From 823f18f8b860526fc099c222619a126d57d2ad8c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 29 Aug 2018 15:36:10 +0300 Subject: regulator: bd71837: Disable voltage monitoring for LDO3/4 There is a HW quirk in BD71837. The shutdown sequence timings for bucks/LDOs which are enabled via register interface are changed. At PMIC poweroff the voltage for BUCK6/7 is cut immediately at the beginning of shut-down sequence. This causes LDO5/6 voltage monitoring to detect under voltage and force PMIC to emergency state instead of poweroff. Disable voltage monitoring for LDO5 and LDO6 at probe to avoid this. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/mfd/rohm-bd718x7.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index a528747f8aed..e8338e5dc10b 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -78,9 +78,9 @@ enum { BD71837_REG_TRANS_COND0 = 0x1F, BD71837_REG_TRANS_COND1 = 0x20, BD71837_REG_VRFAULTEN = 0x21, - BD71837_REG_MVRFLTMASK0 = 0x22, - BD71837_REG_MVRFLTMASK1 = 0x23, - BD71837_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, BD71837_REG_RCVCFG = 0x25, BD71837_REG_RCVNUM = 0x26, BD71837_REG_PWRONCONFIG0 = 0x27, @@ -159,6 +159,33 @@ enum { #define BUCK8_MASK 0x3F #define BUCK8_DEFAULT 0x1E +/* BD718XX Voltage monitoring masks */ +#define BD718XX_BUCK1_VRMON80 0x1 +#define BD718XX_BUCK1_VRMON130 0x2 +#define BD718XX_BUCK2_VRMON80 0x4 +#define BD718XX_BUCK2_VRMON130 0x8 +#define BD718XX_1ST_NODVS_BUCK_VRMON80 0x1 +#define BD718XX_1ST_NODVS_BUCK_VRMON130 0x2 +#define BD718XX_2ND_NODVS_BUCK_VRMON80 0x4 +#define BD718XX_2ND_NODVS_BUCK_VRMON130 0x8 +#define BD718XX_3RD_NODVS_BUCK_VRMON80 0x10 +#define BD718XX_3RD_NODVS_BUCK_VRMON130 0x20 +#define BD718XX_4TH_NODVS_BUCK_VRMON80 0x40 +#define BD718XX_4TH_NODVS_BUCK_VRMON130 0x80 +#define BD718XX_LDO1_VRMON80 0x1 +#define BD718XX_LDO2_VRMON80 0x2 +#define BD718XX_LDO3_VRMON80 0x4 +#define BD718XX_LDO4_VRMON80 0x8 +#define BD718XX_LDO5_VRMON80 0x10 +#define BD718XX_LDO6_VRMON80 0x20 + +/* BD71837 specific voltage monitoring masks */ +#define BD71837_BUCK3_VRMON80 0x10 +#define BD71837_BUCK3_VRMON130 0x20 +#define BD71837_BUCK4_VRMON80 0x40 +#define BD71837_BUCK4_VRMON130 0x80 +#define BD71837_LDO7_VRMON80 0x40 + /* BD71837_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 -- cgit v1.2.3-71-gd317 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 --- Documentation/filesystems/vfs.txt | 3 ++ include/linux/fs.h | 5 +++ mm/fadvise.c | 78 ++++++++++++++++++++++----------------- 3 files changed, 53 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index ec2142c8dbd3..a6c6a8af48a2 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -885,6 +885,7 @@ struct file_operations { ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); }; Again, all methods are called without any locks being held, unless @@ -965,6 +966,8 @@ otherwise noted. dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE command. + fadvise: possibly called by the fadvise64() system call. + Note that the file operations are implemented by the specific filesystem in which the inode resides. When opening a device node (character or block special) most filesystems will call special 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 */ diff --git a/mm/fadvise.c b/mm/fadvise.c index 2d8376e3c640..2f59bac1cb77 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -27,9 +27,9 @@ * deactivate the pages and clear PG_Referenced. */ -int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +static int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice) { - struct fd f = fdget(fd); struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; @@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; - int ret = 0; - if (!f.file) - return -EBADF; + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; - inode = file_inode(f.file); - if (S_ISFIFO(inode->i_mode)) { - ret = -ESPIPE; - goto out; - } - - mapping = f.file->f_mapping; - if (!mapping || len < 0) { - ret = -EINVAL; - goto out; - } + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; bdi = inode_to_bdi(mapping->host); @@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* no bad return value, but ignore advice */ break; default: - ret = -EINVAL; + return -EINVAL; } - goto out; + return 0; } /* @@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: - f.file->f_ra.ra_pages = bdi->ra_pages; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - spin_lock(&f.file->f_lock); - f.file->f_mode |= FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: - f.file->f_ra.ra_pages = bdi->ra_pages * 2; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ @@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) * Ignore return value because fadvise() shall return * success even if filesystem can't retrieve a hint, */ - force_page_cache_readahead(mapping, f.file, start_index, - nrpages); + force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: break; @@ -183,9 +174,30 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) } break; default: - ret = -EINVAL; + return -EINVAL; } -out: + return 0; +} + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + fdput(f); return ret; } -- cgit v1.2.3-71-gd317 From ef394f3fbecbe61d69450ad8cf0fa8f713c8ce8f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: regulator: 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: Geert Uytterhoeven Reviewed-by: Marek Vasut Signed-off-by: Mark Brown --- 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 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 3edd79cf5a44b12dbb13bc320f5788aed6562b36 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 3 Sep 2018 16:49:37 +0200 Subject: regulator: Fix 'do-nothing' value for regulators without suspend state Some regulators don't have all states defined and in such cases regulator core should not assume anything. However in current implementation of of_get_regulation_constraints() DO_NOTHING_IN_SUSPEND enable value was set only for regulators which had suspend node defined, otherwise the default 0 value was used, what means DISABLE_IN_SUSPEND. This lead to broken system suspend/resume on boards, which had simple regulator constraints definition (without suspend state nodes). To avoid further mismatches between the default and uninitialized values of the suspend enabled/disabled states, change the values of the them, so default '0' means DO_NOTHING_IN_SUSPEND. Fixes: 72069f9957a1: regulator: leave one item to record whether regulator is enabled Signed-off-by: Marek Szyprowski Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- drivers/regulator/core.c | 2 +- drivers/regulator/of_regulator.c | 2 -- include/linux/regulator/machine.h | 6 +++--- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index bb1324f93143..90215f57270f 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3161,7 +3161,7 @@ static inline int regulator_suspend_toggle(struct regulator_dev *rdev, if (!rstate->changeable) return -EPERM; - rstate->enabled = en; + rstate->enabled = (en) ? ENABLE_IN_SUSPEND : DISABLE_IN_SUSPEND; return 0; } diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 638f17d4c848..210fc20f7de7 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -213,8 +213,6 @@ static void of_get_regulation_constraints(struct device_node *np, else if (of_property_read_bool(suspend_np, "regulator-off-in-suspend")) suspend_state->enabled = DISABLE_IN_SUSPEND; - else - suspend_state->enabled = DO_NOTHING_IN_SUSPEND; if (!of_property_read_u32(np, "regulator-suspend-min-microvolt", &pval)) diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 3468703d663a..a459a5e973a7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -48,9 +48,9 @@ struct regulator; * DISABLE_IN_SUSPEND - turn off regulator in suspend states * ENABLE_IN_SUSPEND - keep regulator on in suspend states */ -#define DO_NOTHING_IN_SUSPEND (-1) -#define DISABLE_IN_SUSPEND 0 -#define ENABLE_IN_SUSPEND 1 +#define DO_NOTHING_IN_SUSPEND 0 +#define DISABLE_IN_SUSPEND 1 +#define ENABLE_IN_SUSPEND 2 /* Regulator active discharge flags */ enum regulator_active_discharge { -- 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 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 dfb06cba8c73c0704710b2e3fbe2c35ac66a01b4 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 5 Sep 2018 13:31:40 -0700 Subject: uaccess: Fix is_source param for check_copy_size() in copy_to_iter_mcsafe() copy_to_iter_mcsafe() is passing in the is_source parameter as "false" to check_copy_size(). This is different than what copy_to_iter() does. Also, the addr parameter passed to check_copy_size() is the source so therefore we should be passing in "true" instead. Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Cc: Reported-by: Fan Du Signed-off-by: Dave Jiang Reviewed-by: Vishal Verma Reported-by: Wenwei Tao Signed-off-by: Dan Williams --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 409c845d4cd3..422b1c01ee0d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -172,7 +172,7 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) + if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter_mcsafe(addr, bytes, i); -- 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 8fce3331702316d4bcfeb0771c09ac75d2192bbc Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 17 Sep 2018 09:22:56 +0100 Subject: net: stmmac: Rework coalesce timer and fix multi-queue races This follows David Miller advice and tries to fix coalesce timer in multi-queue scenarios. We are now using per-queue coalesce values and per-queue TX timer. Coalesce timer default values was changed to 1ms and the coalesce frames to 25. Tested in B2B setup between XGMAC2 and GMAC5. Signed-off-by: Jose Abreu Fixes: ce736788e8a ("net: stmmac: adding multiple buffers for TX") Cc: Florian Fainelli Cc: Neil Armstrong Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 +- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 14 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 233 ++++++++++++---------- include/linux/stmmac.h | 1 + 4 files changed, 146 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 1854f270ad66..b1b305f8f414 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -258,10 +258,10 @@ struct stmmac_safety_stats { #define MAX_DMA_RIWT 0xff #define MIN_DMA_RIWT 0x20 /* Tx coalesce parameters */ -#define STMMAC_COAL_TX_TIMER 40000 +#define STMMAC_COAL_TX_TIMER 1000 #define STMMAC_MAX_COAL_TX_TICK 100000 #define STMMAC_TX_MAX_FRAMES 256 -#define STMMAC_TX_FRAMES 64 +#define STMMAC_TX_FRAMES 25 /* Packets types */ enum packets_types { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index c0a855b7ab3b..63e1064b27a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -48,6 +48,8 @@ struct stmmac_tx_info { /* Frequently used values are kept adjacent for cache effect */ struct stmmac_tx_queue { + u32 tx_count_frames; + struct timer_list txtimer; u32 queue_index; struct stmmac_priv *priv_data; struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp; @@ -73,7 +75,14 @@ struct stmmac_rx_queue { u32 rx_zeroc_thresh; dma_addr_t dma_rx_phy; u32 rx_tail_addr; +}; + +struct stmmac_channel { struct napi_struct napi ____cacheline_aligned_in_smp; + struct stmmac_priv *priv_data; + u32 index; + int has_rx; + int has_tx; }; struct stmmac_tc_entry { @@ -109,14 +118,12 @@ struct stmmac_pps_cfg { struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ - u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; int tx_coalesce; int hwts_tx_en; bool tx_path_in_lpi_mode; - struct timer_list txtimer; bool tso; unsigned int dma_buf_sz; @@ -137,6 +144,9 @@ struct stmmac_priv { /* TX Queue */ struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES]; + /* Generic channel for NAPI */ + struct stmmac_channel channel[STMMAC_CH_MAX]; + bool oldlink; int speed; int oldduplex; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9f458bb16f2a..ab9cc0143ff2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -148,12 +148,14 @@ static void stmmac_verify_args(void) static void stmmac_disable_all_queues(struct stmmac_priv *priv) { u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 maxq = max(rx_queues_cnt, tx_queues_cnt); u32 queue; - for (queue = 0; queue < rx_queues_cnt; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - napi_disable(&rx_q->napi); + napi_disable(&ch->napi); } } @@ -164,12 +166,14 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv) static void stmmac_enable_all_queues(struct stmmac_priv *priv) { u32 rx_queues_cnt = priv->plat->rx_queues_to_use; + u32 tx_queues_cnt = priv->plat->tx_queues_to_use; + u32 maxq = max(rx_queues_cnt, tx_queues_cnt); u32 queue; - for (queue = 0; queue < rx_queues_cnt; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - napi_enable(&rx_q->napi); + napi_enable(&ch->napi); } } @@ -1843,18 +1847,18 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) * @queue: TX queue index * Description: it reclaims the transmit resources after transmission completes. */ -static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) +static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; - unsigned int entry; + unsigned int entry, count = 0; - netif_tx_lock(priv->dev); + __netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue)); priv->xstats.tx_clean++; entry = tx_q->dirty_tx; - while (entry != tx_q->cur_tx) { + while ((entry != tx_q->cur_tx) && (count < budget)) { struct sk_buff *skb = tx_q->tx_skbuff[entry]; struct dma_desc *p; int status; @@ -1870,6 +1874,8 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) if (unlikely(status & tx_dma_own)) break; + count++; + /* Make sure descriptor fields are read after reading * the own bit. */ @@ -1937,7 +1943,10 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) stmmac_enable_eee_mode(priv); mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); } - netif_tx_unlock(priv->dev); + + __netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue)); + + return count; } /** @@ -2020,6 +2029,33 @@ static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv) return false; } +static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan) +{ + int status = stmmac_dma_interrupt_status(priv, priv->ioaddr, + &priv->xstats, chan); + struct stmmac_channel *ch = &priv->channel[chan]; + bool needs_work = false; + + if ((status & handle_rx) && ch->has_rx) { + needs_work = true; + } else { + status &= ~handle_rx; + } + + if ((status & handle_tx) && ch->has_tx) { + needs_work = true; + } else { + status &= ~handle_tx; + } + + if (needs_work && napi_schedule_prep(&ch->napi)) { + stmmac_disable_dma_irq(priv, priv->ioaddr, chan); + __napi_schedule(&ch->napi); + } + + return status; +} + /** * stmmac_dma_interrupt - DMA ISR * @priv: driver private structure @@ -2034,57 +2070,14 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) u32 channels_to_check = tx_channel_count > rx_channel_count ? tx_channel_count : rx_channel_count; u32 chan; - bool poll_scheduled = false; int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)]; /* Make sure we never check beyond our status buffer. */ if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status))) channels_to_check = ARRAY_SIZE(status); - /* Each DMA channel can be used for rx and tx simultaneously, yet - * napi_struct is embedded in struct stmmac_rx_queue rather than in a - * stmmac_channel struct. - * Because of this, stmmac_poll currently checks (and possibly wakes) - * all tx queues rather than just a single tx queue. - */ for (chan = 0; chan < channels_to_check; chan++) - status[chan] = stmmac_dma_interrupt_status(priv, priv->ioaddr, - &priv->xstats, chan); - - for (chan = 0; chan < rx_channel_count; chan++) { - if (likely(status[chan] & handle_rx)) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; - - if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, priv->ioaddr, chan); - __napi_schedule(&rx_q->napi); - poll_scheduled = true; - } - } - } - - /* If we scheduled poll, we already know that tx queues will be checked. - * If we didn't schedule poll, see if any DMA channel (used by tx) has a - * completed transmission, if so, call stmmac_poll (once). - */ - if (!poll_scheduled) { - for (chan = 0; chan < tx_channel_count; chan++) { - if (status[chan] & handle_tx) { - /* It doesn't matter what rx queue we choose - * here. We use 0 since it always exists. - */ - struct stmmac_rx_queue *rx_q = - &priv->rx_queue[0]; - - if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, - priv->ioaddr, chan); - __napi_schedule(&rx_q->napi); - } - break; - } - } - } + status[chan] = stmmac_napi_check(priv, chan); for (chan = 0; chan < tx_channel_count; chan++) { if (unlikely(status[chan] & tx_hard_error_bump_tc)) { @@ -2233,6 +2226,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) return ret; } +static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue) +{ + struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; + + mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer)); +} + /** * stmmac_tx_timer - mitigation sw timer for tx. * @data: data pointer @@ -2241,13 +2241,14 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) */ static void stmmac_tx_timer(struct timer_list *t) { - struct stmmac_priv *priv = from_timer(priv, t, txtimer); - u32 tx_queues_count = priv->plat->tx_queues_to_use; - u32 queue; + struct stmmac_tx_queue *tx_q = from_timer(tx_q, t, txtimer); + struct stmmac_priv *priv = tx_q->priv_data; + struct stmmac_channel *ch; + + ch = &priv->channel[tx_q->queue_index]; - /* let's scan all the tx queues */ - for (queue = 0; queue < tx_queues_count; queue++) - stmmac_tx_clean(priv, queue); + if (likely(napi_schedule_prep(&ch->napi))) + __napi_schedule(&ch->napi); } /** @@ -2260,11 +2261,17 @@ static void stmmac_tx_timer(struct timer_list *t) */ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv) { + u32 tx_channel_count = priv->plat->tx_queues_to_use; + u32 chan; + priv->tx_coal_frames = STMMAC_TX_FRAMES; priv->tx_coal_timer = STMMAC_COAL_TX_TIMER; - timer_setup(&priv->txtimer, stmmac_tx_timer, 0); - priv->txtimer.expires = STMMAC_COAL_TIMER(priv->tx_coal_timer); - add_timer(&priv->txtimer); + + for (chan = 0; chan < tx_channel_count; chan++) { + struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan]; + + timer_setup(&tx_q->txtimer, stmmac_tx_timer, 0); + } } static void stmmac_set_rings_length(struct stmmac_priv *priv) @@ -2592,6 +2599,7 @@ static void stmmac_hw_teardown(struct net_device *dev) static int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan; int ret; stmmac_check_ether_addr(priv); @@ -2688,7 +2696,9 @@ irq_error: if (dev->phydev) phy_stop(dev->phydev); - del_timer_sync(&priv->txtimer); + for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) + del_timer_sync(&priv->tx_queue[chan].txtimer); + stmmac_hw_teardown(dev); init_error: free_dma_desc_resources(priv); @@ -2708,6 +2718,7 @@ dma_desc_error: static int stmmac_release(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + u32 chan; if (priv->eee_enabled) del_timer_sync(&priv->eee_ctrl_timer); @@ -2722,7 +2733,8 @@ static int stmmac_release(struct net_device *dev) stmmac_disable_all_queues(priv); - del_timer_sync(&priv->txtimer); + for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) + del_timer_sync(&priv->tx_queue[chan].txtimer); /* Free the IRQ lines */ free_irq(dev->irq, dev); @@ -2936,14 +2948,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_tso_nfrags += nfrags; /* Manage tx mitigation */ - priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { - mod_timer(&priv->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer)); - } else { - priv->tx_count_frames = 0; + tx_q->tx_count_frames += nfrags + 1; + if (priv->tx_coal_frames <= tx_q->tx_count_frames) { stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; + tx_q->tx_count_frames = 0; + } else { + stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); @@ -3146,14 +3157,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * This approach takes care about the fragments: desc is the first * element in case of no SG. */ - priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { - mod_timer(&priv->txtimer, - STMMAC_COAL_TIMER(priv->tx_coal_timer)); - } else { - priv->tx_count_frames = 0; + tx_q->tx_count_frames += nfrags + 1; + if (priv->tx_coal_frames <= tx_q->tx_count_frames) { stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; + tx_q->tx_count_frames = 0; + } else { + stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); @@ -3199,6 +3209,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); return NETDEV_TX_OK; @@ -3319,6 +3330,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + struct stmmac_channel *ch = &priv->channel[queue]; unsigned int entry = rx_q->cur_rx; int coe = priv->hw->rx_csum; unsigned int next_entry; @@ -3491,7 +3503,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else skb->ip_summed = CHECKSUM_UNNECESSARY; - napi_gro_receive(&rx_q->napi, skb); + napi_gro_receive(&ch->napi, skb); priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; @@ -3514,27 +3526,33 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) * Description : * To look at the incoming frames and clear the tx resources. */ -static int stmmac_poll(struct napi_struct *napi, int budget) +static int stmmac_napi_poll(struct napi_struct *napi, int budget) { - struct stmmac_rx_queue *rx_q = - container_of(napi, struct stmmac_rx_queue, napi); - struct stmmac_priv *priv = rx_q->priv_data; - u32 tx_count = priv->plat->tx_queues_to_use; - u32 chan = rx_q->queue_index; - int work_done = 0; - u32 queue; + struct stmmac_channel *ch = + container_of(napi, struct stmmac_channel, napi); + struct stmmac_priv *priv = ch->priv_data; + int work_done = 0, work_rem = budget; + u32 chan = ch->index; priv->xstats.napi_poll++; - /* check all the queues */ - for (queue = 0; queue < tx_count; queue++) - stmmac_tx_clean(priv, queue); + if (ch->has_tx) { + int done = stmmac_tx_clean(priv, work_rem, chan); - work_done = stmmac_rx(priv, budget, rx_q->queue_index); - if (work_done < budget) { - napi_complete_done(napi, work_done); - stmmac_enable_dma_irq(priv, priv->ioaddr, chan); + work_done += done; + work_rem -= done; + } + + if (ch->has_rx) { + int done = stmmac_rx(priv, work_rem, chan); + + work_done += done; + work_rem -= done; } + + if (work_done < budget && napi_complete_done(napi, work_done)) + stmmac_enable_dma_irq(priv, priv->ioaddr, chan); + return work_done; } @@ -4198,8 +4216,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; + u32 queue, maxq; int ret = 0; - u32 queue; ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, @@ -4322,11 +4340,22 @@ int stmmac_dvr_probe(struct device *device, "Enable RX Mitigation via HW Watchdog Timer\n"); } - for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + /* Setup channels NAPI */ + maxq = max(priv->plat->rx_queues_to_use, priv->plat->tx_queues_to_use); - netif_napi_add(ndev, &rx_q->napi, stmmac_poll, - (8 * priv->plat->rx_queues_to_use)); + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; + + ch->priv_data = priv; + ch->index = queue; + + if (queue < priv->plat->rx_queues_to_use) + ch->has_rx = true; + if (queue < priv->plat->tx_queues_to_use) + ch->has_tx = true; + + netif_napi_add(ndev, &ch->napi, stmmac_napi_poll, + NAPI_POLL_WEIGHT); } mutex_init(&priv->lock); @@ -4372,10 +4401,10 @@ error_netdev_register: priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); error_mdio_register: - for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; + for (queue = 0; queue < maxq; queue++) { + struct stmmac_channel *ch = &priv->channel[queue]; - netif_napi_del(&rx_q->napi); + netif_napi_del(&ch->napi); } error_hw_init: destroy_workqueue(priv->wq); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c43e9a01b892..7ddfc65586b0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -30,6 +30,7 @@ #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 +#define STMMAC_CH_MAX 8 #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 -- 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 60489f085574157c343fc62a32f997fe7346a659 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:10 +0200 Subject: spi: spi-mem: Add missing description for data.nbytes field Add a description for spi_mem_op.data.nbytes to the kerneldoc header. Fixes: c36ff266dc82 ("spi: Extend the core to ease integration of SPI memory controllers") Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 62722fb7472d..0cfbb1ad8d96 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -79,6 +79,8 @@ enum spi_mem_data_dir { * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes * @data.buswidth: number of IO lanes used to send/receive the data * @data.dir: direction of the transfer + * @data.nbytes: number of data bytes to send/receive. Can be zero if the + * operation does not involve transferring data * @data.buf.in: input buffer * @data.buf.out: output buffer */ -- cgit v1.2.3-71-gd317 From c949a8e8b43f2c75567269bcc9a50d704ae3c420 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:11 +0200 Subject: spi: spi-mem: Move the DMA-able constraint doc to the kerneldoc header We'd better have that documented in the kerneldoc header, so that it's exposed to the doc generated by Sphinx. Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 0cfbb1ad8d96..7195fbc234aa 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -81,8 +81,8 @@ enum spi_mem_data_dir { * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data - * @data.buf.in: input buffer - * @data.buf.out: output buffer + * @data.buf.in: input buffer (must be DMA-able) + * @data.buf.out: output buffer (must be DMA-able) */ struct spi_mem_op { struct { @@ -105,7 +105,6 @@ struct spi_mem_op { u8 buswidth; enum spi_mem_data_dir dir; unsigned int nbytes; - /* buf.{in,out} must be DMA-able. */ union { void *in; const void *out; -- 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 From ac3d9dd034e565df2c034ab2ca71f0a9f69153c1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 15:27:38 -0700 Subject: netpoll: make ndo_poll_controller() optional As diagnosed by Song Liu, ndo_poll_controller() can be very dangerous on loaded hosts, since the cpu calling ndo_poll_controller() might steal all NAPI contexts (for all RX/TX queues of the NIC). This capture can last for unlimited amount of time, since one cpu is generally not able to drain all the queues under load. It seems that all networking drivers that do use NAPI for their TX completions, should not provide a ndo_poll_controller(). NAPI drivers have netpoll support already handled in core networking stack, since netpoll_poll_dev() uses poll_napi(dev) to iterate through registered NAPI contexts for a device. This patch allows netpoll_poll_dev() to process NAPI contexts even for drivers not providing ndo_poll_controller(), allowing for following patches in NAPI drivers. Also we export netpoll_poll_dev() so that it can be called by bonding/team drivers in following patches. Reported-by: Song Liu Signed-off-by: Eric Dumazet Tested-by: Song Liu Signed-off-by: David S. Miller --- include/linux/netpoll.h | 5 +++-- net/core/netpoll.c | 19 +++++++------------ 2 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 67662d01130a..3ef82d3a78db 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -49,8 +49,9 @@ struct netpoll_info { }; #ifdef CONFIG_NETPOLL -extern void netpoll_poll_disable(struct net_device *dev); -extern void netpoll_poll_enable(struct net_device *dev); +void netpoll_poll_dev(struct net_device *dev); +void netpoll_poll_disable(struct net_device *dev); +void netpoll_poll_enable(struct net_device *dev); #else static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 57557a6a950c..3219a2932463 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -187,16 +187,16 @@ static void poll_napi(struct net_device *dev) } } -static void netpoll_poll_dev(struct net_device *dev) +void netpoll_poll_dev(struct net_device *dev) { - const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + const struct net_device_ops *ops; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity * while changing device state */ - if (down_trylock(&ni->dev_lock)) + if (!ni || down_trylock(&ni->dev_lock)) return; if (!netif_running(dev)) { @@ -205,13 +205,8 @@ static void netpoll_poll_dev(struct net_device *dev) } ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) { - up(&ni->dev_lock); - return; - } - - /* Process pending work on NIC */ - ops->ndo_poll_controller(dev); + if (ops->ndo_poll_controller) + ops->ndo_poll_controller(dev); poll_napi(dev); @@ -219,6 +214,7 @@ static void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } +EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { @@ -613,8 +609,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) strlcpy(np->dev_name, ndev->name, IFNAMSIZ); INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); - if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || - !ndev->netdev_ops->ndo_poll_controller) { + if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", np->dev_name); err = -ENOTSUPP; -- cgit v1.2.3-71-gd317