From 77ef8f5177599efd0cedeb52c1950c1bd73fa5e3 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Mon, 25 Jan 2016 15:05:34 -0500 Subject: [PATCH 001/196] tile kgdb: fix bug in copy to gdb regs, and optimize memset David Binderman pointed out that we were doing a full memset() of the gdb register buffer and then doing a memcpy() to it that was almost as big. This commit optimizes that by only doing a memset() of the registers that are intended to be zero. While making this change I noticed that we were not copying the link register (LR, number 55) due to a fencepost error in commit f419e6f63c5a ("arch: tile: kernel: kgdb.c: Use memcpy() instead of pointer copy one by one"), and I've corrected that as well. Reported-by: David Binderman Signed-off-by: Chris Metcalf --- arch/tile/kernel/kgdb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c index a506c2c28943..6ad99925900e 100644 --- a/arch/tile/kernel/kgdb.c +++ b/arch/tile/kernel/kgdb.c @@ -126,15 +126,15 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) { struct pt_regs *thread_regs; + const int NGPRS = TREG_LAST_GPR + 1; if (task == NULL) return; - /* Initialize to zero. */ - memset(gdb_regs, 0, NUMREGBYTES); - thread_regs = task_pt_regs(task); - memcpy(gdb_regs, thread_regs, TREG_LAST_GPR * sizeof(unsigned long)); + memcpy(gdb_regs, thread_regs, NGPRS * sizeof(unsigned long)); + memset(&gdb_regs[NGPRS], 0, + (TILEGX_PC_REGNUM - NGPRS) * sizeof(unsigned long)); gdb_regs[TILEGX_PC_REGNUM] = thread_regs->pc; gdb_regs[TILEGX_FAULTNUM_REGNUM] = thread_regs->faultnum; } From b9a279f601011efd6f173b73001b0989f8c9c444 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Wed, 2 Mar 2016 15:32:27 -0500 Subject: [PATCH 002/196] MAINTAINERS: update arch/tile maintainer email domain Mellanox has acquired EZchip, so my email address as arch/tile maintainer changes to cmetcalf@mellanox.com. http://www.mellanox.com/page/press_release_item?id=1681 Signed-off-by: Chris Metcalf --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4978dc19a4d2..c6bd10d0aaf6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10940,7 +10940,7 @@ F: include/uapi/linux/tipc*.h F: net/tipc/ TILE ARCHITECTURE -M: Chris Metcalf +M: Chris Metcalf W: http://www.ezchip.com/scm/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile.git S: Supported From 8c34d8d9bec0b2a38e8beab46a643e9b323c8310 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Fri, 4 Mar 2016 11:12:28 -0500 Subject: [PATCH 003/196] MAINTAINERS: update web link for tile architecture We have integrated the tile open-source overview information into the Mellanox web server, so update the tile architecture pointer. Signed-off-by: Chris Metcalf --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index c6bd10d0aaf6..0337c58bd6f3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10941,7 +10941,7 @@ F: net/tipc/ TILE ARCHITECTURE M: Chris Metcalf -W: http://www.ezchip.com/scm/ +W: http://www.mellanox.com/repository/solutions/tile-scm/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile.git S: Supported F: arch/tile/ From 35b90a2939a563df4b1f57f18dd925d6aa7cb38a Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Fri, 4 Mar 2016 11:22:24 -0800 Subject: [PATCH 004/196] tile: Fix misspellings in comments. Signed-off-by: Adam Buchbinder Signed-off-by: Chris Metcalf [plus "uninitalization"] --- arch/tile/include/hv/drv_mpipe_intf.h | 26 +++++++++++++------------- arch/tile/kernel/kgdb.c | 8 ++++---- arch/tile/kernel/pci_gx.c | 2 +- 3 files changed, 18 insertions(+), 18 deletions(-) diff --git a/arch/tile/include/hv/drv_mpipe_intf.h b/arch/tile/include/hv/drv_mpipe_intf.h index c97e416dd963..ff7f50f970a5 100644 --- a/arch/tile/include/hv/drv_mpipe_intf.h +++ b/arch/tile/include/hv/drv_mpipe_intf.h @@ -211,7 +211,7 @@ _gxio_mpipe_link_mac_t; * request shared data permission on the same link. * * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, - * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. */ #define GXIO_MPIPE_LINK_DATA 0x00000001UL @@ -219,7 +219,7 @@ _gxio_mpipe_link_mac_t; /** Do not request data permission on the specified link. * * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, - * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. */ #define GXIO_MPIPE_LINK_NO_DATA 0x00000002UL @@ -230,7 +230,7 @@ _gxio_mpipe_link_mac_t; * data permission on it, this open will fail. * * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, - * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. */ #define GXIO_MPIPE_LINK_EXCL_DATA 0x00000004UL @@ -241,7 +241,7 @@ _gxio_mpipe_link_mac_t; * permission on the same link. * * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, - * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. */ #define GXIO_MPIPE_LINK_STATS 0x00000008UL @@ -249,7 +249,7 @@ _gxio_mpipe_link_mac_t; /** Do not request stats permission on the specified link. * * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, - * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. */ #define GXIO_MPIPE_LINK_NO_STATS 0x00000010UL @@ -267,7 +267,7 @@ _gxio_mpipe_link_mac_t; * reset by other statistics programs. * * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, - * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. */ #define GXIO_MPIPE_LINK_EXCL_STATS 0x00000020UL @@ -278,7 +278,7 @@ _gxio_mpipe_link_mac_t; * permission on the same link. * * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, - * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. */ #define GXIO_MPIPE_LINK_CTL 0x00000040UL @@ -286,7 +286,7 @@ _gxio_mpipe_link_mac_t; /** Do not request control permission on the specified link. * * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, - * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. */ #define GXIO_MPIPE_LINK_NO_CTL 0x00000080UL @@ -301,7 +301,7 @@ _gxio_mpipe_link_mac_t; * it prevents programs like mpipe-link from configuring the link. * * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, - * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. */ #define GXIO_MPIPE_LINK_EXCL_CTL 0x00000100UL @@ -311,7 +311,7 @@ _gxio_mpipe_link_mac_t; * change the desired state of the link when it is closed or the process * exits. No more than one of ::GXIO_MPIPE_LINK_AUTO_UP, * ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or - * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open() + * ::GXIO_MPIPE_LINK_AUTO_NONE may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. */ #define GXIO_MPIPE_LINK_AUTO_UP 0x00000200UL @@ -322,7 +322,7 @@ _gxio_mpipe_link_mac_t; * open, set the desired state of the link to down. No more than one of * ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN, * ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be - * specifed in a gxio_mpipe_link_open() call. If none are specified, + * specified in a gxio_mpipe_link_open() call. If none are specified, * ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. */ #define GXIO_MPIPE_LINK_AUTO_UPDOWN 0x00000400UL @@ -332,7 +332,7 @@ _gxio_mpipe_link_mac_t; * process has the link open, set the desired state of the link to down. * No more than one of ::GXIO_MPIPE_LINK_AUTO_UP, * ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or - * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open() + * ::GXIO_MPIPE_LINK_AUTO_NONE may be specified in a gxio_mpipe_link_open() * call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. */ #define GXIO_MPIPE_LINK_AUTO_DOWN 0x00000800UL @@ -342,7 +342,7 @@ _gxio_mpipe_link_mac_t; * closed or the process exits. No more than one of * ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN, * ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be - * specifed in a gxio_mpipe_link_open() call. If none are specified, + * specified in a gxio_mpipe_link_open() call. If none are specified, * ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. */ #define GXIO_MPIPE_LINK_AUTO_NONE 0x00001000UL diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c index 6ad99925900e..9247d6b562f4 100644 --- a/arch/tile/kernel/kgdb.c +++ b/arch/tile/kernel/kgdb.c @@ -433,9 +433,9 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, struct kgdb_arch arch_kgdb_ops; /* - * kgdb_arch_init - Perform any architecture specific initalization. + * kgdb_arch_init - Perform any architecture specific initialization. * - * This function will handle the initalization of any architecture + * This function will handle the initialization of any architecture * specific callbacks. */ int kgdb_arch_init(void) @@ -447,9 +447,9 @@ int kgdb_arch_init(void) } /* - * kgdb_arch_exit - Perform any architecture specific uninitalization. + * kgdb_arch_exit - Perform any architecture specific uninitialization. * - * This function will handle the uninitalization of any architecture + * This function will handle the uninitialization of any architecture * specific callbacks, for dynamic registration and unregistration. */ void kgdb_arch_exit(void) diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index 4c017d0d2de8..aa2b44cd8fd3 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -1326,7 +1326,7 @@ invalid_device: /* - * See tile_cfg_read() for relevent comments. + * See tile_cfg_read() for relevant comments. * Note that "val" is the value to write, not a pointer to that value. */ static int tile_cfg_write(struct pci_bus *bus, unsigned int devfn, int offset, From a987884295891f18fddf9c76d7d47c9486701560 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Fri, 11 Mar 2016 11:52:37 +0100 Subject: [PATCH 005/196] s390/cpum_cf: Fix missing cpu hotplug notifier transition The cpumf_pmu_notfier() hotplug callback lacks handling of the CPU_DOWN_FAILED case. That means, if CPU_DOWN_PREPARE failes, the PMC of the CPU is not setup again. Add handling for CPU_DOWN_FAILED transition to setup the PMC of the CPU. Signed-off-by: Anna-Maria Gleixner Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_cpum_cf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 58bf4572d457..62f066b5259e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -670,6 +670,7 @@ static int cpumf_pmu_notifier(struct notifier_block *self, unsigned long action, switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: + case CPU_DOWN_FAILED: flags = PMC_INIT; smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1); break; From 1e3c1dd15dd30232458e35128fd062b788b1c9e4 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Fri, 11 Mar 2016 11:52:38 +0100 Subject: [PATCH 006/196] s390/cpum_sf: Fix cpu hotplug notifier transitions The cpumf_pmu_notfier() hotplug callback lacks handling of the CPU_DOWN_FAILED case. That means, if CPU_DOWN_PREPARE failes, the PMC of the CPU is not setup again. Furthermore the CPU_ONLINE_FROZEN case will never be processed because of masking the switch expression with CPU_TASKS_FROZEN. Add handling for CPU_DOWN_FAILED transition to setup the PMC of the CPU. Remove CPU_ONLINE_FROZEN case. Signed-off-by: Anna-Maria Gleixner Acked-by: Hendrik Brueckner Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_cpum_sf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 1a43474df541..eaab9a7cb3be 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1521,7 +1521,7 @@ static int cpumf_pmu_notifier(struct notifier_block *self, switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED: flags = PMC_INIT; smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1); break; From 59a9ed5f87b6e396aed1f6bf7d6496f7ba66c37a Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 23 Feb 2016 10:15:27 +0100 Subject: [PATCH 007/196] s390/dasd: reorder lcu and device lock Reorder lcu and device lock to get rid of the error-prone trylock mechanism. The locking order is lcu lock -> device lock. This protects against changes to the lcu device lists and enables us to iterate over the devices, take the cdev lock and make changes to the device structures. The complicated part is the summary unit check handler that gets an interrupt on one device of the lcu that leads to structural changes of the whole lcu itself. This work needs to be done even if devices on the lcu disappear. So a device independent worker is used. The old approach tried to update some lcu structures and set up the lcu worker in the interrupt context with the device lock held. But this forced the lock order "cdev lock -> lcu lock" that made it hard to have the lcu lock held and iterate over all devices and change them. The new approach is to schedule a device specific worker that gets out of the interrupt context and rid of the device lock for summary unit checks. This worker is able to take the lcu lock and schedule the lcu worker that updates all devices. The time between interrupt and worker execution is no problem because the devices in the lcu reject all I/O in this time with an appropriate error. The dasd driver can deal with this situation and re-drive the I/O later on. Signed-off-by: Stefan Haberland Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd_alias.c | 226 ++++++++------------------------ drivers/s390/block/dasd_eckd.c | 38 ++++-- drivers/s390/block/dasd_eckd.h | 3 +- drivers/s390/block/dasd_int.h | 2 + 4 files changed, 86 insertions(+), 183 deletions(-) diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 17ad5749e91d..1e560188dd13 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -317,17 +317,17 @@ static int _add_device_to_lcu(struct alias_lcu *lcu, struct alias_pav_group *group; struct dasd_uid uid; + spin_lock(get_ccwdev_lock(device->cdev)); private->uid.type = lcu->uac->unit[private->uid.real_unit_addr].ua_type; private->uid.base_unit_addr = lcu->uac->unit[private->uid.real_unit_addr].base_ua; uid = private->uid; - + spin_unlock(get_ccwdev_lock(device->cdev)); /* if we have no PAV anyway, we don't need to bother with PAV groups */ if (lcu->pav == NO_PAV) { list_move(&device->alias_list, &lcu->active_devices); return 0; } - group = _find_group(lcu, &uid); if (!group) { group = kzalloc(sizeof(*group), GFP_ATOMIC); @@ -397,130 +397,6 @@ suborder_not_supported(struct dasd_ccw_req *cqr) return 0; } -/* - * This function tries to lock all devices on an lcu via trylock - * return NULL on success otherwise return first failed device - */ -static struct dasd_device *_trylock_all_devices_on_lcu(struct alias_lcu *lcu, - struct dasd_device *pos) - -{ - struct alias_pav_group *pavgroup; - struct dasd_device *device; - - list_for_each_entry(device, &lcu->active_devices, alias_list) { - if (device == pos) - continue; - if (!spin_trylock(get_ccwdev_lock(device->cdev))) - return device; - } - list_for_each_entry(device, &lcu->inactive_devices, alias_list) { - if (device == pos) - continue; - if (!spin_trylock(get_ccwdev_lock(device->cdev))) - return device; - } - list_for_each_entry(pavgroup, &lcu->grouplist, group) { - list_for_each_entry(device, &pavgroup->baselist, alias_list) { - if (device == pos) - continue; - if (!spin_trylock(get_ccwdev_lock(device->cdev))) - return device; - } - list_for_each_entry(device, &pavgroup->aliaslist, alias_list) { - if (device == pos) - continue; - if (!spin_trylock(get_ccwdev_lock(device->cdev))) - return device; - } - } - return NULL; -} - -/* - * unlock all devices except the one that is specified as pos - * stop if enddev is specified and reached - */ -static void _unlock_all_devices_on_lcu(struct alias_lcu *lcu, - struct dasd_device *pos, - struct dasd_device *enddev) - -{ - struct alias_pav_group *pavgroup; - struct dasd_device *device; - - list_for_each_entry(device, &lcu->active_devices, alias_list) { - if (device == pos) - continue; - if (device == enddev) - return; - spin_unlock(get_ccwdev_lock(device->cdev)); - } - list_for_each_entry(device, &lcu->inactive_devices, alias_list) { - if (device == pos) - continue; - if (device == enddev) - return; - spin_unlock(get_ccwdev_lock(device->cdev)); - } - list_for_each_entry(pavgroup, &lcu->grouplist, group) { - list_for_each_entry(device, &pavgroup->baselist, alias_list) { - if (device == pos) - continue; - if (device == enddev) - return; - spin_unlock(get_ccwdev_lock(device->cdev)); - } - list_for_each_entry(device, &pavgroup->aliaslist, alias_list) { - if (device == pos) - continue; - if (device == enddev) - return; - spin_unlock(get_ccwdev_lock(device->cdev)); - } - } -} - -/* - * this function is needed because the locking order - * device lock -> lcu lock - * needs to be assured when iterating over devices in an LCU - * - * if a device is specified in pos then the device lock is already hold - */ -static void _trylock_and_lock_lcu_irqsave(struct alias_lcu *lcu, - struct dasd_device *pos, - unsigned long *flags) -{ - struct dasd_device *failed; - - do { - spin_lock_irqsave(&lcu->lock, *flags); - failed = _trylock_all_devices_on_lcu(lcu, pos); - if (failed) { - _unlock_all_devices_on_lcu(lcu, pos, failed); - spin_unlock_irqrestore(&lcu->lock, *flags); - cpu_relax(); - } - } while (failed); -} - -static void _trylock_and_lock_lcu(struct alias_lcu *lcu, - struct dasd_device *pos) -{ - struct dasd_device *failed; - - do { - spin_lock(&lcu->lock); - failed = _trylock_all_devices_on_lcu(lcu, pos); - if (failed) { - _unlock_all_devices_on_lcu(lcu, pos, failed); - spin_unlock(&lcu->lock); - cpu_relax(); - } - } while (failed); -} - static int read_unit_address_configuration(struct dasd_device *device, struct alias_lcu *lcu) { @@ -615,7 +491,7 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu) if (rc) return rc; - _trylock_and_lock_lcu_irqsave(lcu, NULL, &flags); + spin_lock_irqsave(&lcu->lock, flags); lcu->pav = NO_PAV; for (i = 0; i < MAX_DEVICES_PER_LCU; ++i) { switch (lcu->uac->unit[i].ua_type) { @@ -634,7 +510,6 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu) alias_list) { _add_device_to_lcu(lcu, device, refdev); } - _unlock_all_devices_on_lcu(lcu, NULL, NULL); spin_unlock_irqrestore(&lcu->lock, flags); return 0; } @@ -722,8 +597,7 @@ int dasd_alias_add_device(struct dasd_device *device) lcu = private->lcu; rc = 0; - spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags); - spin_lock(&lcu->lock); + spin_lock_irqsave(&lcu->lock, flags); if (!(lcu->flags & UPDATE_PENDING)) { rc = _add_device_to_lcu(lcu, device, device); if (rc) @@ -733,8 +607,7 @@ int dasd_alias_add_device(struct dasd_device *device) list_move(&device->alias_list, &lcu->active_devices); _schedule_lcu_update(lcu, device); } - spin_unlock(&lcu->lock); - spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); + spin_unlock_irqrestore(&lcu->lock, flags); return rc; } @@ -933,15 +806,27 @@ static void _stop_all_devices_on_lcu(struct alias_lcu *lcu) struct alias_pav_group *pavgroup; struct dasd_device *device; - list_for_each_entry(device, &lcu->active_devices, alias_list) + list_for_each_entry(device, &lcu->active_devices, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_set_stop_bits(device, DASD_STOPPED_SU); - list_for_each_entry(device, &lcu->inactive_devices, alias_list) + spin_unlock(get_ccwdev_lock(device->cdev)); + } + list_for_each_entry(device, &lcu->inactive_devices, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_set_stop_bits(device, DASD_STOPPED_SU); + spin_unlock(get_ccwdev_lock(device->cdev)); + } list_for_each_entry(pavgroup, &lcu->grouplist, group) { - list_for_each_entry(device, &pavgroup->baselist, alias_list) + list_for_each_entry(device, &pavgroup->baselist, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_set_stop_bits(device, DASD_STOPPED_SU); - list_for_each_entry(device, &pavgroup->aliaslist, alias_list) + spin_unlock(get_ccwdev_lock(device->cdev)); + } + list_for_each_entry(device, &pavgroup->aliaslist, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_set_stop_bits(device, DASD_STOPPED_SU); + spin_unlock(get_ccwdev_lock(device->cdev)); + } } } @@ -950,15 +835,27 @@ static void _unstop_all_devices_on_lcu(struct alias_lcu *lcu) struct alias_pav_group *pavgroup; struct dasd_device *device; - list_for_each_entry(device, &lcu->active_devices, alias_list) + list_for_each_entry(device, &lcu->active_devices, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_remove_stop_bits(device, DASD_STOPPED_SU); - list_for_each_entry(device, &lcu->inactive_devices, alias_list) + spin_unlock(get_ccwdev_lock(device->cdev)); + } + list_for_each_entry(device, &lcu->inactive_devices, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_remove_stop_bits(device, DASD_STOPPED_SU); + spin_unlock(get_ccwdev_lock(device->cdev)); + } list_for_each_entry(pavgroup, &lcu->grouplist, group) { - list_for_each_entry(device, &pavgroup->baselist, alias_list) + list_for_each_entry(device, &pavgroup->baselist, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_remove_stop_bits(device, DASD_STOPPED_SU); - list_for_each_entry(device, &pavgroup->aliaslist, alias_list) + spin_unlock(get_ccwdev_lock(device->cdev)); + } + list_for_each_entry(device, &pavgroup->aliaslist, alias_list) { + spin_lock(get_ccwdev_lock(device->cdev)); dasd_device_remove_stop_bits(device, DASD_STOPPED_SU); + spin_unlock(get_ccwdev_lock(device->cdev)); + } } } @@ -984,48 +881,32 @@ static void summary_unit_check_handling_work(struct work_struct *work) spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); reset_summary_unit_check(lcu, device, suc_data->reason); - _trylock_and_lock_lcu_irqsave(lcu, NULL, &flags); + spin_lock_irqsave(&lcu->lock, flags); _unstop_all_devices_on_lcu(lcu); _restart_all_base_devices_on_lcu(lcu); /* 3. read new alias configuration */ _schedule_lcu_update(lcu, device); lcu->suc_data.device = NULL; dasd_put_device(device); - _unlock_all_devices_on_lcu(lcu, NULL, NULL); spin_unlock_irqrestore(&lcu->lock, flags); } -/* - * note: this will be called from int handler context (cdev locked) - */ -void dasd_alias_handle_summary_unit_check(struct dasd_device *device, - struct irb *irb) +void dasd_alias_handle_summary_unit_check(struct work_struct *work) { + struct dasd_device *device = container_of(work, struct dasd_device, + suc_work); struct dasd_eckd_private *private = device->private; struct alias_lcu *lcu; - char reason; - char *sense; - - sense = dasd_get_sense(irb); - if (sense) { - reason = sense[8]; - DBF_DEV_EVENT(DBF_NOTICE, device, "%s %x", - "eckd handle summary unit check: reason", reason); - } else { - DBF_DEV_EVENT(DBF_WARNING, device, "%s", - "eckd handle summary unit check:" - " no reason code available"); - return; - } + unsigned long flags; lcu = private->lcu; if (!lcu) { DBF_DEV_EVENT(DBF_WARNING, device, "%s", "device not ready to handle summary" " unit check (no lcu structure)"); - return; + goto out; } - _trylock_and_lock_lcu(lcu, device); + spin_lock_irqsave(&lcu->lock, flags); /* If this device is about to be removed just return and wait for * the next interrupt on a different device */ @@ -1033,27 +914,26 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device, DBF_DEV_EVENT(DBF_WARNING, device, "%s", "device is in offline processing," " don't do summary unit check handling"); - _unlock_all_devices_on_lcu(lcu, device, NULL); - spin_unlock(&lcu->lock); - return; + goto out_unlock; } if (lcu->suc_data.device) { /* already scheduled or running */ DBF_DEV_EVENT(DBF_WARNING, device, "%s", "previous instance of summary unit check worker" " still pending"); - _unlock_all_devices_on_lcu(lcu, device, NULL); - spin_unlock(&lcu->lock); - return ; + goto out_unlock; } _stop_all_devices_on_lcu(lcu); /* prepare for lcu_update */ - private->lcu->flags |= NEED_UAC_UPDATE | UPDATE_PENDING; - lcu->suc_data.reason = reason; + lcu->flags |= NEED_UAC_UPDATE | UPDATE_PENDING; + lcu->suc_data.reason = private->suc_reason; lcu->suc_data.device = device; dasd_get_device(device); - _unlock_all_devices_on_lcu(lcu, device, NULL); - spin_unlock(&lcu->lock); if (!schedule_work(&lcu->suc_data.worker)) dasd_put_device(device); +out_unlock: + spin_unlock_irqrestore(&lcu->lock, flags); +out: + clear_bit(DASD_FLAG_SUC, &device->flags); + dasd_put_device(device); }; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 75c032dcf173..c1b4ae55e129 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1682,6 +1682,8 @@ dasd_eckd_check_characteristics(struct dasd_device *device) /* setup work queue for validate server*/ INIT_WORK(&device->kick_validate, dasd_eckd_do_validate_server); + /* setup work queue for summary unit check */ + INIT_WORK(&device->suc_work, dasd_alias_handle_summary_unit_check); if (!ccw_device_is_pathgroup(device->cdev)) { dev_warn(&device->cdev->dev, @@ -2549,14 +2551,6 @@ static void dasd_eckd_check_for_device_change(struct dasd_device *device, device->state == DASD_STATE_ONLINE && !test_bit(DASD_FLAG_OFFLINE, &device->flags) && !test_bit(DASD_FLAG_SUSPENDED, &device->flags)) { - /* - * the state change could be caused by an alias - * reassignment remove device from alias handling - * to prevent new requests from being scheduled on - * the wrong alias device - */ - dasd_alias_remove_device(device); - /* schedule worker to reload device */ dasd_reload_device(device); } @@ -2571,7 +2565,27 @@ static void dasd_eckd_check_for_device_change(struct dasd_device *device, /* summary unit check */ if ((sense[27] & DASD_SENSE_BIT_0) && (sense[7] == 0x0D) && (scsw_dstat(&irb->scsw) & DEV_STAT_UNIT_CHECK)) { - dasd_alias_handle_summary_unit_check(device, irb); + if (test_and_set_bit(DASD_FLAG_SUC, &device->flags)) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "eckd suc: device already notified"); + return; + } + sense = dasd_get_sense(irb); + if (!sense) { + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "eckd suc: no reason code available"); + clear_bit(DASD_FLAG_SUC, &device->flags); + return; + + } + private->suc_reason = sense[8]; + DBF_DEV_EVENT(DBF_NOTICE, device, "%s %x", + "eckd handle summary unit check: reason", + private->suc_reason); + dasd_get_device(device); + if (!schedule_work(&device->suc_work)) + dasd_put_device(device); + return; } @@ -4495,6 +4509,12 @@ static int dasd_eckd_reload_device(struct dasd_device *device) struct dasd_uid uid; unsigned long flags; + /* + * remove device from alias handling to prevent new requests + * from being scheduled on the wrong alias device + */ + dasd_alias_remove_device(device); + spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags); old_base = private->uid.base_unit_addr; spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h index f8f91ee652d3..6d9a6d3517cd 100644 --- a/drivers/s390/block/dasd_eckd.h +++ b/drivers/s390/block/dasd_eckd.h @@ -525,6 +525,7 @@ struct dasd_eckd_private { int count; u32 fcx_max_data; + char suc_reason; }; @@ -534,7 +535,7 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *); int dasd_alias_add_device(struct dasd_device *); int dasd_alias_remove_device(struct dasd_device *); struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *); -void dasd_alias_handle_summary_unit_check(struct dasd_device *, struct irb *); +void dasd_alias_handle_summary_unit_check(struct work_struct *); void dasd_eckd_reset_ccw_to_base_io(struct dasd_ccw_req *); void dasd_alias_lcu_setup_complete(struct dasd_device *); void dasd_alias_wait_for_lcu_setup(struct dasd_device *); diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 8de29be32a56..0f0add932e7a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -470,6 +470,7 @@ struct dasd_device { struct work_struct restore_device; struct work_struct reload_device; struct work_struct kick_validate; + struct work_struct suc_work; struct timer_list timer; debug_info_t *debug_area; @@ -542,6 +543,7 @@ struct dasd_attention_data { #define DASD_FLAG_SAFE_OFFLINE_RUNNING 11 /* safe offline running */ #define DASD_FLAG_ABORTALL 12 /* Abort all noretry requests */ #define DASD_FLAG_PATH_VERIFY 13 /* Path verification worker running */ +#define DASD_FLAG_SUC 14 /* unhandled summary unit check */ #define DASD_SLEEPON_START_TAG ((void *) 1) #define DASD_SLEEPON_END_TAG ((void *) 2) From df9ceff906abf5edc284c11ac899b3b3f32b4dd3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Mar 2016 12:45:33 +0100 Subject: [PATCH 008/196] s390: disable postinit-readonly for now This is a temporary fix to let lkdtm run again on s390, though it'll still fail the ro_after_init tests. Until rodata and ro_after_init sections can be split on s390, disable special handling of ro_after_init. Signed-off-by: Kees Cook Reported-by: Christian Borntraeger Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/cache.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h index 4d7ccac5fd1d..22da3b34c655 100644 --- a/arch/s390/include/asm/cache.h +++ b/arch/s390/include/asm/cache.h @@ -15,4 +15,7 @@ #define __read_mostly __attribute__((__section__(".data..read_mostly"))) +/* Read-only memory is marked before mark_rodata_ro() is called. */ +#define __ro_after_init __read_mostly + #endif From 91d37211769510ae0b4747045d8f81d3b9dd4278 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 17 Mar 2016 12:47:12 +0100 Subject: [PATCH 009/196] s390: add DEBUG_RODATA support git commit d2aa1acad22f ("mm/init: Add 'rodata=off' boot cmdline parameter to disable read-only kernel mappings") adds a bogus warning to the console which states that s390 does not support kernel memory protection. This however is not true. We do support that since a couple of years however in a different way than the author of the above named patch expected. To get rid of the misleading message implement the mark_rodata_ro function and emit a message which states the amount of memory which was write protected already earlier. This is the same what parisc currently does. We currently do not support the kernel parameter "rodata=off" which would allow to write to the rodata section again. However since we have this feature since years without any problems there is no reason to add support for this. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/Kconfig | 3 +++ arch/s390/mm/init.c | 10 +++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 7e3e8a8338d6..f8dea162bd32 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -59,6 +59,9 @@ config PCI_QUIRKS config ARCH_SUPPORTS_UPROBES def_bool y +config DEBUG_RODATA + def_bool y + config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 73e290337092..c7b0451397d6 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -108,6 +108,13 @@ void __init paging_init(void) free_area_init_nodes(max_zone_pfns); } +void mark_rodata_ro(void) +{ + /* Text and rodata are already protected. Nothing to do here. */ + pr_info("Write protecting the kernel read-only data: %luk\n", + ((unsigned long)&_eshared - (unsigned long)&_stext) >> 10); +} + void __init mem_init(void) { if (MACHINE_HAS_TLB_LC) @@ -126,9 +133,6 @@ void __init mem_init(void) setup_zero_pages(); /* Setup zeroed pages. */ mem_init_print_info(NULL); - printk("Write protected kernel read-only data: %#lx - %#lx\n", - (unsigned long)&_stext, - PFN_ALIGN((unsigned long)&_eshared) - 1); } void free_initmem(void) From fc897c95e91451271cd707ee0f71022b9b201ce9 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 17 Mar 2016 15:00:04 +0100 Subject: [PATCH 010/196] s390/mm: handle PTE-mapped tail pages in fast gup With the THP refcounting rework it is possible to see THP compound tail pages mapped with PTEs during a THP split. This needs to be considered when using page_cache_get_speculative(), which will always fail on tail pages because ->_count is always zero. commit 7aef4172 "mm: handle PTE-mapped tail pages in gerneric fast gup implementaiton" fixed it for the generic fast gup code by using compound_head(page) instead of page, but not for s390. This patch is a 1:1 adaption of commit 7aef4172 for the s390 fast gup code. Without this fix, gup will fall back to the slow path or fail in the unlikely scenario that we hit a THP under splitting in-between the page table split and the compound page split. Cc: stable@vger.kernel.org # v4.5 Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/mm/gup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 13dab0c1645c..3776aca22082 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -20,9 +20,9 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct page *head, *page; unsigned long mask; pte_t *ptep, pte; - struct page *page; mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL; @@ -37,12 +37,14 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) return 0; if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_page(page); + put_page(head); return 0; } + VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; (*nr)++; From eccf432f6542d9895d6c50edb5634c6147918ed2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Feb 2016 15:31:45 +0100 Subject: [PATCH 011/196] ide: icside: remove incorrect initconst annotation The icside_probe function can be called for hotplugged devices, so its reference to the __initconst icside_v6_port_info variable may be invalid, as Kbuild points out: WARNING: drivers/ide/icside.o(.text+0x338): Section mismatch in reference from the function icside_probe() to the (unknown reference) .init.rodata:(unknown) Interestingly, this problem only shows up with clang but not with gcc, which optimizes out the __initconst variable. This removes the incorrect annotation. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/ide/icside.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ide/icside.c b/drivers/ide/icside.c index 9f0a48e39b8a..80e933b296f6 100644 --- a/drivers/ide/icside.c +++ b/drivers/ide/icside.c @@ -451,7 +451,7 @@ err_free: return ret; } -static const struct ide_port_info icside_v6_port_info __initconst = { +static const struct ide_port_info icside_v6_port_info = { .init_dma = icside_dma_off_init, .port_ops = &icside_v6_no_dma_port_ops, .host_flags = IDE_HFLAG_SERIALIZE | IDE_HFLAG_MMIO, From 0d7ef45cdeebcc95d581703f45f6de7b2ee89b8d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 2 Mar 2016 23:33:32 +0100 Subject: [PATCH 012/196] ide: palm_bk3710: test clock rate to avoid division by 0 The clk API may return 0 on clk_get_rate, so we should check the result before using it as a divisor. Signed-off-by: Wolfram Sang Signed-off-by: David S. Miller --- drivers/ide/palm_bk3710.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/ide/palm_bk3710.c b/drivers/ide/palm_bk3710.c index 8012e43bf8f6..46427ea01753 100644 --- a/drivers/ide/palm_bk3710.c +++ b/drivers/ide/palm_bk3710.c @@ -325,6 +325,8 @@ static int __init palm_bk3710_probe(struct platform_device *pdev) clk_enable(clk); rate = clk_get_rate(clk); + if (!rate) + return -EINVAL; /* NOTE: round *down* to meet minimum timings; we count in clocks */ ideclk_period = 1000000000UL / rate; From 08f80073039aba911fbf3f316a00a4ac5d03052f Mon Sep 17 00:00:00 2001 From: Adam Buchbinder Date: Fri, 4 Mar 2016 11:21:18 -0800 Subject: [PATCH 013/196] sparc: Fix misspellings in comments. Signed-off-by: Adam Buchbinder Reviewed-by: Julian Calaby Signed-off-by: David S. Miller --- arch/sparc/include/asm/pgtable_64.h | 2 +- arch/sparc/include/asm/processor_64.h | 2 +- arch/sparc/include/asm/tsb.h | 2 +- arch/sparc/kernel/entry.S | 2 +- arch/sparc/kernel/ioport.c | 6 +++--- arch/sparc/kernel/leon_kernel.c | 2 +- arch/sparc/kernel/sysfs.c | 2 +- arch/sparc/net/bpf_jit_comp.c | 2 +- 8 files changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 7a38d6a576c5..f089cfa249f3 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -218,7 +218,7 @@ extern pgprot_t PAGE_KERNEL_LOCKED; extern pgprot_t PAGE_COPY; extern pgprot_t PAGE_SHARED; -/* XXX This uglyness is for the atyfb driver's sparc mmap() support. XXX */ +/* XXX This ugliness is for the atyfb driver's sparc mmap() support. XXX */ extern unsigned long _PAGE_IE; extern unsigned long _PAGE_E; extern unsigned long _PAGE_CACHE; diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 6924bdefe148..ce2595c89471 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -201,7 +201,7 @@ unsigned long get_wchan(struct task_struct *task); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->u_regs[UREG_FP]) /* Please see the commentary in asm/backoff.h for a description of - * what these instructions are doing and how they have been choosen. + * what these instructions are doing and how they have been chosen. * To make a long story short, we are trying to yield the current cpu * strand during busy loops. */ diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index ecb49cfa3be9..c6a155c3904e 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -149,7 +149,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * page size in question. So for PMD mappings (which fall on * bit 23, for 8MB per PMD) we must propagate bit 22 for a * 4MB huge page. For huge PUDs (which fall on bit 33, for - * 8GB per PUD), we have to accomodate 256MB and 2GB huge + * 8GB per PUD), we have to accommodate 256MB and 2GB huge * pages. So for those we propagate bits 32 to 28. */ #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL) \ diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index a83707c83be8..51aa6e86a5f8 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -1255,7 +1255,7 @@ flush_patch_exception: kuw_patch1_7win: sll %o3, 6, %o3 /* No matter how much overhead this routine has in the worst - * case scenerio, it is several times better than taking the + * case scenario, it is several times better than taking the * traps with the old method of just doing flush_user_windows(). */ kill_user_windows: diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 28fed53b13a0..ffd5ff4678cf 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -131,7 +131,7 @@ void __iomem *ioremap(unsigned long offset, unsigned long size) EXPORT_SYMBOL(ioremap); /* - * Comlimentary to ioremap(). + * Complementary to ioremap(). */ void iounmap(volatile void __iomem *virtual) { @@ -233,7 +233,7 @@ _sparc_ioremap(struct resource *res, u32 bus, u32 pa, int sz) } /* - * Comlimentary to _sparc_ioremap(). + * Complementary to _sparc_ioremap(). */ static void _sparc_free_io(struct resource *res) { @@ -532,7 +532,7 @@ static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size, } /* Map a set of buffers described by scatterlist in streaming - * mode for DMA. This is the scather-gather version of the + * mode for DMA. This is the scatter-gather version of the * above pci_map_single interface. Here the scatter gather list * elements are each tagged with the appropriate dma address * and length. They are obtained via sg_dma_{address,length}(SG). diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index 42efcf85f721..33cd171d933e 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -203,7 +203,7 @@ static struct irq_chip leon_irq = { /* * Build a LEON IRQ for the edge triggered LEON IRQ controller: - * Edge (normal) IRQ - handle_simple_irq, ack=DONT-CARE, never ack + * Edge (normal) IRQ - handle_simple_irq, ack=DON'T-CARE, never ack * Level IRQ (PCI|Level-GPIO) - handle_fasteoi_irq, ack=1, ack after ISR * Per-CPU Edge - handle_percpu_irq, ack=0 */ diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c index 7f41d40b7e6e..fa8e21abb5e0 100644 --- a/arch/sparc/kernel/sysfs.c +++ b/arch/sparc/kernel/sysfs.c @@ -1,4 +1,4 @@ -/* sysfs.c: Toplogy sysfs support code for sparc64. +/* sysfs.c: Topology sysfs support code for sparc64. * * Copyright (C) 2007 David S. Miller */ diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 3e6e05a7c4c2..a6d9204a6a0b 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -351,7 +351,7 @@ do { *prog++ = BR_OPC | WDISP22(OFF); \ * * Sometimes we need to emit a branch earlier in the code * sequence. And in these situations we adjust "destination" - * to accomodate this difference. For example, if we needed + * to accommodate this difference. For example, if we needed * to emit a branch (and it's delay slot) right before the * final instruction emitted for a BPF opcode, we'd use * "destination + 4" instead of just plain "destination" above. From 9ef595d83aea6b4d93c9a120df3c5db2e226929f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 10 Mar 2016 15:21:43 -0800 Subject: [PATCH 014/196] sparc: Convert naked unsigned uses to unsigned int Use the more normal kernel definition/declaration style. Done via: $ git ls-files arch/sparc | \ xargs ./scripts/checkpatch.pl -f --fix-inplace --types=unspecified_int Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- arch/sparc/include/asm/compat_signal.h | 8 +++---- arch/sparc/include/asm/obio.h | 32 +++++++++++++------------- arch/sparc/include/asm/openprom.h | 10 ++++---- arch/sparc/include/asm/sigcontext.h | 2 +- arch/sparc/include/uapi/asm/stat.h | 4 ++-- arch/sparc/kernel/audit.c | 12 +++++----- arch/sparc/kernel/compat_audit.c | 12 +++++----- arch/sparc/kernel/kernel.h | 12 +++++----- arch/sparc/kernel/process_64.c | 2 +- arch/sparc/kernel/setup_32.c | 2 +- arch/sparc/kernel/setup_64.c | 2 +- arch/sparc/kernel/signal32.c | 2 +- arch/sparc/kernel/sys_sparc_64.c | 4 ++-- arch/sparc/kernel/unaligned_64.c | 4 ++-- arch/sparc/mm/fault_32.c | 8 +++---- 15 files changed, 58 insertions(+), 58 deletions(-) diff --git a/arch/sparc/include/asm/compat_signal.h b/arch/sparc/include/asm/compat_signal.h index 9ed1f128b4d1..4b027b1044fa 100644 --- a/arch/sparc/include/asm/compat_signal.h +++ b/arch/sparc/include/asm/compat_signal.h @@ -6,17 +6,17 @@ #ifdef CONFIG_COMPAT struct __new_sigaction32 { - unsigned sa_handler; + unsigned int sa_handler; unsigned int sa_flags; - unsigned sa_restorer; /* not used by Linux/SPARC yet */ + unsigned int sa_restorer; /* not used by Linux/SPARC yet */ compat_sigset_t sa_mask; }; struct __old_sigaction32 { - unsigned sa_handler; + unsigned int sa_handler; compat_old_sigset_t sa_mask; unsigned int sa_flags; - unsigned sa_restorer; /* not used by Linux/SPARC yet */ + unsigned int sa_restorer; /* not used by Linux/SPARC yet */ }; #endif diff --git a/arch/sparc/include/asm/obio.h b/arch/sparc/include/asm/obio.h index 910c1d9af1f8..426ad75103fb 100644 --- a/arch/sparc/include/asm/obio.h +++ b/arch/sparc/include/asm/obio.h @@ -117,9 +117,9 @@ static inline void bw_clear_intr_mask(int sbus_level, int mask) "i" (ASI_M_CTL)); } -static inline unsigned bw_get_prof_limit(int cpu) +static inline unsigned int bw_get_prof_limit(int cpu) { - unsigned limit; + unsigned int limit; __asm__ __volatile__ ("lda [%1] %2, %0" : "=r" (limit) : @@ -128,7 +128,7 @@ static inline unsigned bw_get_prof_limit(int cpu) return limit; } -static inline void bw_set_prof_limit(int cpu, unsigned limit) +static inline void bw_set_prof_limit(int cpu, unsigned int limit) { __asm__ __volatile__ ("sta %0, [%1] %2" : : "r" (limit), @@ -136,9 +136,9 @@ static inline void bw_set_prof_limit(int cpu, unsigned limit) "i" (ASI_M_CTL)); } -static inline unsigned bw_get_ctrl(int cpu) +static inline unsigned int bw_get_ctrl(int cpu) { - unsigned ctrl; + unsigned int ctrl; __asm__ __volatile__ ("lda [%1] %2, %0" : "=r" (ctrl) : @@ -147,7 +147,7 @@ static inline unsigned bw_get_ctrl(int cpu) return ctrl; } -static inline void bw_set_ctrl(int cpu, unsigned ctrl) +static inline void bw_set_ctrl(int cpu, unsigned int ctrl) { __asm__ __volatile__ ("sta %0, [%1] %2" : : "r" (ctrl), @@ -155,9 +155,9 @@ static inline void bw_set_ctrl(int cpu, unsigned ctrl) "i" (ASI_M_CTL)); } -static inline unsigned cc_get_ipen(void) +static inline unsigned int cc_get_ipen(void) { - unsigned pending; + unsigned int pending; __asm__ __volatile__ ("lduha [%1] %2, %0" : "=r" (pending) : @@ -166,7 +166,7 @@ static inline unsigned cc_get_ipen(void) return pending; } -static inline void cc_set_iclr(unsigned clear) +static inline void cc_set_iclr(unsigned int clear) { __asm__ __volatile__ ("stha %0, [%1] %2" : : "r" (clear), @@ -174,9 +174,9 @@ static inline void cc_set_iclr(unsigned clear) "i" (ASI_M_MXCC)); } -static inline unsigned cc_get_imsk(void) +static inline unsigned int cc_get_imsk(void) { - unsigned mask; + unsigned int mask; __asm__ __volatile__ ("lduha [%1] %2, %0" : "=r" (mask) : @@ -185,7 +185,7 @@ static inline unsigned cc_get_imsk(void) return mask; } -static inline void cc_set_imsk(unsigned mask) +static inline void cc_set_imsk(unsigned int mask) { __asm__ __volatile__ ("stha %0, [%1] %2" : : "r" (mask), @@ -193,9 +193,9 @@ static inline void cc_set_imsk(unsigned mask) "i" (ASI_M_MXCC)); } -static inline unsigned cc_get_imsk_other(int cpuid) +static inline unsigned int cc_get_imsk_other(int cpuid) { - unsigned mask; + unsigned int mask; __asm__ __volatile__ ("lduha [%1] %2, %0" : "=r" (mask) : @@ -204,7 +204,7 @@ static inline unsigned cc_get_imsk_other(int cpuid) return mask; } -static inline void cc_set_imsk_other(int cpuid, unsigned mask) +static inline void cc_set_imsk_other(int cpuid, unsigned int mask) { __asm__ __volatile__ ("stha %0, [%1] %2" : : "r" (mask), @@ -212,7 +212,7 @@ static inline void cc_set_imsk_other(int cpuid, unsigned mask) "i" (ASI_M_CTL)); } -static inline void cc_set_igen(unsigned gen) +static inline void cc_set_igen(unsigned int gen) { __asm__ __volatile__ ("sta %0, [%1] %2" : : "r" (gen), diff --git a/arch/sparc/include/asm/openprom.h b/arch/sparc/include/asm/openprom.h index 47eaafad15ce..63374c4413a8 100644 --- a/arch/sparc/include/asm/openprom.h +++ b/arch/sparc/include/asm/openprom.h @@ -29,12 +29,12 @@ struct linux_dev_v0_funcs { /* V2 and later prom device operations. */ struct linux_dev_v2_funcs { phandle (*v2_inst2pkg)(int d); /* Convert ihandle to phandle */ - char * (*v2_dumb_mem_alloc)(char *va, unsigned sz); - void (*v2_dumb_mem_free)(char *va, unsigned sz); + char * (*v2_dumb_mem_alloc)(char *va, unsigned int sz); + void (*v2_dumb_mem_free)(char *va, unsigned int sz); /* To map devices into virtual I/O space. */ - char * (*v2_dumb_mmap)(char *virta, int which_io, unsigned paddr, unsigned sz); - void (*v2_dumb_munmap)(char *virta, unsigned size); + char * (*v2_dumb_mmap)(char *virta, int which_io, unsigned int paddr, unsigned int sz); + void (*v2_dumb_munmap)(char *virta, unsigned int size); int (*v2_dev_open)(char *devpath); void (*v2_dev_close)(int d); @@ -50,7 +50,7 @@ struct linux_dev_v2_funcs { struct linux_mlist_v0 { struct linux_mlist_v0 *theres_more; unsigned int start_adr; - unsigned num_bytes; + unsigned int num_bytes; }; struct linux_mem_v0 { diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h index fc2df1e892cb..f4eb630a58ed 100644 --- a/arch/sparc/include/asm/sigcontext.h +++ b/arch/sparc/include/asm/sigcontext.h @@ -25,7 +25,7 @@ struct sigcontext32 { int sigc_oswins; /* outstanding windows */ /* stack ptrs for each regwin buf */ - unsigned sigc_spbuf[__SUNOS_MAXWIN]; + unsigned int sigc_spbuf[__SUNOS_MAXWIN]; /* Windows to restore after signal */ struct reg_window32 sigc_wbuf[__SUNOS_MAXWIN]; diff --git a/arch/sparc/include/uapi/asm/stat.h b/arch/sparc/include/uapi/asm/stat.h index a232e9e1f4e5..2f0583a2c689 100644 --- a/arch/sparc/include/uapi/asm/stat.h +++ b/arch/sparc/include/uapi/asm/stat.h @@ -6,13 +6,13 @@ #if defined(__sparc__) && defined(__arch64__) /* 64 bit sparc */ struct stat { - unsigned st_dev; + unsigned int st_dev; ino_t st_ino; mode_t st_mode; short st_nlink; uid_t st_uid; gid_t st_gid; - unsigned st_rdev; + unsigned int st_rdev; off_t st_size; time_t st_atime; time_t st_mtime; diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c index 24361b494a93..2585c1e14bcc 100644 --- a/arch/sparc/kernel/audit.c +++ b/arch/sparc/kernel/audit.c @@ -5,27 +5,27 @@ #include "kernel.h" -static unsigned dir_class[] = { +static unsigned int dir_class[] = { #include ~0U }; -static unsigned read_class[] = { +static unsigned int read_class[] = { #include ~0U }; -static unsigned write_class[] = { +static unsigned int write_class[] = { #include ~0U }; -static unsigned chattr_class[] = { +static unsigned int chattr_class[] = { #include ~0U }; -static unsigned signal_class[] = { +static unsigned int signal_class[] = { #include ~0U }; @@ -39,7 +39,7 @@ int audit_classify_arch(int arch) return 0; } -int audit_classify_syscall(int abi, unsigned syscall) +int audit_classify_syscall(int abi, unsigned int syscall) { #ifdef CONFIG_COMPAT if (abi == AUDIT_ARCH_SPARC) diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c index 7062263d09c1..e5611cd428f1 100644 --- a/arch/sparc/kernel/compat_audit.c +++ b/arch/sparc/kernel/compat_audit.c @@ -2,32 +2,32 @@ #include #include "kernel.h" -unsigned sparc32_dir_class[] = { +unsigned int sparc32_dir_class[] = { #include ~0U }; -unsigned sparc32_chattr_class[] = { +unsigned int sparc32_chattr_class[] = { #include ~0U }; -unsigned sparc32_write_class[] = { +unsigned int sparc32_write_class[] = { #include ~0U }; -unsigned sparc32_read_class[] = { +unsigned int sparc32_read_class[] = { #include ~0U }; -unsigned sparc32_signal_class[] = { +unsigned int sparc32_signal_class[] = { #include ~0U }; -int sparc32_classify_syscall(unsigned syscall) +int sparc32_classify_syscall(unsigned int syscall) { switch(syscall) { case __NR_open: diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index e7f652be9e61..5057ec2e4af6 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -54,12 +54,12 @@ void do_signal32(struct pt_regs * regs); asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp); /* compat_audit.c */ -extern unsigned sparc32_dir_class[]; -extern unsigned sparc32_chattr_class[]; -extern unsigned sparc32_write_class[]; -extern unsigned sparc32_read_class[]; -extern unsigned sparc32_signal_class[]; -int sparc32_classify_syscall(unsigned syscall); +extern unsigned int sparc32_dir_class[]; +extern unsigned int sparc32_chattr_class[]; +extern unsigned int sparc32_write_class[]; +extern unsigned int sparc32_read_class[]; +extern unsigned int sparc32_signal_class[]; +int sparc32_classify_syscall(unsigned int syscall); #endif #ifdef CONFIG_SPARC32 diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 46a59643bb1c..c16ef1af1843 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -103,7 +103,7 @@ static void show_regwindow32(struct pt_regs *regs) mm_segment_t old_fs; __asm__ __volatile__ ("flushw"); - rw = compat_ptr((unsigned)regs->u_regs[14]); + rw = compat_ptr((unsigned int)regs->u_regs[14]); old_fs = get_fs(); set_fs (USER_DS); if (copy_from_user (&r_w, rw, sizeof(r_w))) { diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index baef495c06bd..69d75ff1c25c 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -109,7 +109,7 @@ unsigned long cmdline_memory_size __initdata = 0; unsigned char boot_cpu_id = 0xff; /* 0xff will make it into DATA section... */ static void -prom_console_write(struct console *con, const char *s, unsigned n) +prom_console_write(struct console *con, const char *s, unsigned int n) { prom_write(s, n); } diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index f3185e2b028b..26db95b54ee9 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -77,7 +77,7 @@ struct screen_info screen_info = { }; static void -prom_console_write(struct console *con, const char *s, unsigned n) +prom_console_write(struct console *con, const char *s, unsigned int n) { prom_write(s, n); } diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 4eed773a7735..3c25241fa5cb 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -144,7 +144,7 @@ void do_sigreturn32(struct pt_regs *regs) compat_uptr_t fpu_save; compat_uptr_t rwin_save; unsigned int psr; - unsigned pc, npc; + unsigned int pc, npc; sigset_t set; compat_sigset_t seta; int err, i; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index b489e9759518..fe8b8ee8e660 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -337,10 +337,10 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second switch (call) { case SEMOP: err = sys_semtimedop(first, ptr, - (unsigned)second, NULL); + (unsigned int)second, NULL); goto out; case SEMTIMEDOP: - err = sys_semtimedop(first, ptr, (unsigned)second, + err = sys_semtimedop(first, ptr, (unsigned int)second, (const struct timespec __user *) (unsigned long) fifth); goto out; diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index d89e97b374cf..9aacb9159262 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -209,8 +209,8 @@ static inline int do_int_store(int reg_num, int size, unsigned long *dst_addr, if (size == 16) { size = 8; zero = (((long)(reg_num ? - (unsigned)fetch_reg(reg_num, regs) : 0)) << 32) | - (unsigned)fetch_reg(reg_num + 1, regs); + (unsigned int)fetch_reg(reg_num, regs) : 0)) << 32) | + (unsigned int)fetch_reg(reg_num + 1, regs); } else if (reg_num) { src_val_p = fetch_reg_addr(reg_num, regs); } diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index c399e7b3b035..b6c559cbd64d 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -303,10 +303,10 @@ no_context: fixup = search_extables_range(regs->pc, &g2); /* Values below 10 are reserved for other things */ if (fixup > 10) { - extern const unsigned __memset_start[]; - extern const unsigned __memset_end[]; - extern const unsigned __csum_partial_copy_start[]; - extern const unsigned __csum_partial_copy_end[]; + extern const unsigned int __memset_start[]; + extern const unsigned int __memset_end[]; + extern const unsigned int __csum_partial_copy_start[]; + extern const unsigned int __csum_partial_copy_end[]; #ifdef DEBUG_EXCEPTIONS printk("Exception: PC<%08lx> faddr<%08lx>\n", From 8bd98f0e6bf792e8fa7c3fed709321ad42ba8d2e Mon Sep 17 00:00:00 2001 From: Alex Lyakas Date: Thu, 10 Mar 2016 13:09:46 +0200 Subject: [PATCH 015/196] btrfs: csum_tree_block: return proper errno value Signed-off-by: Alex Lyakas Reviewed-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a998ef15ec6d..9cafae5c2061 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -302,7 +302,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, err = map_private_extent_buffer(buf, offset, 32, &kaddr, &map_start, &map_len); if (err) - return 1; + return err; cur_len = min(len, map_len - (offset - map_start)); crc = btrfs_csum_data(kaddr + offset - map_start, crc, cur_len); @@ -312,7 +312,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, if (csum_size > sizeof(inline_result)) { result = kzalloc(csum_size, GFP_NOFS); if (!result) - return 1; + return -ENOMEM; } else { result = (char *)&inline_result; } @@ -333,7 +333,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info, val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) kfree(result); - return 1; + return -EUCLEAN; } } else { write_extent_buffer(buf, result, 0, csum_size); @@ -515,8 +515,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) found_start = btrfs_header_bytenr(eb); if (WARN_ON(found_start != start || !PageUptodate(page))) return 0; - csum_tree_block(fs_info, eb, 0); - return 0; + return csum_tree_block(fs_info, eb, 0); } static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, @@ -660,10 +659,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, eb, found_level); ret = csum_tree_block(fs_info, eb, 1); - if (ret) { - ret = -EIO; + if (ret) goto err; - } /* * If this is a leaf block and it is corrupt, set the corrupt bit so From 0f805531daa2ebfb5706422dc2ead1cff9e53e65 Mon Sep 17 00:00:00 2001 From: Alex Lyakas Date: Thu, 10 Mar 2016 13:10:15 +0200 Subject: [PATCH 016/196] btrfs: do not write corrupted metadata blocks to disk csum_dirty_buffer was issuing a warning in case the extent buffer did not look alright, but was still returning success. Let's return error in this case, and also add an additional sanity check on the extent buffer header. The caller up the chain may BUG_ON on this, for example flush_epd_write_bio will, but it is better than to have a silent metadata corruption on disk. Signed-off-by: Alex Lyakas Reviewed-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9cafae5c2061..8579b35bb160 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -512,9 +512,20 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) eb = (struct extent_buffer *)page->private; if (page != eb->pages[0]) return 0; + found_start = btrfs_header_bytenr(eb); - if (WARN_ON(found_start != start || !PageUptodate(page))) - return 0; + /* + * Please do not consolidate these warnings into a single if. + * It is useful to know what went wrong. + */ + if (WARN_ON(found_start != start)) + return -EUCLEAN; + if (WARN_ON(!PageUptodate(page))) + return -EUCLEAN; + + ASSERT(memcmp_extent_buffer(eb, fs_info->fsid, + btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0); + return csum_tree_block(fs_info, eb, 0); } From 838fe1887765f4cc679febea60d87d2a06bd300e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 15 Mar 2016 11:28:54 +0100 Subject: [PATCH 017/196] btrfs: cleaner_kthread() doesn't need explicit freeze cleaner_kthread() is not marked freezable, and therefore calling try_to_freeze() in its context is a pointless no-op. In addition to that, as has been clearly demonstrated by 80ad623edd2d ("Revert "btrfs: clear PF_NOFREEZE in cleaner_kthread()"), it's perfectly valid / legal for cleaner_kthread() to stay scheduled out in an arbitrary place during suspend (in that particular example that was waiting for reading of extent pages), so there is no need to leave any traces of freezer in this kthread. Fixes: 80ad623edd2d ("Revert "btrfs: clear PF_NOFREEZE in cleaner_kthread()") Fixes: 696249132158 ("btrfs: clear PF_NOFREEZE in cleaner_kthread()") Signed-off-by: Jiri Kosina Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8579b35bb160..ff36a33ee9ca 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1838,7 +1838,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(root->fs_info); sleep: - if (!try_to_freeze() && !again) { + if (!again) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop()) schedule(); From ce63f891e1a87ae79c4325dad5f512e8d6a8a78e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 15 Mar 2016 11:28:59 +0100 Subject: [PATCH 018/196] btrfs: transaction_kthread() is not freezable transaction_kthread() is calling try_to_freeze(), but that's just an expeinsive no-op given the fact that the thread is not marked freezable. After removing this, disk-io.c is now independent on freezer API. Signed-off-by: Jiri Kosina Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ff36a33ee9ca..81966676a26b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include @@ -1928,14 +1927,12 @@ sleep: if (unlikely(test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))) btrfs_cleanup_transaction(root); - if (!try_to_freeze()) { - set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop() && - (!btrfs_transaction_blocked(root->fs_info) || - cannot_commit)) - schedule_timeout(delay); - __set_current_state(TASK_RUNNING); - } + set_current_state(TASK_INTERRUPTIBLE); + if (!kthread_should_stop() && + (!btrfs_transaction_blocked(root->fs_info) || + cannot_commit)) + schedule_timeout(delay); + __set_current_state(TASK_RUNNING); } while (!kthread_should_stop()); return 0; } From 91d2178e26fdc806f33063f9df5904a48e3b6aeb Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 23 Mar 2016 08:03:59 +0900 Subject: [PATCH 019/196] ALSA: timer: fix gparams ioctl compatibility for different architectures 'struct snd_timer_gparams' includes some members with 'unsigned long', therefore its size differs depending on data models of architecture. As a result, x86/x32 applications fail to execute ioctl(2) with SNDRV_TIMER_GPARAMS command on x86_64 machine. This commit fixes this bug by adding a pair of structure and ioctl command for the compatibility. Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/core/timer.c | 20 +++++++++++++------- sound/core/timer_compat.c | 30 +++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 8 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index aa1b15c155d1..ea4d999113ef 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1502,17 +1502,13 @@ static int snd_timer_user_ginfo(struct file *file, return err; } -static int snd_timer_user_gparams(struct file *file, - struct snd_timer_gparams __user *_gparams) +static int timer_set_gparams(struct snd_timer_gparams *gparams) { - struct snd_timer_gparams gparams; struct snd_timer *t; int err; - if (copy_from_user(&gparams, _gparams, sizeof(gparams))) - return -EFAULT; mutex_lock(®ister_mutex); - t = snd_timer_find(&gparams.tid); + t = snd_timer_find(&gparams->tid); if (!t) { err = -ENODEV; goto _error; @@ -1525,12 +1521,22 @@ static int snd_timer_user_gparams(struct file *file, err = -ENOSYS; goto _error; } - err = t->hw.set_period(t, gparams.period_num, gparams.period_den); + err = t->hw.set_period(t, gparams->period_num, gparams->period_den); _error: mutex_unlock(®ister_mutex); return err; } +static int snd_timer_user_gparams(struct file *file, + struct snd_timer_gparams __user *_gparams) +{ + struct snd_timer_gparams gparams; + + if (copy_from_user(&gparams, _gparams, sizeof(gparams))) + return -EFAULT; + return timer_set_gparams(&gparams); +} + static int snd_timer_user_gstatus(struct file *file, struct snd_timer_gstatus __user *_gstatus) { diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index 2e908225d754..6a437eb66115 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -22,6 +22,19 @@ #include +/* + * ILP32/LP64 has different size for 'long' type. Additionally, the size + * of storage alignment differs depending on architectures. Here, '__packed' + * qualifier is used so that the size of this structure is multiple of 4 and + * it fits to any architectures with 32 bit storage alignment. + */ +struct snd_timer_gparams32 { + struct snd_timer_id tid; + u32 period_num; + u32 period_den; + unsigned char reserved[32]; +} __packed; + struct snd_timer_info32 { u32 flags; s32 card; @@ -32,6 +45,19 @@ struct snd_timer_info32 { unsigned char reserved[64]; }; +static int snd_timer_user_gparams_compat(struct file *file, + struct snd_timer_gparams32 __user *user) +{ + struct snd_timer_gparams gparams; + + if (copy_from_user(&gparams.tid, &user->tid, sizeof(gparams.tid)) || + get_user(gparams.period_num, &user->period_num) || + get_user(gparams.period_den, &user->period_den)) + return -EFAULT; + + return timer_set_gparams(&gparams); +} + static int snd_timer_user_info_compat(struct file *file, struct snd_timer_info32 __user *_info) { @@ -99,6 +125,7 @@ static int snd_timer_user_status_compat(struct file *file, */ enum { + SNDRV_TIMER_IOCTL_GPARAMS32 = _IOW('T', 0x04, struct snd_timer_gparams32), SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32), SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32), #ifdef CONFIG_X86_X32 @@ -114,7 +141,6 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns case SNDRV_TIMER_IOCTL_PVERSION: case SNDRV_TIMER_IOCTL_TREAD: case SNDRV_TIMER_IOCTL_GINFO: - case SNDRV_TIMER_IOCTL_GPARAMS: case SNDRV_TIMER_IOCTL_GSTATUS: case SNDRV_TIMER_IOCTL_SELECT: case SNDRV_TIMER_IOCTL_PARAMS: @@ -128,6 +154,8 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns case SNDRV_TIMER_IOCTL_PAUSE_OLD: case SNDRV_TIMER_IOCTL_NEXT_DEVICE: return snd_timer_user_ioctl(file, cmd, (unsigned long)argp); + case SNDRV_TIMER_IOCTL_GPARAMS32: + return snd_timer_user_gparams_compat(file, argp); case SNDRV_TIMER_IOCTL_INFO32: return snd_timer_user_info_compat(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: From e54358915d0a00399c11c2c23ae1be674cba188a Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Sun, 20 Mar 2016 23:23:46 +0100 Subject: [PATCH 020/196] PKCS#7: pkcs7_validate_trust(): initialize the _trusted output argument Despite what the DocBook comment to pkcs7_validate_trust() says, the *_trusted argument is never set to false. pkcs7_validate_trust() only positively sets *_trusted upon encountering a trusted PKCS#7 SignedInfo block. This is quite unfortunate since its callers, system_verify_data() for example, depend on pkcs7_validate_trust() clearing *_trusted on non-trust. Indeed, UBSAN splats when attempting to load the uninitialized local variable 'trusted' from system_verify_data() in pkcs7_validate_trust(): UBSAN: Undefined behaviour in crypto/asymmetric_keys/pkcs7_trust.c:194:14 load of value 82 is not a valid value for type '_Bool' [...] Call Trace: [] dump_stack+0xbc/0x117 [] ? _atomic_dec_and_lock+0x169/0x169 [] ubsan_epilogue+0xd/0x4e [] __ubsan_handle_load_invalid_value+0x111/0x158 [] ? val_to_string.constprop.12+0xcf/0xcf [] ? x509_request_asymmetric_key+0x114/0x370 [] ? kfree+0x220/0x370 [] ? public_key_verify_signature_2+0x32/0x50 [] pkcs7_validate_trust+0x524/0x5f0 [] system_verify_data+0xca/0x170 [] ? top_trace_array+0x9b/0x9b [] ? __vfs_read+0x279/0x3d0 [] mod_verify_sig+0x1ff/0x290 [...] The implication is that pkcs7_validate_trust() effectively grants trust when it really shouldn't have. Fix this by explicitly setting *_trusted to false at the very beginning of pkcs7_validate_trust(). Cc: Signed-off-by: Nicolai Stange Signed-off-by: Herbert Xu --- crypto/asymmetric_keys/pkcs7_trust.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c index 90d6d47965b0..ecdb5a2ce085 100644 --- a/crypto/asymmetric_keys/pkcs7_trust.c +++ b/crypto/asymmetric_keys/pkcs7_trust.c @@ -178,6 +178,8 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7, int cached_ret = -ENOKEY; int ret; + *_trusted = false; + for (p = pkcs7->certs; p; p = p->next) p->seen = false; From 70cf2cbd685e218c3ffd105d9fb6cf0f8d767481 Mon Sep 17 00:00:00 2001 From: Bobi Mihalca Date: Wed, 23 Mar 2016 13:23:55 +0200 Subject: [PATCH 021/196] ALSA: hda - Asus N750JV external subwoofer fixup ASUS N750JV needs the same fixup as N550 for enabling its subwoofer. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=115181 Signed-off-by: Bobi Mihalca Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4f5ca0b9ce27..44c52c2b7be7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6670,6 +6670,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), From 9d4dc5840f93bcb002fa311693349deae7702bc5 Mon Sep 17 00:00:00 2001 From: Bobi Mihalca Date: Wed, 23 Mar 2016 13:26:11 +0200 Subject: [PATCH 022/196] ALSA: hda - Fix white noise on Asus N750JV headphone For reducing the noise from the headphone output on ASUS N750JV, call the existing fixup, alc_fixup_auto_mute_via_amp(), additionally. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=115181 Signed-off-by: Bobi Mihalca Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 44c52c2b7be7..f6bac82814b3 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6406,6 +6406,7 @@ enum { ALC668_FIXUP_AUTO_MUTE, ALC668_FIXUP_DELL_DISABLE_AAMIX, ALC668_FIXUP_DELL_XPS13, + ALC662_FIXUP_ASUS_Nx50, }; static const struct hda_fixup alc662_fixups[] = { @@ -6646,6 +6647,12 @@ static const struct hda_fixup alc662_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_bass_chmap, }, + [ALC662_FIXUP_ASUS_Nx50] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_auto_mute_via_amp, + .chained = true, + .chain_id = ALC662_FIXUP_BASS_1A + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -6670,7 +6677,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), - SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), From 83a9efb5b8170b7cffef4f62656656e1d8ad2ccd Mon Sep 17 00:00:00 2001 From: Bobi Mihalca Date: Wed, 23 Mar 2016 13:32:33 +0200 Subject: [PATCH 023/196] ALSA: hda - Apply fix for white noise on Asus N550JV, too Apply the new fixup that is used for ASUS N750JV to another similar model, N500JV, too, for reducing the headphone noise. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=115181 Signed-off-by: Bobi Mihalca Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f6bac82814b3..73978c79981f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6675,7 +6675,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x069f, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), - SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A), + SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x13df, "Asus N550JX", ALC662_FIXUP_BASS_1A), SND_PCI_QUIRK(0x1043, 0x129d, "Asus N750", ALC662_FIXUP_ASUS_Nx50), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), From 4016260ba47a43ec67d4bf3610be37fcb2e416d7 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 23 Mar 2016 07:10:17 -0400 Subject: [PATCH 024/196] drm/msm: fix bug after preclose removal commit 53190c7194d9a8337fe419134e44c30eb63ebd08 Author: Daniel Vetter AuthorDate: Mon Jan 25 22:16:49 2016 +0100 Commit: Daniel Vetter CommitDate: Mon Feb 8 09:55:50 2016 +0100 drm/msm: Nuke preclose hooks Left around the unused (and null) preclose fxn ptr, and things predictibly explode when you try to call that. Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_drv.c | 3 --- drivers/gpu/drm/msm/msm_kms.h | 1 - 2 files changed, 4 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index d52910e2c26c..c03b96709179 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -467,9 +467,6 @@ static void msm_preclose(struct drm_device *dev, struct drm_file *file) struct msm_file_private *ctx = file->driver_priv; struct msm_kms *kms = priv->kms; - if (kms) - kms->funcs->preclose(kms, file); - mutex_lock(&dev->struct_mutex); if (ctx == priv->lastctx) priv->lastctx = NULL; diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index 9bcabaada179..e32222c3d44f 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -55,7 +55,6 @@ struct msm_kms_funcs { struct drm_encoder *slave_encoder, bool is_cmd_mode); /* cleanup: */ - void (*preclose)(struct msm_kms *kms, struct drm_file *file); void (*destroy)(struct msm_kms *kms); }; From 0a69509f24ebf3e701bf1df6e2673ca16bdbe5c9 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Wed, 23 Mar 2016 10:09:00 -0400 Subject: [PATCH 025/196] drm/msm: fix typo in the !COMMON_CLK case Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/hdmi/hdmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index b04a64664673..65428cf233ce 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -196,7 +196,7 @@ void __exit msm_hdmi_phy_driver_unregister(void); int msm_hdmi_pll_8960_init(struct platform_device *pdev); int msm_hdmi_pll_8996_init(struct platform_device *pdev); #else -static inline int msm_hdmi_pll_8960_init(struct platform_device *pdev); +static inline int msm_hdmi_pll_8960_init(struct platform_device *pdev) { return -ENODEV; } From cde88355f2cd7082f5a208901f99b80f4823872c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 24 Mar 2016 11:22:43 -0300 Subject: [PATCH 026/196] perf tests: Fix tarpkg build test error output redirection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So we need to trow away just stdout, leaving stderr to be caught by the build tests infrastructure, so that we can see what went wrong when the tarpkg build test fails: $ make -C tools/perf build-test make: Entering directory '/home/acme/git/linux/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . tests/make:302: recipe for target 'tarpkg' failed make[1]: *** [tarpkg] Error 2 Makefile:102: recipe for target 'build-test' failed make: *** [build-test] Error 2 make: Leaving directory '/home/acme/git/linux/tools/perf' $ cat tools/perf/tarpkg ./tests/perf-targz-src-pkg . PERF_VERSION = 4.5.g05f5ec PERF_VERSION = 4.5.g05f5ec In file included from bench/mem-memcpy-x86-64-asm.S:9:0: bench/../../../arch/x86/lib/memcpy_64.S:5:29: fatal error: asm/cpufeatures.h: No such file or directory compilation terminated. mv: cannot stat ‘bench/.mem-memcpy-x86-64-asm.o.tmp’: No such file or directory make[5]: *** [bench/mem-memcpy-x86-64-asm.o] Error 1 make[5]: *** Waiting for unfinished jobs.... make[4]: *** [bench] Error 2 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [perf-in.o] Error 2 make[3]: *** Waiting for unfinished jobs.... make[2]: *** [all] Error 2 $ So the test flow is: 1. Run: 'make -C tools/perf build-test' 2. One of its tests failed, in this case, the 'tarpkg' one 3. Look at what went wrong, by looking at the output of that test, in tools/perf/tarpkg Admittedly, this should be shortcircuited to showing what went wrong directly from the 'make build-test' step, but lets first fix this tarpkg one and the problem it spotted, which should be fixed by adding some extra file to the tools/perf/MANIFEST so that detached tarballs continue being self contained and build successfully. Cc: Adrian Hunter Cc: Borislav Petkov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-ynld6egoxolmftcddpnd7oh6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-targz-src-pkg | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg index 238aa3927c71..f2d9c5fe58e0 100755 --- a/tools/perf/tests/perf-targz-src-pkg +++ b/tools/perf/tests/perf-targz-src-pkg @@ -15,7 +15,7 @@ TMP_DEST=$(mktemp -d) tar xf ${TARBALL} -C $TMP_DEST rm -f ${TARBALL} cd - > /dev/null -make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1 +make -C $TMP_DEST/perf*/tools/perf > /dev/null RC=$? rm -rf ${TMP_DEST} exit $RC From 6a1a77baa7d81c8217ed10ba17a84c5f100343d9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 24 Mar 2016 11:48:23 -0300 Subject: [PATCH 027/196] perf bench: Fix detached tarball building due to missing 'perf bench memcpy' headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A change on kernel files included by the 'perf bench memcpy' code grew some new include deps, breaking the detached tarball build: $ make -C tools/perf build-test make: Entering directory '/home/acme/git/linux/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . tests/make:302: recipe for target 'tarpkg' failed make[1]: *** [tarpkg] Error 2 Makefile:102: recipe for target 'build-test' failed make: *** [build-test] Error 2 make: Leaving directory '/home/acme/git/linux/tools/perf' $ cat tools/perf/tarpkg ./tests/perf-targz-src-pkg . PERF_VERSION = 4.5.g05f5ec PERF_VERSION = 4.5.g05f5ec In file included from bench/mem-memcpy-x86-64-asm.S:9:0: bench/../../../arch/x86/lib/memcpy_64.S:5:29: fatal error: asm/cpufeatures.h: No such file or directory compilation terminated. mv: cannot stat ‘bench/.mem-memcpy-x86-64-asm.o.tmp’: No such file or directory make[5]: *** [bench/mem-memcpy-x86-64-asm.o] Error 1 make[5]: *** Waiting for unfinished jobs.... make[4]: *** [bench] Error 2 make[4]: *** Waiting for unfinished jobs.... make[3]: *** [perf-in.o] Error 2 make[3]: *** Waiting for unfinished jobs.... make[2]: *** [all] Error 2 $ Add arch/*/include/asm/*features.h to tools/perf/MANIFEST so that we can continue to use detached tarballs to build perf. Now it builds ok, doing it manually: $ make help | grep perf perf-tar-src-pkg - Build perf-4.5.0.tar source tarball perf-targz-src-pkg - Build perf-4.5.0.tar.gz source tarball perf-tarbz2-src-pkg - Build perf-4.5.0.tar.bz2 source tarball perf-tarxz-src-pkg - Build perf-4.5.0.tar.xz source tarball $ ls -la perf-4.5.0.tar ls: cannot access perf-4.5.0.tar: No such file or directory $ make perf-tar-src-pkg TAR PERF_VERSION = 4.5.g32c25b $ ls -la perf-4.5.0.tar -rw-rw-r--. 1 acme acme 6318080 Mar 24 11:52 perf-4.5.0.tar $ mv perf-4.5.0.tar /tmp $ cd /tmp $ tar xf perf-4.5.0.tar $ cd perf-4.5.0/tools/perf $ make > /dev/null PERF_VERSION = 4.5.g32c25b $ ls -la perf -rwxrwxr-x. 1 acme acme 14046416 Mar 24 11:53 perf $ ./perf --version perf version 4.5.g32c25b $ perf bench Usage: perf bench [] [] # List of all available benchmark collections: sched: Scheduler and IPC benchmarks mem: Memory access benchmarks numa: NUMA scheduling and MM benchmarks futex: Futex stressing benchmarks all: All benchmarks $ perf bench mem # List of available benchmarks for collection 'mem': memcpy: Benchmark for memcpy() functions memset: Benchmark for memset() functions all: Run all memory access benchmarks $ perf bench mem memcpy # Running 'mem/memcpy' benchmark: # function 'default' (Default memcpy() provided by glibc) # Copying 1MB bytes ... 15.024038 GB/sec # function 'x86-64-unrolled' (unrolled memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB bytes ... 17.438616 GB/sec # function 'x86-64-movsq' (movsq-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB bytes ... 25.040064 GB/sec # function 'x86-64-movsb' (movsb-based memcpy() in arch/x86/lib/memcpy_64.S) # Copying 1MB bytes ... 25.040064 GB/sec $ Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Hitoshi Mitake Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-2c2sncwffuabw58fj1pw86gu@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 2e1fa2357528..8c8c6b9ce915 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -74,6 +74,7 @@ arch/*/include/uapi/asm/unistd*.h arch/*/include/uapi/asm/perf_regs.h arch/*/lib/memcpy*.S arch/*/lib/memset*.S +arch/*/include/asm/*features.h include/linux/poison.h include/linux/hw_breakpoint.h include/uapi/linux/perf_event.h From 071d36bf21bcc837be00cea55bcef8d129e7f609 Mon Sep 17 00:00:00 2001 From: "subashab@codeaurora.org" Date: Wed, 23 Mar 2016 22:39:50 -0600 Subject: [PATCH 028/196] xfrm: Fix crash observed during device unregistration and decryption A crash is observed when a decrypted packet is processed in receive path. get_rps_cpus() tries to dereference the skb->dev fields but it appears that the device is freed from the poison pattern. [] get_rps_cpu+0x94/0x2f0 [] netif_rx_internal+0x140/0x1cc [] netif_rx+0x74/0x94 [] xfrm_input+0x754/0x7d0 [] xfrm_input_resume+0x10/0x1c [] esp_input_done+0x20/0x30 [] process_one_work+0x244/0x3fc [] worker_thread+0x2f8/0x418 [] kthread+0xe0/0xec -013|get_rps_cpu( | dev = 0xFFFFFFC08B688000, | skb = 0xFFFFFFC0C76AAC00 -> ( | dev = 0xFFFFFFC08B688000 -> ( | name = "...................................................... | name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev = 0xAAAAAAAAAAA Following are the sequence of events observed - - Encrypted packet in receive path from netdevice is queued - Encrypted packet queued for decryption (asynchronous) - Netdevice brought down and freed - Packet is decrypted and returned through callback in esp_input_done - Packet is queued again for process in network stack using netif_rx Since the device appears to have been freed, the dereference of skb->dev in get_rps_cpus() leads to an unhandled page fault exception. Fix this by holding on to device reference when queueing packets asynchronously and releasing the reference on call back return. v2: Make the change generic to xfrm as mentioned by Steffen and update the title to xfrm Suggested-by: Herbert Xu Signed-off-by: Jerome Stanislaus Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- net/xfrm/xfrm_input.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index ad7f5b3f9b61..1c4ad477ce93 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; skb_dst_force(skb); + dev_hold(skb->dev); nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: + dev_put(skb->dev); + spin_lock(&x->lock); if (nexthdr <= 0) { if (nexthdr == -EBADMSG) { From 526131262223e9315bfd41213f5a76e792f184ff Mon Sep 17 00:00:00 2001 From: Qianqian Xie Date: Thu, 24 Mar 2016 19:08:00 +0800 Subject: [PATCH 029/196] net: hns: fix a bug for cycle index The cycle index should be varied while the variable j is a fixed value. The patch will fix this bug. Signed-off-by: Qianqian Xie Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 5c1ac9ba1bf2..5978a5c8ef35 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2219,17 +2219,17 @@ void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data) /* dsaf onode registers */ for (i = 0; i < DSAF_XOD_NUM; i++) { p[311 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_TSA_TC0_TC3_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_TSA_TC0_TC3_CFG_0_REG + i * 0x90); p[319 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_TSA_TC4_TC7_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_TSA_TC4_TC7_CFG_0_REG + i * 0x90); p[327 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_BW_TC0_TC3_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_BW_TC0_TC3_CFG_0_REG + i * 0x90); p[335 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_BW_TC4_TC7_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_BW_TC4_TC7_CFG_0_REG + i * 0x90); p[343 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_BW_OFFSET_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_BW_OFFSET_CFG_0_REG + i * 0x90); p[351 + i] = dsaf_read_dev(ddev, - DSAF_XOD_ETS_TOKEN_CFG_0_REG + j * 0x90); + DSAF_XOD_ETS_TOKEN_CFG_0_REG + i * 0x90); } p[359] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_0_0_REG + port * 0x90); From 8d71397bd2021f8ef68ae34d8bea431cc903fcdd Mon Sep 17 00:00:00 2001 From: Qianqian Xie Date: Thu, 24 Mar 2016 19:08:01 +0800 Subject: [PATCH 030/196] net: hns: optimizate fmt of snprintf() It misses string format in function snprintf(), as below: snprintf(buff, ETH_GSTRING_LEN, g_gmac_stats_string[i].desc); It needs to add "%s" to fix it as below: snprintf(buff, ETH_GSTRING_LEN, "%s", g_gmac_stats_string[i].desc); Signed-off-by: Qianqian Xie Signed-off-by: Kejian Yan Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 6e2b76ede075..44abb08de155 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -664,7 +664,8 @@ static void hns_gmac_get_strings(u32 stringset, u8 *data) return; for (i = 0; i < ARRAY_SIZE(g_gmac_stats_string); i++) { - snprintf(buff, ETH_GSTRING_LEN, g_gmac_stats_string[i].desc); + snprintf(buff, ETH_GSTRING_LEN, "%s", + g_gmac_stats_string[i].desc); buff = buff + ETH_GSTRING_LEN; } } From 055a94177dfa0bcbf2c4be475fef56bc80c9a233 Mon Sep 17 00:00:00 2001 From: Qianqian Xie Date: Thu, 24 Mar 2016 19:08:02 +0800 Subject: [PATCH 031/196] net: hns: bug fix for return values The return values in the first two functions mdiobus_write() are ignored. The patch will fix it. Signed-off-by: Qianqian Xie Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 9c3ba65988e1..0e7da3f0a564 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -1013,8 +1013,8 @@ int hns_phy_led_set(struct net_device *netdev, int value) struct phy_device *phy_dev = priv->phy; retval = phy_write(phy_dev, HNS_PHY_PAGE_REG, HNS_PHY_PAGE_LED); - retval = phy_write(phy_dev, HNS_LED_FC_REG, value); - retval = phy_write(phy_dev, HNS_PHY_PAGE_REG, HNS_PHY_PAGE_COPPER); + retval |= phy_write(phy_dev, HNS_LED_FC_REG, value); + retval |= phy_write(phy_dev, HNS_PHY_PAGE_REG, HNS_PHY_PAGE_COPPER); if (retval) { netdev_err(netdev, "mdiobus_write fail !\n"); return retval; From 1c3bae6e475fed5c570ac16fef2afe743c477886 Mon Sep 17 00:00:00 2001 From: Qianqian Xie Date: Thu, 24 Mar 2016 19:08:03 +0800 Subject: [PATCH 032/196] net: hns: remove useless variable assignment and comment The variable head in hns_nic_tx_fini_pro has read a value, but it is obviously no use. The patch will fix it. And the comment is nothing to do with the routine, so it has to be removed Signed-off-by: Qianqian Xie Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 71aa37b4b338..f0c9a41a7443 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -913,10 +913,7 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; - int head = ring->next_to_clean; - - /* for hardware bug fixed */ - head = readl_relaxed(ring->io_base + RCB_REG_HEAD); + int head = readl_relaxed(ring->io_base + RCB_REG_HEAD); if (head != ring->next_to_clean) { ring_data->ring->q->handle->dev->ops->toggle_ring_irq( From 4b34aa412c1213912608742b4d016f616b23d9e2 Mon Sep 17 00:00:00 2001 From: Sheng Li Date: Thu, 24 Mar 2016 19:08:04 +0800 Subject: [PATCH 033/196] net: hns: optimizate irq proccess for HNS V2 In hns V1, common_poll should check and clean fbd pkts, because it can not pend irq to clean them if there is no new pkt comes in. But hns V2 hw fixes this bug, and will pend irq itself to do this. So, for hns V2, we set ring_data->fini_process to NULL. Signed-off-by: Sheng Li Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index f0c9a41a7443..66d1652ffbed 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -956,8 +956,8 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget) napi_complete(napi); ring_data->ring->q->handle->dev->ops->toggle_ring_irq( ring_data->ring, 0); - - ring_data->fini_process(ring_data); + if (ring_data->fini_process) + ring_data->fini_process(ring_data); return 0; } @@ -1720,6 +1720,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) { struct hnae_handle *h = priv->ae_handle; struct hns_nic_ring_data *rd; + bool is_ver1 = AE_IS_VER1(priv->enet_ver); int i; if (h->q_num > NIC_MAX_Q_PER_VF) { @@ -1737,7 +1738,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) rd->queue_index = i; rd->ring = &h->qs[i]->tx_ring; rd->poll_one = hns_nic_tx_poll_one; - rd->fini_process = hns_nic_tx_fini_pro; + rd->fini_process = is_ver1 ? hns_nic_tx_fini_pro : NULL; netif_napi_add(priv->netdev, &rd->napi, hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM); @@ -1749,7 +1750,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) rd->ring = &h->qs[i - h->q_num]->rx_ring; rd->poll_one = hns_nic_rx_poll_one; rd->ex_process = hns_nic_rx_up_pro; - rd->fini_process = hns_nic_rx_fini_pro; + rd->fini_process = is_ver1 ? hns_nic_rx_fini_pro : NULL; netif_napi_add(priv->netdev, &rd->napi, hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM); From daa8cfd9da728b9e35c49311b23127a8859a5f3b Mon Sep 17 00:00:00 2001 From: Kejian Yan Date: Thu, 24 Mar 2016 19:08:05 +0800 Subject: [PATCH 034/196] net: hns: fix warning of passing zero to 'PTR_ERR' There is a misuse of PTR as shown below: ae_node = (void *)of_parse_phandle(dev->of_node, "ae-handle", 0); if (IS_ERR_OR_NULL(ae_node)) { ret = PTR_ERR(ae_node); dev_err(dev, "not find ae-handle\n"); goto out_read_prop_fail; } if the ae_node is NULL, PTR_ERR(ae_node) means it returns success. And the return value should be -ENODEV. Signed-off-by: Kejian Yan Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 66d1652ffbed..687204b780b0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1814,7 +1814,7 @@ static int hns_nic_try_get_ae(struct net_device *ndev) h = hnae_get_handle(&priv->netdev->dev, priv->ae_node, priv->port_id, NULL); if (IS_ERR_OR_NULL(h)) { - ret = PTR_ERR(h); + ret = -ENODEV; dev_dbg(priv->dev, "has not handle, register notifier!\n"); goto out; } From c1203fe7bb34e2fe7d281882bcce8b6f107df038 Mon Sep 17 00:00:00 2001 From: Sheng Li Date: Thu, 24 Mar 2016 19:08:06 +0800 Subject: [PATCH 035/196] net: hns: bug fix about getting hilink status for HNS v2 The hilink status reg in HNS V2 is different from HNS v1. In HNS V2, It distinguishes differnt lane status according to the bit-field of the reg. As is shown below: [0:0] ---> lane0 [1:1] ---> lane1 ... But the current driver reads the reg to get the hilink status ONLY concidering HNS V1 situation. Here is a patch to support both of them. Signed-off-by: Sheng Li Signed-off-by: Daode Huang Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns/hns_dsaf_misc.c | 44 ++++++++++--------- .../net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 2 + 2 files changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 607c3be42241..e69b02287c44 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -244,31 +244,35 @@ void hns_ppe_com_srst(struct ppe_common_cb *ppe_common, u32 val) */ phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb) { - u32 hilink3_mode; - u32 hilink4_mode; + u32 mode; + u32 reg; + u32 shift; + bool is_ver1 = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver); void __iomem *sys_ctl_vaddr = mac_cb->sys_ctl_vaddr; - int dev_id = mac_cb->mac_id; + int mac_id = mac_cb->mac_id; phy_interface_t phy_if = PHY_INTERFACE_MODE_NA; - hilink3_mode = dsaf_read_reg(sys_ctl_vaddr, HNS_MAC_HILINK3_REG); - hilink4_mode = dsaf_read_reg(sys_ctl_vaddr, HNS_MAC_HILINK4_REG); - if (dev_id >= 0 && dev_id <= 3) { - if (hilink4_mode == 0) - phy_if = PHY_INTERFACE_MODE_SGMII; - else - phy_if = PHY_INTERFACE_MODE_XGMII; - } else if (dev_id >= 4 && dev_id <= 5) { - if (hilink3_mode == 0) - phy_if = PHY_INTERFACE_MODE_SGMII; - else - phy_if = PHY_INTERFACE_MODE_XGMII; - } else { + if (is_ver1 && (mac_id >= 6 && mac_id <= 7)) { phy_if = PHY_INTERFACE_MODE_SGMII; + } else if (mac_id >= 0 && mac_id <= 3) { + reg = is_ver1 ? HNS_MAC_HILINK4_REG : HNS_MAC_HILINK4V2_REG; + mode = dsaf_read_reg(sys_ctl_vaddr, reg); + /* mac_id 0, 1, 2, 3 ---> hilink4 lane 0, 1, 2, 3 */ + shift = is_ver1 ? 0 : mac_id; + if (dsaf_get_bit(mode, shift)) + phy_if = PHY_INTERFACE_MODE_XGMII; + else + phy_if = PHY_INTERFACE_MODE_SGMII; + } else if (mac_id >= 4 && mac_id <= 7) { + reg = is_ver1 ? HNS_MAC_HILINK3_REG : HNS_MAC_HILINK3V2_REG; + mode = dsaf_read_reg(sys_ctl_vaddr, reg); + /* mac_id 4, 5, 6, 7 ---> hilink3 lane 2, 3, 0, 1 */ + shift = is_ver1 ? 0 : mac_id <= 5 ? mac_id - 2 : mac_id - 6; + if (dsaf_get_bit(mode, shift)) + phy_if = PHY_INTERFACE_MODE_XGMII; + else + phy_if = PHY_INTERFACE_MODE_SGMII; } - - dev_dbg(mac_cb->dev, - "hilink3_mode=%d, hilink4_mode=%d dev_id=%d, phy_if=%d\n", - hilink3_mode, hilink4_mode, dev_id, phy_if); return phy_if; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index bf62687e5ea7..e2206f938a9c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -103,6 +103,8 @@ /*serdes offset**/ #define HNS_MAC_HILINK3_REG DSAF_SUB_SC_HILINK3_CRG_CTRL0_REG #define HNS_MAC_HILINK4_REG DSAF_SUB_SC_HILINK4_CRG_CTRL0_REG +#define HNS_MAC_HILINK3V2_REG DSAF_SUB_SC_HILINK3_CRG_CTRL1_REG +#define HNS_MAC_HILINK4V2_REG DSAF_SUB_SC_HILINK4_CRG_CTRL1_REG #define HNS_MAC_LANE0_CTLEDFE_REG 0x000BFFCCULL #define HNS_MAC_LANE1_CTLEDFE_REG 0x000BFFBCULL #define HNS_MAC_LANE2_CTLEDFE_REG 0x000BFFACULL From ba5049945421b8d2f3e2af786a15d13b82316503 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Thu, 24 Mar 2016 15:40:04 +0100 Subject: [PATCH 036/196] net: macb: replace macb_writel() call by queue_writel() to update queue ISR macb_interrupt() should not use macb_writel(bp, ISR, ) but only queue_writel(queue, ISR, ). There is one IRQ and one set of {ISR, IER, IDR, IMR} [1] registers per queue on gem hardware, though only queue0 is actually used for now to receive frames: other queues can already be used to transmit frames. The queue_readl() and queue_writel() helper macros are designed to access the relevant IRQ registers. [1] ISR: Interrupt Status Register IER: Interrupt Enable Register IDR: Interrupt Disable Register IMR: Interrupt Mask Register Signed-off-by: Cyrille Pitchen Fixes: bfbb92c44670 ("net: macb: Handle the RXUBR interrupt on all devices") Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 6619178ed77b..f715352a9b85 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -1100,7 +1100,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) macb_writel(bp, NCR, ctrl | MACB_BIT(RE)); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) - macb_writel(bp, ISR, MACB_BIT(RXUBR)); + queue_writel(queue, ISR, MACB_BIT(RXUBR)); } if (status & MACB_BIT(ISR_ROVR)) { From 3e347660488818070bff7533f8561928e09e1d65 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 24 Mar 2016 16:50:00 +0100 Subject: [PATCH 037/196] switchdev: fix typo in comments/doc Two minor typo. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 2 +- net/switchdev/switchdev.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index fad63136ee3e..2f659129694b 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -386,7 +386,7 @@ used. First phase is to "prepare" anything needed, including various checks, memory allocation, etc. The goal is to handle the stuff that is not unlikely to fail here. The second phase is to "commit" the actual changes. -Switchdev provides an inftrastructure for sharing items (for example memory +Switchdev provides an infrastructure for sharing items (for example memory allocations) between the two phases. The object created by a driver in "prepare" phase and it is queued up by: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 8b5833c1ff2e..2b9b98f1c2ff 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1079,7 +1079,7 @@ nla_put_failure: * @filter_dev: filter device * @idx: * - * Delete FDB entry from switch device. + * Dump FDB entries from switch device. */ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, From 55868120a3e5420bf5aa26a816c07d691579c9e6 Mon Sep 17 00:00:00 2001 From: Petri Gynther Date: Thu, 24 Mar 2016 11:27:20 -0700 Subject: [PATCH 038/196] net: bcmgenet: fix dev->stats.tx_bytes accounting 1. Add bytes_compl local variable to __bcmgenet_tx_reclaim() to collect transmitted bytes. dev->stats updates can then be moved outside the while-loop. bytes_compl is also needed for future BQL support. 2. When bcmgenet device uses Tx checksum offload, each transmitted skb gets an extra 64-byte header prepended to it. Before this header is prepended to the skb, we need to save the skb "wire" length in GENET_CB(skb)->bytes_sent, so that proper Tx bytes accounting can be done in __bcmgenet_tx_reclaim(). 3. skb->len covers the entire length of skb, whether it is linear or fragmented. Thus, when we clean the fragments, do not increase transmitted bytes. Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Petri Gynther Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 14 ++++++++++---- drivers/net/ethernet/broadcom/genet/bcmgenet.h | 6 ++++++ 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 6746fd03cb3a..c1c7c0e6fb7c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1171,6 +1171,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned int pkts_compl = 0; + unsigned int bytes_compl = 0; unsigned int c_index; unsigned int txbds_ready; unsigned int txbds_processed = 0; @@ -1193,16 +1194,13 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, tx_cb_ptr = &priv->tx_cbs[ring->clean_ptr]; if (tx_cb_ptr->skb) { pkts_compl++; - dev->stats.tx_packets++; - dev->stats.tx_bytes += tx_cb_ptr->skb->len; + bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; dma_unmap_single(&dev->dev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); bcmgenet_free_cb(tx_cb_ptr); } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dev->stats.tx_bytes += - dma_unmap_len(tx_cb_ptr, dma_len); dma_unmap_page(&dev->dev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), @@ -1220,6 +1218,9 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, ring->free_bds += txbds_processed; ring->c_index = (ring->c_index + txbds_processed) & DMA_C_INDEX_MASK; + dev->stats.tx_packets += pkts_compl; + dev->stats.tx_bytes += bytes_compl; + if (ring->free_bds > (MAX_SKB_FRAGS + 1)) { txq = netdev_get_tx_queue(dev, ring->queue); if (netif_tx_queue_stopped(txq)) @@ -1464,6 +1465,11 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } + /* Retain how many bytes will be sent on the wire, without TSB inserted + * by transmit checksum offload + */ + GENET_CB(skb)->bytes_sent = skb->len; + /* set the SKB transmit checksum */ if (priv->desc_64b_en) { skb = bcmgenet_put_tx_csum(dev, skb); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 967367557309..1e2dc34d331a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -531,6 +531,12 @@ struct bcmgenet_hw_params { u32 flags; }; +struct bcmgenet_skb_cb { + unsigned int bytes_sent; /* bytes on the wire (no TSB) */ +}; + +#define GENET_CB(skb) ((struct bcmgenet_skb_cb *)((skb)->cb)) + struct bcmgenet_tx_ring { spinlock_t lock; /* ring lock */ struct napi_struct napi; /* NAPI per tx queue */ From 7dd399130efb5a454daf24075b7563d197114e39 Mon Sep 17 00:00:00 2001 From: Petri Gynther Date: Thu, 24 Mar 2016 11:27:21 -0700 Subject: [PATCH 039/196] net: bcmgenet: fix skb_len in bcmgenet_xmit_single() skb_len needs to be skb_headlen(skb) in bcmgenet_xmit_single(). Fragmented skbs can have only Ethernet + IP + TCP headers (14+20+20=54 bytes) in the linear buffer, followed by the rest in fragments. Bumping skb_len to ETH_ZLEN would be incorrect for this case, as it would introduce garbage between TCP header and the fragment data. This also works with regular/non-fragmented small packets < ETH_ZLEN bytes. Successfully tested this on GENETv3 with 42-byte ARP frames. For testing, I used: ethtool -K eth0 tx-checksum-ipv4 off ethtool -K eth0 tx-checksum-ipv6 off echo 0 > /proc/sys/net/ipv4/tcp_timestamps Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Petri Gynther Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index c1c7c0e6fb7c..cf6445d148ca 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1297,7 +1297,7 @@ static int bcmgenet_xmit_single(struct net_device *dev, tx_cb_ptr->skb = skb; - skb_len = skb_headlen(skb) < ETH_ZLEN ? ETH_ZLEN : skb_headlen(skb); + skb_len = skb_headlen(skb); mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE); ret = dma_mapping_error(kdev, mapping); From a49ac9f83b31e41c8311d64bd2b3f97a23dcb38d Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Fri, 25 Mar 2016 11:18:25 +0800 Subject: [PATCH 040/196] perf/x86: Move events_sysfs_show() outside CPU_SUP_INTEL randconfig builds can sometimes disable CONFIG_CPU_SUP_INTEL while enabling the AMD power reporting PMU driver, resulting in this build failure: arch/x86/kernel/cpu/perf_event.h:663:31: error: 'events_sysfs_show' undeclared here (not in a function) To fix it, move events_sysfs_show() outside of #ifdef CONFIG_CPU_SUP_INTEL. Reported-by: Randy Dunlap Reported-by: build test robot Signed-off-by: Huang Rui Cc: Borislav Petkov Cc: Borislav Petkov Cc: Fengguang Wu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sherry Hurwitz Cc: Stephen Rothwell Cc: Thomas Gleixner Cc: acme@kernel.org Cc: kbuild-all@01.org Cc: linux-next@vger.kernel.org Cc: spg_linux_kernel@amd.com Link: http://lkml.kernel.org/r/1458875905-4278-1-git-send-email-ray.huang@amd.com Signed-off-by: Ingo Molnar --- arch/x86/events/perf_event.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ba6ef18528c9..a6771e2303d2 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -795,6 +795,9 @@ ssize_t intel_event_sysfs_show(char *page, u64 config); struct attribute **merge_attr(struct attribute **a, struct attribute **b); +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -925,9 +928,6 @@ int p6_pmu_init(void); int knc_pmu_init(void); -ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, - char *page); - static inline int is_ht_workaround_enabled(void) { return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED); From 4a8d224c32238bcee05aa554512ea0256b62f1f9 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 25 Mar 2016 12:27:42 +0100 Subject: [PATCH 041/196] drm/amd: Beef up ACP Kconfig menu text The current "text" needs a user to use a crystal ball in order to find out what this ACP thing is. Use the text from a8fe58cec351 ("drm/amd: add ACP driver support") to make it a bit more understandable to the rest of the world. Signed-off-by: Borislav Petkov Cc: Alex Deucher Cc: Chunming Zhou Cc: Jammy Zhou Cc: Maruthi Bayyavarapu Cc: Murali Krishna Vemuri Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/acp/Kconfig | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/acp/Kconfig b/drivers/gpu/drm/amd/acp/Kconfig index 0f734ee05274..ca77ec10147c 100644 --- a/drivers/gpu/drm/amd/acp/Kconfig +++ b/drivers/gpu/drm/amd/acp/Kconfig @@ -1,10 +1,14 @@ -menu "ACP Configuration" +menu "ACP (Audio CoProcessor) Configuration" config DRM_AMD_ACP - bool "Enable ACP IP support" + bool "Enable AMD Audio CoProcessor IP support" select MFD_CORE select PM_GENERIC_DOMAINS if PM help Choose this option to enable ACP IP support for AMD SOCs. + This adds the ACP (Audio CoProcessor) IP driver and wires + it up into the amdgpu driver. The ACP block provides the DMA + engine for the i2s-based ALSA driver. It is required for audio + on APUs which utilize an i2s codec. endmenu From f971f2263deaa4a441e377b385c11aee0f3b3f9a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 25 Mar 2016 10:31:04 -0400 Subject: [PATCH 042/196] drm/radeon: add a dpm quirk for sapphire Dual-X R7 370 2G D5 bug: https://bugs.freedesktop.org/show_bug.cgi?id=94692 Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/si_dpm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index cb75ab72098a..d153b09ac880 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2926,6 +2926,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { /* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */ { PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, From 543e3a8da5a4c453e992d5351ef405d5e32f27d7 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 24 Mar 2016 21:56:21 -0500 Subject: [PATCH 043/196] netpoll: Fix extra refcount release in netpoll_cleanup() netpoll_setup() does a dev_hold() on np->dev, the netpoll device. If it fails, it correctly does a dev_put() but leaves np->dev set. If we call netpoll_cleanup() after the failure, np->dev is still set so we do another dev_put(), which decrements the refcount an extra time. It's questionable to call netpoll_cleanup() after netpoll_setup() fails, but it can be difficult to find the problem, and we can easily avoid it in this case. The extra decrements can lead to hangs like this: unregister_netdevice: waiting for bond0 to become free. Usage count = -3 Set and clear np->dev at the points where we dev_hold() and dev_put() the device. Signed-off-by: Bjorn Helgaas Signed-off-by: David S. Miller --- net/core/netpoll.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 94acfc89ad97..a57bd17805b4 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -603,7 +603,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; - np->dev = ndev; strlcpy(np->dev_name, ndev->name, IFNAMSIZ); INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); @@ -670,6 +669,7 @@ int netpoll_setup(struct netpoll *np) goto unlock; } dev_hold(ndev); + np->dev = ndev; if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); @@ -770,6 +770,7 @@ int netpoll_setup(struct netpoll *np) return 0; put: + np->dev = NULL; dev_put(ndev); unlock: rtnl_unlock(); From 322cea2f41adb62c975f46a3242f4e3b43226fa1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 25 Mar 2016 00:30:25 +0100 Subject: [PATCH 044/196] bpf: add missing map_flags to bpf_map_show_fdinfo Add map_flags attribute to bpf_map_show_fdinfo(), so that tools like tc can check for them when loading objects from a pinned entry, e.g. if user intent wrt allocation (BPF_F_NO_PREALLOC) is different to the pinned object, it can bail out. Follow-up to 6c9059817432 ("bpf: pre-allocate hash map elements"), so that tc can still support this with v4.6. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2a2efe1bc76c..adc5e4bd74f8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -137,11 +137,13 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" - "max_entries:\t%u\n", + "max_entries:\t%u\n" + "map_flags:\t%#x\n", map->map_type, map->key_size, map->value_size, - map->max_entries); + map->max_entries, + map->map_flags); } #endif From 4cef191d05871fbc8bb3b812880e1997e855a3b9 Mon Sep 17 00:00:00 2001 From: Jaedon Shin Date: Fri, 25 Mar 2016 12:46:54 +0900 Subject: [PATCH 045/196] net: phy: bcm7xxx: Add entries for Broadcom BCM7346 and BCM7362 Add PHY entries for the Broadcom BCM7346 and BCM7362 chips, these are 40nm generation Ethernet PHY. Fixes: 815717d1473e ("net: phy: bcm7xxx: Remove wildcard entries") Signed-off-by: Jaedon Shin Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 4 ++++ include/linux/brcmphy.h | 2 ++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index b881a7b1e4f6..9636da0b6efc 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -339,6 +339,8 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"), + BCM7XXX_40NM_EPHY(PHY_ID_BCM7346, "Broadcom BCM7346"), + BCM7XXX_40NM_EPHY(PHY_ID_BCM7362, "Broadcom BCM7362"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7429, "Broadcom BCM7429"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7435, "Broadcom BCM7435"), @@ -348,6 +350,8 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7250, 0xfffffff0, }, { PHY_ID_BCM7364, 0xfffffff0, }, { PHY_ID_BCM7366, 0xfffffff0, }, + { PHY_ID_BCM7346, 0xfffffff0, }, + { PHY_ID_BCM7362, 0xfffffff0, }, { PHY_ID_BCM7425, 0xfffffff0, }, { PHY_ID_BCM7429, 0xfffffff0, }, { PHY_ID_BCM7439, 0xfffffff0, }, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index f0ba9c2ec639..e3354b74286c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -24,6 +24,8 @@ #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7364 0xae025260 #define PHY_ID_BCM7366 0x600d8490 +#define PHY_ID_BCM7346 0x600d8650 +#define PHY_ID_BCM7362 0x600d84b0 #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 #define PHY_ID_BCM7435 0x600d8750 From d31fecd1af991e39cbe27a59f290cdcefb7ba6ae Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Fri, 25 Mar 2016 07:14:09 -0400 Subject: [PATCH 046/196] qlge: Update version to 1.00.00.35 Just updating version as many fixes got accumulated over 1.00.00.34 Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlge/qlge.