkcg_css_free to eventually be called. + * + * This is the blkcg counterpart of ioc_release_fn(). + */ +void blkcg_destroy_blkgs(struct blkcg *blkcg) +{ spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { @@ -1075,8 +1113,6 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css) } spin_unlock_irq(&blkcg->lock); - - wb_blkcg_offline(blkcg); } static void blkcg_css_free(struct cgroup_subsys_state *css) @@ -1146,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); + refcount_set(&blkcg->cgwb_refcnt, 1); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1615cdd4c797..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -386,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f5981e9d6ae2..8a8bb8796c6c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); + /* triggers blkg destruction if cgwb_refcnt becomes zero */ + blkcg_cgwb_put(blkcg); + fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); wb_exit(wb); @@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); + blkcg_cgwb_get(blkcg); css_get(memcg_css); css_get(blkcg_css); } -- cgit v1.2.3-71-gd317 From c43c5e9f524ec914e7e202f9c5ab91779629ccc6 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 3 Sep 2018 10:15:33 +0200 Subject: timekeeping: Fix declaration of read_persistent_wall_and_boot_offset() It is read_persistent_wall_and_boot_offset() and not read_persistent_clock_and_boot_offset() Fixes: 3eca993740b8eb40f51 ("timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()") Signed-off-by: Christian Borntraeger Signed-off-by: Thomas Gleixner Cc: Pavel Tatashin Link: https://lkml.kernel.org/r/20180903081533.34366-1-borntraeger@de.ibm.com --- include/linux/timekeeping.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* -- cgit v1.2.3-71-gd317 From 9fd0e09a4e86499639653243edfcb417a05c5c46 Mon Sep 17 00:00:00 2001 From: Anthony Wong Date: Fri, 31 Aug 2018 20:06:42 +0800 Subject: r8169: add support for NCube 8168 network card This card identifies itself as: Ethernet controller [0200]: NCube Device [10ff:8168] (rev 06) Subsystem: TP-LINK Technologies Co., Ltd. Device [7470:3468] Adding a new entry to rtl8169_pci_tbl makes the card work. Link: http://launchpad.net/bugs/1788730 Signed-off-by: Anthony Wong Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 1 + include/linux/pci_ids.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index ac306797590e..b08d51bf7a20 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -218,6 +218,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 }, + { PCI_DEVICE(PCI_VENDOR_ID_NCUBE, 0x8168), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 }, { PCI_VENDOR_ID_DLINK, 0x4300, PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 }, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 99d366cb0e9f..d157983b84cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3084,4 +3084,6 @@ #define PCI_VENDOR_ID_OCZ 0x1b85 +#define PCI_VENDOR_ID_NCUBE 0x10ff + #endif /* _LINUX_PCI_IDS_H */ -- cgit v1.2.3-71-gd317 From 0d6c3011409135ea84e2a231b013a22017ff999a Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 4 Sep 2018 15:31:14 +0200 Subject: HID: core: fix grouping by application commit f07b3c1da92d ("HID: generic: create one input report per application type") was effectively the same as MULTI_INPUT: hidinput->report was never set, so hidinput_match_application() always returned null. Fix that by testing against the real application. Note that this breaks some old eGalax touchscreens that expect MULTI_INPUT instead of HID_QUIRK_INPUT_PER_APP. Enable this quirk for backward compatibility on all non-Win8 touchscreens. link: https://bugzilla.kernel.org/show_bug.cgi?id=200847 link: https://bugzilla.kernel.org/show_bug.cgi?id=200849 link: https://bugs.archlinux.org/task/59699 link: https://github.com/NixOS/nixpkgs/issues/45165 Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-input.c | 4 ++-- drivers/hid/hid-multitouch.c | 3 +++ include/linux/hid.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index ac201817a2dd..a481eaf39e88 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1582,6 +1582,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid, input_dev->dev.parent = &hid->dev; hidinput->input = input_dev; + hidinput->application = application; list_add_tail(&hidinput->list, &hid->inputs); INIT_LIST_HEAD(&hidinput->reports); @@ -1677,8 +1678,7 @@ static struct hid_input *hidinput_match_application(struct hid_report *report) struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { - if (hidinput->report && - hidinput->report->application == report->application) + if (hidinput->application == report->application) return hidinput; } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 88da991ef256..da954f3f4da7 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1697,6 +1697,9 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) */ hdev->quirks |= HID_QUIRK_INPUT_PER_APP; + if (id->group != HID_GROUP_MULTITOUCH_WIN_8) + hdev->quirks |= HID_QUIRK_MULTI_INPUT; + timer_setup(&td->release_timer, mt_expired_timeout, 0); ret = hid_parse(hdev); diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { -- cgit v1.2.3-71-gd317 From d23df2dc56325c72b51670b1fb400ddd23dc17cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:51:59 -0700 Subject: linux/mod_devicetable.h: fix kernel-doc missing notation for typec_device_id Fix kernel-doc warning for missing struct member description: ../include/linux/mod_devicetable.h:763: warning: Function parameter or member 'driver_data' not described in 'typec_device_id' Fixes: 8a37d87d72f0c ("usb: typec: Bus type for alternate modes") Signed-off-by: Randy Dunlap Cc: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; -- cgit v1.2.3-71-gd317 From 865e63b04e9b2a658d7f26bd13a71dcd964a9118 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 4 Sep 2018 16:26:11 -0400 Subject: tracing: Add back in rcu_irq_enter/exit_irqson() for rcuidle tracepoints Borislav reported the following splat: ============================= WARNING: suspicious RCU usage 4.19.0-rc1+ #1 Not tainted ----------------------------- ./include/linux/rcupdate.h:631 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 2, debug_locks = 1 RCU used illegally from extended quiescent state! 1 lock held by swapper/0/0: #0: 000000004557ee0e (rcu_read_lock){....}, at: perf_event_output_forward+0x0/0x130 stack backtrace: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.0-rc1+ #1 Hardware name: LENOVO 2320CTO/2320CTO, BIOS G2ET86WW (2.06 ) 11/13/2012 Call Trace: dump_stack+0x85/0xcb perf_event_output_forward+0xf6/0x130 __perf_event_overflow+0x52/0xe0 perf_swevent_overflow+0x91/0xb0 perf_tp_event+0x11a/0x350 ? find_held_lock+0x2d/0x90 ? __lock_acquire+0x2ce/0x1350 ? __lock_acquire+0x2ce/0x1350 ? retint_kernel+0x2d/0x2d ? find_held_lock+0x2d/0x90 ? tick_nohz_get_sleep_length+0x83/0xb0 ? perf_trace_cpu+0xbb/0xd0 ? perf_trace_buf_alloc+0x5a/0xa0 perf_trace_cpu+0xbb/0xd0 cpuidle_enter_state+0x185/0x340 do_idle+0x1eb/0x260 cpu_startup_entry+0x5f/0x70 start_kernel+0x49b/0x4a6 secondary_startup_64+0xa4/0xb0 This is due to the tracepoints moving to SRCU usage which does not require RCU to be "watching". But perf uses these tracepoints with RCU and expects it to be. Hence, we still need to add in the rcu_irq_enter/exit_irqson() calls for "rcuidle" tracepoints. This is a temporary fix until we have SRCU working in NMI context, and then perf can be converted to use that instead of normal RCU. Link: http://lkml.kernel.org/r/20180904162611.6a120068@gandalf.local.home Cc: x86-ml Cc: Peter Zijlstra Reported-by: Borislav Petkov Tested-by: Borislav Petkov Reviewed-by: "Paul E. McKenney" Fixes: e6753f23d961d ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) -- cgit v1.2.3-71-gd317 From 76d5581c870454be5f1f1a106c57985902e7ea20 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 5 Aug 2018 09:19:33 +0300 Subject: net/mlx5: Fix use-after-free in self-healing flow When the mlx5 health mechanism detects a problem while the driver is in the middle of init_one or remove_one, the driver needs to prevent the health mechanism from scheduling future work; if future work is scheduled, there is a problem with use-after-free: the system WQ tries to run the work item (which has been freed) at the scheduled future time. Prevent this by disabling work item scheduling in the health mechanism when the driver is in the middle of init_one() or remove_one(). Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Jack Morgenstein Reviewed-by: Feras Daoud Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 10 +++++++++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 +++--- include/linux/mlx5/driver.h | 2 +- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d39b0b7011b2..9f39aeca863f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) add_timer(&health->timer); } -void mlx5_stop_health_poll(struct mlx5_core_dev *dev) +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; + + if (disable_health) { + spin_lock_irqsave(&health->wq_lock, flags); + set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock_irqrestore(&health->wq_lock, flags); + } del_timer_sync(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cf3e4a659052..739aad0a0b35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1286,7 +1286,7 @@ err_cleanup_once: mlx5_cleanup_once(dev); err_stop_poll: - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, boot); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); goto out_err; @@ -1346,7 +1346,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_free_irq_vectors(dev); if (cleanup) mlx5_cleanup_once(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, cleanup); err = mlx5_cmd_teardown_hca(dev); if (err) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); @@ -1608,7 +1608,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) * with the HCA, so the health polll is no longer needed. */ mlx5_drain_health_wq(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_force_teardown_hca(dev); if (ret) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..aa65f58c6610 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1052,7 +1052,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); -- cgit v1.2.3-71-gd317 From 8d71e818506718e8d7032ce824b5c74a17d4f7a5 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:04:41 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer fragment size Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: 388ca8be0037 ("IB/mlx5: Implement fragmented completion queue (CQ)") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/wq.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/wq.h | 2 +- include/linux/mlx5/driver.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index c8c315eb5128..d838af9539b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) return (u32)wq->fbc.sz_m1 + 1; } -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) { - return (u32)wq->fbc.frag_sz_m1 + 1; + return wq->fbc.frag_sz_m1 + 1; } u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 2bd4c3184eba..3a1a170bb2d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa65f58c6610..3a1258fd8ac3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,7 +362,7 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; + u16 frag_sz_m1; u32 strides_offset; u8 log_sz; u8 log_stride; -- cgit v1.2.3-71-gd317 From a09036221092989b88c55d24d1f12ceb1d7d361f Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:07:58 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer strides offset Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: d7037ad73daa ("net/mlx5: Fix QP fragmented buffer allocation") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/wq.c | 2 +- include/linux/mlx5/driver.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index d838af9539b1..68e7f8df2a6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -138,7 +138,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { - u32 sq_strides_offset; + u16 sq_strides_offset; u32 rq_pg_remainder; int err; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3a1258fd8ac3..66d94b4557cf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -363,7 +363,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u16 frag_sz_m1; - u32 strides_offset; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -995,7 +995,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; -- cgit v1.2.3-71-gd317 From a318c2432218d3cd189ec8228b8a795666899c2a Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: mfd: da9063: Fix DT probing with constraints Commit 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") reordered the da9063_regulator_info[] array, but not the DA9063_ID_* regulator ids and not the da9063_matches[] array, because ids are used as indices in the array initializer. This mismatch between regulator id and da9063_regulator_info[] array index causes the driver probe to fail because constraints from DT are not applied to the correct regulator: da9063 0-0058: Device detected (chip-ID: 0x61, var-ID: 0x50) DA9063_BMEM: Bringing 900000uV into 3300000-3300000uV DA9063_LDO9: Bringing 3300000uV into 2500000-2500000uV DA9063_LDO1: Bringing 900000uV into 3300000-3300000uV DA9063_LDO1: failed to apply 3300000-3300000uV constraint(-22) This patch reorders the DA9063_ID_* as apparently intended, and with them the entries in the da90630_matches[] array. Fixes: 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") Signed-off-by: Philipp Zabel Reviewed-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/da9063/pdata.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ -- cgit v1.2.3-71-gd317 From 01c5f85aebaaddfd7e6051fb2ec80c1d4b463554 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Sep 2018 10:59:53 -0600 Subject: blk-cgroup: increase number of supported policies After merging the iolatency policy, we potentially now have 4 policies being registered, but only support 3. This causes one of them to fail loading. Takashi reports that BFQ no longer works for him, because it fails to load due to policy registration failure. Bump to 5 policies, and also add a warning for when we have exceeded the global amount. If we have to touch this again, we should switch to a dynamic scheme instead. Reported-by: Takashi Iwai Reviewed-by: Jeff Moyer Tested-by: Takashi Iwai Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 4 +++- include/linux/blkdev.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c19f9078da1e..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1510,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; - if (i >= BLKCG_MAX_POLS) + if (i >= BLKCG_MAX_POLS) { + pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; + } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3-71-gd317 From bfc456060d0cbcf6902a436d358b60cb1534668c Mon Sep 17 00:00:00 2001 From: Dennis Dalessandro Date: Fri, 31 Aug 2018 10:34:14 -0700 Subject: IB/hfi1,PCI: Allow bus reset while probing Calling into the new API to reset the secondary bus results in a deadlock. This occurs because the device/bus is already locked at probe time. Reverting back to the old behavior while the API is improved. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200985 Fixes: c6a44ba950d1 ("PCI: Rename pci_try_reset_bus() to pci_reset_bus()") Fixes: 409888e0966e ("IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus Reset") Signed-off-by: Dennis Dalessandro Signed-off-by: Bjorn Helgaas Reviewed-by: Michael J. Ruhl Cc: Sinan Kaya --- drivers/infiniband/hw/hfi1/pcie.c | 11 ++++------- drivers/pci/pci.c | 1 + include/linux/pci.h | 3 +++ 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 30b260332a10..1835f3a7aa8d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4547,6 +4547,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } +EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ -- cgit v1.2.3-71-gd317 From 37a3a98ef601f89100e3bb657fb0e190b857028c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 10 Sep 2018 16:20:25 +0200 Subject: ALSA: hda - Enable runtime PM only for discrete GPU The recent change of vga_switcheroo allowed the runtime PM for HD-audio on AMD GPUs, but this also resulted in a regression. When the HD-audio controller driver gets runtime-suspended, HD-audio link is turned off, and the hotplug notification is ignored. This leads to the inconsistent audio state (the connection isn't notified and ELD is ignored). The best fix would be to implement the proper ELD notification via the audio component, but it's still not ready. As a quick workaround, this patch adds the check of runtime_idle and allows the runtime suspend only when the vga_switcheroo is bound with discrete GPU. That is, a system with a single GPU and APU would be again without runtime PM to keep the HD-audio link for the hotplug notification and ELD read out. Also, the codec->auto_runtime_pm flag is set only for the discrete GPU at the time GPU gets bound via vga_switcheroo (i.e. only dGPU is forcibly runtime-PM enabled), so that APU can still get the ELD notification. For identifying which GPU is bound, a new vga_switcheroo client callback, gpu_bound, is implemented. The vga_switcheroo simply calls this when GPU is bound, and tells whether it's dGPU or APU. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200945 Fixes: 07f4f97d7b4b ("vga_switcheroo: Use device link for HDA controller") Reported-by: Jian-Hong Pan Tested-by: Jian-Hong Pan Acked-by: Lukas Wunner Signed-off-by: Takashi Iwai --- drivers/gpu/vga/vga_switcheroo.c | 2 + include/linux/vga_switcheroo.h | 3 ++ sound/pci/hda/hda_intel.c | 86 +++++++++++++++++++++++++++++----------- sound/pci/hda/hda_intel.h | 1 + 4 files changed, 69 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index a96bf46bc483..cf2a18571d48 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -215,6 +215,8 @@ static void vga_switcheroo_enable(void) return; client->id = ret | ID_BIT_AUDIO; + if (client->ops->gpu_bound) + client->ops->gpu_bound(client->pdev, ret); } vga_switcheroo_debugfs_init(&vgasr_priv); diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a34539b7f750..7e6ac0114d55 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -133,15 +133,18 @@ struct vga_switcheroo_handler { * @can_switch: check if the device is in a position to switch now. * Mandatory. The client should return false if a user space process * has one of its device files open + * @gpu_bound: notify the client id to audio client when the GPU is bound. * * Client callbacks. A client can be either a GPU or an audio device on a GPU. * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be * set to NULL. For audio clients, the @reprobe member is bogus. + * OTOH, @gpu_bound is only for audio clients, and not used for GPU clients. */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); bool (*can_switch)(struct pci_dev *dev); + void (*gpu_bound)(struct pci_dev *dev, enum vga_switcheroo_client_id); }; #if defined(CONFIG_VGA_SWITCHEROO) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 1b2ce304152a..aa4c672dbaf7 