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index ef332708e5f2..6d31f92ef2b6 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -18,7 +18,7 @@ */ #define DRV_NAME "qlge" #define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "1.00.00.34" +#define DRV_VERSION "1.00.00.35" #define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ From 9ba723b081a2d1be81fb6f60f912bd94fa744965 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Fri, 25 Mar 2016 10:37:34 +0100 Subject: [PATCH 047/196] net: macb: remove BUG_ON() and reset the queue to handle RX errors This patch removes two BUG_ON() used to notify about RX queue corruptions on macb (not gem) hardware without actually handling the error. The new code skips corrupted frames but still processes faultless frames. Then it resets the RX queue before restarting the reception from a clean state. This patch is a rework of an older patch proposed by Neil Armstrong: http://patchwork.ozlabs.org/patch/371525/ Signed-off-by: Cyrille Pitchen Acked-by: Neil Armstrong Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 59 ++++++++++++++++++++++++----- 1 file changed, 49 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index f715352a9b85..6c3dc27cb100 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -917,7 +917,10 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag, unsigned int frag_len = bp->rx_buffer_size; if (offset + frag_len > len) { - BUG_ON(frag != last_frag); + if (unlikely(frag != last_frag)) { + dev_kfree_skb_any(skb); + return -1; + } frag_len = len - offset; } skb_copy_to_linear_data_offset(skb, offset, @@ -945,8 +948,23 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag, return 0; } +static inline void macb_init_rx_ring(struct macb *bp) +{ + dma_addr_t addr; + int i; + + addr = bp->rx_buffers_dma; + for (i = 0; i < RX_RING_SIZE; i++) { + bp->rx_ring[i].addr = addr; + bp->rx_ring[i].ctrl = 0; + addr += bp->rx_buffer_size; + } + bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP); +} + static int macb_rx(struct macb *bp, int budget) { + bool reset_rx_queue = false; int received = 0; unsigned int tail; int first_frag = -1; @@ -972,10 +990,18 @@ static int macb_rx(struct macb *bp, int budget) if (ctrl & MACB_BIT(RX_EOF)) { int dropped; - BUG_ON(first_frag == -1); + + if (unlikely(first_frag == -1)) { + reset_rx_queue = true; + continue; + } dropped = macb_rx_frame(bp, first_frag, tail); first_frag = -1; + if (unlikely(dropped < 0)) { + reset_rx_queue = true; + continue; + } if (!dropped) { received++; budget--; @@ -983,6 +1009,26 @@ static int macb_rx(struct macb *bp, int budget) } } + if (unlikely(reset_rx_queue)) { + unsigned long flags; + u32 ctrl; + + netdev_err(bp->dev, "RX queue corruption: reset it\n"); + + spin_lock_irqsave(&bp->lock, flags); + + ctrl = macb_readl(bp, NCR); + macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE)); + + macb_init_rx_ring(bp); + macb_writel(bp, RBQP, bp->rx_ring_dma); + + macb_writel(bp, NCR, ctrl | MACB_BIT(RE)); + + spin_unlock_irqrestore(&bp->lock, flags); + return received; + } + if (first_frag != -1) bp->rx_tail = first_frag; else @@ -1523,15 +1569,8 @@ static void gem_init_rings(struct macb *bp) static void macb_init_rings(struct macb *bp) { int i; - dma_addr_t addr; - addr = bp->rx_buffers_dma; - for (i = 0; i < RX_RING_SIZE; i++) { - bp->rx_ring[i].addr = addr; - bp->rx_ring[i].ctrl = 0; - addr += bp->rx_buffer_size; - } - bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP); + macb_init_rx_ring(bp); for (i = 0; i < TX_RING_SIZE; i++) { bp->queues[0].tx_ring[i].addr = 0; From 96c22a3293512ba684e73a981196430f524689da Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Wed, 23 Mar 2016 14:14:48 +0200 Subject: [PATCH 048/196] configfs: fix CONFIGFS_BIN_ATTR_[RW]O definitions The type should be struct configfs_bin_attribute and not struct configfs_attribute. Signed-off-by: Octavian Purdila Signed-off-by: Christoph Hellwig --- include/linux/configfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 485fe5519448..d9d6a9d77489 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -188,7 +188,7 @@ static struct configfs_bin_attribute _pfx##attr_##_name = { \ } #define CONFIGFS_BIN_ATTR_RO(_pfx, _name, _priv, _maxsz) \ -static struct configfs_attribute _pfx##attr_##_name = { \ +static struct configfs_bin_attribute _pfx##attr_##_name = { \ .cb_attr = { \ .ca_name = __stringify(_name), \ .ca_mode = S_IRUGO, \ @@ -200,7 +200,7 @@ static struct configfs_attribute _pfx##attr_##_name = { \ } #define CONFIGFS_BIN_ATTR_WO(_pfx, _name, _priv, _maxsz) \ -static struct configfs_attribute _pfx##attr_##_name = { \ +static struct configfs_bin_attribute _pfx##attr_##_name = { \ .cb_attr = { \ .ca_name = __stringify(_name), \ .ca_mode = S_IWUSR, \ From a21211672c9a1d730a39aa65d4a5b3414700adfb Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 23 Mar 2016 21:07:39 -0700 Subject: [PATCH 049/196] ACPI / processor: Request native thermal interrupt handling via _OSC There are several reports of freeze on enabling HWP (Hardware PStates) feature on Skylake-based systems by the Intel P-states driver. The root cause is identified as the HWP interrupts causing BIOS code to freeze. HWP interrupts use the thermal LVT which can be handled by Linux natively, but on the affected Skylake-based systems SMM will respond to it by default. This is a problem for several reasons: - On the affected systems the SMM thermal LVT handler is broken (it will crash when invoked) and a BIOS update is necessary to fix it. - With thermal interrupt handled in SMM we lose all of the reporting features of the arch/x86/kernel/cpu/mcheck/therm_throt driver. - Some thermal drivers like x86-package-temp depend on the thermal threshold interrupts signaled via the thermal LVT. - The HWP interrupts are useful for debugging and tuning performance (if the kernel can handle them). The native handling of thermal interrupts needs to be enabled because of that. This requires some way to tell SMM that the OS can handle thermal interrupts. That can be done by using _OSC/_PDC in processor scope very early during ACPI initialization. The meaning of _OSC/_PDC bit 12 in processor scope is whether or not the OS supports native handling of interrupts for Collaborative Processor Performance Control (CPPC) notifications. Since on HWP-capable systems CPPC is a firmware interface to HWP, setting this bit effectively tells the firmware that the OS will handle thermal interrupts natively going forward. For details on _OSC/_PDC refer to: http://www.intel.com/content/www/us/en/standards/processor-vendor-specific-acpi-specification.html To implement the _OSC/_PDC handshake as described, introduce a new function, acpi_early_processor_osc(), that walks the ACPI namespace looking for ACPI processor objects and invokes _OSC for them with bit 12 in the capabilities buffer set and terminates the namespace walk on the first success. Also modify intel_thermal_interrupt() to clear HWP status bits in the HWP_STATUS MSR to acknowledge HWP interrupts (which prevents them from firing continuously). Signed-off-by: Srinivas Pandruvada [ rjw: Subject & changelog, function rename ] Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 3 ++ drivers/acpi/acpi_processor.c | 52 ++++++++++++++++++++++++ drivers/acpi/bus.c | 3 ++ drivers/acpi/internal.h | 6 +++ 4 files changed, 64 insertions(+) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8c2e2f..05538582a809 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void) { __u64 msr_val; + if (static_cpu_has(X86_FEATURE_HWP)) + wrmsrl_safe(MSR_HWP_STATUS, 0); + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); /* Check for violation of core thermal thresholds*/ diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index b5e54f2da53d..0d92d0f915e9 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -491,6 +491,58 @@ static void acpi_processor_remove(struct acpi_device *device) } #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_X86 +static bool acpi_hwp_native_thermal_lvt_set; +static acpi_status __init acpi_hwp_native_thermal_lvt_osc(acpi_handle handle, + u32 lvl, + void *context, + void **rv) +{ + u8 sb_uuid_str[] = "4077A616-290C-47BE-9EBD-D87058713953"; + u32 capbuf[2]; + struct acpi_osc_context osc_context = { + .uuid_str = sb_uuid_str, + .rev = 1, + .cap.length = 8, + .cap.pointer = capbuf, + }; + + if (acpi_hwp_native_thermal_lvt_set) + return AE_CTRL_TERMINATE; + + capbuf[0] = 0x0000; + capbuf[1] = 0x1000; /* set bit 12 */ + + if (ACPI_SUCCESS(acpi_run_osc(handle, &osc_context))) { + if (osc_context.ret.pointer && osc_context.ret.length > 1) { + u32 *capbuf_ret = osc_context.ret.pointer; + + if (capbuf_ret[1] & 0x1000) { + acpi_handle_info(handle, + "_OSC native thermal LVT Acked\n"); + acpi_hwp_native_thermal_lvt_set = true; + } + } + kfree(osc_context.ret.pointer); + } + + return AE_OK; +} + +void __init acpi_early_processor_osc(void) +{ + if (boot_cpu_has(X86_FEATURE_HWP)) { + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL, NULL); + acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL); + } +} +#endif + /* * The following ACPI IDs are known to be suitable for representing as * processor devices. diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 891c42d1cd65..f9081b791b81 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1005,6 +1005,9 @@ static int __init acpi_bus_init(void) goto error1; } + /* Set capability bits for _OSC under processor scope */ + acpi_early_processor_osc(); + /* * _OSC method may exist in module level code, * so it must be run after ACPI_FULL_INITIALIZATION diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 1e6833a5cd44..6f41c73f82bb 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -138,6 +138,12 @@ void acpi_early_processor_set_pdc(void); static inline void acpi_early_processor_set_pdc(void) {} #endif +#ifdef CONFIG_X86 +void acpi_early_processor_osc(void); +#else +static inline void acpi_early_processor_osc(void) {} +#endif + /* -------------------------------------------------------------------------- Embedded Controller -------------------------------------------------------------------------- */ From 3c2e2266a5bd2d1cef258e6e54dca1d99946379f Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 26 Mar 2016 12:28:05 -0700 Subject: [PATCH 050/196] hwmon: (max1111) Return -ENODEV from max1111_read_channel if not instantiated arm:pxa_defconfig can result in the following crash if the max1111 driver is not instantiated. Unhandled fault: page domain fault (0x01b) at 0x00000000 pgd = c0004000 [00000000] *pgd=00000000 Internal error: : 1b [#1] PREEMPT ARM Modules linked in: CPU: 0 PID: 300 Comm: kworker/0:1 Not tainted 4.5.0-01301-g1701f680407c #10 Hardware name: SHARP Akita Workqueue: events sharpsl_charge_toggle task: c390a000 ti: c391e000 task.ti: c391e000 PC is at max1111_read_channel+0x20/0x30 LR is at sharpsl_pm_pxa_read_max1111+0x2c/0x3c pc : [] lr : [] psr: 20000013 ... [] (max1111_read_channel) from [] (sharpsl_pm_pxa_read_max1111+0x2c/0x3c) [] (sharpsl_pm_pxa_read_max1111) from [] (spitzpm_read_devdata+0x5c/0xc4) [] (spitzpm_read_devdata) from [] (sharpsl_check_battery_temp+0x78/0x110) [] (sharpsl_check_battery_temp) from [] (sharpsl_charge_toggle+0x48/0x110) [] (sharpsl_charge_toggle) from [] (process_one_work+0x14c/0x48c) [] (process_one_work) from [] (worker_thread+0x3c/0x5d4) [] (worker_thread) from [] (kthread+0xd0/0xec) [] (kthread) from [] (ret_from_fork+0x14/0x24) This can occur because the SPI controller driver (SPI_PXA2XX) is built as module and thus not necessarily loaded. While building SPI_PXA2XX into the kernel would make the problem disappear, it appears prudent to ensure that the driver is instantiated before accessing its data structures. Cc: Arnd Bergmann Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck --- drivers/hwmon/max1111.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c index 36544c4f653c..303d0c9df907 100644 --- a/drivers/hwmon/max1111.c +++ b/drivers/hwmon/max1111.c @@ -85,6 +85,9 @@ static struct max1111_data *the_max1111; int max1111_read_channel(int channel) { + if (!the_max1111 || !the_max1111->spi) + return -ENODEV; + return max1111_read(&the_max1111->spi->dev, channel); } EXPORT_SYMBOL(max1111_read_channel); @@ -258,6 +261,9 @@ static int max1111_remove(struct spi_device *spi) { struct max1111_data *data = spi_get_drvdata(spi); +#ifdef CONFIG_SHARPSL_PM + the_max1111 = NULL; +#endif hwmon_device_unregister(data->hwmon_dev); sysfs_remove_group(&spi->dev.kobj, &max1110_attr_group); sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group); From a69f0e281d9eb08eb277be051f920ea863e258e2 Mon Sep 17 00:00:00 2001 From: Diego Viola Date: Sun, 27 Mar 2016 20:58:15 -0300 Subject: [PATCH 051/196] drivers/net/usb/plusb.c: Fix typo Signed-off-by: Diego Viola Signed-off-by: David S. Miller --- drivers/net/usb/plusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 1bfe0fcaccf5..22e1a9a99a7d 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -38,7 +38,7 @@ * HEADS UP: this handshaking isn't all that robust. This driver * gets confused easily if you unplug one end of the cable then * try to connect it again; you'll need to restart both ends. The - * "naplink" software (used by some PlayStation/2 deveopers) does + * "naplink" software (used by some PlayStation/2 developers) does * the handshaking much better! Also, sometimes this hardware * seems to get wedged under load. Prolific docs are weak, and * don't identify differences between PL2301 and PL2302, much less From 995096a0a438396a570104e9c240a2a26623a5a1 Mon Sep 17 00:00:00 2001 From: Quentin Armitage Date: Sun, 27 Mar 2016 17:06:11 +0100 Subject: [PATCH 052/196] Fix returned tc and hoplimit values for route with IPv6 encapsulation For a route with IPv6 encapsulation, the traffic class and hop limit values are interchanged when returned to userspace by the kernel. For example, see below. ># ip route add 192.168.0.1 dev eth0.2 encap ip6 dst 0x50 tc 0x50 hoplimit 100 table 1000 ># ip route show table 1000 192.168.0.1 encap ip6 id 0 src :: dst fe83::1 hoplimit 80 tc 100 dev eth0.2 scope link Signed-off-by: Quentin Armitage Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 02dd990af542..6165f30c4d72 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -372,8 +372,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || - nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || - nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || + nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; From 66391b383b70920629df403f2881ea48805e6659 Mon Sep 17 00:00:00 2001 From: Cosmin-Gabriel Samoila Date: Sat, 26 Mar 2016 02:49:50 +0200 Subject: [PATCH 053/196] Drivers: isdn: hisax: isac.c: Fix assignment and check into one expression. Fix variable assignment inside if statement. It is error-prone and hard to read. Signed-off-by: Cosmin-Gabriel Samoila Signed-off-by: David S. Miller --- drivers/isdn/hisax/isac.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c index 7fdf78f46433..df7e05ca8f9c 100644 --- a/drivers/isdn/hisax/isac.c +++ b/drivers/isdn/hisax/isac.c @@ -215,9 +215,11 @@ isac_interrupt(struct IsdnCardState *cs, u_char val) if (count == 0) count = 32; isac_empty_fifo(cs, count); - if ((count = cs->rcvidx) > 0) { + count = cs->rcvidx; + if (count > 0) { cs->rcvidx = 0; - if (!(skb = alloc_skb(count, GFP_ATOMIC))) + skb = alloc_skb(count, GFP_ATOMIC); + if (!skb) printk(KERN_WARNING "HiSax: D receive out of memory\n"); else { memcpy(skb_put(skb, count), cs->rcvbuf, count); @@ -251,7 +253,8 @@ isac_interrupt(struct IsdnCardState *cs, u_char val) cs->tx_skb = NULL; } } - if ((cs->tx_skb = skb_dequeue(&cs->sq))) { + cs->tx_skb = skb_dequeue(&cs->sq); + if (cs->tx_skb) { cs->tx_cnt = 0; isac_fill_fifo(cs); } else @@ -313,7 +316,8 @@ afterXPR: #if ARCOFI_USE if (v1 & 0x08) { if (!cs->dc.isac.mon_rx) { - if (!(cs->dc.isac.mon_rx = kmalloc(MAX_MON_FRAME, GFP_ATOMIC))) { + cs->dc.isac.mon_rx = kmalloc(MAX_MON_FRAME, GFP_ATOMIC); + if (!cs->dc.isac.mon_rx) { if (cs->debug & L1_DEB_WARN) debugl1(cs, "ISAC MON RX out of memory!"); cs->dc.isac.mocr &= 0xf0; @@ -343,7 +347,8 @@ afterXPR: afterMONR0: if (v1 & 0x80) { if (!cs->dc.isac.mon_rx) { - if (!(cs->dc.isac.mon_rx = kmalloc(MAX_MON_FRAME, GFP_ATOMIC))) { + cs->dc.isac.mon_rx = kmalloc(MAX_MON_FRAME, GFP_ATOMIC); + if (!cs->dc.isac.mon_rx) { if (cs->debug & L1_DEB_WARN) debugl1(cs, "ISAC MON RX out of memory!"); cs->dc.isac.mocr &= 0x0f; From 79c134239df989167acd277364b83ff9e91e70c4 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Sat, 26 Mar 2016 22:24:09 +0100 Subject: [PATCH 054/196] net: sxgbe: fix error paths in sxgbe_platform_probe() We need to use post-decrement to ensure that irq_dispose_mapping is also called on priv->rxq[0]->irq_no; moreover, if one of the above for loops failed already at i==0 (so we reach one of these labels with that value of i), we'll enter an essentially infinite loop of out-of-bounds accesses. Signed-off-by: Rasmus Villemoes Reviewed-by: Francois Romieu Signed-off-by: David S. Miller --- drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c index b02eed12bfc5..73427e29df2a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c @@ -155,11 +155,11 @@ static int sxgbe_platform_probe(struct platform_device *pdev) return 0; err_rx_irq_unmap: - while (--i) + while (i--) irq_dispose_mapping(priv->rxq[i]->irq_no); i = SXGBE_TX_QUEUES; err_tx_irq_unmap: - while (--i) + while (i--) irq_dispose_mapping(priv->txq[i]->irq_no); irq_dispose_mapping(priv->irq); err_drv_remove: From d7be81a5916bdb1d904803958e5991a16f7ae4b2 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Sun, 27 Mar 2016 12:22:02 +0200 Subject: [PATCH 055/196] ravb: fix software timestamping In ravb_start_xmit dont call skb_tx_timestamp only when hardware timestamping is requested: in the latter case software timestamps are suppressed and thus the call of skb_tx_timestamp does not have any effect. Instead call skb_tx_timestamp unconditionally in ravb_start_xmit, since the function checks itself if software timestamping is required or should be skipped due to hardware timestamping. Signed-off-by: Lino Sanfilippo Acked-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 4e1a7dba7c4a..087e14a3fba7 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1377,11 +1377,11 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) /* TAG and timestamp required flag */ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - skb_tx_timestamp(skb); desc->tagh_tsr = (ts_skb->tag >> 4) | TX_TSR; desc->ds_tagl |= le16_to_cpu(ts_skb->tag << 12); } + skb_tx_timestamp(skb); /* Descriptor type must be set after all the above writes */ dma_wmb(); desc->die_dt = DT_FEND; From 92915da647be831ddbaa7e03e7528d921ec7f8aa Mon Sep 17 00:00:00 2001 From: John Keeping Date: Fri, 4 Mar 2016 11:04:03 +0000 Subject: [PATCH 056/196] drm/rockchip: vop: fix crtc size in plane check If the geometry of a crtc is changing in an atomic update then we must validate the plane size against the new state of the crtc and not the current size, otherwise if the crtc size is increasing the plane will be cropped at the previous size and will not fill the screen. Signed-off-by: John Keeping --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index fd370548d7d7..82d55bd8deb6 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -549,6 +549,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) { struct drm_crtc *crtc = state->crtc; + struct drm_crtc_state *crtc_state; struct drm_framebuffer *fb = state->fb; struct vop_win *vop_win = to_vop_win(plane); struct vop_plane_state *vop_plane_state = to_vop_plane_state(state); @@ -563,12 +564,13 @@ static int vop_plane_atomic_check(struct drm_plane *plane, int max_scale = win->phy->scl ? FRAC_16_16(8, 1) : DRM_PLANE_HELPER_NO_SCALING; - crtc = crtc ? crtc : plane->state->crtc; - /* - * Both crtc or plane->state->crtc can be null. - */ if (!crtc || !fb) goto out_disable; + + crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc); + if (WARN_ON(!crtc_state)) + return -EINVAL; + src->x1 = state->src_x; src->y1 = state->src_y; src->x2 = state->src_x + state->src_w; @@ -580,8 +582,8 @@ static int vop_plane_atomic_check(struct drm_plane *plane, clip.x1 = 0; clip.y1 = 0; - clip.x2 = crtc->mode.hdisplay; - clip.y2 = crtc->mode.vdisplay; + clip.x2 = crtc_state->adjusted_mode.hdisplay; + clip.y2 = crtc_state->adjusted_mode.vdisplay; ret = drm_plane_helper_check_update(plane, crtc, state->fb, src, dest, &clip, From f135046e519dc54a701110fa93a6d61c4989ed96 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Fri, 11 Mar 2016 17:21:17 +0000 Subject: [PATCH 057/196] drm/rockchip: cancel pending vblanks on close When closing the DRM device while a vblank is pending, we access file_priv after it has been free'd, which gives: Unable to handle kernel NULL pointer dereference at virtual address 00000000 ... PC is at __list_add+0x5c/0xe8 LR is at send_vblank_event+0x54/0x1f0 ... [] (__list_add) from [] (send_vblank_event+0x54/0x1f0) [] (send_vblank_event) from [] (drm_send_vblank_event+0x70/0x78) [] (drm_send_vblank_event) from [] (drm_crtc_send_vblank_event+0x30/0x34) [] (drm_crtc_send_vblank_event) from [] (vop_isr+0x224/0x28c) [] (vop_isr) from [] (handle_irq_event_percpu+0x12c/0x3e4) This can be triggered somewhat reliably with: modetest -M rockchip -v -s ... Add a preclose hook to the driver so that we can discard any pending vblank events when the device is closed. Signed-off-by: John Keeping --- drivers/gpu/drm/rockchip/rockchip_drm_drv.c | 22 +++++++++++++++++++++ drivers/gpu/drm/rockchip/rockchip_drm_drv.h | 1 + drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 20 +++++++++++++++++++ 3 files changed, 43 insertions(+) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 896da09e49ee..f556a8f4fde6 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -251,6 +251,27 @@ static int rockchip_drm_unload(struct drm_device *drm_dev) return 0; } +static void rockchip_drm_crtc_cancel_pending_vblank(struct drm_crtc *crtc, + struct drm_file *file_priv) +{ + struct rockchip_drm_private *priv = crtc->dev->dev_private; + int pipe = drm_crtc_index(crtc); + + if (pipe < ROCKCHIP_MAX_CRTC && + priv->crtc_funcs[pipe] && + priv->crtc_funcs[pipe]->cancel_pending_vblank) + priv->crtc_funcs[pipe]->cancel_pending_vblank(crtc, file_priv); +} + +static void rockchip_drm_preclose(struct drm_device *dev, + struct drm_file *file_priv) +{ + struct drm_crtc *crtc; + + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + rockchip_drm_crtc_cancel_pending_vblank(crtc, file_priv); +} + void rockchip_drm_lastclose(struct drm_device *dev) { struct rockchip_drm_private *priv = dev->dev_private; @@ -281,6 +302,7 @@ static struct drm_driver rockchip_drm_driver = { DRIVER_PRIME | DRIVER_ATOMIC, .load = rockchip_drm_load, .unload = rockchip_drm_unload, + .preclose = rockchip_drm_preclose, .lastclose = rockchip_drm_lastclose, .get_vblank_counter = drm_vblank_no_hw_counter, .enable_vblank = rockchip_drm_crtc_enable_vblank, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index 3529f692edb8..00d17d71aa4c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -40,6 +40,7 @@ struct rockchip_crtc_funcs { int (*enable_vblank)(struct drm_crtc *crtc); void (*disable_vblank)(struct drm_crtc *crtc); void (*wait_for_update)(struct drm_crtc *crtc); + void (*cancel_pending_vblank)(struct drm_crtc *crtc, struct drm_file *file_priv); }; struct rockchip_atomic_commit { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 82d55bd8deb6..44b2ba7b5cc9 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -875,10 +875,30 @@ static void vop_crtc_wait_for_update(struct drm_crtc *crtc) WARN_ON(!wait_for_completion_timeout(&vop->wait_update_complete, 100)); } +static void vop_crtc_cancel_pending_vblank(struct drm_crtc *crtc, + struct drm_file *file_priv) +{ + struct drm_device *drm = crtc->dev; + struct vop *vop = to_vop(crtc); + struct drm_pending_vblank_event *e; + unsigned long flags; + + spin_lock_irqsave(&drm->event_lock, flags); + e = vop->event; + if (e && e->base.file_priv == file_priv) { + vop->event = NULL; + + e->base.destroy(&e->base); + file_priv->event_space += sizeof(e->event); + } + spin_unlock_irqrestore(&drm->event_lock, flags); +} + static const struct rockchip_crtc_funcs private_crtc_funcs = { .enable_vblank = vop_crtc_enable_vblank, .disable_vblank = vop_crtc_disable_vblank, .wait_for_update = vop_crtc_wait_for_update, + .cancel_pending_vblank = vop_crtc_cancel_pending_vblank, }; static bool vop_crtc_mode_fixup(struct drm_crtc *crtc, From eac5ad8861639754a3976bfa1581a73e772624c6 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 18 Mar 2016 12:22:02 +0100 Subject: [PATCH 058/196] drm/rockchip: vop: Don't reject empty modesets So that when DRM_IOCTL_MODE_SETCRTC is called without a FB nor mode, the CRTC gets disabled. Signed-off-by: Tomeu Vizoso Link: http://lkml.kernel.org/g/CAAObsKAv+05ih5U+=4kic_NsjGMhfxYheHR8xXXmacZs+p5SHw@mail.gmail.com --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 44b2ba7b5cc9..c01a380e3bb9 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -907,9 +907,6 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc, { struct vop *vop = to_vop(crtc); - if (adjusted_mode->htotal == 0 || adjusted_mode->vtotal == 0) - return false; - adjusted_mode->clock = clk_round_rate(vop->dclk, mode->clock * 1000) / 1000; From 3ed6c64911f2335b271c21363b7834072fc03303 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Tue, 22 Mar 2016 16:08:04 +0100 Subject: [PATCH 059/196] drm/rockchip: vop: Disable planes when disabling CRTC When a VOP is re-enabled, it will start scanning right away the framebuffers that were configured from the last time, even if those have been destroyed already. To prevent the VOP from trying to access freed memory, disable all its windows when the CRTC is being disabled, then each window will get a valid framebuffer address before it's enabled again. Signed-off-by: Tomeu Vizoso Link: http://lkml.kernel.org/g/CAAObsKAv+05ih5U+=4kic_NsjGMhfxYheHR8xXXmacZs+p5SHw@mail.gmail.com --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index c01a380e3bb9..12854ac9d542 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -499,10 +499,25 @@ err_disable_hclk: static void vop_crtc_disable(struct drm_crtc *crtc) { struct vop *vop = to_vop(crtc); + int i; if (!vop->is_enabled) return; + /* + * We need to make sure that all windows are disabled before we + * disable that crtc. Otherwise we might try to scan from a destroyed + * buffer later. + */ + for (i = 0; i < vop->data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + const struct vop_win_data *win = vop_win->data; + + spin_lock(&vop->reg_lock); + VOP_WIN_SET(vop, win, enable, 0); + spin_unlock(&vop->reg_lock); + } + drm_crtc_vblank_off(crtc); /* From 948cf42700b15fc65ec4cc3ac52a8bbeb84b87ef Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 7 Mar 2016 14:00:50 -0800 Subject: [PATCH 060/196] drm/rockchip: dw_hdmi: Call drm_encoder_cleanup() in error path The drm_encoder_cleanup() was missing both from the error path of dw_hdmi_rockchip_bind(). This caused a crash when slub_debug was enabled and we ended up deferring probe of HDMI at boot. This call isn't needed from unbind() because if dw_hdmi_bind() returns no error then it takes over the job of freeing the encoder (in dw_hdmi_unbind). Signed-off-by: Douglas Anderson --- drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index 3d3cf2f8891e..88776aba984e 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -293,7 +293,16 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, drm_encoder_init(drm, encoder, &dw_hdmi_rockchip_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); - return dw_hdmi_bind(dev, master, data, encoder, iores, irq, plat_data); + ret = dw_hdmi_bind(dev, master, data, encoder, iores, irq, plat_data); + + /* + * If dw_hdmi_bind() fails we'll never call dw_hdmi_unbind(), + * which would have called the encoder cleanup. Do it manually. + */ + if (ret) + drm_encoder_cleanup(encoder); + + return ret; } static void dw_hdmi_rockchip_unbind(struct device *dev, struct device *master, From 328b51c0f5a07f3ee891ff012eb7f454be9d17c0 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 7 Mar 2016 14:00:52 -0800 Subject: [PATCH 061/196] drm/rockchip: vop: Fix vop crtc cleanup This fixes a few problems in the vop crtc cleanup (handling error paths and cleanup upon exit): * The vop_create_crtc() error path had an unsafe version of the iterator used for iterating over all planes (though it was destroying planes in the iterator so should have used the safe version) * vop_destroy_crtc() - wasn't calling vop_plane_destroy(), which made slub_debug unhappy, at least if we ended up running this due to a deferred probe. * In vop_create_crtc() if we were missing the "port" device tree node we would fail but not return an error (found by code inspection). Fix these problems. Signed-off-by: Douglas Anderson --- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 27 ++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 12854ac9d542..a619f120f801 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1142,7 +1142,7 @@ static int vop_create_crtc(struct vop *vop) const struct vop_data *vop_data = vop->data; struct device *dev = vop->dev; struct drm_device *drm_dev = vop->drm_dev; - struct drm_plane *primary = NULL, *cursor = NULL, *plane; + struct drm_plane *primary = NULL, *cursor = NULL, *plane, *tmp; struct drm_crtc *crtc = &vop->crtc; struct device_node *port; int ret; @@ -1182,7 +1182,7 @@ static int vop_create_crtc(struct vop *vop) ret = drm_crtc_init_with_planes(drm_dev, crtc, primary, cursor, &vop_crtc_funcs, NULL); if (ret) - return ret; + goto err_cleanup_planes; drm_crtc_helper_add(crtc, &vop_crtc_helper_funcs); @@ -1215,6 +1215,7 @@ static int vop_create_crtc(struct vop *vop) if (!port) { DRM_ERROR("no port node found in %s\n", dev->of_node->full_name); + ret = -ENOENT; goto err_cleanup_crtc; } @@ -1228,7 +1229,8 @@ static int vop_create_crtc(struct vop *vop) err_cleanup_crtc: drm_crtc_cleanup(crtc); err_cleanup_planes: - list_for_each_entry(plane, &drm_dev->mode_config.plane_list, head) + list_for_each_entry_safe(plane, tmp, &drm_dev->mode_config.plane_list, + head) drm_plane_cleanup(plane); return ret; } @@ -1236,9 +1238,28 @@ err_cleanup_planes: static void vop_destroy_crtc(struct vop *vop) { struct drm_crtc *crtc = &vop->crtc; + struct drm_device *drm_dev = vop->drm_dev; + struct drm_plane *plane, *tmp; rockchip_unregister_crtc_funcs(crtc); of_node_put(crtc->port); + + /* + * We need to cleanup the planes now. Why? + * + * The planes are "&vop->win[i].base". That means the memory is + * all part of the big "struct vop" chunk of memory. That memory + * was devm allocated and associated with this component. We need to + * free it ourselves before vop_unbind() finishes. + */ + list_for_each_entry_safe(plane, tmp, &drm_dev->mode_config.plane_list, + head) + vop_plane_destroy(plane); + + /* + * Destroy CRTC after vop_plane_destroy() since vop_disable_plane() + * references the CRTC. + */ drm_crtc_cleanup(crtc); } From 06b898ec84139b9d5957ec0e275fa0a6a1825df3 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 7 Mar 2016 14:00:53 -0800 Subject: [PATCH 062/196] drm/rockchip: dw_hdmi: Don't call platform_set_drvdata() The Rockchip dw_hdmi driver just called platform_set_drvdata() to get your hopes up that maybe, somehow, you'd be able to retrieve the 'struct rockchip_hdmi' from a pointer to the 'struct device'. You can't. When we call dw_hdmi_bind() the main driver calls dev_set_drvdata(), which clobbers our setting. Let's just remove the platform_set_drvdata() to avoid dashing people's hopes. Signed-off-by: Douglas Anderson --- drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index 88776aba984e..d5cfef75fc80 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -271,8 +271,6 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, if (!iores) return -ENXIO; - platform_set_drvdata(pdev, hdmi); - encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node); /* * If we failed to find the CRTC(s) which this encoder is From 6b94fb14fcff3d9be13aae271f2345ab3f656b0c Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 28 Mar 2016 08:29:32 +0900 Subject: [PATCH 063/196] ALSA: dice: fix memory leak when unplugging When sound card is going to be released, dice private data is also released. Then all of data should be released. However, stream data is not released. This causes memory leak when unplugging dice unit. This commit fixes the bug. Fixes: 4bdc495c87b3('ALSA: dice: handle several PCM substreams when any isochronous streams are available') Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/firewire/dice/dice-stream.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/sound/firewire/dice/dice-stream.c b/sound/firewire/dice/dice-stream.c index 845d5e5884a4..ec4db3a514fc 100644 --- a/sound/firewire/dice/dice-stream.c +++ b/sound/firewire/dice/dice-stream.c @@ -446,18 +446,12 @@ end: void snd_dice_stream_destroy_duplex(struct snd_dice *dice) { - struct reg_params tx_params, rx_params; + unsigned int i; - snd_dice_transaction_clear_enable(dice); - - if (get_register_params(dice, &tx_params, &rx_params) == 0) { - stop_streams(dice, AMDTP_IN_STREAM, &tx_params); - stop_streams(dice, AMDTP_OUT_STREAM, &rx_params); + for (i = 0; i < MAX_STREAMS; i++) { + destroy_stream(dice, AMDTP_IN_STREAM, i); + destroy_stream(dice, AMDTP_OUT_STREAM, i); } - - release_resources(dice); - - dice->substreams_counter = 0; } void snd_dice_stream_update_duplex(struct snd_dice *dice) From a64663d9870364bd2a2df62bf0d3a9fbe5ea62a8 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 28 Mar 2016 10:16:40 -0400 Subject: [PATCH 064/196] drm/radeon: add another R7 370 quirk bug: https://bugzilla.kernel.org/show_bug.cgi?id=115291 Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/si_dpm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index d153b09ac880..a280a3201832 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2930,6 +2930,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = { { PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 }, { PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 }, + { PCI_VENDOR_ID_ATI, 0x6811, 0x148c, 0x2015, 0, 120000 }, { 0, 0, 0, 0 }, }; From 0e5585dc870af947fab2af96a88c2d8b4270247c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 28 Mar 2016 10:21:20 -0400 Subject: [PATCH 065/196] drm/radeon: add a dpm quirk for all R7 370 parts Higher mclk values are not stable due to a bug somewhere. Limit them for now. Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/si_dpm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index a280a3201832..af4df81c4e0c 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -3010,6 +3010,10 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, } ++p; } + /* limit mclk on all R7 370 parts for stability */ + if (rdev->pdev->device == 0x6811 && + rdev->pdev->revision == 0x81) + max_mclk = 120000; if (rps->vce_active) { rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk; From ac71b46efd2838c02ec193987c8f61c3ba33b495 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Mon, 28 Mar 2016 18:08:59 +0800 Subject: [PATCH 066/196] openvswitch: Use proper buffer size in nla_memcpy For the input parameter count, it's better to use the size of destination buffer size, as nla_memcpy would take into account the length of the source netlink attribute when a data is copied from an attribute. Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- net/openvswitch/conntrack.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index dc5eb29fe7d6..f8a8d4390a8a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -968,7 +968,8 @@ static int parse_nat(const struct nlattr *attr, break; case OVS_NAT_ATTR_IP_MIN: - nla_memcpy(&info->range.min_addr, a, nla_len(a)); + nla_memcpy(&info->range.min_addr, a, + sizeof(info->range.min_addr)); info->range.flags |= NF_NAT_RANGE_MAP_IPS; break; From 43adc067c5a070a5ef97d0c25e33df19c4481484 Mon Sep 17 00:00:00 2001 From: Lisheng Date: Mon, 28 Mar 2016 18:40:56 +0800 Subject: [PATCH 067/196] net: hns: fixed the setting and getting overtime bug The overtime setting and getting REGs in HNS V2 is defferent from HNS V1. It needs to be distinguished between them if getting or setting the REGs. Signed-off-by: Lisheng Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- .../net/ethernet/hisilicon/hns/hns_ae_adapt.c | 60 ++---- .../net/ethernet/hisilicon/hns/hns_dsaf_rcb.c | 196 ++++++++---------- .../net/ethernet/hisilicon/hns/hns_dsaf_rcb.h | 23 +- .../net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 1 + 4 files changed, 126 insertions(+), 154 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 285c893ab135..1dd1d6974d47 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -159,11 +159,6 @@ struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, ae_handle->qs[i]->tx_ring.q = ae_handle->qs[i]; ring_pair_cb->used_by_vf = 1; - if (port_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) - ring_pair_cb->port_id_in_dsa = port_idx; - else - ring_pair_cb->port_id_in_dsa = 0; - ring_pair_cb++; } @@ -453,59 +448,46 @@ static int hns_ae_set_pauseparam(struct hnae_handle *handle, static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle, u32 *tx_usecs, u32 *rx_usecs) { - int port; + struct ring_pair_cb *ring_pair = + container_of(handle->qs[0], struct ring_pair_cb, q); - port = hns_ae_map_eport_to_dport(handle->eport_id); - - *tx_usecs = hns_rcb_get_coalesce_usecs( - hns_ae_get_dsaf_dev(handle->dev), - hns_dsaf_get_comm_idx_by_port(port)); - *rx_usecs = hns_rcb_get_coalesce_usecs( - hns_ae_get_dsaf_dev(handle->dev), - hns_dsaf_get_comm_idx_by_port(port)); + *tx_usecs = hns_rcb_get_coalesce_usecs(ring_pair->rcb_common, + ring_pair->port_id_in_comm); + *rx_usecs = hns_rcb_get_coalesce_usecs(ring_pair->rcb_common, + ring_pair->port_id_in_comm); } static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle, u32 *tx_frames, u32 *rx_frames) { - int port; + struct ring_pair_cb *ring_pair = + container_of(handle->qs[0], struct ring_pair_cb, q); - assert(handle); - - port = hns_ae_map_eport_to_dport(handle->eport_id); - - *tx_frames = hns_rcb_get_coalesced_frames( - hns_ae_get_dsaf_dev(handle->dev), port); - *rx_frames = hns_rcb_get_coalesced_frames( - hns_ae_get_dsaf_dev(handle->dev), port); + *tx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common, + ring_pair->port_id_in_comm); + *rx_frames = hns_rcb_get_coalesced_frames(ring_pair->rcb_common, + ring_pair->port_id_in_comm); } static void hns_ae_set_coalesce_usecs(struct hnae_handle *handle, u32 timeout) { - int port; + struct ring_pair_cb *ring_pair = + container_of(handle->qs[0], struct ring_pair_cb, q); - assert(handle); - - port = hns_ae_map_eport_to_dport(handle->eport_id); - - hns_rcb_set_coalesce_usecs(hns_ae_get_dsaf_dev(handle->dev), - port, timeout); + (void)hns_rcb_set_coalesce_usecs( + ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout); } static int hns_ae_set_coalesce_frames(struct hnae_handle *handle, u32 coalesce_frames) { - int port; - int ret; + struct ring_pair_cb *ring_pair = + container_of(handle->qs[0], struct ring_pair_cb, q); - assert(handle); - - port = hns_ae_map_eport_to_dport(handle->eport_id); - - ret = hns_rcb_set_coalesced_frames(hns_ae_get_dsaf_dev(handle->dev), - port, coalesce_frames); - return ret; + return hns_rcb_set_coalesced_frames( + ring_pair->rcb_common, + ring_pair->port_id_in_comm, coalesce_frames); } void hns_ae_update_stats(struct hnae_handle *handle, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 12188807468c..28ee26e5c478 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -215,9 +215,9 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG, bd_size_type); dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG, - ring_pair->port_id_in_dsa); + ring_pair->port_id_in_comm); dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG, - ring_pair->port_id_in_dsa); + ring_pair->port_id_in_comm); } else { dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_L_REG, (u32)dma); @@ -227,9 +227,9 @@ static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG, bd_size_type); dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG, - ring_pair->port_id_in_dsa); + ring_pair->port_id_in_comm); dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG, - ring_pair->port_id_in_dsa); + ring_pair->port_id_in_comm); } } @@ -256,50 +256,16 @@ static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common, desc_cnt); } -/** - *hns_rcb_set_port_coalesced_frames - set rcb port coalesced frames - *@rcb_common: rcb_common device - *@port_idx:port index - *@coalesced_frames:BD num for coalesced frames - */ -static int hns_rcb_set_port_coalesced_frames(struct rcb_common_cb *rcb_common, - u32 port_idx, - u32 coalesced_frames) +static void hns_rcb_set_port_timeout( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout) { - if (coalesced_frames >= rcb_common->desc_num || - coalesced_frames > HNS_RCB_MAX_COALESCED_FRAMES) - return -EINVAL; - - dsaf_write_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4, - coalesced_frames); - return 0; -} - -/** - *hns_rcb_get_port_coalesced_frames - set rcb port coalesced frames - *@rcb_common: rcb_common device - *@port_idx:port index - * return coaleseced frames value - */ -static u32 hns_rcb_get_port_coalesced_frames(struct rcb_common_cb *rcb_common, - u32 port_idx) -{ - if (port_idx >= HNS_RCB_SERVICE_NW_ENGINE_NUM) - port_idx = 0; - - return dsaf_read_dev(rcb_common, - RCB_CFG_PKTLINE_REG + port_idx * 4); -} - -/** - *hns_rcb_set_timeout - set rcb port coalesced time_out - *@rcb_common: rcb_common device - *@time_out:time for coalesced time_out - */ -static void hns_rcb_set_timeout(struct rcb_common_cb *rcb_common, - u32 timeout) -{ - dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG, timeout); + if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) + dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG, + timeout * HNS_RCB_CLK_FREQ_MHZ); + else + dsaf_write_dev(rcb_common, + RCB_PORT_CFG_OVERTIME_REG + port_idx * 4, + timeout); } static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common) @@ -361,10 +327,11 @@ int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common) for (i = 0; i < port_num; i++) { hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num); - (void)hns_rcb_set_port_coalesced_frames( - rcb_common, i, rcb_common->coalesced_frames); + (void)hns_rcb_set_coalesced_frames( + rcb_common, i, HNS_RCB_DEF_COALESCED_FRAMES); + hns_rcb_set_port_timeout( + rcb_common, i, HNS_RCB_DEF_COALESCED_USECS); } - hns_rcb_set_timeout(rcb_common, rcb_common->timeout); dsaf_write_dev(rcb_common, RCB_COM_CFG_ENDIAN_REG, HNS_RCB_COMMON_ENDIAN); @@ -460,7 +427,8 @@ static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb) hns_rcb_ring_get_cfg(&ring_pair_cb->q, TX_RING); } -static int hns_rcb_get_port(struct rcb_common_cb *rcb_common, int ring_idx) +static int hns_rcb_get_port_in_comm( + struct rcb_common_cb *rcb_common, int ring_idx) { int comm_index = rcb_common->comm_index; int port; @@ -470,7 +438,7 @@ static int hns_rcb_get_port(struct rcb_common_cb *rcb_common, int ring_idx) q_num = (int)rcb_common->max_q_per_vf * rcb_common->max_vfn; port = ring_idx / q_num; } else { - port = HNS_RCB_SERVICE_NW_ENGINE_NUM + comm_index - 1; + port = 0; /* config debug-ports port_id_in_comm to 0*/ } return port; @@ -518,7 +486,8 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common) ring_pair_cb->index = i; ring_pair_cb->q.io_base = RCB_COMM_BASE_TO_RING_BASE(rcb_common->io_base, i); - ring_pair_cb->port_id_in_dsa = hns_rcb_get_port(rcb_common, i); + ring_pair_cb->port_id_in_comm = + hns_rcb_get_port_in_comm(rcb_common, i); ring_pair_cb->virq[HNS_RCB_IRQ_IDX_TX] = is_ver1 ? irq_of_parse_and_map(np, base_irq_idx + i * 2) : platform_get_irq(pdev, base_irq_idx + i * 3 + 1); @@ -534,82 +503,95 @@ void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common) /** *hns_rcb_get_coalesced_frames - get rcb port coalesced frames *@rcb_common: rcb_common device - *@comm_index:port index - *return coalesced_frames + *@port_idx:port id in comm + * + *Returns: coalesced_frames */ -u32 hns_rcb_get_coalesced_frames(struct dsaf_device *dsaf_dev, int port) +u32 hns_rcb_get_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx) { - int comm_index = hns_dsaf_get_comm_idx_by_port(port); - struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; - - return hns_rcb_get_port_coalesced_frames(rcb_comm, port); + return dsaf_read_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4); } /** *hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out *@rcb_common: rcb_common device - *@comm_index:port index - *return time_out + *@port_idx:port id in comm + * + *Returns: time_out */ -u32 hns_rcb_get_coalesce_usecs(struct dsaf_device *dsaf_dev, int comm_index) +u32 hns_rcb_get_coalesce_usecs( + struct rcb_common_cb *rcb_common, u32 port_idx) { - struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; - - return rcb_comm->timeout; + if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) + return dsaf_read_dev(rcb_common, RCB_CFG_OVERTIME_REG) / + HNS_RCB_CLK_FREQ_MHZ; + else + return dsaf_read_dev(rcb_common, + RCB_PORT_CFG_OVERTIME_REG + port_idx * 4); } /** *hns_rcb_set_coalesce_usecs - set rcb port coalesced time_out *@rcb_common: rcb_common device - *@comm_index: comm :index - *@etx_usecs:tx time for coalesced time_out - *@rx_usecs:rx time for coalesced time_out + *@port_idx:port id in comm + *@timeout:tx/rx time for coalesced time_out + * + * Returns: + * Zero for success, or an error code in case of failure */ -void hns_rcb_set_coalesce_usecs(struct dsaf_device *dsaf_dev, - int port, u32 timeout) +int hns_rcb_set_coalesce_usecs( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout) { - int comm_index = hns_dsaf_get_comm_idx_by_port(port); - struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; + u32 old_timeout = hns_rcb_get_coalesce_usecs(rcb_common, port_idx); - if (rcb_comm->timeout == timeout) - return; + if (timeout == old_timeout) + return 0; - if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { - dev_err(dsaf_dev->dev, - "error: not support coalesce_usecs setting!\n"); - return; + if (AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) { + if (rcb_common->comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + dev_err(rcb_common->dsaf_dev->dev, + "error: not support coalesce_usecs setting!\n"); + return -EINVAL; + } } - rcb_comm->timeout = timeout; - hns_rcb_set_timeout(rcb_comm, rcb_comm->timeout); + if (timeout > HNS_RCB_MAX_COALESCED_USECS) { + dev_err(rcb_common->dsaf_dev->dev, + "error: not support coalesce %dus!\n", timeout); + return -EINVAL; + } + hns_rcb_set_port_timeout(rcb_common, port_idx, timeout); + return 0; } /** *hns_rcb_set_coalesced_frames - set rcb coalesced frames *@rcb_common: rcb_common device - *@tx_frames:tx BD num for coalesced frames - *@rx_frames:rx BD num for coalesced frames - *Return 0 on success, negative on failure + *@port_idx:port id in comm + *@coalesced_frames:tx/rx BD num for coalesced frames + * + * Returns: + * Zero for success, or an error code in case of failure */ -int hns_rcb_set_coalesced_frames(struct dsaf_device *dsaf_dev, - int port, u32 coalesced_frames) +int hns_rcb_set_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames) { - int comm_index = hns_dsaf_get_comm_idx_by_port(port); - struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; - u32 coalesced_reg_val; - int ret; + u32 old_waterline = hns_rcb_get_coalesced_frames(rcb_common, port_idx); - coalesced_reg_val = hns_rcb_get_port_coalesced_frames(rcb_comm, port); - - if (coalesced_reg_val == coalesced_frames) + if (coalesced_frames == old_waterline) return 0; - if (coalesced_frames >= HNS_RCB_MIN_COALESCED_FRAMES) { - ret = hns_rcb_set_port_coalesced_frames(rcb_comm, port, - coalesced_frames); - return ret; - } else { + if (coalesced_frames >= rcb_common->desc_num || + coalesced_frames > HNS_RCB_MAX_COALESCED_FRAMES || + coalesced_frames < HNS_RCB_MIN_COALESCED_FRAMES) { + dev_err(rcb_common->dsaf_dev->dev, + "error: not support coalesce_frames setting!\n"); return -EINVAL; } + + dsaf_write_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4, + coalesced_frames); + return 0; } /** @@ -749,8 +731,6 @@ int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, rcb_common->dsaf_dev = dsaf_dev; rcb_common->desc_num = dsaf_dev->desc_num; - rcb_common->coalesced_frames = HNS_RCB_DEF_COALESCED_FRAMES; - rcb_common->timeout = HNS_RCB_MAX_TIME_OUT; hns_rcb_get_queue_mode(dsaf_mode, comm_index, &max_vfn, &max_q_per_vf); rcb_common->max_vfn = max_vfn; @@ -951,6 +931,10 @@ void hns_rcb_get_strings(int stringset, u8 *data, int index) void hns_rcb_get_common_regs(struct rcb_common_cb *rcb_com, void *data) { u32 *regs = data; + bool is_ver1 = AE_IS_VER1(rcb_com->dsaf_dev->dsaf_ver); + bool is_dbg = (rcb_com->comm_index != HNS_DSAF_COMM_SERVICE_NW_IDX); + u32 reg_tmp; + u32 reg_num_tmp; u32 i = 0; /*rcb common registers */ @@ -1004,12 +988,16 @@ void hns_rcb_get_common_regs(struct rcb_common_cb *rcb_com, void *data) = dsaf_read_dev(rcb_com, RCB_CFG_PKTLINE_REG + 4 * i); } - regs[70] = dsaf_read_dev(rcb_com, RCB_CFG_OVERTIME_REG); - regs[71] = dsaf_read_dev(rcb_com, RCB_CFG_PKTLINE_INT_NUM_REG); - regs[72] = dsaf_read_dev(rcb_com, RCB_CFG_OVERTIME_INT_NUM_REG); + reg_tmp = is_ver1 ? RCB_CFG_OVERTIME_REG : RCB_PORT_CFG_OVERTIME_REG; + reg_num_tmp = (is_ver1 || is_dbg) ? 1 : 6; + for (i = 0; i < reg_num_tmp; i++) + regs[70 + i] = dsaf_read_dev(rcb_com, reg_tmp); + + regs[76] = dsaf_read_dev(rcb_com, RCB_CFG_PKTLINE_INT_NUM_REG); + regs[77] = dsaf_read_dev(rcb_com, RCB_CFG_OVERTIME_INT_NUM_REG); /* mark end of rcb common regs */ - for (i = 73; i < 80; i++) + for (i = 78; i < 80; i++) regs[i] = 0xcccccccc; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 81fe9f849973..eb61014ad615 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -38,7 +38,9 @@ struct rcb_common_cb; #define HNS_RCB_MAX_COALESCED_FRAMES 1023 #define HNS_RCB_MIN_COALESCED_FRAMES 1 #define HNS_RCB_DEF_COALESCED_FRAMES 50 -#define HNS_RCB_MAX_TIME_OUT 0x500 +#define HNS_RCB_CLK_FREQ_MHZ 350 +#define HNS_RCB_MAX_COALESCED_USECS 0x3ff +#define HNS_RCB_DEF_COALESCED_USECS 3 #define HNS_RCB_COMMON_ENDIAN 1 @@ -82,7 +84,7 @@ struct ring_pair_cb { int virq[HNS_RCB_IRQ_NUM_PER_QUEUE]; - u8 port_id_in_dsa; + u8 port_id_in_comm; u8 used_by_vf; struct hns_ring_hw_stats hw_stats; @@ -97,8 +99,6 @@ struct rcb_common_cb { u8 comm_index; u32 ring_num; - u32 coalesced_frames; /* frames threshold of rx interrupt */ - u32 timeout; /* time threshold of rx interrupt */ u32 desc_num; /* desc num per queue*/ struct ring_pair_cb ring_pair_cb[0]; @@ -125,13 +125,14 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag); void hns_rcb_init_hw(struct ring_pair_cb *ring); void hns_rcb_reset_ring_hw(struct hnae_queue *q); void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag); - -u32 hns_rcb_get_coalesced_frames(struct dsaf_device *dsaf_dev, int comm_index); -u32 hns_rcb_get_coalesce_usecs(struct dsaf_device *dsaf_dev, int comm_index); -void hns_rcb_set_coalesce_usecs(struct dsaf_device *dsaf_dev, - int comm_index, u32 timeout); -int hns_rcb_set_coalesced_frames(struct dsaf_device *dsaf_dev, - int comm_index, u32 coalesce_frames); +u32 hns_rcb_get_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx); +u32 hns_rcb_get_coalesce_usecs( + struct rcb_common_cb *rcb_common, u32 port_idx); +int hns_rcb_set_coalesce_usecs( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 timeout); +int hns_rcb_set_coalesced_frames( + struct rcb_common_cb *rcb_common, u32 port_idx, u32 coalesced_frames); void hns_rcb_update_stats(struct hnae_queue *queue); void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index e2206f938a9c..7d7204f45e78 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -406,6 +406,7 @@ #define RCB_CFG_OVERTIME_REG 0x9300 #define RCB_CFG_PKTLINE_INT_NUM_REG 0x9304 #define RCB_CFG_OVERTIME_INT_NUM_REG 0x9308 +#define RCB_PORT_CFG_OVERTIME_REG 0x9430 #define RCB_RING_RX_RING_BASEADDR_L_REG 0x00000 #define RCB_RING_RX_RING_BASEADDR_H_REG 0x00004 From 9832ce4c0bb90e4dcedf4280947341b1eb6728e6 Mon Sep 17 00:00:00 2001 From: Lisheng Date: Mon, 28 Mar 2016 18:40:57 +0800 Subject: [PATCH 068/196] net: hns: set-coalesce-usecs returns errno by dsaf.ko It may fail to set coalesce usecs to HW, and Ethtool needs to know if it is successful to cfg the parameter or not. So it needs return the errno by dsaf.ko. Signed-off-by: Lisheng Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hnae.h | 2 +- drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 6 +++--- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 6 ++++-- 3 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 37d0cce392be..e8d36aaea223 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -469,7 +469,7 @@ struct hnae_ae_ops { u32 *tx_usecs, u32 *rx_usecs); void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle, u32 *tx_frames, u32 *rx_frames); - void (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout); + int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout); int (*set_coalesce_frames)(struct hnae_handle *handle, u32 coalesce_frames); void (*set_promisc_mode)(struct hnae_handle *handle, u32 en); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 1dd1d6974d47..a1cb461ac45f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -469,13 +469,13 @@ static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle, ring_pair->port_id_in_comm); } -static void hns_ae_set_coalesce_usecs(struct hnae_handle *handle, - u32 timeout) +static int hns_ae_set_coalesce_usecs(struct hnae_handle *handle, + u32 timeout) { struct ring_pair_cb *ring_pair = container_of(handle->qs[0], struct ring_pair_cb, q); - (void)hns_rcb_set_coalesce_usecs( + return hns_rcb_set_coalesce_usecs( ring_pair->rcb_common, ring_pair->port_id_in_comm, timeout); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 0e7da3f0a564..3d746c887873 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -794,8 +794,10 @@ static int hns_set_coalesce(struct net_device *net_dev, (!ops->set_coalesce_frames)) return -ESRCH; - ops->set_coalesce_usecs(priv->ae_handle, - ec->rx_coalesce_usecs); + ret = ops->set_coalesce_usecs(priv->ae_handle, + ec->rx_coalesce_usecs); + if (ret) + return ret; ret = ops->set_coalesce_frames( priv->ae_handle, From 0e3e7999703e7df93a9deee8ba89b604c5fd662d Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 28 Mar 2016 13:47:42 +0100 Subject: [PATCH 069/196] net: macb: Only call GPIO functions if there is a valid GPIO GPIOlib will print warning messages if we call GPIO functions without a valid GPIO. Change the code to avoid doing so. Signed-off-by: Charles Keepax Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 6c3dc27cb100..48a7d7dee846 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2996,9 +2996,10 @@ static int macb_probe(struct platform_device *pdev) phy_node = of_get_next_available_child(np, NULL); if (phy_node) { int gpio = of_get_named_gpio(phy_node, "reset-gpios", 0); - if (gpio_is_valid(gpio)) + if (gpio_is_valid(gpio)) { bp->reset_gpio = gpio_to_desc(gpio); - gpiod_direction_output(bp->reset_gpio, 1); + gpiod_direction_output(bp->reset_gpio, 1); + } } of_node_put(phy_node); @@ -3068,7 +3069,8 @@ static int macb_remove(struct platform_device *pdev) mdiobus_free(bp->mii_bus); /* Shutdown the PHY if there is a GPIO reset */ - gpiod_set_value(bp->reset_gpio, 0); + if (bp->reset_gpio) + gpiod_set_value(bp->reset_gpio, 0); unregister_netdev(dev); clk_disable_unprepare(bp->tx_clk); From e1a575ada8d2a3c3f107fdd12ac9215f983a7c80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Mon, 28 Mar 2016 16:39:14 +0900 Subject: [PATCH 070/196] drm/radeon: Don't move pinned BOs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The purpose of pinning is to prevent a buffer from moving. Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_object.c | 4 ++++ drivers/gpu/drm/radeon/radeon_ttm.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index dd46c38676db..2d901bf28a94 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -799,6 +799,10 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) if ((offset + size) <= rdev->mc.visible_vram_size) return 0; + /* Can't move a pinned BO to visible VRAM */ + if (rbo->pin_count > 0) + return -EINVAL; + /* hurrah the memory is not visible ! */ radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM); lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e06ac546a90f..636c1cf7d106 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -397,9 +397,15 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) { struct radeon_device *rdev; + struct radeon_bo *rbo; struct ttm_mem_reg *old_mem = &bo->mem; int r; + /* Can't move a pinned BO */ + rbo = container_of(bo, struct radeon_bo, tbo); + if (WARN_ON_ONCE(rbo->pin_count > 0)) + return -EINVAL; + rdev = radeon_get_rdev(bo->bdev); if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) { radeon_move_null(bo, new_mem); From 104ece975746d94b8276cd7f38d6b5c056d700b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Mon, 28 Mar 2016 12:53:02 +0900 Subject: [PATCH 071/196] drm/amdgpu: Don't move pinned BOs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The purpose of pinning is to prevent a buffer from moving. Reviewed-by: Christian König Tested-by: Rex Zhu Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 151a2d42c639..56d1458393cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -608,6 +608,10 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) if ((offset + size) <= adev->mc.visible_vram_size) return 0; + /* Can't move a pinned BO to visible VRAM */ + if (abo->pin_count > 0) + return -EINVAL; + /* hurrah the memory is not visible ! */ amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM); lpfn = adev->mc.visible_vram_size >> PAGE_SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 0f42b1a24446..9d3341dbeb04 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -384,9 +384,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) { struct amdgpu_device *adev; + struct amdgpu_bo *abo; struct ttm_mem_reg *old_mem = &bo->mem; int r; + /* Can't move a pinned BO */ + abo = container_of(bo, struct amdgpu_bo, tbo); + if (WARN_ON_ONCE(abo->pin_count > 0)) + return -EINVAL; + adev = amdgpu_get_adev(bo->bdev); if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) { amdgpu_move_null(bo, new_mem); From 596cf3fe5854fe2b1703b0466ed6bf9cfb83c91e Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Wed, 16 Mar 2016 21:49:00 +0100 Subject: [PATCH 072/196] netfilter: ipset: fix race condition in ipset save, swap and delete This fix adds a new reference counter (ref_netlink) for the struct ip_set. The other reference counter (ref) can be swapped out by ip_set_swap and we need a separate counter to keep track of references for netlink events like dump. Using the same ref counter for dump causes a race condition which can be demonstrated by the following script: ipset create hash_ip1 hash:ip family inet hashsize 1024 maxelem 500000 \ counters ipset create hash_ip2 hash:ip family inet hashsize 300000 maxelem 500000 \ counters ipset create hash_ip3 hash:ip family inet hashsize 1024 maxelem 500000 \ counters ipset save & ipset swap hash_ip3 hash_ip2 ipset destroy hash_ip3 /* will crash the machine */ Swap will exchange the values of ref so destroy will see ref = 0 instead of ref = 1. With this fix in place swap will not succeed because ipset save still has ref_netlink on the set (ip_set_swap doesn't swap ref_netlink). Both delete and swap will error out if ref_netlink != 0 on the set. Note: The changes to *_head functions is because previously we would increment ref whenever we called these functions, we don't do that anymore. Reviewed-by: Joshua Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 +++ net/netfilter/ipset/ip_set_bitmap_gen.h | 2 +- net/netfilter/ipset/ip_set_core.c | 33 +++++++++++++++++++++---- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- net/netfilter/ipset/ip_set_list_set.c | 2 +- 5 files changed, 35 insertions(+), 8 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0e1f433cc4b7..f48b8a664b0f 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -234,6 +234,10 @@ struct ip_set { spinlock_t lock; /* References to the set */ u32 ref; + /* References to the set for netlink events like dump, + * ref can be swapped out by ip_set_swap + */ + u32 ref_netlink; /* The core set type */ struct ip_set_type *type; /* The type variant doing the real job */ diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index b0bc475f641e..2e8e7e5fb4a6 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -95,7 +95,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (!nested) goto nla_put_failure; if (mtype_do_head(skb, map) || - nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7e6568cad494..a748b0c2c981 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -497,6 +497,26 @@ __ip_set_put(struct ip_set *set) write_unlock_bh(&ip_set_ref_lock); } +/* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need + * a separate reference counter + */ +static inline void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + +static inline void +__ip_set_put_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + BUG_ON(set->ref_netlink == 0); + set->ref_netlink--; + write_unlock_bh(&ip_set_ref_lock); +} + /* Add, del and test set entries from kernel. * * The set behind the index must exist and must be referenced @@ -1002,7 +1022,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); - if (s && s->ref) { + if (s && (s->ref || s->ref_netlink)) { ret = -IPSET_ERR_BUSY; goto out; } @@ -1024,7 +1044,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (!s) { ret = -ENOENT; goto out; - } else if (s->ref) { + } else if (s->ref || s->ref_netlink) { ret = -IPSET_ERR_BUSY; goto out; } @@ -1171,6 +1191,9 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; + if (from->ref_netlink || to->ref_netlink) + return -EBUSY; + strncpy(from_name, from->name, IPSET_MAXNAMELEN); strncpy(from->name, to->name, IPSET_MAXNAMELEN); strncpy(to->name, from_name, IPSET_MAXNAMELEN); @@ -1206,7 +1229,7 @@ ip_set_dump_done(struct netlink_callback *cb) if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); - __ip_set_put_byindex(inst, index); + __ip_set_put_netlink(set); } return 0; } @@ -1328,7 +1351,7 @@ dump_last: if (!cb->args[IPSET_CB_ARG0]) { /* Start listing: make sure set won't be destroyed */ pr_debug("reference set\n"); - set->ref++; + set->ref_netlink++; } write_unlock_bh(&ip_set_ref_lock); nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, @@ -1396,7 +1419,7 @@ release_refcount: if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); - __ip_set_put_byindex(inst, index); + __ip_set_put_netlink(set); cb->args[IPSET_CB_ARG0] = 0; } out: diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index e5336ab36d67..d32fd6b036bf 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -1082,7 +1082,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif - if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 24c6c1962aea..a2a89e4e0a14 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -458,7 +458,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb) if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || - nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || + nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(sizeof(*map) + n * set->dsize))) goto nla_put_failure; From 5745b0be05a0f8ccbc92a36b69f3a6bc58e91954 Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Mon, 21 Mar 2016 11:15:19 -0700 Subject: [PATCH 073/196] openvswitch: Fix checking for new expected connections. OVS should call into CT NAT for packets of new expected connections only when the conntrack state is persisted with the 'commit' option to the OVS CT action. The test for this condition is doubly wrong, as the CT status field is ANDed with the bit number (IPS_EXPECTED_BIT) rather than the mask (IPS_EXPECTED), and due to the wrong assumption that the expected bit would apply only for the first (i.e., 'new') packet of a connection, while in fact the expected bit remains on for the lifetime of an expected connection. The 'ctinfo' value IP_CT_RELATED derived from the ct status can be used instead, as it is only ever applicable to the 'new' packets of the expected connection. Fixes: 05752523e565 ('openvswitch: Interface with NAT.') Reported-by: Dan Carpenter Signed-off-by: Jarno Rajahalme Signed-off-by: Pablo Neira Ayuso --- net/openvswitch/conntrack.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index dc5eb29fe7d6..47f7c62761d2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -664,11 +664,12 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, /* Determine NAT type. * Check if the NAT type can be deduced from the tracked connection. - * Make sure expected traffic is NATted only when committing. + * Make sure new expected connections (IP_CT_RELATED) are NATted only + * when committing. */ if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK && - (!(ct->status & IPS_EXPECTED_BIT) || info->commit)) { + (ctinfo != IP_CT_RELATED || info->commit)) { /* NAT an established or related connection like before. */ if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) /* This is the REPLY direction for a connection From 99b7248e2ad57ca93ada10c6598affb267ffc99a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 18 Mar 2016 14:33:45 +0100 Subject: [PATCH 074/196] openvswitch: call only into reachable nf-nat code The openvswitch code has gained support for calling into the nf-nat-ipv4/ipv6 modules, however those can be loadable modules in a configuration in which openvswitch is built-in, leading to link errors: net/built-in.o: In function `__ovs_ct_lookup': :(.text+0x2cc2c8): undefined reference to `nf_nat_icmp_reply_translation' :(.text+0x2cc66c): undefined reference to `nf_nat_icmpv6_reply_translation' The dependency on (!NF_NAT || NF_NAT) prevents similar issues, but NF_NAT is set to 'y' if any of the symbols selecting it are built-in, but the link error happens when any of them are modular. A second issue is that even if CONFIG_NF_NAT_IPV6 is built-in, CONFIG_NF_NAT_IPV4 might be completely disabled. This is unlikely to be useful in practice, but the driver currently only handles IPv6 being optional. This patch improves the Kconfig dependency so that openvswitch cannot be built-in if either of the two other symbols are set to 'm', and it replaces the incorrect #ifdef in ovs_ct_nat_execute() with two "if (IS_ENABLED())" checks that should catch all corner cases also make the code more readable. The same #ifdef exists ovs_ct_nat_to_attr(), where it does not cause a link error, but for consistency I'm changing it the same way. Signed-off-by: Arnd Bergmann Fixes: 05752523e565 ("openvswitch: Interface with NAT.") Acked-by: Joe Stringer Signed-off-by: Pablo Neira Ayuso --- net/openvswitch/Kconfig | 4 +++- net/openvswitch/conntrack.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 234a73344c6e..ce947292ae77 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -7,7 +7,9 @@ config OPENVSWITCH depends on INET depends on !NF_CONNTRACK || \ (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ - (!NF_NAT || NF_NAT))) + (!NF_NAT || NF_NAT) && \ + (!NF_NAT_IPV4 || NF_NAT_IPV4) && \ + (!NF_NAT_IPV6 || NF_NAT_IPV6))) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 47f7c62761d2..3797879b0bf8 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -535,14 +535,15 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto push; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + skb->protocol == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -557,7 +558,6 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, err = NF_DROP; goto push; } -#endif } /* Non-ICMP, fall thru to initialize if needed. */ case IP_CT_NEW: @@ -1239,7 +1239,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, } if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { - if (info->family == NFPROTO_IPV4) { + if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || (info->range.max_addr.ip @@ -1247,8 +1248,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; -#if IS_ENABLED(CONFIG_NF_NAT_IPV6) - } else if (info->family == NFPROTO_IPV6) { + } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || (memcmp(&info->range.max_addr.in6, @@ -1257,7 +1258,6 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX, &info->range.max_addr.in6)))) return false; -#endif } else { return false; } From bdf533de6968e9686df777dc178486f600c6e617 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Mar 2016 18:02:49 +0100 Subject: [PATCH 075/196] netfilter: x_tables: validate e->target_offset early We should check that e->target_offset is sane before mark_source_chains gets called since it will fetch the target entry for loop detection. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 17 ++++++++--------- net/ipv4/netfilter/ip_tables.c | 17 ++++++++--------- net/ipv6/netfilter/ip6_tables.c | 17 ++++++++--------- 3 files changed, 24 insertions(+), 27 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index bf081927e06b..830bbe8ec13d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -474,14 +474,12 @@ next: return 1; } -static inline int check_entry(const struct arpt_entry *e, const char *name) +static inline int check_entry(const struct arpt_entry *e) { const struct xt_entry_target *t; - if (!arp_checkentry(&e->arp)) { - duprintf("arp_tables: arp check failed %p %s.\n", e, name); + if (!arp_checkentry(&e->arp)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -522,10 +520,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) struct xt_target *target; int ret; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -576,6 +570,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { @@ -590,6 +585,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -1246,7 +1245,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct arpt_entry *)e, name); + ret = check_entry((struct arpt_entry *)e); if (ret) return ret; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e53f8d6f326d..1d72a3c4a7e7 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -569,14 +569,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ipt_entry *e, const char *name) +check_entry(const struct ipt_entry *e) { const struct xt_entry_target *t; - if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, name); + if (!ip_checkentry(&e->ip)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) @@ -666,10 +664,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -741,6 +735,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { @@ -755,6 +750,10 @@ check_entry_size_and_hooks(struct ipt_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -1506,7 +1505,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ipt_entry *)e, name); + ret = check_entry((struct ipt_entry *)e); if (ret) return ret; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 84f9baf7aee8..26a5ad1cc4fd 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -581,14 +581,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ip6t_entry *e, const char *name) +check_entry(const struct ip6t_entry *e) { const struct xt_entry_target *t; - if (!ip6_checkentry(&e->ipv6)) { - duprintf("ip_tables: ip check failed %p %s.\n", e, name); + if (!ip6_checkentry(&e->ipv6)) return -EINVAL; - } if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) @@ -679,10 +677,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - e->counters.pcnt = xt_percpu_counter_alloc(); if (IS_ERR_VALUE(e->counters.pcnt)) return -ENOMEM; @@ -753,6 +747,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { @@ -767,6 +762,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e, return -EINVAL; } + err = check_entry(e); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -1518,7 +1517,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, } /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ip6t_entry *)e, name); + ret = check_entry((struct ip6t_entry *)e); if (ret) return ret; From 6e94e0cfb0887e4013b3b930fa6ab1fe6bb6ba91 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Mar 2016 18:02:50 +0100 Subject: [PATCH 076/196] netfilter: x_tables: make sure e->next_offset covers remaining blob size Otherwise this function may read data beyond the ruleset blob. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 6 ++++-- net/ipv4/netfilter/ip_tables.c | 6 ++++-- net/ipv6/netfilter/ip6_tables.c | 6 ++++-- 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 830bbe8ec13d..51d4fe56b807 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -573,7 +573,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1232,7 +1233,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 1d72a3c4a7e7..fb7694e6663e 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -738,7 +738,8 @@ check_entry_size_and_hooks(struct ipt_entry *e, int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1492,7 +1493,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 26a5ad1cc4fd..b248528f2a17 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -750,7 +750,8 @@ check_entry_size_and_hooks(struct ip6t_entry *e, int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1504,7 +1505,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } From 54d83fc74aa9ec72794373cb47432c5f7fb1a309 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 22 Mar 2016 18:02:52 +0100 Subject: [PATCH 077/196] netfilter: x_tables: fix unconditional helper Ben Hawkes says: In the mark_source_chains function (net/ipv4/netfilter/ip_tables.c) it is possible for a user-supplied ipt_entry structure to have a large next_offset field. This field is not bounds checked prior to writing a counter value at the supplied offset. Problem is that mark_source_chains should not have been called -- the rule doesn't have a next entry, so its supposed to return an absolute verdict of either ACCEPT or DROP. However, the function conditional() doesn't work as the name implies. It only checks that the rule is using wildcard address matching. However, an unconditional rule must also not be using any matches (no -m args). The underflow validator only checked the addresses, therefore passing the 'unconditional absolute verdict' test, while mark_source_chains also tested for presence of matches, and thus proceeeded to the next (not-existent) rule. Unify this so that all the callers have same idea of 'unconditional rule'. Reported-by: Ben Hawkes Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 18 +++++++++--------- net/ipv4/netfilter/ip_tables.c | 23 +++++++++++------------ net/ipv6/netfilter/ip6_tables.c | 23 +++++++++++------------ 3 files changed, 31 insertions(+), 33 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 51d4fe56b807..a1bb5e7129a2 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -359,11 +359,12 @@ unsigned int arpt_do_table(struct sk_buff *skb, } /* All zeroes == unconditional rule. */ -static inline bool unconditional(const struct arpt_arp *arp) +static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; - return memcmp(arp, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct arpt_entry) && + memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if @@ -402,11 +403,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->arp)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -551,7 +551,7 @@ static bool check_underflow(const struct arpt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->arp)) + if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -598,9 +598,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index fb7694e6663e..89b5d959eda3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ipt_ip *ip) +static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; - return memcmp(ip, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ipt_entry) && + memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; #undef FWINV } @@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ip)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -476,11 +476,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->ip)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -715,7 +714,7 @@ static bool check_underflow(const struct ipt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ip)) + if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -763,9 +762,9 @@ check_entry_size_and_hooks(struct ipt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index b248528f2a17..541b59f83595 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -198,11 +198,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ip6t_ip6 *ipv6) +static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; - return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ip6t_entry) && + memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * @@ -258,11 +259,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ipv6)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -488,11 +488,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && - unconditional(&e->ipv6)) || visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -727,7 +726,7 @@ static bool check_underflow(const struct ip6t_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ipv6)) + if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -775,9 +774,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; From 931401137f60fc299256bbc221c0b756be31c32c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 23 Mar 2016 12:58:01 +0100 Subject: [PATCH 078/196] netfilter: nfnetlink_queue: honor NFQA_CFG_F_FAIL_OPEN when netlink unicast fails When netlink unicast fails to deliver the message to userspace, we should also check if the NFQA_CFG_F_FAIL_OPEN flag is set so we reinject the packet back to the stack. I think the user expects no packet drops when this flag is set due to queueing to userspace errors, no matter if related to the internal queue or when sending the netlink message to userspace. The userspace application will still get the ENOBUFS error via recvmsg() so the user still knows that, with the current configuration that is in place, the userspace application is not consuming the messages at the pace that the kernel needs. Reported-by: "Yigal Reiss (yreiss)" Signed-off-by: Pablo Neira Ayuso Tested-by: "Yigal Reiss (yreiss)" --- net/netfilter/nfnetlink_queue.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 75429997ed41..cb5b630a645b 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -582,7 +582,12 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT); if (err < 0) { - queue->queue_user_dropped++; + if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { + failopen = 1; + err = 0; + } else { + queue->queue_user_dropped++; + } goto err_out_unlock; } From b301f2538759933cf9ff1f7c4f968da72e3f0757 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 24 Mar 2016 21:29:53 +0100 Subject: [PATCH 079/196] netfilter: x_tables: enforce nul-terminated table name from getsockopt GET_ENTRIES Make sure the table names via getsockopt GET_ENTRIES is nul-terminated in ebtables and all the x_tables variants and their respective compat code. Uncovered by KASAN. Reported-by: Baozeng Ding Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 4 ++++ net/ipv4/netfilter/arp_tables.c | 2 ++ net/ipv4/netfilter/ip_tables.c | 2 ++ net/ipv6/netfilter/ip6_tables.c | 2 ++ 4 files changed, 10 insertions(+) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 67b2e27999aa..8570bc7744c2 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1521,6 +1521,8 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; + tmp.name[sizeof(tmp.name) - 1] = '\0'; + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; @@ -2332,6 +2334,8 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; + tmp.name[sizeof(tmp.name) - 1] = '\0'; + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index a1bb5e7129a2..4133b0f513af 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -969,6 +969,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, sizeof(struct arpt_get_entries) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1663,6 +1664,7 @@ static int compat_get_entries(struct net *net, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 89b5d959eda3..631c100a1338 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1156,6 +1156,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1935,6 +1936,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 541b59f83595..86b67b70b626 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1168,6 +1168,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR_OR_NULL(t)) { @@ -1944,6 +1945,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, *len, sizeof(get) + get.size); return -EINVAL; } + get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); From 29421198c3a860092e27c2ad8499dfe603398817 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 26 Mar 2016 16:32:57 +0800 Subject: [PATCH 080/196] netfilter: ipv4: fix NULL dereference Commit fa50d974d104 ("ipv4: Namespaceify ip_default_ttl sysctl knob") use sock_net(skb->sk) to get the net namespace, but we can't assume that sk_buff->sk is always exist, so when it is NULL, oops will happen. Signed-off-by: Liping Zhang Reviewed-by: Nikolay Borisov Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/nft_reject_bridge.c | 20 ++++----- net/ipv4/netfilter/ipt_SYNPROXY.c | 54 ++++++++++++------------ 2 files changed, 38 insertions(+), 36 deletions(-) diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index adc8d7221dbb..77f7e7a9ebe1 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -40,7 +40,8 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, /* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT) * or the bridge port (NF_BRIDGE PREROUTING). */ -static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, +static void nft_reject_br_send_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, const struct net_device *dev, int hook) { @@ -48,7 +49,6 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _oth; - struct net *net = sock_net(oldskb->sk); if (!nft_bridge_iphdr_validate(oldskb)) return; @@ -75,7 +75,8 @@ static void nft_reject_br_send_v4_tcp_reset(struct sk_buff *oldskb, br_deliver(br_port_get_rcu(dev), nskb); } -static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, +static void nft_reject_br_send_v4_unreach(struct net *net, + struct sk_buff *oldskb, const struct net_device *dev, int hook, u8 code) { @@ -86,7 +87,6 @@ static void nft_reject_br_send_v4_unreach(struct sk_buff *oldskb, void *payload; __wsum csum; u8 proto; - struct net *net = sock_net(oldskb->sk); if (oldskb->csum_bad || !nft_bridge_iphdr_validate(oldskb)) return; @@ -273,17 +273,17 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IP): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->hook, + nft_reject_br_send_v4_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, - pkt->hook); + nft_reject_br_send_v4_tcp_reset(pkt->net, pkt->skb, + pkt->in, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->hook, + nft_reject_br_send_v4_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, nft_reject_icmp_code(priv->icmp_code)); break; } diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 7b8fbb352877..db5b87509446 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -18,10 +18,10 @@ #include static struct iphdr * -synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) +synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, + __be32 daddr) { struct iphdr *iph; - struct net *net = sock_net(skb->sk); skb_reset_network_header(skb); iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); @@ -40,14 +40,12 @@ synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) } static void -synproxy_send_tcp(const struct synproxy_net *snet, +synproxy_send_tcp(struct net *net, const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct iphdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { - struct net *net = nf_ct_net(snet->tmpl); - nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; @@ -72,7 +70,7 @@ free_nskb: } static void -synproxy_send_client_synack(const struct synproxy_net *snet, +synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { @@ -91,7 +89,7 @@ synproxy_send_client_synack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -109,15 +107,16 @@ synproxy_send_client_synack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } static void -synproxy_send_server_syn(const struct synproxy_net *snet, +synproxy_send_server_syn(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts, u32 recv_seq) { + struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *nskb; struct iphdr *iph, *niph; struct tcphdr *nth; @@ -132,7 +131,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -153,12 +152,12 @@ synproxy_send_server_syn(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + synproxy_send_tcp(net, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } static void -synproxy_send_server_ack(const struct synproxy_net *snet, +synproxy_send_server_ack(struct net *net, const struct ip_ct_tcp *state, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) @@ -177,7 +176,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->daddr, iph->saddr); + niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -193,11 +192,11 @@ synproxy_send_server_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(net, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void -synproxy_send_client_ack(const struct synproxy_net *snet, +synproxy_send_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { @@ -215,7 +214,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, return; skb_reserve(nskb, MAX_TCP_HEADER); - niph = synproxy_build_ip(nskb, iph->saddr, iph->daddr); + niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); @@ -231,15 +230,16 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(net, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } static bool -synproxy_recv_client_ack(const struct synproxy_net *snet, +synproxy_recv_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq) { + struct synproxy_net *snet = synproxy_pernet(net); int mss; mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1); @@ -255,7 +255,7 @@ synproxy_recv_client_ack(const struct synproxy_net *snet, if (opts->options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_check_timestamp_cookie(opts); - synproxy_send_server_syn(snet, skb, th, opts, recv_seq); + synproxy_send_server_syn(net, skb, th, opts, recv_seq); return true; } @@ -263,7 +263,8 @@ static unsigned int synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_synproxy_info *info = par->targinfo; - struct synproxy_net *snet = synproxy_pernet(par->net); + struct net *net = par->net; + struct synproxy_net *snet = synproxy_pernet(net); struct synproxy_options opts = {}; struct tcphdr *th, _th; @@ -292,12 +293,12 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); - synproxy_send_client_synack(snet, skb, th, &opts); + synproxy_send_client_synack(net, skb, th, &opts); return NF_DROP; } else if (th->ack && !(th->fin || th->rst || th->syn)) { /* ACK from client */ - synproxy_recv_client_ack(snet, skb, th, &opts, ntohl(th->seq)); + synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq)); return NF_DROP; } @@ -308,7 +309,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(nhs->net); + struct net *net = nhs->net; + struct synproxy_net *snet = synproxy_pernet(net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; @@ -365,7 +367,7 @@ static unsigned int ipv4_synproxy_hook(void *priv, * therefore we need to add 1 to make the SYN sequence * number match the one of first SYN. */ - if (synproxy_recv_client_ack(snet, skb, th, &opts, + if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq) + 1)) this_cpu_inc(snet->stats->cookie_retrans); @@ -391,12 +393,12 @@ static unsigned int ipv4_synproxy_hook(void *priv, XT_SYNPROXY_OPT_SACK_PERM); swap(opts.tsval, opts.tsecr); - synproxy_send_server_ack(snet, state, skb, th, &opts); + synproxy_send_server_ack(net, state, skb, th, &opts); nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); swap(opts.tsval, opts.tsecr); - synproxy_send_client_ack(snet, skb, th, &opts); + synproxy_send_client_ack(net, skb, th, &opts); consume_skb(skb); return NF_STOLEN; From 379649cfeafef29b77d29860741f4d1c5870b65f Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Mon, 28 Mar 2016 09:31:41 -0300 Subject: [PATCH 081/196] perf tools: Fix build break on powerpc Commit 531d2410635c ("perf tools: Do not include stringify.h from the kernel sources") seems to have accidentially removed the inclusion of "util/header.h" from "arch/powerpc/util/header.c". "util/header.h" provides the prototype for get_cpuid() and is needed to build perf on Powerpc: arch/powerpc/util/header.c:17:1: error: no previous prototype for 'get_cpuid' [-Werror=missing-prototypes] Reported-by: Michael Ellerman Tested-by: Arnaldo Carvalho de Melo Cc: Stephen Rothwell Fixes: 531d2410635c ("perf tools: Do not include stringify.h from the kernel sources") Signed-off-by: Sukadev Bhattiprolu [ Included "util.h" too, to get the scnprintf() prototype ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/powerpc/util/header.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 6138bdef6e63..f8ccee132867 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -4,6 +4,8 @@ #include #include #include +#include "header.h" +#include "util.h" #define mfspr(rn) ({unsigned long rval; \ asm volatile("mfspr %0," __stringify(rn) \ From 4b28038fd60d346337dcaca80c255db2724adf76 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 19 Mar 2016 15:31:10 +0200 Subject: [PATCH 082/196] remoteproc: st: fix check of syscon_regmap_lookup_by_phandle() return value syscon_regmap_lookup_by_phandle() returns either a valid pointer to struct regmap or ERR_PTR() error value, check for NULL is invalid and on error path may lead to oops, the change corrects the check. Signed-off-by: Vladimir Zapolskiy Acked-by: Lee Jones Signed-off-by: Bjorn Andersson --- drivers/remoteproc/st_remoteproc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/remoteproc/st_remoteproc.c b/drivers/remoteproc/st_remoteproc.c index 6bb04d453247..6f056caa8a56 100644 --- a/drivers/remoteproc/st_remoteproc.c +++ b/drivers/remoteproc/st_remoteproc.c @@ -189,9 +189,9 @@ static int st_rproc_parse_dt(struct platform_device *pdev) } ddata->boot_base = syscon_regmap_lookup_by_phandle(np, "st,syscfg"); - if (!ddata->boot_base) { + if (IS_ERR(ddata->boot_base)) { dev_err(dev, "Boot base not found\n"); - return -EINVAL; + return PTR_ERR(ddata->boot_base); } err = of_property_read_u32_index(np, "st,syscfg", 1, From e84810c7b85a2d7897797b3ad3e879168a8e032a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Mon, 28 Mar 2016 22:38:16 +0200 Subject: [PATCH 083/196] qmi_wwan: add "D-Link DWM-221 B1" device id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thomas reports: "Windows: 00 diagnostics 01 modem 02 at-port 03 nmea 04 nic Linux: T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2001 ProdID=7e19 Rev=02.32 S: Manufacturer=Mobile Connect S: Product=Mobile Connect S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage" Reported-by: Thomas Schäfer Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 7d717c66bcb0..9d1fce8a6e84 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -844,6 +844,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */ {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ + {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ From fc0c2028135c7f75fce36b90e44efb8003a9173b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Mar 2016 10:30:19 -0800 Subject: [PATCH 084/196] x86, pmem: use memcpy_mcsafe() for memcpy_from_pmem() Update the definition of memcpy_from_pmem() to return 0 or a negative error code. Implement x86/arch_memcpy_from_pmem() with memcpy_mcsafe(). Cc: Borislav Petkov Cc: Tony Luck Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Acked-by: Ingo Molnar Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- arch/x86/include/asm/pmem.h | 9 +++++++++ drivers/nvdimm/pmem.c | 4 ++-- include/linux/pmem.h | 22 ++++++++++++++++------ 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index bf8b35d2035a..fbc5e92e1ecc 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -47,6 +47,15 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, BUG(); } +static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src, + size_t n) +{ + if (static_cpu_has(X86_FEATURE_MCE_RECOVERY)) + return memcpy_mcsafe(dst, (void __force *) src, n); + memcpy(dst, (void __force *) src, n); + return 0; +} + /** * arch_wmb_pmem - synchronize writes to persistent memory * diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ca5721c306bb..cc31c6f1f88e 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -99,7 +99,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page, if (unlikely(bad_pmem)) rc = -EIO; else { - memcpy_from_pmem(mem + off, pmem_addr, len); + rc = memcpy_from_pmem(mem + off, pmem_addr, len); flush_dcache_page(page); } } else { @@ -295,7 +295,7 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns, if (unlikely(is_bad_pmem(&pmem->bb, offset / 512, sz_align))) return -EIO; - memcpy_from_pmem(buf, pmem->virt_addr + offset, size); + return memcpy_from_pmem(buf, pmem->virt_addr + offset, size); } else { memcpy_to_pmem(pmem->virt_addr + offset, buf, size); wmb_pmem(); diff --git a/include/linux/pmem.h b/include/linux/pmem.h index 3ec5309e29f3..ac6d872ce067 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -42,6 +42,13 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, BUG(); } +static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src, + size_t n) +{ + BUG(); + return -EFAULT; +} + static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, struct iov_iter *i) { @@ -66,14 +73,17 @@ static inline void arch_invalidate_pmem(void __pmem *addr, size_t size) #endif /* - * Architectures that define ARCH_HAS_PMEM_API must provide - * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(), - * arch_copy_from_iter_pmem(), arch_clear_pmem(), arch_wb_cache_pmem() - * and arch_has_wmb_pmem(). + * memcpy_from_pmem - read from persistent memory with error handling + * @dst: destination buffer + * @src: source buffer + * @size: transfer length + * + * Returns 0 on success negative error code on failure. */ -static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) +static inline int memcpy_from_pmem(void *dst, void __pmem const *src, + size_t size) { - memcpy(dst, (void __force const *) src, size); + return arch_memcpy_from_pmem(dst, src, size); } static inline bool arch_has_pmem_api(void) From 08a5bb2921e490939f78f38fd0d02858bb709942 Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Tue, 8 Mar 2016 10:03:56 +0100 Subject: [PATCH 085/196] powerpc/mm: Fixup preempt underflow with huge pages hugepd_free() used __get_cpu_var() once. Nothing ensured that the code accessing the variable did not migrate from one CPU to another and soon this was noticed by Tiejun Chen in 94b09d755462 ("powerpc/hugetlb: Replace __get_cpu_var with get_cpu_var"). So we had it fixed. Christoph Lameter was doing his __get_cpu_var() replaces and forgot PowerPC. Then he noticed this and sent his fixed up batch again which got applied as 69111bac42f5 ("powerpc: Replace __get_cpu_var uses"). The careful reader will noticed one little detail: get_cpu_var() got replaced with this_cpu_ptr(). So now we have a put_cpu_var() which does a preempt_enable() and nothing that does preempt_disable() so we underflow the preempt counter. Cc: Benjamin Herrenschmidt Cc: Christoph Lameter Cc: stable@vger.kernel.org Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hugetlbpage.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 6dd272b6196f..d991b9e80dbb 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -413,13 +413,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = this_cpu_ptr(&hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); - put_cpu_var(hugepd_freelist_cur); + put_cpu_var(hugepd_freelist_cur); return; } From 01d7c2a2de47890934faba91a71d183795e4348d Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 8 Mar 2016 09:08:47 +1100 Subject: [PATCH 086/196] powerpc/process: Fix altivec SPR not being saved In save_sprs() in process.c contains the following test: if (cpu_has_feature(cpu_has_feature(CPU_FTR_ALTIVEC))) t->vrsave = mfspr(SPRN_VRSAVE); CPU feature with the mask 0x1 is CPU_FTR_COHERENT_ICACHE so the test is equivilent to: if (cpu_has_feature(CPU_FTR_ALTIVEC) && cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) On CPUs without support for both (i.e G5) this results in vrsave not being saved between context switches. The vector register save/restore code doesn't use VRSAVE to determine which registers to save/restore, but the value of VRSAVE is used to determine if altivec is being used in several code paths. Fixes: 152d523e6307 ("powerpc: Create context switch helpers save_sprs() and restore_sprs()") Cc: stable@vger.kernel.org Signed-off-by: Oliver O'Halloran Signed-off-by: Anton Blanchard Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 612df305886b..b8500b4ac7fe 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -983,7 +983,7 @@ void restore_tm_state(struct pt_regs *regs) static inline void save_sprs(struct thread_struct *t) { #ifdef CONFIG_ALTIVEC - if (cpu_has_feature(cpu_has_feature(CPU_FTR_ALTIVEC))) + if (cpu_has_feature(CPU_FTR_ALTIVEC)) t->vrsave = mfspr(SPRN_VRSAVE); #endif #ifdef CONFIG_PPC_BOOK3S_64 From 71528d8bd7a8aa920cd69d4223c6c87d5849257d Mon Sep 17 00:00:00 2001 From: Simon Guo Date: Fri, 25 Mar 2016 01:12:21 +0800 Subject: [PATCH 087/196] powerpc: Correct used_vsr comment The used_vsr flag is set if process has used VSX registers, not Altivec registers. But the comment says otherwise, correct the comment. Signed-off-by: Simon Guo Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8ab8a1a9610a..009fab130cd8 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -246,7 +246,7 @@ struct thread_struct { #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX /* VSR status */ - int used_vsr; /* set if process has used altivec */ + int used_vsr; /* set if process has used VSX */ #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE unsigned long evr[32]; /* upper 32-bits of SPE regs */ From ee6825c80e870fff1a370c718ec77022ade0889b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Mar 2016 15:52:34 +0100 Subject: [PATCH 088/196] x86/topology: Fix AMD core count It turns out AMD gets x86_max_cores wrong when there are compute units. The issue is that Linux assumes: nr_logical_cpus = nr_cores * nr_siblings But AMD reports its CU unit as 2 cores, but then sets num_smp_siblings to 2 as well. Boris: fixup ras/mce_amd_inj.c too, to compute the Node Base Core properly, according to the new nomenclature. Fixes: 1f12e32f4cd5 ("x86/topology: Create logical package id") Reported-by: Xiong Zhou Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Cc: Andreas Herrmann Cc: Andy Lutomirski Link: http://lkml.kernel.org/r/20160317095220.GO6344@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/smp.h | 1 + arch/x86/kernel/cpu/amd.c | 8 ++++---- arch/x86/ras/mce_amd_inj.c | 3 ++- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 20a3de5cb3b0..66b057306f40 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -155,6 +155,7 @@ static inline int wbinvd_on_all_cpus(void) wbinvd(); return 0; } +#define smp_num_siblings 1 #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6e47e3a916f1..4d0087f94ee5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -312,9 +312,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c) node_id = ecx & 7; /* get compute unit information */ - smp_num_siblings = ((ebx >> 8) & 3) + 1; + cores_per_cu = smp_num_siblings = ((ebx >> 8) & 3) + 1; + c->x86_max_cores /= smp_num_siblings; c->compute_unit_id = ebx & 0xff; - cores_per_cu += ((ebx >> 8) & 3); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; @@ -329,8 +329,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes_per_socket; - cus_per_node = cores_per_node / cores_per_cu; + cus_per_node = c->x86_max_cores / nodes_per_socket; + cores_per_node = cus_per_node * cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ per_cpu(cpu_llc_id, cpu) = node_id; diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 55d38cfa46c2..9e02dcaef683 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -20,6 +20,7 @@ #include #include +#include #include #include @@ -206,7 +207,7 @@ static u32 get_nbc_for_node(int node_id) struct cpuinfo_x86 *c = &boot_cpu_data; u32 cores_per_node; - cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket(); + cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); return cores_per_node * node_id; } From 32b62f446827f696cc474a6d83cea93693c5ed49 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Mar 2016 15:52:35 +0100 Subject: [PATCH 089/196] perf/x86/amd: Cleanup Fam10h NB event constraints Avoid allocating the AMD NB event constraints data structure when not needed. This gets rid of x86_max_cores usage and avoids allocating this on AMD Core Perfctr supporting hardware (which has separate MSRs for NB events). Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Cc: aherrmann@suse.com Cc: Rui Huang Cc: Borislav Petkov Cc: jencce.kernel@gmail.com Link: http://lkml.kernel.org/r/20160320124629.GY6375@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- arch/x86/events/amd/core.c | 21 ++++++++++++++++++--- arch/x86/events/perf_event.h | 5 +++++ 2 files changed, 23 insertions(+), 3 deletions(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 049ada8d4e9c..86a9bec18dab 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -369,7 +369,7 @@ static int amd_pmu_cpu_prepare(int cpu) WARN_ON_ONCE(cpuc->amd_nb); - if (boot_cpu_data.x86_max_cores < 2) + if (!x86_pmu.amd_nb_constraints) return NOTIFY_OK; cpuc->amd_nb = amd_alloc_nb(cpu); @@ -388,7 +388,7 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; - if (boot_cpu_data.x86_max_cores < 2) + if (!x86_pmu.amd_nb_constraints) return; nb_id = amd_get_nb_id(cpu); @@ -414,7 +414,7 @@ static void amd_pmu_cpu_dead(int cpu) { struct cpu_hw_events *cpuhw; - if (boot_cpu_data.x86_max_cores < 2) + if (!x86_pmu.amd_nb_constraints) return; cpuhw = &per_cpu(cpu_hw_events, cpu); @@ -648,6 +648,8 @@ static __initconst const struct x86_pmu amd_pmu = { .cpu_prepare = amd_pmu_cpu_prepare, .cpu_starting = amd_pmu_cpu_starting, .cpu_dead = amd_pmu_cpu_dead, + + .amd_nb_constraints = 1, }; static int __init amd_core_pmu_init(void) @@ -674,6 +676,11 @@ static int __init amd_core_pmu_init(void) x86_pmu.eventsel = MSR_F15H_PERF_CTL; x86_pmu.perfctr = MSR_F15H_PERF_CTR; x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; + /* + * AMD Core perfctr has separate MSRs for the NB events, see + * the amd/uncore.c driver. + */ + x86_pmu.amd_nb_constraints = 0; pr_cont("core perfctr, "); return 0; @@ -693,6 +700,14 @@ __init int amd_pmu_init(void) if (ret) return ret; + if (num_possible_cpus() == 1) { + /* + * No point in allocating data structures to serialize + * against other CPUs, when there is only the one CPU. + */ + x86_pmu.amd_nb_constraints = 0; + } + /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ba6ef18528c9..716d0482f5db 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -607,6 +607,11 @@ struct x86_pmu { */ atomic_t lbr_exclusive[x86_lbr_exclusive_max]; + /* + * AMD bits + */ + unsigned int amd_nb_constraints : 1; + /* * Extra registers for events */ From 8196dab4fc159943df6baaac04973bb1accb7100 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 25 Mar 2016 15:52:36 +0100 Subject: [PATCH 090/196] x86/cpu: Get rid of compute_unit_id It is cpu_core_id anyway. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1458917557-8757-3-git-send-email-bp@alien8.de Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/processor.h | 2 -- arch/x86/kernel/amd_nb.c | 6 ++---- arch/x86/kernel/cpu/amd.c | 10 +++------- arch/x86/kernel/smpboot.c | 2 +- 4 files changed, 6 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 983738ac014c..9264476f3d57 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -132,8 +132,6 @@ struct cpuinfo_x86 { u16 logical_proc_id; /* Core id: */ u16 cpu_core_id; - /* Compute unit id */ - u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 29fa475ec518..a147e676fc7b 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -170,15 +170,13 @@ int amd_get_subcaches(int cpu) { struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; unsigned int mask; - int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return 0; pci_read_config_dword(link, 0x1d4, &mask); - cuid = cpu_data(cpu).compute_unit_id; - return (mask >> (4 * cuid)) & 0xf; + return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf; } int amd_set_subcaches(int cpu, unsigned long mask) @@ -204,7 +202,7 @@ int amd_set_subcaches(int cpu, unsigned long mask) pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); } - cuid = cpu_data(cpu).compute_unit_id; + cuid = cpu_data(cpu).cpu_core_id; mask <<= 4 * cuid; mask |= (0xf ^ (1 << cuid)) << 26; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 4d0087f94ee5..7b76eb67a9b3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -300,7 +300,6 @@ static int nearby_node(int apicid) #ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -312,9 +311,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c) node_id = ecx & 7; /* get compute unit information */ - cores_per_cu = smp_num_siblings = ((ebx >> 8) & 3) + 1; + smp_num_siblings = ((ebx >> 8) & 3) + 1; c->x86_max_cores /= smp_num_siblings; - c->compute_unit_id = ebx & 0xff; + c->cpu_core_id = ebx & 0xff; } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; @@ -325,19 +324,16 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* fixup multi-node processor information */ if (nodes_per_socket > 1) { - u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); cus_per_node = c->x86_max_cores / nodes_per_socket; - cores_per_node = cus_per_node * cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ per_cpu(cpu_llc_id, cpu) = node_id; /* core id has to be in the [0 .. cores_per_node - 1] range */ - c->cpu_core_id %= cores_per_node; - c->compute_unit_id %= cus_per_node; + c->cpu_core_id %= cus_per_node; } } #endif diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b2c99f811c3f..a2065d3b3b39 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -422,7 +422,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) if (c->phys_proc_id == o->phys_proc_id && per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->compute_unit_id == o->compute_unit_id) + c->cpu_core_id == o->cpu_core_id) return topology_sane(c, o, "smt"); } else if (c->phys_proc_id == o->phys_proc_id && From f7be8610bca88e59dd2fd5d98fcbc5031ef0e079 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 28 Mar 2016 11:56:09 +0200 Subject: [PATCH 091/196] x86/Documentation: Start documenting x86 topology This should contain important aspects of how we represent the system topology on x86. If people have questions about it and this file doesn't answer it, then it must be updated. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/20160328095609.GD26651@pd.tnic Signed-off-by: Thomas Gleixner --- Documentation/x86/topology.txt | 208 +++++++++++++++++++++++++++++++++ 1 file changed, 208 insertions(+) create mode 100644 Documentation/x86/topology.txt diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt new file mode 100644 index 000000000000..06afac252f5b --- /dev/null +++ b/Documentation/x86/topology.txt @@ -0,0 +1,208 @@ +x86 Topology +============ + +This documents and clarifies the main aspects of x86 topology modelling and +representation in the kernel. Update/change when doing changes to the +respective code. + +The architecture-agnostic topology definitions are in +Documentation/cputopology.txt. This file holds x86-specific +differences/specialities which must not necessarily apply to the generic +definitions. Thus, the way to read up on Linux topology on x86 is to start +with the generic one and look at this one in parallel for the x86 specifics. + +Needless to say, code should use the generic functions - this file is *only* +here to *document* the inner workings of x86 topology. + +Started by Thomas Gleixner and Borislav Petkov . + +The main aim of the topology facilities is to present adequate interfaces to +code which needs to know/query/use the structure of the running system wrt +threads, cores, packages, etc. + +The kernel does not care about the concept of physical sockets because a +socket has no relevance to software. It's an electromechanical component. In +the past a socket always contained a single package (see below), but with the +advent of Multi Chip Modules (MCM) a socket can hold more than one package. So +there might be still references to sockets in the code, but they are of +historical nature and should be cleaned up. + +The topology of a system is described in the units of: + + - packages + - cores + - threads + +* Package: + + Packages contain a number of cores plus shared resources, e.g. DRAM + controller, shared caches etc. + + AMD nomenclature for package is 'Node'. + + Package-related topology information in the kernel: + + - cpuinfo_x86.x86_max_cores: + + The number of cores in a package. This information is retrieved via CPUID. + + - cpuinfo_x86.phys_proc_id: + + The physical ID of the package. This information is retrieved via CPUID + and deduced from the APIC IDs of the cores in the package. + + - cpuinfo_x86.logical_id: + + The logical ID of the package. As we do not trust BIOSes to enumerate the + packages in a consistent way, we introduced the concept of logical package + ID so we can sanely calculate the number of maximum possible packages in + the system and have the packages enumerated linearly. + + - topology_max_packages(): + + The maximum possible number of packages in the system. Helpful for per + package facilities to preallocate per package information. + + +* Cores: + + A core consists of 1 or more threads. It does not matter whether the threads + are SMT- or CMT-type threads. + + AMDs nomenclature for a CMT core is "Compute Unit". The kernel always uses + "core". + + Core-related topology information in the kernel: + + - smp_num_siblings: + + The number of threads in a core. The number of threads in a package can be + calculated by: + + threads_per_package = cpuinfo_x86.x86_max_cores * smp_num_siblings + + +* Threads: + + A thread is a single scheduling unit. It's the equivalent to a logical Linux + CPU. + + AMDs nomenclature for CMT threads is "Compute Unit Core". The kernel always + uses "thread". + + Thread-related topology information in the kernel: + + - topology_core_cpumask(): + + The cpumask contains all online threads in the package to which a thread + belongs. + + The number of online threads is also printed in /proc/cpuinfo "siblings." + + - topology_sibling_mask(): + + The cpumask contains all online threads in the core to which a thread + belongs. + + - topology_logical_package_id(): + + The logical package ID to which a thread belongs. + + - topology_physical_package_id(): + + The physical package ID to which a thread belongs. + + - topology_core_id(); + + The ID of the core to which a thread belongs. It is also printed in /proc/cpuinfo + "core_id." + + + +System topology examples + +Note: + +The alternative Linux CPU enumeration depends on how the BIOS enumerates the +threads. Many BIOSes enumerate all threads 0 first and then all threads 1. +That has the "advantage" that the logical Linux CPU numbers of threads 0 stay +the same whether threads are enabled or not. That's merely an implementation +detail and has no practical impact. + +1) Single Package, Single Core + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + +2) Single Package, Dual Core + + a) One thread per core + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [core 1] -> [thread 0] -> Linux CPU 1 + + b) Two threads per core + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [thread 1] -> Linux CPU 1 + -> [core 1] -> [thread 0] -> Linux CPU 2 + -> [thread 1] -> Linux CPU 3 + + Alternative enumeration: + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [thread 1] -> Linux CPU 2 + -> [core 1] -> [thread 0] -> Linux CPU 1 + -> [thread 1] -> Linux CPU 3 + + AMD nomenclature for CMT systems: + + [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0 + -> [Compute Unit Core 1] -> Linux CPU 1 + -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2 + -> [Compute Unit Core 1] -> Linux CPU 3 + +4) Dual Package, Dual Core + + a) One thread per core + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [core 1] -> [thread 0] -> Linux CPU 1 + + [package 1] -> [core 0] -> [thread 0] -> Linux CPU 2 + -> [core 1] -> [thread 0] -> Linux CPU 3 + + b) Two threads per core + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [thread 1] -> Linux CPU 1 + -> [core 1] -> [thread 0] -> Linux CPU 2 + -> [thread 1] -> Linux CPU 3 + + [package 1] -> [core 0] -> [thread 0] -> Linux CPU 4 + -> [thread 1] -> Linux CPU 5 + -> [core 1] -> [thread 0] -> Linux CPU 6 + -> [thread 1] -> Linux CPU 7 + + Alternative enumeration: + + [package 0] -> [core 0] -> [thread 0] -> Linux CPU 0 + -> [thread 1] -> Linux CPU 4 + -> [core 1] -> [thread 0] -> Linux CPU 1 + -> [thread 1] -> Linux CPU 5 + + [package 1] -> [core 0] -> [thread 0] -> Linux CPU 2 + -> [thread 1] -> Linux CPU 6 + -> [core 1] -> [thread 0] -> Linux CPU 3 + -> [thread 1] -> Linux CPU 7 + + AMD nomenclature for CMT systems: + + [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0 + -> [Compute Unit Core 1] -> Linux CPU 1 + -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2 + -> [Compute Unit Core 1] -> Linux CPU 3 + + [node 1] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 4 + -> [Compute Unit Core 1] -> Linux CPU 5 + -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 6 + -> [Compute Unit Core 1] -> Linux CPU 7 From 74b2375e6767935e6d9220bdbc6ed0db57f71a59 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Thu, 17 Mar 2016 14:52:17 +0100 Subject: [PATCH 092/196] s390/crypto: provide correct file mode at device register. When the prng device driver calls misc_register() there is the possibility to also provide the recommented file permissions. This fix now gives useful values (0644) where previously just the default was used (resulting in 0600 for the device file). Signed-off-by: Harald Freudenberger Signed-off-by: Martin Schwidefsky --- arch/s390/crypto/prng.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index b8045b97f4fb..d750cc0dfe30 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -669,11 +669,13 @@ static const struct file_operations prng_tdes_fops = { static struct miscdevice prng_sha512_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, + .mode = 0644, .fops = &prng_sha512_fops, }; static struct miscdevice prng_tdes_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, + .mode = 0644, .fops = &prng_tdes_fops, }; From 4a6772f514891eaacf26bcb7c2c808c557d23c6f Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Sat, 26 Mar 2016 20:47:00 +0200 Subject: [PATCH 093/196] x86/cpufreq: Remove duplicated TDP MSR macro definitions The list of CPU model specific registers contains two copies of TDP registers, remove the one, which is out of numerical order in the list. Fixes: 6a35fc2d6c22 ("cpufreq: intel_pstate: get P1 from TAR when available") Signed-off-by: Vladimir Zapolskiy Cc: Len Brown Cc: "Rafael J. Wysocki" Cc: Kristen Carlson Accardi Cc: Srinivas Pandruvada Link: http://lkml.kernel.org/r/1459018020-24577-1-git-send-email-vladimir_zapolskiy@mentor.com Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/msr-index.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2da46ac16e37..426e946ed0c0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -190,6 +190,7 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +/* Config TDP MSRs */ #define MSR_CONFIG_TDP_NOMINAL 0x00000648 #define MSR_CONFIG_TDP_LEVEL_1 0x00000649 #define MSR_CONFIG_TDP_LEVEL_2 0x0000064A @@ -210,13 +211,6 @@ #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 -/* Config TDP MSRs */ -#define MSR_CONFIG_TDP_NOMINAL 0x00000648 -#define MSR_CONFIG_TDP_LEVEL1 0x00000649 -#define MSR_CONFIG_TDP_LEVEL2 0x0000064A -#define MSR_CONFIG_TDP_CONTROL 0x0000064B -#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C - /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f From 5f870a3f7188065e13efafe1faeb01c136173bc4 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 28 Mar 2016 20:20:17 +0200 Subject: [PATCH 094/196] x86/thread_info: Merge two !__ASSEMBLY__ sections We have #ifndef __ASSEMBLY__ ... #endif #ifndef __ASSEMBLY__ ... #endif Merge the two. No functionality change. Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1459189217-25532-1-git-send-email-bp@alien8.de Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/thread_info.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 82866697fcf1..ffae84df8a93 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -276,11 +276,9 @@ static inline bool is_ia32_task(void) */ #define force_iret() set_thread_flag(TIF_NOTIFY_RESUME) -#endif /* !__ASSEMBLY__ */ - -#ifndef __ASSEMBLY__ extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); -#endif +#endif /* !__ASSEMBLY__ */ + #endif /* _ASM_X86_THREAD_INFO_H */ From 34a4cceb78e48c75d1b48b25352a3f3b2cc2b2da Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Fri, 25 Mar 2016 10:08:40 +0800 Subject: [PATCH 095/196] x86/cpu: Add advanced power management bits Bit 11 of CPUID 8000_0007 edx is processor feedback interface. Bit 12 of CPUID 8000_0007 edx is accumulated power. Print proper names in proc/cpuinfo Reported-and-tested-by: Borislav Petkov Signed-off-by: Huang Rui Cc: Tony Li Cc: Fenghua Yu Cc: Tony Luck Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Andy Lutomirski Cc: Fengguang Wu Cc: Sherry Hurwitz Cc: Borislav Petkov Cc: "Len Brown" Link: http://lkml.kernel.org/r/1458871720-3209-1-git-send-email-ray.huang@amd.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/powerflags.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c index 31f0f335ed22..1dd8294fd730 100644 --- a/arch/x86/kernel/cpu/powerflags.c +++ b/arch/x86/kernel/cpu/powerflags.c @@ -18,4 +18,6 @@ const char *const x86_power_flags[32] = { "", /* tsc invariant mapped to constant_tsc */ "cpb", /* core performance boost */ "eff_freq_ro", /* Readonly aperf/mperf */ + "proc_feedback", /* processor feedback interface */ + "acc_power", /* accumulated power mechanism */ }; From 5acba71e18833b9d06686b3751598bfa263a3ac3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:37:59 +0100 Subject: [PATCH 096/196] locking/atomic: Introduce atomic_fetch_or() This is deemed to replace the type generic fetch_or() which brings a lot of issues such as macro induced block variable aliasing and sloppy types. Not to mention fetch_or() doesn't refer to any namespace, adding even more confusion. So lets provide an atomic_t version. Current and next users of fetch_or() are thus encouraged to use atomic_t. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/include/linux/atomic.h b/include/linux/atomic.h index df4f369254c0..3d64c0852164 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -558,6 +558,27 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif +/** + * atomic_fetch_or - perform *p |= mask and return old value of *p + * @p: pointer to atomic_t + * @mask: mask to OR on the atomic_t + */ +#ifndef atomic_fetch_or +static inline int atomic_fetch_or(atomic_t *p, int mask) +{ + int old, val = atomic_read(p); + + for (;;) { + old = atomic_cmpxchg(p, val, val | mask); + if (old == val) + break; + val = old; + } + + return old; +} +#endif + /** * fetch_or - perform *ptr |= mask and return old value of *ptr * @ptr: pointer to value From f009a7a767e792d5ab0b46c08d46236ea5271dd9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:00 +0100 Subject: [PATCH 097/196] timers/nohz: Convert tick dependency mask to atomic_t The tick dependency mask was intially unsigned long because this is the type on which clear_bit() operates on and fetch_or() accepts it. But now that we have atomic_fetch_or(), we can instead use atomic_andnot() to clear the bit. This consolidates the type of our tick dependency mask, reduce its size on structures and benefit from possible architecture optimizations on atomic_t operations. Suggested-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +-- kernel/time/tick-sched.c | 61 ++++++++++++++++++++-------------------- kernel/time/tick-sched.h | 2 +- 3 files changed, 33 insertions(+), 34 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 60bba7e032dc..52c4847b05e2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -720,7 +720,7 @@ struct signal_struct { struct task_cputime cputime_expires; #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif struct list_head cpu_timers[3]; @@ -1549,7 +1549,7 @@ struct task_struct { #endif #ifdef CONFIG_NO_HZ_FULL - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; #endif unsigned long nvcsw, nivcsw; /* context switch counts */ u64 start_time; /* monotonic time in nsec */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 084b79f5917e..58e3310c9b21 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -157,52 +157,50 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) cpumask_var_t tick_nohz_full_mask; cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; -static unsigned long tick_dep_mask; +static atomic_t tick_dep_mask; -static void trace_tick_dependency(unsigned long dep) +static bool check_tick_dependency(atomic_t *dep) { - if (dep & TICK_DEP_MASK_POSIX_TIMER) { + int val = atomic_read(dep); + + if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); - return; + return true; } - if (dep & TICK_DEP_MASK_PERF_EVENTS) { + if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); - return; + return true; } - if (dep & TICK_DEP_MASK_SCHED) { + if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); - return; + return true; } - if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE) + if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); + return true; + } + + return false; } static bool can_stop_full_tick(struct tick_sched *ts) { WARN_ON_ONCE(!irqs_disabled()); - if (tick_dep_mask) { - trace_tick_dependency(tick_dep_mask); + if (check_tick_dependency(&tick_dep_mask)) return false; - } - if (ts->tick_dep_mask) { - trace_tick_dependency(ts->tick_dep_mask); + if (check_tick_dependency(&ts->tick_dep_mask)) return false; - } - if (current->tick_dep_mask) { - trace_tick_dependency(current->tick_dep_mask); + if (check_tick_dependency(¤t->tick_dep_mask)) return false; - } - if (current->signal->tick_dep_mask) { - trace_tick_dependency(current->signal->tick_dep_mask); + if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; - } return true; } @@ -259,12 +257,12 @@ static void tick_nohz_full_kick_all(void) preempt_enable(); } -static void tick_nohz_dep_set_all(unsigned long *dep, +static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { - unsigned long prev; + int prev; - prev = fetch_or(dep, BIT_MASK(bit)); + prev = atomic_fetch_or(dep, BIT(bit)); if (!prev) tick_nohz_full_kick_all(); } @@ -280,7 +278,7 @@ void tick_nohz_dep_set(enum tick_dep_bits bit) void tick_nohz_dep_clear(enum tick_dep_bits bit) { - clear_bit(bit, &tick_dep_mask); + atomic_andnot(BIT(bit), &tick_dep_mask); } /* @@ -289,12 +287,12 @@ void tick_nohz_dep_clear(enum tick_dep_bits bit) */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { - unsigned long prev; + int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); - prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit)); + prev = atomic_fetch_or(&ts->tick_dep_mask, BIT(bit)); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ @@ -313,7 +311,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); - clear_bit(bit, &ts->tick_dep_mask); + atomic_andnot(BIT(bit), &ts->tick_dep_mask); } /* @@ -331,7 +329,7 @@ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { - clear_bit(bit, &tsk->tick_dep_mask); + atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } /* @@ -345,7 +343,7 @@ void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { - clear_bit(bit, &sig->tick_dep_mask); + atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* @@ -366,7 +364,8 @@ void __tick_nohz_task_switch(void) ts = this_cpu_ptr(&tick_cpu_sched); if (ts->tick_stopped) { - if (current->tick_dep_mask || current->signal->tick_dep_mask) + if (atomic_read(¤t->tick_dep_mask) || + atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } out: diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index eb4e32566a83..bf38226e5c17 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -60,7 +60,7 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; int do_timer_last; - unsigned long tick_dep_mask; + atomic_t tick_dep_mask; }; extern struct tick_sched *tick_get_tick_sched(int cpu); From 5529578a27288d11d4d15635c258c6dde0f0fb10 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 24 Mar 2016 15:38:01 +0100 Subject: [PATCH 098/196] locking/atomic, sched: Unexport fetch_or() This patch functionally reverts: 5fd7a09cfb8c ("atomic: Export fetch_or()") During the merge Linus observed that the generic version of fetch_or() was messy: " This makes the ugly "fetch_or()" macro that the scheduler used internally a new generic helper, and does a bad job at it. " e23604edac2a Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Now that we have introduced atomic_fetch_or(), fetch_or() is only used by the scheduler in order to deal with thread_info flags which type can vary across architectures. Lets confine fetch_or() back to the scheduler so that we encourage future users to use the more robust and well typed atomic_t version instead. While at it, fetch_or() gets robustified, pasting improvements from a previous patch by Ingo Molnar that avoids needless expression re-evaluations in the loop. Reported-by: Linus Torvalds Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1458830281-4255-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 21 --------------------- kernel/sched/core.c | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 21 deletions(-) diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 3d64c0852164..506c3531832e 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -579,27 +579,6 @@ static inline int atomic_fetch_or(atomic_t *p, int mask) } #endif -/** - * fetch_or - perform *ptr |= mask and return old value of *ptr - * @ptr: pointer to value - * @mask: mask to OR on the value - * - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#ifndef fetch_or -#define fetch_or(ptr, mask) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (mask)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) -#endif - - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d8465eeab8b3..8b489fcac37b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -321,6 +321,24 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, mask) \ + ({ \ + typeof(ptr) _ptr = (ptr); \ + typeof(mask) _mask = (mask); \ + typeof(*_ptr) _old, _val = *_ptr; \ + \ + for (;;) { \ + _old = cmpxchg(_ptr, _val, _val | _mask); \ + if (_old == _val) \ + break; \ + _val = _old; \ + } \ + _old; \ +}) + #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, From d75868496ca0af1685f31726d8f5b5037c092a7a Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 21 Mar 2016 22:43:54 -0700 Subject: [PATCH 099/196] MAINTAINERS: Add mailing list for remote processor subsystems Add the newly created linux-remoteproc mailing list for the three subsystems related to remote processor management and communication. Acked-by: Ohad Ben-Cohen Acked-by: Suman Anna Signed-off-by: Bjorn Andersson --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 03e00c7c88eb..46ff01a877df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5042,6 +5042,7 @@ F: include/linux/hw_random.h HARDWARE SPINLOCK CORE M: Ohad Ben-Cohen M: Bjorn Andersson +L: linux-remoteproc@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/ohad/hwspinlock.git F: Documentation/hwspinlock.txt @@ -9314,6 +9315,7 @@ F: include/linux/regmap.h REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM M: Ohad Ben-Cohen M: Bjorn Andersson +L: linux-remoteproc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/ohad/remoteproc.git S: Maintained F: drivers/remoteproc/ @@ -9323,6 +9325,7 @@ F: include/linux/remoteproc.h REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM M: Ohad Ben-Cohen M: Bjorn Andersson +L: linux-remoteproc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/ohad/rpmsg.git S: Maintained F: drivers/rpmsg/ From a6002ec5a8c68e69706b2efd6db6d682d0ab672c Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 24 Mar 2016 16:54:34 +0000 Subject: [PATCH 100/196] arm64: opcodes.h: Add arm big-endian config options before including arm header arm and arm64 use different config options to specify big endian. This needs taking into account when including code/headers between the two architectures. A case in point is PAN, which uses the __instr_arm() macro to output instructions. The macro comes from opcodes.h, which lives under arch/arm. On a big-endian build the mismatched config options mean the instruction isn't byte swapped correctly, resulting in undefined instruction exceptions during boot: | alternatives: patching kernel code | kdevtmpfs[87]: undefined instruction: pc=ffffffc0004505b4 | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | kdevtmpfs[87]: undefined instruction: pc=ffffffc00076231c | Internal error: Oops - undefined instruction: 0 [#1] SMP | Modules linked in: | CPU: 0 PID: 87 Comm: kdevtmpfs Not tainted 4.1.16+ #5 | Hardware name: Hisilicon PhosphorHi1382 EVB (DT) | task: ffffffc336591700 ti: ffffffc3365a4000 task.ti: ffffffc3365a4000 | PC is at dump_instr+0x68/0x100 | LR is at do_undefinstr+0x1d4/0x2a4 | pc : [] lr : [] pstate: 604001c5 | sp : ffffffc3365a6450 Cc: #4.3.x- Reported-by: Hanjun Guo Tested-by: Xuefeng Wang Signed-off-by: James Morse Signed-off-by: Will Deacon --- arch/arm64/include/asm/opcodes.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h index 4e603ea36ad3..123f45d92cd1 100644 --- a/arch/arm64/include/asm/opcodes.h +++ b/arch/arm64/include/asm/opcodes.h @@ -1 +1,5 @@ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN +#endif + #include <../../arm/include/asm/opcodes.h> From b8cfadfcefdc8c306ca2c0b1bdbdd4e01f0155e3 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 24 Mar 2016 16:01:16 +0000 Subject: [PATCH 101/196] arm64: perf: Move PMU register related defines to asm/perf_event.h To use the ARMv8 PMU related register defines from the KVM code, we move the relevant definitions to asm/perf_event.h header file and rename them with prefix ARMV8_PMU_. This allows us to get rid of kvm_perf_event.h. Signed-off-by: Anup Patel Signed-off-by: Shannon Zhao Acked-by: Marc Zyngier Reviewed-by: Andrew Jones Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/include/asm/kvm_hyp.h | 1 - arch/arm64/include/asm/kvm_perf_event.h | 68 ----------------------- arch/arm64/include/asm/perf_event.h | 47 ++++++++++++++++ arch/arm64/kernel/perf_event.c | 72 +++++++------------------ 5 files changed, 66 insertions(+), 123 deletions(-) delete mode 100644 arch/arm64/include/asm/kvm_perf_event.h diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 227ed475dbd3..b7e82a795ac9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -27,7 +27,6 @@ #include #include #include -#include #define __KVM_HAVE_ARCH_INTC_INITIALIZED diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index a46b019ebcf5..44eaff70da6a 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -21,7 +21,6 @@ #include #include #include -#include #include #define __hyp_text __section(.hyp.text) notrace diff --git a/arch/arm64/include/asm/kvm_perf_event.h b/arch/arm64/include/asm/kvm_perf_event.h deleted file mode 100644 index c18fdebb8f66..000000000000 --- a/arch/arm64/include/asm/kvm_perf_event.h +++ /dev/null @@ -1,68 +0,0 @@ -/* - * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - */ - -#ifndef __ASM_KVM_PERF_EVENT_H -#define __ASM_KVM_PERF_EVENT_H - -#define ARMV8_PMU_MAX_COUNTERS 32 -#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) - -/* - * Per-CPU PMCR: config reg - */ -#define ARMV8_PMU_PMCR_E (1 << 0) /* Enable all counters */ -#define ARMV8_PMU_PMCR_P (1 << 1) /* Reset all counters */ -#define ARMV8_PMU_PMCR_C (1 << 2) /* Cycle counter reset */ -#define ARMV8_PMU_PMCR_D (1 << 3) /* CCNT counts every 64th cpu cycle */ -#define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */ -#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ -/* Determines which bit of PMCCNTR_EL0 generates an overflow */ -#define ARMV8_PMU_PMCR_LC (1 << 6) -#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ -#define ARMV8_PMU_PMCR_N_MASK 0x1f -#define ARMV8_PMU_PMCR_MASK 0x7f /* Mask for writable bits */ - -/* - * PMOVSR: counters overflow flag status reg - */ -#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */ -#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK - -/* - * PMXEVTYPER: Event selection reg - */ -#define ARMV8_PMU_EVTYPE_MASK 0xc80003ff /* Mask for writable bits */ -#define ARMV8_PMU_EVTYPE_EVENT 0x3ff /* Mask for EVENT bits */ - -#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR 0 /* Software increment event */ - -/* - * Event filters for PMUv3 - */ -#define ARMV8_PMU_EXCLUDE_EL1 (1 << 31) -#define ARMV8_PMU_EXCLUDE_EL0 (1 << 30) -#define ARMV8_PMU_INCLUDE_EL2 (1 << 27) - -/* - * PMUSERENR: user enable reg - */ -#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */ -#define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */ -#define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ -#define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ -#define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ - -#endif diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index 7bd3cdb533ea..2065f46fa740 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -17,6 +17,53 @@ #ifndef __ASM_PERF_EVENT_H #define __ASM_PERF_EVENT_H +#define ARMV8_PMU_MAX_COUNTERS 32 +#define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) + +/* + * Per-CPU PMCR: config reg + */ +#define ARMV8_PMU_PMCR_E (1 << 0) /* Enable all counters */ +#define ARMV8_PMU_PMCR_P (1 << 1) /* Reset all counters */ +#define ARMV8_PMU_PMCR_C (1 << 2) /* Cycle counter reset */ +#define ARMV8_PMU_PMCR_D (1 << 3) /* CCNT counts every 64th cpu cycle */ +#define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */ +#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ +#define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ +#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */ +#define ARMV8_PMU_PMCR_N_MASK 0x1f +#define ARMV8_PMU_PMCR_MASK 0x7f /* Mask for writable bits */ + +/* + * PMOVSR: counters overflow flag status reg + */ +#define ARMV8_PMU_OVSR_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV8_PMU_OVERFLOWED_MASK ARMV8_PMU_OVSR_MASK + +/* + * PMXEVTYPER: Event selection reg + */ +#define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ +#define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ + +#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR 0 /* Software increment event */ + +/* + * Event filters for PMUv3 + */ +#define ARMV8_PMU_EXCLUDE_EL1 (1 << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1 << 30) +#define ARMV8_PMU_INCLUDE_EL2 (1 << 27) + +/* + * PMUSERENR: user enable reg + */ +#define ARMV8_PMU_USERENR_MASK 0xf /* Mask for writable bits */ +#define ARMV8_PMU_USERENR_EN (1 << 0) /* PMU regs can be accessed at EL0 */ +#define ARMV8_PMU_USERENR_SW (1 << 1) /* PMSWINC can be written at EL0 */ +#define ARMV8_PMU_USERENR_CR (1 << 2) /* Cycle counter can be read at EL0 */ +#define ARMV8_PMU_USERENR_ER (1 << 3) /* Event counter can be read at EL0 */ + #ifdef CONFIG_PERF_EVENTS struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 767c4f6e1f5b..f419a7c075a4 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -20,6 +20,7 @@ */ #include +#include #include #include @@ -384,9 +385,6 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = { #define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \ (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) -#define ARMV8_MAX_COUNTERS 32 -#define ARMV8_COUNTER_MASK (ARMV8_MAX_COUNTERS - 1) - /* * ARMv8 low level PMU access */ @@ -395,40 +393,7 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = { * Perf Event to low level counters mapping */ #define ARMV8_IDX_TO_COUNTER(x) \ - (((x) - ARMV8_IDX_COUNTER0) & ARMV8_COUNTER_MASK) - -/* - * Per-CPU PMCR: config reg - */ -#define ARMV8_PMCR_E (1 << 0) /* Enable all counters */ -#define ARMV8_PMCR_P (1 << 1) /* Reset all counters */ -#define ARMV8_PMCR_C (1 << 2) /* Cycle counter reset */ -#define ARMV8_PMCR_D (1 << 3) /* CCNT counts every 64th cpu cycle */ -#define ARMV8_PMCR_X (1 << 4) /* Export to ETM */ -#define ARMV8_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ -#define ARMV8_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */ -#define ARMV8_PMCR_N_SHIFT 11 /* Number of counters supported */ -#define ARMV8_PMCR_N_MASK 0x1f -#define ARMV8_PMCR_MASK 0x7f /* Mask for writable bits */ - -/* - * PMOVSR: counters overflow flag status reg - */ -#define ARMV8_OVSR_MASK 0xffffffff /* Mask for writable bits */ -#define ARMV8_OVERFLOWED_MASK ARMV8_OVSR_MASK - -/* - * PMXEVTYPER: Event selection reg - */ -#define ARMV8_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ -#define ARMV8_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ - -/* - * Event filters for PMUv3 - */ -#define ARMV8_EXCLUDE_EL1 (1 << 31) -#define ARMV8_EXCLUDE_EL0 (1 << 30) -#define ARMV8_INCLUDE_EL2 (1 << 27) + (((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK) static inline u32 armv8pmu_pmcr_read(void) { @@ -439,14 +404,14 @@ static inline u32 armv8pmu_pmcr_read(void) static inline void armv8pmu_pmcr_write(u32 val) { - val &= ARMV8_PMCR_MASK; + val &= ARMV8_PMU_PMCR_MASK; isb(); asm volatile("msr pmcr_el0, %0" :: "r" (val)); } static inline int armv8pmu_has_overflowed(u32 pmovsr) { - return pmovsr & ARMV8_OVERFLOWED_MASK; + return pmovsr & ARMV8_PMU_OVERFLOWED_MASK; } static inline int armv8pmu_counter_valid(struct arm_pmu *cpu_pmu, int idx) @@ -512,7 +477,7 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) static inline void armv8pmu_write_evtype(int idx, u32 val) { if (armv8pmu_select_counter(idx) == idx) { - val &= ARMV8_EVTYPE_MASK; + val &= ARMV8_PMU_EVTYPE_MASK; asm volatile("msr pmxevtyper_el0, %0" :: "r" (val)); } } @@ -558,7 +523,7 @@ static inline u32 armv8pmu_getreset_flags(void) asm volatile("mrs %0, pmovsclr_el0" : "=r" (value)); /* Write to clear flags */ - value &= ARMV8_OVSR_MASK; + value &= ARMV8_PMU_OVSR_MASK; asm volatile("msr pmovsclr_el0, %0" :: "r" (value)); return value; @@ -696,7 +661,7 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu) raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Enable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMCR_E); + armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -707,7 +672,7 @@ static void armv8pmu_stop(struct arm_pmu *cpu_pmu) raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Disable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMCR_E); + armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } @@ -717,7 +682,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, int idx; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - unsigned long evtype = hwc->config_base & ARMV8_EVTYPE_EVENT; + unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT; /* Always place a cycle counter into the cycle counter. */ if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) { @@ -754,11 +719,11 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, attr->exclude_kernel != attr->exclude_hv) return -EINVAL; if (attr->exclude_user) - config_base |= ARMV8_EXCLUDE_EL0; + config_base |= ARMV8_PMU_EXCLUDE_EL0; if (!is_kernel_in_hyp_mode() && attr->exclude_kernel) - config_base |= ARMV8_EXCLUDE_EL1; + config_base |= ARMV8_PMU_EXCLUDE_EL1; if (!attr->exclude_hv) - config_base |= ARMV8_INCLUDE_EL2; + config_base |= ARMV8_PMU_INCLUDE_EL2; /* * Install the filter into config_base as this is used to @@ -784,35 +749,36 @@ static void armv8pmu_reset(void *info) * Initialize & Reset PMNC. Request overflow interrupt for * 64 bit cycle counter but cheat in armv8pmu_write_counter(). */ - armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C | ARMV8_PMCR_LC); + armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | + ARMV8_PMU_PMCR_LC); } static int armv8_pmuv3_map_event(struct perf_event *event) { return armpmu_map_event(event, &armv8_pmuv3_perf_map, &armv8_pmuv3_perf_cache_map, - ARMV8_EVTYPE_EVENT); + ARMV8_PMU_EVTYPE_EVENT); } static int armv8_a53_map_event(struct perf_event *event) { return armpmu_map_event(event, &armv8_a53_perf_map, &armv8_a53_perf_cache_map, - ARMV8_EVTYPE_EVENT); + ARMV8_PMU_EVTYPE_EVENT); } static int armv8_a57_map_event(struct perf_event *event) { return armpmu_map_event(event, &armv8_a57_perf_map, &armv8_a57_perf_cache_map, - ARMV8_EVTYPE_EVENT); + ARMV8_PMU_EVTYPE_EVENT); } static int armv8_thunder_map_event(struct perf_event *event) { return armpmu_map_event(event, &armv8_thunder_perf_map, &armv8_thunder_perf_cache_map, - ARMV8_EVTYPE_EVENT); + ARMV8_PMU_EVTYPE_EVENT); } static void armv8pmu_read_num_pmnc_events(void *info) @@ -820,7 +786,7 @@ static void armv8pmu_read_num_pmnc_events(void *info) int *nb_cnt = info; /* Read the nb of CNTx counters supported from PMNC */ - *nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK; + *nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; /* Add the CPU cycles counter */ *nb_cnt += 1; From 82c7d823cc31cf56d964eebe1f91aaf1691cddce Mon Sep 17 00:00:00 2001 From: Andrew Price Date: Tue, 22 Mar 2016 17:36:34 +0000 Subject: [PATCH 102/196] dlm: config: Fix ENOMEM failures in make_cluster() Commit 1ae1602de0 "configfs: switch ->default groups to a linked list" left the NULL gps pointer behind after removing the kcalloc() call which made it non-NULL. It also left the !gps check in place so make_cluster() now fails with ENOMEM. Remove the remaining uses of the gps variable to fix that. Reviewed-by: Bob Peterson Reviewed-by: Andreas Gruenbacher Signed-off-by: Andrew Price Signed-off-by: David Teigland --- fs/dlm/config.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 519112168a9e..1669f6291c95 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -343,13 +343,12 @@ static struct config_group *make_cluster(struct config_group *g, struct dlm_cluster *cl = NULL; struct dlm_spaces *sps = NULL; struct dlm_comms *cms = NULL; - void *gps = NULL; cl = kzalloc(sizeof(struct dlm_cluster), GFP_NOFS); sps = kzalloc(sizeof(struct dlm_spaces), GFP_NOFS); cms = kzalloc(sizeof(struct dlm_comms), GFP_NOFS); - if (!cl || !gps || !sps || !cms) + if (!cl || !sps || !cms) goto fail; config_group_init_type_name(&cl->group, name, &cluster_type); From 431597bb95560c975221c0394c442723d7a21f2d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 29 Mar 2016 16:39:12 +0100 Subject: [PATCH 103/196] arm64: defconfig: updates for 4.6 A few defconfig updates got dropped on the floor during the merge window, so I've rounded up the remainder here: * Fix duplicate definition of MMC_BLOCK_MINORS and bump to 32 for msm8916 * CPUFreq support for the Juno platform, using the MHU/SCPI interface * Removal of the default command line, which assumed a console called ttyAMA0 * Bits and pieces for the Hi6220 (96Boards HiKey) Signed-off-by: Will Deacon --- arch/arm64/configs/defconfig | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index f70505186820..a44ef995d8ae 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -68,11 +68,13 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y CONFIG_XEN=y -CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y CONFIG_CPU_IDLE=y CONFIG_ARM_CPUIDLE=y +CONFIG_CPU_FREQ=y +CONFIG_ARM_BIG_LITTLE_CPUFREQ=y +CONFIG_ARM_SCPI_CPUFREQ=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -80,7 +82,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_BPF_JIT=y # CONFIG_WIRELESS is not set @@ -144,16 +145,18 @@ CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y CONFIG_SERIAL_MVEBU_UART=y CONFIG_VIRTIO_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_I2C=y CONFIG_I2C_CHARDEV=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y CONFIG_I2C_MV64XXX=y CONFIG_I2C_QUP=y +CONFIG_I2C_TEGRA=y CONFIG_I2C_UNIPHIER_F=y CONFIG_I2C_RCAR=y CONFIG_SPI=y CONFIG_SPI_PL022=y CONFIG_SPI_QUP=y CONFIG_SPMI=y +CONFIG_PINCTRL_SINGLE=y CONFIG_PINCTRL_MSM8916=y CONFIG_PINCTRL_QCOM_SPMI_PMIC=y CONFIG_GPIO_SYSFS=y @@ -196,6 +199,7 @@ CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y +CONFIG_USB_DWC2=y CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_UDC=y CONFIG_USB_CHIPIDEA_HOST=y @@ -205,19 +209,20 @@ CONFIG_USB_MSM_OTG=y CONFIG_USB_ULPI=y CONFIG_USB_GADGET=y CONFIG_MMC=y -CONFIG_MMC_BLOCK_MINORS=16 +CONFIG_MMC_BLOCK_MINORS=32 CONFIG_MMC_ARMMMCI=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_TEGRA=y CONFIG_MMC_SDHCI_MSM=y CONFIG_MMC_SPI=y -CONFIG_MMC_SUNXI=y CONFIG_MMC_DW=y CONFIG_MMC_DW_EXYNOS=y -CONFIG_MMC_BLOCK_MINORS=16 +CONFIG_MMC_DW_K3=y +CONFIG_MMC_SUNXI=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y CONFIG_LEDS_SYSCON=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y @@ -229,8 +234,8 @@ CONFIG_RTC_DRV_PL031=y CONFIG_RTC_DRV_SUN6I=y CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y -CONFIG_QCOM_BAM_DMA=y CONFIG_TEGRA20_APB_DMA=y +CONFIG_QCOM_BAM_DMA=y CONFIG_RCAR_DMAC=y CONFIG_VFIO=y CONFIG_VFIO_PCI=y @@ -239,20 +244,26 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_MMIO=y CONFIG_XEN_GNTDEV=y CONFIG_XEN_GRANT_DEV_ALLOC=y +CONFIG_COMMON_CLK_SCPI=y CONFIG_COMMON_CLK_CS2000_CP=y CONFIG_COMMON_CLK_QCOM=y CONFIG_MSM_GCC_8916=y CONFIG_HWSPINLOCK_QCOM=y +CONFIG_MAILBOX=y +CONFIG_ARM_MHU=y +CONFIG_HI6220_MBOX=y CONFIG_ARM_SMMU=y CONFIG_QCOM_SMEM=y CONFIG_QCOM_SMD=y CONFIG_QCOM_SMD_RPM=y CONFIG_ARCH_TEGRA_132_SOC=y CONFIG_ARCH_TEGRA_210_SOC=y -CONFIG_HISILICON_IRQ_MBIGEN=y CONFIG_EXTCON_USB_GPIO=y +CONFIG_COMMON_RESET_HI6220=y CONFIG_PHY_RCAR_GEN3_USB2=y +CONFIG_PHY_HI6220_USB=y CONFIG_PHY_XGENE=y +CONFIG_ARM_SCPI_PROTOCOL=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y CONFIG_FANOTIFY=y @@ -264,6 +275,7 @@ CONFIG_CUSE=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y +CONFIG_CONFIGFS_FS=y CONFIG_EFIVAR_FS=y CONFIG_SQUASHFS=y CONFIG_NFS_FS=y From 3ea223adcb0c5893a6dc8ed3a84dce264cbb61d6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 29 Mar 2016 18:46:04 -0300 Subject: [PATCH 104/196] perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples In 473398a21d28 ("perf tools: Add cpumode to struct perf_sample"), I missed some places where perf_sample fields are directly initialized in addition to what is done in perf_evsel__parse_sample(), namely when synthesizing PERF_RECORD_{MMAP*,COMM,FORK,EXIT} for pre-existing threads and also in intel_pt and intel_bts when synthesizing events from processor trace, the jitdump code also was affected, fix it. The problem was noticed with running: # perf record -e intel_pt//u true # perf script Where the samples wouldn't get resolved because perf_sample.cpumode would be left as zero, i.e. PERF_RECORD_MISC_CPUMODE_UNKNOWN, not resolving as kernel, hypervisor or user cpu modes. Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Fixes: 473398a21d28 ("perf tools: Add cpumode to struct perf_sample") Link: http://lkml.kernel.org/n/tip-n5sdauxgk24d5nun8kuuu2mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.c | 23 ++++++++++++++++------- tools/perf/util/intel-bts.c | 1 + tools/perf/util/intel-pt.c | 3 +++ tools/perf/util/jitdump.c | 2 ++ 4 files changed, 22 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 52cf479bc593..dad55d04ffdd 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -56,13 +56,22 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } -static struct perf_sample synth_sample = { +static int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process) +{ + struct perf_sample synth_sample = { .pid = -1, .tid = -1, .time = -1, .stream_id = -1, .cpu = -1, .period = 1, + .cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK, + }; + + return process(tool, event, &synth_sample, machine); }; /* @@ -186,7 +195,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0) return -1; - if (process(tool, event, &synth_sample, machine) != 0) + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) return -1; return tgid; @@ -218,7 +227,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool, event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size); - if (process(tool, event, &synth_sample, machine) != 0) + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) return -1; return 0; @@ -344,7 +353,7 @@ out: event->mmap2.pid = tgid; event->mmap2.tid = pid; - if (process(tool, event, &synth_sample, machine) != 0) { + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { rc = -1; break; } @@ -402,7 +411,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, memcpy(event->mmap.filename, pos->dso->long_name, pos->dso->long_name_len + 1); - if (process(tool, event, &synth_sample, machine) != 0) { + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { rc = -1; break; } @@ -472,7 +481,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, /* * Send the prepared comm event */ - if (process(tool, comm_event, &synth_sample, machine) != 0) + if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0) break; rc = 0; @@ -701,7 +710,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, event->mmap.len = map->end - event->mmap.start; event->mmap.pid = machine->pid; - err = process(tool, event, &synth_sample, machine); + err = perf_tool__process_synth_event(tool, event, machine, process); free(event); return err; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 6bc3ecd2e7ca..abf1366e2a24 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -279,6 +279,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, event.sample.header.misc = PERF_RECORD_MISC_USER; event.sample.header.size = sizeof(struct perf_event_header); + sample.cpumode = PERF_RECORD_MISC_USER; sample.ip = le64_to_cpu(branch->from); sample.pid = btsq->pid; sample.tid = btsq->tid; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 05d815851be1..407f11b97c8d 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -979,6 +979,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (!pt->timeless_decoding) sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.cpumode = PERF_RECORD_MISC_USER; sample.ip = ptq->state->from_ip; sample.pid = ptq->pid; sample.tid = ptq->tid; @@ -1035,6 +1036,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) if (!pt->timeless_decoding) sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.cpumode = PERF_RECORD_MISC_USER; sample.ip = ptq->state->from_ip; sample.pid = ptq->pid; sample.tid = ptq->tid; @@ -1092,6 +1094,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) if (!pt->timeless_decoding) sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.cpumode = PERF_RECORD_MISC_USER; sample.ip = ptq->state->from_ip; sample.pid = ptq->pid; sample.tid = ptq->tid; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index cd272cc21e05..ad0c0bb1fbc7 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -417,6 +417,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) * use first address as sample address */ memset(&sample, 0, sizeof(sample)); + sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; sample.time = id->time; @@ -505,6 +506,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) * use first address as sample address */ memset(&sample, 0, sizeof(sample)); + sample.cpumode = PERF_RECORD_MISC_USER; sample.pid = pid; sample.tid = tid; sample.time = id->time; From f39bb4579cbf3ff174d936d37aa3669eb98370c6 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:06 +0100 Subject: [PATCH 105/196] clk: mediatek: Make reset_control_ops const The mtk_reset_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Reviewed-by: Matthias Brugger Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/reset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/reset.c b/drivers/clk/mediatek/reset.c index 9e9fe4b19ac4..309049d41f1b 100644 --- a/drivers/clk/mediatek/reset.c +++ b/drivers/clk/mediatek/reset.c @@ -57,7 +57,7 @@ static int mtk_reset(struct reset_controller_dev *rcdev, return mtk_reset_deassert(rcdev, id); } -static struct reset_control_ops mtk_reset_ops = { +static const struct reset_control_ops mtk_reset_ops = { .assert = mtk_reset_assert, .deassert = mtk_reset_deassert, .reset = mtk_reset, From fd92f41dc2527722e5fd63f859ff811482f0ce1a Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:07 +0100 Subject: [PATCH 106/196] clk: mmp: Make reset_control_ops const The mmp_clk_reset_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Signed-off-by: Stephen Boyd --- drivers/clk/mmp/reset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/mmp/reset.c b/drivers/clk/mmp/reset.c index b54da1fe73f0..b4e4d6aa2631 100644 --- a/drivers/clk/mmp/reset.c +++ b/drivers/clk/mmp/reset.c @@ -74,7 +74,7 @@ static int mmp_clk_reset_deassert(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops mmp_clk_reset_ops = { +static const struct reset_control_ops mmp_clk_reset_ops = { .assert = mmp_clk_reset_assert, .deassert = mmp_clk_reset_deassert, }; From 3fb950fea6e14b159899b713ede0b7506ca03649 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:08 +0100 Subject: [PATCH 107/196] clk: rockchip: Make reset_control_ops const The rockchip_softrst_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- drivers/clk/rockchip/softrst.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/softrst.c b/drivers/clk/rockchip/softrst.c index 552f7bb15bc5..21218987bbc3 100644 --- a/drivers/clk/rockchip/softrst.c +++ b/drivers/clk/rockchip/softrst.c @@ -81,7 +81,7 @@ static int rockchip_softrst_deassert(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops rockchip_softrst_ops = { +static const struct reset_control_ops rockchip_softrst_ops = { .assert = rockchip_softrst_assert, .deassert = rockchip_softrst_deassert, }; From b1b69c5dd5ada9be222721dd297c329dafb65d06 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:09 +0100 Subject: [PATCH 108/196] clk: atlas7: Make reset_control_ops const The atlas7_rst_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Signed-off-by: Stephen Boyd --- drivers/clk/sirf/clk-atlas7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sirf/clk-atlas7.c b/drivers/clk/sirf/clk-atlas7.c index 957aae63e7cc..d0c6c9a2d06a 100644 --- a/drivers/clk/sirf/clk-atlas7.c +++ b/drivers/clk/sirf/clk-atlas7.c @@ -1423,7 +1423,7 @@ static int atlas7_reset_module(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops atlas7_rst_ops = { +static const struct reset_control_ops atlas7_rst_ops = { .reset = atlas7_reset_module, }; From 5e7bc9c6cee68fdd3583eb689583214a3d56341e Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:10 +0100 Subject: [PATCH 109/196] clk: sunxi: Make reset_control_ops const The sunxi_ve_reset_ops, sun9i_mmc_reset_ops, and sunxi_usb_reset_ops structures are never modified. Make them const. Signed-off-by: Philipp Zabel Signed-off-by: Stephen Boyd --- drivers/clk/sunxi/clk-a10-ve.c | 2 +- drivers/clk/sunxi/clk-sun9i-mmc.c | 2 +- drivers/clk/sunxi/clk-usb.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/sunxi/clk-a10-ve.c b/drivers/clk/sunxi/clk-a10-ve.c index 044c1717b762..d9ea22ec4e25 100644 --- a/drivers/clk/sunxi/clk-a10-ve.c +++ b/drivers/clk/sunxi/clk-a10-ve.c @@ -85,7 +85,7 @@ static int sunxi_ve_of_xlate(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops sunxi_ve_reset_ops = { +static const struct reset_control_ops sunxi_ve_reset_ops = { .assert = sunxi_ve_reset_assert, .deassert = sunxi_ve_reset_deassert, }; diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c index a9b176139aca..028dd832a39f 100644 --- a/drivers/clk/sunxi/clk-sun9i-mmc.c +++ b/drivers/clk/sunxi/clk-sun9i-mmc.c @@ -83,7 +83,7 @@ static int sun9i_mmc_reset_deassert(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops sun9i_mmc_reset_ops = { +static const struct reset_control_ops sun9i_mmc_reset_ops = { .assert = sun9i_mmc_reset_assert, .deassert = sun9i_mmc_reset_deassert, }; diff --git a/drivers/clk/sunxi/clk-usb.c b/drivers/clk/sunxi/clk-usb.c index 5432b1c198a4..fe0c3d169377 100644 --- a/drivers/clk/sunxi/clk-usb.c +++ b/drivers/clk/sunxi/clk-usb.c @@ -76,7 +76,7 @@ static int sunxi_usb_reset_deassert(struct reset_controller_dev *rcdev, return 0; } -static struct reset_control_ops sunxi_usb_reset_ops = { +static const struct reset_control_ops sunxi_usb_reset_ops = { .assert = sunxi_usb_reset_assert, .deassert = sunxi_usb_reset_deassert, }; From 7ba256d2aa2a18e24b7c9ec4e03cd22b0149c51c Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:11 +0100 Subject: [PATCH 110/196] clk: tegra: Make reset_control_ops const The rst_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c index 2a3a4fe803d6..f60fe2e344ca 100644 --- a/drivers/clk/tegra/clk.c +++ b/drivers/clk/tegra/clk.c @@ -271,7 +271,7 @@ void __init tegra_init_from_table(struct tegra_clk_init_table *tbl, } } -static struct reset_control_ops rst_ops = { +static const struct reset_control_ops rst_ops = { .assert = tegra_clk_rst_assert, .deassert = tegra_clk_rst_deassert, }; From add479eeb1a208a31ab913ae7c97506a81383079 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 25 Feb 2016 10:45:12 +0100 Subject: [PATCH 111/196] clk: qcom: Make reset_control_ops const The qcom_reset_ops structure is never modified. Make it const. Signed-off-by: Philipp Zabel Signed-off-by: Stephen Boyd --- drivers/clk/qcom/reset.c | 2 +- drivers/clk/qcom/reset.