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -365,8 +365,10 @@ enum { */ #ifdef SUPPORT_VGA_SWITCHEROO #define use_vga_switcheroo(chip) ((chip)->use_vga_switcheroo) +#define needs_eld_notify_link(chip) ((chip)->need_eld_notify_link) #else #define use_vga_switcheroo(chip) 0 +#define needs_eld_notify_link(chip) false #endif #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ @@ -453,6 +455,7 @@ static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev, #endif static int azx_acquire_irq(struct azx *chip, int do_disconnect); +static void set_default_power_save(struct azx *chip); /* * initialize the PCI registers @@ -1201,6 +1204,10 @@ static int azx_runtime_idle(struct device *dev) azx_bus(chip)->codec_powered || !chip->running) return -EBUSY; + /* ELD notification gets broken when HD-audio bus is off */ + if (needs_eld_notify_link(hda)) + return -EBUSY; + return 0; } @@ -1298,6 +1305,36 @@ static bool azx_vs_can_switch(struct pci_dev *pci) return true; } +/* + * The discrete GPU cannot power down unless the HDA controller runtime + * suspends, so activate runtime PM on codecs even if power_save == 0. + */ +static void setup_vga_switcheroo_runtime_pm(struct azx *chip) +{ + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + struct hda_codec *codec; + + if (hda->use_vga_switcheroo && !hda->need_eld_notify_link) { + list_for_each_codec(codec, &chip->bus) + codec->auto_runtime_pm = 1; + /* reset the power save setup */ + if (chip->running) + set_default_power_save(chip); + } +} + +static void azx_vs_gpu_bound(struct pci_dev *pci, + enum vga_switcheroo_client_id client_id) +{ + struct snd_card *card = pci_get_drvdata(pci); + struct azx *chip = card->private_data; + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + + if (client_id == VGA_SWITCHEROO_DIS) + hda->need_eld_notify_link = 0; + setup_vga_switcheroo_runtime_pm(chip); +} + static void init_vga_switcheroo(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -1306,6 +1343,7 @@ static void init_vga_switcheroo(struct azx *chip) dev_info(chip->card->dev, "Handle vga_switcheroo audio client\n"); hda->use_vga_switcheroo = 1; + hda->need_eld_notify_link = 1; /* cleared in gpu_bound op */ chip->driver_caps |= AZX_DCAPS_PM_RUNTIME; pci_dev_put(p); } @@ -1314,6 +1352,7 @@ static void init_vga_switcheroo(struct azx *chip) static const struct vga_switcheroo_client_ops azx_vs_ops = { .set_gpu_state = azx_vs_set_state, .can_switch = azx_vs_can_switch, + .gpu_bound = azx_vs_gpu_bound, }; static int register_vga_switcheroo(struct azx *chip) @@ -1339,6 +1378,7 @@ static int register_vga_switcheroo(struct azx *chip) #define init_vga_switcheroo(chip) /* NOP */ #define register_vga_switcheroo(chip) 0 #define check_hdmi_disabled(pci) false +#define setup_vga_switcheroo_runtime_pm(chip) /* NOP */ #endif /* SUPPORT_VGA_SWITCHER */ /* @@ -1352,6 +1392,7 @@ static int azx_free(struct azx *chip) if (azx_has_pm_runtime(chip) && chip->running) pm_runtime_get_noresume(&pci->dev); + chip->running = 0; azx_del_card_list(chip); @@ -2230,6 +2271,25 @@ static struct snd_pci_quirk power_save_blacklist[] = { }; #endif /* CONFIG_PM */ +static void set_default_power_save(struct azx *chip) +{ + int val = power_save; + +#ifdef CONFIG_PM + if (pm_blacklist) { + const struct snd_pci_quirk *q; + + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); +} + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2241,9 +2301,7 @@ static int azx_probe_continue(struct azx *chip) struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; - struct hda_codec *codec; int dev = chip->dev_index; - int val; int err; hda->probe_continued = 1; @@ -2322,31 +2380,13 @@ static int azx_probe_continue(struct azx *chip) if (err < 0) goto out_free; + setup_vga_switcheroo_runtime_pm(chip); + chip->running = 1; azx_add_card_list(chip); - val = power_save; -#ifdef CONFIG_PM - if (pm_blacklist) { - const struct snd_pci_quirk *q; - - q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); - if (q && val) { - dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", - q->subvendor, q->subdevice); - val = 0; - } - } -#endif /* CONFIG_PM */ - /* - * The discrete GPU cannot power down unless the HDA controller runtime - * suspends, so activate runtime PM on codecs even if power_save == 0. - */ - if (use_vga_switcheroo(hda)) - list_for_each_codec(codec, &chip->bus) - codec->auto_runtime_pm = 1; + set_default_power_save(chip); - snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip)) pm_runtime_put_autosuspend(&pci->dev); diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h index e3a3d318d2e5..f59719e06b91 100644 --- a/sound/pci/hda/hda_intel.h +++ b/sound/pci/hda/hda_intel.h @@ -37,6 +37,7 @@ struct hda_intel { /* vga_switcheroo setup */ unsigned int use_vga_switcheroo:1; + unsigned int need_eld_notify_link:1; unsigned int vga_switcheroo_registered:1; unsigned int init_failed:1; /* delayed init failed */ -- cgit v1.2.3-71-gd317 From 7a9cdebdcc17e426fb5287e4a82db1dfe86339b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 12 Sep 2018 23:57:48 -1000 Subject: mm: get rid of vmacache_flush_all() entirely Jann Horn points out that the vmacache_flush_all() function is not only potentially expensive, it's buggy too. It also happens to be entirely unnecessary, because the sequence number overflow case can be avoided by simply making the sequence number be 64-bit. That doesn't even grow the data structures in question, because the other adjacent fields are already 64-bit. So simplify the whole thing by just making the sequence number overflow case go away entirely, which gets rid of all the complications and makes the code faster too. Win-win. [ Oleg Nesterov points out that the VMACACHE_FULL_FLUSHES statistics also just goes away entirely with this ] Reported-by: Jann Horn Suggested-by: Will Deacon Acked-by: Davidlohr Bueso Cc: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 2 +- include/linux/vm_event_item.h | 1 - include/linux/vmacache.h | 5 ----- mm/debug.c | 4 ++-- mm/vmacache.c | 38 -------------------------------------- 6 files changed, 4 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -19,44 +19,6 @@ #endif #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) -/* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - /* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this -- cgit v1.2.3-71-gd317 From 822f312d47f0200dc0999c9f006fe94aa43bd0bd Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 12 Sep 2018 15:33:45 +0200 Subject: kvm: x86: make kvm_{load|put}_guest_fpu() static The functions kvm_load_guest_fpu() kvm_put_guest_fpu() are only used locally, make them static. This requires also that both functions are moved because they are used before their implementation. Those functions were exported (via EXPORT_SYMBOL) before commit e5bb40251a920 ("KVM: Drop kvm_{load,put}_guest_fpu() exports"). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 46 +++++++++++++++++++++++----------------------- include/linux/kvm_host.h | 2 -- 2 files changed, 23 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9d0fda9056de..6f4789398876 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7835,6 +7835,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +/* Swap (qemu) user FPU context for the guest FPU context. */ +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); + preempt_enable(); + trace_kvm_fpu(1); +} + +/* When vcpu_run ends, restore user space FPU context. */ +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); + ++vcpu->stat.fpu_reload; + trace_kvm_fpu(0); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -8412,29 +8435,6 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -/* Swap (qemu) user FPU context for the guest FPU context. */ -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); - trace_kvm_fpu(1); -} - -/* When vcpu_run ends, restore user space FPU context. */ -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); - preempt_enable(); - ++vcpu->stat.fpu_reload; - trace_kvm_fpu(0); -} - void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0205aee44ded..c926698040e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,8 +733,6 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -- cgit v1.2.3-71-gd317 From d124b44f09cab67fc6da4a4513417e3e54b01efc Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:41 +0200 Subject: Compiler Attributes: naked was fixed in gcc 4.6 Commit 9c695203a7dd ("compiler-gcc.h: gcc-4.5 needs noclone and noinline on __naked functions") added noinline and noclone as a workaround for a gcc 4.5 bug, which was resolved in 4.6.0. Since now the minimum gcc supported version is 4.6, we can clean it up. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44290 and https://godbolt.org/z/h6NMIL Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..25d3dd6b2702 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -84,14 +84,8 @@ * to trace naked functions because then mcount is called without * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. - * - * The asm() bodies of naked functions often depend on standard calling - * conventions, therefore they must be noinline and noclone. - * - * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. - * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) notrace #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -- cgit v1.2.3-71-gd317 From ae596de1a0c8c2c924dc99d23c026259372ab234 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:42 +0200 Subject: Compiler Attributes: naked can be shared The naked attribute is supported by at least gcc >= 4.6 (for ARM, which is the only current user), gcc >= 8 (for x86), clang >= 3.1 and icc >= 13. See https://godbolt.org/z/350Dyc Therefore, move it out of compiler-gcc.h so that the definition is shared by all compilers. This also fixes Clang support for ARM32 --- 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Suggested-by: Arnd Bergmann Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 -------- include/linux/compiler_types.h | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 25d3dd6b2702..4d36b27214fd 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,14 +79,6 @@ #define __noretpoline __attribute__((indirect_branch("keep"))) #endif -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - */ -#define __naked __attribute__((naked)) notrace - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..db192becfec4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,14 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((naked)) notrace + #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* -- cgit v1.2.3-71-gd317 From b57e99b4b8b0ebdf9707424e7ddc0c392bdc5fe6 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 21 Sep 2018 16:44:34 -0700 Subject: block: use nanosecond resolution for iostat Klaus Kusche reported that the I/O busy time in /proc/diskstats was not updating properly on 4.18. This is because we started using ktime to track elapsed time, and we convert nanoseconds to jiffies when we update the partition counter. However, this gets rounded down, so any I/Os that take less than a jiffy are not accounted for. Previously in this case, the value of jiffies would sometimes increment while we were doing I/O, so at least some I/Os were accounted for. Let's convert the stats to use nanoseconds internally. We still report milliseconds as before, now more accurately than ever. The value is still truncated to 32 bits for backwards compatibility. Fixes: 522a777566f5 ("block: consolidate struct request timestamp fields") Cc: stable@vger.kernel.org Reported-by: Klaus Kusche Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/bio.c | 2 +- block/blk-core.c | 4 +--- block/genhd.c | 6 +++--- block/partition-generic.c | 6 +++--- include/linux/genhd.h | 5 ++++- 5 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 8c680a776171..0093bed81c0e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op, const int sgrp = op_stat_group(req_op); int cpu = part_stat_lock(); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_round_stats(q, cpu, part); part_dec_in_flight(q, part, op_is_write(req_op)); diff --git a/block/blk-core.c b/block/blk-core.c index 4dbc93f43b38..cff0a60ee200 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2733,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now) * containing request is enough. */ if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { - unsigned long duration; const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; int cpu; - duration = nsecs_to_jiffies(now - req->start_time_ns); cpu = part_stat_lock(); part = req->part; part_stat_inc(cpu, part, ios[sgrp]); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns); part_round_stats(req->q, cpu, part); part_dec_in_flight(req->q, part, rq_data_dir(req)); diff --git a/block/genhd.c b/block/genhd.c index 8cc719a37b32..be5bab20b2ab 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_READ]), part_stat_read(hd, merges[STAT_READ]), part_stat_read(hd, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(hd, STAT_READ), part_stat_read(hd, ios[STAT_WRITE]), part_stat_read(hd, merges[STAT_WRITE]), part_stat_read(hd, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(hd, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)), part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD])) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) ); } disk_part_iter_exit(&piter); diff --git a/block/partition-generic.c b/block/partition-generic.c index 5a8975a1201c..d3d14e81fb12 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), (unsigned long long)part_stat_read(p, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(p, STAT_READ), part_stat_read(p, ios[STAT_WRITE]), part_stat_read(p, merges[STAT_WRITE]), (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(p, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue)), part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD]))); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..25c08c6c7f99 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; - unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_msecs(part, which) \ + div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC) + #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ -- cgit v1.2.3-71-gd317