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index 6c977d3a8590..0324d8daab9b 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -55,7 +55,7 @@ qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) return regmap_update_bits(rst->regmap, map->reg, mask, 0); } -struct reset_control_ops qcom_reset_ops = { +const struct reset_control_ops qcom_reset_ops = { .reset = qcom_reset, .assert = qcom_reset_assert, .deassert = qcom_reset_deassert, diff --git a/drivers/clk/qcom/reset.h b/drivers/clk/qcom/reset.h index 0e11e2130f97..cda877927d43 100644 --- a/drivers/clk/qcom/reset.h +++ b/drivers/clk/qcom/reset.h @@ -32,6 +32,6 @@ struct qcom_reset_controller { #define to_qcom_reset_controller(r) \ container_of(r, struct qcom_reset_controller, rcdev); -extern struct reset_control_ops qcom_reset_ops; +extern const struct reset_control_ops qcom_reset_ops; #endif From bc95d4f0a920150e77083c2946fe7b7d2f6e217c Mon Sep 17 00:00:00 2001 From: Matthew McClintock Date: Wed, 23 Mar 2016 17:04:59 -0500 Subject: [PATCH 112/196] clk: qcom: ipq4019: switch remaining defines to enums When this was added not all the remaining defines were switched over to use enums, so let's complete that process here Reported-by: Stephen Boyd Signed-off-by: Matthew McClintock Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-ipq4019.c | 60 ++++++++++++++-------------------- 1 file changed, 25 insertions(+), 35 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index 5428efb9fbf5..3599ade11b0c 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -129,20 +129,10 @@ static const char * const gcc_xo_ddr_500_200[] = { }; #define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) } -#define P_XO 0 -#define FE_PLL_200 1 -#define FE_PLL_500 2 -#define DDRC_PLL_666 3 - -#define DDRC_PLL_666_SDCC 1 -#define FE_PLL_125_DLY 1 - -#define FE_PLL_WCSS2G 1 -#define FE_PLL_WCSS5G 1 static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = { F(48000000, P_XO, 1, 0, 0), - F(200000000, FE_PLL_200, 1, 0, 0), + F(200000000, P_FEPLL200, 1, 0, 0), { } }; @@ -334,15 +324,15 @@ static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = { }; static const struct freq_tbl ftbl_gcc_blsp1_uart1_2_apps_clk[] = { - F(1843200, FE_PLL_200, 1, 144, 15625), - F(3686400, FE_PLL_200, 1, 288, 15625), - F(7372800, FE_PLL_200, 1, 576, 15625), - F(14745600, FE_PLL_200, 1, 1152, 15625), - F(16000000, FE_PLL_200, 1, 2, 25), + F(1843200, P_FEPLL200, 1, 144, 15625), + F(3686400, P_FEPLL200, 1, 288, 15625), + F(7372800, P_FEPLL200, 1, 576, 15625), + F(14745600, P_FEPLL200, 1, 1152, 15625), + F(16000000, P_FEPLL200, 1, 2, 25), F(24000000, P_XO, 1, 1, 2), - F(32000000, FE_PLL_200, 1, 4, 25), - F(40000000, FE_PLL_200, 1, 1, 5), - F(46400000, FE_PLL_200, 1, 29, 125), + F(32000000, P_FEPLL200, 1, 4, 25), + F(40000000, P_FEPLL200, 1, 1, 5), + F(46400000, P_FEPLL200, 1, 29, 125), F(48000000, P_XO, 1, 0, 0), { } }; @@ -410,9 +400,9 @@ static struct clk_branch gcc_blsp1_uart2_apps_clk = { }; static const struct freq_tbl ftbl_gcc_gp_clk[] = { - F(1250000, FE_PLL_200, 1, 16, 0), - F(2500000, FE_PLL_200, 1, 8, 0), - F(5000000, FE_PLL_200, 1, 4, 0), + F(1250000, P_FEPLL200, 1, 16, 0), + F(2500000, P_FEPLL200, 1, 8, 0), + F(5000000, P_FEPLL200, 1, 4, 0), { } }; @@ -512,11 +502,11 @@ static struct clk_branch gcc_gp3_clk = { static const struct freq_tbl ftbl_gcc_sdcc1_apps_clk[] = { F(144000, P_XO, 1, 3, 240), F(400000, P_XO, 1, 1, 0), - F(20000000, FE_PLL_500, 1, 1, 25), - F(25000000, FE_PLL_500, 1, 1, 20), - F(50000000, FE_PLL_500, 1, 1, 10), - F(100000000, FE_PLL_500, 1, 1, 5), - F(193000000, DDRC_PLL_666_SDCC, 1, 0, 0), + F(20000000, P_FEPLL500, 1, 1, 25), + F(25000000, P_FEPLL500, 1, 1, 20), + F(50000000, P_FEPLL500, 1, 1, 10), + F(100000000, P_FEPLL500, 1, 1, 5), + F(193000000, P_DDRPLL, 1, 0, 0), { } }; @@ -536,9 +526,9 @@ static struct clk_rcg2 sdcc1_apps_clk_src = { static const struct freq_tbl ftbl_gcc_apps_clk[] = { F(48000000, P_XO, 1, 0, 0), - F(200000000, FE_PLL_200, 1, 0, 0), - F(500000000, FE_PLL_500, 1, 0, 0), - F(626000000, DDRC_PLL_666, 1, 0, 0), + F(200000000, P_FEPLL200, 1, 0, 0), + F(500000000, P_FEPLL500, 1, 0, 0), + F(626000000, P_DDRPLLAPSS, 1, 0, 0), { } }; @@ -557,7 +547,7 @@ static struct clk_rcg2 apps_clk_src = { static const struct freq_tbl ftbl_gcc_apps_ahb_clk[] = { F(48000000, P_XO, 1, 0, 0), - F(100000000, FE_PLL_200, 2, 0, 0), + F(100000000, P_FEPLL200, 2, 0, 0), { } }; @@ -940,7 +930,7 @@ static struct clk_branch gcc_usb2_mock_utmi_clk = { }; static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk[] = { - F(2000000, FE_PLL_200, 10, 0, 0), + F(2000000, P_FEPLL200, 10, 0, 0), { } }; @@ -1007,7 +997,7 @@ static struct clk_branch gcc_usb3_mock_utmi_clk = { }; static const struct freq_tbl ftbl_gcc_fephy_dly_clk[] = { - F(125000000, FE_PLL_125_DLY, 1, 0, 0), + F(125000000, P_FEPLL125DLY, 1, 0, 0), { } }; @@ -1027,7 +1017,7 @@ static struct clk_rcg2 fephy_125m_dly_clk_src = { static const struct freq_tbl ftbl_gcc_wcss2g_clk[] = { F(48000000, P_XO, 1, 0, 0), - F(250000000, FE_PLL_WCSS2G, 1, 0, 0), + F(250000000, P_FEPLLWCSS2G, 1, 0, 0), { } }; @@ -1097,7 +1087,7 @@ static struct clk_branch gcc_wcss2g_rtc_clk = { static const struct freq_tbl ftbl_gcc_wcss5g_clk[] = { F(48000000, P_XO, 1, 0, 0), - F(250000000, FE_PLL_WCSS5G, 1, 0, 0), + F(250000000, P_FEPLLWCSS5G, 1, 0, 0), { } }; From 2aac7ddf9a410e3418c9cc69618f304550466793 Mon Sep 17 00:00:00 2001 From: Matthew McClintock Date: Wed, 23 Mar 2016 17:05:00 -0500 Subject: [PATCH 113/196] clk: qcom: ipq4019: add some fixed clocks for ddrppl and fepll Drivers for these don't exist yet so we will add them as fixed clocks so we don't BUG() if we change clocks that reference these clocks. Signed-off-by: Matthew McClintock Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-ipq4019.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index 3599ade11b0c..3cd1af0af0d9 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -1315,6 +1315,16 @@ MODULE_DEVICE_TABLE(of, gcc_ipq4019_match_table); static int gcc_ipq4019_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; + + clk_register_fixed_rate(dev, "fepll125", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "fepll125dly", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "fepllwcss2g", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "fepllwcss5g", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "fepll200", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "fepll500", "xo", 0, 200000000); + clk_register_fixed_rate(dev, "ddrpllapss", "xo", 0, 666000000); + return qcom_cc_probe(pdev, &gcc_ipq4019_desc); } From 56768045186c183f1d6e5cd916dd07751a777a8d Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Thu, 7 Jan 2016 14:17:03 -0800 Subject: [PATCH 114/196] ixgbe: Fix for RAR0 not being set to default MAC addr commit c9f53e63c208 ("ixgbe: Refactor MAC address configuration code") introduced code that doesn't set HW register RAR0 to default mac address but FF:FF:FF:FF:FF:FF. Due to this, ixgbe HW discards all incoming packets that doesn't have destination mac address equals to FF:FF:FF:FF:FF:FF. This commit sets RAR0 correctly to default HW mac address. Signed-off-by: Tushar Dave Tested-by: Sowmini Varadhan Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 569cb0757c93..f19327325675 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9329,6 +9329,8 @@ skip_sriov: goto err_sw_init; } + /* Set hw->mac.addr to permanent MAC address */ + ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); setup_timer(&adapter->service_timer, &ixgbe_service_timer, From 9f12df906cd807a05d71aa53a951532d1dd3b888 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 25 Jan 2016 19:36:29 -0800 Subject: [PATCH 115/196] ixgbe: Store VXLAN port number in network order The VXLAN port number should be stored in network order instead of in host order as it is accessed from the hot-path in ATR. This way we can avoid having to do any byte swaps in order to validate the port number. I moved the vxlan_port value into a hole in the read-mostly region of the adapter struct. This way it should be in a warm cache-line instead of in some isolated region in memory when it needs to be accessed. In addition I went through and stripped a bunch of unneeded ifdef flags since having an extra variable present doesn't really hurt anything and makes the code easier to read. I also went through and dropped the NETIF_F_RXCSUM flag which was being set in hw_encap_features but provides no value as the flag is not evaluated in the Rx path. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 8 +-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 61 ++++++------------- 2 files changed, 20 insertions(+), 49 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 84fa28ceb200..458549c06a4f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -661,9 +661,7 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP (u32)(1 << 9) #define IXGBE_FLAG2_PTP_PPS_ENABLED (u32)(1 << 10) #define IXGBE_FLAG2_PHY_INTERRUPT (u32)(1 << 11) -#ifdef CONFIG_IXGBE_VXLAN #define IXGBE_FLAG2_VXLAN_REREG_NEEDED BIT(12) -#endif #define IXGBE_FLAG2_VLAN_PROMISC BIT(13) /* Tx fast path data */ @@ -675,6 +673,9 @@ struct ixgbe_adapter { int num_rx_queues; u16 rx_itr_setting; + /* Port number used to identify VXLAN traffic */ + __be16 vxlan_port; + /* TX */ struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp; @@ -782,9 +783,6 @@ struct ixgbe_adapter { u32 timer_event_accumulator; u32 vferr_refcount; struct ixgbe_mac_addr *mac_table; -#ifdef CONFIG_IXGBE_VXLAN - u16 vxlan_port; -#endif struct kobject *info_kobj; #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff *ixgbe_hwmon_buff; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f19327325675..f67c9a6429ac 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4531,9 +4531,7 @@ static void ixgbe_clear_vxlan_port(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: IXGBE_WRITE_REG(&adapter->hw, IXGBE_VXLANCTRL, 0); -#ifdef CONFIG_IXGBE_VXLAN adapter->vxlan_port = 0; -#endif break; default: break; @@ -7561,9 +7559,6 @@ static void ixgbe_atr(struct ixgbe_ring *ring, } hdr; struct tcphdr *th; struct sk_buff *skb; -#ifdef CONFIG_IXGBE_VXLAN - u8 encap = false; -#endif /* CONFIG_IXGBE_VXLAN */ __be16 vlan_id; /* if ring doesn't have a interrupt vector, cannot perform ATR */ @@ -7579,28 +7574,21 @@ static void ixgbe_atr(struct ixgbe_ring *ring, /* snag network header to get L4 type and address */ skb = first->skb; hdr.network = skb_network_header(skb); - if (!skb->encapsulation) { - th = tcp_hdr(skb); - } else { + th = tcp_hdr(skb); #ifdef CONFIG_IXGBE_VXLAN + if (skb->encapsulation && + first->protocol == htons(ETH_P_IP) && + hdr.ipv4->protocol != IPPROTO_UDP) { struct ixgbe_adapter *adapter = q_vector->adapter; - if (!adapter->vxlan_port) - return; - if (first->protocol != htons(ETH_P_IP) || - hdr.ipv4->version != IPVERSION || - hdr.ipv4->protocol != IPPROTO_UDP) { - return; + /* verify the port is recognized as VXLAN */ + if (adapter->vxlan_port && + udp_hdr(skb)->dest == adapter->vxlan_port) { + hdr.network = skb_inner_network_header(skb); + th = inner_tcp_hdr(skb); } - if (ntohs(udp_hdr(skb)->dest) != adapter->vxlan_port) - return; - encap = true; - hdr.network = skb_inner_network_header(skb); - th = inner_tcp_hdr(skb); -#else - return; -#endif /* CONFIG_IXGBE_VXLAN */ } +#endif /* CONFIG_IXGBE_VXLAN */ /* Currently only IPv4/IPv6 with TCP is supported */ switch (hdr.ipv4->version) { @@ -7682,10 +7670,8 @@ static void ixgbe_atr(struct ixgbe_ring *ring, break; } -#ifdef CONFIG_IXGBE_VXLAN - if (encap) + if (hdr.network != skb_network_header(skb)) input.formatted.flow_type |= IXGBE_ATR_L4TYPE_TUNNEL_MASK; -#endif /* CONFIG_IXGBE_VXLAN */ /* This assumes the Rx queue and Tx queue are bound to the same CPU */ ixgbe_fdir_add_signature_filter_82599(&q_vector->adapter->hw, @@ -8554,7 +8540,6 @@ static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family, { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - u16 new_port = ntohs(port); if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) return; @@ -8562,18 +8547,18 @@ static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family, if (sa_family == AF_INET6) return; - if (adapter->vxlan_port == new_port) + if (adapter->vxlan_port == port) return; if (adapter->vxlan_port) { netdev_info(dev, "Hit Max num of VXLAN ports, not adding port %d\n", - new_port); + ntohs(port)); return; } - adapter->vxlan_port = new_port; - IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, new_port); + adapter->vxlan_port = port; + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, ntohs(port)); } /** @@ -8586,7 +8571,6 @@ static void ixgbe_del_vxlan_port(struct net_device *dev, sa_family_t sa_family, __be16 port) { struct ixgbe_adapter *adapter = netdev_priv(dev); - u16 new_port = ntohs(port); if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) return; @@ -8594,9 +8578,9 @@ static void ixgbe_del_vxlan_port(struct net_device *dev, sa_family_t sa_family, if (sa_family == AF_INET6) return; - if (adapter->vxlan_port != new_port) { + if (adapter->vxlan_port != port) { netdev_info(dev, "Port %d was not found, not deleting\n", - new_port); + ntohs(port)); return; } @@ -9265,17 +9249,6 @@ skip_sriov: netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; -#ifdef CONFIG_IXGBE_VXLAN - switch (adapter->hw.mac.type) { - case ixgbe_mac_X550: - case ixgbe_mac_X550EM_x: - netdev->hw_enc_features |= NETIF_F_RXCSUM; - break; - default: - break; - } -#endif /* CONFIG_IXGBE_VXLAN */ - #ifdef CONFIG_IXGBE_DCB netdev->dcbnl_ops = &dcbnl_ops; #endif From e2873d43f9c607e9d855b8ae120d5990ba1722df Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 25 Jan 2016 19:39:40 -0800 Subject: [PATCH 116/196] ixgbe: Fix ATR so that it correctly handles IPv6 extension headers The ATR code was assuming that it would be able to use tcp_hdr for every TCP frame that came through. However this isn't the case as it is possible for a frame to arrive that is TCP but sent through something like a raw socket. As a result the driver was setting up bad filters in which tcp_hdr was really pointing to the network header so the data was all invalid. In order to correct this I have added a bit of parsing logic that will determine the TCP header location based off of the network header and either the offset in the case of the IPv4 header, or a walk through the IPv6 extension headers until it encounters the header that indicates IPPROTO_TCP. In addition I have added checks to verify that the lowest protocol provided is recognized as IPv4 or IPv6 to help mitigate raw sockets using ETH_P_ALL from having ATR applied to them. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 45 +++++++++---------- 1 file changed, 21 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f67c9a6429ac..ee81618bb9f0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7558,8 +7558,10 @@ static void ixgbe_atr(struct ixgbe_ring *ring, struct ipv6hdr *ipv6; } hdr; struct tcphdr *th; + unsigned int hlen; struct sk_buff *skb; __be16 vlan_id; + int l4_proto; /* if ring doesn't have a interrupt vector, cannot perform ATR */ if (!q_vector) @@ -7571,10 +7573,14 @@ static void ixgbe_atr(struct ixgbe_ring *ring, ring->atr_count++; + /* currently only IPv4/IPv6 with TCP is supported */ + if ((first->protocol != htons(ETH_P_IP)) && + (first->protocol != htons(ETH_P_IPV6))) + return; + /* snag network header to get L4 type and address */ skb = first->skb; hdr.network = skb_network_header(skb); - th = tcp_hdr(skb); #ifdef CONFIG_IXGBE_VXLAN if (skb->encapsulation && first->protocol == htons(ETH_P_IP) && @@ -7583,43 +7589,34 @@ static void ixgbe_atr(struct ixgbe_ring *ring, /* verify the port is recognized as VXLAN */ if (adapter->vxlan_port && - udp_hdr(skb)->dest == adapter->vxlan_port) { + udp_hdr(skb)->dest == adapter->vxlan_port) hdr.network = skb_inner_network_header(skb); - th = inner_tcp_hdr(skb); - } } #endif /* CONFIG_IXGBE_VXLAN */ /* Currently only IPv4/IPv6 with TCP is supported */ switch (hdr.ipv4->version) { case IPVERSION: - if (hdr.ipv4->protocol != IPPROTO_TCP) - return; + /* access ihl as u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[0] & 0x0F) << 2; + l4_proto = hdr.ipv4->protocol; break; case 6: - if (likely((unsigned char *)th - hdr.network == - sizeof(struct ipv6hdr))) { - if (hdr.ipv6->nexthdr != IPPROTO_TCP) - return; - } else { - __be16 frag_off; - u8 l4_hdr; - - ipv6_skip_exthdr(skb, hdr.network - skb->data + - sizeof(struct ipv6hdr), - &l4_hdr, &frag_off); - if (unlikely(frag_off)) - return; - if (l4_hdr != IPPROTO_TCP) - return; - } + hlen = hdr.network - skb->data; + l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL); + hlen -= hdr.network - skb->data; break; default: return; } - /* skip this packet since it is invalid or the socket is closing */ - if (!th || th->fin) + if (l4_proto != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(hdr.network + hlen); + + /* skip this packet since the socket is closing */ + if (th->fin) return; /* sample on all syn packets or once every atr sample count */ From d90b5b0ec1c7a3099dee9c18071a5b714eb3de52 Mon Sep 17 00:00:00 2001 From: Mark Rustad Date: Fri, 29 Jan 2016 14:44:29 -0800 Subject: [PATCH 117/196] ixgbe: Use udelay to avoid sleeping while atomic Use udelay instead of usleep_range because this can be called while a lock is held. Signed-off-by: Mark Rustad Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 87aca3f7c3de..68a9c646498e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -355,7 +355,7 @@ static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl) command = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL); if (!(command & IXGBE_SB_IOSF_CTRL_BUSY)) break; - usleep_range(10, 20); + udelay(10); } if (ctrl) *ctrl = command; From 6c211fe1e71e2bf7baa45a78ac5358a1f45a7fe9 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Wed, 3 Feb 2016 09:20:48 +0100 Subject: [PATCH 118/196] ixgbe: call ndo_stop() instead of dev_close() when running offline selftest Calling dev_close() causes IFF_UP to be cleared which will remove the interfaces routes and some addresses. That's probably not what the user intended when running the offline selftest. Besides this does not happen if the interface is brought down before the test, so the current behaviour is inconsistent. Instead call the net_device_ops ndo_stop function directly and avoid touching IFF_UP at all. Signed-off-by: Stefan Assmann Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 ++ drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 4 ++-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 458549c06a4f..e4949af7dd6b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -877,6 +877,8 @@ extern const char ixgbe_driver_version[]; extern char ixgbe_default_device_descr[]; #endif /* IXGBE_FCOE */ +int ixgbe_open(struct net_device *netdev); +int ixgbe_close(struct net_device *netdev); void ixgbe_up(struct ixgbe_adapter *adapter); void ixgbe_down(struct ixgbe_adapter *adapter); void ixgbe_reinit_locked(struct ixgbe_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 726e0eeee63b..b3530e1e3ce1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2053,7 +2053,7 @@ static void ixgbe_diag_test(struct net_device *netdev, if (if_running) /* indicate we're in test mode */ - dev_close(netdev); + ixgbe_close(netdev); else ixgbe_reset(adapter); @@ -2091,7 +2091,7 @@ skip_loopback: /* clear testing bit and return adapter to previous state */ clear_bit(__IXGBE_TESTING, &adapter->state); if (if_running) - dev_open(netdev); + ixgbe_open(netdev); else if (hw->mac.ops.disable_tx_laser) hw->mac.ops.disable_tx_laser(hw); } else { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ee81618bb9f0..267a50747cbf 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5992,7 +5992,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) * handler is registered with the OS, the watchdog timer is started, * and the stack is notified that the interface is ready. **/ -static int ixgbe_open(struct net_device *netdev) +int ixgbe_open(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -6094,7 +6094,7 @@ static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) * needs to be disabled. A global MAC reset is issued to stop the * hardware, and all transmit and receive resources are freed. **/ -static int ixgbe_close(struct net_device *netdev) +int ixgbe_close(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); From 324d086709978fce1671ba04087bf90865b04398 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Wed, 3 Feb 2016 09:20:49 +0100 Subject: [PATCH 119/196] ixgbevf: call ndo_stop() instead of dev_close() when running offline selftest Calling dev_close() causes IFF_UP to be cleared which will remove the interfaces routes and some addresses. That's probably not what the user intended when running the offline selftest. Besides this does not happen if the interface is brought down before the test, so the current behaviour is inconsistent. Instead call the net_device_ops ndo_stop function directly and avoid touching IFF_UP at all. Signed-off-by: Stefan Assmann Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ethtool.c | 4 ++-- drivers/net/ethernet/intel/ixgbevf/ixgbevf.h | 2 ++ drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index c48aef613b0a..d7aa4b203f40 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -680,7 +680,7 @@ static void ixgbevf_diag_test(struct net_device *netdev, if (if_running) /* indicate we're in test mode */ - dev_close(netdev); + ixgbevf_close(netdev); else ixgbevf_reset(adapter); @@ -692,7 +692,7 @@ static void ixgbevf_diag_test(struct net_device *netdev, clear_bit(__IXGBEVF_TESTING, &adapter->state); if (if_running) - dev_open(netdev); + ixgbevf_open(netdev); } else { hw_dbg(&adapter->hw, "online testing starting\n"); /* Online tests */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 68ec7daa04fd..991eeae81473 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -486,6 +486,8 @@ extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops; extern const char ixgbevf_driver_name[]; extern const char ixgbevf_driver_version[]; +int ixgbevf_open(struct net_device *netdev); +int ixgbevf_close(struct net_device *netdev); void ixgbevf_up(struct ixgbevf_adapter *adapter); void ixgbevf_down(struct ixgbevf_adapter *adapter); void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0ea14c0a2e74..6a337bbf6820 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3122,7 +3122,7 @@ static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter) * handler is registered with the OS, the watchdog timer is started, * and the stack is notified that the interface is ready. **/ -static int ixgbevf_open(struct net_device *netdev) +int ixgbevf_open(struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -3205,7 +3205,7 @@ err_setup_reset: * needs to be disabled. A global MAC reset is issued to stop the * hardware, and all transmit and receive resources are freed. **/ -static int ixgbevf_close(struct net_device *netdev) +int ixgbevf_close(struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); From 32ca68683532ab629d16cede1102b36ae5346f40 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Wed, 10 Feb 2016 15:16:30 -0800 Subject: [PATCH 120/196] ixgbevf: fix error code path when setting MAC address Return error when a MAC address change is rejected by the PF. This will prevent the user from modifying the MAC address when that operation is not permitted. Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 12 ++++++++---- drivers/net/ethernet/intel/ixgbevf/vf.c | 4 +++- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 6a337bbf6820..b0edae94d73d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3692,19 +3692,23 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; struct sockaddr *addr = p; + int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - ether_addr_copy(netdev->dev_addr, addr->sa_data); - ether_addr_copy(hw->mac.addr, addr->sa_data); - spin_lock_bh(&adapter->mbx_lock); - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + err = hw->mac.ops.set_rar(hw, 0, addr->sa_data, 0); spin_unlock_bh(&adapter->mbx_lock); + if (err) + return -EPERM; + + ether_addr_copy(hw->mac.addr, addr->sa_data); + ether_addr_copy(netdev->dev_addr, addr->sa_data); + return 0; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 61a98f4c5746..4d613a4f2a7f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -408,8 +408,10 @@ static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr, /* if nacked the address was rejected, use "perm_addr" */ if (!ret_val && - (msgbuf[0] == (IXGBE_VF_SET_MAC_ADDR | IXGBE_VT_MSGTYPE_NACK))) + (msgbuf[0] == (IXGBE_VF_SET_MAC_ADDR | IXGBE_VT_MSGTYPE_NACK))) { ixgbevf_get_mac_addr_vf(hw, hw->mac.addr); + return IXGBE_ERR_MBX; + } return ret_val; } From 6e2a60b57a83ea134c06c5226aaff20e7e9ce221 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Wed, 17 Feb 2016 15:55:06 -0800 Subject: [PATCH 121/196] ixgbe: make __ixgbe_setup_tc static This function is only used in ixgbe_main.c Resolves a "missing prototype" warning when building the driver with W=1 Reported-by: Phil Schmitt Signed-off-by: Emil Tantilov Acked-by: John Fastabend Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 267a50747cbf..f5736a3b252e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8376,8 +8376,8 @@ err_out: return -EINVAL; } -int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, - struct tc_to_netdev *tc) +static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) { struct ixgbe_adapter *adapter = netdev_priv(dev); From 176621c964e9279c42c6b641688360e5cd0baedf Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Mon, 7 Mar 2016 09:41:47 -0800 Subject: [PATCH 122/196] ixgbe: fix error handling in TC cls_u32 offload routines Check for handle ids when adding/deleting hash nodes OR adding/deleting filter entries and limit them to max number of links or header nodes supported(IXGBE_MAX_LINK_HANDLE). Start from bit 0 when setting hash table bit-map.(adapter->tables) Signed-off-by: Sridhar Samudrala Acked-by: John Fastabend Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 52 ++++++++++++------- 1 file changed, 34 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f5736a3b252e..ca9c54341784 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8192,10 +8192,17 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter, struct tc_cls_u32_offload *cls) { + u32 uhtid = TC_U32_USERHTID(cls->knode.handle); + u32 loc; int err; + if ((uhtid != 0x800) && (uhtid >= IXGBE_MAX_LINK_HANDLE)) + return -EINVAL; + + loc = cls->knode.handle & 0xfffff; + spin_lock(&adapter->fdir_perfect_lock); - err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, cls->knode.handle); + err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, loc); spin_unlock(&adapter->fdir_perfect_lock); return err; } @@ -8204,20 +8211,30 @@ static int ixgbe_configure_clsu32_add_hnode(struct ixgbe_adapter *adapter, __be16 protocol, struct tc_cls_u32_offload *cls) { + u32 uhtid = TC_U32_USERHTID(cls->hnode.handle); + + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + /* This ixgbe devices do not support hash tables at the moment * so abort when given hash tables. */ if (cls->hnode.divisor > 0) return -EINVAL; - set_bit(TC_U32_USERHTID(cls->hnode.handle), &adapter->tables); + set_bit(uhtid - 1, &adapter->tables); return 0; } static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter, struct tc_cls_u32_offload *cls) { - clear_bit(TC_U32_USERHTID(cls->hnode.handle), &adapter->tables); + u32 uhtid = TC_U32_USERHTID(cls->hnode.handle); + + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + + clear_bit(uhtid - 1, &adapter->tables); return 0; } @@ -8235,27 +8252,29 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, #endif int i, err = 0; u8 queue; - u32 handle; + u32 uhtid, link_uhtid; memset(&mask, 0, sizeof(union ixgbe_atr_input)); - handle = cls->knode.handle; + uhtid = TC_U32_USERHTID(cls->knode.handle); + link_uhtid = TC_U32_USERHTID(cls->knode.link_handle); - /* At the moment cls_u32 jumps to transport layer and skips past + /* At the moment cls_u32 jumps to network layer and skips past * L2 headers. The canonical method to match L2 frames is to use * negative values. However this is error prone at best but really * just broken because there is no way to "know" what sort of hdr - * is in front of the transport layer. Fix cls_u32 to support L2 + * is in front of the network layer. Fix cls_u32 to support L2 * headers when needed. */ if (protocol != htons(ETH_P_IP)) return -EINVAL; - if (cls->knode.link_handle || - cls->knode.link_handle >= IXGBE_MAX_LINK_HANDLE) { + if (link_uhtid) { struct ixgbe_nexthdr *nexthdr = ixgbe_ipv4_jumps; - u32 uhtid = TC_U32_USERHTID(cls->knode.link_handle); - if (!test_bit(uhtid, &adapter->tables)) + if (link_uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + + if (!test_bit(link_uhtid - 1, &adapter->tables)) return -EINVAL; for (i = 0; nexthdr[i].jump; i++) { @@ -8271,10 +8290,7 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, nexthdr->mask != cls->knode.sel->keys[0].mask) return -EINVAL; - if (uhtid >= IXGBE_MAX_LINK_HANDLE) - return -EINVAL; - - adapter->jump_tables[uhtid] = nexthdr->jump; + adapter->jump_tables[link_uhtid] = nexthdr->jump; } return 0; } @@ -8291,13 +8307,13 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, * To add support for new nodes update ixgbe_model.h parse structures * this function _should_ be generic try not to hardcode values here. */ - if (TC_U32_USERHTID(handle) == 0x800) { + if (uhtid == 0x800) { field_ptr = adapter->jump_tables[0]; } else { - if (TC_U32_USERHTID(handle) >= ARRAY_SIZE(adapter->jump_tables)) + if (uhtid >= IXGBE_MAX_LINK_HANDLE) return -EINVAL; - field_ptr = adapter->jump_tables[TC_U32_USERHTID(handle)]; + field_ptr = adapter->jump_tables[uhtid]; } if (!field_ptr) From ebd83ad818d2d4502d5e343388000d5dc829b7a8 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Mon, 7 Mar 2016 09:41:48 -0800 Subject: [PATCH 123/196] ixgbe: Fix cls_u32 offload support for fields with masks Remove the incorrect check for mask in ixgbe_configure_clsu32 and drop the 'mask' field that is not required in struct ixgbe_mat_field Verified with the following filters: #tc qdisc add dev p4p1 ingress #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 800:0:1 u32 ht 800: \ match ip dst 10.0.0.1/8 match ip src 10.0.0.2/8 action drop #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 800:0:2 u32 ht 800: \ match ip dst 11.0.0.1/16 match ip src 11.0.0.2/16 action drop #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 800:0:3 u32 ht 800: \ match ip dst 12.0.0.1/24 match ip src 12.0.0.2/24 action drop #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 800:0:4 u32 ht 800: \ match ip dst 13.0.0.1/32 match ip src 13.0.0.2/32 action drop Signed-off-by: Sridhar Samudrala Acked-by: John Fastabend Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- drivers/net/ethernet/intel/ixgbe/ixgbe_model.h | 9 ++++----- 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ca9c54341784..7df3fe29b210 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8331,8 +8331,7 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, int j; for (j = 0; field_ptr[j].val; j++) { - if (field_ptr[j].off == off && - field_ptr[j].mask == m) { + if (field_ptr[j].off == off) { field_ptr[j].val(input, &mask, val, m); input->filter.formatted.flow_type |= field_ptr[j].type; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h index ce48872d4782..61f729073978 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h @@ -32,7 +32,6 @@ struct ixgbe_mat_field { unsigned int off; - unsigned int mask; int (*val)(struct ixgbe_fdir_filter *input, union ixgbe_atr_input *mask, u32 val, u32 m); @@ -58,9 +57,9 @@ static inline int ixgbe_mat_prgm_dip(struct ixgbe_fdir_filter *input, } static struct ixgbe_mat_field ixgbe_ipv4_fields[] = { - { .off = 12, .mask = -1, .val = ixgbe_mat_prgm_sip, + { .off = 12, .val = ixgbe_mat_prgm_sip, .type = IXGBE_ATR_FLOW_TYPE_IPV4}, - { .off = 16, .mask = -1, .val = ixgbe_mat_prgm_dip, + { .off = 16, .val = ixgbe_mat_prgm_dip, .type = IXGBE_ATR_FLOW_TYPE_IPV4}, { .val = NULL } /* terminal node */ }; @@ -84,9 +83,9 @@ static inline int ixgbe_mat_prgm_dport(struct ixgbe_fdir_filter *input, }; static struct ixgbe_mat_field ixgbe_tcp_fields[] = { - {.off = 0, .mask = 0xffff, .val = ixgbe_mat_prgm_sport, + {.off = 0, .val = ixgbe_mat_prgm_sport, .type = IXGBE_ATR_FLOW_TYPE_TCPV4}, - {.off = 2, .mask = 0xffff, .val = ixgbe_mat_prgm_dport, + {.off = 2, .val = ixgbe_mat_prgm_dport, .type = IXGBE_ATR_FLOW_TYPE_TCPV4}, { .val = NULL } /* terminal node */ }; From b5aea3de88e526a46839b7ccf049fab4f8ad7a4b Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Mon, 7 Mar 2016 09:41:49 -0800 Subject: [PATCH 124/196] ixgbe: Fix cls_u32 offload support for L4 ports Fix support for 16 bit source/dest port matches in ixgbe model. u32 uses a single 32-bit key value for both source and destination ports starting at offset 0. So replace the 2 functions with a single function that takes this key value/mask to program both source and dest ports. Verified with the following filter: #tc qdisc add dev p4p1 ingress #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 1: u32 divisor 1 #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 800:0:10 u32 ht 800: link 1: \ offset at 0 mask 0f00 shift 6 plus 0 eat match ip protocol 6 ff #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 1:0:10 u32 ht 1: \ match tcp src 1024 ffff match tcp dst 80 ffff action drop #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 1:0:11 u32 ht 1: \ match tcp src 1025 ffff action drop #tc filter add dev p4p1 parent ffff: protocol ip prio 99 \ handle 1:0:12 u32 ht 1: \ match tcp dst 81 ffff action drop Signed-off-by: Sridhar Samudrala Acked-by: John Fastabend Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_model.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h index 61f729073978..74c53ad9d268 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h @@ -64,28 +64,20 @@ static struct ixgbe_mat_field ixgbe_ipv4_fields[] = { { .val = NULL } /* terminal node */ }; -static inline int ixgbe_mat_prgm_sport(struct ixgbe_fdir_filter *input, +static inline int ixgbe_mat_prgm_ports(struct ixgbe_fdir_filter *input, union ixgbe_atr_input *mask, u32 val, u32 m) { input->filter.formatted.src_port = val & 0xffff; mask->formatted.src_port = m & 0xffff; - return 0; -}; + input->filter.formatted.dst_port = val >> 16; + mask->formatted.dst_port = m >> 16; -static inline int ixgbe_mat_prgm_dport(struct ixgbe_fdir_filter *input, - union ixgbe_atr_input *mask, - u32 val, u32 m) -{ - input->filter.formatted.dst_port = val & 0xffff; - mask->formatted.dst_port = m & 0xffff; return 0; }; static struct ixgbe_mat_field ixgbe_tcp_fields[] = { - {.off = 0, .val = ixgbe_mat_prgm_sport, - .type = IXGBE_ATR_FLOW_TYPE_TCPV4}, - {.off = 2, .val = ixgbe_mat_prgm_dport, + {.off = 0, .val = ixgbe_mat_prgm_ports, .type = IXGBE_ATR_FLOW_TYPE_TCPV4}, { .val = NULL } /* terminal node */ }; From fd975a7b180c9a8f6e02d2251eaabe9b0dcfeed6 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 9 Mar 2016 20:38:55 +0800 Subject: [PATCH 125/196] gpio: menz127: Drop lock field from struct men_z127_gpio Current code uses a uninitialized spin lock. bgpio_init() already initialized a spin lock, so let's switch to use &gc->bgpio_lock instead and remove the lock from struct men_z127_gpio. Fixes: f436bc2726c6 "gpio: add driver for MEN 16Z127 GPIO controller" Signed-off-by: Axel Lin Signed-off-by: Linus Walleij --- drivers/gpio/gpio-menz127.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c index a68e199d579d..c5c9599a3a71 100644 --- a/drivers/gpio/gpio-menz127.c +++ b/drivers/gpio/gpio-menz127.c @@ -37,7 +37,6 @@ struct men_z127_gpio { void __iomem *reg_base; struct mcb_device *mdev; struct resource *mem; - spinlock_t lock; }; static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio, @@ -69,7 +68,7 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio, debounce /= 50; } - spin_lock(&priv->lock); + spin_lock(&gc->bgpio_lock); db_en = readl(priv->reg_base + MEN_Z127_DBER); @@ -84,7 +83,7 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio, writel(db_en, priv->reg_base + MEN_Z127_DBER); writel(db_cnt, priv->reg_base + GPIO_TO_DBCNT_REG(gpio)); - spin_unlock(&priv->lock); + spin_unlock(&gc->bgpio_lock); return 0; } @@ -97,7 +96,7 @@ static int men_z127_request(struct gpio_chip *gc, unsigned gpio_pin) if (gpio_pin >= gc->ngpio) return -EINVAL; - spin_lock(&priv->lock); + spin_lock(&gc->bgpio_lock); od_en = readl(priv->reg_base + MEN_Z127_ODER); if (gpiochip_line_is_open_drain(gc, gpio_pin)) @@ -106,7 +105,7 @@ static int men_z127_request(struct gpio_chip *gc, unsigned gpio_pin) od_en &= ~BIT(gpio_pin); writel(od_en, priv->reg_base + MEN_Z127_ODER); - spin_unlock(&priv->lock); + spin_unlock(&gc->bgpio_lock); return 0; } From 8d8ee18cc707f498b6dad18915576f23b00bcff8 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Mon, 21 Mar 2016 20:03:50 +0800 Subject: [PATCH 126/196] gpio: xgene: Prevent NULL pointer dereference platform_get_resource() can return NULL, thus add NULL test to prevent NULL pointer dereference. Signed-off-by: Axel Lin Signed-off-by: Linus Walleij --- drivers/gpio/gpio-xgene.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c index c0aa387664bf..0dc916191689 100644 --- a/drivers/gpio/gpio-xgene.c +++ b/drivers/gpio/gpio-xgene.c @@ -173,6 +173,11 @@ static int xgene_gpio_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + err = -EINVAL; + goto err; + } + gpio->base = devm_ioremap_nocache(&pdev->dev, res->start, resource_size(res)); if (!gpio->base) { From a189c017ded0f13650793067fb7a1afbc2b98cd5 Mon Sep 17 00:00:00 2001 From: Sedat Dilek Date: Wed, 30 Mar 2016 10:22:49 +0200 Subject: [PATCH 127/196] tools/lib/lockdep: Fix unsupported 'basename -s' in run_tests.sh Here on Ubuntu/precise I have GNU/coreutils v8.13 installed where 'basename -s' is not supported. The result is that run_tests.sh is not done properly. How to reproduce: $ cd $BUILD_DIR $ LC_ALL=C make -C tools/ liblockdep $ cd tools/lib/lockdep/ $ LC_ALL=C ./run_tests.sh basename: invalid option -- 's' Try `basename --help' for more information. ... timeout: failed to run command `./tests/': Permission denied FAILED! rm: cannot remove `tests/': Is a directory Due to unsupported basename the tests programs are not generated and cannot be removed. Fix this by doing a compatible basename invocation and check for the existence of generated tests programs. For more details see this LKML thread: http://marc.info/?t=145906667300001&r=1&w=2 Signed-off-by: Sedat Dilek Cc: Boqun Feng Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin (maintainer:LIBLOCKDEP) Cc: Shuah Khan Cc: Theodore Ts'o Cc: Thomas Gleixner Cc: linux-fsdevel Link: http://lkml.kernel.org/r/1459326169-7009-1-git-send-email-sedat.dilek@gmail.com Signed-off-by: Ingo Molnar --- tools/lib/lockdep/run_tests.sh | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 5334ad9d39b7..1069d96248c1 100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh @@ -3,7 +3,7 @@ make &> /dev/null for i in `ls tests/*.c`; do - testname=$(basename -s .c "$i") + testname=$(basename "$i" .c) gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null echo -ne "$testname... " if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then @@ -11,11 +11,13 @@ for i in `ls tests/*.c`; do else echo "FAILED!" fi - rm tests/$testname + if [ -f "tests/$testname" ]; then + rm tests/$testname + fi done for i in `ls tests/*.c`; do - testname=$(basename -s .c "$i") + testname=$(basename "$i" .c) gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null echo -ne "(PRELOAD) $testname... " if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then @@ -23,5 +25,7 @@ for i in `ls tests/*.c`; do else echo "FAILED!" fi - rm tests/$testname + if [ -f "tests/$testname" ]; then + rm tests/$testname + fi done From 283d757378371e8044d873e661b1dccee46c5887 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Wed, 30 Mar 2016 00:14:57 +0200 Subject: [PATCH 128/196] uapi/linux/stddef.h: Provide __always_inline to userspace headers Josh Boyer reported that my recent change to uapi/linux/swab.h broke the Qemu build: bc27fb68aaad ("include/uapi/linux/byteorder, swab: force inlining of some byteswap operations") Unfortunately, UAPI headers don't include compiler.h so fixing it there is not enough, add an __always_inline definition to uapi/linux/stddef.h instead. Testcase: "make headers_install" and try to compile this: #include void main() {} Reported-by: Josh Boyer Signed-off-by: Denys Vlasenko Cc: Andrew Morton Cc: Arnd Bergmann Cc: David Rientjes Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Thomas Graf Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/1459289697-12875-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar --- include/uapi/linux/stddef.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index aa9f10428743..621fa8ac4425 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1 +1,5 @@ #include + +#ifndef __always_inline +#define __always_inline inline +#endif From 5e263f712691615fb802f06c98d7638c378f5d11 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Tue, 29 Mar 2016 18:48:08 +0800 Subject: [PATCH 129/196] bridge: Allow set bridge ageing time when switchdev disabled When NET_SWITCHDEV=n, switchdev_port_attr_set will return -EOPNOTSUPP, we should ignore this error code and continue to set the ageing time. Fixes: c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev") Signed-off-by: Haishuang Yan Acked-by: Ido Schimmel Signed-off-by: David S. Miller --- net/bridge/br_stp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index e23449094188..9cb7044d0801 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -582,7 +582,7 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time) int err; err = switchdev_port_attr_set(br->dev, &attr); - if (err) + if (err && err != -EOPNOTSUPP) return err; br->ageing_time = t; From 28fd34985bd5edaea6282a0586f91bcddd336f5e Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 29 Mar 2016 10:41:03 -0300 Subject: [PATCH 130/196] sctp: really allow using GFP_KERNEL on sctp_packet_transmit Somehow my patch for commit cea8768f333e ("sctp: allow sctp_transmit_packet and others to use gfp") missed two important chunks, which are now added. Fixes: cea8768f333e ("sctp: allow sctp_transmit_packet and others to use gfp") Signed-off-by: Marcelo Ricardo Leitner Acked-By: Neil Horman Signed-off-by: David S. Miller --- net/sctp/output.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sctp/output.c b/net/sctp/output.c index 736c004abfbc..97745351d58c 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -401,7 +401,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC); + nskb = alloc_skb(packet->size + MAX_HEADER, gfp); if (!nskb) goto nomem; @@ -523,8 +523,8 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) */ if (auth) sctp_auth_calculate_hmac(asoc, nskb, - (struct sctp_auth_chunk *)auth, - GFP_ATOMIC); + (struct sctp_auth_chunk *)auth, + gfp); /* 2) Calculate the Adler-32 checksum of the whole packet, * including the SCTP common header and all the From fea24857bb62990b839feb62090ad72a1c93735a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 29 Mar 2016 18:00:50 +0100 Subject: [PATCH 131/196] qed: initialize return rc to avoid returning garbage in the case where qed_slowpath_irq_req is not called, rc is not assigned and so qed_int_igu_enable will return a garbage value. Fix this by initializing rc to 0. Signed-off-by: Colin Ian King Acked-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_int.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index ffd0accc2ec9..2017b0121f5f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -2750,7 +2750,7 @@ void qed_int_igu_enable_int(struct qed_hwfn *p_hwfn, int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_int_mode int_mode) { - int rc; + int rc = 0; /* Configure AEU signal change to produce attentions */ qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0); From c3483384ee511ee2af40b4076366cd82a6a47b86 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 29 Mar 2016 14:55:22 -0700 Subject: [PATCH 132/196] gro: Allow tunnel stacking in the case of FOU/GUE This patch should fix the issues seen with a recent fix to prevent tunnel-in-tunnel frames from being generated with GRO. The fix itself is correct for now as long as we do not add any devices that support NETIF_F_GSO_GRE_CSUM. When such a device is added it could have the potential to mess things up due to the fact that the outer transport header points to the outer UDP header and not the GRE header as would be expected. Fixes: fac8e0f579695 ("tunnels: Don't apply GRO to multiple layers of encapsulation.") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/fou.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index a0586b4a197d..5a94aea280d3 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -195,6 +195,14 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head, u8 proto = NAPI_GRO_CB(skb)->proto; const struct net_offload **offloads; + /* We can clear the encap_mark for FOU as we are essentially doing + * one of two possible things. We are either adding an L4 tunnel + * header to the outer L3 tunnel header, or we are are simply + * treating the GRE tunnel header as though it is a UDP protocol + * specific header such as VXLAN or GENEVE. + */ + NAPI_GRO_CB(skb)->encap_mark = 0; + rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); @@ -352,6 +360,14 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, } } + /* We can clear the encap_mark for GUE as we are essentially doing + * one of two possible things. We are either adding an L4 tunnel + * header to the outer L3 tunnel header, or we are are simply + * treating the GRE tunnel header as though it is a UDP protocol + * specific header such as VXLAN or GENEVE. + */ + NAPI_GRO_CB(skb)->encap_mark = 0; + rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[guehdr->proto_ctype]); From cb41c997d4446b39dd03b8a74196125739d7c3ac Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 30 Mar 2016 10:58:39 +0800 Subject: [PATCH 133/196] team: team should sync the port's uc/mc addrs when add a port There is an issue when we use mavtap over team: When we replug nic links from team0, the real nics's mc list will not include the maddr for macvtap any more. then we can't receive pkts to macvtap device, as they are filterred by mc list of nic. In Bonding Driver, it syncs the uc/mc addrs in bond_enslave(). We will fix this issue on team by adding the port's uc/mc addrs sync in team_port_add. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- drivers/net/team/team.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 26c64d2782fa..a0f64cba86ba 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1198,6 +1198,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_dev_open; } + dev_uc_sync_multiple(port_dev, dev); + dev_mc_sync_multiple(port_dev, dev); + err = vlan_vids_add_by_dev(port_dev, dev); if (err) { netdev_err(dev, "Failed to add vlan ids to device %s\n", @@ -1261,6 +1264,8 @@ err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: + dev_uc_unsync(port_dev, dev); + dev_mc_unsync(port_dev, dev); dev_close(port_dev); err_dev_open: From 909890355507e92bdaf648e73870f6b5df606da8 Mon Sep 17 00:00:00 2001 From: Andres Freund Date: Wed, 30 Mar 2016 21:02:45 +0200 Subject: [PATCH 134/196] perf hists: Fix determination of a callchain node's childlessness The 4b3a3212233a ("perf hists browser: Support flat callchains") commit over-aggressively tried to optimize callchain_node__init_have_children(). That lead to --tui mode not allowing to expand call chain elements if a call chain element had only one parent. That's why --inverted callgraphs looked halfway sane, but plain ones didn't. Revert that individual optimization, it wasn't really related to the rest of the commit. Signed-off-by: Andres Freund Acked-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Fixes: 4b3a3212233a ("perf hists browser: Support flat callchains") Link: http://lkml.kernel.org/r/20160330190245.GB13305@awork2.anarazel.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 4b9816555946..2a83414159a6 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -337,7 +337,7 @@ static void callchain_node__init_have_children(struct callchain_node *node, chain = list_entry(node->val.next, struct callchain_list, list); chain->has_children = has_sibling; - if (node->val.next != node->val.prev) { + if (!list_empty(&node->val)) { chain = list_entry(node->val.prev, struct callchain_list, list); chain->has_children = !RB_EMPTY_ROOT(&node->rb_root); } From 9f56c092b99b40ce3cf4c6d0134ff7e513c9f1a6 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 29 Mar 2016 17:59:44 +1100 Subject: [PATCH 135/196] perf jit: genelf makes assumptions about endian Commit 9b07e27f88b9 ("perf inject: Add jitdump mmap injection support") incorrectly assumed that PowerPC is big endian only. Simplify things by consolidating the define of GEN_ELF_ENDIAN and checking for __BYTE_ORDER == __BIG_ENDIAN. The PowerPC checks were also incorrect, they do not match what gcc emits. We should first look for __powerpc64__, then __powerpc__. Signed-off-by: Anton Blanchard Acked-by: Michael Ellerman Cc: Carl Love Cc: Stephane Eranian Cc: Sukadev Bhattiprolu Cc: linuxppc-dev@lists.ozlabs.org Fixes: 9b07e27f88b9 ("perf inject: Add jitdump mmap injection support") Link: http://lkml.kernel.org/r/20160329175944.33a211cc@kryten Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/genelf.h | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index cd67e64a0494..2fbeb59c4bdd 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -9,36 +9,32 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #if defined(__arm__) #define GEN_ELF_ARCH EM_ARM -#define GEN_ELF_ENDIAN ELFDATA2LSB #define GEN_ELF_CLASS ELFCLASS32 #elif defined(__aarch64__) #define GEN_ELF_ARCH EM_AARCH64 -#define GEN_ELF_ENDIAN ELFDATA2LSB #define GEN_ELF_CLASS ELFCLASS64 #elif defined(__x86_64__) #define GEN_ELF_ARCH EM_X86_64 -#define GEN_ELF_ENDIAN ELFDATA2LSB #define GEN_ELF_CLASS ELFCLASS64 #elif defined(__i386__) #define GEN_ELF_ARCH EM_386 -#define GEN_ELF_ENDIAN ELFDATA2LSB #define GEN_ELF_CLASS ELFCLASS32 -#elif defined(__ppcle__) -#define GEN_ELF_ARCH EM_PPC -#define GEN_ELF_ENDIAN ELFDATA2LSB +#elif defined(__powerpc64__) +#define GEN_ELF_ARCH EM_PPC64 #define GEN_ELF_CLASS ELFCLASS64 #elif defined(__powerpc__) -#define GEN_ELF_ARCH EM_PPC64 -#define GEN_ELF_ENDIAN ELFDATA2MSB -#define GEN_ELF_CLASS ELFCLASS64 -#elif defined(__powerpcle__) -#define GEN_ELF_ARCH EM_PPC64 -#define GEN_ELF_ENDIAN ELFDATA2LSB -#define GEN_ELF_CLASS ELFCLASS64 +#define GEN_ELF_ARCH EM_PPC +#define GEN_ELF_CLASS ELFCLASS32 #else #error "unsupported architecture" #endif +#if __BYTE_ORDER == __BIG_ENDIAN +#define GEN_ELF_ENDIAN ELFDATA2MSB +#else +#define GEN_ELF_ENDIAN ELFDATA2LSB +#endif + #if GEN_ELF_CLASS == ELFCLASS64 #define elf_newehdr elf64_newehdr #define elf_getshdr elf64_getshdr From 33e52d888d0c84a0c66f13357a53113fd9710bd6 Mon Sep 17 00:00:00 2001 From: Prashant Sreedharan Date: Mon, 28 Mar 2016 19:46:04 -0400 Subject: [PATCH 136/196] bnxt_en: Initialize CP doorbell value before ring allocation The existing code does the following: allocate completion ring initialize completion ring doorbell disable interrupts on this completion ring by writing to the doorbell We can have a race where firmware sends an asynchronous event to the host after completion ring allocation and before doorbell is initialized. When this happens driver can crash while ringing the doorbell using uninitialized value as part of handling the IRQ/napi request. Signed-off-by: Prashant Sreedharan Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index aabbd51db981..c92053c8b2cc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3391,11 +3391,11 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + cpr->cp_doorbell = bp->bar1 + i * 0x80; rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_CMPL, i, INVALID_STATS_CTX_ID); if (rc) goto err_out; - cpr->cp_doorbell = bp->bar1 + i * 0x80; BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons); bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; } From e6ef26991a46e20879bebb8298080eb7ceed4ae8 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 28 Mar 2016 19:46:05 -0400 Subject: [PATCH 137/196] bnxt_en: Implement proper firmware message padding. The size of every padded firmware message is specified in the first HWRM_VER_GET response message. Use this value to pad every message after that. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++++- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c92053c8b2cc..4600a05a1d7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2653,7 +2653,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, /* Write request msg to hwrm channel */ __iowrite32_copy(bp->bar0, data, msg_len / 4); - for (i = msg_len; i < HWRM_MAX_REQ_LEN; i += 4) + for (i = msg_len; i < BNXT_HWRM_MAX_REQ_LEN; i += 4) writel(0, bp->bar0 + i); /* currently supports only one outstanding message */ @@ -3830,6 +3830,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) struct hwrm_ver_get_input req = {0}; struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr; + bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VER_GET, -1, -1); req.hwrm_intf_maj = HWRM_VERSION_MAJOR; req.hwrm_intf_min = HWRM_VERSION_MINOR; @@ -3855,6 +3856,9 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp) if (!bp->hwrm_cmd_timeout) bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT; + if (resp->hwrm_intf_maj >= 1) + bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len); + hwrm_ver_get_exit: mutex_unlock(&bp->hwrm_cmd_lock); return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index ec04c47172b7..709b95b8fcba 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -477,6 +477,7 @@ struct rx_tpa_end_cmp_ext { #define RING_CMP(idx) ((idx) & bp->cp_ring_mask) #define NEXT_CMP(idx) RING_CMP(ADV_RAW_CMP(idx, 1)) +#define BNXT_HWRM_MAX_REQ_LEN (bp->hwrm_max_req_len) #define DFLT_HWRM_CMD_TIMEOUT 500 #define HWRM_CMD_TIMEOUT (bp->hwrm_cmd_timeout) #define HWRM_RESET_TIMEOUT ((HWRM_CMD_TIMEOUT) * 4) @@ -953,6 +954,7 @@ struct bnxt { dma_addr_t hw_tx_port_stats_map; int hw_port_stats_size; + u16 hwrm_max_req_len; int hwrm_cmd_timeout; struct mutex hwrm_cmd_lock; /* serialize hwrm messages */ struct hwrm_ver_get_output ver_resp; From 49b5c7a125201bb42c25831fda3a50305c29ef50 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 28 Mar 2016 19:46:06 -0400 Subject: [PATCH 138/196] bnxt_en: Fix typo in bnxt_hwrm_set_pause_common(). The typo caused the wrong flow control bit to be set. Reported by: Ajit Khaparde Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4600a05a1d7d..12a009d720cd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4559,7 +4559,7 @@ bnxt_hwrm_set_pause_common(struct bnxt *bp, struct hwrm_port_phy_cfg_input *req) if (bp->link_info.req_flow_ctrl & BNXT_LINK_PAUSE_RX) req->auto_pause |= PORT_PHY_CFG_REQ_AUTO_PAUSE_RX; if (bp->link_info.req_flow_ctrl & BNXT_LINK_PAUSE_TX) - req->auto_pause |= PORT_PHY_CFG_REQ_AUTO_PAUSE_RX; + req->auto_pause |= PORT_PHY_CFG_REQ_AUTO_PAUSE_TX; req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE); } else { From 3c02d1bb32347d0674714ee170772d771d513469 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 28 Mar 2016 19:46:07 -0400 Subject: [PATCH 139/196] bnxt_en: Fix ethtool -a reporting. To report flow control tx/rx settings accurately regardless of autoneg setting, we should use link_info->req_flow_ctrl. Before this patch, the reported settings were only correct when autoneg was on. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 9ada1662b651..2e472f6dbf2d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -855,10 +855,8 @@ static void bnxt_get_pauseparam(struct net_device *dev, if (BNXT_VF(bp)) return; epause->autoneg = !!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL); - epause->rx_pause = - ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_RX) != 0); - epause->tx_pause = - ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_TX) != 0); + epause->rx_pause = !!(link_info->req_flow_ctrl & BNXT_LINK_PAUSE_RX); + epause->tx_pause = !!(link_info->req_flow_ctrl & BNXT_LINK_PAUSE_TX); } static int bnxt_set_pauseparam(struct net_device *dev, From 2d4212261fdf13e29728ddb5ea9d60c342cc92b5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 29 Mar 2016 08:43:41 -0700 Subject: [PATCH 140/196] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates IPv6 counters updates use a different macro than IPv4. Fixes: 36cbb2452cbaf ("udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts") Signed-off-by: Eric Dumazet Cc: Rick Jones Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv6/udp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd25e447a5fa..8125931106be 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -843,8 +843,8 @@ start_lookup: flush_stack(stack, count, skb, count - 1); } else { if (!inner_flushed) - UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, - proto == IPPROTO_UDPLITE); + UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); consume_skb(skb); } return 0; From c0e760c9c66ebd8a5a1ede81868677f4df993dfb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Mar 2016 00:02:00 +0200 Subject: [PATCH 141/196] bpf: make padding in bpf_tunnel_key explicit Make the 2 byte padding in struct bpf_tunnel_key between tunnel_ttl and tunnel_label members explicit. No issue has been observed, and gcc/llvm does padding for the old struct already, where tunnel_label was not yet present, so the current code works, but since it's part of uapi, make sure we don't introduce holes in structs. Therefore, add tunnel_ext that we can use generically in future (f.e. to flag OAM messages for backends, etc). Also add the offset to the compat tests to be sure should some compilers not padd the tail of the old version of bpf_tunnel_key. Fixes: 4018ab1875e0 ("bpf: support flow label for bpf_skb_{set, get}_tunnel_key") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 924f537183fd..23917bb47bf3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -375,6 +375,7 @@ struct bpf_tunnel_key { }; __u8 tunnel_tos; __u8 tunnel_ttl; + __u16 tunnel_ext; __u32 tunnel_label; }; diff --git a/net/core/filter.c b/net/core/filter.c index b7177d01ecb0..4b81b71171b4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1764,6 +1764,7 @@ static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have @@ -1849,6 +1850,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, tunnel_label): + case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. @@ -1861,7 +1863,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) return -EINVAL; } } - if (unlikely(!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label)) + if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || + from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); From 8fe889274c7a4d95c3e2d06f87ead499ea6faa2d Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 29 Mar 2016 17:02:13 +0800 Subject: [PATCH 142/196] nios2: Replace fdt_translate_address with of_flat_dt_translate_address nios2 builds fail with the following build error. arch/nios2/kernel/prom.c: In function 'early_init_dt_scan_serial': arch/nios2/kernel/prom.c:100:2: error: implicit declaration of function 'fdt_translate_address' Commit c90fe9c0394b ("of: earlycon: Move address translation to of_setup_earlycon()") replaced fdt_translate_address() with of_flat_dt_translate_address() but missed updating the nios2 code. Fixes: c90fe9c0394b ("of: earlycon: Move address translation to of_setup_earlycon()") Cc: Peter Hurley Cc: Rob Herring Signed-off-by: Guenter Roeck Acked-by: Ley Foon Tan --- arch/nios2/kernel/prom.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c index 718dd197909f..367c5426157b 100644 --- a/arch/nios2/kernel/prom.c +++ b/arch/nios2/kernel/prom.c @@ -97,8 +97,7 @@ static int __init early_init_dt_scan_serial(unsigned long node, return 0; #endif - *addr64 = fdt_translate_address((const void *)initial_boot_params, - node); + *addr64 = of_flat_dt_translate_address(node); return *addr64 == OF_BAD_ADDR ? 0 : 1; } From 572a143489a10360ce2aca98c64f8be43c8400a6 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 24 Feb 2016 19:24:09 +0200 Subject: [PATCH 143/196] iser-target: Use ib_drain_qp Now the rdma core offers a QP draining service in v4.6-rc1, use it instead of our own. Signed-off-by: Sagi Grimberg Reported-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 39 +++---------------------- drivers/infiniband/ulp/isert/ib_isert.h | 2 -- 2 files changed, 4 insertions(+), 37 deletions(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 60b30d338a81..411e4464ca23 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -63,7 +63,6 @@ isert_rdma_accept(struct isert_conn *isert_conn); struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np); static void isert_release_work(struct work_struct *work); -static void isert_wait4flush(struct isert_conn *isert_conn); static void isert_recv_done(struct ib_cq *cq, struct ib_wc *wc); static void isert_send_done(struct ib_cq *cq, struct ib_wc *wc); static void isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc); @@ -141,7 +140,7 @@ isert_create_qp(struct isert_conn *isert_conn, attr.qp_context = isert_conn; attr.send_cq = comp->cq; attr.recv_cq = comp->cq; - attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS; + attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS + 1; attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1; attr.cap.max_send_sge = device->ib_device->attrs.max_sge; isert_conn->max_sge = min(device->ib_device->attrs.max_sge, @@ -887,7 +886,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id, break; case ISER_CONN_UP: isert_conn_terminate(isert_conn); - isert_wait4flush(isert_conn); + ib_drain_qp(isert_conn->qp); isert_handle_unbound_conn(isert_conn); break; case ISER_CONN_BOUND: @@ -3213,36 +3212,6 @@ isert_wait4cmds(struct iscsi_conn *conn) } } -static void -isert_beacon_done(struct ib_cq *cq, struct ib_wc *wc) -{ - struct isert_conn *isert_conn = wc->qp->qp_context; - - isert_print_wc(wc, "beacon"); - - isert_info("conn %p completing wait_comp_err\n", isert_conn); - complete(&isert_conn->wait_comp_err); -} - -static void -isert_wait4flush(struct isert_conn *isert_conn) -{ - struct ib_recv_wr *bad_wr; - static struct ib_cqe cqe = { .done = isert_beacon_done }; - - isert_info("conn %p\n", isert_conn); - - init_completion(&isert_conn->wait_comp_err); - isert_conn->beacon.wr_cqe = &cqe; - /* post an indication that all flush errors were consumed */ - if (ib_post_recv(isert_conn->qp, &isert_conn->beacon, &bad_wr)) { - isert_err("conn %p failed to post beacon", isert_conn); - return; - } - - wait_for_completion(&isert_conn->wait_comp_err); -} - /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -3288,7 +3257,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->mutex); - isert_wait4flush(isert_conn); + ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); isert_wait4cmds(conn); isert_wait4logout(isert_conn); @@ -3300,7 +3269,7 @@ static void isert_free_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; - isert_wait4flush(isert_conn); + ib_drain_qp(isert_conn->qp); isert_put_conn(isert_conn); } diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 192788a4820c..147900cbb578 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -209,14 +209,12 @@ struct isert_conn { struct ib_qp *qp; struct isert_device *device; struct mutex mutex; - struct completion wait_comp_err; struct kref kref; struct list_head fr_pool; int fr_pool_size; /* lock to protect fastreg pool */ spinlock_t pool_lock; struct work_struct release_work; - struct ib_recv_wr beacon; bool logout_posted; bool snd_w_inv; }; From ce7043fd903eb9722a885b98b53fffe2cedfb047 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2016 13:03:33 +0200 Subject: [PATCH 144/196] target: remove ->fabric_cleanup_nodeacl Instead we can clean up the list of default ACLs in core code. Signed-off-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_configfs.c | 9 --------- drivers/target/target_core_fabric_configfs.c | 4 +--- include/target/target_core_fabric.h | 1 - 3 files changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index a24443ba59ea..3c05d1e97f8f 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -779,14 +779,6 @@ static int lio_target_init_nodeacl(struct se_node_acl *se_nacl, return 0; } -static void lio_target_cleanup_nodeacl( struct se_node_acl *se_nacl) -{ - struct iscsi_node_acl *acl = container_of(se_nacl, - struct iscsi_node_acl, se_node_acl); - - configfs_remove_default_groups(&acl->se_node_acl.acl_fabric_stat_group); -} - /* End items for lio_target_acl_cit */ /* Start items for lio_target_tpg_attrib_cit */ @@ -1665,7 +1657,6 @@ const struct target_core_fabric_ops iscsi_ops = { .fabric_make_np = lio_target_call_addnptotpg, .fabric_drop_np = lio_target_call_delnpfromtpg, .fabric_init_nodeacl = lio_target_init_nodeacl, - .fabric_cleanup_nodeacl = lio_target_cleanup_nodeacl, .tfc_discovery_attrs = lio_target_discovery_auth_attrs, .tfc_wwn_attrs = lio_target_wwn_attrs, diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 1bd5c72b663e..096790ad6e50 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -338,10 +338,8 @@ static void target_fabric_nacl_base_release(struct config_item *item) { struct se_node_acl *se_nacl = container_of(to_config_group(item), struct se_node_acl, acl_group); - struct target_fabric_configfs *tf = se_nacl->se_tpg->se_tpg_wwn->wwn_tf; - if (tf->tf_ops->fabric_cleanup_nodeacl) - tf->tf_ops->fabric_cleanup_nodeacl(se_nacl); + configfs_remove_default_groups(&se_nacl->acl_fabric_stat_group); core_tpg_del_initiator_node_acl(se_nacl); } diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 685a51aa98cc..5a9dd1892b70 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -87,7 +87,6 @@ struct target_core_fabric_ops { struct config_group *, const char *); void (*fabric_drop_np)(struct se_tpg_np *); int (*fabric_init_nodeacl)(struct se_node_acl *, const char *); - void (*fabric_cleanup_nodeacl)(struct se_node_acl *); struct configfs_attribute **tfc_discovery_attrs; struct configfs_attribute **tfc_wwn_attrs; From e6e202edf000004422a901dfa301d600e32f17e3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2016 13:03:34 +0200 Subject: [PATCH 145/196] target: initialize the nacl base CIT begfore init_nodeacl The iSCSI targets wants to add a default group, for which we need to have the list of default groups initialized previously. Signed-off-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_fabric_configfs.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 096790ad6e50..5991a4f816d8 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -381,14 +381,6 @@ static struct config_group *target_fabric_make_nodeacl( if (IS_ERR(se_nacl)) return ERR_CAST(se_nacl); - if (tf->tf_ops->fabric_init_nodeacl) { - int ret = tf->tf_ops->fabric_init_nodeacl(se_nacl, name); - if (ret) { - core_tpg_del_initiator_node_acl(se_nacl); - return ERR_PTR(ret); - } - } - config_group_init_type_name(&se_nacl->acl_group, name, &tf->tf_tpg_nacl_base_cit); @@ -412,6 +404,15 @@ static struct config_group *target_fabric_make_nodeacl( configfs_add_default_group(&se_nacl->acl_fabric_stat_group, &se_nacl->acl_group); + if (tf->tf_ops->fabric_init_nodeacl) { + int ret = tf->tf_ops->fabric_init_nodeacl(se_nacl, name); + if (ret) { + configfs_remove_default_groups(&se_nacl->acl_fabric_stat_group); + core_tpg_del_initiator_node_acl(se_nacl); + return ERR_PTR(ret); + } + } + return &se_nacl->acl_group; } From 839559e10601ed4459c802cbfb69747bf1844078 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2016 13:03:35 +0200 Subject: [PATCH 146/196] target: add a new add_wwn_groups fabrics method We need to have the WWN fully initialized before addig default groups to it, so add a new method to add these groups after the WWN has been initialized. Also remove the default groups in the core while we're at it. Signed-off-by: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_configfs.c | 19 +++++++++++-------- drivers/target/target_core_fabric_configfs.c | 3 +++ include/target/target_core_fabric.h | 1 + 3 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 3c05d1e97f8f..97e5b69e0668 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1239,6 +1239,16 @@ static struct se_wwn *lio_target_call_coreaddtiqn( if (IS_ERR(tiqn)) return ERR_CAST(tiqn); + pr_debug("LIO_Target_ConfigFS: REGISTER -> %s\n", tiqn->tiqn); + pr_debug("LIO_Target_ConfigFS: REGISTER -> Allocated Node:" + " %s\n", name); + return &tiqn->tiqn_wwn; +} + +static void lio_target_add_wwn_groups(struct se_wwn *wwn) +{ + struct iscsi_tiqn *tiqn = container_of(wwn, struct iscsi_tiqn, tiqn_wwn); + config_group_init_type_name(&tiqn->tiqn_stat_grps.iscsi_instance_group, "iscsi_instance", &iscsi_stat_instance_cit); configfs_add_default_group(&tiqn->tiqn_stat_grps.iscsi_instance_group, @@ -1263,12 +1273,6 @@ static struct se_wwn *lio_target_call_coreaddtiqn( "iscsi_logout_stats", &iscsi_stat_logout_cit); configfs_add_default_group(&tiqn->tiqn_stat_grps.iscsi_logout_stats_group, &tiqn->tiqn_wwn.fabric_stat_group); - - - pr_debug("LIO_Target_ConfigFS: REGISTER -> %s\n", tiqn->tiqn); - pr_debug("LIO_Target_ConfigFS: REGISTER -> Allocated Node:" - " %s\n", name); - return &tiqn->tiqn_wwn; } static void lio_target_call_coredeltiqn( @@ -1276,8 +1280,6 @@ static void lio_target_call_coredeltiqn( { struct iscsi_tiqn *tiqn = container_of(wwn, struct iscsi_tiqn, tiqn_wwn); - configfs_remove_default_groups(&tiqn->tiqn_wwn.fabric_stat_group); - pr_debug("LIO_Target_ConfigFS: DEREGISTER -> %s\n", tiqn->tiqn); iscsit_del_tiqn(tiqn); @@ -1652,6 +1654,7 @@ const struct target_core_fabric_ops iscsi_ops = { .aborted_task = lio_aborted_task, .fabric_make_wwn = lio_target_call_coreaddtiqn, .fabric_drop_wwn = lio_target_call_coredeltiqn, + .add_wwn_groups = lio_target_add_wwn_groups, .fabric_make_tpg = lio_target_tiqn_addtpg, .fabric_drop_tpg = lio_target_tiqn_deltpg, .fabric_make_np = lio_target_call_addnptotpg, diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 5991a4f816d8..31a096aa16ab 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -891,6 +891,7 @@ static void target_fabric_release_wwn(struct config_item *item) struct se_wwn, wwn_group); struct target_fabric_configfs *tf = wwn->wwn_tf; + configfs_remove_default_groups(&wwn->fabric_stat_group); tf->tf_ops->fabric_drop_wwn(wwn); } @@ -944,6 +945,8 @@ static struct config_group *target_fabric_make_wwn( &tf->tf_wwn_fabric_stats_cit); configfs_add_default_group(&wwn->fabric_stat_group, &wwn->wwn_group); + if (tf->tf_ops->add_wwn_groups) + tf->tf_ops->add_wwn_groups(wwn); return &wwn->wwn_group; } diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 5a9dd1892b70..8ff6d40a294f 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -76,6 +76,7 @@ struct target_core_fabric_ops { struct se_wwn *(*fabric_make_wwn)(struct target_fabric_configfs *, struct config_group *, const char *); void (*fabric_drop_wwn)(struct se_wwn *); + void (*add_wwn_groups)(struct se_wwn *); struct se_portal_group *(*fabric_make_tpg)(struct se_wwn *, struct config_group *, const char *); void (*fabric_drop_tpg)(struct se_portal_group *); From 7500c38ac3258815f86f41744a538850c3221b23 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 31 Mar 2016 00:23:05 -0400 Subject: [PATCH 147/196] fix the braino in "namei: massage lookup_slow() to be usable by lookup_one_len_unlocked()" We should try to trigger automount *before* bailing out on negative dentry. Reported-by: Jun'ichi Nomura Reported-by: Jun'ichi Nomura Reported-by: Arend van Spriel Tested-by: Arend van Spriel Tested-by: Jun'ichi Nomura Signed-off-by: Al Viro --- fs/namei.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 794f81dce766..1d9ca2d5dff6 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1740,15 +1740,17 @@ static int walk_component(struct nameidata *nd, int flags) nd->flags); if (IS_ERR(path.dentry)) return PTR_ERR(path.dentry); - if (unlikely(d_is_negative(path.dentry))) { - dput(path.dentry); - return -ENOENT; - } + path.mnt = nd->path.mnt; err = follow_managed(&path, nd); if (unlikely(err < 0)) return err; + if (unlikely(d_is_negative(path.dentry))) { + path_to_nameidata(&path, nd); + return -ENOENT; + } + seq = 0; /* we are already out of RCU mode */ inode = d_backing_inode(path.dentry); } From 8fdc65391c6ad16461526a685f03262b3b01bfde Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 29 Mar 2016 09:26:44 +0200 Subject: [PATCH 148/196] perf/core: Fix time tracking bug with multiplexing Stephane reported that commit: 3cbaa5906967 ("perf: Fix ctx time tracking by introducing EVENT_TIME") introduced a regression wrt. time tracking, as easily observed by: > This patch introduce a bug in the time tracking of events when > multiplexing is used. > > The issue is easily reproducible with the following perf run: > > $ perf stat -a -C 0 -e branches,branches,branches,branches,branches,branches -I 1000 > 1.000730239 652,394 branches (66.41%) > 1.000730239 597,809 branches (66.41%) > 1.000730239 593,870 branches (66.63%) > 1.000730239 651,440 branches (67.03%) > 1.000730239 656,725 branches (66.96%) > 1.000730239 branches > > One branches event is shown as not having run. Yet, with > multiplexing, all events should run especially with a 1s (-I 1000) > interval. The delta for time_running comes out to 0. Yet, the event > has run because the kernel is actually multiplexing the events. The > problem is that the time tracking is the kernel and especially in > ctx_sched_out() is wrong now. > > The problem is that in case that the kernel enters ctx_sched_out() with the > following state: > ctx->is_active=0x7 event_type=0x1 > Call Trace: > [] dump_stack+0x63/0x82 > [] ctx_sched_out+0x2bc/0x2d0 > [] perf_mux_hrtimer_handler+0xf6/0x2c0 > [] ? __perf_install_in_context+0x130/0x130 > [] __hrtimer_run_queues+0xf8/0x2f0 > [] hrtimer_interrupt+0xb7/0x1d0 > [] local_apic_timer_interrupt+0x38/0x60 > [] smp_apic_timer_interrupt+0x3d/0x50 > [] apic_timer_interrupt+0x8c/0xa0 > > In that case, the test: > if (is_active & EVENT_TIME) > > will be false and the time will not be updated. Time must always be updated on > sched out. Fix this by always updating time if EVENT_TIME was set, as opposed to only updating time when EVENT_TIME changed. Reported-by: Stephane Eranian Tested-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: kan.liang@intel.com Cc: namhyung@kernel.org Fixes: 3cbaa5906967 ("perf: Fix ctx time tracking by introducing EVENT_TIME") Link: http://lkml.kernel.org/r/20160329072644.GB3408@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index de24fbce5277..8c11388e92a5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2417,14 +2417,24 @@ static void ctx_sched_out(struct perf_event_context *ctx, cpuctx->task_ctx = NULL; } - is_active ^= ctx->is_active; /* changed bits */ - + /* + * Always update time if it was set; not only when it changes. + * Otherwise we can 'forget' to update time for any but the last + * context we sched out. For example: + * + * ctx_sched_out(.event_type = EVENT_FLEXIBLE) + * ctx_sched_out(.event_type = EVENT_PINNED) + * + * would only update time for the pinned events. + */ if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx); } + is_active ^= ctx->is_active; /* changed bits */ + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; From 201c2f85bd0bc13b712d9c0b3d11251b182e06ae Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Mon, 21 Mar 2016 10:02:42 +0200 Subject: [PATCH 149/196] perf/core: Don't leak event in the syscall error path In the error path, event_file not being NULL is used to determine whether the event itself still needs to be free'd, so fix it up to avoid leaking. Reported-by: Leon Yu Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 130056275ade ("perf: Do not double free") Link: http://lkml.kernel.org/r/87twk06yxp.fsf@ashishki-desk.ger.corp.intel.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 8c11388e92a5..52bedc5a5aaa 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8542,6 +8542,7 @@ SYSCALL_DEFINE5(perf_event_open, f_flags); if (IS_ERR(event_file)) { err = PTR_ERR(event_file); + event_file = NULL; goto err_context; } From 85dc600263c2291cea33bffa90038808ee64198b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 21 Mar 2016 11:47:52 +0100 Subject: [PATCH 150/196] perf/x86/amd/ibs: Fix pmu::stop() nesting Patch 5a50f5291701 ("perf/x86/ibs: Fix race with IBS_STARTING state") closed a big hole while opening another, smaller hole. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 5a50f5291701 ("perf/x86/ibs: Fix race with IBS_STARTING state") Signed-off-by: Ingo Molnar --- arch/x86/events/amd/ibs.c | 52 +++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 7 deletions(-) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 3ea25c3917c0..feb90f6730e8 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -28,10 +28,46 @@ static u32 ibs_caps; #define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT) #define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT + +/* + * IBS states: + * + * ENABLED; tracks the pmu::add(), pmu::del() state, when set the counter is taken + * and any further add()s must fail. + * + * STARTED/STOPPING/STOPPED; deal with pmu::start(), pmu::stop() state but are + * complicated by the fact that the IBS hardware can send late NMIs (ie. after + * we've cleared the EN bit). + * + * In order to consume these late NMIs we have the STOPPED state, any NMI that + * happens after we've cleared the EN state will clear this bit and report the + * NMI handled (this is fundamentally racy in the face or multiple NMI sources, + * someone else can consume our BIT and our NMI will go unhandled). + * + * And since we cannot set/clear this separate bit together with the EN bit, + * there are races; if we cleared STARTED early, an NMI could land in + * between clearing STARTED and clearing the EN bit (in fact multiple NMIs + * could happen if the period is small enough), and consume our STOPPED bit + * and trigger streams of unhandled NMIs. + * + * If, however, we clear STARTED late, an NMI can hit between clearing the + * EN bit and clearing STARTED, still see STARTED set and process the event. + * If this event will have the VALID bit clear, we bail properly, but this + * is not a given. With VALID set we can end up calling pmu::stop() again + * (the throttle logic) and trigger the WARNs in there. + * + * So what we do is set STOPPING before clearing EN to avoid the pmu::stop() + * nesting, and clear STARTED late, so that we have a well defined state over + * the clearing of the EN bit. + * + * XXX: we could probably be using !atomic bitops for all this. + */ + enum ibs_states { IBS_ENABLED = 0, IBS_STARTED = 1, IBS_STOPPING = 2, + IBS_STOPPED = 3, IBS_MAX_STATES, }; @@ -377,11 +413,10 @@ static void perf_ibs_start(struct perf_event *event, int flags) perf_ibs_set_period(perf_ibs, hwc, &period); /* - * Set STARTED before enabling the hardware, such that - * a subsequent NMI must observe it. Then clear STOPPING - * such that we don't consume NMIs by accident. + * Set STARTED before enabling the hardware, such that a subsequent NMI + * must observe it. */ - set_bit(IBS_STARTED, pcpu->state); + set_bit(IBS_STARTED, pcpu->state); clear_bit(IBS_STOPPING, pcpu->state); perf_ibs_enable_event(perf_ibs, hwc, period >> 4); @@ -396,6 +431,9 @@ static void perf_ibs_stop(struct perf_event *event, int flags) u64 config; int stopping; + if (test_and_set_bit(IBS_STOPPING, pcpu->state)) + return; + stopping = test_bit(IBS_STARTED, pcpu->state); if (!stopping && (hwc->state & PERF_HES_UPTODATE)) @@ -405,12 +443,12 @@ static void perf_ibs_stop(struct perf_event *event, int flags) if (stopping) { /* - * Set STOPPING before disabling the hardware, such that it + * Set STOPPED before disabling the hardware, such that it * must be visible to NMIs the moment we clear the EN bit, * at which point we can generate an !VALID sample which * we need to consume. */ - set_bit(IBS_STOPPING, pcpu->state); + set_bit(IBS_STOPPED, pcpu->state); perf_ibs_disable_event(perf_ibs, hwc, config); /* * Clear STARTED after disabling the hardware; if it were @@ -556,7 +594,7 @@ fail: * with samples that even have the valid bit cleared. * Mark all this NMIs as handled. */ - if (test_and_clear_bit(IBS_STOPPING, pcpu->state)) + if (test_and_clear_bit(IBS_STOPPED, pcpu->state)) return 1; return 0; From 4f4acc9472e54ce702f1d85fc9e6d57767dec91f Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 30 Mar 2016 14:11:50 +0200 Subject: [PATCH 151/196] parisc: Fix SIGSYS signals in compat case Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # v4.5 --- arch/parisc/include/asm/compat.h | 7 +++++++ arch/parisc/kernel/signal32.c | 5 +++++ 2 files changed, 12 insertions(+) diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 0448a2c8eafb..3387307cc33e 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -183,6 +183,13 @@ typedef struct compat_siginfo { int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; + + /* SIGSYS */ + struct { + compat_uptr_t _call_addr; /* calling user insn */ + int _syscall; /* triggering system call number */ + compat_uint_t _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; } _sifields; } compat_siginfo_t; diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c index 984abbee71ca..c342b2e17492 100644 --- a/arch/parisc/kernel/signal32.c +++ b/arch/parisc/kernel/signal32.c @@ -371,6 +371,11 @@ copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from) val = (compat_int_t)from->si_int; err |= __put_user(val, &to->si_int); break; + case __SI_SYS >> 16: + err |= __put_user(ptr_to_compat(from->si_call_addr), &to->si_call_addr); + err |= __put_user(from->si_syscall, &to->si_syscall); + err |= __put_user(from->si_arch, &to->si_arch); + break; } } return err; From 910cd32e552ea09caa89cdbe328e468979b030dd Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 30 Mar 2016 14:14:31 +0200 Subject: [PATCH 152/196] parisc: Fix and enable seccomp filter support The seccomp filter support requires careful handling of task registers. This includes reloading of the return value (%r28) and proper syscall exit if secure_computing() returned -1. Additionally we need to sign-extend the syscall number from signed 32bit to signed 64bit in do_syscall_trace_enter() since the ptrace interface only allows storing 32bit values in compat mode. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org # v4.5 --- arch/parisc/Kconfig | 1 + arch/parisc/include/asm/syscall.h | 13 +++++++++++++ arch/parisc/kernel/ptrace.c | 9 +++++++-- arch/parisc/kernel/syscall.S | 2 ++ 4 files changed, 23 insertions(+), 2 deletions(-) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 14f655cf542e..86ed37671ef5 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -29,6 +29,7 @@ config PARISC select TTY # Needed for pdc_cons.c select HAVE_DEBUG_STACKOVERFLOW select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_SECCOMP_FILTER select ARCH_NO_COHERENT_DMA_MMAP help diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h index a5eba95d87fe..637ce8d6f375 100644 --- a/arch/parisc/include/asm/syscall.h +++ b/arch/parisc/include/asm/syscall.h @@ -39,6 +39,19 @@ static inline void syscall_get_arguments(struct task_struct *tsk, } } +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + regs->gr[28] = error ? error : val; +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + /* do nothing */ +} + static inline int syscall_get_arch(void) { int arch = AUDIT_ARCH_PARISC; diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index ce0b2b4075c7..8fb81a391599 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -270,7 +270,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { /* Do the secure computing check first. */ - secure_computing_strict(regs->gr[20]); + if (secure_computing() == -1) + return -1; if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) { @@ -296,7 +297,11 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[23] & 0xffffffff); out: - return regs->gr[20]; + /* + * Sign extend the syscall number to 64bit since it may have been + * modified by a compat ptrace call + */ + return (int) ((u32) regs->gr[20]); } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index fbafa0d0e2bf..c976ebfe2269 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -329,6 +329,7 @@ tracesys_next: ldo -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1 /* get task ptr */ LDREG TI_TASK(%r1), %r1 + LDREG TASK_PT_GR28(%r1), %r28 /* Restore return value */ LDREG TASK_PT_GR26(%r1), %r26 /* Restore the users args */ LDREG TASK_PT_GR25(%r1), %r25 LDREG TASK_PT_GR24(%r1), %r24 @@ -342,6 +343,7 @@ tracesys_next: stw %r21, -56(%r30) /* 6th argument */ #endif + cmpib,COND(=),n -1,%r20,tracesys_exit /* seccomp may have returned -1 */ comiclr,>>= __NR_Linux_syscalls, %r20, %r0 b,n .Ltracesys_nosys From 8eb22214b7cb0c0a28be6caf3b81201629d8ea7c Mon Sep 17 00:00:00 2001 From: Maruthi Srinivas Bayyavarapu Date: Thu, 31 Mar 2016 18:10:03 +0530 Subject: [PATCH 153/196] ALSA: hda: add AMD Polaris-10/11 AZ PCI IDs with proper driver caps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit fixes garbled audio on Polaris-10/11 variants Signed-off-by: Maruthi Bayyavarapu Reviewed-by: Alex Deucher Acked-by: Christian König Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 2624cfe98884..b680be0e937d 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2361,6 +2361,10 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, { PCI_DEVICE(0x1002, 0xaae8), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, + { PCI_DEVICE(0x1002, 0xaae0), + .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, + { PCI_DEVICE(0x1002, 0xaaf0), + .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS }, /* VIA VT8251/VT8237A */ { PCI_DEVICE(0x1106, 0x3288), .driver_data = AZX_DRIVER_VIA }, /* VIA GFX VT7122/VX900 */ From 39e2e173fb1f900959d3a25c21c65fa88b06c6ee Mon Sep 17 00:00:00 2001 From: Alfredo Alvarez Fernandez Date: Wed, 30 Mar 2016 19:03:36 +0200 Subject: [PATCH 154/196] locking/lockdep: Print chain_key collision information A sequence of pairs [class_idx -> corresponding chain_key iteration] is printed for both the current held_lock chain and the cached chain. That exposes the two different class_idx sequences that led to that particular hash value. This helps with debugging hash chain collision reports. Signed-off-by: Alfredo Alvarez Fernandez Acked-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-fsdevel@vger.kernel.org Cc: sedat.dilek@gmail.com Cc: tytso@mit.edu Link: http://lkml.kernel.org/r/1459357416-19190-1-git-send-email-alfredoalvarezernandez@gmail.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 79 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 77 insertions(+), 2 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 53ab2f85d77e..2324ba5310db 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1999,6 +1999,77 @@ static inline int get_first_held_lock(struct task_struct *curr, return ++i; } +/* + * Returns the next chain_key iteration + */ +static u64 print_chain_key_iteration(int class_idx, u64 chain_key) +{ + u64 new_chain_key = iterate_chain_key(chain_key, class_idx); + + printk(" class_idx:%d -> chain_key:%016Lx", + class_idx, + (unsigned long long)new_chain_key); + return new_chain_key; +} + +static void +print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_next) +{ + struct held_lock *hlock; + u64 chain_key = 0; + int depth = curr->lockdep_depth; + int i; + + printk("depth: %u\n", depth + 1); + for (i = get_first_held_lock(curr, hlock_next); i < depth; i++) { + hlock = curr->held_locks + i; + chain_key = print_chain_key_iteration(hlock->class_idx, chain_key); + + print_lock(hlock); + } + + print_chain_key_iteration(hlock_next->class_idx, chain_key); + print_lock(hlock_next); +} + +static void print_chain_keys_chain(struct lock_chain *chain) +{ + int i; + u64 chain_key = 0; + int class_id; + + printk("depth: %u\n", chain->depth); + for (i = 0; i < chain->depth; i++) { + class_id = chain_hlocks[chain->base + i]; + chain_key = print_chain_key_iteration(class_id + 1, chain_key); + + print_lock_name(lock_classes + class_id); + printk("\n"); + } +} + +static void print_collision(struct task_struct *curr, + struct held_lock *hlock_next, + struct lock_chain *chain) +{ + printk("\n"); + printk("======================\n"); + printk("[chain_key collision ]\n"); + print_kernel_ident(); + printk("----------------------\n"); + printk("%s/%d: ", current->comm, task_pid_nr(current)); + printk("Hash chain already cached but the contents don't match!\n"); + + printk("Held locks:"); + print_chain_keys_held_locks(curr, hlock_next); + + printk("Locks in cached chain:"); + print_chain_keys_chain(chain); + + printk("\nstack backtrace:\n"); + dump_stack(); +} + /* * Checks whether the chain and the current held locks are consistent * in depth and also in content. If they are not it most likely means @@ -2014,14 +2085,18 @@ static int check_no_collision(struct task_struct *curr, i = get_first_held_lock(curr, hlock); - if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) { + print_collision(curr, hlock, chain); return 0; + } for (j = 0; j < chain->depth - 1; j++, i++) { id = curr->held_locks[i].class_idx - 1; - if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) { + print_collision(curr, hlock, chain); return 0; + } } #endif return 1; From 641bb3246dbb64c0b4a0b6dfa6a024e82c155533 Mon Sep 17 00:00:00 2001 From: Martin Brandenburg Date: Mon, 28 Mar 2016 17:18:27 -0400 Subject: [PATCH 155/196] orangefs: don't put readdir slot twice This was quite an oversight. After a readdir, the module could not be unloaded, the number of slots is wrong, and memory near the slot bitmap is possibly corrupt. Oops. Signed-off-by: Martin Brandenburg --- fs/orangefs/dir.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/orangefs/dir.c b/fs/orangefs/dir.c index f30b6ecacdd1..ba7dec40771e 100644 --- a/fs/orangefs/dir.c +++ b/fs/orangefs/dir.c @@ -235,7 +235,7 @@ get_new_buffer_index: if (ret == -EIO && op_state_purged(new_op)) { gossip_err("%s: Client is down. Aborting readdir call.\n", __func__); - goto out_slot; + goto out_free_op; } if (ret < 0 || new_op->downcall.status != 0) { @@ -244,14 +244,14 @@ get_new_buffer_index: new_op->downcall.status); if (ret >= 0) ret = new_op->downcall.status; - goto out_slot; + goto out_free_op; } dents_buf = new_op->downcall.trailer_buf; if (dents_buf == NULL) { gossip_err("Invalid NULL buffer in readdir response\n"); ret = -ENOMEM; - goto out_slot; + goto out_free_op; } bytes_decoded = decode_dirents(dents_buf, new_op->downcall.trailer_size, @@ -363,8 +363,6 @@ out_destroy_handle: out_vfree: gossip_debug(GOSSIP_DIR_DEBUG, "vfree %p\n", dents_buf); vfree(dents_buf); -out_slot: - orangefs_readdir_index_put(buffer_index); out_free_op: op_release(new_op); gossip_debug(GOSSIP_DIR_DEBUG, "orangefs_readdir returning %d\n", ret); From 878dfd3210e0bfc047995022de3091724ea9a5f6 Mon Sep 17 00:00:00 2001 From: Martin Brandenburg Date: Wed, 30 Mar 2016 16:18:43 -0400 Subject: [PATCH 156/196] orangefs: minimum userspace version is 2.9.3 Version 2.9.4 isn't even released yet. Signed-off-by: Martin Brandenburg --- fs/orangefs/protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h index 45ce4ff4cbc7..50578a28bd9e 100644 --- a/fs/orangefs/protocol.h +++ b/fs/orangefs/protocol.h @@ -407,7 +407,7 @@ enum { * space. Zero signifies the upstream version of the kernel module. */ #define ORANGEFS_KERNEL_PROTO_VERSION 0 -#define ORANGEFS_MINIMUM_USERSPACE_VERSION 20904 +#define ORANGEFS_MINIMUM_USERSPACE_VERSION 20903 /* * describes memory regions to map in the ORANGEFS_DEV_MAP ioctl. From 836b34a935abc91e13e63053d0a83b24dfb5ea78 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Thu, 31 Mar 2016 12:05:43 -0400 Subject: [PATCH 157/196] ALSA: usb-audio: Fix double-free in error paths after snd_usb_add_audio_stream() call create_fixed_stream_quirk(), snd_usb_parse_audio_interface() and create_uaxx_quirk() functions allocate the audioformat object by themselves and free it upon error before returning. However, once the object is linked to a stream, it's freed again in snd_usb_audio_pcm_free(), thus it'll be double-freed, eventually resulting in a memory corruption. This patch fixes these failures in the error paths by unlinking the audioformat object before freeing it. Based on a patch by Takashi Iwai [Note for stable backports: this patch requires the commit 902eb7fd1e4a ('ALSA: usb-audio: Minor code cleanup in create_fixed_stream_quirk()')] Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1283358 Reported-by: Ralf Spenneberg Cc: # see the note above Signed-off-by: Vladis Dronov Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 4 ++++ sound/usb/stream.c | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index fb62bce2435c..6178bb5d0731 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -150,6 +150,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, usb_audio_err(chip, "cannot memdup\n"); return -ENOMEM; } + INIT_LIST_HEAD(&fp->list); if (fp->nr_rates > MAX_NR_RATES) { kfree(fp); return -EINVAL; @@ -193,6 +194,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip, return 0; error: + list_del(&fp->list); /* unlink for avoiding double-free */ kfree(fp); kfree(rate_table); return err; @@ -469,6 +471,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip, fp->ep_attr = get_endpoint(alts, 0)->bmAttributes; fp->datainterval = 0; fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize); + INIT_LIST_HEAD(&fp->list); switch (fp->maxpacksize) { case 0x120: @@ -492,6 +495,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip, ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; err = snd_usb_add_audio_stream(chip, stream, fp); if (err < 0) { + list_del(&fp->list); /* unlink for avoiding double-free */ kfree(fp); return err; } diff --git a/sound/usb/stream.c b/sound/usb/stream.c index c4dc577ab1bd..8e9548bc1f1a 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -314,7 +314,9 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, /* * add this endpoint to the chip instance. * if a stream with the same endpoint already exists, append to it. - * if not, create a new pcm stream. + * if not, create a new pcm stream. note, fp is added to the substream + * fmt_list and will be freed on the chip instance release. do not free + * fp or do remove it from the substream fmt_list to avoid double-free. */ int snd_usb_add_audio_stream(struct snd_usb_audio *chip, int stream, @@ -675,6 +677,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no) * (fp->maxpacksize & 0x7ff); fp->attributes = parse_uac_endpoint_attributes(chip, alts, protocol, iface_no); fp->clock = clock; + INIT_LIST_HEAD(&fp->list); /* some quirks for attributes here */ @@ -723,6 +726,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no) dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint); err = snd_usb_add_audio_stream(chip, stream, fp); if (err < 0) { + list_del(&fp->list); /* unlink for avoiding double-free */ kfree(fp->rate_table); kfree(fp->chmap); kfree(fp); From 75baacf00fb471c3b01e604357ab53da7cf72dd4 Mon Sep 17 00:00:00 2001 From: Patrick Uiterwijk Date: Wed, 30 Mar 2016 01:39:40 +0000 Subject: [PATCH 158/196] net: dsa: mv88e6xxx: Introduce _mv88e6xxx_phy_page_{read, write} Add versions of the phy_page_read and _write functions to be used in a context where the SMI mutex is held. Tested-by: Vivien Didelot Reviewed-by: Vivien Didelot Signed-off-by: Patrick Uiterwijk Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 49 +++++++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 13 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index fa086e09d6b7..86a202975c02 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2264,6 +2264,38 @@ static void mv88e6xxx_bridge_work(struct work_struct *work) mutex_unlock(&ps->smi_mutex); } +static int _mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page, + int reg, int val) +{ + int ret; + + ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page); + if (ret < 0) + goto restore_page_0; + + ret = _mv88e6xxx_phy_write_indirect(ds, port, reg, val); +restore_page_0: + _mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0); + + return ret; +} + +static int _mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, + int reg) +{ + int ret; + + ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page); + if (ret < 0) + goto restore_page_0; + + ret = _mv88e6xxx_phy_read_indirect(ds, port, reg); +restore_page_0: + _mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0); + + return ret; +} + static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); @@ -2714,13 +2746,9 @@ int mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, int reg) int ret; mutex_lock(&ps->smi_mutex); - ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page); - if (ret < 0) - goto error; - ret = _mv88e6xxx_phy_read_indirect(ds, port, reg); -error: - _mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0); + ret = _mv88e6xxx_phy_page_read(ds, port, page, reg); mutex_unlock(&ps->smi_mutex); + return ret; } @@ -2731,14 +2759,9 @@ int mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page, int ret; mutex_lock(&ps->smi_mutex); - ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page); - if (ret < 0) - goto error; - - ret = _mv88e6xxx_phy_write_indirect(ds, port, reg, val); -error: - _mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0); + ret = _mv88e6xxx_phy_page_write(ds, port, page, reg, val); mutex_unlock(&ps->smi_mutex); + return ret; } From 13a7ebb38a659254e71a4a95cf39429a9287912b Mon Sep 17 00:00:00 2001 From: Patrick Uiterwijk Date: Wed, 30 Mar 2016 01:39:41 +0000 Subject: [PATCH 159/196] net: dsa: mv88e6xxx: Clear the PDOWN bit on setup Some of the vendor-specific bootloaders set up this part of the initialization for us, so this was never added. However, since upstream bootloaders don't initialize the chip specifically, they leave the fiber MII's PDOWN flag set, which means that the CPU port doesn't connect. This patch checks whether this flag has been clear prior by something else, and if not make us clear it. Reviewed-by: Andrew Lunn Signed-off-by: Patrick Uiterwijk Tested-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 36 ++++++++++++++++++++++++++++++++++++ drivers/net/dsa/mv88e6xxx.h | 8 ++++++++ 2 files changed, 44 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 86a202975c02..50454be86570 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2296,6 +2296,25 @@ restore_page_0: return ret; } +static int mv88e6xxx_power_on_serdes(struct dsa_switch *ds) +{ + int ret; + + ret = _mv88e6xxx_phy_page_read(ds, REG_FIBER_SERDES, PAGE_FIBER_SERDES, + MII_BMCR); + if (ret < 0) + return ret; + + if (ret & BMCR_PDOWN) { + ret &= ~BMCR_PDOWN; + ret = _mv88e6xxx_phy_page_write(ds, REG_FIBER_SERDES, + PAGE_FIBER_SERDES, MII_BMCR, + ret); + } + + return ret; +} + static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); @@ -2399,6 +2418,23 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) goto abort; } + /* If this port is connected to a SerDes, make sure the SerDes is not + * powered down. + */ + if (mv88e6xxx_6352_family(ds)) { + ret = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_STATUS); + if (ret < 0) + goto abort; + ret &= PORT_STATUS_CMODE_MASK; + if ((ret == PORT_STATUS_CMODE_100BASE_X) || + (ret == PORT_STATUS_CMODE_1000BASE_X) || + (ret == PORT_STATUS_CMODE_SGMII)) { + ret = mv88e6xxx_power_on_serdes(ds); + if (ret < 0) + goto abort; + } + } + /* Port Control 2: don't force a good FCS, set the maximum frame size to * 10240 bytes, disable 802.1q tags checking, don't discard tagged or * untagged frames on this port, do a destination address lookup on all diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 9a038aba48fb..26a424acd10f 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -28,6 +28,10 @@ #define SMI_CMD_OP_45_READ_DATA_INC ((3 << 10) | SMI_CMD_BUSY) #define SMI_DATA 0x01 +/* Fiber/SERDES Registers are located at SMI address F, page 1 */ +#define REG_FIBER_SERDES 0x0f +#define PAGE_FIBER_SERDES 0x01 + #define REG_PORT(p) (0x10 + (p)) #define PORT_STATUS 0x00 #define PORT_STATUS_PAUSE_EN BIT(15) @@ -45,6 +49,10 @@ #define PORT_STATUS_MGMII BIT(6) /* 6185 */ #define PORT_STATUS_TX_PAUSED BIT(5) #define PORT_STATUS_FLOW_CTRL BIT(4) +#define PORT_STATUS_CMODE_MASK 0x0f +#define PORT_STATUS_CMODE_100BASE_X 0x8 +#define PORT_STATUS_CMODE_1000BASE_X 0x9 +#define PORT_STATUS_CMODE_SGMII 0xa #define PORT_PCS_CTRL 0x01 #define PORT_PCS_CTRL_RGMII_DELAY_RXCLK BIT(15) #define PORT_PCS_CTRL_RGMII_DELAY_TXCLK BIT(14) From b7854efce20be7c7bcd43424dee027124e9af27f Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Wed, 30 Mar 2016 19:53:41 +0800 Subject: [PATCH 160/196] net: mvpp2: replace MVPP2_CPU_D_CACHE_LINE_SIZE with L1_CACHE_BYTES The mvpp2 ip maybe used in SoCs which may have have 64bytes cacheline size. Replace the MVPP2_CPU_D_CACHE_LINE_SIZE with L1_CACHE_BYTES. And since dma_alloc_coherent() is always cacheline size aligned, so remove the align checks. Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index c797971aefab..05f358b81791 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -321,7 +321,6 @@ /* Lbtd 802.3 type */ #define MVPP2_IP_LBDT_TYPE 0xfffa -#define MVPP2_CPU_D_CACHE_LINE_SIZE 32 #define MVPP2_TX_CSUM_MAX_SIZE 9800 /* Timeout constants */ @@ -377,7 +376,7 @@ #define MVPP2_RX_PKT_SIZE(mtu) \ ALIGN((mtu) + MVPP2_MH_SIZE + MVPP2_VLAN_TAG_LEN + \ - ETH_HLEN + ETH_FCS_LEN, MVPP2_CPU_D_CACHE_LINE_SIZE) + ETH_HLEN + ETH_FCS_LEN, L1_CACHE_BYTES) #define MVPP2_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD) #define MVPP2_RX_TOTAL_SIZE(buf_size) ((buf_size) + MVPP2_SKB_SHINFO_SIZE) @@ -4493,10 +4492,6 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, if (!aggr_txq->descs) return -ENOMEM; - /* Make sure descriptor address is cache line size aligned */ - BUG_ON(aggr_txq->descs != - PTR_ALIGN(aggr_txq->descs, MVPP2_CPU_D_CACHE_LINE_SIZE)); - aggr_txq->last_desc = aggr_txq->size - 1; /* Aggr TXQ no reset WA */ @@ -4526,9 +4521,6 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, if (!rxq->descs) return -ENOMEM; - BUG_ON(rxq->descs != - PTR_ALIGN(rxq->descs, MVPP2_CPU_D_CACHE_LINE_SIZE)); - rxq->last_desc = rxq->size - 1; /* Zero occupied and non-occupied counters - direct access */ @@ -4616,10 +4608,6 @@ static int mvpp2_txq_init(struct mvpp2_port *port, if (!txq->descs) return -ENOMEM; - /* Make sure descriptor address is cache line size aligned */ - BUG_ON(txq->descs != - PTR_ALIGN(txq->descs, MVPP2_CPU_D_CACHE_LINE_SIZE)); - txq->last_desc = txq->size - 1; /* Set Tx descriptors queue starting address - indirect access */ From 9bd9ddb7f89edae241d2da78e3119f226b9b0cf6 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Wed, 30 Mar 2016 19:55:21 +0800 Subject: [PATCH 161/196] net: mvneta: replace MVNETA_CPU_D_CACHE_LINE_SIZE with L1_CACHE_BYTES The mvneta is also used in some Marvell berlin family SoCs which may have 64bytes cacheline size. Replace the MVNETA_CPU_D_CACHE_LINE_SIZE usage with L1_CACHE_BYTES. And since dma_alloc_coherent() is always cacheline size aligned, so remove the align checks. Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 577f7ca7deba..58808718d114 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -260,7 +260,6 @@ #define MVNETA_VLAN_TAG_LEN 4 -#define MVNETA_CPU_D_CACHE_LINE_SIZE 32 #define MVNETA_TX_CSUM_DEF_SIZE 1600 #define MVNETA_TX_CSUM_MAX_SIZE 9800 #define MVNETA_ACC_MODE_EXT1 1 @@ -300,7 +299,7 @@ #define MVNETA_RX_PKT_SIZE(mtu) \ ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \ ETH_HLEN + ETH_FCS_LEN, \ - MVNETA_CPU_D_CACHE_LINE_SIZE) + L1_CACHE_BYTES) #define IS_TSO_HEADER(txq, addr) \ ((addr >= txq->tso_hdrs_phys) && \ @@ -2764,9 +2763,6 @@ static int mvneta_rxq_init(struct mvneta_port *pp, if (rxq->descs == NULL) return -ENOMEM; - BUG_ON(rxq->descs != - PTR_ALIGN(rxq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE)); - rxq->last_desc = rxq->size - 1; /* Set Rx descriptors queue starting address */ @@ -2837,10 +2833,6 @@ static int mvneta_txq_init(struct mvneta_port *pp, if (txq->descs == NULL) return -ENOMEM; - /* Make sure descriptor address is cache line size aligned */ - BUG_ON(txq->descs != - PTR_ALIGN(txq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE)); - txq->last_desc = txq->size - 1; /* Set maximum bandwidth for enabled TXQs */ From 32867fcc0ef9e56939d5200ad983801bbfd581ad Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Thu, 31 Mar 2016 12:05:17 -0300 Subject: [PATCH 162/196] fec: Do not access unexisting register in Coldfire Commit 55cd48c821de ("net: fec: stop the "rcv is not +last, " error messages") introduces a write to a register that does not exist in Coldfire. Move the FEC_FTRL register access inside the FEC_QUIRK_HAS_RACC 'if' block, so that we guarantee it will not be used on Coldfire CPUs. Reported-by: Greg Ungerer Signed-off-by: Fabio Estevam Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 37c081583084..08243c2ff4b4 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -943,8 +943,8 @@ fec_restart(struct net_device *ndev) else val &= ~FEC_RACC_OPTIONS; writel(val, fep->hwp + FEC_RACC); + writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_FTRL); } - writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_FTRL); #endif /* From c57c7a95da842807b475b823ed2e5435c42cb3b0 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 31 Mar 2016 18:10:31 +0200 Subject: [PATCH 163/196] rtnl: fix msg size calculation in if_nlmsg_size() Size of the attribute IFLA_PHYS_PORT_NAME was missing. Fixes: db24a9044ee1 ("net: add support for phys_port_name") CC: David Ahern Signed-off-by: Nicolas Dichtel Acked-by: David Ahern Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f2066772d0f3..a75f7e94b445 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -909,6 +909,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } From 79f4223257bfef52b0a26d0d7ad4019e764be6ce Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Thu, 31 Mar 2016 15:16:47 +0200 Subject: [PATCH 164/196] net: usb: cdc_ncm: adding Telit LE910 V2 mobile broadband card MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Telit LE910 V2 is a mobile broadband card with no ARP capabilities: the patch makes this device to use wwan_noarp_info struct Signed-off-by: Daniele Palmas Reviewed-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ncm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 86ba30ba35e8..2fb31edab125 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1626,6 +1626,13 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long) &wwan_info, }, + /* Telit LE910 V2 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x0036, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + /* DW5812 LTE Verizon Mobile Broadband Card * Unlike DW5550 this device requires FLAG_NOARP */ From 7779c5e23c5132c22a219f1f5554ef81dd15ee91 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 25 Feb 2016 16:15:05 -0500 Subject: [PATCH 165/196] drm/dp: move hw_mutex up the call stack MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 1) don't let other threads trying to bang on aux channel interrupt the defer timeout/logic 2) don't let other threads interrupt the i2c over aux logic Technically, according to people who actually have the DP spec, this should not be required. In practice, it makes some troublesome Dell monitor (and perhaps others) work, so probably a case of "It's compliant if it works with windows" on the hw vendor's part.. v2: rebased to come before DPCD/AUX logging patch for easier backport to stable branches. Reported-by: Dave Wysochanski Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1274157 Cc: stable@vger.kernel.org Signed-off-by: Rob Clark Reviewed-by: Ville Syrjälä Reviewed-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_dp_helper.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 7d58f594cffe..df64ed1c0139 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -179,7 +179,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, { struct drm_dp_aux_msg msg; unsigned int retry; - int err; + int err = 0; memset(&msg, 0, sizeof(msg)); msg.address = offset; @@ -187,6 +187,8 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, msg.buffer = buffer; msg.size = size; + mutex_lock(&aux->hw_mutex); + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -195,25 +197,24 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, */ for (retry = 0; retry < 32; retry++) { - mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); - mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; - return err; + goto unlock; } switch (msg.reply & DP_AUX_NATIVE_REPLY_MASK) { case DP_AUX_NATIVE_REPLY_ACK: if (err < size) - return -EPROTO; - return err; + err = -EPROTO; + goto unlock; case DP_AUX_NATIVE_REPLY_NACK: - return -EIO; + err = -EIO; + goto unlock; case DP_AUX_NATIVE_REPLY_DEFER: usleep_range(AUX_RETRY_INTERVAL, AUX_RETRY_INTERVAL + 100); @@ -222,7 +223,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, } DRM_DEBUG_KMS("too many retries, giving up\n"); - return -EIO; + err = -EIO; + +unlock: + mutex_unlock(&aux->hw_mutex); + return err; } /** @@ -544,9 +549,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) int max_retries = max(7, drm_dp_i2c_retry_count(msg, dp_aux_i2c_speed_khz)); for (retry = 0, defer_i2c = 0; retry < (max_retries + defer_i2c); retry++) { - mutex_lock(&aux->hw_mutex); ret = aux->transfer(aux, msg); - mutex_unlock(&aux->hw_mutex); if (ret < 0) { if (ret == -EBUSY) continue; @@ -685,6 +688,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, memset(&msg, 0, sizeof(msg)); + mutex_lock(&aux->hw_mutex); + for (i = 0; i < num; i++) { msg.address = msgs[i].addr; drm_dp_i2c_msg_set_request(&msg, &msgs[i]); @@ -739,6 +744,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, msg.size = 0; (void)drm_dp_i2c_do_msg(aux, &msg); + mutex_unlock(&aux->hw_mutex); + return err; } From 72b9ff0612ad8fc969b910cd00ac16b57a1a9ba4 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 30 Mar 2016 11:40:43 +0200 Subject: [PATCH 166/196] drm/udl: Use unlocked gem unreferencing For drm_gem_object_unreference callers are required to hold dev->struct_mutex, which these paths don't. Enforcing this requirement has become a bit more strict with commit ef4c6270bf2867e2f8032e9614d1a8cfc6c71663 Author: Daniel Vetter Date: Thu Oct 15 09:36:25 2015 +0200 drm/gem: Check locking in drm_gem_object_unreference Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/udl/udl_fb.c | 2 +- drivers/gpu/drm/udl/udl_gem.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index 33239a2b264a..fd1eb9d03f0b 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -536,7 +536,7 @@ static int udlfb_create(struct drm_fb_helper *helper, out_destroy_fbi: drm_fb_helper_release_fbi(helper); out_gfree: - drm_gem_object_unreference(&ufbdev->ufb.obj->base); + drm_gem_object_unreference_unlocked(&ufbdev->ufb.obj->base); out: return ret; } diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c index 2a0a784ab6ee..d7528e0d8442 100644 --- a/drivers/gpu/drm/udl/udl_gem.c +++ b/drivers/gpu/drm/udl/udl_gem.c @@ -52,7 +52,7 @@ udl_gem_create(struct drm_file *file, return ret; } - drm_gem_object_unreference(&obj->base); + drm_gem_object_unreference_unlocked(&obj->base); *handle_p = handle; return 0; } From e549d190f7b5f94e9ab36bd965028112914d010d Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Fri, 1 Apr 2016 11:00:15 +0800 Subject: [PATCH 167/196] ALSA: hda - fix front mic problem for a HP desktop The front mic jack (pink color) can't detect any plug or unplug. After applying this fix, both detecting function and recording function work well. BugLink: https://bugs.launchpad.net/bugs/1564712 Cc: stable@vger.kernel.org Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 73978c79981f..fefe83f2beab 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4759,6 +4759,7 @@ enum { ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC280_FIXUP_HP_HEADSET_MIC, + ALC221_FIXUP_HP_FRONT_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -5401,6 +5402,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC, }, + [ALC221_FIXUP_HP_FRONT_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x02a19020 }, /* Front Mic */ + { } + }, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5506,6 +5514,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC), + SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From 353def94606fda16d9ae1761b4b0583286481ec5 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 31 Mar 2016 22:33:23 +0900 Subject: [PATCH 168/196] MAINTAINERS: Update my email address Since I moved to Linaro, this old address doesn't work anymore. I'll use my kernel.org account for upstreaming. Signed-off-by: Masami Hiramatsu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/1459431203-7438-1-git-send-email-mhiramat@kernel.org Signed-off-by: Ingo Molnar --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 378ebfff2d1f..ed121a5b9319 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6402,7 +6402,7 @@ KPROBES M: Ananth N Mavinakayanahalli M: Anil S Keshavamurthy M: "David S. Miller" -M: Masami Hiramatsu +M: Masami Hiramatsu S: Maintained F: Documentation/kprobes.txt F: include/linux/kprobes.h From aa624886b6fa5807ef0540d153f542d72c64acf3 Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Wed, 16 Mar 2016 13:56:35 +0100 Subject: [PATCH 169/196] s390/pci: PCI function group 0 is valid for clp_query_pci_fn The PCI function group 0 is a valid function group, it is wrong to reject it. Let's accept PCI function group 0. Signed-off-by: Pierre Morel Acked-by: Sebastian Ott Signed-off-by: Martin Schwidefsky --- arch/s390/pci/pci_clp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 21591ddb4c1f..1a4512c8544a 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -176,8 +176,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh) rc = clp_store_query_pci_fn(zdev, &rrb->response); if (rc) goto out; - if (rrb->response.pfgid) - rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid); + rc = clp_query_pci_fngrp(zdev, rrb->response.pfgid); } else { zpci_err("Q PCI FN:\n"); zpci_err_clp(rrb->response.hdr.rsp, rc); From 3358999a8e7ae82912e5908adb7150a6558d6702 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 21 Mar 2016 13:48:43 +0100 Subject: [PATCH 170/196] s390: wire up preadv2/pwritev2 syscalls Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/uapi/asm/unistd.h | 4 +++- arch/s390/kernel/syscalls.S | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index ab3aa6875a59..4384bc797a54 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -311,7 +311,9 @@ #define __NR_shutdown 373 #define __NR_mlock2 374 #define __NR_copy_file_range 375 -#define NR_syscalls 376 +#define __NR_preadv2 376 +#define __NR_pwritev2 377 +#define NR_syscalls 378 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 293d8b98fd52..9b59e6212d8f 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -384,3 +384,5 @@ SYSCALL(sys_recvmsg,compat_sys_recvmsg) SYSCALL(sys_shutdown,sys_shutdown) SYSCALL(sys_mlock2,compat_sys_mlock2) SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */ +SYSCALL(sys_preadv2,compat_sys_preadv2) +SYSCALL(sys_pwritev2,compat_sys_pwritev2) From 4a07083ed613644c96c34a7dd2853dc5d7c70902 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 1 Apr 2016 12:28:16 +0200 Subject: [PATCH 171/196] ALSA: timer: Use mod_timer() for rearming the system timer ALSA system timer backend stops the timer via del_timer() without sync and leaves del_timer_sync() at the close instead. This is because of the restriction by the design of ALSA timer: namely, the stop callback may be called from the timer handler, and calling the sync shall lead to a hangup. However, this also triggers a kernel BUG() when the timer is rearmed immediately after stopping without sync: kernel BUG at kernel/time/timer.c:966! Call Trace: [] snd_timer_s_start+0x13e/0x1a0 [] snd_timer_interrupt+0x504/0xec0 [] ? debug_check_no_locks_freed+0x290/0x290 [] snd_timer_s_function+0xb4/0x120 [] call_timer_fn+0x162/0x520 [] ? call_timer_fn+0xcd/0x520 [] ? snd_timer_interrupt+0xec0/0xec0 .... It's the place where add_timer() checks the pending timer. It's clear that this may happen after the immediate restart without sync in our cases. So, the workaround here is just to use mod_timer() instead of add_timer(). This looks like a band-aid fix, but it's a right move, as snd_timer_interrupt() takes care of the continuous rearm of timer. Reported-by: Jiri Slaby Cc: Signed-off-by: Takashi Iwai --- sound/core/timer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/core/timer.c b/sound/core/timer.c index ea4d999113ef..6469bedda2f3 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1019,8 +1019,8 @@ static int snd_timer_s_start(struct snd_timer * timer) njiff += timer->sticks - priv->correction; priv->correction = 0; } - priv->last_expires = priv->tlist.expires = njiff; - add_timer(&priv->tlist); + priv->last_expires = njiff; + mod_timer(&priv->tlist, njiff); return 0; } From 5a5abb1fa3b05dd6aa821525832644c1e7d2905f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Mar 2016 02:13:18 +0200 Subject: [PATCH 172/196] tun, bpf: fix suspicious RCU usage in tun_{attach, detach}_filter Sasha Levin reported a suspicious rcu_dereference_protected() warning found while fuzzing with trinity that is similar to this one: [ 52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage! [ 52.765688] other info that might help us debug this: [ 52.765695] rcu_scheduler_active = 1, debug_locks = 1 [ 52.765701] 1 lock held by a.out/1525: [ 52.765704] #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x17/0x20 [ 52.765721] stack backtrace: [ 52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264 [...] [ 52.765768] Call Trace: [ 52.765775] [] dump_stack+0x85/0xc8 [ 52.765784] [] lockdep_rcu_suspicious+0xd5/0x110 [ 52.765792] [] sk_detach_filter+0x82/0x90 [ 52.765801] [] tun_detach_filter+0x35/0x90 [tun] [ 52.765810] [] __tun_chr_ioctl+0x354/0x1130 [tun] [ 52.765818] [] ? selinux_file_ioctl+0x130/0x210 [ 52.765827] [] tun_chr_ioctl+0x13/0x20 [tun] [ 52.765834] [] do_vfs_ioctl+0x96/0x690 [ 52.765843] [] ? security_file_ioctl+0x43/0x60 [ 52.765850] [] SyS_ioctl+0x79/0x90 [ 52.765858] [] do_syscall_64+0x62/0x140 [ 52.765866] [] entry_SYSCALL64_slow_path+0x25/0x25 Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH, DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices. Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu fixes") sk_attach_filter()/sk_detach_filter() now dereferences the filter with rcu_dereference_protected(), checking whether socket lock is held in control path. Since its introduction in 994051625981 ("tun: socket filter support"), tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the sock_owned_by_user(sk) doesn't apply in this specific case and therefore triggers the false positive. Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair that is used by tap filters and pass in lockdep_rtnl_is_held() for the rcu_dereference_protected() checks instead. Reported-by: Sasha Levin Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/tun.c | 8 +++++--- include/linux/filter.h | 4 ++++ net/core/filter.c | 33 +++++++++++++++++++++------------ 3 files changed, 30 insertions(+), 15 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index afdf950617c3..510e90a6bb26 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -622,7 +622,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { - err = sk_attach_filter(&tun->fprog, tfile->socket.sk); + err = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (!err) goto out; } @@ -1822,7 +1823,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n) for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - sk_detach_filter(tfile->socket.sk); + __sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held()); } tun->filter_attached = false; @@ -1835,7 +1836,8 @@ static int tun_attach_filter(struct tun_struct *tun) for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); - ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); + ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); if (ret) { tun_detach_filter(tun, i); return ret; diff --git a/include/linux/filter.h b/include/linux/filter.h index 43aa1f8855c7..a51a5361695f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -465,10 +465,14 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); +int __sk_detach_filter(struct sock *sk, bool locked); + int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); diff --git a/net/core/filter.c b/net/core/filter.c index 4b81b71171b4..ca7f832b2980 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1149,7 +1149,8 @@ void bpf_prog_destroy(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_destroy); -static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk, + bool locked) { struct sk_filter *fp, *old_fp; @@ -1165,10 +1166,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + old_fp = rcu_dereference_protected(sk->sk_filter, locked); rcu_assign_pointer(sk->sk_filter, fp); - if (old_fp) sk_filter_uncharge(sk, old_fp); @@ -1247,7 +1246,8 @@ struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; @@ -1255,7 +1255,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, locked); if (err < 0) { __bpf_prog_release(prog); return err; @@ -1263,7 +1263,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(sk_attach_filter); +EXPORT_SYMBOL_GPL(__sk_attach_filter); + +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk)); +} int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { @@ -1309,7 +1314,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk)); if (err < 0) { bpf_prog_put(prog); return err; @@ -2250,7 +2255,7 @@ static int __init register_sk_filter_ops(void) } late_initcall(register_sk_filter_ops); -int sk_detach_filter(struct sock *sk) +int __sk_detach_filter(struct sock *sk, bool locked) { int ret = -ENOENT; struct sk_filter *filter; @@ -2258,8 +2263,7 @@ int sk_detach_filter(struct sock *sk) if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; - filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + filter = rcu_dereference_protected(sk->sk_filter, locked); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -2268,7 +2272,12 @@ int sk_detach_filter(struct sock *sk) return ret; } -EXPORT_SYMBOL_GPL(sk_detach_filter); +EXPORT_SYMBOL_GPL(__sk_detach_filter); + +int sk_detach_filter(struct sock *sk) +{ + return __sk_detach_filter(sk, sock_owned_by_user(sk)); +} int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) From d82b0c21d44d1cc61a23db56c2b2cf52ea9f3220 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Thu, 31 Mar 2016 17:01:23 +0800 Subject: [PATCH 173/196] net: mvpp2: fix maybe-uninitialized warning This is to fix the following maybe-uninitialized warning: drivers/net/ethernet/marvell/mvpp2.c:6007:18: warning: 'err' may be used uninitialized in this function [-Wmaybe-uninitialized] Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 05f358b81791..2750cb978f42 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -6047,8 +6047,10 @@ static int mvpp2_port_init(struct mvpp2_port *port) /* Map physical Rx queue to port's logical Rx queue */ rxq = devm_kzalloc(dev, sizeof(*rxq), GFP_KERNEL); - if (!rxq) + if (!rxq) { + err = -ENOMEM; goto err_free_percpu; + } /* Map this Rx queue to a physical queue */ rxq->id = port->first_rxq + queue; rxq->port = port->id; From 4a0a12d27ca5e892579f3c61c18c8dcfebf425d4 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 1 Apr 2016 17:11:05 +0800 Subject: [PATCH 174/196] net: mvpp2: use cache_line_size() to get cacheline size L1_CACHE_BYTES may not be the real cacheline size, use cache_line_size to determine the cacheline size in runtime. Signed-off-by: Jisheng Zhang Suggested-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 2750cb978f42..868a957f24bb 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -376,7 +376,7 @@ #define MVPP2_RX_PKT_SIZE(mtu) \ ALIGN((mtu) + MVPP2_MH_SIZE + MVPP2_VLAN_TAG_LEN + \ - ETH_HLEN + ETH_FCS_LEN, L1_CACHE_BYTES) + ETH_HLEN + ETH_FCS_LEN, cache_line_size()) #define MVPP2_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD) #define MVPP2_RX_TOTAL_SIZE(buf_size) ((buf_size) + MVPP2_SKB_SHINFO_SIZE) From c66e98c9532bf7b58fe78cc59fb37d3ff651756d Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 1 Apr 2016 17:12:49 +0800 Subject: [PATCH 175/196] net: mvneta: use cache_line_size() to get cacheline size L1_CACHE_BYTES may not be the real cacheline size, use cache_line_size to determine the cacheline size in runtime. Signed-off-by: Jisheng Zhang Suggested-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 58808718d114..b1db000f1927 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -299,7 +299,7 @@ #define MVNETA_RX_PKT_SIZE(mtu) \ ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \ ETH_HLEN + ETH_FCS_LEN, \ - L1_CACHE_BYTES) + cache_line_size()) #define IS_TSO_HEADER(txq, addr) \ ((addr >= txq->tso_hdrs_phys) && \ From a00e3ab64be2e482bd25fe30bdc9bfa6e2b0cf1c Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 1 Apr 2016 09:07:14 +0200 Subject: [PATCH 176/196] stmmac: fix TX normal DESC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixs a regression raised when test on chips that use the normal descriptor layout. In fact, no len bits were set for the TDES1 and no OWN bit inside the TDES0. Signed-off-by: Giuseppe CAVALLARO Tested-by: Andreas Färber Cc: Fabrice Gasnier Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index e13228f115f0..011386f6f24d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -199,11 +199,6 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, { unsigned int tdes1 = p->des1; - if (mode == STMMAC_CHAIN_MODE) - norm_set_tx_desc_len_on_chain(p, len); - else - norm_set_tx_desc_len_on_ring(p, len); - if (is_fs) tdes1 |= TDES1_FIRST_SEGMENT; else @@ -217,10 +212,15 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, if (ls) tdes1 |= TDES1_LAST_SEGMENT; - if (tx_own) - tdes1 |= TDES0_OWN; - p->des1 = tdes1; + + if (mode == STMMAC_CHAIN_MODE) + norm_set_tx_desc_len_on_chain(p, len); + else + norm_set_tx_desc_len_on_ring(p, len); + + if (tx_own) + p->des0 |= TDES0_OWN; } static void ndesc_set_tx_ic(struct dma_desc *p) From d7e944c8ddc0983640a9a32868fb217485d12ca2 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 1 Apr 2016 09:07:15 +0200 Subject: [PATCH 177/196] Revert "stmmac: Fix 'eth0: No PHY found' regression" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 88f8b1bb41c6208f81b6a480244533ded7b59493. due to problems on GeekBox and Banana Pi M1 board when connected to a real transceiver instead of a switch via fixed-link. Signed-off-by: Giuseppe Cavallaro Cc: Gabriel Fernandez Cc: Andreas Färber Cc: Frank Schäfer Cc: Dinh Nguyen Cc: David S. Miller Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 11 ++++++++++- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 9 +-------- include/linux/stmmac.h | 1 - 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index ea76129dafc2..af09ced53bd8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -199,12 +199,21 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; - struct device_node *mdio_node = priv->plat->mdio_node; + struct device_node *mdio_node = NULL; + struct device_node *child_node = NULL; if (!mdio_bus_data) return 0; if (IS_ENABLED(CONFIG_OF)) { + for_each_child_of_node(priv->device->of_node, child_node) { + if (of_device_is_compatible(child_node, + "snps,dwmac-mdio")) { + mdio_node = child_node; + break; + } + } + if (mdio_node) { netdev_dbg(ndev, "FOUND MDIO subnode\n"); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index dcbd2a1601e8..9cf181f839fd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -146,7 +146,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; - struct device_node *child_node = NULL; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -177,19 +176,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->phy_node = of_node_get(np); } - for_each_child_of_node(np, child_node) - if (of_device_is_compatible(child_node, "snps,dwmac-mdio")) { - plat->mdio_node = child_node; - break; - } - /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 4bcf5a61aada..6e53fa8942a4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -114,7 +114,6 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; - struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; From a7657f128c279ae5796ab2ca7d04a7819f4259f0 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 1 Apr 2016 09:07:16 +0200 Subject: [PATCH 178/196] stmmac: fix MDIO settings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Initially the phy_bus_name was added to manipulate the driver name but it was recently just used to manage the fixed-link and then to take some decision at run-time. So the patch uses the is_pseudo_fixed_link and removes the phy_bus_name variable not necessary anymore. The driver can manage the mdio registration by using phy-handle, dwmac-mdio and own parameter e.g. snps,phy-addr. This patch takes care about all these possible configurations and fixes the mdio registration in case of there is a real transceiver or a switch (that needs to be managed by using fixed-link). Signed-off-by: Giuseppe Cavallaro Reviewed-by: Andreas Färber Tested-by: Frank Schäfer Cc: Gabriel Fernandez Cc: Dinh Nguyen Cc: David S. Miller Cc: Phil Reid Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 16 ++-- .../net/ethernet/stmicro/stmmac/stmmac_mdio.c | 19 +---- .../ethernet/stmicro/stmmac/stmmac_platform.c | 84 +++++++++++++++---- include/linux/stmmac.h | 2 +- 4 files changed, 73 insertions(+), 48 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4c5ce9848ca9..78464fa7fe1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -278,7 +278,6 @@ static void stmmac_eee_ctrl_timer(unsigned long arg) */ bool stmmac_eee_init(struct stmmac_priv *priv) { - char *phy_bus_name = priv->plat->phy_bus_name; unsigned long flags; bool ret = false; @@ -290,7 +289,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) goto out; /* Never init EEE in case of a switch is attached */ - if (phy_bus_name && (!strcmp(phy_bus_name, "fixed"))) + if (priv->phydev->is_pseudo_fixed_link) goto out; /* MAC core supports the EEE feature. */ @@ -827,12 +826,8 @@ static int stmmac_init_phy(struct net_device *dev) phydev = of_phy_connect(dev, priv->plat->phy_node, &stmmac_adjust_link, 0, interface); } else { - if (priv->plat->phy_bus_name) - snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x", - priv->plat->phy_bus_name, priv->plat->bus_id); - else - snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x", - priv->plat->bus_id); + snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x", + priv->plat->bus_id); snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id, priv->plat->phy_addr); @@ -871,9 +866,8 @@ static int stmmac_init_phy(struct net_device *dev) } /* If attached to a switch, there is no reason to poll phy handler */ - if (priv->plat->phy_bus_name) - if (!strcmp(priv->plat->phy_bus_name, "fixed")) - phydev->irq = PHY_IGNORE_INTERRUPT; + if (phydev->is_pseudo_fixed_link) + phydev->irq = PHY_IGNORE_INTERRUPT; pr_debug("stmmac_init_phy: %s: attached to PHY (UID 0x%x)" " Link = %d\n", dev->name, phydev->phy_id, phydev->link); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index af09ced53bd8..06704ca6f9ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -198,29 +198,12 @@ int stmmac_mdio_register(struct net_device *ndev) struct mii_bus *new_bus; struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; + struct device_node *mdio_node = priv->plat->mdio_node; int addr, found; - struct device_node *mdio_node = NULL; - struct device_node *child_node = NULL; if (!mdio_bus_data) return 0; - if (IS_ENABLED(CONFIG_OF)) { - for_each_child_of_node(priv->device->of_node, child_node) { - if (of_device_is_compatible(child_node, - "snps,dwmac-mdio")) { - mdio_node = child_node; - break; - } - } - - if (mdio_node) { - netdev_dbg(ndev, "FOUND MDIO subnode\n"); - } else { - netdev_warn(ndev, "No MDIO subnode found\n"); - } - } - new_bus = mdiobus_alloc(); if (new_bus == NULL) return -ENOMEM; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 9cf181f839fd..cf37ea558ecc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -131,6 +131,69 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) return axi; } +/** + * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources + * @plat: driver data platform structure + * @np: device tree node + * @dev: device pointer + * Description: + * The mdio bus will be allocated in case of a phy transceiver is on board; + * it will be NULL if the fixed-link is configured. + * If there is the "snps,dwmac-mdio" sub-node the mdio will be allocated + * in any case (for DSA, mdio must be registered even if fixed-link). + * The table below sums the supported configurations: + * ------------------------------- + * snps,phy-addr | Y + * ------------------------------- + * phy-handle | Y + * ------------------------------- + * fixed-link | N + * ------------------------------- + * snps,dwmac-mdio | + * even if | Y + * fixed-link | + * ------------------------------- + * + * It returns 0 in case of success otherwise -ENODEV. + */ +static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, + struct device_node *np, struct device *dev) +{ + bool mdio = true; + + /* If phy-handle property is passed from DT, use it as the PHY */ + plat->phy_node = of_parse_phandle(np, "phy-handle", 0); + if (plat->phy_node) + dev_dbg(dev, "Found phy-handle subnode\n"); + + /* If phy-handle is not specified, check if we have a fixed-phy */ + if (!plat->phy_node && of_phy_is_fixed_link(np)) { + if ((of_phy_register_fixed_link(np) < 0)) + return -ENODEV; + + dev_dbg(dev, "Found fixed-link subnode\n"); + plat->phy_node = of_node_get(np); + mdio = false; + } + + /* If snps,dwmac-mdio is passed from DT, always register the MDIO */ + for_each_child_of_node(np, plat->mdio_node) { + if (of_device_is_compatible(plat->mdio_node, "snps,dwmac-mdio")) + break; + } + + if (plat->mdio_node) { + dev_dbg(dev, "Found MDIO subnode\n"); + mdio = true; + } + + if (mdio) + plat->mdio_bus_data = + devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data), + GFP_KERNEL); + return 0; +} + /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure @@ -165,30 +228,15 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) /* Default to phy auto-detection */ plat->phy_addr = -1; - /* If we find a phy-handle property, use it as the PHY */ - plat->phy_node = of_parse_phandle(np, "phy-handle", 0); - - /* If phy-handle is not specified, check if we have a fixed-phy */ - if (!plat->phy_node && of_phy_is_fixed_link(np)) { - if ((of_phy_register_fixed_link(np) < 0)) - return ERR_PTR(-ENODEV); - - plat->phy_node = of_node_get(np); - } - /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) - plat->mdio_bus_data = NULL; - else - plat->mdio_bus_data = - devm_kzalloc(&pdev->dev, - sizeof(struct stmmac_mdio_bus_data), - GFP_KERNEL); + /* To Configure PHY by using all device-tree supported properties */ + if (stmmac_dt_phy(plat, np, &pdev->dev)) + return ERR_PTR(-ENODEV); of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 6e53fa8942a4..e6bc30a42a74 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -108,12 +108,12 @@ struct stmmac_axi { }; struct plat_stmmacenet_data { - char *phy_bus_name; int bus_id; int phy_addr; int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; From db5dd0db2d8352bb7fd5e9d16e17b79d66c7e4e3 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Fri, 1 Apr 2016 15:21:18 +0200 Subject: [PATCH 179/196] net: mvneta: fix changing MTU when using per-cpu processing After enabling per-cpu processing it appeared that under heavy load changing MTU can result in blocking all port's interrupts and transmitting data is not possible after the change. This commit fixes above issue by disabling percpu interrupts for the time, when TXQs and RXQs are reconfigured. Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 30 ++++++++++++++------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index b1db000f1927..7fc490225da5 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3042,6 +3042,20 @@ static int mvneta_check_mtu_valid(struct net_device *dev, int mtu) return mtu; } +static void mvneta_percpu_enable(void *arg) +{ + struct mvneta_port *pp = arg; + + enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE); +} + +static void mvneta_percpu_disable(void *arg) +{ + struct mvneta_port *pp = arg; + + disable_percpu_irq(pp->dev->irq); +} + /* Change the device mtu */ static int mvneta_change_mtu(struct net_device *dev, int mtu) { @@ -3066,6 +3080,7 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) * reallocation of the queues */ mvneta_stop_dev(pp); + on_each_cpu(mvneta_percpu_disable, pp, true); mvneta_cleanup_txqs(pp); mvneta_cleanup_rxqs(pp); @@ -3089,6 +3104,7 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) return ret; } + on_each_cpu(mvneta_percpu_enable, pp, true); mvneta_start_dev(pp); mvneta_port_up(pp); @@ -3242,20 +3258,6 @@ static void mvneta_mdio_remove(struct mvneta_port *pp) pp->phy_dev = NULL; } -static void mvneta_percpu_enable(void *arg) -{ - struct mvneta_port *pp = arg; - - enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE); -} - -static void mvneta_percpu_disable(void *arg) -{ - struct mvneta_port *pp = arg; - - disable_percpu_irq(pp->dev->irq); -} - /* Electing a CPU must be done in an atomic way: it should be done * after or before the removal/insertion of a CPU and this function is * not reentrant. From b39c3cf44cda4770025a660af9abcd4cf9b62f56 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 1 Apr 2016 14:31:12 -0700 Subject: [PATCH 180/196] MAINTAINERS: orangefs mailing list is subscribers-only So update MAINTAINERS to say so. Signed-off-by: Joe Perches Cc: Mike Marshall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 378ebfff2d1f..7ba7bc485d74 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8253,7 +8253,7 @@ F: Documentation/filesystems/overlayfs.txt ORANGEFS FILESYSTEM M: Mike Marshall -L: pvfs2-developers@beowulf-underground.org +L: pvfs2-developers@beowulf-underground.org (subscribers-only) T: git git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux.git S: Supported F: fs/orangefs/ From 0b355eaaaae9bb8bb08b563ef55ecb23a4d743da Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 1 Apr 2016 14:31:15 -0700 Subject: [PATCH 181/196] mm, kasan: fix compilation for CONFIG_SLAB Add the missing argument to set_track(). Fixes: cd11016e5f52 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB") Signed-off-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Christoph Lameter Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Steven Rostedt Cc: Joonsoo Kim Cc: Konstantin Serebryany Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index acb3b6c4dd89..38f1dd79acdb 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -498,7 +498,7 @@ void kasan_slab_free(struct kmem_cache *cache, void *object) struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object); alloc_info->state = KASAN_STATE_FREE; - set_track(&free_info->track); + set_track(&free_info->track, GFP_NOWAIT); } #endif From 969e8d7e47f93ef693028667480558de8f70523f Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Fri, 1 Apr 2016 14:31:17 -0700 Subject: [PATCH 182/196] include/linux/huge_mm.h: return NULL instead of false for pmd_trans_huge_lock() The return value of pmd_trans_huge_lock() is a pointer, not a boolean value, so use NULL instead of false as the return value. Signed-off-by: Chen Gang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 79b0ef6aaa14..7008623e24b1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -127,7 +127,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else - return false; + return NULL; } static inline int hpage_nr_pages(struct page *page) { From 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 Mon Sep 17 00:00:00 2001 From: Xishi Qiu Date: Fri, 1 Apr 2016 14:31:20 -0700 Subject: [PATCH 183/196] mm: fix invalid node in alloc_migrate_target() It is incorrect to use next_node to find a target node, it will return MAX_NUMNODES or invalid node. This will lead to crash in buddy system allocation. Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage") Signed-off-by: Xishi Qiu Acked-by: Vlastimil Babka Acked-by: Naoya Horiguchi Cc: Joonsoo Kim Cc: David Rientjes Cc: "Laura Abbott" Cc: Hui Zhu Cc: Wang Xiaoqiang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 92c4c36501e7..31555b689eb9 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -289,11 +289,11 @@ struct page *alloc_migrate_target(struct page *page, unsigned long private, * now as a simple work-around, we use the next node for destination. */ if (PageHuge(page)) { - nodemask_t src = nodemask_of_node(page_to_nid(page)); - nodemask_t dst; - nodes_complement(dst, src); + int node = next_online_node(page_to_nid(page)); + if (node == MAX_NUMNODES) + node = first_online_node; return alloc_huge_page_node(page_hstate(compound_head(page)), - next_node(page_to_nid(page), dst)); + node); } if (PageHighMem(page)) From 18c98243ddf05a1827ad2c359c5ac051101e7ff7 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Fri, 1 Apr 2016 14:31:23 -0700 Subject: [PATCH 184/196] x86/mm: TLB_REMOTE_SEND_IPI should count pages TLB_REMOTE_SEND_IPI was recently introduced, but it counts bytes instead of pages. In addition, it does not report correctly the case in which flush_tlb_page flushes a page. Fix it to be consistent with other TLB counters. Fixes: 5b74283ab251b9d ("x86, mm: trace when an IPI is about to be sent") Signed-off-by: Nadav Amit Cc: Mel Gorman Cc: Rik van Riel Cc: Dave Hansen Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/tlb.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8f4cc3dfac32..5fb6adaaa796 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -106,8 +106,6 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - if (!f->flush_end) - f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { @@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask, unsigned long end) { struct flush_tlb_info info; + + if (end == 0) + end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); + if (end == TLB_FLUSH_ALL) + trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); + else + trace_tlb_flush(TLB_REMOTE_SEND_IPI, + (end - start) >> PAGE_SHIFT); + if (is_uv_system()) { unsigned int cpu; From 858eaaa711700ce4595e039441e239e56d7b9514 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Fri, 1 Apr 2016 14:31:26 -0700 Subject: [PATCH 185/196] mm/rmap: batched invalidations should use existing api The recently introduced batched invalidations mechanism uses its own mechanism for shootdown. However, it does wrong accounting of interrupts (e.g., inc_irq_stat is called for local invalidations), trace-points (e.g., TLB_REMOTE_SHOOTDOWN for local invalidations) and may break some platforms as it bypasses the invalidation mechanisms of Xen and SGI UV. This patch reuses the existing TLB flushing mechnaisms instead. We use NULL as mm to indicate a global invalidation is required. Fixes 72b252aed506b8 ("mm: send one IPI per CPU to TLB flush all entries after unmapping pages") Signed-off-by: Nadav Amit Cc: Mel Gorman Cc: Rik van Riel Cc: Dave Hansen Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/tlbflush.h | 6 ------ arch/x86/mm/tlb.c | 2 +- mm/rmap.c | 28 +++++++--------------------- 3 files changed, 8 insertions(+), 28 deletions(-) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index c24b4224d439..1fde8d580a5b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -319,12 +319,6 @@ static inline void reset_lazy_tlbstate(void) #endif /* SMP */ -/* Not inlined due to inc_irq_stat not being defined yet */ -#define flush_tlb_local() { \ - inc_irq_stat(irq_tlb_count); \ - local_flush_tlb(); \ -} - #ifndef CONFIG_PARAVIRT #define flush_tlb_others(mask, mm, start, end) \ native_flush_tlb_others(mask, mm, start, end) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5fb6adaaa796..fe9b9f776361 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -104,7 +104,7 @@ static void flush_tlb_func(void *info) inc_irq_stat(irq_tlb_count); - if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) + if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); diff --git a/mm/rmap.c b/mm/rmap.c index c399a0d41b31..395e314b7996 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -569,19 +569,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH -static void percpu_flush_tlb_batch_pages(void *data) -{ - /* - * All TLB entries are flushed on the assumption that it is - * cheaper to flush all TLBs and let them be refilled than - * flushing individual PFNs. Note that we do not track mm's - * to flush as that might simply be multiple full TLB flushes - * for no gain. - */ - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - flush_tlb_local(); -} - /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed @@ -598,15 +585,14 @@ void try_to_unmap_flush(void) cpu = get_cpu(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, -1UL); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) - percpu_flush_tlb_batch_pages(&tlb_ubc->cpumask); - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) { - smp_call_function_many(&tlb_ubc->cpumask, - percpu_flush_tlb_batch_pages, (void *)tlb_ubc, true); + if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); } + + if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); cpumask_clear(&tlb_ubc->cpumask); tlb_ubc->flush_required = false; tlb_ubc->writable = false; From bbe3de2560280c0420d36a192e69f2772e893cf4 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 1 Apr 2016 14:31:32 -0700 Subject: [PATCH 186/196] mm/page_isolation: fix tracepoint to mirror check function behavior Page isolation has not failed if the fin pfn extends beyond the end pfn and test_pages_isolated checks this correctly. Fix the tracepoint to report the same result as the actual check function. Signed-off-by: Lucas Stach Acked-by: Vlastimil Babka Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/page_isolation.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/page_isolation.h b/include/trace/events/page_isolation.h index 6fb644029c80..8738a78e6bf4 100644 --- a/include/trace/events/page_isolation.h +++ b/include/trace/events/page_isolation.h @@ -29,7 +29,7 @@ TRACE_EVENT(test_pages_isolated, TP_printk("start_pfn=0x%lx end_pfn=0x%lx fin_pfn=0x%lx ret=%s", __entry->start_pfn, __entry->end_pfn, __entry->fin_pfn, - __entry->end_pfn == __entry->fin_pfn ? "success" : "fail") + __entry->end_pfn <= __entry->fin_pfn ? "success" : "fail") ); #endif /* _TRACE_PAGE_ISOLATION_H */ From af8e15cc85a253155fdcea707588bf6ddfc0be2e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Apr 2016 14:31:34 -0700 Subject: [PATCH 187/196] oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head Commit bb29902a7515 ("oom, oom_reaper: protect oom_reaper_list using simpler way") has simplified the check for tasks already enqueued for the oom reaper by checking tsk->oom_reaper_list != NULL. This check is not sufficient because the tsk might be the head of the queue without any other tasks queued and then we would simply lockup looping on the same task. Fix the condition by checking for the head as well. Fixes: bb29902a7515 ("oom, oom_reaper: protect oom_reaper_list using simpler way") Signed-off-by: Michal Hocko Acked-by: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b34d279a7ee6..86349586eacb 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -547,7 +547,11 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - if (!oom_reaper_th || tsk->oom_reaper_list) + if (!oom_reaper_th) + return; + + /* tsk is already queued? */ + if (tsk == oom_reaper_list || tsk->oom_reaper_list) return; get_task_struct(tsk); From ec3b6882509188602dfaadf2814a9cca062f2786 Mon Sep 17 00:00:00 2001 From: Neil Zhang Date: Fri, 1 Apr 2016 14:31:37 -0700 Subject: [PATCH 188/196] mm/page_isolation.c: fix the function comments Commit fea85cff11de ("mm/page_isolation.c: return last tested pfn rather than failure indicator") changed the meaning of the return value. Let's change the function comments as well. Signed-off-by: Neil Zhang Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 31555b689eb9..c4f568206544 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -215,7 +215,7 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 1 if all pages in the range are isolated. + * Returns the last tested pfn. */ static unsigned long __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, From f76be61755c52f4e827755901f6317cc1d007b51 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 1 Apr 2016 14:31:40 -0700 Subject: [PATCH 189/196] Make CONFIG_FHANDLE default y Newer Fedora and OpenSUSE didn't boot with my standard configuration. It took me some time to figure out why, in fact I had to write a script to try different config options systematically. The problem is that something (systemd) in dracut depends on CONFIG_FHANDLE, which adds open by file handle syscalls. While it is set in defconfigs it is very easy to miss when updating older configs because it is not default y. Make it default y and also depend on EXPERT, as dracut use is likely widespread. Signed-off-by: Andi Kleen Cc: Richard Weinberger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index e0d26162432e..0dfd09d54c65 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -272,8 +272,9 @@ config CROSS_MEMORY_ATTACH See the man page for more details. config FHANDLE - bool "open by fhandle syscalls" + bool "open by fhandle syscalls" if EXPERT select EXPORTFS + default y help If you say Y here, a user level program will be able to map file names to handle and then later use the handle for From 394532e4b639dd6ac6053f0d777fb86948f29233 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Fri, 1 Apr 2016 14:31:42 -0700 Subject: [PATCH 190/196] .mailmap: add Christophe Ricard Different computers had different settings in the mail client. Some contributions appear as Christophe Ricard, others as Christophe RICARD. Signed-off-by: Christophe Ricard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 7e6c5334c337..90c0aefc276d 100644 --- a/.mailmap +++ b/.mailmap @@ -33,6 +33,7 @@ Björn Steinbrink Brian Avery Brian King Christoph Hellwig +Christophe Ricard Corey Minyard Damian Hobson-Garcia David Brownell From cb107161df3c52e58033554dcb40065964350f67 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 2 Apr 2016 18:35:05 -0500 Subject: [PATCH 191/196] Convert straggling drivers to new six-argument get_user_pages() Commit d4edcf0d5695 ("mm/gup: Switch all callers of get_user_pages() to not pass tsk/mm") switched get_user_pages() callers to the simpler model where they no longer pass in the thread and mm pointer. But since then we've merged changes to a few drivers that re-introduce use of the old interface. Let's fix them up. They continued to work fine (thanks to the truly disgusting macros introduced in commit cde70140fed8: "mm/gup: Overload get_user_pages() functions"), but cause unnecessary build noise. Signed-off-by: Linus Torvalds --- drivers/platform/goldfish/goldfish_pipe.c | 3 +-- drivers/rapidio/devices/rio_mport_cdev.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c index 9973cebb4d6f..07462d79d040 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -309,8 +309,7 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer, * much memory to the process. */ down_read(¤t->mm->mmap_sem); - ret = get_user_pages(current, current->mm, address, 1, - !is_write, 0, &page, NULL); + ret = get_user_pages(address, 1, !is_write, 0, &page, NULL); up_read(¤t->mm->mmap_sem); if (ret < 0) break; diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 9607bc826460..5d4d91846357 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -886,7 +886,7 @@ rio_dma_transfer(struct file *filp, uint32_t transfer_mode, } down_read(¤t->mm->mmap_sem); - pinned = get_user_pages(current, current->mm, + pinned = get_user_pages( (unsigned long)xfer->loc_addr & PAGE_MASK, nr_pages, dir == DMA_FROM_DEVICE, 0, page_list, NULL); From 17084b7e07909d3a8d51b66b7dfb50a2083a2685 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Apr 2016 07:03:49 -0500 Subject: [PATCH 192/196] v4l2-mc: avoid warning about unused variable Commit 840f5b0572ea ("media: au0828 disable tuner to demod link in au0828_media_device_register()") removed all uses of the 'dtv_demod', but left the variable itself around. Remove it. Signed-off-by: Linus Torvalds --- drivers/media/v4l2-core/v4l2-mc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c index 2a7b79bc90fd..2228cd3a846e 100644 --- a/drivers/media/v4l2-core/v4l2-mc.c +++ b/drivers/media/v4l2-core/v4l2-mc.c @@ -34,7 +34,7 @@ int v4l2_mc_create_media_graph(struct media_device *mdev) { struct media_entity *entity; struct media_entity *if_vid = NULL, *if_aud = NULL; - struct media_entity *tuner = NULL, *decoder = NULL, *dtv_demod = NULL; + struct media_entity *tuner = NULL, *decoder = NULL; struct media_entity *io_v4l = NULL, *io_vbi = NULL, *io_swradio = NULL; bool is_webcam = false; u32 flags; From 9735a22799b9214d17d3c231fe377fc852f042e9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Apr 2016 09:09:40 -0500 Subject: [PATCH 193/196] Linux 4.6-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 916b26e999d8..173437debc87 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Blurry Fish Butt # *DOCUMENTATION* From ea6db90e750328068837bed34cb1302b7a177339 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Thu, 10 Mar 2016 09:48:52 -0500 Subject: [PATCH 194/196] USB: serial: ftdi_sio: Add support for ICP DAS I-756xU devices A Fedora user reports that the ftdi_sio driver works properly for the ICP DAS I-7561U device. Further, the user manual for these devices instructs users to load the driver and add the ids using the sysfs interface. Add support for these in the driver directly so that the devices work out of the box instead of needing manual configuration. Reported-by: CC: stable Signed-off-by: Josh Boyer Signed-off-by: Johan Hovold --- drivers/usb/serial/ftdi_sio.c | 4 ++++ drivers/usb/serial/ftdi_sio_ids.h | 8 ++++++++ 2 files changed, 12 insertions(+) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 427ae43ee898..3a814e802dee 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1004,6 +1004,10 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_DISPLAY_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_LITE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASMART_ANALOG_PID) }, + /* ICP DAS I-756xU devices */ + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) }, + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, + { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index a84df2513994..c5d6c1e73e8e 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -871,6 +871,14 @@ #define NOVITUS_VID 0x1a28 #define NOVITUS_BONO_E_PID 0x6010 +/* + * ICPDAS I-756*U devices + */ +#define ICPDAS_VID 0x1b5c +#define ICPDAS_I7560U_PID 0x0103 +#define ICPDAS_I7561U_PID 0x0104 +#define ICPDAS_I7563U_PID 0x0105 + /* * RT Systems programming cables for various ham radios */ From cddc9434e3dcc37a85c4412fb8e277d3a582e456 Mon Sep 17 00:00:00 2001 From: Martyn Welch Date: Tue, 29 Mar 2016 17:47:29 +0100 Subject: [PATCH 195/196] USB: serial: cp210x: Adding GE Healthcare Device ID The CP2105 is used in the GE Healthcare Remote Alarm Box, with the Manufacturer ID of 0x1901 and Product ID of 0x0194. Signed-off-by: Martyn Welch Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index fbfe761c7fba..dd47823bb014 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -165,6 +165,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ + { USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */ { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ From d48d5691ebf88a15d95ba96486917ffc79256536 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Thu, 7 Apr 2016 12:09:17 +0200 Subject: [PATCH 196/196] USB: option: add "D-Link DWM-221 B1" device id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thomas reports: "Windows: 00 diagnostics 01 modem 02 at-port 03 nmea 04 nic Linux: T: Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=2001 ProdID=7e19 Rev=02.32 S: Manufacturer=Mobile Connect S: Product=Mobile Connect S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage" Reported-by: Thomas Schäfer Cc: Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 348e19834b83..c6f497f16526 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1818,6 +1818,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) }, { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, + { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e19, 0xff), /* D-Link DWM-221 B1 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */