diff options
172 files changed, 8477 insertions, 5448 deletions
diff --git a/Documentation/devicetree/bindings/opp/opp.txt b/Documentation/devicetree/bindings/opp/opp.txt index ecdcfb790704..63725498bd20 100644 --- a/Documentation/devicetree/bindings/opp/opp.txt +++ b/Documentation/devicetree/bindings/opp/opp.txt @@ -188,14 +188,14 @@ Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together. opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <970000 975000 985000>; + opp-microvolt = <975000 970000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; - opp-microvolt = <980000 1000000 1010000>; + opp-microvolt = <1000000 980000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; @@ -267,14 +267,14 @@ independently. opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <970000 975000 985000>; + opp-microvolt = <975000 970000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; - opp-microvolt = <980000 1000000 1010000>; + opp-microvolt = <1000000 980000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; @@ -343,14 +343,14 @@ DVFS state together. opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <970000 975000 985000>; + opp-microvolt = <975000 970000 985000>; opp-microamp = <70000>; clock-latency-ns = <300000>; opp-suspend; }; opp@1100000000 { opp-hz = /bits/ 64 <1100000000>; - opp-microvolt = <980000 1000000 1010000>; + opp-microvolt = <1000000 980000 1010000>; opp-microamp = <80000>; clock-latency-ns = <310000>; }; @@ -369,7 +369,7 @@ DVFS state together. opp@1300000000 { opp-hz = /bits/ 64 <1300000000>; - opp-microvolt = <1045000 1050000 1055000>; + opp-microvolt = <1050000 1045000 1055000>; opp-microamp = <95000>; clock-latency-ns = <400000>; opp-suspend; @@ -382,7 +382,7 @@ DVFS state together. }; opp@1500000000 { opp-hz = /bits/ 64 <1500000000>; - opp-microvolt = <1010000 1100000 1110000>; + opp-microvolt = <1100000 1010000 1110000>; opp-microamp = <95000>; clock-latency-ns = <400000>; turbo-mode; @@ -424,9 +424,9 @@ Example 4: Handling multiple regulators opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <970000 975000 985000>, /* Supply 0 */ - <960000 965000 975000>, /* Supply 1 */ - <960000 965000 975000>; /* Supply 2 */ + opp-microvolt = <975000 970000 985000>, /* Supply 0 */ + <965000 960000 975000>, /* Supply 1 */ + <965000 960000 975000>; /* Supply 2 */ opp-microamp = <70000>, /* Supply 0 */ <70000>, /* Supply 1 */ <70000>; /* Supply 2 */ @@ -437,9 +437,9 @@ Example 4: Handling multiple regulators opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt = <970000 975000 985000>, /* Supply 0 */ - <960000 965000 975000>, /* Supply 1 */ - <960000 965000 975000>; /* Supply 2 */ + opp-microvolt = <975000 970000 985000>, /* Supply 0 */ + <965000 960000 975000>, /* Supply 1 */ + <965000 960000 975000>; /* Supply 2 */ opp-microamp = <70000>, /* Supply 0 */ <0>, /* Supply 1 doesn't need this */ <70000>; /* Supply 2 */ @@ -474,7 +474,7 @@ Example 5: opp-supported-hw */ opp-supported-hw = <0xF 0xFFFFFFFF 0xFFFFFFFF> opp-hz = /bits/ 64 <600000000>; - opp-microvolt = <900000 915000 925000>; + opp-microvolt = <915000 900000 925000>; ... }; @@ -487,7 +487,7 @@ Example 5: opp-supported-hw */ opp-supported-hw = <0x20 0xff0000ff 0x0000f4f0> opp-hz = /bits/ 64 <800000000>; - opp-microvolt = <900000 915000 925000>; + opp-microvolt = <915000 900000 925000>; ... }; }; @@ -512,18 +512,18 @@ Example 6: opp-microvolt-<name>, opp-microamp-<name>: opp@1000000000 { opp-hz = /bits/ 64 <1000000000>; - opp-microvolt-slow = <900000 915000 925000>; - opp-microvolt-fast = <970000 975000 985000>; + opp-microvolt-slow = <915000 900000 925000>; + opp-microvolt-fast = <975000 970000 985000>; opp-microamp-slow = <70000>; opp-microamp-fast = <71000>; }; opp@1200000000 { opp-hz = /bits/ 64 <1200000000>; - opp-microvolt-slow = <900000 915000 925000>, /* Supply vcc0 */ - <910000 925000 935000>; /* Supply vcc1 */ - opp-microvolt-fast = <970000 975000 985000>, /* Supply vcc0 */ - <960000 965000 975000>; /* Supply vcc1 */ + opp-microvolt-slow = <915000 900000 925000>, /* Supply vcc0 */ + <925000 910000 935000>; /* Supply vcc1 */ + opp-microvolt-fast = <975000 970000 985000>, /* Supply vcc0 */ + <965000 960000 975000>; /* Supply vcc1 */ opp-microamp = <70000>; /* Will be used for both slow/fast */ }; }; diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt index 129f7c0e1483..21d2d48f87a2 100644 --- a/Documentation/power/pm_qos_interface.txt +++ b/Documentation/power/pm_qos_interface.txt @@ -163,8 +163,7 @@ of flags and remove sysfs attributes pm_qos_no_power_off and pm_qos_remote_wakeu under the device's power directory. Notification mechanisms: -The per-device PM QoS framework has 2 different and distinct notification trees: -a per-device notification tree and a global notification tree. +The per-device PM QoS framework has a per-device notification tree. int dev_pm_qos_add_notifier(device, notifier): Adds a notification callback function for the device. @@ -174,16 +173,6 @@ is changed (for resume latency device PM QoS only). int dev_pm_qos_remove_notifier(device, notifier): Removes the notification callback function for the device. -int dev_pm_qos_add_global_notifier(notifier): -Adds a notification callback function in the global notification tree of the -framework. -The callback is called when the aggregated value for any device is changed -(for resume latency device PM QoS only). - -int dev_pm_qos_remove_global_notifier(notifier): -Removes the notification callback function from the global notification tree -of the framework. - Active state latency tolerance diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 4870980e967e..64546eb9a16a 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -100,7 +100,7 @@ knows what to do to handle the device). * If the suspend callback returns an error code different from -EBUSY and -EAGAIN, the PM core regards this as a fatal error and will refuse to run the helper functions described in Section 4 for the device until its status - is directly set to either'active', or 'suspended' (the PM core provides + is directly set to either 'active', or 'suspended' (the PM core provides special helper functions for this purpose). In particular, if the driver requires remote wakeup capability (i.e. hardware @@ -217,7 +217,7 @@ defined in include/linux/pm.h: one to complete spinlock_t lock; - - lock used for synchronisation + - lock used for synchronization atomic_t usage_count; - the usage counter of the device @@ -565,7 +565,7 @@ appropriate to ensure that the device is not put back to sleep during the probe. This can happen with systems such as the network device layer. It may be desirable to suspend the device once ->probe() has finished. -Therefore the driver core uses the asyncronous pm_request_idle() to submit a +Therefore the driver core uses the asynchronous pm_request_idle() to submit a request to execute the subsystem-level idle callback for the device at that time. A driver that makes use of the runtime autosuspend feature, may want to update the last busy mark before returning from ->probe(). diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt index 3849814bfe6d..0e03baf271bd 100644 --- a/Documentation/security/keys.txt +++ b/Documentation/security/keys.txt @@ -1151,8 +1151,21 @@ access the data: usage. This is called key->payload.rcu_data0. The following accessors wrap the RCU calls to this element: - rcu_assign_keypointer(struct key *key, void *data); - void *rcu_dereference_key(struct key *key); + (a) Set or change the first payload pointer: + + rcu_assign_keypointer(struct key *key, void *data); + + (b) Read the first payload pointer with the key semaphore held: + + [const] void *dereference_key_locked([const] struct key *key); + + Note that the return value will inherit its constness from the key + parameter. Static analysis will give an error if it things the lock + isn't held. + + (c) Read the first payload pointer with the RCU read lock held: + + const void *dereference_key_rcu(const struct key *key); =================== diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 8167fdb67ae8..9814db42b790 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -59,6 +59,7 @@ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ #define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C +#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 00293a94ffaf..d8b5f8ab8ef9 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -46,7 +46,7 @@ #define MSR_FSB_FREQ 0x000000cd #define MSR_PLATFORM_INFO 0x000000ce -#define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 +#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) #define NHM_C1_AUTO_DEMOTE (1UL << 26) #define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25) @@ -147,6 +147,7 @@ /* C-state Residency Counters */ #define MSR_PKG_C3_RESIDENCY 0x000003f8 #define MSR_PKG_C6_RESIDENCY 0x000003f9 +#define MSR_ATOM_PKG_C6_RESIDENCY 0x000003fa #define MSR_PKG_C7_RESIDENCY 0x000003fa #define MSR_CORE_C3_RESIDENCY 0x000003fc #define MSR_CORE_C6_RESIDENCY 0x000003fd @@ -203,10 +204,17 @@ #define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B #define MSR_CORE_C1_RES 0x00000660 +#define MSR_MODULE_C6_RES_MS 0x00000664 #define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 #define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669 +#define MSR_ATOM_CORE_RATIOS 0x0000066a +#define MSR_ATOM_CORE_VIDS 0x0000066b +#define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c +#define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d + + #define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 @@ -459,6 +467,7 @@ #define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 #define MSR_MISC_PWR_MGMT 0x000001aa #define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 diff --git a/block/Kconfig b/block/Kconfig index a2a92e57a87d..e9f780f815f5 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -189,4 +189,9 @@ config BLK_MQ_PCI depends on BLOCK && PCI default y +config BLK_MQ_VIRTIO + bool + depends on BLOCK && VIRTIO + default y + source block/Kconfig.iosched diff --git a/block/Makefile b/block/Makefile index 2ad7c304e3f5..081bb680789b 100644 --- a/block/Makefile +++ b/block/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o +obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o obj-$(CONFIG_BLK_WBT) += blk-wbt.o obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c new file mode 100644 index 000000000000..c3afbca11299 --- /dev/null +++ b/block/blk-mq-virtio.c @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2016 Christoph Hellwig. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + */ +#include <linux/device.h> +#include <linux/blk-mq.h> +#include <linux/blk-mq-virtio.h> +#include <linux/virtio_config.h> +#include <linux/module.h> +#include "blk-mq.h" + +/** + * blk_mq_virtio_map_queues - provide a default queue mapping for virtio device + * @set: tagset to provide the mapping for + * @vdev: virtio device associated with @set. + * @first_vec: first interrupt vectors to use for queues (usually 0) + * + * This function assumes the virtio device @vdev has at least as many available + * interrupt vetors as @set has queues. It will then queuery the vector + * corresponding to each queue for it's affinity mask and built queue mapping + * that maps a queue to the CPUs that have irq affinity for the corresponding + * vector. + */ +int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set, + struct virtio_device *vdev, int first_vec) +{ + const struct cpumask *mask; + unsigned int queue, cpu; + + if (!vdev->config->get_vq_affinity) + goto fallback; + + for (queue = 0; queue < set->nr_hw_queues; queue++) { + mask = vdev->config->get_vq_affinity(vdev, first_vec + queue); + if (!mask) + goto fallback; + + for_each_cpu(cpu, mask) + set->mq_map[cpu] = queue; + } + + return 0; +fallback: + return blk_mq_map_queues(set); +} +EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues); diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index a05b5c0cf181..12771fcf0417 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -97,6 +97,7 @@ static int __init bert_check_table(struct acpi_table_bert *bert_tab) static int __init bert_init(void) { + struct apei_resources bert_resources; struct acpi_bert_region *boot_error_region; struct acpi_table_bert *bert_tab; unsigned int region_len; @@ -127,13 +128,14 @@ static int __init bert_init(void) } region_len = bert_tab->region_length; - if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) { - pr_err("Can't request iomem region <%016llx-%016llx>.\n", - (unsigned long long)bert_tab->address, - (unsigned long long)bert_tab->address + region_len - 1); - return -EIO; - } - + apei_resources_init(&bert_resources); + rc = apei_resources_add(&bert_resources, bert_tab->address, + region_len, true); + if (rc) + return rc; + rc = apei_resources_request(&bert_resources, "APEI BERT"); + if (rc) + goto out_fini; boot_error_region = ioremap_cache(bert_tab->address, region_len); if (boot_error_region) { bert_print_all(boot_error_region, region_len); @@ -142,7 +144,9 @@ static int __init bert_init(void) rc = -ENOMEM; } - release_mem_region(bert_tab->address, region_len); + apei_resources_release(&bert_resources); +out_fini: + apei_resources_fini(&bert_resources); return rc; } diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 3a75fb1b4126..e697dec9d25b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -274,6 +274,93 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) } /** + * genpd_power_off - Remove power from a given PM domain. + * @genpd: PM domain to power down. + * @one_dev_on: If invoked from genpd's ->runtime_suspend|resume() callback, the + * RPM status of the releated device is in an intermediate state, not yet turned + * into RPM_SUSPENDED. This means genpd_power_off() must allow one device to not + * be RPM_SUSPENDED, while it tries to power off the PM domain. + * + * If all of the @genpd's devices have been suspended and all of its subdomains + * have been powered down, remove power from @genpd. + */ +static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on, + unsigned int depth) +{ + struct pm_domain_data *pdd; + struct gpd_link *link; + unsigned int not_suspended = 0; + + /* + * Do not try to power off the domain in the following situations: + * (1) The domain is already in the "power off" state. + * (2) System suspend is in progress. + */ + if (genpd->status == GPD_STATE_POWER_OFF + || genpd->prepared_count > 0) + return 0; + + if (atomic_read(&genpd->sd_count) > 0) + return -EBUSY; + + list_for_each_entry(pdd, &genpd->dev_list, list_node) { + enum pm_qos_flags_status stat; + + stat = dev_pm_qos_flags(pdd->dev, + PM_QOS_FLAG_NO_POWER_OFF + | PM_QOS_FLAG_REMOTE_WAKEUP); + if (stat > PM_QOS_FLAGS_NONE) + return -EBUSY; + + /* + * Do not allow PM domain to be powered off, when an IRQ safe + * device is part of a non-IRQ safe domain. + */ + if (!pm_runtime_suspended(pdd->dev) || + irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) + not_suspended++; + } + + if (not_suspended > 1 || (not_suspended == 1 && !one_dev_on)) + return -EBUSY; + + if (genpd->gov && genpd->gov->power_down_ok) { + if (!genpd->gov->power_down_ok(&genpd->domain)) + return -EAGAIN; + } + + if (genpd->power_off) { + int ret; + + if (atomic_read(&genpd->sd_count) > 0) + return -EBUSY; + + /* + * If sd_count > 0 at this point, one of the subdomains hasn't + * managed to call genpd_power_on() for the master yet after + * incrementing it. In that case genpd_power_on() will wait + * for us to drop the lock, so we can call .power_off() and let + * the genpd_power_on() restore power for us (this shouldn't + * happen very often). + */ + ret = _genpd_power_off(genpd, true); + if (ret) + return ret; + } + + genpd->status = GPD_STATE_POWER_OFF; + + list_for_each_entry(link, &genpd->slave_links, slave_node) { + genpd_sd_counter_dec(link->master); + genpd_lock_nested(link->master, depth + 1); + genpd_power_off(link->master, false, depth + 1); + genpd_unlock(link->master); + } + + return 0; +} + +/** * genpd_power_on - Restore power to a given PM domain and its masters. * @genpd: PM domain to power up. * @depth: nesting count for lockdep. @@ -321,7 +408,9 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth) &genpd->slave_links, slave_node) { genpd_sd_counter_dec(link->master); - genpd_queue_power_off_work(link->master); + genpd_lock_nested(link->master, depth + 1); + genpd_power_off(link->master, false, depth + 1); + genpd_unlock(link->master); } return ret; @@ -368,87 +457,6 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, } /** - * genpd_power_off - Remove power from a given PM domain. - * @genpd: PM domain to power down. - * @is_async: PM domain is powered down from a scheduled work - * - * If all of the @genpd's devices have been suspended and all of its subdomains - * have been powered down, remove power from @genpd. - */ -static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async) -{ - struct pm_domain_data *pdd; - struct gpd_link *link; - unsigned int not_suspended = 0; - - /* - * Do not try to power off the domain in the following situations: - * (1) The domain is already in the "power off" state. - * (2) System suspend is in progress. - */ - if (genpd->status == GPD_STATE_POWER_OFF - || genpd->prepared_count > 0) - return 0; - - if (atomic_read(&genpd->sd_count) > 0) - return -EBUSY; - - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - enum pm_qos_flags_status stat; - - stat = dev_pm_qos_flags(pdd->dev, - PM_QOS_FLAG_NO_POWER_OFF - | PM_QOS_FLAG_REMOTE_WAKEUP); - if (stat > PM_QOS_FLAGS_NONE) - return -EBUSY; - - /* - * Do not allow PM domain to be powered off, when an IRQ safe - * device is part of a non-IRQ safe domain. - */ - if (!pm_runtime_suspended(pdd->dev) || - irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd)) - not_suspended++; - } - - if (not_suspended > 1 || (not_suspended == 1 && is_async)) - return -EBUSY; - - if (genpd->gov && genpd->gov->power_down_ok) { - if (!genpd->gov->power_down_ok(&genpd->domain)) - return -EAGAIN; - } - - if (genpd->power_off) { - int ret; - - if (atomic_read(&genpd->sd_count) > 0) - return -EBUSY; - - /* - * If sd_count > 0 at this point, one of the subdomains hasn't - * managed to call genpd_power_on() for the master yet after - * incrementing it. In that case genpd_power_on() will wait - * for us to drop the lock, so we can call .power_off() and let - * the genpd_power_on() restore power for us (this shouldn't - * happen very often). - */ - ret = _genpd_power_off(genpd, true); - if (ret) - return ret; - } - - genpd->status = GPD_STATE_POWER_OFF; - - list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_dec(link->master); - genpd_queue_power_off_work(link->master); - } - - return 0; -} - -/** * genpd_power_off_work_fn - Power off PM domain whose subdomain count is 0. * @work: Work structure used for scheduling the execution of this function. */ @@ -459,7 +467,7 @@ static void genpd_power_off_work_fn(struct work_struct *work) genpd = container_of(work, struct generic_pm_domain, power_off_work); genpd_lock(genpd); - genpd_power_off(genpd, true); + genpd_power_off(genpd, false, 0); genpd_unlock(genpd); } @@ -578,7 +586,7 @@ static int genpd_runtime_suspend(struct device *dev) return 0; genpd_lock(genpd); - genpd_power_off(genpd, false); + genpd_power_off(genpd, true, 0); genpd_unlock(genpd); return 0; @@ -658,7 +666,7 @@ err_poweroff: if (!pm_runtime_is_irq_safe(dev) || (pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) { genpd_lock(genpd); - genpd_power_off(genpd, 0); + genpd_power_off(genpd, true, 0); genpd_unlock(genpd); } diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 91ec3232d630..dae61720b314 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -231,7 +231,8 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) * The caller needs to ensure that opp_table (and hence the regulator) * isn't freed, while we are executing this routine. */ - for (i = 0; reg = regulators[i], i < count; i++) { + for (i = 0; i < count; i++) { + reg = regulators[i]; ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max); if (ret > 0) latency_ns += ret * 1000; diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index d888d9869b6a..f850daeffba4 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -17,12 +17,9 @@ * * This QoS design is best effort based. Dependents register their QoS needs. * Watchers register to keep track of the current QoS needs of the system. - * Watchers can register different types of notification callbacks: - * . a per-device notification callback using the dev_pm_qos_*_notifier API. - * The notification chain data is stored in the per-device constraint - * data struct. - * . a system-wide notification callback using the dev_pm_qos_*_global_notifier - * API. The notification chain data is stored in a static variable. + * Watchers can register a per-device notification callback using the + * dev_pm_qos_*_notifier API. The notification chain data is stored in the + * per-device constraint data struct. * * Note about the per-device constraint data struct allocation: * . The per-device constraints data struct ptr is tored into the device @@ -49,8 +46,6 @@ static DEFINE_MUTEX(dev_pm_qos_mtx); static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx); -static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers); - /** * __dev_pm_qos_flags - Check PM QoS flags for a given device. * @dev: Device to check the PM QoS flags for. @@ -108,8 +103,7 @@ s32 __dev_pm_qos_read_value(struct device *dev) { lockdep_assert_held(&dev->power.lock); - return IS_ERR_OR_NULL(dev->power.qos) ? - 0 : pm_qos_read_value(&dev->power.qos->resume_latency); + return dev_pm_qos_raw_read_value(dev); } /** @@ -135,8 +129,7 @@ s32 dev_pm_qos_read_value(struct device *dev) * @value: Value to assign to the QoS request. * * Internal function to update the constraints list using the PM QoS core - * code and if needed call the per-device and the global notification - * callbacks + * code and if needed call the per-device callbacks. */ static int apply_constraint(struct dev_pm_qos_request *req, enum pm_qos_req_action action, s32 value) @@ -148,12 +141,6 @@ static int apply_constraint(struct dev_pm_qos_request *req, case DEV_PM_QOS_RESUME_LATENCY: ret = pm_qos_update_target(&qos->resume_latency, &req->data.pnode, action, value); - if (ret) { - value = pm_qos_read_value(&qos->resume_latency); - blocking_notifier_call_chain(&dev_pm_notifiers, - (unsigned long)value, - req); - } break; case DEV_PM_QOS_LATENCY_TOLERANCE: ret = pm_qos_update_target(&qos->latency_tolerance, @@ -536,36 +523,6 @@ int dev_pm_qos_remove_notifier(struct device *dev, EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier); /** - * dev_pm_qos_add_global_notifier - sets notification entry for changes to - * target value of the PM QoS constraints for any device - * - * @notifier: notifier block managed by caller. - * - * Will register the notifier into a notification chain that gets called - * upon changes to the target value for any device. - */ -int dev_pm_qos_add_global_notifier(struct notifier_block *notifier) -{ - return blocking_notifier_chain_register(&dev_pm_notifiers, notifier); -} -EXPORT_SYMBOL_GPL(dev_pm_qos_add_global_notifier); - -/** - * dev_pm_qos_remove_global_notifier - deletes notification for changes to - * target value of PM QoS constraints for any device - * - * @notifier: notifier block to be removed. - * - * Will remove the notifier from the notification chain that gets called - * upon changes to the target value for any device. - */ -int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier) -{ - return blocking_notifier_chain_unregister(&dev_pm_notifiers, notifier); -} -EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier); - -/** * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor. * @dev: Device whose ancestor to add the request for. * @req: Pointer to the preallocated handle. diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index c7d530a95e53..92c60cbd04ee 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1847,7 +1847,7 @@ int drbd_send_out_of_sync(struct drbd_peer_device *peer_device, struct drbd_requ int drbd_send(struct drbd_connection *connection, struct socket *sock, void *buf, size_t size, unsigned msg_flags) { - struct kvec iov; + struct kvec iov = {.iov_base = buf, .iov_len = size}; struct msghdr msg; int rv, sent = 0; @@ -1856,15 +1856,14 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, /* THINK if (signal_pending) return ... ? */ - iov.iov_base = buf; - iov.iov_len = size; - msg.msg_name = NULL; msg.msg_namelen = 0; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = msg_flags | MSG_NOSIGNAL; + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + if (sock == connection->data.socket) { rcu_read_lock(); connection->ko_count = rcu_dereference(connection->net_conf)->ko_count; @@ -1872,7 +1871,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, drbd_update_congested(connection); } do { - rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len); + rv = sock_sendmsg(sock, &msg); if (rv == -EAGAIN) { if (we_should_drop_the_connection(connection, sock)) break; @@ -1886,8 +1885,6 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, if (rv < 0) break; sent += rv; - iov.iov_base += rv; - iov.iov_len -= rv; } while (sent < size); if (sock == connection->data.socket) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 4b52a1690329..eeb1db73f44e 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -501,9 +501,9 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, cmd->iocb.ki_flags = IOCB_DIRECT; if (rw == WRITE) - ret = file->f_op->write_iter(&cmd->iocb, &iter); + ret = call_write_iter(file, &cmd->iocb, &iter); else - ret = file->f_op->read_iter(&cmd->iocb, &iter); + ret = call_read_iter(file, &cmd->iocb, &iter); if (ret != -EIOCBQUEUED) cmd->iocb.ki_complete(&cmd->iocb, ret, 0); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 0bf2b21a62cb..1541cb880744 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -201,13 +201,12 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, /* * Send or receive packet. */ -static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf, - int size, int msg_flags) +static int sock_xmit(struct nbd_device *nbd, int index, int send, + struct iov_iter *iter, int msg_flags) { struct socket *sock = nbd->socks[index]->sock; int result; struct msghdr msg; - struct kvec iov; unsigned long pflags = current->flags; if (unlikely(!sock)) { @@ -217,11 +216,11 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf, return -EINVAL; } + msg.msg_iter = *iter; + current->flags |= PF_MEMALLOC; do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; - iov.iov_base = buf; - iov.iov_len = size; msg.msg_name = NULL; msg.msg_namelen = 0; msg.msg_control = NULL; @@ -229,47 +228,37 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, void *buf, msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) - result = kernel_sendmsg(sock, &msg, &iov, 1, size); + result = sock_sendmsg(sock, &msg); else - result = kernel_recvmsg(sock, &msg, &iov, 1, size, - msg.msg_flags); + result = sock_recvmsg(sock, &msg, msg.msg_flags); if (result <= 0) { if (result == 0) result = -EPIPE; /* short read */ break; } - size -= result; - buf += result; - } while (size > 0); + } while (msg_data_left(&msg)); tsk_restore_flags(current, pflags, PF_MEMALLOC); return result; } -static inline int sock_send_bvec(struct nbd_device *nbd, int index, - struct bio_vec *bvec, int flags) -{ - int result; - void *kaddr = kmap(bvec->bv_page); - result = sock_xmit(nbd, index, 1, kaddr + bvec->bv_offset, - bvec->bv_len, flags); - kunmap(bvec->bv_page); - return result; -} - /* always call with the tx_lock held */ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); int result; - struct nbd_request request; + struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)}; + struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; + struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; u32 type; u32 tag = blk_mq_unique_tag(req); + iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + switch (req_op(req)) { case REQ_OP_DISCARD: type = NBD_CMD_TRIM; @@ -294,8 +283,6 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return -EIO; } - memset(&request, 0, sizeof(request)); - request.magic = htonl(NBD_REQUEST_MAGIC); request.type = htonl(type); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); @@ -306,7 +293,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", cmd, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); - result = sock_xmit(nbd, index, 1, &request, sizeof(request), + result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0); if (result <= 0) { dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -329,7 +316,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", cmd, bvec.bv_len); - result = sock_send_bvec(nbd, index, &bvec, flags); + iov_iter_bvec(&from, ITER_BVEC | WRITE, + &bvec, 1, bvec.bv_len); + result = sock_xmit(nbd, index, 1, &from, flags); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -350,17 +339,6 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return 0; } -static inline int sock_recv_bvec(struct nbd_device *nbd, int index, - struct bio_vec *bvec) -{ - int result; - void *kaddr = kmap(bvec->bv_page); - result = sock_xmit(nbd, index, 0, kaddr + bvec->bv_offset, - bvec->bv_len, MSG_WAITALL); - kunmap(bvec->bv_page); - return result; -} - /* NULL returned = something went wrong, inform userspace */ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) { @@ -370,9 +348,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct request *req = NULL; u16 hwq; u32 tag; + struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; + struct iov_iter to; reply.magic = 0; - result = sock_xmit(nbd, index, 0, &reply, sizeof(reply), MSG_WAITALL); + iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); + result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL); if (result <= 0) { if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags)) @@ -412,7 +393,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { - result = sock_recv_bvec(nbd, index, &bvec); + iov_iter_bvec(&to, ITER_BVEC | READ, + &bvec, 1, bvec.bv_len); + result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", result); @@ -641,14 +624,17 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev) static void send_disconnects(struct nbd_device *nbd) { - struct nbd_request request = {}; + struct nbd_request request = { + .magic = htonl(NBD_REQUEST_MAGIC), + .type = htonl(NBD_CMD_DISC), + }; + struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; + struct iov_iter from; int i, ret; - request.magic = htonl(NBD_REQUEST_MAGIC); - request.type = htonl(NBD_CMD_DISC); - for (i = 0; i < nbd->num_connections; i++) { - ret = sock_xmit(nbd, i, 1, &request, sizeof(request), 0); + iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + ret = sock_xmit(nbd, i, 1, &from, 0); if (ret <= 0) dev_err(disk_to_dev(nbd->disk), "Send disconnect failed %d\n", ret); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 024b473524c0..1d4c9f8bc1e1 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -5,6 +5,7 @@ #include <linux/hdreg.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/interrupt.h> #include <linux/virtio.h> #include <linux/virtio_blk.h> #include <linux/scatterlist.h> @@ -12,6 +13,7 @@ #include <scsi/scsi_cmnd.h> #include <linux/idr.h> #include <linux/blk-mq.h> +#include <linux/blk-mq-virtio.h> #include <linux/numa.h> #define PART_BITS 4 @@ -426,6 +428,7 @@ static int init_vq(struct virtio_blk *vblk) struct virtqueue **vqs; unsigned short num_vqs; struct virtio_device *vdev = vblk->vdev; + struct irq_affinity desc = { 0, }; err = virtio_cread_feature(vdev, VIRTIO_BLK_F_MQ, struct virtio_blk_config, num_queues, @@ -452,7 +455,8 @@ static int init_vq(struct virtio_blk *vblk) } /* Discover virtqueues and write information to configuration. */ - err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names); + err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names, + &desc); if (err) goto out; @@ -586,10 +590,18 @@ static int virtblk_init_request(void *data, struct request *rq, return 0; } +static int virtblk_map_queues(struct blk_mq_tag_set *set) +{ + struct virtio_blk *vblk = set->driver_data; + + return blk_mq_virtio_map_queues(set, vblk->vdev, 0); +} + static struct blk_mq_ops virtio_mq_ops = { .queue_rq = virtio_queue_rq, .complete = virtblk_request_done, .init_request = virtblk_init_request, + .map_queues = virtblk_map_queues, }; static unsigned int virtblk_queue_depth; diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 17857beb4892..e9b7e0b3cabe 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1136,6 +1136,8 @@ static int put_chars(u32 vtermno, const char *buf, int count) { struct port *port; struct scatterlist sg[1]; + void *data; + int ret; if (unlikely(early_put_chars)) return early_put_chars(vtermno, buf, count); @@ -1144,8 +1146,14 @@ static int put_chars(u32 vtermno, const char *buf, int count) if (!port) return -EPIPE; - sg_init_one(sg, buf, count); - return __send_to_port(port, sg, 1, count, (void *)buf, false); + data = kmemdup(buf, count, GFP_ATOMIC); + if (!data) + return -ENOMEM; + + sg_init_one(sg, data, count); + ret = __send_to_port(port, sg, 1, count, data, false); + kfree(data); + return ret; } /* @@ -1939,7 +1947,7 @@ static int init_vqs(struct ports_device *portdev) /* Find the queues. */ err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs, io_callbacks, - (const char **)io_names); + (const char **)io_names, NULL); if (err) goto free; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 8f6d29302aac..b1fbaa30ae04 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -39,11 +39,6 @@ #define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 -#define ATOM_RATIOS 0x66a -#define ATOM_VIDS 0x66b -#define ATOM_TURBO_RATIOS 0x66c -#define ATOM_TURBO_VIDS 0x66d - #ifdef CONFIG_ACPI #include <acpi/processor.h> #include <acpi/cppc_acpi.h> @@ -364,37 +359,25 @@ static bool driver_registered __read_mostly; static bool acpi_ppc; #endif -static struct perf_limits performance_limits = { - .no_turbo = 0, - .turbo_disabled = 0, - .max_perf_pct = 100, - .max_perf = int_ext_tofp(1), - .min_perf_pct = 100, - .min_perf = int_ext_tofp(1), - .max_policy_pct = 100, - .max_sysfs_pct = 100, - .min_policy_pct = 0, - .min_sysfs_pct = 0, -}; +static struct perf_limits performance_limits; +static struct perf_limits powersave_limits; +static struct perf_limits *limits; -static struct perf_limits powersave_limits = { - .no_turbo = 0, - .turbo_disabled = 0, - .max_perf_pct = 100, - .max_perf = int_ext_tofp(1), - .min_perf_pct = 0, - .min_perf = 0, - .max_policy_pct = 100, - .max_sysfs_pct = 100, - .min_policy_pct = 0, - .min_sysfs_pct = 0, -}; +static void intel_pstate_init_limits(struct perf_limits *limits) +{ + memset(limits, 0, sizeof(*limits)); + limits->max_perf_pct = 100; + limits->max_perf = int_ext_tofp(1); + limits->max_policy_pct = 100; + limits->max_sysfs_pct = 100; +} -#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE -static struct perf_limits *limits = &performance_limits; -#else -static struct perf_limits *limits = &powersave_limits; -#endif +static void intel_pstate_set_performance_limits(struct perf_limits *limits) +{ + intel_pstate_init_limits(limits); + limits->min_perf_pct = 100; + limits->min_perf = int_ext_tofp(1); +} static DEFINE_MUTEX(intel_pstate_driver_lock); static DEFINE_MUTEX(intel_pstate_limits_lock); @@ -1367,7 +1350,7 @@ static int atom_get_min_pstate(void) { u64 value; - rdmsrl(ATOM_RATIOS, value); + rdmsrl(MSR_ATOM_CORE_RATIOS, value); return (value >> 8) & 0x7F; } @@ -1375,7 +1358,7 @@ static int atom_get_max_pstate(void) { u64 value; - rdmsrl(ATOM_RATIOS, value); + rdmsrl(MSR_ATOM_CORE_RATIOS, value); return (value >> 16) & 0x7F; } @@ -1383,7 +1366,7 @@ static int atom_get_turbo_pstate(void) { u64 value; - rdmsrl(ATOM_TURBO_RATIOS, value); + rdmsrl(MSR_ATOM_CORE_TURBO_RATIOS, value); return value & 0x7F; } @@ -1445,7 +1428,7 @@ static void atom_get_vid(struct cpudata *cpudata) { u64 value; - rdmsrl(ATOM_VIDS, value); + rdmsrl(MSR_ATOM_CORE_VIDS, value); cpudata->vid.min = int_tofp((value >> 8) & 0x7f); cpudata->vid.max = int_tofp((value >> 16) & 0x7f); cpudata->vid.ratio = div_fp( @@ -1453,7 +1436,7 @@ static void atom_get_vid(struct cpudata *cpudata) int_tofp(cpudata->pstate.max_pstate - cpudata->pstate.min_pstate)); - rdmsrl(ATOM_TURBO_VIDS, value); + rdmsrl(MSR_ATOM_CORE_TURBO_VIDS, value); cpudata->vid.turbo = value & 0x7f; } @@ -2084,20 +2067,6 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu) synchronize_sched(); } -static void intel_pstate_set_performance_limits(struct perf_limits *limits) -{ - limits->no_turbo = 0; - limits->turbo_disabled = 0; - limits->max_perf_pct = 100; - limits->max_perf = int_ext_tofp(1); - limits->min_perf_pct = 100; - limits->min_perf = int_ext_tofp(1); - limits->max_policy_pct = 100; - limits->max_sysfs_pct = 100; - limits->min_policy_pct = 0; - limits->min_sysfs_pct = 0; -} - static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, struct perf_limits *limits) { @@ -2466,6 +2435,11 @@ static int intel_pstate_register_driver(void) { int ret; + intel_pstate_init_limits(&powersave_limits); + intel_pstate_set_performance_limits(&performance_limits); + limits = IS_ENABLED(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE) ? + &performance_limits : &powersave_limits; + ret = cpufreq_register_driver(intel_pstate_driver); if (ret) { intel_pstate_driver_cleanup(); diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index a6fefac8afe4..bfec1bcd3835 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -23,10 +23,6 @@ #include <linux/slab.h> #include <linux/smp.h> -#if !defined(CONFIG_ARM) -#include <asm/smp.h> /* for get_hard_smp_processor_id() in UP configs */ -#endif - /** * struct cpu_data * @pclk: the parent clock of cpu diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 6d8a4026a903..b2330fd69e34 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -289,7 +289,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) unsigned int interactivity_req; unsigned int expected_interval; unsigned long nr_iowaiters, cpu_load; - int resume_latency = dev_pm_qos_read_value(device); + int resume_latency = dev_pm_qos_raw_read_value(device); if (data->needs_update) { menu_update(drv, dev); diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index b5b153317376..21472e427f6f 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -120,7 +120,7 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi) } ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks, - names); + names, NULL); if (ret) goto err_find; diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index d037adcda6f2..29bb8011dbc4 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -141,7 +141,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct * if (!obj->base.filp) return -ENODEV; - ret = obj->base.filp->f_op->mmap(obj->base.filp, vma); + ret = call_mmap(obj->base.filp, vma); if (ret) return ret; diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index 7ccbb03e98de..a1f42d125e6e 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -288,7 +288,7 @@ static int vgem_prime_mmap(struct drm_gem_object *obj, if (!obj->filp) return -ENODEV; - ret = obj->filp->f_op->mmap(obj->filp, vma); + ret = call_mmap(obj->filp, vma); if (ret) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 30f989a0cafc..491866865c33 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -176,7 +176,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) #endif ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs, - callbacks, names); + callbacks, names, NULL); if (ret) { DRM_ERROR("failed to find virt queues\n"); goto err_vqs; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 7d8ea3d5fda6..5805b041dd0f 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -125,7 +125,7 @@ static struct cpuidle_state *cpuidle_state_table; */ static struct cpuidle_state nehalem_cstates[] = { { - .name = "C1-NHM", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 3, @@ -133,7 +133,7 @@ static struct cpuidle_state nehalem_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-NHM", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -141,7 +141,7 @@ static struct cpuidle_state nehalem_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-NHM", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 20, @@ -149,7 +149,7 @@ static struct cpuidle_state nehalem_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-NHM", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 200, @@ -162,7 +162,7 @@ static struct cpuidle_state nehalem_cstates[] = { static struct cpuidle_state snb_cstates[] = { { - .name = "C1-SNB", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -170,7 +170,7 @@ static struct cpuidle_state snb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-SNB", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -178,7 +178,7 @@ static struct cpuidle_state snb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-SNB", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 80, @@ -186,7 +186,7 @@ static struct cpuidle_state snb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-SNB", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 104, @@ -194,7 +194,7 @@ static struct cpuidle_state snb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7-SNB", + .name = "C7", .desc = "MWAIT 0x30", .flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 109, @@ -207,7 +207,7 @@ static struct cpuidle_state snb_cstates[] = { static struct cpuidle_state byt_cstates[] = { { - .name = "C1-BYT", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -215,7 +215,7 @@ static struct cpuidle_state byt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6N-BYT", + .name = "C6N", .desc = "MWAIT 0x58", .flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 300, @@ -223,7 +223,7 @@ static struct cpuidle_state byt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6S-BYT", + .name = "C6S", .desc = "MWAIT 0x52", .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 500, @@ -231,7 +231,7 @@ static struct cpuidle_state byt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7-BYT", + .name = "C7", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 1200, @@ -239,7 +239,7 @@ static struct cpuidle_state byt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7S-BYT", + .name = "C7S", .desc = "MWAIT 0x64", .flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 10000, @@ -252,7 +252,7 @@ static struct cpuidle_state byt_cstates[] = { static struct cpuidle_state cht_cstates[] = { { - .name = "C1-CHT", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -260,7 +260,7 @@ static struct cpuidle_state cht_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6N-CHT", + .name = "C6N", .desc = "MWAIT 0x58", .flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 80, @@ -268,7 +268,7 @@ static struct cpuidle_state cht_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6S-CHT", + .name = "C6S", .desc = "MWAIT 0x52", .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 200, @@ -276,7 +276,7 @@ static struct cpuidle_state cht_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7-CHT", + .name = "C7", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 1200, @@ -284,7 +284,7 @@ static struct cpuidle_state cht_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7S-CHT", + .name = "C7S", .desc = "MWAIT 0x64", .flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 10000, @@ -297,7 +297,7 @@ static struct cpuidle_state cht_cstates[] = { static struct cpuidle_state ivb_cstates[] = { { - .name = "C1-IVB", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -305,7 +305,7 @@ static struct cpuidle_state ivb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-IVB", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -313,7 +313,7 @@ static struct cpuidle_state ivb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-IVB", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 59, @@ -321,7 +321,7 @@ static struct cpuidle_state ivb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-IVB", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 80, @@ -329,7 +329,7 @@ static struct cpuidle_state ivb_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7-IVB", + .name = "C7", .desc = "MWAIT 0x30", .flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 87, @@ -342,7 +342,7 @@ static struct cpuidle_state ivb_cstates[] = { static struct cpuidle_state ivt_cstates[] = { { - .name = "C1-IVT", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -350,7 +350,7 @@ static struct cpuidle_state ivt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-IVT", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -358,7 +358,7 @@ static struct cpuidle_state ivt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-IVT", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 59, @@ -366,7 +366,7 @@ static struct cpuidle_state ivt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-IVT", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 82, @@ -379,7 +379,7 @@ static struct cpuidle_state ivt_cstates[] = { static struct cpuidle_state ivt_cstates_4s[] = { { - .name = "C1-IVT-4S", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -387,7 +387,7 @@ static struct cpuidle_state ivt_cstates_4s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-IVT-4S", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -395,7 +395,7 @@ static struct cpuidle_state ivt_cstates_4s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-IVT-4S", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 59, @@ -403,7 +403,7 @@ static struct cpuidle_state ivt_cstates_4s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-IVT-4S", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 84, @@ -416,7 +416,7 @@ static struct cpuidle_state ivt_cstates_4s[] = { static struct cpuidle_state ivt_cstates_8s[] = { { - .name = "C1-IVT-8S", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -424,7 +424,7 @@ static struct cpuidle_state ivt_cstates_8s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-IVT-8S", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -432,7 +432,7 @@ static struct cpuidle_state ivt_cstates_8s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-IVT-8S", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 59, @@ -440,7 +440,7 @@ static struct cpuidle_state ivt_cstates_8s[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-IVT-8S", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 88, @@ -453,7 +453,7 @@ static struct cpuidle_state ivt_cstates_8s[] = { static struct cpuidle_state hsw_cstates[] = { { - .name = "C1-HSW", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -461,7 +461,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-HSW", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -469,7 +469,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-HSW", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 33, @@ -477,7 +477,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-HSW", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 133, @@ -485,7 +485,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7s-HSW", + .name = "C7s", .desc = "MWAIT 0x32", .flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 166, @@ -493,7 +493,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C8-HSW", + .name = "C8", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 300, @@ -501,7 +501,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C9-HSW", + .name = "C9", .desc = "MWAIT 0x50", .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 600, @@ -509,7 +509,7 @@ static struct cpuidle_state hsw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C10-HSW", + .name = "C10", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 2600, @@ -521,7 +521,7 @@ static struct cpuidle_state hsw_cstates[] = { }; static struct cpuidle_state bdw_cstates[] = { { - .name = "C1-BDW", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -529,7 +529,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-BDW", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -537,7 +537,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-BDW", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 40, @@ -545,7 +545,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-BDW", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 133, @@ -553,7 +553,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7s-BDW", + .name = "C7s", .desc = "MWAIT 0x32", .flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 166, @@ -561,7 +561,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C8-BDW", + .name = "C8", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 300, @@ -569,7 +569,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C9-BDW", + .name = "C9", .desc = "MWAIT 0x50", .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 600, @@ -577,7 +577,7 @@ static struct cpuidle_state bdw_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C10-BDW", + .name = "C10", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 2600, @@ -590,7 +590,7 @@ static struct cpuidle_state bdw_cstates[] = { static struct cpuidle_state skl_cstates[] = { { - .name = "C1-SKL", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -598,7 +598,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-SKL", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -606,7 +606,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C3-SKL", + .name = "C3", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 70, @@ -614,7 +614,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-SKL", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 85, @@ -622,7 +622,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7s-SKL", + .name = "C7s", .desc = "MWAIT 0x33", .flags = MWAIT2flg(0x33) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 124, @@ -630,7 +630,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C8-SKL", + .name = "C8", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 200, @@ -638,7 +638,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C9-SKL", + .name = "C9", .desc = "MWAIT 0x50", .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 480, @@ -646,7 +646,7 @@ static struct cpuidle_state skl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C10-SKL", + .name = "C10", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 890, @@ -659,7 +659,7 @@ static struct cpuidle_state skl_cstates[] = { static struct cpuidle_state skx_cstates[] = { { - .name = "C1-SKX", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -667,7 +667,7 @@ static struct cpuidle_state skx_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-SKX", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -675,7 +675,7 @@ static struct cpuidle_state skx_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-SKX", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 133, @@ -688,7 +688,7 @@ static struct cpuidle_state skx_cstates[] = { static struct cpuidle_state atom_cstates[] = { { - .name = "C1E-ATM", + .name = "C1E", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 10, @@ -696,7 +696,7 @@ static struct cpuidle_state atom_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C2-ATM", + .name = "C2", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10), .exit_latency = 20, @@ -704,7 +704,7 @@ static struct cpuidle_state atom_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C4-ATM", + .name = "C4", .desc = "MWAIT 0x30", .flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 100, @@ -712,7 +712,7 @@ static struct cpuidle_state atom_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-ATM", + .name = "C6", .desc = "MWAIT 0x52", .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 140, @@ -724,7 +724,7 @@ static struct cpuidle_state atom_cstates[] = { }; static struct cpuidle_state tangier_cstates[] = { { - .name = "C1-TNG", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -732,7 +732,7 @@ static struct cpuidle_state tangier_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C4-TNG", + .name = "C4", .desc = "MWAIT 0x30", .flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 100, @@ -740,7 +740,7 @@ static struct cpuidle_state tangier_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-TNG", + .name = "C6", .desc = "MWAIT 0x52", .flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 140, @@ -748,7 +748,7 @@ static struct cpuidle_state tangier_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7-TNG", + .name = "C7", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 1200, @@ -756,7 +756,7 @@ static struct cpuidle_state tangier_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C9-TNG", + .name = "C9", .desc = "MWAIT 0x64", .flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 10000, @@ -768,7 +768,7 @@ static struct cpuidle_state tangier_cstates[] = { }; static struct cpuidle_state avn_cstates[] = { { - .name = "C1-AVN", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -776,7 +776,7 @@ static struct cpuidle_state avn_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-AVN", + .name = "C6", .desc = "MWAIT 0x51", .flags = MWAIT2flg(0x51) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 15, @@ -788,7 +788,7 @@ static struct cpuidle_state avn_cstates[] = { }; static struct cpuidle_state knl_cstates[] = { { - .name = "C1-KNL", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 1, @@ -796,7 +796,7 @@ static struct cpuidle_state knl_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze }, { - .name = "C6-KNL", + .name = "C6", .desc = "MWAIT 0x10", .flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 120, @@ -809,7 +809,7 @@ static struct cpuidle_state knl_cstates[] = { static struct cpuidle_state bxt_cstates[] = { { - .name = "C1-BXT", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -817,7 +817,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-BXT", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -825,7 +825,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-BXT", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 133, @@ -833,7 +833,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C7s-BXT", + .name = "C7s", .desc = "MWAIT 0x31", .flags = MWAIT2flg(0x31) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 155, @@ -841,7 +841,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C8-BXT", + .name = "C8", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 1000, @@ -849,7 +849,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C9-BXT", + .name = "C9", .desc = "MWAIT 0x50", .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 2000, @@ -857,7 +857,7 @@ static struct cpuidle_state bxt_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C10-BXT", + .name = "C10", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 10000, @@ -870,7 +870,7 @@ static struct cpuidle_state bxt_cstates[] = { static struct cpuidle_state dnv_cstates[] = { { - .name = "C1-DNV", + .name = "C1", .desc = "MWAIT 0x00", .flags = MWAIT2flg(0x00), .exit_latency = 2, @@ -878,7 +878,7 @@ static struct cpuidle_state dnv_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C1E-DNV", + .name = "C1E", .desc = "MWAIT 0x01", .flags = MWAIT2flg(0x01), .exit_latency = 10, @@ -886,7 +886,7 @@ static struct cpuidle_state dnv_cstates[] = { .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { - .name = "C6-DNV", + .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, .exit_latency = 50, @@ -961,9 +961,9 @@ static void auto_demotion_disable(void) { unsigned long long msr_bits; - rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits); + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits); msr_bits &= ~(icpu->auto_demotion_disable_flags); - wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits); + wrmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr_bits); } static void c1e_promotion_disable(void) { @@ -1273,7 +1273,7 @@ static void sklh_idle_state_table_update(void) if ((mwait_substates & (0xF << 28)) == 0) return; - rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr); + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr); /* PC10 is not enabled in PKG C-state limit */ if ((msr & 0xF) != 8) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 1cb2ca9dfae3..389a3637ffcc 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1536,7 +1536,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string down_read(&key->sem); - ukp = user_key_payload(key); + ukp = user_key_payload_locked(key); if (!ukp) { up_read(&key->sem); key_put(key); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5c9e95d66f3b..f8564d63982f 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -101,6 +101,8 @@ struct raid_dev { #define CTR_FLAG_RAID10_USE_NEAR_SETS (1 << __CTR_FLAG_RAID10_USE_NEAR_SETS) #define CTR_FLAG_JOURNAL_DEV (1 << __CTR_FLAG_JOURNAL_DEV) +#define RESUME_STAY_FROZEN_FLAGS (CTR_FLAG_DELTA_DISKS | CTR_FLAG_DATA_OFFSET) + /* * Definitions of various constructor flags to * be used in checks of valid / invalid flags @@ -3462,9 +3464,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv) else if (!strcasecmp(argv[0], "recover")) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); else { - if (!strcasecmp(argv[0], "check")) + if (!strcasecmp(argv[0], "check")) { set_bit(MD_RECOVERY_CHECK, &mddev->recovery); - else if (!strcasecmp(argv[0], "repair")) { + set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); + set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + } else if (!strcasecmp(argv[0], "repair")) { set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); } else @@ -3771,7 +3775,15 @@ static void raid_resume(struct dm_target *ti) mddev->ro = 0; mddev->in_sync = 0; - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + /* + * Keep the RAID set frozen if reshape/rebuild flags are set. + * The RAID set is unfrozen once the next table load/resume, + * which clears the reshape/rebuild flags, occurs. + * This ensures that the constructor for the inactive table + * retrieves an up-to-date reshape_position. + */ + if (!(rs->ctr_flags & RESUME_STAY_FROZEN_FLAGS)) + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (mddev->suspended) mddev_resume(mddev); @@ -3779,7 +3791,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 10, 0}, + .version = {1, 10, 1}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 1a2b67f3183d..c2e29d7f0de8 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -374,7 +374,7 @@ unmap: static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], struct irq_affinity *desc) { struct _vop_vdev *vdev = to_vopvdev(dev); struct vop_device *vpdev = vdev->vpdev; diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index b306210b02b7..bc0eb47eccee 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -679,7 +679,8 @@ static int cfv_probe(struct virtio_device *vdev) goto err; /* Get the TX virtio ring. This is a "guest side vring". */ - err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names); + err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names, + NULL); if (err) goto err; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 5043b64805f0..8098c93cd16e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -1364,6 +1364,10 @@ struct cpl_tx_data { #define TX_FORCE_S 13 #define TX_FORCE_V(x) ((x) << TX_FORCE_S) +#define T6_TX_FORCE_S 20 +#define T6_TX_FORCE_V(x) ((x) << T6_TX_FORCE_S) +#define T6_TX_FORCE_F T6_TX_FORCE_V(1U) + enum { ULP_TX_MEM_READ = 2, ULP_TX_MEM_WRITE = 3, diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h index e995a1a3840a..a91ad766cef0 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h @@ -59,7 +59,7 @@ struct cxgbi_pagepod_hdr { #define PPOD_PAGES_MAX 4 struct cxgbi_pagepod { struct cxgbi_pagepod_hdr hdr; - u64 addr[PPOD_PAGES_MAX + 1]; + __be64 addr[PPOD_PAGES_MAX + 1]; }; /* ddp tag format diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index bf95016f442a..66fd3139be60 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2080,7 +2080,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi) } ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks, - names); + names, NULL); if (ret) goto err_find; diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index 364411fb7734..0142cc3f0c91 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -137,7 +137,8 @@ static void rproc_virtio_del_vqs(struct virtio_device *vdev) static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], + struct irq_affinity *desc) { int i, ret; diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 3090b0d3072f..5e66e081027e 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -869,7 +869,7 @@ static int rpmsg_probe(struct virtio_device *vdev) init_waitqueue_head(&vrp->sendq); /* We expect two virtqueues, rx and tx (and in this order) */ - err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names); + err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names, NULL); if (err) goto free_vrp; diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c index 5e5c11f37b24..2ce0b3eb2efe 100644 --- a/drivers/s390/virtio/kvm_virtio.c +++ b/drivers/s390/virtio/kvm_virtio.c @@ -255,7 +255,8 @@ static void kvm_del_vqs(struct virtio_device *vdev) static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], + struct irq_affinity *desc) { struct kvm_device *kdev = to_kvmdev(vdev); int i; diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 648373cde4a1..0ed209f3d8b0 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -628,7 +628,8 @@ out: static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], + struct irq_affinity *desc) { struct virtio_ccw_device *vcdev = to_vc_device(vdev); unsigned long *indicatorp = NULL; diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index f201f4099620..f610103994af 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2163,6 +2163,9 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) clear_bit(vha->vp_idx, ha->vp_idx_map); mutex_unlock(&ha->vport_lock); + dma_free_coherent(&ha->pdev->dev, vha->gnl.size, vha->gnl.l, + vha->gnl.ldma); + if (vha->qpair->vp_idx == vha->vp_idx) { if (qla2xxx_delete_qpair(vha, vha->qpair) != QLA_SUCCESS) ql_log(ql_log_warn, vha, 0x7087, diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c index 40ca75bbcb9d..84c9098cc089 100644 --- a/drivers/scsi/qla2xxx/qla_bsg.c +++ b/drivers/scsi/qla2xxx/qla_bsg.c @@ -13,28 +13,25 @@ /* BSG support for ELS/CT pass through */ void -qla2x00_bsg_job_done(void *data, void *ptr, int res) +qla2x00_bsg_job_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; - struct scsi_qla_host *vha = (scsi_qla_host_t *)data; + srb_t *sp = ptr; struct bsg_job *bsg_job = sp->u.bsg_job; struct fc_bsg_reply *bsg_reply = bsg_job->reply; bsg_reply->result = res; bsg_job_done(bsg_job, bsg_reply->result, bsg_reply->reply_payload_rcv_len); - sp->free(vha, sp); + sp->free(sp); } void -qla2x00_bsg_sp_free(void *data, void *ptr) +qla2x00_bsg_sp_free(void *ptr) { - srb_t *sp = (srb_t *)ptr; - struct scsi_qla_host *vha = sp->fcport->vha; + srb_t *sp = ptr; + struct qla_hw_data *ha = sp->vha->hw; struct bsg_job *bsg_job = sp->u.bsg_job; struct fc_bsg_request *bsg_request = bsg_job->request; - - struct qla_hw_data *ha = vha->hw; struct qla_mt_iocb_rqst_fx00 *piocb_rqst; if (sp->type == SRB_FXIOCB_BCMD) { @@ -62,7 +59,7 @@ qla2x00_bsg_sp_free(void *data, void *ptr) sp->type == SRB_FXIOCB_BCMD || sp->type == SRB_ELS_CMD_HST) kfree(sp->fcport); - qla2x00_rel_sp(vha, sp); + qla2x00_rel_sp(sp); } int @@ -394,7 +391,7 @@ qla2x00_process_els(struct bsg_job *bsg_job) if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x700e, "qla2x00_start_sp failed = %d\n", rval); - qla2x00_rel_sp(vha, sp); + qla2x00_rel_sp(sp); rval = -EIO; goto done_unmap_sg; } @@ -542,7 +539,7 @@ qla2x00_process_ct(struct bsg_job *bsg_job) if (rval != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x7017, "qla2x00_start_sp failed=%d.\n", rval); - qla2x00_rel_sp(vha, sp); + qla2x00_rel_sp(sp); rval = -EIO; goto done_free_fcport; } @@ -2578,6 +2575,6 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job) done: spin_unlock_irqrestore(&ha->hardware_lock, flags); - sp->free(vha, sp); + sp->free(sp); return 0; } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 2f14adfab018..625d438e3cce 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -55,6 +55,8 @@ #include "qla_settings.h" +#define MODE_DUAL (MODE_TARGET | MODE_INITIATOR) + /* * Data bit definitions */ @@ -251,6 +253,14 @@ #define MAX_CMDSZ 16 /* SCSI maximum CDB size. */ #include "qla_fw.h" + +struct name_list_extended { + struct get_name_list_extended *l; + dma_addr_t ldma; + struct list_head fcports; /* protect by sess_list */ + u32 size; + u8 sent; +}; /* * Timeout timer counts in seconds */ @@ -309,6 +319,17 @@ struct els_logo_payload { uint8_t wwpn[WWN_SIZE]; }; +struct ct_arg { + void *iocb; + u16 nport_handle; + dma_addr_t req_dma; + dma_addr_t rsp_dma; + u32 req_size; + u32 rsp_size; + void *req; + void *rsp; +}; + /* * SRB extensions. */ @@ -320,6 +341,7 @@ struct srb_iocb { #define SRB_LOGIN_COND_PLOGI BIT_1 #define SRB_LOGIN_SKIP_PRLI BIT_2 uint16_t data[2]; + u32 iop[2]; } logio; struct { #define ELS_DCMD_TIMEOUT 20 @@ -372,6 +394,16 @@ struct srb_iocb { __le16 comp_status; struct completion comp; } abt; + struct ct_arg ctarg; + struct { + __le16 in_mb[28]; /* fr fw */ + __le16 out_mb[28]; /* to fw */ + void *out, *in; + dma_addr_t out_dma, in_dma; + } mbx; + struct { + struct imm_ntfy_from_isp *ntfy; + } nack; } u; struct timer_list timer; @@ -392,23 +424,31 @@ struct srb_iocb { #define SRB_FXIOCB_BCMD 11 #define SRB_ABT_CMD 12 #define SRB_ELS_DCMD 13 +#define SRB_MB_IOCB 14 +#define SRB_CT_PTHRU_CMD 15 +#define SRB_NACK_PLOGI 16 +#define SRB_NACK_PRLI 17 +#define SRB_NACK_LOGO 18 typedef struct srb { atomic_t ref_count; struct fc_port *fcport; + struct scsi_qla_host *vha; uint32_t handle; uint16_t flags; uint16_t type; char *name; int iocbs; struct qla_qpair *qpair; + u32 gen1; /* scratch */ + u32 gen2; /* scratch */ union { struct srb_iocb iocb_cmd; struct bsg_job *bsg_job; struct srb_cmd scmd; } u; - void (*done)(void *, void *, int); - void (*free)(void *, void *); + void (*done)(void *, int); + void (*free)(void *); } srb_t; #define GET_CMD_SP(sp) (sp->u.scmd.cmd) @@ -1794,6 +1834,7 @@ typedef struct { #define SS_RESIDUAL_OVER BIT_10 #define SS_SENSE_LEN_VALID BIT_9 #define SS_RESPONSE_INFO_LEN_VALID BIT_8 +#define SS_SCSI_STATUS_BYTE 0xff #define SS_RESERVE_CONFLICT (BIT_4 | BIT_3) #define SS_BUSY_CONDITION BIT_3 @@ -1975,6 +2016,84 @@ struct mbx_entry { uint8_t port_name[WWN_SIZE]; }; +#ifndef IMMED_NOTIFY_TYPE +#define IMMED_NOTIFY_TYPE 0x0D /* Immediate notify entry. */ +/* + * ISP queue - immediate notify entry structure definition. + * This is sent by the ISP to the Target driver. + * This IOCB would have report of events sent by the + * initiator, that needs to be handled by the target + * driver immediately. + */ +struct imm_ntfy_from_isp { + uint8_t entry_type; /* Entry type. */ + uint8_t entry_count; /* Entry count. */ + uint8_t sys_define; /* System defined. */ + uint8_t entry_status; /* Entry Status. */ + union { + struct { + uint32_t sys_define_2; /* System defined. */ + target_id_t target; + uint16_t lun; + uint8_t target_id; + uint8_t reserved_1; + uint16_t status_modifier; + uint16_t status; + uint16_t task_flags; + uint16_t seq_id; + uint16_t srr_rx_id; + uint32_t srr_rel_offs; + uint16_t srr_ui; +#define SRR_IU_DATA_IN 0x1 +#define SRR_IU_DATA_OUT 0x5 +#define SRR_IU_STATUS 0x7 + uint16_t srr_ox_id; + uint8_t reserved_2[28]; + } isp2x; + struct { + uint32_t reserved; + uint16_t nport_handle; + uint16_t reserved_2; + uint16_t flags; +#define NOTIFY24XX_FLAGS_GLOBAL_TPRLO BIT_1 +#define NOTIFY24XX_FLAGS_PUREX_IOCB BIT_0 + uint16_t srr_rx_id; + uint16_t status; + uint8_t status_subcode; + uint8_t fw_handle; + uint32_t exchange_address; + uint32_t srr_rel_offs; + uint16_t srr_ui; + uint16_t srr_ox_id; + union { + struct { + uint8_t node_name[8]; + } plogi; /* PLOGI/ADISC/PDISC */ + struct { + /* PRLI word 3 bit 0-15 */ + uint16_t wd3_lo; + uint8_t resv0[6]; + } prli; + struct { + uint8_t port_id[3]; + uint8_t resv1; + uint16_t nport_handle; + uint16_t resv2; + } req_els; + } u; + uint8_t port_name[8]; + uint8_t resv3[3]; + uint8_t vp_index; + uint32_t reserved_5; + uint8_t port_id[3]; + uint8_t reserved_6; + } isp24; + } u; + uint16_t reserved_7; + uint16_t ox_id; +} __packed; +#endif + /* * ISP request and response queue entry sizes */ @@ -2022,10 +2141,22 @@ typedef struct { #define FC4_TYPE_OTHER 0x0 #define FC4_TYPE_UNKNOWN 0xff +/* mailbox command 4G & above */ +struct mbx_24xx_entry { + uint8_t entry_type; + uint8_t entry_count; + uint8_t sys_define1; + uint8_t entry_status; + uint32_t handle; + uint16_t mb[28]; +}; + +#define IOCB_SIZE 64 + /* * Fibre channel port type. */ - typedef enum { +typedef enum { FCT_UNKNOWN, FCT_RSCN, FCT_SWITCH, @@ -2034,6 +2165,74 @@ typedef struct { FCT_TARGET } fc_port_type_t; +enum qla_sess_deletion { + QLA_SESS_DELETION_NONE = 0, + QLA_SESS_DELETION_IN_PROGRESS, + QLA_SESS_DELETED, +}; + +enum qlt_plogi_link_t { + QLT_PLOGI_LINK_SAME_WWN, + QLT_PLOGI_LINK_CONFLICT, + QLT_PLOGI_LINK_MAX +}; + +struct qlt_plogi_ack_t { + struct list_head list; + struct imm_ntfy_from_isp iocb; + port_id_t id; + int ref_count; + void *fcport; +}; + +struct ct_sns_desc { + struct ct_sns_pkt *ct_sns; + dma_addr_t ct_sns_dma; +}; + +enum discovery_state { + DSC_DELETED, + DSC_GID_PN, + DSC_GNL, + DSC_LOGIN_PEND, + DSC_LOGIN_FAILED, + DSC_GPDB, + DSC_GPSC, + DSC_UPD_FCPORT, + DSC_LOGIN_COMPLETE, + DSC_DELETE_PEND, +}; + +enum login_state { /* FW control Target side */ + DSC_LS_LLIOCB_SENT = 2, + DSC_LS_PLOGI_PEND, + DSC_LS_PLOGI_COMP, + DSC_LS_PRLI_PEND, + DSC_LS_PRLI_COMP, + DSC_LS_PORT_UNAVAIL, + DSC_LS_PRLO_PEND = 9, + DSC_LS_LOGO_PEND, +}; + +enum fcport_mgt_event { + FCME_RELOGIN = 1, + FCME_RSCN, + FCME_GIDPN_DONE, + FCME_PLOGI_DONE, /* Initiator side sent LLIOCB */ + FCME_GNL_DONE, + FCME_GPSC_DONE, + FCME_GPDB_DONE, + FCME_GPNID_DONE, + FCME_DELETE_DONE, +}; + +enum rscn_addr_format { + RSCN_PORT_ADDR, + RSCN_AREA_ADDR, + RSCN_DOM_ADDR, + RSCN_FAB_ADDR, +}; + /* * Fibre channel port structure. */ @@ -2047,6 +2246,29 @@ typedef struct fc_port { uint16_t loop_id; uint16_t old_loop_id; + unsigned int conf_compl_supported:1; + unsigned int deleted:2; + unsigned int local:1; + unsigned int logout_on_delete:1; + unsigned int logo_ack_needed:1; + unsigned int keep_nport_handle:1; + unsigned int send_els_logo:1; + unsigned int login_pause:1; + unsigned int login_succ:1; + + struct fc_port *conflict; + unsigned char logout_completed; + int generation; + + struct se_session *se_sess; + struct kref sess_kref; + struct qla_tgt *tgt; + unsigned long expires; + struct list_head del_list_entry; + struct work_struct free_work; + + struct qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX]; + uint16_t tgt_id; uint16_t old_tgt_id; @@ -2075,8 +2297,30 @@ typedef struct fc_port { unsigned long retry_delay_timestamp; struct qla_tgt_sess *tgt_session; + struct ct_sns_desc ct_desc; + enum discovery_state disc_state; + enum login_state fw_login_state; + u32 login_gen, last_login_gen; + u32 rscn_gen, last_rscn_gen; + u32 chip_reset; + struct list_head gnl_entry; + struct work_struct del_work; + u8 iocb[IOCB_SIZE]; } fc_port_t; +#define QLA_FCPORT_SCAN 1 +#define QLA_FCPORT_FOUND 2 + +struct event_arg { + enum fcport_mgt_event event; + fc_port_t *fcport; + srb_t *sp; + port_id_t id; + u16 data[2], rc; + u8 port_name[WWN_SIZE]; + u32 iop[2]; +}; + #include "qla_mr.h" /* @@ -2154,6 +2398,10 @@ static const char * const port_state_str[] = { #define GFT_ID_REQ_SIZE (16 + 4) #define GFT_ID_RSP_SIZE (16 + 32) +#define GID_PN_CMD 0x121 +#define GID_PN_REQ_SIZE (16 + 8) +#define GID_PN_RSP_SIZE (16 + 4) + #define RFT_ID_CMD 0x217 #define RFT_ID_REQ_SIZE (16 + 4 + 32) #define RFT_ID_RSP_SIZE 16 @@ -2479,6 +2727,10 @@ struct ct_sns_req { uint8_t reserved; uint8_t port_name[3]; } gff_id; + + struct { + uint8_t port_name[8]; + } gid_pn; } req; }; @@ -2558,6 +2810,10 @@ struct ct_sns_rsp { struct { uint8_t fc4_features[128]; } gff_id; + struct { + uint8_t reserved; + uint8_t port_id[3]; + } gid_pn; } rsp; }; @@ -2699,11 +2955,11 @@ struct isp_operations { uint16_t (*calc_req_entries) (uint16_t); void (*build_iocbs) (srb_t *, cmd_entry_t *, uint16_t); - void * (*prep_ms_iocb) (struct scsi_qla_host *, uint32_t, uint32_t); - void * (*prep_ms_fdmi_iocb) (struct scsi_qla_host *, uint32_t, + void *(*prep_ms_iocb) (struct scsi_qla_host *, struct ct_arg *); + void *(*prep_ms_fdmi_iocb) (struct scsi_qla_host *, uint32_t, uint32_t); - uint8_t * (*read_nvram) (struct scsi_qla_host *, uint8_t *, + uint8_t *(*read_nvram) (struct scsi_qla_host *, uint8_t *, uint32_t, uint32_t); int (*write_nvram) (struct scsi_qla_host *, uint8_t *, uint32_t, uint32_t); @@ -2765,13 +3021,21 @@ enum qla_work_type { QLA_EVT_AEN, QLA_EVT_IDC_ACK, QLA_EVT_ASYNC_LOGIN, - QLA_EVT_ASYNC_LOGIN_DONE, QLA_EVT_ASYNC_LOGOUT, QLA_EVT_ASYNC_LOGOUT_DONE, QLA_EVT_ASYNC_ADISC, QLA_EVT_ASYNC_ADISC_DONE, QLA_EVT_UEVENT, QLA_EVT_AENFX, + QLA_EVT_GIDPN, + QLA_EVT_GPNID, + QLA_EVT_GPNID_DONE, + QLA_EVT_NEW_SESS, + QLA_EVT_GPDB, + QLA_EVT_GPSC, + QLA_EVT_UPD_FCPORT, + QLA_EVT_GNL, + QLA_EVT_NACK, }; @@ -2807,6 +3071,23 @@ struct qla_work_evt { struct { srb_t *sp; } iosb; + struct { + port_id_t id; + } gpnid; + struct { + port_id_t id; + u8 port_name[8]; + void *pla; + } new_sess; + struct { /*Get PDB, Get Speed, update fcport, gnl, gidpn */ + fc_port_t *fcport; + u8 opt; + } fcport; + struct { + fc_port_t *fcport; + u8 iocb[IOCB_SIZE]; + int type; + } nack; } u; }; @@ -2943,6 +3224,7 @@ struct qla_qpair { struct qla_hw_data *hw; struct work_struct q_work; struct list_head qp_list_elem; /* vha->qp_list */ + struct scsi_qla_host *vha; }; /* Place holder for FW buffer parameters */ @@ -2963,7 +3245,6 @@ struct qlt_hw_data { /* Protected by hw lock */ uint32_t enable_class_2:1; uint32_t enable_explicit_conf:1; - uint32_t ini_mode_force_reverse:1; uint32_t node_name_set:1; dma_addr_t atio_dma; /* Physical address. */ @@ -3115,6 +3396,7 @@ struct qla_hw_data { #define FLOGI_SP_SUPPORT BIT_13 uint8_t port_no; /* Physical port of adapter */ + uint8_t exch_starvation; /* Timeout timers. */ uint8_t loop_down_abort_time; /* port down timer */ @@ -3682,7 +3964,7 @@ typedef struct scsi_qla_host { #define FCOE_CTX_RESET_NEEDED 18 /* Initiate FCoE context reset */ #define MPI_RESET_NEEDED 19 /* Initiate MPI FW reset */ #define ISP_QUIESCE_NEEDED 20 /* Driver need some quiescence */ -#define SCR_PENDING 21 /* SCR in target mode */ +#define FREE_BIT 21 #define PORT_UPDATE_NEEDED 22 #define FX00_RESET_RECOVERY 23 #define FX00_TARGET_SCAN 24 @@ -3736,7 +4018,9 @@ typedef struct scsi_qla_host { /* list of commands waiting on workqueue */ struct list_head qla_cmd_list; struct list_head qla_sess_op_cmd_list; + struct list_head unknown_atio_list; spinlock_t cmd_list_lock; + struct delayed_work unknown_atio_work; /* Counter to detect races between ELS and RSCN events */ atomic_t generation_tick; @@ -3788,6 +4072,10 @@ typedef struct scsi_qla_host { struct qla8044_reset_template reset_tmplt; struct qla_tgt_counters tgt_counters; uint16_t bbcr; + struct name_list_extended gnl; + /* Count of active session/fcport */ + int fcport_count; + wait_queue_head_t fcport_waitQ; } scsi_qla_host_t; struct qla27xx_image_status { diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c index 34272fde8a5b..b48cce696bac 100644 --- a/drivers/scsi/qla2xxx/qla_dfs.c +++ b/drivers/scsi/qla2xxx/qla_dfs.c @@ -18,7 +18,7 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused) scsi_qla_host_t *vha = s->private; struct qla_hw_data *ha = vha->hw; unsigned long flags; - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; struct qla_tgt *tgt= vha->vha_tgt.qla_tgt; seq_printf(s, "%s\n",vha->host_str); @@ -26,12 +26,11 @@ qla2x00_dfs_tgt_sess_show(struct seq_file *s, void *unused) seq_printf(s, "Port ID Port Name Handle\n"); spin_lock_irqsave(&ha->tgt.sess_lock, flags); - list_for_each_entry(sess, &tgt->sess_list, sess_list_entry) { + list_for_each_entry(sess, &vha->vp_fcports, list) seq_printf(s, "%02x:%02x:%02x %8phC %d\n", - sess->s_id.b.domain,sess->s_id.b.area, - sess->s_id.b.al_pa, sess->port_name, - sess->loop_id); - } + sess->d_id.b.domain, sess->d_id.b.area, + sess->d_id.b.al_pa, sess->port_name, + sess->loop_id); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h index 8a2368b32dec..1f808928763b 100644 --- a/drivers/scsi/qla2xxx/qla_fw.h +++ b/drivers/scsi/qla2xxx/qla_fw.h @@ -72,6 +72,37 @@ struct port_database_24xx { uint8_t reserved_3[24]; }; +/* + * MB 75h returns a list of DB entries similar to port_database_24xx(64B). + * However, in this case it returns 1st 40 bytes. + */ +struct get_name_list_extended { + __le16 flags; + u8 current_login_state; + u8 last_login_state; + u8 hard_address[3]; + u8 reserved_1; + u8 port_id[3]; + u8 sequence_id; + __le16 port_timer; + __le16 nport_handle; /* N_PORT handle. */ + __le16 receive_data_size; + __le16 reserved_2; + + /* PRLI SVC Param are Big endian */ + u8 prli_svc_param_word_0[2]; /* Bits 15-0 of word 0 */ + u8 prli_svc_param_word_3[2]; /* Bits 15-0 of word 3 */ + u8 port_name[WWN_SIZE]; + u8 node_name[WWN_SIZE]; +}; + +/* MB 75h: This is the short version of the database */ +struct get_name_list { + u8 port_node_name[WWN_SIZE]; /* B7 most sig, B0 least sig */ + __le16 nport_handle; + u8 reserved; +}; + struct vp_database_24xx { uint16_t vp_status; uint8_t options; @@ -1270,27 +1301,76 @@ struct vp_config_entry_24xx { }; #define VP_RPT_ID_IOCB_TYPE 0x32 /* Report ID Acquisition entry. */ +enum VP_STATUS { + VP_STAT_COMPL, + VP_STAT_FAIL, + VP_STAT_ID_CHG, + VP_STAT_SNS_TO, /* timeout */ + VP_STAT_SNS_RJT, + VP_STAT_SCR_TO, /* timeout */ + VP_STAT_SCR_RJT, +}; + +enum VP_FLAGS { + VP_FLAGS_CON_FLOOP = 1, + VP_FLAGS_CON_P2P = 2, + VP_FLAGS_CON_FABRIC = 3, + VP_FLAGS_NAME_VALID = BIT_5, +}; + struct vp_rpt_id_entry_24xx { uint8_t entry_type; /* Entry type. */ uint8_t entry_count; /* Entry count. */ uint8_t sys_define; /* System defined. */ uint8_t entry_status; /* Entry Status. */ - - uint32_t handle; /* System handle. */ - - uint16_t vp_count; /* Format 0 -- | VP setup | VP acq |. */ - /* Format 1 -- | VP count |. */ - uint16_t vp_idx; /* Format 0 -- Reserved. */ - /* Format 1 -- VP status and index. */ + uint32_t resv1; + uint8_t vp_acquired; + uint8_t vp_setup; + uint8_t vp_idx; /* Format 0=reserved */ + uint8_t vp_status; /* Format 0=reserved */ uint8_t port_id[3]; uint8_t format; - - uint8_t vp_idx_map[16]; - - uint8_t reserved_4[24]; - uint16_t bbcr; - uint8_t reserved_5[6]; + union { + struct { + /* format 0 loop */ + uint8_t vp_idx_map[16]; + uint8_t reserved_4[32]; + } f0; + struct { + /* format 1 fabric */ + uint8_t vpstat1_subcode; /* vp_status=1 subcode */ + uint8_t flags; + uint16_t fip_flags; + uint8_t rsv2[12]; + + uint8_t ls_rjt_vendor; + uint8_t ls_rjt_explanation; + uint8_t ls_rjt_reason; + uint8_t rsv3[5]; + + uint8_t port_name[8]; + uint8_t node_name[8]; + uint16_t bbcr; + uint8_t reserved_5[6]; + } f1; + struct { /* format 2: N2N direct connect */ + uint8_t vpstat1_subcode; + uint8_t flags; + uint16_t rsv6; + uint8_t rsv2[12]; + + uint8_t ls_rjt_vendor; + uint8_t ls_rjt_explanation; + uint8_t ls_rjt_reason; + uint8_t rsv3[5]; + + uint8_t port_name[8]; + uint8_t node_name[8]; + uint32_t remote_nport_id; + uint32_t reserved_5; + } f2; + } u; }; #define VF_EVFP_IOCB_TYPE 0x26 /* Exchange Virtual Fabric Parameters entry. */ diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index afa0116a163b..b3d6441d1d90 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -73,6 +73,10 @@ extern void qla2x00_async_logout_done(struct scsi_qla_host *, fc_port_t *, uint16_t *); extern void qla2x00_async_adisc_done(struct scsi_qla_host *, fc_port_t *, uint16_t *); +struct qla_work_evt *qla2x00_alloc_work(struct scsi_qla_host *, + enum qla_work_type); +extern int qla24xx_async_gnl(struct scsi_qla_host *, fc_port_t *); +int qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e); extern void *qla2x00_alloc_iocbs(struct scsi_qla_host *, srb_t *); extern void *qla2x00_alloc_iocbs_ready(struct scsi_qla_host *, srb_t *); extern int qla24xx_update_fcport_fcp_prio(scsi_qla_host_t *, fc_port_t *); @@ -94,6 +98,13 @@ extern uint8_t qla27xx_find_valid_image(struct scsi_qla_host *); extern struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *, int, int); extern int qla2xxx_delete_qpair(struct scsi_qla_host *, struct qla_qpair *); +void qla2x00_fcport_event_handler(scsi_qla_host_t *, struct event_arg *); +int qla24xx_async_gpdb(struct scsi_qla_host *, fc_port_t *, u8); +int qla24xx_async_notify_ack(scsi_qla_host_t *, fc_port_t *, + struct imm_ntfy_from_isp *, int); +int qla24xx_post_newsess_work(struct scsi_qla_host *, port_id_t *, u8 *, + void *); +int qla24xx_fcport_handle_login(struct scsi_qla_host *, fc_port_t *); /* * Global Data in qla_os.c source file. @@ -127,6 +138,7 @@ extern int ql2xmdenable; extern int ql2xexlogins; extern int ql2xexchoffld; extern int ql2xfwholdabts; +extern int ql2xmvasynctoatio; extern int qla2x00_loop_reset(scsi_qla_host_t *); extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int); @@ -135,8 +147,6 @@ extern int qla2x00_post_aen_work(struct scsi_qla_host *, enum extern int qla2x00_post_idc_ack_work(struct scsi_qla_host *, uint16_t *); extern int qla2x00_post_async_login_work(struct scsi_qla_host *, fc_port_t *, uint16_t *); -extern int qla2x00_post_async_login_done_work(struct scsi_qla_host *, - fc_port_t *, uint16_t *); extern int qla2x00_post_async_logout_work(struct scsi_qla_host *, fc_port_t *, uint16_t *); extern int qla2x00_post_async_logout_done_work(struct scsi_qla_host *, @@ -176,9 +186,13 @@ extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32); extern int qla2x00_post_uevent_work(struct scsi_qla_host *, u32); extern void qla2x00_disable_board_on_pci_error(struct work_struct *); -extern void qla2x00_sp_compl(void *, void *, int); -extern void qla2xxx_qpair_sp_free_dma(void *, void *); -extern void qla2xxx_qpair_sp_compl(void *, void *, int); +extern void qla2x00_sp_compl(void *, int); +extern void qla2xxx_qpair_sp_free_dma(void *); +extern void qla2xxx_qpair_sp_compl(void *, int); +extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *); +void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *, + uint16_t *); +int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *); /* * Global Functions in qla_mid.c source file. @@ -201,7 +215,7 @@ extern void qla2x00_do_dpc_all_vps(scsi_qla_host_t *); extern int qla24xx_vport_create_req_sanity_check(struct fc_vport *); extern scsi_qla_host_t * qla24xx_create_vhost(struct fc_vport *); -extern void qla2x00_sp_free_dma(void *, void *); +extern void qla2x00_sp_free_dma(void *); extern char *qla2x00_get_fw_version_str(struct scsi_qla_host *, char *); extern void qla2x00_mark_device_lost(scsi_qla_host_t *, fc_port_t *, int, int); @@ -302,9 +316,6 @@ extern int qla2x00_init_firmware(scsi_qla_host_t *, uint16_t); extern int -qla2x00_get_node_name_list(scsi_qla_host_t *, void **, int *); - -extern int qla2x00_get_port_database(scsi_qla_host_t *, fc_port_t *, uint8_t); extern int @@ -483,6 +494,9 @@ qla2x00_process_completed_request(struct scsi_qla_host *, struct req_que *, uint32_t); extern irqreturn_t qla2xxx_msix_rsp_q(int irq, void *dev_id); +fc_port_t *qla2x00_find_fcport_by_loopid(scsi_qla_host_t *, uint16_t); +fc_port_t *qla2x00_find_fcport_by_wwpn(scsi_qla_host_t *, u8 *, u8); +fc_port_t *qla2x00_find_fcport_by_nportid(scsi_qla_host_t *, port_id_t *, u8); /* * Global Function Prototypes in qla_sup.c source file. @@ -574,8 +588,8 @@ extern void qla2xxx_dump_post_process(scsi_qla_host_t *, int); /* * Global Function Prototypes in qla_gs.c source file. */ -extern void *qla2x00_prep_ms_iocb(scsi_qla_host_t *, uint32_t, uint32_t); -extern void *qla24xx_prep_ms_iocb(scsi_qla_host_t *, uint32_t, uint32_t); +extern void *qla2x00_prep_ms_iocb(scsi_qla_host_t *, struct ct_arg *); +extern void *qla24xx_prep_ms_iocb(scsi_qla_host_t *, struct ct_arg *); extern int qla2x00_ga_nxt(scsi_qla_host_t *, fc_port_t *); extern int qla2x00_gid_pt(scsi_qla_host_t *, sw_info_t *); extern int qla2x00_gpn_id(scsi_qla_host_t *, sw_info_t *); @@ -591,6 +605,23 @@ extern int qla2x00_fdmi_register(scsi_qla_host_t *); extern int qla2x00_gfpn_id(scsi_qla_host_t *, sw_info_t *); extern int qla2x00_gpsc(scsi_qla_host_t *, sw_info_t *); extern void qla2x00_get_sym_node_name(scsi_qla_host_t *, uint8_t *, size_t); +extern int qla2x00_chk_ms_status(scsi_qla_host_t *, ms_iocb_entry_t *, + struct ct_sns_rsp *, const char *); +extern void qla2x00_async_iocb_timeout(void *data); +extern int qla24xx_async_gidpn(scsi_qla_host_t *, fc_port_t *); +int qla24xx_post_gidpn_work(struct scsi_qla_host *, fc_port_t *); +void qla24xx_handle_gidpn_event(scsi_qla_host_t *, struct event_arg *); + +extern void qla2x00_free_fcport(fc_port_t *); + +extern int qla24xx_post_gpnid_work(struct scsi_qla_host *, port_id_t *); +extern int qla24xx_async_gpnid(scsi_qla_host_t *, port_id_t *); +void qla24xx_async_gpnid_done(scsi_qla_host_t *, srb_t*); +void qla24xx_handle_gpnid_event(scsi_qla_host_t *, struct event_arg *); + +int qla24xx_post_gpsc_work(struct scsi_qla_host *, fc_port_t *); +int qla24xx_async_gpsc(scsi_qla_host_t *, fc_port_t *); +int qla2x00_mgmt_svr_login(scsi_qla_host_t *); /* * Global Function Prototypes in qla_attr.c source file. @@ -702,10 +733,10 @@ extern int qla82xx_restart_isp(scsi_qla_host_t *); /* IOCB related functions */ extern int qla82xx_start_scsi(srb_t *); -extern void qla2x00_sp_free(void *, void *); +extern void qla2x00_sp_free(void *); extern void qla2x00_sp_timeout(unsigned long); -extern void qla2x00_bsg_job_done(void *, void *, int); -extern void qla2x00_bsg_sp_free(void *, void *); +extern void qla2x00_bsg_job_done(void *, int); +extern void qla2x00_bsg_sp_free(void *); extern void qla2x00_start_iocbs(struct scsi_qla_host *, struct req_que *); /* Interrupt related */ @@ -803,4 +834,17 @@ extern int qla_get_exchoffld_status(scsi_qla_host_t *, uint16_t *, uint16_t *); extern int qla_set_exchoffld_mem_cfg(scsi_qla_host_t *, dma_addr_t); extern void qlt_handle_abts_recv(struct scsi_qla_host *, response_t *); +int qla24xx_async_notify_ack(scsi_qla_host_t *, fc_port_t *, + struct imm_ntfy_from_isp *, int); +void qla24xx_do_nack_work(struct scsi_qla_host *, struct qla_work_evt *); +void qlt_plogi_ack_link(struct scsi_qla_host *, struct qlt_plogi_ack_t *, + struct fc_port *, enum qlt_plogi_link_t); +void qlt_plogi_ack_unref(struct scsi_qla_host *, struct qlt_plogi_ack_t *); +extern void qlt_schedule_sess_for_deletion(struct fc_port *, bool); +extern void qlt_schedule_sess_for_deletion_lock(struct fc_port *); +extern struct fc_port *qlt_find_sess_invalidate_other(scsi_qla_host_t *, + uint64_t wwn, port_id_t port_id, uint16_t loop_id, struct fc_port **); +void qla24xx_delete_sess_fn(struct work_struct *); +void qlt_unknown_atio_work_fn(struct work_struct *); + #endif /* _QLA_GBL_H */ diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index ee3df8794806..ab0f873fd6a1 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -24,12 +24,12 @@ static int qla2x00_sns_rnn_id(scsi_qla_host_t *); * Returns a pointer to the @ha's ms_iocb. */ void * -qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size) +qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, struct ct_arg *arg) { struct qla_hw_data *ha = vha->hw; ms_iocb_entry_t *ms_pkt; - ms_pkt = ha->ms_iocb; + ms_pkt = (ms_iocb_entry_t *)arg->iocb; memset(ms_pkt, 0, sizeof(ms_iocb_entry_t)); ms_pkt->entry_type = MS_IOCB_TYPE; @@ -39,15 +39,15 @@ qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size) ms_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2); ms_pkt->cmd_dsd_count = cpu_to_le16(1); ms_pkt->total_dsd_count = cpu_to_le16(2); - ms_pkt->rsp_bytecount = cpu_to_le32(rsp_size); - ms_pkt->req_bytecount = cpu_to_le32(req_size); + ms_pkt->rsp_bytecount = cpu_to_le32(arg->rsp_size); + ms_pkt->req_bytecount = cpu_to_le32(arg->req_size); - ms_pkt->dseg_req_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ms_pkt->dseg_req_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); + ms_pkt->dseg_req_address[0] = cpu_to_le32(LSD(arg->req_dma)); + ms_pkt->dseg_req_address[1] = cpu_to_le32(MSD(arg->req_dma)); ms_pkt->dseg_req_length = ms_pkt->req_bytecount; - ms_pkt->dseg_rsp_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ms_pkt->dseg_rsp_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); + ms_pkt->dseg_rsp_address[0] = cpu_to_le32(LSD(arg->rsp_dma)); + ms_pkt->dseg_rsp_address[1] = cpu_to_le32(MSD(arg->rsp_dma)); ms_pkt->dseg_rsp_length = ms_pkt->rsp_bytecount; vha->qla_stats.control_requests++; @@ -64,29 +64,29 @@ qla2x00_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size) * Returns a pointer to the @ha's ms_iocb. */ void * -qla24xx_prep_ms_iocb(scsi_qla_host_t *vha, uint32_t req_size, uint32_t rsp_size) +qla24xx_prep_ms_iocb(scsi_qla_host_t *vha, struct ct_arg *arg) { struct qla_hw_data *ha = vha->hw; struct ct_entry_24xx *ct_pkt; - ct_pkt = (struct ct_entry_24xx *)ha->ms_iocb; + ct_pkt = (struct ct_entry_24xx *)arg->iocb; memset(ct_pkt, 0, sizeof(struct ct_entry_24xx)); ct_pkt->entry_type = CT_IOCB_TYPE; ct_pkt->entry_count = 1; - ct_pkt->nport_handle = cpu_to_le16(NPH_SNS); + ct_pkt->nport_handle = cpu_to_le16(arg->nport_handle); ct_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2); ct_pkt->cmd_dsd_count = cpu_to_le16(1); ct_pkt->rsp_dsd_count = cpu_to_le16(1); - ct_pkt->rsp_byte_count = cpu_to_le32(rsp_size); - ct_pkt->cmd_byte_count = cpu_to_le32(req_size); + ct_pkt->rsp_byte_count = cpu_to_le32(arg->rsp_size); + ct_pkt->cmd_byte_count = cpu_to_le32(arg->req_size); - ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); + ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(arg->req_dma)); + ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(arg->req_dma)); ct_pkt->dseg_0_len = ct_pkt->cmd_byte_count; - ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); + ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(arg->rsp_dma)); + ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(arg->rsp_dma)); ct_pkt->dseg_1_len = ct_pkt->rsp_byte_count; ct_pkt->vp_index = vha->vp_idx; @@ -117,7 +117,7 @@ qla2x00_prep_ct_req(struct ct_sns_pkt *p, uint16_t cmd, uint16_t rsp_size) return &p->p.req; } -static int +int qla2x00_chk_ms_status(scsi_qla_host_t *vha, ms_iocb_entry_t *ms_pkt, struct ct_sns_rsp *ct_rsp, const char *routine) { @@ -183,14 +183,21 @@ qla2x00_ga_nxt(scsi_qla_host_t *vha, fc_port_t *fcport) struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; struct qla_hw_data *ha = vha->hw; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_ga_nxt(vha, fcport); + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GA_NXT_REQ_SIZE; + arg.rsp_size = GA_NXT_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Issue GA_NXT */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GA_NXT_REQ_SIZE, - GA_NXT_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GA_NXT_CMD, @@ -269,16 +276,24 @@ qla2x00_gid_pt(scsi_qla_host_t *vha, sw_info_t *list) struct ct_sns_gid_pt_data *gid_data; struct qla_hw_data *ha = vha->hw; uint16_t gid_pt_rsp_size; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_gid_pt(vha, list); gid_data = NULL; gid_pt_rsp_size = qla2x00_gid_pt_rsp_size(vha); + + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GID_PT_REQ_SIZE; + arg.rsp_size = gid_pt_rsp_size; + arg.nport_handle = NPH_SNS; + /* Issue GID_PT */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GID_PT_REQ_SIZE, - gid_pt_rsp_size); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GID_PT_CMD, gid_pt_rsp_size); @@ -344,15 +359,22 @@ qla2x00_gpn_id(scsi_qla_host_t *vha, sw_info_t *list) struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; struct qla_hw_data *ha = vha->hw; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_gpn_id(vha, list); + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GPN_ID_REQ_SIZE; + arg.rsp_size = GPN_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + for (i = 0; i < ha->max_fibre_devices; i++) { /* Issue GPN_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GPN_ID_REQ_SIZE, - GPN_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GPN_ID_CMD, @@ -406,15 +428,22 @@ qla2x00_gnn_id(scsi_qla_host_t *vha, sw_info_t *list) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_gnn_id(vha, list); + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GNN_ID_REQ_SIZE; + arg.rsp_size = GNN_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + for (i = 0; i < ha->max_fibre_devices; i++) { /* Issue GNN_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GNN_ID_REQ_SIZE, - GNN_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GNN_ID_CMD, @@ -473,14 +502,21 @@ qla2x00_rft_id(scsi_qla_host_t *vha) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_rft_id(vha); + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = RFT_ID_REQ_SIZE; + arg.rsp_size = RFT_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Issue RFT_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RFT_ID_REQ_SIZE, - RFT_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, RFT_ID_CMD, @@ -526,6 +562,7 @@ qla2x00_rff_id(scsi_qla_host_t *vha) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) { ql_dbg(ql_dbg_disc, vha, 0x2046, @@ -533,10 +570,16 @@ qla2x00_rff_id(scsi_qla_host_t *vha) return (QLA_SUCCESS); } + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = RFF_ID_REQ_SIZE; + arg.rsp_size = RFF_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Issue RFF_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RFF_ID_REQ_SIZE, - RFF_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, RFF_ID_CMD, @@ -584,14 +627,21 @@ qla2x00_rnn_id(scsi_qla_host_t *vha) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) return qla2x00_sns_rnn_id(vha); + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = RNN_ID_REQ_SIZE; + arg.rsp_size = RNN_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Issue RNN_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, RNN_ID_REQ_SIZE, - RNN_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, RNN_ID_CMD, RNN_ID_RSP_SIZE); @@ -651,6 +701,7 @@ qla2x00_rsnn_nn(scsi_qla_host_t *vha) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (IS_QLA2100(ha) || IS_QLA2200(ha)) { ql_dbg(ql_dbg_disc, vha, 0x2050, @@ -658,10 +709,17 @@ qla2x00_rsnn_nn(scsi_qla_host_t *vha) return (QLA_SUCCESS); } + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = 0; + arg.rsp_size = RSNN_NN_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Issue RSNN_NN */ /* Prepare common MS IOCB */ /* Request size adjusted after CT preparation */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, 0, RSNN_NN_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, RSNN_NN_CMD, @@ -1103,7 +1161,7 @@ qla2x00_sns_rnn_id(scsi_qla_host_t *vha) * * Returns 0 on success. */ -static int +int qla2x00_mgmt_svr_login(scsi_qla_host_t *vha) { int ret, rval; @@ -2425,15 +2483,22 @@ qla2x00_gfpn_id(scsi_qla_host_t *vha, sw_info_t *list) ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (!IS_IIDMA_CAPABLE(ha)) return QLA_FUNCTION_FAILED; + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GFPN_ID_REQ_SIZE; + arg.rsp_size = GFPN_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + for (i = 0; i < ha->max_fibre_devices; i++) { /* Issue GFPN_ID */ /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GFPN_ID_REQ_SIZE, - GFPN_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GFPN_ID_CMD, @@ -2471,36 +2536,6 @@ qla2x00_gfpn_id(scsi_qla_host_t *vha, sw_info_t *list) return (rval); } -static inline void * -qla24xx_prep_ms_fm_iocb(scsi_qla_host_t *vha, uint32_t req_size, - uint32_t rsp_size) -{ - struct ct_entry_24xx *ct_pkt; - struct qla_hw_data *ha = vha->hw; - ct_pkt = (struct ct_entry_24xx *)ha->ms_iocb; - memset(ct_pkt, 0, sizeof(struct ct_entry_24xx)); - - ct_pkt->entry_type = CT_IOCB_TYPE; - ct_pkt->entry_count = 1; - ct_pkt->nport_handle = cpu_to_le16(vha->mgmt_svr_loop_id); - ct_pkt->timeout = cpu_to_le16(ha->r_a_tov / 10 * 2); - ct_pkt->cmd_dsd_count = cpu_to_le16(1); - ct_pkt->rsp_dsd_count = cpu_to_le16(1); - ct_pkt->rsp_byte_count = cpu_to_le32(rsp_size); - ct_pkt->cmd_byte_count = cpu_to_le32(req_size); - - ct_pkt->dseg_0_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ct_pkt->dseg_0_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); - ct_pkt->dseg_0_len = ct_pkt->cmd_byte_count; - - ct_pkt->dseg_1_address[0] = cpu_to_le32(LSD(ha->ct_sns_dma)); - ct_pkt->dseg_1_address[1] = cpu_to_le32(MSD(ha->ct_sns_dma)); - ct_pkt->dseg_1_len = ct_pkt->rsp_byte_count; - ct_pkt->vp_index = vha->vp_idx; - - return ct_pkt; -} - static inline struct ct_sns_req * qla24xx_prep_ct_fm_req(struct ct_sns_pkt *p, uint16_t cmd, @@ -2530,9 +2565,10 @@ qla2x00_gpsc(scsi_qla_host_t *vha, sw_info_t *list) int rval; uint16_t i; struct qla_hw_data *ha = vha->hw; - ms_iocb_entry_t *ms_pkt; + ms_iocb_entry_t *ms_pkt; struct ct_sns_req *ct_req; struct ct_sns_rsp *ct_rsp; + struct ct_arg arg; if (!IS_IIDMA_CAPABLE(ha)) return QLA_FUNCTION_FAILED; @@ -2543,11 +2579,17 @@ qla2x00_gpsc(scsi_qla_host_t *vha, sw_info_t *list) if (rval) return rval; + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GPSC_REQ_SIZE; + arg.rsp_size = GPSC_RSP_SIZE; + arg.nport_handle = vha->mgmt_svr_loop_id; + for (i = 0; i < ha->max_fibre_devices; i++) { /* Issue GFPN_ID */ /* Prepare common MS IOCB */ - ms_pkt = qla24xx_prep_ms_fm_iocb(vha, GPSC_REQ_SIZE, - GPSC_RSP_SIZE); + ms_pkt = qla24xx_prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla24xx_prep_ct_fm_req(ha->ct_sns, GPSC_CMD, @@ -2641,6 +2683,7 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list) struct ct_sns_rsp *ct_rsp; struct qla_hw_data *ha = vha->hw; uint8_t fcp_scsi_features = 0; + struct ct_arg arg; for (i = 0; i < ha->max_fibre_devices; i++) { /* Set default FC4 Type as UNKNOWN so the default is to @@ -2651,9 +2694,15 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list) if (!IS_FWI2_CAPABLE(ha)) continue; + arg.iocb = ha->ms_iocb; + arg.req_dma = ha->ct_sns_dma; + arg.rsp_dma = ha->ct_sns_dma; + arg.req_size = GFF_ID_REQ_SIZE; + arg.rsp_size = GFF_ID_RSP_SIZE; + arg.nport_handle = NPH_SNS; + /* Prepare common MS IOCB */ - ms_pkt = ha->isp_ops->prep_ms_iocb(vha, GFF_ID_REQ_SIZE, - GFF_ID_RSP_SIZE); + ms_pkt = ha->isp_ops->prep_ms_iocb(vha, &arg); /* Prepare CT request */ ct_req = qla2x00_prep_ct_req(ha->ct_sns, GFF_ID_CMD, @@ -2692,3 +2741,538 @@ qla2x00_gff_id(scsi_qla_host_t *vha, sw_info_t *list) break; } } + +/* GID_PN completion processing. */ +void qla24xx_handle_gidpn_event(scsi_qla_host_t *vha, struct event_arg *ea) +{ + fc_port_t *fcport = ea->fcport; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC login state %d \n", + __func__, fcport->port_name, fcport->fw_login_state); + + if (ea->sp->gen2 != fcport->login_gen) { + /* PLOGI/PRLI/LOGO came in while cmd was out.*/ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC generation changed rscn %d|%d login %d|%d \n", + __func__, fcport->port_name, fcport->last_rscn_gen, + fcport->rscn_gen, fcport->last_login_gen, fcport->login_gen); + return; + } + + if (!ea->rc) { + if (ea->sp->gen1 == fcport->rscn_gen) { + fcport->scan_state = QLA_FCPORT_FOUND; + fcport->flags |= FCF_FABRIC_DEVICE; + + if (fcport->d_id.b24 == ea->id.b24) { + /* cable plugged into the same place */ + switch (vha->host->active_mode) { + case MODE_TARGET: + /* NOOP. let the other guy login to us.*/ + break; + case MODE_INITIATOR: + case MODE_DUAL: + default: + if (atomic_read(&fcport->state) == + FCS_ONLINE) + break; + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gnl\n", + __func__, __LINE__, fcport->port_name); + qla24xx_post_gnl_work(vha, fcport); + break; + } + } else { /* fcport->d_id.b24 != ea->id.b24 */ + fcport->d_id.b24 = ea->id.b24; + if (fcport->deleted == QLA_SESS_DELETED) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, fcport->port_name); + qlt_schedule_sess_for_deletion_lock(fcport); + } + } + } else { /* ea->sp->gen1 != fcport->rscn_gen */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gidpn\n", + __func__, __LINE__, fcport->port_name); + /* rscn came in while cmd was out */ + qla24xx_post_gidpn_work(vha, fcport); + } + } else { /* ea->rc */ + /* cable pulled */ + if (ea->sp->gen1 == fcport->rscn_gen) { + if (ea->sp->gen2 == fcport->login_gen) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", __func__, + __LINE__, fcport->port_name); + qlt_schedule_sess_for_deletion_lock(fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC login\n", __func__, __LINE__, + fcport->port_name); + qla24xx_fcport_handle_login(vha, fcport); + } + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gidpn\n", __func__, __LINE__, + fcport->port_name); + qla24xx_post_gidpn_work(vha, fcport); + } + } +} /* gidpn_event */ + +static void qla2x00_async_gidpn_sp_done(void *s, int res) +{ + struct srb *sp = s; + struct scsi_qla_host *vha = sp->vha; + fc_port_t *fcport = sp->fcport; + u8 *id = fcport->ct_desc.ct_sns->p.rsp.rsp.gid_pn.port_id; + struct event_arg ea; + + fcport->flags &= ~FCF_ASYNC_SENT; + + memset(&ea, 0, sizeof(ea)); + ea.fcport = fcport; + ea.id.b.domain = id[0]; + ea.id.b.area = id[1]; + ea.id.b.al_pa = id[2]; + ea.sp = sp; + ea.rc = res; + ea.event = FCME_GIDPN_DONE; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x, WWPN %8phC ID %3phC \n", + sp->name, res, fcport->port_name, id); + + qla2x00_fcport_event_handler(vha, &ea); + + sp->free(sp); +} + +int qla24xx_async_gidpn(scsi_qla_host_t *vha, fc_port_t *fcport) +{ + int rval = QLA_FUNCTION_FAILED; + struct ct_sns_req *ct_req; + srb_t *sp; + + if (!vha->flags.online) + goto done; + + fcport->flags |= FCF_ASYNC_SENT; + fcport->disc_state = DSC_GID_PN; + fcport->scan_state = QLA_FCPORT_SCAN; + sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC); + if (!sp) + goto done; + + sp->type = SRB_CT_PTHRU_CMD; + sp->name = "gidpn"; + sp->gen1 = fcport->rscn_gen; + sp->gen2 = fcport->login_gen; + + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); + + /* CT_IU preamble */ + ct_req = qla2x00_prep_ct_req(fcport->ct_desc.ct_sns, GID_PN_CMD, + GID_PN_RSP_SIZE); + + /* GIDPN req */ + memcpy(ct_req->req.gid_pn.port_name, fcport->port_name, + WWN_SIZE); + + /* req & rsp use the same buffer */ + sp->u.iocb_cmd.u.ctarg.req = fcport->ct_desc.ct_sns; + sp->u.iocb_cmd.u.ctarg.req_dma = fcport->ct_desc.ct_sns_dma; + sp->u.iocb_cmd.u.ctarg.rsp = fcport->ct_desc.ct_sns; + sp->u.iocb_cmd.u.ctarg.rsp_dma = fcport->ct_desc.ct_sns_dma; + sp->u.iocb_cmd.u.ctarg.req_size = GID_PN_REQ_SIZE; + sp->u.iocb_cmd.u.ctarg.rsp_size = GID_PN_RSP_SIZE; + sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS; + + sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout; + sp->done = qla2x00_async_gidpn_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0x206f, + "Async-%s - %8phC hdl=%x loopid=%x portid %02x%02x%02x.\n", + sp->name, fcport->port_name, + sp->handle, fcport->loop_id, fcport->d_id.b.domain, + fcport->d_id.b.area, fcport->d_id.b.al_pa); + return rval; + +done_free_sp: + sp->free(sp); +done: + fcport->flags &= ~FCF_ASYNC_SENT; + return rval; +} + +int qla24xx_post_gidpn_work(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + struct qla_work_evt *e; + int ls; + + ls = atomic_read(&vha->loop_state); + if (((ls != LOOP_READY) && (ls != LOOP_UP)) || + test_bit(UNLOADING, &vha->dpc_flags)) + return 0; + + e = qla2x00_alloc_work(vha, QLA_EVT_GIDPN); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.fcport.fcport = fcport; + return qla2x00_post_work(vha, e); +} + +int qla24xx_post_gpsc_work(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + struct qla_work_evt *e; + + e = qla2x00_alloc_work(vha, QLA_EVT_GPSC); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.fcport.fcport = fcport; + return qla2x00_post_work(vha, e); +} + +static void qla24xx_async_gpsc_sp_done(void *s, int res) +{ + struct srb *sp = s; + struct scsi_qla_host *vha = sp->vha; + struct qla_hw_data *ha = vha->hw; + fc_port_t *fcport = sp->fcport; + struct ct_sns_rsp *ct_rsp; + struct event_arg ea; + + ct_rsp = &fcport->ct_desc.ct_sns->p.rsp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x, WWPN %8phC \n", + sp->name, res, fcport->port_name); + + fcport->flags &= ~FCF_ASYNC_SENT; + + if (res == (DID_ERROR << 16)) { + /* entry status error */ + goto done; + } else if (res) { + if ((ct_rsp->header.reason_code == + CT_REASON_INVALID_COMMAND_CODE) || + (ct_rsp->header.reason_code == + CT_REASON_COMMAND_UNSUPPORTED)) { + ql_dbg(ql_dbg_disc, vha, 0x205a, + "GPSC command unsupported, disabling " + "query.\n"); + ha->flags.gpsc_supported = 0; + res = QLA_SUCCESS; + } + } else { + switch (be16_to_cpu(ct_rsp->rsp.gpsc.speed)) { + case BIT_15: + fcport->fp_speed = PORT_SPEED_1GB; + break; + case BIT_14: + fcport->fp_speed = PORT_SPEED_2GB; + break; + case BIT_13: + fcport->fp_speed = PORT_SPEED_4GB; + break; + case BIT_12: + fcport->fp_speed = PORT_SPEED_10GB; + break; + case BIT_11: + fcport->fp_speed = PORT_SPEED_8GB; + break; + case BIT_10: + fcport->fp_speed = PORT_SPEED_16GB; + break; + case BIT_8: + fcport->fp_speed = PORT_SPEED_32GB; + break; + } + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s OUT WWPN %8phC speeds=%04x speed=%04x.\n", + sp->name, + fcport->fabric_port_name, + be16_to_cpu(ct_rsp->rsp.gpsc.speeds), + be16_to_cpu(ct_rsp->rsp.gpsc.speed)); + } +done: + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_GPSC_DONE; + ea.rc = res; + ea.fcport = fcport; + qla2x00_fcport_event_handler(vha, &ea); + + sp->free(sp); +} + +int qla24xx_async_gpsc(scsi_qla_host_t *vha, fc_port_t *fcport) +{ + int rval = QLA_FUNCTION_FAILED; + struct ct_sns_req *ct_req; + srb_t *sp; + + if (!vha->flags.online) + goto done; + + fcport->flags |= FCF_ASYNC_SENT; + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) + goto done; + + sp->type = SRB_CT_PTHRU_CMD; + sp->name = "gpsc"; + sp->gen1 = fcport->rscn_gen; + sp->gen2 = fcport->login_gen; + + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); + + /* CT_IU preamble */ + ct_req = qla24xx_prep_ct_fm_req(fcport->ct_desc.ct_sns, GPSC_CMD, + GPSC_RSP_SIZE); + + /* GPSC req */ + memcpy(ct_req->req.gpsc.port_name, fcport->port_name, + WWN_SIZE); + + sp->u.iocb_cmd.u.ctarg.req = fcport->ct_desc.ct_sns; + sp->u.iocb_cmd.u.ctarg.req_dma = fcport->ct_desc.ct_sns_dma; + sp->u.iocb_cmd.u.ctarg.rsp = fcport->ct_desc.ct_sns; + sp->u.iocb_cmd.u.ctarg.rsp_dma = fcport->ct_desc.ct_sns_dma; + sp->u.iocb_cmd.u.ctarg.req_size = GPSC_REQ_SIZE; + sp->u.iocb_cmd.u.ctarg.rsp_size = GPSC_RSP_SIZE; + sp->u.iocb_cmd.u.ctarg.nport_handle = vha->mgmt_svr_loop_id; + + sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout; + sp->done = qla24xx_async_gpsc_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s %8phC hdl=%x loopid=%x portid=%02x%02x%02x.\n", + sp->name, fcport->port_name, sp->handle, + fcport->loop_id, fcport->d_id.b.domain, + fcport->d_id.b.area, fcport->d_id.b.al_pa); + return rval; + +done_free_sp: + sp->free(sp); +done: + fcport->flags &= ~FCF_ASYNC_SENT; + return rval; +} + +int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id) +{ + struct qla_work_evt *e; + + if (test_bit(UNLOADING, &vha->dpc_flags)) + return 0; + + e = qla2x00_alloc_work(vha, QLA_EVT_GPNID); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.gpnid.id = *id; + return qla2x00_post_work(vha, e); +} + +void qla24xx_async_gpnid_done(scsi_qla_host_t *vha, srb_t *sp) +{ + if (sp->u.iocb_cmd.u.ctarg.req) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + + sp->free(sp); +} + +void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea) +{ + fc_port_t *fcport; + unsigned long flags; + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + fcport = qla2x00_find_fcport_by_wwpn(vha, ea->port_name, 1); + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + if (fcport) { + /* cable moved. just plugged in */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, fcport->port_name); + + fcport->rscn_gen++; + fcport->d_id = ea->id; + fcport->scan_state = QLA_FCPORT_FOUND; + fcport->flags |= FCF_FABRIC_DEVICE; + + qlt_schedule_sess_for_deletion_lock(fcport); + } else { + /* create new fcport */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post new sess\n", + __func__, __LINE__, ea->port_name); + + qla24xx_post_newsess_work(vha, &ea->id, ea->port_name, NULL); + } +} + +static void qla2x00_async_gpnid_sp_done(void *s, int res) +{ + struct srb *sp = s; + struct scsi_qla_host *vha = sp->vha; + struct ct_sns_req *ct_req = + (struct ct_sns_req *)sp->u.iocb_cmd.u.ctarg.req; + struct ct_sns_rsp *ct_rsp = + (struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp; + struct event_arg ea; + struct qla_work_evt *e; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x ID %3phC. %8phC\n", + sp->name, res, ct_req->req.port_id.port_id, + ct_rsp->rsp.gpn_id.port_name); + + memset(&ea, 0, sizeof(ea)); + memcpy(ea.port_name, ct_rsp->rsp.gpn_id.port_name, WWN_SIZE); + ea.sp = sp; + ea.id.b.domain = ct_req->req.port_id.port_id[0]; + ea.id.b.area = ct_req->req.port_id.port_id[1]; + ea.id.b.al_pa = ct_req->req.port_id.port_id[2]; + ea.rc = res; + ea.event = FCME_GPNID_DONE; + + qla2x00_fcport_event_handler(vha, &ea); + + e = qla2x00_alloc_work(vha, QLA_EVT_GPNID_DONE); + if (!e) { + /* please ignore kernel warning. otherwise, we have mem leak. */ + if (sp->u.iocb_cmd.u.ctarg.req) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + + sp->free(sp); + return; + } + + e->u.iosb.sp = sp; + qla2x00_post_work(vha, e); +} + +/* Get WWPN with Nport ID. */ +int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) +{ + int rval = QLA_FUNCTION_FAILED; + struct ct_sns_req *ct_req; + srb_t *sp; + struct ct_sns_pkt *ct_sns; + + if (!vha->flags.online) + goto done; + + sp = qla2x00_get_sp(vha, NULL, GFP_KERNEL); + if (!sp) + goto done; + + sp->type = SRB_CT_PTHRU_CMD; + sp->name = "gpnid"; + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); + + sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma, + GFP_KERNEL); + if (!sp->u.iocb_cmd.u.ctarg.req) { + ql_log(ql_log_warn, vha, 0xffff, + "Failed to allocate ct_sns request.\n"); + goto done_free_sp; + } + + sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma, + GFP_KERNEL); + if (!sp->u.iocb_cmd.u.ctarg.rsp) { + ql_log(ql_log_warn, vha, 0xffff, + "Failed to allocate ct_sns request.\n"); + goto done_free_sp; + } + + ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.rsp; + memset(ct_sns, 0, sizeof(*ct_sns)); + + ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.req; + /* CT_IU preamble */ + ct_req = qla2x00_prep_ct_req(ct_sns, GPN_ID_CMD, GPN_ID_RSP_SIZE); + + /* GPN_ID req */ + ct_req->req.port_id.port_id[0] = id->b.domain; + ct_req->req.port_id.port_id[1] = id->b.area; + ct_req->req.port_id.port_id[2] = id->b.al_pa; + + sp->u.iocb_cmd.u.ctarg.req_size = GPN_ID_REQ_SIZE; + sp->u.iocb_cmd.u.ctarg.rsp_size = GPN_ID_RSP_SIZE; + sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS; + + sp->u.iocb_cmd.timeout = qla2x00_async_iocb_timeout; + sp->done = qla2x00_async_gpnid_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s hdl=%x ID %3phC.\n", sp->name, + sp->handle, ct_req->req.port_id.port_id); + return rval; + +done_free_sp: + if (sp->u.iocb_cmd.u.ctarg.req) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp) { + dma_free_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + + sp->free(sp); +done: + return rval; +} diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 265e1395bdb8..32fb9007f137 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -30,15 +30,15 @@ static int qla2x00_configure_hba(scsi_qla_host_t *); static int qla2x00_configure_loop(scsi_qla_host_t *); static int qla2x00_configure_local_loop(scsi_qla_host_t *); static int qla2x00_configure_fabric(scsi_qla_host_t *); -static int qla2x00_find_all_fabric_devs(scsi_qla_host_t *, struct list_head *); -static int qla2x00_fabric_dev_login(scsi_qla_host_t *, fc_port_t *, - uint16_t *); - +static int qla2x00_find_all_fabric_devs(scsi_qla_host_t *); static int qla2x00_restart_isp(scsi_qla_host_t *); static struct qla_chip_state_84xx *qla84xx_get_chip(struct scsi_qla_host *); static int qla84xx_init_chip(scsi_qla_host_t *); static int qla25xx_init_queues(struct qla_hw_data *); +static int qla24xx_post_gpdb_work(struct scsi_qla_host *, fc_port_t *, u8); +static void qla24xx_handle_plogi_done_event(struct scsi_qla_host *, + struct event_arg *); /* SRB Extensions ---------------------------------------------------------- */ @@ -47,29 +47,27 @@ qla2x00_sp_timeout(unsigned long __data) { srb_t *sp = (srb_t *)__data; struct srb_iocb *iocb; - fc_port_t *fcport = sp->fcport; - struct qla_hw_data *ha = fcport->vha->hw; + scsi_qla_host_t *vha = sp->vha; struct req_que *req; unsigned long flags; - spin_lock_irqsave(&ha->hardware_lock, flags); - req = ha->req_q_map[0]; + spin_lock_irqsave(&vha->hw->hardware_lock, flags); + req = vha->hw->req_q_map[0]; req->outstanding_cmds[sp->handle] = NULL; iocb = &sp->u.iocb_cmd; iocb->timeout(sp); - sp->free(fcport->vha, sp); - spin_unlock_irqrestore(&ha->hardware_lock, flags); + sp->free(sp); + spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); } void -qla2x00_sp_free(void *data, void *ptr) +qla2x00_sp_free(void *ptr) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct srb_iocb *iocb = &sp->u.iocb_cmd; - struct scsi_qla_host *vha = (scsi_qla_host_t *)data; del_timer(&iocb->timer); - qla2x00_rel_sp(vha, sp); + qla2x00_rel_sp(sp); } /* Asynchronous Login/Logout Routines -------------------------------------- */ @@ -94,43 +92,72 @@ qla2x00_get_async_timeout(struct scsi_qla_host *vha) return tmo; } -static void +void qla2x00_async_iocb_timeout(void *data) { - srb_t *sp = (srb_t *)data; + srb_t *sp = data; fc_port_t *fcport = sp->fcport; + struct srb_iocb *lio = &sp->u.iocb_cmd; + struct event_arg ea; ql_dbg(ql_dbg_disc, fcport->vha, 0x2071, - "Async-%s timeout - hdl=%x portid=%02x%02x%02x.\n", - sp->name, sp->handle, fcport->d_id.b.domain, fcport->d_id.b.area, - fcport->d_id.b.al_pa); + "Async-%s timeout - hdl=%x portid=%06x %8phC.\n", + sp->name, sp->handle, fcport->d_id.b24, fcport->port_name); fcport->flags &= ~FCF_ASYNC_SENT; - if (sp->type == SRB_LOGIN_CMD) { - struct srb_iocb *lio = &sp->u.iocb_cmd; - qla2x00_post_async_logout_work(fcport->vha, fcport, NULL); + + switch (sp->type) { + case SRB_LOGIN_CMD: /* Retry as needed. */ lio->u.logio.data[0] = MBS_COMMAND_ERROR; lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ? QLA_LOGIO_LOGIN_RETRIED : 0; - qla2x00_post_async_login_done_work(fcport->vha, fcport, - lio->u.logio.data); - } else if (sp->type == SRB_LOGOUT_CMD) { + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_PLOGI_DONE; + ea.fcport = sp->fcport; + ea.data[0] = lio->u.logio.data[0]; + ea.data[1] = lio->u.logio.data[1]; + ea.sp = sp; + qla24xx_handle_plogi_done_event(fcport->vha, &ea); + break; + case SRB_LOGOUT_CMD: qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT); + break; + case SRB_CT_PTHRU_CMD: + case SRB_MB_IOCB: + case SRB_NACK_PLOGI: + case SRB_NACK_PRLI: + case SRB_NACK_LOGO: + sp->done(sp, QLA_FUNCTION_TIMEOUT); + break; } } static void -qla2x00_async_login_sp_done(void *data, void *ptr, int res) +qla2x00_async_login_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; + struct scsi_qla_host *vha = sp->vha; struct srb_iocb *lio = &sp->u.iocb_cmd; - struct scsi_qla_host *vha = (scsi_qla_host_t *)data; + struct event_arg ea; - if (!test_bit(UNLOADING, &vha->dpc_flags)) - qla2x00_post_async_login_done_work(sp->fcport->vha, sp->fcport, - lio->u.logio.data); - sp->free(sp->fcport->vha, sp); + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC res %d \n", __func__, sp->fcport->port_name, res); + + sp->fcport->flags &= ~FCF_ASYNC_SENT; + if (!test_bit(UNLOADING, &vha->dpc_flags)) { + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_PLOGI_DONE; + ea.fcport = sp->fcport; + ea.data[0] = lio->u.logio.data[0]; + ea.data[1] = lio->u.logio.data[1]; + ea.iop[0] = lio->u.logio.iop[0]; + ea.iop[1] = lio->u.logio.iop[1]; + ea.sp = sp; + qla2x00_fcport_event_handler(vha, &ea); + } + + sp->free(sp); } int @@ -139,13 +166,23 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, { srb_t *sp; struct srb_iocb *lio; - int rval; + int rval = QLA_FUNCTION_FAILED; + + if (!vha->flags.online) + goto done; + + if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || + (fcport->fw_login_state == DSC_LS_PLOGI_COMP) || + (fcport->fw_login_state == DSC_LS_PRLI_PEND)) + goto done; - rval = QLA_FUNCTION_FAILED; sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) goto done; + fcport->flags |= FCF_ASYNC_SENT; + fcport->logout_completed = 0; + sp->type = SRB_LOGIN_CMD; sp->name = "login"; qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); @@ -165,29 +202,30 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport, } ql_dbg(ql_dbg_disc, vha, 0x2072, - "Async-login - hdl=%x, loopid=%x portid=%02x%02x%02x " - "retries=%d.\n", sp->handle, fcport->loop_id, + "Async-login - %8phC hdl=%x, loopid=%x portid=%02x%02x%02x " + "retries=%d.\n", fcport->port_name, sp->handle, fcport->loop_id, fcport->d_id.b.domain, fcport->d_id.b.area, fcport->d_id.b.al_pa, fcport->login_retry); return rval; done_free_sp: - sp->free(fcport->vha, sp); + sp->free(sp); done: + fcport->flags &= ~FCF_ASYNC_SENT; return rval; } static void -qla2x00_async_logout_sp_done(void *data, void *ptr, int res) +qla2x00_async_logout_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct srb_iocb *lio = &sp->u.iocb_cmd; - struct scsi_qla_host *vha = (scsi_qla_host_t *)data; - if (!test_bit(UNLOADING, &vha->dpc_flags)) - qla2x00_post_async_logout_done_work(sp->fcport->vha, sp->fcport, + sp->fcport->flags &= ~FCF_ASYNC_SENT; + if (!test_bit(UNLOADING, &sp->vha->dpc_flags)) + qla2x00_post_async_logout_done_work(sp->vha, sp->fcport, lio->u.logio.data); - sp->free(sp->fcport->vha, sp); + sp->free(sp); } int @@ -198,6 +236,7 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport) int rval; rval = QLA_FUNCTION_FAILED; + fcport->flags |= FCF_ASYNC_SENT; sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) goto done; @@ -214,28 +253,30 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport) goto done_free_sp; ql_dbg(ql_dbg_disc, vha, 0x2070, - "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x.\n", + "Async-logout - hdl=%x loop-id=%x portid=%02x%02x%02x %8phC.\n", sp->handle, fcport->loop_id, fcport->d_id.b.domain, - fcport->d_id.b.area, fcport->d_id.b.al_pa); + fcport->d_id.b.area, fcport->d_id.b.al_pa, + fcport->port_name); return rval; done_free_sp: - sp->free(fcport->vha, sp); + sp->free(sp); done: + fcport->flags &= ~FCF_ASYNC_SENT; return rval; } static void -qla2x00_async_adisc_sp_done(void *data, void *ptr, int res) +qla2x00_async_adisc_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; + struct scsi_qla_host *vha = sp->vha; struct srb_iocb *lio = &sp->u.iocb_cmd; - struct scsi_qla_host *vha = (scsi_qla_host_t *)data; if (!test_bit(UNLOADING, &vha->dpc_flags)) - qla2x00_post_async_adisc_done_work(sp->fcport->vha, sp->fcport, + qla2x00_post_async_adisc_done_work(sp->vha, sp->fcport, lio->u.logio.data); - sp->free(sp->fcport->vha, sp); + sp->free(sp); } int @@ -247,6 +288,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport, int rval; rval = QLA_FUNCTION_FAILED; + fcport->flags |= FCF_ASYNC_SENT; sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) goto done; @@ -271,15 +313,858 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport, return rval; done_free_sp: - sp->free(fcport->vha, sp); + sp->free(sp); done: + fcport->flags &= ~FCF_ASYNC_SENT; return rval; } +static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, + struct event_arg *ea) +{ + fc_port_t *fcport, *conflict_fcport; + struct get_name_list_extended *e; + u16 i, n, found = 0, loop_id; + port_id_t id; + u64 wwn; + u8 opt = 0; + + fcport = ea->fcport; + + if (ea->rc) { /* rval */ + if (fcport->login_retry == 0) { + fcport->login_retry = vha->hw->login_retry_count; + ql_dbg(ql_dbg_disc, vha, 0xffff, + "GNL failed Port login retry %8phN, retry cnt=%d.\n", + fcport->port_name, fcport->login_retry); + } + return; + } + + if (fcport->last_rscn_gen != fcport->rscn_gen) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC rscn gen changed rscn %d|%d \n", + __func__, fcport->port_name, + fcport->last_rscn_gen, fcport->rscn_gen); + qla24xx_post_gidpn_work(vha, fcport); + return; + } else if (fcport->last_login_gen != fcport->login_gen) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC login gen changed login %d|%d \n", + __func__, fcport->port_name, + fcport->last_login_gen, fcport->login_gen); + return; + } + + n = ea->data[0] / sizeof(struct get_name_list_extended); + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC n %d %02x%02x%02x lid %d \n", + __func__, __LINE__, fcport->port_name, n, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa, fcport->loop_id); + + for (i = 0; i < n; i++) { + e = &vha->gnl.l[i]; + wwn = wwn_to_u64(e->port_name); + + if (memcmp((u8 *)&wwn, fcport->port_name, WWN_SIZE)) + continue; + + found = 1; + id.b.domain = e->port_id[2]; + id.b.area = e->port_id[1]; + id.b.al_pa = e->port_id[0]; + id.b.rsvd_1 = 0; + + loop_id = le16_to_cpu(e->nport_handle); + loop_id = (loop_id & 0x7fff); + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s found %8phC CLS [%d|%d] ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n", + __func__, fcport->port_name, + e->current_login_state, fcport->fw_login_state, + id.b.domain, id.b.area, id.b.al_pa, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa, loop_id, fcport->loop_id); + + if ((id.b24 != fcport->d_id.b24) || + ((fcport->loop_id != FC_NO_LOOP_ID) && + (fcport->loop_id != loop_id))) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, fcport->port_name); + qlt_schedule_sess_for_deletion(fcport, 1); + return; + } + + fcport->loop_id = loop_id; + + wwn = wwn_to_u64(fcport->port_name); + qlt_find_sess_invalidate_other(vha, wwn, + id, loop_id, &conflict_fcport); + + if (conflict_fcport) { + /* + * Another share fcport share the same loop_id & + * nport id. Conflict fcport needs to finish + * cleanup before this fcport can proceed to login. + */ + conflict_fcport->conflict = fcport; + fcport->login_pause = 1; + } + + switch (e->current_login_state) { + case DSC_LS_PRLI_COMP: + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpdb\n", + __func__, __LINE__, fcport->port_name); + opt = PDO_FORCE_ADISC; + qla24xx_post_gpdb_work(vha, fcport, opt); + break; + + case DSC_LS_PORT_UNAVAIL: + default: + if (fcport->loop_id == FC_NO_LOOP_ID) { + qla2x00_find_new_loop_id(vha, fcport); + fcport->fw_login_state = DSC_LS_PORT_UNAVAIL; + } + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC \n", + __func__, __LINE__, fcport->port_name); + qla24xx_fcport_handle_login(vha, fcport); + break; + } + } + + if (!found) { + /* fw has no record of this port */ + if (fcport->loop_id == FC_NO_LOOP_ID) { + qla2x00_find_new_loop_id(vha, fcport); + fcport->fw_login_state = DSC_LS_PORT_UNAVAIL; + } else { + for (i = 0; i < n; i++) { + e = &vha->gnl.l[i]; + id.b.domain = e->port_id[0]; + id.b.area = e->port_id[1]; + id.b.al_pa = e->port_id[2]; + id.b.rsvd_1 = 0; + loop_id = le16_to_cpu(e->nport_handle); + + if (fcport->d_id.b24 == id.b24) { + conflict_fcport = + qla2x00_find_fcport_by_wwpn(vha, + e->port_name, 0); + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, + conflict_fcport->port_name); + qlt_schedule_sess_for_deletion + (conflict_fcport, 1); + } + + if (fcport->loop_id == loop_id) { + /* FW already picked this loop id for another fcport */ + qla2x00_find_new_loop_id(vha, fcport); + } + } + } + qla24xx_fcport_handle_login(vha, fcport); + } +} /* gnl_event */ + +static void +qla24xx_async_gnl_sp_done(void *s, int res) +{ + struct srb *sp = s; + struct scsi_qla_host *vha = sp->vha; + unsigned long flags; + struct fc_port *fcport = NULL, *tf; + u16 i, n = 0, loop_id; + struct event_arg ea; + struct get_name_list_extended *e; + u64 wwn; + struct list_head h; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x mb[1]=%x mb[2]=%x \n", + sp->name, res, sp->u.iocb_cmd.u.mbx.in_mb[1], + sp->u.iocb_cmd.u.mbx.in_mb[2]); + + memset(&ea, 0, sizeof(ea)); + ea.sp = sp; + ea.rc = res; + ea.event = FCME_GNL_DONE; + + if (sp->u.iocb_cmd.u.mbx.in_mb[1] >= + sizeof(struct get_name_list_extended)) { + n = sp->u.iocb_cmd.u.mbx.in_mb[1] / + sizeof(struct get_name_list_extended); + ea.data[0] = sp->u.iocb_cmd.u.mbx.in_mb[1]; /* amnt xfered */ + } + + for (i = 0; i < n; i++) { + e = &vha->gnl.l[i]; + loop_id = le16_to_cpu(e->nport_handle); + /* mask out reserve bit */ + loop_id = (loop_id & 0x7fff); + set_bit(loop_id, vha->hw->loop_id_map); + wwn = wwn_to_u64(e->port_name); + + ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff, + "%s %8phC %02x:%02x:%02x state %d/%d lid %x \n", + __func__, (void *)&wwn, e->port_id[2], e->port_id[1], + e->port_id[0], e->current_login_state, e->last_login_state, + (loop_id & 0x7fff)); + } + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + vha->gnl.sent = 0; + + INIT_LIST_HEAD(&h); + fcport = tf = NULL; + if (!list_empty(&vha->gnl.fcports)) + list_splice_init(&vha->gnl.fcports, &h); + + list_for_each_entry_safe(fcport, tf, &h, gnl_entry) { + list_del_init(&fcport->gnl_entry); + fcport->flags &= ~FCF_ASYNC_SENT; + ea.fcport = fcport; + + qla2x00_fcport_event_handler(vha, &ea); + } + + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + sp->free(sp); +} + +int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + srb_t *sp; + struct srb_iocb *mbx; + int rval = QLA_FUNCTION_FAILED; + unsigned long flags; + u16 *mb; + + if (!vha->flags.online) + goto done; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-gnlist WWPN %8phC \n", fcport->port_name); + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + fcport->flags |= FCF_ASYNC_SENT; + fcport->disc_state = DSC_GNL; + fcport->last_rscn_gen = fcport->rscn_gen; + fcport->last_login_gen = fcport->login_gen; + + list_add_tail(&fcport->gnl_entry, &vha->gnl.fcports); + if (vha->gnl.sent) { + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + rval = QLA_SUCCESS; + goto done; + } + vha->gnl.sent = 1; + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) + goto done; + sp->type = SRB_MB_IOCB; + sp->name = "gnlist"; + sp->gen1 = fcport->rscn_gen; + sp->gen2 = fcport->login_gen; + + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha)+2); + + mb = sp->u.iocb_cmd.u.mbx.out_mb; + mb[0] = MBC_PORT_NODE_NAME_LIST; + mb[1] = BIT_2 | BIT_3; + mb[2] = MSW(vha->gnl.ldma); + mb[3] = LSW(vha->gnl.ldma); + mb[6] = MSW(MSD(vha->gnl.ldma)); + mb[7] = LSW(MSD(vha->gnl.ldma)); + mb[8] = vha->gnl.size; + mb[9] = vha->vp_idx; + + mbx = &sp->u.iocb_cmd; + mbx->timeout = qla2x00_async_iocb_timeout; + + sp->done = qla24xx_async_gnl_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s - OUT WWPN %8phC hndl %x\n", + sp->name, fcport->port_name, sp->handle); + + return rval; + +done_free_sp: + sp->free(sp); +done: + fcport->flags &= ~FCF_ASYNC_SENT; + return rval; +} + +int qla24xx_post_gnl_work(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + struct qla_work_evt *e; + + e = qla2x00_alloc_work(vha, QLA_EVT_GNL); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.fcport.fcport = fcport; + return qla2x00_post_work(vha, e); +} + +static +void qla24xx_async_gpdb_sp_done(void *s, int res) +{ + struct srb *sp = s; + struct scsi_qla_host *vha = sp->vha; + struct qla_hw_data *ha = vha->hw; + uint64_t zero = 0; + struct port_database_24xx *pd; + fc_port_t *fcport = sp->fcport; + u16 *mb = sp->u.iocb_cmd.u.mbx.in_mb; + int rval = QLA_SUCCESS; + struct event_arg ea; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x, WWPN %8phC mb[1]=%x mb[2]=%x \n", + sp->name, res, fcport->port_name, mb[1], mb[2]); + + fcport->flags &= ~FCF_ASYNC_SENT; + + if (res) { + rval = res; + goto gpd_error_out; + } + + pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in; + + /* Check for logged in state. */ + if (pd->current_login_state != PDS_PRLI_COMPLETE && + pd->last_login_state != PDS_PRLI_COMPLETE) { + ql_dbg(ql_dbg_mbx, vha, 0xffff, + "Unable to verify login-state (%x/%x) for " + "loop_id %x.\n", pd->current_login_state, + pd->last_login_state, fcport->loop_id); + rval = QLA_FUNCTION_FAILED; + goto gpd_error_out; + } + + if (fcport->loop_id == FC_NO_LOOP_ID || + (memcmp(fcport->port_name, (uint8_t *)&zero, 8) && + memcmp(fcport->port_name, pd->port_name, 8))) { + /* We lost the device mid way. */ + rval = QLA_NOT_LOGGED_IN; + goto gpd_error_out; + } + + /* Names are little-endian. */ + memcpy(fcport->node_name, pd->node_name, WWN_SIZE); + + /* Get port_id of device. */ + fcport->d_id.b.domain = pd->port_id[0]; + fcport->d_id.b.area = pd->port_id[1]; + fcport->d_id.b.al_pa = pd->port_id[2]; + fcport->d_id.b.rsvd_1 = 0; + + /* If not target must be initiator or unknown type. */ + if ((pd->prli_svc_param_word_3[0] & BIT_4) == 0) + fcport->port_type = FCT_INITIATOR; + else + fcport->port_type = FCT_TARGET; + + /* Passback COS information. */ + fcport->supported_classes = (pd->flags & PDF_CLASS_2) ? + FC_COS_CLASS2 : FC_COS_CLASS3; + + if (pd->prli_svc_param_word_3[0] & BIT_7) { + fcport->flags |= FCF_CONF_COMP_SUPPORTED; + fcport->conf_compl_supported = 1; + } + +gpd_error_out: + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_GPDB_DONE; + ea.rc = rval; + ea.fcport = fcport; + ea.sp = sp; + + qla2x00_fcport_event_handler(vha, &ea); + + dma_pool_free(ha->s_dma_pool, sp->u.iocb_cmd.u.mbx.in, + sp->u.iocb_cmd.u.mbx.in_dma); + + sp->free(sp); +} + +static int qla24xx_post_gpdb_work(struct scsi_qla_host *vha, fc_port_t *fcport, + u8 opt) +{ + struct qla_work_evt *e; + + e = qla2x00_alloc_work(vha, QLA_EVT_GPDB); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.fcport.fcport = fcport; + e->u.fcport.opt = opt; + return qla2x00_post_work(vha, e); +} + +int qla24xx_async_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt) +{ + srb_t *sp; + struct srb_iocb *mbx; + int rval = QLA_FUNCTION_FAILED; + u16 *mb; + dma_addr_t pd_dma; + struct port_database_24xx *pd; + struct qla_hw_data *ha = vha->hw; + + if (!vha->flags.online) + goto done; + + fcport->flags |= FCF_ASYNC_SENT; + fcport->disc_state = DSC_GPDB; + + sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); + if (!sp) + goto done; + + pd = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &pd_dma); + if (pd == NULL) { + ql_log(ql_log_warn, vha, 0xffff, + "Failed to allocate port database structure.\n"); + goto done_free_sp; + } + memset(pd, 0, max(PORT_DATABASE_SIZE, PORT_DATABASE_24XX_SIZE)); + + sp->type = SRB_MB_IOCB; + sp->name = "gpdb"; + sp->gen1 = fcport->rscn_gen; + sp->gen2 = fcport->login_gen; + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2); + + mb = sp->u.iocb_cmd.u.mbx.out_mb; + mb[0] = MBC_GET_PORT_DATABASE; + mb[1] = fcport->loop_id; + mb[2] = MSW(pd_dma); + mb[3] = LSW(pd_dma); + mb[6] = MSW(MSD(pd_dma)); + mb[7] = LSW(MSD(pd_dma)); + mb[9] = vha->vp_idx; + mb[10] = opt; + + mbx = &sp->u.iocb_cmd; + mbx->timeout = qla2x00_async_iocb_timeout; + mbx->u.mbx.in = (void *)pd; + mbx->u.mbx.in_dma = pd_dma; + + sp->done = qla24xx_async_gpdb_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s %8phC hndl %x opt %x\n", + sp->name, fcport->port_name, sp->handle, opt); + + return rval; + +done_free_sp: + if (pd) + dma_pool_free(ha->s_dma_pool, pd, pd_dma); + + sp->free(sp); +done: + fcport->flags &= ~FCF_ASYNC_SENT; + qla24xx_post_gpdb_work(vha, fcport, opt); + return rval; +} + +static +void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) +{ + int rval = ea->rc; + fc_port_t *fcport = ea->fcport; + unsigned long flags; + + fcport->flags &= ~FCF_ASYNC_SENT; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC DS %d LS %d rval %d\n", __func__, fcport->port_name, + fcport->disc_state, fcport->fw_login_state, rval); + + if (ea->sp->gen2 != fcport->login_gen) { + /* target side must have changed it. */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC generation changed rscn %d|%d login %d|%d \n", + __func__, fcport->port_name, fcport->last_rscn_gen, + fcport->rscn_gen, fcport->last_login_gen, + fcport->login_gen); + return; + } else if (ea->sp->gen1 != fcport->rscn_gen) { + ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post gidpn\n", + __func__, __LINE__, fcport->port_name); + qla24xx_post_gidpn_work(vha, fcport); + return; + } + + if (rval != QLA_SUCCESS) { + ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post del sess\n", + __func__, __LINE__, fcport->port_name); + qlt_schedule_sess_for_deletion_lock(fcport); + return; + } + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + ea->fcport->login_gen++; + ea->fcport->deleted = 0; + ea->fcport->logout_on_delete = 1; + + if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) { + vha->fcport_count++; + ea->fcport->login_succ = 1; + + if (!IS_IIDMA_CAPABLE(vha->hw) || + !vha->hw->flags.gpsc_supported) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post upd_fcport fcp_cnt %d\n", + __func__, __LINE__, fcport->port_name, + vha->fcport_count); + + qla24xx_post_upd_fcport_work(vha, fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpsc fcp_cnt %d\n", + __func__, __LINE__, fcport->port_name, + vha->fcport_count); + + qla24xx_post_gpsc_work(vha, fcport); + } + } + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); +} /* gpdb event */ + +int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + if (fcport->login_retry == 0) + return 0; + + if (fcport->scan_state != QLA_FCPORT_FOUND) + return 0; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC DS %d LS %d P %d fl %x confl %p rscn %d|%d login %d|%d retry %d lid %d\n", + __func__, fcport->port_name, fcport->disc_state, + fcport->fw_login_state, fcport->login_pause, fcport->flags, + fcport->conflict, fcport->last_rscn_gen, fcport->rscn_gen, + fcport->last_login_gen, fcport->login_gen, fcport->login_retry, + fcport->loop_id); + + fcport->login_retry--; + + if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || + (fcport->fw_login_state == DSC_LS_PLOGI_COMP) || + (fcport->fw_login_state == DSC_LS_PRLI_PEND)) + return 0; + + /* for pure Target Mode. Login will not be initiated */ + if (vha->host->active_mode == MODE_TARGET) + return 0; + + if (fcport->flags & FCF_ASYNC_SENT) { + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + return 0; + } + + switch (fcport->disc_state) { + case DSC_DELETED: + if (fcport->loop_id == FC_NO_LOOP_ID) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gnl\n", + __func__, __LINE__, fcport->port_name); + qla24xx_async_gnl(vha, fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post login\n", + __func__, __LINE__, fcport->port_name); + fcport->disc_state = DSC_LOGIN_PEND; + qla2x00_post_async_login_work(vha, fcport, NULL); + } + break; + + case DSC_GNL: + if (fcport->login_pause) { + fcport->last_rscn_gen = fcport->rscn_gen; + fcport->last_login_gen = fcport->login_gen; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + break; + } + + if (fcport->flags & FCF_FCP2_DEVICE) { + u8 opt = PDO_FORCE_ADISC; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpdb\n", + __func__, __LINE__, fcport->port_name); + + fcport->disc_state = DSC_GPDB; + qla24xx_post_gpdb_work(vha, fcport, opt); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post login \n", + __func__, __LINE__, fcport->port_name); + fcport->disc_state = DSC_LOGIN_PEND; + qla2x00_post_async_login_work(vha, fcport, NULL); + } + + break; + + case DSC_LOGIN_FAILED: + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gidpn \n", + __func__, __LINE__, fcport->port_name); + + qla24xx_post_gidpn_work(vha, fcport); + break; + + case DSC_LOGIN_COMPLETE: + /* recheck login state */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpdb \n", + __func__, __LINE__, fcport->port_name); + + qla24xx_post_gpdb_work(vha, fcport, PDO_FORCE_ADISC); + break; + + default: + break; + } + + return 0; +} + +static +void qla24xx_handle_rscn_event(fc_port_t *fcport, struct event_arg *ea) +{ + fcport->rscn_gen++; + + ql_dbg(ql_dbg_disc, fcport->vha, 0xffff, + "%s %8phC DS %d LS %d\n", + __func__, fcport->port_name, fcport->disc_state, + fcport->fw_login_state); + + if (fcport->flags & FCF_ASYNC_SENT) + return; + + switch (fcport->disc_state) { + case DSC_DELETED: + case DSC_LOGIN_COMPLETE: + qla24xx_post_gidpn_work(fcport->vha, fcport); + break; + + default: + break; + } +} + +int qla24xx_post_newsess_work(struct scsi_qla_host *vha, port_id_t *id, + u8 *port_name, void *pla) +{ + struct qla_work_evt *e; + e = qla2x00_alloc_work(vha, QLA_EVT_NEW_SESS); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.new_sess.id = *id; + e->u.new_sess.pla = pla; + memcpy(e->u.new_sess.port_name, port_name, WWN_SIZE); + + return qla2x00_post_work(vha, e); +} + +static +int qla24xx_handle_delete_done_event(scsi_qla_host_t *vha, + struct event_arg *ea) +{ + fc_port_t *fcport = ea->fcport; + + if (test_bit(UNLOADING, &vha->dpc_flags)) + return 0; + + switch (vha->host->active_mode) { + case MODE_INITIATOR: + case MODE_DUAL: + if (fcport->scan_state == QLA_FCPORT_FOUND) + qla24xx_fcport_handle_login(vha, fcport); + break; + + case MODE_TARGET: + default: + /* no-op */ + break; + } + + return 0; +} + +static +void qla24xx_handle_relogin_event(scsi_qla_host_t *vha, + struct event_arg *ea) +{ + fc_port_t *fcport = ea->fcport; + + if (fcport->scan_state != QLA_FCPORT_FOUND) { + fcport->login_retry++; + return; + } + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phC DS %d LS %d P %d del %d cnfl %p rscn %d|%d login %d|%d fl %x\n", + __func__, fcport->port_name, fcport->disc_state, + fcport->fw_login_state, fcport->login_pause, + fcport->deleted, fcport->conflict, + fcport->last_rscn_gen, fcport->rscn_gen, + fcport->last_login_gen, fcport->login_gen, + fcport->flags); + + if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || + (fcport->fw_login_state == DSC_LS_PLOGI_COMP) || + (fcport->fw_login_state == DSC_LS_PRLI_PEND)) + return; + + if (fcport->flags & FCF_ASYNC_SENT) { + fcport->login_retry++; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + return; + } + + if (fcport->disc_state == DSC_DELETE_PEND) { + fcport->login_retry++; + return; + } + + if (fcport->last_rscn_gen != fcport->rscn_gen) { + ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC post gidpn\n", + __func__, __LINE__, fcport->port_name); + + qla24xx_async_gidpn(vha, fcport); + return; + } + + qla24xx_fcport_handle_login(vha, fcport); +} + +void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea) +{ + fc_port_t *fcport, *f, *tf; + uint32_t id = 0, mask, rid; + int rc; + + switch (ea->event) { + case FCME_RELOGIN: + if (test_bit(UNLOADING, &vha->dpc_flags)) + return; + + qla24xx_handle_relogin_event(vha, ea); + break; + case FCME_RSCN: + if (test_bit(UNLOADING, &vha->dpc_flags)) + return; + switch (ea->id.b.rsvd_1) { + case RSCN_PORT_ADDR: + fcport = qla2x00_find_fcport_by_nportid(vha, &ea->id, 1); + if (!fcport) { + /* cable moved */ + rc = qla24xx_post_gpnid_work(vha, &ea->id); + if (rc) { + ql_log(ql_log_warn, vha, 0xffff, + "RSCN GPNID work failed %02x%02x%02x\n", + ea->id.b.domain, ea->id.b.area, + ea->id.b.al_pa); + } + } else { + ea->fcport = fcport; + qla24xx_handle_rscn_event(fcport, ea); + } + break; + case RSCN_AREA_ADDR: + case RSCN_DOM_ADDR: + if (ea->id.b.rsvd_1 == RSCN_AREA_ADDR) { + mask = 0xffff00; + ql_log(ql_dbg_async, vha, 0xffff, + "RSCN: Area 0x%06x was affected\n", + ea->id.b24); + } else { + mask = 0xff0000; + ql_log(ql_dbg_async, vha, 0xffff, + "RSCN: Domain 0x%06x was affected\n", + ea->id.b24); + } + + rid = ea->id.b24 & mask; + list_for_each_entry_safe(f, tf, &vha->vp_fcports, + list) { + id = f->d_id.b24 & mask; + if (rid == id) { + ea->fcport = f; + qla24xx_handle_rscn_event(f, ea); + } + } + break; + case RSCN_FAB_ADDR: + default: + ql_log(ql_log_warn, vha, 0xffff, + "RSCN: Fabric was affected. Addr format %d\n", + ea->id.b.rsvd_1); + qla2x00_mark_all_devices_lost(vha, 1); + set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); + set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); + } + break; + case FCME_GIDPN_DONE: + qla24xx_handle_gidpn_event(vha, ea); + break; + case FCME_GNL_DONE: + qla24xx_handle_gnl_done_event(vha, ea); + break; + case FCME_GPSC_DONE: + qla24xx_post_upd_fcport_work(vha, ea->fcport); + break; + case FCME_PLOGI_DONE: /* Initiator side sent LLIOCB */ + qla24xx_handle_plogi_done_event(vha, ea); + break; + case FCME_GPDB_DONE: + qla24xx_handle_gpdb_event(vha, ea); + break; + case FCME_GPNID_DONE: + qla24xx_handle_gpnid_event(vha, ea); + break; + case FCME_DELETE_DONE: + qla24xx_handle_delete_done_event(vha, ea); + break; + default: + BUG_ON(1); + break; + } +} + static void qla2x00_tmf_iocb_timeout(void *data) { - srb_t *sp = (srb_t *)data; + srb_t *sp = data; struct srb_iocb *tmf = &sp->u.iocb_cmd; tmf->u.tmf.comp_status = CS_TIMEOUT; @@ -287,10 +1172,11 @@ qla2x00_tmf_iocb_timeout(void *data) } static void -qla2x00_tmf_sp_done(void *data, void *ptr, int res) +qla2x00_tmf_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct srb_iocb *tmf = &sp->u.iocb_cmd; + complete(&tmf->u.tmf.comp); } @@ -348,7 +1234,7 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, } done_free_sp: - sp->free(vha, sp); + sp->free(sp); done: return rval; } @@ -356,7 +1242,7 @@ done: static void qla24xx_abort_iocb_timeout(void *data) { - srb_t *sp = (srb_t *)data; + srb_t *sp = data; struct srb_iocb *abt = &sp->u.iocb_cmd; abt->u.abt.comp_status = CS_TIMEOUT; @@ -364,9 +1250,9 @@ qla24xx_abort_iocb_timeout(void *data) } static void -qla24xx_abort_sp_done(void *data, void *ptr, int res) +qla24xx_abort_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct srb_iocb *abt = &sp->u.iocb_cmd; complete(&abt->u.abt.comp); @@ -375,7 +1261,7 @@ qla24xx_abort_sp_done(void *data, void *ptr, int res) static int qla24xx_async_abort_cmd(srb_t *cmd_sp) { - scsi_qla_host_t *vha = cmd_sp->fcport->vha; + scsi_qla_host_t *vha = cmd_sp->vha; fc_port_t *fcport = cmd_sp->fcport; struct srb_iocb *abt_iocb; srb_t *sp; @@ -408,7 +1294,7 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp) QLA_SUCCESS : QLA_FUNCTION_FAILED; done_free_sp: - sp->free(vha, sp); + sp->free(sp); done: return rval; } @@ -441,59 +1327,65 @@ qla24xx_async_abort_command(srb_t *sp) return qla24xx_async_abort_cmd(sp); } -void -qla2x00_async_login_done(struct scsi_qla_host *vha, fc_port_t *fcport, - uint16_t *data) +static void +qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) { - int rval; + port_id_t cid; /* conflict Nport id */ - switch (data[0]) { + switch (ea->data[0]) { case MBS_COMMAND_COMPLETE: /* * Driver must validate login state - If PRLI not complete, * force a relogin attempt via implicit LOGO, PLOGI, and PRLI * requests. */ - rval = qla2x00_get_port_database(vha, fcport, 0); - if (rval == QLA_NOT_LOGGED_IN) { - fcport->flags &= ~FCF_ASYNC_SENT; - fcport->flags |= FCF_LOGIN_NEEDED; - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - break; - } - - if (rval != QLA_SUCCESS) { - qla2x00_post_async_logout_work(vha, fcport, NULL); - qla2x00_post_async_login_work(vha, fcport, NULL); - break; - } - if (fcport->flags & FCF_FCP2_DEVICE) { - qla2x00_post_async_adisc_work(vha, fcport, data); - break; - } - qla2x00_update_fcport(vha, fcport); + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpdb\n", + __func__, __LINE__, ea->fcport->port_name); + ea->fcport->chip_reset = vha->hw->chip_reset; + ea->fcport->logout_on_delete = 1; + qla24xx_post_gpdb_work(vha, ea->fcport, 0); break; case MBS_COMMAND_ERROR: - fcport->flags &= ~FCF_ASYNC_SENT; - if (data[1] & QLA_LOGIO_LOGIN_RETRIED) + ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC cmd error %x\n", + __func__, __LINE__, ea->fcport->port_name, ea->data[1]); + + ea->fcport->flags &= ~FCF_ASYNC_SENT; + ea->fcport->disc_state = DSC_LOGIN_FAILED; + if (ea->data[1] & QLA_LOGIO_LOGIN_RETRIED) set_bit(RELOGIN_NEEDED, &vha->dpc_flags); else - qla2x00_mark_device_lost(vha, fcport, 1, 0); - break; - case MBS_PORT_ID_USED: - fcport->loop_id = data[1]; - qla2x00_post_async_logout_work(vha, fcport, NULL); - qla2x00_post_async_login_work(vha, fcport, NULL); + qla2x00_mark_device_lost(vha, ea->fcport, 1, 0); break; case MBS_LOOP_ID_USED: - fcport->loop_id++; - rval = qla2x00_find_new_loop_id(vha, fcport); - if (rval != QLA_SUCCESS) { - fcport->flags &= ~FCF_ASYNC_SENT; - qla2x00_mark_device_lost(vha, fcport, 1, 0); - break; + /* data[1] = IO PARAM 1 = nport ID */ + cid.b.domain = (ea->iop[1] >> 16) & 0xff; + cid.b.area = (ea->iop[1] >> 8) & 0xff; + cid.b.al_pa = ea->iop[1] & 0xff; + cid.b.rsvd_1 = 0; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC LoopID 0x%x in use post gnl\n", + __func__, __LINE__, ea->fcport->port_name, + ea->fcport->loop_id); + + if (IS_SW_RESV_ADDR(cid)) { + set_bit(ea->fcport->loop_id, vha->hw->loop_id_map); + ea->fcport->loop_id = FC_NO_LOOP_ID; + } else { + qla2x00_clear_loop_id(ea->fcport); } - qla2x00_post_async_login_work(vha, fcport, NULL); + qla24xx_post_gnl_work(vha, ea->fcport); + break; + case MBS_PORT_ID_USED: + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC NPortId %02x%02x%02x inuse post gidpn\n", + __func__, __LINE__, ea->fcport->port_name, + ea->fcport->d_id.b.domain, ea->fcport->d_id.b.area, + ea->fcport->d_id.b.al_pa); + + qla2x00_clear_loop_id(ea->fcport); + qla24xx_post_gidpn_work(vha, ea->fcport); break; } return; @@ -503,10 +1395,9 @@ void qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { - /* Don't re-login in target mode */ - if (!fcport->tgt_session) - qla2x00_mark_device_lost(vha, fcport, 1, 0); + qla2x00_mark_device_lost(vha, fcport, 1, 0); qlt_logo_completion_handler(fcport, data[0]); + fcport->login_gen++; return; } @@ -709,7 +1600,7 @@ qla2x00_initialize_adapter(scsi_qla_host_t *vha) } } - if (qla_ini_mode_enabled(vha)) + if (qla_ini_mode_enabled(vha) || qla_dual_mode_enabled(vha)) rval = qla2x00_init_rings(vha); ha->flags.chip_reset_done = 1; @@ -2088,6 +2979,21 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha) __func__, ha->fw_options[2]); } + /* Move PUREX, ABTS RX & RIDA to ATIOQ */ + if (ql2xmvasynctoatio) { + if (qla_tgt_mode_enabled(vha) || + qla_dual_mode_enabled(vha)) + ha->fw_options[2] |= BIT_11; + else + ha->fw_options[2] &= ~BIT_11; + } + + ql_dbg(ql_dbg_init, vha, 0xffff, + "%s, add FW options 1-3 = 0x%04x 0x%04x 0x%04x mode %x\n", + __func__, ha->fw_options[1], ha->fw_options[2], + ha->fw_options[3], vha->host->active_mode); + qla2x00_set_fw_options(vha, ha->fw_options); + /* Update Serial Link options. */ if ((le16_to_cpu(ha->fw_seriallink_options24[0]) & BIT_0) == 0) return; @@ -2968,8 +3874,14 @@ qla2x00_rport_del(void *data) rport = fcport->drport ? fcport->drport: fcport->rport; fcport->drport = NULL; spin_unlock_irqrestore(fcport->vha->host->host_lock, flags); - if (rport) + if (rport) { + ql_dbg(ql_dbg_disc, fcport->vha, 0xffff, + "%s %8phN. rport %p roles %x \n", + __func__, fcport->port_name, rport, + rport->roles); + fc_remote_port_delete(rport); + } } /** @@ -2995,9 +3907,42 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) qla2x00_set_fcport_state(fcport, FCS_UNCONFIGURED); fcport->supported_classes = FC_COS_UNSPECIFIED; + fcport->ct_desc.ct_sns = dma_alloc_coherent(&vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), &fcport->ct_desc.ct_sns_dma, + flags); + fcport->disc_state = DSC_DELETED; + fcport->fw_login_state = DSC_LS_PORT_UNAVAIL; + fcport->deleted = QLA_SESS_DELETED; + fcport->login_retry = vha->hw->login_retry_count; + fcport->login_retry = 5; + fcport->logout_on_delete = 1; + + if (!fcport->ct_desc.ct_sns) { + ql_log(ql_log_warn, vha, 0xffff, + "Failed to allocate ct_sns request.\n"); + kfree(fcport); + fcport = NULL; + } + INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn); + INIT_LIST_HEAD(&fcport->gnl_entry); + INIT_LIST_HEAD(&fcport->list); + return fcport; } +void +qla2x00_free_fcport(fc_port_t *fcport) +{ + if (fcport->ct_desc.ct_sns) { + dma_free_coherent(&fcport->vha->hw->pdev->dev, + sizeof(struct ct_sns_pkt), fcport->ct_desc.ct_sns, + fcport->ct_desc.ct_sns_dma); + + fcport->ct_desc.ct_sns = NULL; + } + kfree(fcport); +} + /* * qla2x00_configure_loop * Updates Fibre Channel Device Database with what is actually on loop. @@ -3055,10 +4000,11 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) } else if (ha->current_topology == ISP_CFG_N) { clear_bit(RSCN_UPDATE, &flags); - + } else if (ha->current_topology == ISP_CFG_NL) { + clear_bit(RSCN_UPDATE, &flags); + set_bit(LOCAL_LOOP_UPDATE, &flags); } else if (!vha->flags.online || (test_bit(ABORT_ISP_ACTIVE, &flags))) { - set_bit(RSCN_UPDATE, &flags); set_bit(LOCAL_LOOP_UPDATE, &flags); } @@ -3095,7 +4041,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha) * Process any ATIO queue entries that came in * while we weren't online. */ - if (qla_tgt_mode_enabled(vha)) { + if (qla_tgt_mode_enabled(vha) || + qla_dual_mode_enabled(vha)) { if (IS_QLA27XX(ha) || IS_QLA83XX(ha)) { spin_lock_irqsave(&ha->tgt.atio_lock, flags); @@ -3159,6 +4106,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) uint16_t loop_id; uint8_t domain, area, al_pa; struct qla_hw_data *ha = vha->hw; + unsigned long flags; found_devs = 0; new_fcport = NULL; @@ -3199,7 +4147,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) "Marking port lost loop_id=0x%04x.\n", fcport->loop_id); - qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST); + qla2x00_mark_device_lost(vha, fcport, 0, 0); } } @@ -3230,13 +4178,14 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) if (loop_id > LAST_LOCAL_LOOP_ID) continue; - memset(new_fcport, 0, sizeof(fc_port_t)); + memset(new_fcport->port_name, 0, WWN_SIZE); /* Fill in member data. */ new_fcport->d_id.b.domain = domain; new_fcport->d_id.b.area = area; new_fcport->d_id.b.al_pa = al_pa; new_fcport->loop_id = loop_id; + rval2 = qla2x00_get_port_database(vha, new_fcport, 0); if (rval2 != QLA_SUCCESS) { ql_dbg(ql_dbg_disc, vha, 0x201a, @@ -3249,6 +4198,7 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) continue; } + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); /* Check for matching device in port list. */ found = 0; fcport = NULL; @@ -3264,6 +4214,12 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) memcpy(fcport->node_name, new_fcport->node_name, WWN_SIZE); + if (!fcport->login_succ) { + vha->fcport_count++; + fcport->login_succ = 1; + fcport->disc_state = DSC_LOGIN_COMPLETE; + } + found++; break; } @@ -3274,16 +4230,28 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha) /* Allocate a new replacement fcport. */ fcport = new_fcport; + if (!fcport->login_succ) { + vha->fcport_count++; + fcport->login_succ = 1; + fcport->disc_state = DSC_LOGIN_COMPLETE; + } + + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + new_fcport = qla2x00_alloc_fcport(vha, GFP_KERNEL); + if (new_fcport == NULL) { ql_log(ql_log_warn, vha, 0x201c, "Failed to allocate memory for fcport.\n"); rval = QLA_MEMORY_ALLOC_FAILED; goto cleanup_allocation; } + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); new_fcport->flags &= ~FCF_FABRIC_DEVICE; } + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + /* Base iIDMA settings on HBA port speed. */ fcport->fp_speed = ha->link_data_rate; @@ -3334,6 +4302,7 @@ qla2x00_iidma_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) } } +/* qla2x00_reg_remote_port is reserved for Initiator Mode only.*/ static void qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) { @@ -3352,12 +4321,6 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) "Unable to allocate fc remote port.\n"); return; } - /* - * Create target mode FC NEXUS in qla_target.c if target mode is - * enabled.. - */ - - qlt_fc_port_added(vha, fcport); spin_lock_irqsave(fcport->vha->host->host_lock, flags); *((fc_port_t **)rport->dd_data) = fcport; @@ -3370,6 +4333,12 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) rport_ids.roles |= FC_RPORT_ROLE_FCP_INITIATOR; if (fcport->port_type == FCT_TARGET) rport_ids.roles |= FC_RPORT_ROLE_FCP_TARGET; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %8phN. rport %p is %s mode \n", + __func__, fcport->port_name, rport, + (fcport->port_type == FCT_TARGET) ? "tgt" : "ini"); + fc_remote_port_rolechg(rport, rport_ids.roles); } @@ -3393,25 +4362,44 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport) { fcport->vha = vha; + if (IS_SW_RESV_ADDR(fcport->d_id)) + return; + + ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %8phC \n", + __func__, fcport->port_name); + if (IS_QLAFX00(vha->hw)) { qla2x00_set_fcport_state(fcport, FCS_ONLINE); goto reg_port; } fcport->login_retry = 0; fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT); + fcport->disc_state = DSC_LOGIN_COMPLETE; + fcport->deleted = 0; + fcport->logout_on_delete = 1; qla2x00_set_fcport_state(fcport, FCS_ONLINE); qla2x00_iidma_fcport(vha, fcport); qla24xx_update_fcport_fcp_prio(vha, fcport); reg_port: - if (qla_ini_mode_enabled(vha)) + switch (vha->host->active_mode) { + case MODE_INITIATOR: qla2x00_reg_remote_port(vha, fcport); - else { - /* - * Create target mode FC NEXUS in qla_target.c - */ - qlt_fc_port_added(vha, fcport); + break; + case MODE_TARGET: + if (!vha->vha_tgt.qla_tgt->tgt_stop && + !vha->vha_tgt.qla_tgt->tgt_stopped) + qlt_fc_port_added(vha, fcport); + break; + case MODE_DUAL: + qla2x00_reg_remote_port(vha, fcport); + if (!vha->vha_tgt.qla_tgt->tgt_stop && + !vha->vha_tgt.qla_tgt->tgt_stopped) + qlt_fc_port_added(vha, fcport); + break; + default: + break; } } @@ -3430,13 +4418,11 @@ static int qla2x00_configure_fabric(scsi_qla_host_t *vha) { int rval; - fc_port_t *fcport, *fcptemp; - uint16_t next_loopid; + fc_port_t *fcport; uint16_t mb[MAILBOX_REGISTER_COUNT]; uint16_t loop_id; LIST_HEAD(new_fcports); struct qla_hw_data *ha = vha->hw; - struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev); int discovery_gen; /* If FL port exists, then SNS is present */ @@ -3454,7 +4440,19 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) } vha->device_flags |= SWITCH_FOUND; + + if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) { + rval = qla2x00_send_change_request(vha, 0x3, 0); + if (rval != QLA_SUCCESS) + ql_log(ql_log_warn, vha, 0x121, + "Failed to enable receiving of RSCN requests: 0x%x.\n", + rval); + } + + do { + qla2x00_mgmt_svr_login(vha); + /* FDMI support. */ if (ql2xfdmienable && test_and_clear_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags)) @@ -3501,9 +4499,6 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) } } -#define QLA_FCPORT_SCAN 1 -#define QLA_FCPORT_FOUND 2 - list_for_each_entry(fcport, &vha->vp_fcports, list) { fcport->scan_state = QLA_FCPORT_SCAN; } @@ -3516,174 +4511,14 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) * will be newer than discovery_gen. */ qlt_do_generation_tick(vha, &discovery_gen); - rval = qla2x00_find_all_fabric_devs(vha, &new_fcports); + rval = qla2x00_find_all_fabric_devs(vha); if (rval != QLA_SUCCESS) break; - - /* - * Logout all previous fabric devices marked lost, except - * FCP2 devices. - */ - list_for_each_entry(fcport, &vha->vp_fcports, list) { - if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) - break; - - if ((fcport->flags & FCF_FABRIC_DEVICE) == 0) - continue; - - if (fcport->scan_state == QLA_FCPORT_SCAN) { - if (qla_ini_mode_enabled(base_vha) && - atomic_read(&fcport->state) == FCS_ONLINE) { - qla2x00_mark_device_lost(vha, fcport, - ql2xplogiabsentdevice, 0); - if (fcport->loop_id != FC_NO_LOOP_ID && - (fcport->flags & FCF_FCP2_DEVICE) == 0 && - fcport->port_type != FCT_INITIATOR && - fcport->port_type != FCT_BROADCAST) { - ha->isp_ops->fabric_logout(vha, - fcport->loop_id, - fcport->d_id.b.domain, - fcport->d_id.b.area, - fcport->d_id.b.al_pa); - qla2x00_clear_loop_id(fcport); - } - } else if (!qla_ini_mode_enabled(base_vha)) { - /* - * In target mode, explicitly kill - * sessions and log out of devices - * that are gone, so that we don't - * end up with an initiator using the - * wrong ACL (if the fabric recycles - * an FC address and we have a stale - * session around) and so that we don't - * report initiators that are no longer - * on the fabric. - */ - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077, - "port gone, logging out/killing session: " - "%8phC state 0x%x flags 0x%x fc4_type 0x%x " - "scan_state %d\n", - fcport->port_name, - atomic_read(&fcport->state), - fcport->flags, fcport->fc4_type, - fcport->scan_state); - qlt_fc_port_deleted(vha, fcport, - discovery_gen); - } - } - } - - /* Starting free loop ID. */ - next_loopid = ha->min_external_loopid; - - /* - * Scan through our port list and login entries that need to be - * logged in. - */ - list_for_each_entry(fcport, &vha->vp_fcports, list) { - if (atomic_read(&vha->loop_down_timer) || - test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) - break; - - if ((fcport->flags & FCF_FABRIC_DEVICE) == 0 || - (fcport->flags & FCF_LOGIN_NEEDED) == 0) - continue; - - /* - * If we're not an initiator, skip looking for devices - * and logging in. There's no reason for us to do it, - * and it seems to actively cause problems in target - * mode if we race with the initiator logging into us - * (we might get the "port ID used" status back from - * our login command and log out the initiator, which - * seems to cause havoc). - */ - if (!qla_ini_mode_enabled(base_vha)) { - if (fcport->scan_state == QLA_FCPORT_FOUND) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078, - "port %8phC state 0x%x flags 0x%x fc4_type 0x%x " - "scan_state %d (initiator mode disabled; skipping " - "login)\n", fcport->port_name, - atomic_read(&fcport->state), - fcport->flags, fcport->fc4_type, - fcport->scan_state); - } - continue; - } - - if (fcport->loop_id == FC_NO_LOOP_ID) { - fcport->loop_id = next_loopid; - rval = qla2x00_find_new_loop_id( - base_vha, fcport); - if (rval != QLA_SUCCESS) { - /* Ran out of IDs to use */ - break; - } - } - /* Login and update database */ - qla2x00_fabric_dev_login(vha, fcport, &next_loopid); - } - - /* Exit if out of loop IDs. */ - if (rval != QLA_SUCCESS) { - break; - } - - /* - * Login and add the new devices to our port list. - */ - list_for_each_entry_safe(fcport, fcptemp, &new_fcports, list) { - if (atomic_read(&vha->loop_down_timer) || - test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) - break; - - /* - * If we're not an initiator, skip looking for devices - * and logging in. There's no reason for us to do it, - * and it seems to actively cause problems in target - * mode if we race with the initiator logging into us - * (we might get the "port ID used" status back from - * our login command and log out the initiator, which - * seems to cause havoc). - */ - if (qla_ini_mode_enabled(base_vha)) { - /* Find a new loop ID to use. */ - fcport->loop_id = next_loopid; - rval = qla2x00_find_new_loop_id(base_vha, - fcport); - if (rval != QLA_SUCCESS) { - /* Ran out of IDs to use */ - break; - } - - /* Login and update database */ - qla2x00_fabric_dev_login(vha, fcport, - &next_loopid); - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079, - "new port %8phC state 0x%x flags 0x%x fc4_type " - "0x%x scan_state %d (initiator mode disabled; " - "skipping login)\n", - fcport->port_name, - atomic_read(&fcport->state), - fcport->flags, fcport->fc4_type, - fcport->scan_state); - } - - list_move_tail(&fcport->list, &vha->vp_fcports); - } } while (0); - /* Free all new device structures not processed. */ - list_for_each_entry_safe(fcport, fcptemp, &new_fcports, list) { - list_del(&fcport->list); - kfree(fcport); - } - - if (rval) { + if (rval) ql_dbg(ql_dbg_disc, vha, 0x2068, "Configure fabric error exit rval=%d.\n", rval); - } return (rval); } @@ -3702,12 +4537,11 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) * Kernel context. */ static int -qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, - struct list_head *new_fcports) +qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha) { int rval; uint16_t loop_id; - fc_port_t *fcport, *new_fcport, *fcptemp; + fc_port_t *fcport, *new_fcport; int found; sw_info_t *swl; @@ -3716,6 +4550,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, port_id_t wrap = {}, nxt_d_id; struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev); + unsigned long flags; rval = QLA_SUCCESS; @@ -3736,9 +4571,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, swl = NULL; } else if (qla2x00_gnn_id(vha, swl) != QLA_SUCCESS) { swl = NULL; - } else if (ql2xiidmaenable && - qla2x00_gfpn_id(vha, swl) == QLA_SUCCESS) { - qla2x00_gpsc(vha, swl); + } else if (qla2x00_gfpn_id(vha, swl) != QLA_SUCCESS) { + swl = NULL; } /* If other queries succeeded probe for FC-4 type */ @@ -3800,11 +4634,6 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, ql_log(ql_log_warn, vha, 0x2064, "SNS scan failed -- assuming " "zero-entry result.\n"); - list_for_each_entry_safe(fcport, fcptemp, - new_fcports, list) { - list_del(&fcport->list); - kfree(fcport); - } rval = QLA_SUCCESS; break; } @@ -3847,6 +4676,8 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, new_fcport->fc4_type != FC4_TYPE_UNKNOWN)) continue; + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + /* Locate matching device in database. */ found = 0; list_for_each_entry(fcport, &vha->vp_fcports, list) { @@ -3869,7 +4700,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, */ if (fcport->d_id.b24 == new_fcport->d_id.b24 && (atomic_read(&fcport->state) == FCS_ONLINE || - !qla_ini_mode_enabled(base_vha))) { + (vha->host->active_mode == MODE_TARGET))) { break; } @@ -3889,7 +4720,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, * Log it out if still logged in and mark it for * relogin later. */ - if (!qla_ini_mode_enabled(base_vha)) { + if (qla_tgt_mode_enabled(base_vha)) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080, "port changed FC ID, %8phC" " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n", @@ -3907,25 +4738,19 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, fcport->d_id.b24 = new_fcport->d_id.b24; fcport->flags |= FCF_LOGIN_NEEDED; - if (fcport->loop_id != FC_NO_LOOP_ID && - (fcport->flags & FCF_FCP2_DEVICE) == 0 && - (fcport->flags & FCF_ASYNC_SENT) == 0 && - fcport->port_type != FCT_INITIATOR && - fcport->port_type != FCT_BROADCAST) { - ha->isp_ops->fabric_logout(vha, fcport->loop_id, - fcport->d_id.b.domain, fcport->d_id.b.area, - fcport->d_id.b.al_pa); - qla2x00_clear_loop_id(fcport); - } - break; } - if (found) + if (found) { + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); continue; + } /* If device was not in our fcports list, then add it. */ new_fcport->scan_state = QLA_FCPORT_FOUND; - list_add_tail(&new_fcport->list, new_fcports); + list_add_tail(&new_fcport->list, &vha->vp_fcports); + + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + /* Allocate a new replacement fcport. */ nxt_d_id.b24 = new_fcport->d_id.b24; @@ -3939,8 +4764,44 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha, new_fcport->d_id.b24 = nxt_d_id.b24; } - kfree(new_fcport); + qla2x00_free_fcport(new_fcport); + /* + * Logout all previous fabric dev marked lost, except FCP2 devices. + */ + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) + break; + + if ((fcport->flags & FCF_FABRIC_DEVICE) == 0 || + (fcport->flags & FCF_LOGIN_NEEDED) == 0) + continue; + + if (fcport->scan_state == QLA_FCPORT_SCAN) { + if ((qla_dual_mode_enabled(vha) || + qla_ini_mode_enabled(vha)) && + atomic_read(&fcport->state) == FCS_ONLINE) { + qla2x00_mark_device_lost(vha, fcport, + ql2xplogiabsentdevice, 0); + if (fcport->loop_id != FC_NO_LOOP_ID && + (fcport->flags & FCF_FCP2_DEVICE) == 0 && + fcport->port_type != FCT_INITIATOR && + fcport->port_type != FCT_BROADCAST) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, + fcport->port_name); + + qlt_schedule_sess_for_deletion_lock + (fcport); + continue; + } + } + } + + if (fcport->scan_state == QLA_FCPORT_FOUND) + qla24xx_fcport_handle_login(vha, fcport); + } return (rval); } @@ -3992,64 +4853,6 @@ qla2x00_find_new_loop_id(scsi_qla_host_t *vha, fc_port_t *dev) return (rval); } -/* - * qla2x00_fabric_dev_login - * Login fabric target device and update FC port database. - * - * Input: - * ha: adapter state pointer. - * fcport: port structure list pointer. - * next_loopid: contains value of a new loop ID that can be used - * by the next login attempt. - * - * Returns: - * qla2x00 local function return status code. - * - * Context: - * Kernel context. - */ -static int -qla2x00_fabric_dev_login(scsi_qla_host_t *vha, fc_port_t *fcport, - uint16_t *next_loopid) -{ - int rval; - uint8_t opts; - struct qla_hw_data *ha = vha->hw; - - rval = QLA_SUCCESS; - - if (IS_ALOGIO_CAPABLE(ha)) { - if (fcport->flags & FCF_ASYNC_SENT) - return rval; - fcport->flags |= FCF_ASYNC_SENT; - rval = qla2x00_post_async_login_work(vha, fcport, NULL); - if (!rval) - return rval; - } - - fcport->flags &= ~FCF_ASYNC_SENT; - rval = qla2x00_fabric_login(vha, fcport, next_loopid); - if (rval == QLA_SUCCESS) { - /* Send an ADISC to FCP2 devices.*/ - opts = 0; - if (fcport->flags & FCF_FCP2_DEVICE) - opts |= BIT_1; - rval = qla2x00_get_port_database(vha, fcport, opts); - if (rval != QLA_SUCCESS) { - ha->isp_ops->fabric_logout(vha, fcport->loop_id, - fcport->d_id.b.domain, fcport->d_id.b.area, - fcport->d_id.b.al_pa); - qla2x00_mark_device_lost(vha, fcport, 1, 0); - } else { - qla2x00_update_fcport(vha, fcport); - } - } else { - /* Retry Login. */ - qla2x00_mark_device_lost(vha, fcport, 1, 0); - } - - return (rval); -} /* * qla2x00_fabric_login @@ -4341,13 +5144,6 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha) spin_unlock_irqrestore(&ha->vport_slock, flags); qla2x00_rport_del(fcport); - /* - * Release the target mode FC NEXUS in - * qla_target.c, if target mod is enabled. - */ - qlt_fc_port_deleted(vha, fcport, - base_vha->total_fcport_update_gen); - spin_lock_irqsave(&ha->vport_slock, flags); } } @@ -4730,6 +5526,8 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) if (!(IS_P3P_TYPE(ha))) ha->isp_ops->reset_chip(vha); + ha->chip_reset++; + atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); if (atomic_read(&vha->loop_state) != LOOP_DOWN) { atomic_set(&vha->loop_state, LOOP_DOWN); @@ -4784,8 +5582,6 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) /* Requeue all commands in outstanding command list. */ qla2x00_abort_all_cmds(vha, DID_RESET << 16); } - - ha->chip_reset++; /* memory barrier */ wmb(); } @@ -4981,7 +5777,6 @@ qla2x00_restart_isp(scsi_qla_host_t *vha) if (!status) { /* Issue a marker after FW becomes ready. */ qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL); - set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); } @@ -5209,7 +6004,7 @@ qla24xx_nvram_config(scsi_qla_host_t *vha) rval = 1; } - if (!qla_ini_mode_enabled(vha)) { + if (qla_tgt_mode_enabled(vha)) { /* Don't enable full login after initial LIP */ nv->firmware_options_1 &= cpu_to_le32(~BIT_13); /* Don't enable LIP full login for initiator */ @@ -5400,6 +6195,7 @@ uint8_t qla27xx_find_valid_image(struct scsi_qla_host *vha) for (chksum = 0; cnt--; wptr++) chksum += le32_to_cpu(*wptr); + if (chksum) { ql_dbg(ql_dbg_init, vha, 0x018c, "Checksum validation failed for primary image (0x%x)\n", @@ -6412,6 +7208,10 @@ qla81xx_nvram_config(scsi_qla_host_t *vha) vha->flags.process_response_queue = 1; } + /* enable RIDA Format2 */ + if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) + icb->firmware_options_3 |= BIT_0; + if (rval) { ql_log(ql_log_warn, vha, 0x0076, "NVRAM configuration failed.\n"); @@ -6536,13 +7336,26 @@ qla81xx_update_fw_options(scsi_qla_host_t *vha) __func__, ha->fw_options[2]); } - if (!ql2xetsenable) - goto out; + /* Move PUREX, ABTS RX & RIDA to ATIOQ */ + if (ql2xmvasynctoatio) { + if (qla_tgt_mode_enabled(vha) || + qla_dual_mode_enabled(vha)) + ha->fw_options[2] |= BIT_11; + else + ha->fw_options[2] &= ~BIT_11; + } + + if (ql2xetsenable) { + /* Enable ETS Burst. */ + memset(ha->fw_options, 0, sizeof(ha->fw_options)); + ha->fw_options[2] |= BIT_9; + } + + ql_dbg(ql_dbg_init, vha, 0xffff, + "%s, add FW options 1-3 = 0x%04x 0x%04x 0x%04x mode %x\n", + __func__, ha->fw_options[1], ha->fw_options[2], + ha->fw_options[3], vha->host->active_mode); - /* Enable ETS Burst. */ - memset(ha->fw_options, 0, sizeof(ha->fw_options)); - ha->fw_options[2] |= BIT_9; -out: qla2x00_set_fw_options(vha, ha->fw_options); } @@ -6748,6 +7561,7 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, int v memset(qpair, 0, sizeof(struct qla_qpair)); qpair->hw = vha->hw; + qpair->vha = vha; /* Assign available que pair id */ mutex_lock(&ha->mq_lock); diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 44e404583c86..66df6cec59da 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -166,8 +166,8 @@ qla2x00_set_fcport_state(fc_port_t *fcport, int state) /* Don't print state transitions during initial allocation of fcport */ if (old_state && old_state != state) { ql_dbg(ql_dbg_disc, fcport->vha, 0x207d, - "FCPort state transitioned from %s to %s - " - "portid=%02x%02x%02x.\n", + "FCPort %8phC state transitioned from %s to %s - " + "portid=%02x%02x%02x.\n", fcport->port_name, port_state_str[old_state], port_state_str[state], fcport->d_id.b.domain, fcport->d_id.b.area, fcport->d_id.b.al_pa); @@ -232,6 +232,7 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag) memset(sp, 0, sizeof(*sp)); sp->fcport = fcport; sp->iocbs = 1; + sp->vha = qpair->vha; done: if (!sp) QLA_QPAIR_MARK_NOT_BUSY(qpair); @@ -249,20 +250,20 @@ static inline srb_t * qla2x00_get_sp(scsi_qla_host_t *vha, fc_port_t *fcport, gfp_t flag) { srb_t *sp = NULL; - struct qla_hw_data *ha = vha->hw; uint8_t bail; QLA_VHA_MARK_BUSY(vha, bail); if (unlikely(bail)) return NULL; - sp = mempool_alloc(ha->srb_mempool, flag); + sp = mempool_alloc(vha->hw->srb_mempool, flag); if (!sp) goto done; memset(sp, 0, sizeof(*sp)); sp->fcport = fcport; sp->iocbs = 1; + sp->vha = vha; done: if (!sp) QLA_VHA_MARK_NOT_BUSY(vha); @@ -270,10 +271,10 @@ done: } static inline void -qla2x00_rel_sp(scsi_qla_host_t *vha, srb_t *sp) +qla2x00_rel_sp(srb_t *sp) { - mempool_free(sp, vha->hw->srb_mempool); - QLA_VHA_MARK_NOT_BUSY(vha); + QLA_VHA_MARK_NOT_BUSY(sp->vha); + mempool_free(sp, sp->vha->hw->srb_mempool); } static inline void @@ -285,8 +286,7 @@ qla2x00_init_timer(srb_t *sp, unsigned long tmo) sp->u.iocb_cmd.timer.function = qla2x00_sp_timeout; add_timer(&sp->u.iocb_cmd.timer); sp->free = qla2x00_sp_free; - if ((IS_QLAFX00(sp->fcport->vha->hw)) && - (sp->type == SRB_FXIOCB_DCMD)) + if (IS_QLAFX00(sp->vha->hw) && (sp->type == SRB_FXIOCB_DCMD)) init_completion(&sp->u.iocb_cmd.u.fxiocb.fxiocb_comp); if (sp->type == SRB_ELS_DCMD) init_completion(&sp->u.iocb_cmd.u.els_logo.comp); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 58e49a3e1de8..535079280288 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -23,7 +23,7 @@ qla2x00_get_cmd_direction(srb_t *sp) { uint16_t cflags; struct scsi_cmnd *cmd = GET_CMD_SP(sp); - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; cflags = 0; @@ -210,7 +210,7 @@ void qla2x00_build_scsi_iocbs_32(srb_t *sp, cmd_entry_t *cmd_pkt, return; } - vha = sp->fcport->vha; + vha = sp->vha; cmd_pkt->control_flags |= cpu_to_le16(qla2x00_get_cmd_direction(sp)); /* Three DSDs are available in the Command Type 2 IOCB */ @@ -267,7 +267,7 @@ void qla2x00_build_scsi_iocbs_64(srb_t *sp, cmd_entry_t *cmd_pkt, return; } - vha = sp->fcport->vha; + vha = sp->vha; cmd_pkt->control_flags |= cpu_to_le16(qla2x00_get_cmd_direction(sp)); /* Two DSDs are available in the Command Type 3 IOCB */ @@ -324,7 +324,7 @@ qla2x00_start_scsi(srb_t *sp) struct rsp_que *rsp; /* Setup device pointers. */ - vha = sp->fcport->vha; + vha = sp->vha; ha = vha->hw; reg = &ha->iobase->isp; cmd = GET_CMD_SP(sp); @@ -601,7 +601,7 @@ qla24xx_build_scsi_type_6_iocbs(srb_t *sp, struct cmd_type_6 *cmd_pkt, return 0; } - vha = sp->fcport->vha; + vha = sp->vha; ha = vha->hw; /* Set transfer direction */ @@ -716,7 +716,7 @@ qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt, return; } - vha = sp->fcport->vha; + vha = sp->vha; /* Set transfer direction */ if (cmd->sc_data_direction == DMA_TO_DEVICE) { @@ -1108,7 +1108,7 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp, if (sp) { cmd = GET_CMD_SP(sp); sgl = scsi_prot_sglist(cmd); - vha = sp->fcport->vha; + vha = sp->vha; } else if (tc) { vha = tc->vha; sgl = tc->prot_sg; @@ -1215,7 +1215,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt, /* Update entry type to indicate Command Type CRC_2 IOCB */ *((uint32_t *)(&cmd_pkt->entry_type)) = cpu_to_le32(COMMAND_TYPE_CRC_2); - vha = sp->fcport->vha; + vha = sp->vha; ha = vha->hw; /* No data transfer */ @@ -1225,7 +1225,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt, return QLA_SUCCESS; } - cmd_pkt->vp_index = sp->fcport->vha->vp_idx; + cmd_pkt->vp_index = sp->vha->vp_idx; /* Set transfer direction */ if (cmd->sc_data_direction == DMA_TO_DEVICE) { @@ -1415,7 +1415,7 @@ qla24xx_start_scsi(srb_t *sp) struct req_que *req = NULL; struct rsp_que *rsp = NULL; struct scsi_cmnd *cmd = GET_CMD_SP(sp); - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct qla_hw_data *ha = vha->hw; /* Setup device pointers. */ @@ -1492,7 +1492,7 @@ qla24xx_start_scsi(srb_t *sp) cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa; cmd_pkt->port_id[1] = sp->fcport->d_id.b.area; cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain; - cmd_pkt->vp_index = sp->fcport->vha->vp_idx; + cmd_pkt->vp_index = sp->vha->vp_idx; int_to_scsilun(cmd->device->lun, &cmd_pkt->lun); host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, sizeof(cmd_pkt->lun)); @@ -1564,7 +1564,7 @@ qla24xx_dif_start_scsi(srb_t *sp) struct req_que *req = NULL; struct rsp_que *rsp = NULL; struct scsi_cmnd *cmd = GET_CMD_SP(sp); - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct qla_hw_data *ha = vha->hw; struct cmd_type_crc_2 *cmd_pkt; uint32_t status = 0; @@ -2214,13 +2214,13 @@ qla24xx_login_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->port_id[0] = sp->fcport->d_id.b.al_pa; logio->port_id[1] = sp->fcport->d_id.b.area; logio->port_id[2] = sp->fcport->d_id.b.domain; - logio->vp_index = sp->fcport->vha->vp_idx; + logio->vp_index = sp->vha->vp_idx; } static void qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx) { - struct qla_hw_data *ha = sp->fcport->vha->hw; + struct qla_hw_data *ha = sp->vha->hw; struct srb_iocb *lio = &sp->u.iocb_cmd; uint16_t opts; @@ -2238,7 +2238,7 @@ qla2x00_login_iocb(srb_t *sp, struct mbx_entry *mbx) mbx->mb2 = cpu_to_le16(sp->fcport->d_id.b.domain); mbx->mb3 = cpu_to_le16(sp->fcport->d_id.b.area << 8 | sp->fcport->d_id.b.al_pa); - mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx); + mbx->mb9 = cpu_to_le16(sp->vha->vp_idx); } static void @@ -2247,20 +2247,20 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->entry_type = LOGINOUT_PORT_IOCB_TYPE; logio->control_flags = cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO); - if (!sp->fcport->tgt_session || - !sp->fcport->tgt_session->keep_nport_handle) + if (!sp->fcport->se_sess || + !sp->fcport->keep_nport_handle) logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT); logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); logio->port_id[0] = sp->fcport->d_id.b.al_pa; logio->port_id[1] = sp->fcport->d_id.b.area; logio->port_id[2] = sp->fcport->d_id.b.domain; - logio->vp_index = sp->fcport->vha->vp_idx; + logio->vp_index = sp->vha->vp_idx; } static void qla2x00_logout_iocb(srb_t *sp, struct mbx_entry *mbx) { - struct qla_hw_data *ha = sp->fcport->vha->hw; + struct qla_hw_data *ha = sp->vha->hw; mbx->entry_type = MBX_IOCB_TYPE; SET_TARGET_ID(ha, mbx->loop_id, sp->fcport->loop_id); @@ -2271,7 +2271,7 @@ qla2x00_logout_iocb(srb_t *sp, struct mbx_entry *mbx) mbx->mb2 = cpu_to_le16(sp->fcport->d_id.b.domain); mbx->mb3 = cpu_to_le16(sp->fcport->d_id.b.area << 8 | sp->fcport->d_id.b.al_pa); - mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx); + mbx->mb9 = cpu_to_le16(sp->vha->vp_idx); /* Implicit: mbx->mbx10 = 0. */ } @@ -2281,13 +2281,13 @@ qla24xx_adisc_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->entry_type = LOGINOUT_PORT_IOCB_TYPE; logio->control_flags = cpu_to_le16(LCF_COMMAND_ADISC); logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); - logio->vp_index = sp->fcport->vha->vp_idx; + logio->vp_index = sp->vha->vp_idx; } static void qla2x00_adisc_iocb(srb_t *sp, struct mbx_entry *mbx) { - struct qla_hw_data *ha = sp->fcport->vha->hw; + struct qla_hw_data *ha = sp->vha->hw; mbx->entry_type = MBX_IOCB_TYPE; SET_TARGET_ID(ha, mbx->loop_id, sp->fcport->loop_id); @@ -2302,7 +2302,7 @@ qla2x00_adisc_iocb(srb_t *sp, struct mbx_entry *mbx) mbx->mb3 = cpu_to_le16(LSW(ha->async_pd_dma)); mbx->mb6 = cpu_to_le16(MSW(MSD(ha->async_pd_dma))); mbx->mb7 = cpu_to_le16(LSW(MSD(ha->async_pd_dma))); - mbx->mb9 = cpu_to_le16(sp->fcport->vha->vp_idx); + mbx->mb9 = cpu_to_le16(sp->vha->vp_idx); } static void @@ -2338,32 +2338,30 @@ qla24xx_tm_iocb(srb_t *sp, struct tsk_mgmt_entry *tsk) } static void -qla2x00_els_dcmd_sp_free(void *ptr, void *data) +qla2x00_els_dcmd_sp_free(void *data) { - struct scsi_qla_host *vha = (scsi_qla_host_t *)ptr; - struct qla_hw_data *ha = vha->hw; - srb_t *sp = (srb_t *)data; + srb_t *sp = data; struct srb_iocb *elsio = &sp->u.iocb_cmd; kfree(sp->fcport); if (elsio->u.els_logo.els_logo_pyld) - dma_free_coherent(&ha->pdev->dev, DMA_POOL_SIZE, + dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE, elsio->u.els_logo.els_logo_pyld, elsio->u.els_logo.els_logo_pyld_dma); del_timer(&elsio->timer); - qla2x00_rel_sp(vha, sp); + qla2x00_rel_sp(sp); } static void qla2x00_els_dcmd_iocb_timeout(void *data) { - srb_t *sp = (srb_t *)data; - struct srb_iocb *lio = &sp->u.iocb_cmd; + srb_t *sp = data; fc_port_t *fcport = sp->fcport; - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct qla_hw_data *ha = vha->hw; + struct srb_iocb *lio = &sp->u.iocb_cmd; unsigned long flags = 0; ql_dbg(ql_dbg_io, vha, 0x3069, @@ -2386,12 +2384,12 @@ qla2x00_els_dcmd_iocb_timeout(void *data) } static void -qla2x00_els_dcmd_sp_done(void *data, void *ptr, int res) +qla2x00_els_dcmd_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; fc_port_t *fcport = sp->fcport; struct srb_iocb *lio = &sp->u.iocb_cmd; - struct scsi_qla_host *vha = fcport->vha; + struct scsi_qla_host *vha = sp->vha; ql_dbg(ql_dbg_io, vha, 0x3072, "%s hdl=%x, portid=%02x%02x%02x done\n", @@ -2449,7 +2447,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, GFP_KERNEL); if (!elsio->u.els_logo.els_logo_pyld) { - sp->free(vha, sp); + sp->free(sp); return QLA_FUNCTION_FAILED; } @@ -2468,7 +2466,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { - sp->free(vha, sp); + sp->free(sp); return QLA_FUNCTION_FAILED; } @@ -2479,14 +2477,14 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, wait_for_completion(&elsio->u.els_logo.comp); - sp->free(vha, sp); + sp->free(sp); return rval; } static void qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) { - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct srb_iocb *elsio = &sp->u.iocb_cmd; els_iocb->entry_type = ELS_IOCB_TYPE; @@ -2518,7 +2516,7 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) els_iocb->rx_address[1] = 0; els_iocb->rx_len = 0; - sp->fcport->vha->qla_stats.control_requests++; + sp->vha->qla_stats.control_requests++; } static void @@ -2534,7 +2532,7 @@ qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) els_iocb->handle = sp->handle; els_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id); els_iocb->tx_dsd_count = cpu_to_le16(bsg_job->request_payload.sg_cnt); - els_iocb->vp_index = sp->fcport->vha->vp_idx; + els_iocb->vp_index = sp->vha->vp_idx; els_iocb->sof_type = EST_SOFI3; els_iocb->rx_dsd_count = cpu_to_le16(bsg_job->reply_payload.sg_cnt); @@ -2565,7 +2563,7 @@ qla24xx_els_iocb(srb_t *sp, struct els_entry_24xx *els_iocb) els_iocb->rx_len = cpu_to_le32(sg_dma_len (bsg_job->reply_payload.sg_list)); - sp->fcport->vha->qla_stats.control_requests++; + sp->vha->qla_stats.control_requests++; } static void @@ -2576,7 +2574,7 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb) struct scatterlist *sg; int index; uint16_t tot_dsds; - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct qla_hw_data *ha = vha->hw; struct bsg_job *bsg_job = sp->u.bsg_job; int loop_iterartion = 0; @@ -2642,7 +2640,7 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb) } ct_iocb->entry_count = entry_count; - sp->fcport->vha->qla_stats.control_requests++; + sp->vha->qla_stats.control_requests++; } static void @@ -2653,7 +2651,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb) struct scatterlist *sg; int index; uint16_t tot_dsds; - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct qla_hw_data *ha = vha->hw; struct bsg_job *bsg_job = sp->u.bsg_job; int loop_iterartion = 0; @@ -2665,7 +2663,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb) ct_iocb->handle = sp->handle; ct_iocb->nport_handle = cpu_to_le16(sp->fcport->loop_id); - ct_iocb->vp_index = sp->fcport->vha->vp_idx; + ct_iocb->vp_index = sp->vha->vp_idx; ct_iocb->comp_status = cpu_to_le16(0); ct_iocb->cmd_dsd_count = @@ -2739,7 +2737,7 @@ qla82xx_start_scsi(srb_t *sp) uint32_t *fcp_dl; uint8_t additional_cdb_len; struct ct6_dsd *ctx; - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct qla_hw_data *ha = vha->hw; struct req_que *req = NULL; struct rsp_que *rsp = NULL; @@ -2901,7 +2899,7 @@ sufficient_dsds: cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa; cmd_pkt->port_id[1] = sp->fcport->d_id.b.area; cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain; - cmd_pkt->vp_index = sp->fcport->vha->vp_idx; + cmd_pkt->vp_index = sp->vha->vp_idx; /* Build IOCB segments */ if (qla24xx_build_scsi_type_6_iocbs(sp, cmd_pkt, tot_dsds)) @@ -2974,7 +2972,7 @@ sufficient_dsds: cmd_pkt->port_id[0] = sp->fcport->d_id.b.al_pa; cmd_pkt->port_id[1] = sp->fcport->d_id.b.area; cmd_pkt->port_id[2] = sp->fcport->d_id.b.domain; - cmd_pkt->vp_index = sp->fcport->vha->vp_idx; + cmd_pkt->vp_index = sp->vha->vp_idx; int_to_scsilun(cmd->device->lun, &cmd_pkt->lun); host_to_fcp_swap((uint8_t *)&cmd_pkt->lun, @@ -3060,7 +3058,7 @@ static void qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb) { struct srb_iocb *aio = &sp->u.iocb_cmd; - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct req_que *req = vha->req; memset(abt_iocb, 0, sizeof(struct abort_entry_24xx)); @@ -3079,19 +3077,69 @@ qla24xx_abort_iocb(srb_t *sp, struct abort_entry_24xx *abt_iocb) wmb(); } +static void +qla2x00_mb_iocb(srb_t *sp, struct mbx_24xx_entry *mbx) +{ + int i, sz; + + mbx->entry_type = MBX_IOCB_TYPE; + mbx->handle = sp->handle; + sz = min(ARRAY_SIZE(mbx->mb), ARRAY_SIZE(sp->u.iocb_cmd.u.mbx.out_mb)); + + for (i = 0; i < sz; i++) + mbx->mb[i] = cpu_to_le16(sp->u.iocb_cmd.u.mbx.out_mb[i]); +} + +static void +qla2x00_ctpthru_cmd_iocb(srb_t *sp, struct ct_entry_24xx *ct_pkt) +{ + sp->u.iocb_cmd.u.ctarg.iocb = ct_pkt; + qla24xx_prep_ms_iocb(sp->vha, &sp->u.iocb_cmd.u.ctarg); + ct_pkt->handle = sp->handle; +} + +static void qla2x00_send_notify_ack_iocb(srb_t *sp, + struct nack_to_isp *nack) +{ + struct imm_ntfy_from_isp *ntfy = sp->u.iocb_cmd.u.nack.ntfy; + + nack->entry_type = NOTIFY_ACK_TYPE; + nack->entry_count = 1; + nack->ox_id = ntfy->ox_id; + + nack->u.isp24.handle = sp->handle; + nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle; + if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) { + nack->u.isp24.flags = ntfy->u.isp24.flags & + cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB); + } + nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id; + nack->u.isp24.status = ntfy->u.isp24.status; + nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode; + nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle; + nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address; + nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs; + nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui; + nack->u.isp24.srr_flags = 0; + nack->u.isp24.srr_reject_code = 0; + nack->u.isp24.srr_reject_code_expl = 0; + nack->u.isp24.vp_index = ntfy->u.isp24.vp_index; +} + int qla2x00_start_sp(srb_t *sp) { int rval; - struct qla_hw_data *ha = sp->fcport->vha->hw; + scsi_qla_host_t *vha = sp->vha; + struct qla_hw_data *ha = vha->hw; void *pkt; unsigned long flags; rval = QLA_FUNCTION_FAILED; spin_lock_irqsave(&ha->hardware_lock, flags); - pkt = qla2x00_alloc_iocbs(sp->fcport->vha, sp); + pkt = qla2x00_alloc_iocbs(vha, sp); if (!pkt) { - ql_log(ql_log_warn, sp->fcport->vha, 0x700c, + ql_log(ql_log_warn, vha, 0x700c, "qla2x00_alloc_iocbs failed.\n"); goto done; } @@ -3139,12 +3187,23 @@ qla2x00_start_sp(srb_t *sp) case SRB_ELS_DCMD: qla24xx_els_logo_iocb(sp, pkt); break; + case SRB_CT_PTHRU_CMD: + qla2x00_ctpthru_cmd_iocb(sp, pkt); + break; + case SRB_MB_IOCB: + qla2x00_mb_iocb(sp, pkt); + break; + case SRB_NACK_PLOGI: + case SRB_NACK_PRLI: + case SRB_NACK_LOGO: + qla2x00_send_notify_ack_iocb(sp, pkt); + break; default: break; } wmb(); - qla2x00_start_iocbs(sp->fcport->vha, ha->req_q_map[0]); + qla2x00_start_iocbs(vha, ha->req_q_map[0]); done: spin_unlock_irqrestore(&ha->hardware_lock, flags); return rval; diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index edc2264db45b..352cfb6292c6 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -561,14 +561,50 @@ qla2x00_is_a_vp_did(scsi_qla_host_t *vha, uint32_t rscn_entry) return ret; } -static inline fc_port_t * +fc_port_t * qla2x00_find_fcport_by_loopid(scsi_qla_host_t *vha, uint16_t loop_id) { - fc_port_t *fcport; + fc_port_t *f, *tf; + + f = tf = NULL; + list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) + if (f->loop_id == loop_id) + return f; + return NULL; +} - list_for_each_entry(fcport, &vha->vp_fcports, list) - if (fcport->loop_id == loop_id) - return fcport; +fc_port_t * +qla2x00_find_fcport_by_wwpn(scsi_qla_host_t *vha, u8 *wwpn, u8 incl_deleted) +{ + fc_port_t *f, *tf; + + f = tf = NULL; + list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) { + if (memcmp(f->port_name, wwpn, WWN_SIZE) == 0) { + if (incl_deleted) + return f; + else if (f->deleted == 0) + return f; + } + } + return NULL; +} + +fc_port_t * +qla2x00_find_fcport_by_nportid(scsi_qla_host_t *vha, port_id_t *id, + u8 incl_deleted) +{ + fc_port_t *f, *tf; + + f = tf = NULL; + list_for_each_entry_safe(f, tf, &vha->vp_fcports, list) { + if (f->d_id.b24 == id->b24) { + if (incl_deleted) + return f; + else if (f->deleted == 0) + return f; + } + } return NULL; } @@ -934,7 +970,11 @@ skip_rio: ql_dbg(ql_dbg_async, vha, 0x508a, "Marking port lost loopid=%04x portid=%06x.\n", fcport->loop_id, fcport->d_id.b24); - qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1); + if (qla_ini_mode_enabled(vha)) { + qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1); + fcport->logout_on_delete = 0; + qlt_schedule_sess_for_deletion_lock(fcport); + } break; global_port_update: @@ -985,9 +1025,6 @@ global_port_update: qla2x00_mark_all_devices_lost(vha, 1); - if (vha->vp_idx == 0 && !qla_ini_mode_enabled(vha)) - set_bit(SCR_PENDING, &vha->dpc_flags); - set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); set_bit(VP_CONFIG_OK, &vha->vp_flags); @@ -1024,27 +1061,19 @@ global_port_update: if (qla2x00_is_a_vp_did(vha, rscn_entry)) break; - /* - * Search for the rport related to this RSCN entry and mark it - * as lost. - */ - list_for_each_entry(fcport, &vha->vp_fcports, list) { - if (atomic_read(&fcport->state) != FCS_ONLINE) - continue; - if (fcport->d_id.b24 == rscn_entry) { - qla2x00_mark_device_lost(vha, fcport, 0, 0); - break; - } - } - atomic_set(&vha->loop_down_timer, 0); vha->flags.management_server_logged_in = 0; - - set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); - set_bit(RSCN_UPDATE, &vha->dpc_flags); - qla2x00_post_aen_work(vha, FCH_EVT_RSCN, rscn_entry); + { + struct event_arg ea; + + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_RSCN; + ea.id.b24 = rscn_entry; + ea.id.b.rsvd_1 = rscn_entry >> 24; + qla2x00_fcport_event_handler(vha, &ea); + qla2x00_post_aen_work(vha, FCH_EVT_RSCN, rscn_entry); + } break; - /* case MBA_RIO_RESPONSE: */ case MBA_ZIO_RESPONSE: ql_dbg(ql_dbg_async, vha, 0x5015, @@ -1212,7 +1241,7 @@ qla2x00_process_completed_request(struct scsi_qla_host *vha, req->outstanding_cmds[index] = NULL; /* Save ISP completion status */ - sp->done(ha, sp, DID_OK << 16); + sp->done(sp, DID_OK << 16); } else { ql_log(ql_log_warn, vha, 0x3016, "Invalid SCSI SRB.\n"); @@ -1235,7 +1264,8 @@ qla2x00_get_sp_from_handle(scsi_qla_host_t *vha, const char *func, index = LSW(pkt->handle); if (index >= req->num_outstanding_cmds) { ql_log(ql_log_warn, vha, 0x5031, - "Invalid command index (%x).\n", index); + "Invalid command index (%x) type %8ph.\n", + index, iocb); if (IS_P3P_TYPE(ha)) set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags); else @@ -1343,66 +1373,122 @@ qla2x00_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, le16_to_cpu(mbx->mb7)); logio_done: - sp->done(vha, sp, 0); + sp->done(sp, 0); } static void -qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req, - sts_entry_t *pkt, int iocb_type) +qla24xx_mbx_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, + struct mbx_24xx_entry *pkt) { - const char func[] = "CT_IOCB"; - const char *type; + const char func[] = "MBX-IOCB2"; srb_t *sp; - struct bsg_job *bsg_job; - struct fc_bsg_reply *bsg_reply; - uint16_t comp_status; + struct srb_iocb *si; + u16 sz, i; int res; sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); if (!sp) return; - bsg_job = sp->u.bsg_job; - bsg_reply = bsg_job->reply; + si = &sp->u.iocb_cmd; + sz = min(ARRAY_SIZE(pkt->mb), ARRAY_SIZE(sp->u.iocb_cmd.u.mbx.in_mb)); - type = "ct pass-through"; + for (i = 0; i < sz; i++) + si->u.mbx.in_mb[i] = le16_to_cpu(pkt->mb[i]); - comp_status = le16_to_cpu(pkt->comp_status); + res = (si->u.mbx.in_mb[0] & MBS_MASK); - /* return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT - * fc payload to the caller - */ - bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK; - bsg_job->reply_len = sizeof(struct fc_bsg_reply); + sp->done(sp, res); +} - if (comp_status != CS_COMPLETE) { - if (comp_status == CS_DATA_UNDERRUN) { - res = DID_OK << 16; - bsg_reply->reply_payload_rcv_len = - le16_to_cpu(((sts_entry_t *)pkt)->rsp_info_len); +static void +qla24xxx_nack_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, + struct nack_to_isp *pkt) +{ + const char func[] = "nack"; + srb_t *sp; + int res = 0; - ql_log(ql_log_warn, vha, 0x5048, - "CT pass-through-%s error " - "comp_status-status=0x%x total_byte = 0x%x.\n", - type, comp_status, - bsg_reply->reply_payload_rcv_len); - } else { - ql_log(ql_log_warn, vha, 0x5049, - "CT pass-through-%s error " - "comp_status-status=0x%x.\n", type, comp_status); - res = DID_ERROR << 16; - bsg_reply->reply_payload_rcv_len = 0; - } - ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5035, - (uint8_t *)pkt, sizeof(*pkt)); - } else { - res = DID_OK << 16; - bsg_reply->reply_payload_rcv_len = - bsg_job->reply_payload.payload_len; - bsg_job->reply_len = 0; - } + sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); + if (!sp) + return; + + if (pkt->u.isp2x.status != cpu_to_le16(NOTIFY_ACK_SUCCESS)) + res = QLA_FUNCTION_FAILED; - sp->done(vha, sp, res); + sp->done(sp, res); +} + +static void +qla2x00_ct_entry(scsi_qla_host_t *vha, struct req_que *req, + sts_entry_t *pkt, int iocb_type) +{ + const char func[] = "CT_IOCB"; + const char *type; + srb_t *sp; + struct bsg_job *bsg_job; + struct fc_bsg_reply *bsg_reply; + uint16_t comp_status; + int res = 0; + + sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); + if (!sp) + return; + + switch (sp->type) { + case SRB_CT_CMD: + bsg_job = sp->u.bsg_job; + bsg_reply = bsg_job->reply; + + type = "ct pass-through"; + + comp_status = le16_to_cpu(pkt->comp_status); + + /* + * return FC_CTELS_STATUS_OK and leave the decoding of the ELS/CT + * fc payload to the caller + */ + bsg_reply->reply_data.ctels_reply.status = FC_CTELS_STATUS_OK; + bsg_job->reply_len = sizeof(struct fc_bsg_reply); + + if (comp_status != CS_COMPLETE) { + if (comp_status == CS_DATA_UNDERRUN) { + res = DID_OK << 16; + bsg_reply->reply_payload_rcv_len = + le16_to_cpu(((sts_entry_t *)pkt)->rsp_info_len); + + ql_log(ql_log_warn, vha, 0x5048, + "CT pass-through-%s error comp_status=0x%x total_byte=0x%x.\n", + type, comp_status, + bsg_reply->reply_payload_rcv_len); + } else { + ql_log(ql_log_warn, vha, 0x5049, + "CT pass-through-%s error comp_status=0x%x.\n", + type, comp_status); + res = DID_ERROR << 16; + bsg_reply->reply_payload_rcv_len = 0; + } + ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5035, + (uint8_t *)pkt, sizeof(*pkt)); + } else { + res = DID_OK << 16; + bsg_reply->reply_payload_rcv_len = + bsg_job->reply_payload.payload_len; + bsg_job->reply_len = 0; + } + break; + case SRB_CT_PTHRU_CMD: + /* + * borrowing sts_entry_24xx.comp_status. + * same location as ct_entry_24xx.comp_status + */ + res = qla2x00_chk_ms_status(vha, (ms_iocb_entry_t *)pkt, + (struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp, + sp->name); + break; + } + + sp->done(sp, res); } static void @@ -1438,7 +1524,16 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, type = "Driver ELS logo"; ql_dbg(ql_dbg_user, vha, 0x5047, "Completing %s: (%p) type=%d.\n", type, sp, sp->type); - sp->done(vha, sp, 0); + sp->done(sp, 0); + return; + case SRB_CT_PTHRU_CMD: + /* borrowing sts_entry_24xx.comp_status. + same location as ct_entry_24xx.comp_status + */ + res = qla2x00_chk_ms_status(vha, (ms_iocb_entry_t *)pkt, + (struct ct_sns_rsp *)sp->u.iocb_cmd.u.ctarg.rsp, + sp->name); + sp->done(sp, res); return; default: ql_dbg(ql_dbg_user, vha, 0x503e, @@ -1496,7 +1591,7 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, bsg_job->reply_len = 0; } - sp->done(vha, sp, res); + sp->done(sp, res); } static void @@ -1543,6 +1638,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, fcport->d_id.b.area, fcport->d_id.b.al_pa, le32_to_cpu(logio->io_parameter[0])); + vha->hw->exch_starvation = 0; data[0] = MBS_COMMAND_COMPLETE; if (sp->type != SRB_LOGIN_CMD) goto logio_done; @@ -1568,6 +1664,8 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, iop[0] = le32_to_cpu(logio->io_parameter[0]); iop[1] = le32_to_cpu(logio->io_parameter[1]); + lio->u.logio.iop[0] = iop[0]; + lio->u.logio.iop[1] = iop[1]; switch (iop[0]) { case LSC_SCODE_PORTID_USED: data[0] = MBS_PORT_ID_USED; @@ -1576,6 +1674,21 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, case LSC_SCODE_NPORT_USED: data[0] = MBS_LOOP_ID_USED; break; + case LSC_SCODE_NOXCB: + vha->hw->exch_starvation++; + if (vha->hw->exch_starvation > 5) { + ql_log(ql_log_warn, vha, 0xffff, + "Exchange starvation. Resetting RISC\n"); + + vha->hw->exch_starvation = 0; + + if (IS_P3P_TYPE(vha->hw)) + set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags); + else + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + } + /* drop through */ default: data[0] = MBS_COMMAND_ERROR; break; @@ -1590,7 +1703,7 @@ qla24xx_logio_entry(scsi_qla_host_t *vha, struct req_que *req, le32_to_cpu(logio->io_parameter[1])); logio_done: - sp->done(vha, sp, 0); + sp->done(sp, 0); } static void @@ -1640,7 +1753,7 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk) ql_dump_buffer(ql_dbg_async + ql_dbg_buffer, vha, 0x5055, (uint8_t *)sts, sizeof(*sts)); - sp->done(vha, sp, 0); + sp->done(sp, 0); } /** @@ -1728,7 +1841,7 @@ static inline void qla2x00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len, uint32_t sense_len, struct rsp_que *rsp, int res) { - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct scsi_cmnd *cp = GET_CMD_SP(sp); uint32_t track_sense_len; @@ -1756,7 +1869,7 @@ qla2x00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len, if (sense_len) { ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x301c, "Check condition Sense data, nexus%ld:%d:%llu cmd=%p.\n", - sp->fcport->vha->host_no, cp->device->id, cp->device->lun, + sp->vha->host_no, cp->device->id, cp->device->lun, cp); ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x302b, cp->sense_buffer, sense_len); @@ -1778,7 +1891,7 @@ struct scsi_dif_tuple { static inline int qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24) { - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct scsi_cmnd *cmd = GET_CMD_SP(sp); uint8_t *ap = &sts24->data[12]; uint8_t *ep = &sts24->data[20]; @@ -2043,7 +2156,7 @@ done: bsg_job->reply_len = sizeof(struct fc_bsg_reply); /* Always return DID_OK, bsg will send the vendor specific response * in this case only */ - sp->done(vha, sp, (DID_OK << 6)); + sp->done(sp, DID_OK << 6); } @@ -2076,6 +2189,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt) int res = 0; uint16_t state_flags = 0; uint16_t retry_delay = 0; + uint8_t no_logout = 0; sts = (sts_entry_t *) pkt; sts24 = (struct sts_entry_24xx *) pkt; @@ -2336,6 +2450,7 @@ check_scsi_status: break; case CS_PORT_LOGGED_OUT: + no_logout = 1; case CS_PORT_CONFIG_CHG: case CS_PORT_BUSY: case CS_INCOMPLETE: @@ -2358,14 +2473,21 @@ check_scsi_status: break; } - ql_dbg(ql_dbg_io, fcport->vha, 0x3021, - "Port to be marked lost on fcport=%02x%02x%02x, current " - "port state= %s.\n", fcport->d_id.b.domain, - fcport->d_id.b.area, fcport->d_id.b.al_pa, - port_state_str[atomic_read(&fcport->state)]); + if (atomic_read(&fcport->state) == FCS_ONLINE) { + ql_dbg(ql_dbg_disc, fcport->vha, 0x3021, + "Port to be marked lost on fcport=%02x%02x%02x, current " + "port state= %s comp_status %x.\n", fcport->d_id.b.domain, + fcport->d_id.b.area, fcport->d_id.b.al_pa, + port_state_str[atomic_read(&fcport->state)], + comp_status); + + if (no_logout) + fcport->logout_on_delete = 0; - if (atomic_read(&fcport->state) == FCS_ONLINE) qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1); + qlt_schedule_sess_for_deletion_lock(fcport); + } + break; case CS_ABORTED: @@ -2407,7 +2529,7 @@ out: resid_len, fw_resid_len, sp, cp); if (rsp->status_srb == NULL) - sp->done(ha, sp, res); + sp->done(sp, res); } /** @@ -2464,7 +2586,7 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) /* Place command on done queue. */ if (sense_len == 0) { rsp->status_srb = NULL; - sp->done(ha, sp, cp->result); + sp->done(sp, cp->result); } } @@ -2500,7 +2622,7 @@ qla2x00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sts_entry_t *pkt) sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); if (sp) { - sp->done(ha, sp, res); + sp->done(sp, res); return; } fatal: @@ -2558,7 +2680,7 @@ qla24xx_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, abt = &sp->u.iocb_cmd; abt->u.abt.comp_status = le32_to_cpu(pkt->nport_handle); - sp->done(vha, sp, 0); + sp->done(sp, 0); } /** @@ -2629,10 +2751,16 @@ process_err: } case ABTS_RESP_24XX: case CTIO_TYPE7: - case NOTIFY_ACK_TYPE: case CTIO_CRC2: qlt_response_pkt_all_vps(vha, (response_t *)pkt); break; + case NOTIFY_ACK_TYPE: + if (pkt->handle == QLA_TGT_SKIP_HANDLE) + qlt_response_pkt_all_vps(vha, (response_t *)pkt); + else + qla24xxx_nack_iocb_entry(vha, rsp->req, + (struct nack_to_isp *)pkt); + break; case MARKER_TYPE: /* Do nothing in this case, this check is to prevent it * from falling into default case @@ -2642,6 +2770,10 @@ process_err: qla24xx_abort_iocb_entry(vha, rsp->req, (struct abort_entry_24xx *)pkt); break; + case MBX_IOCB_TYPE: + qla24xx_mbx_iocb_entry(vha, rsp->req, + (struct mbx_24xx_entry *)pkt); + break; default: /* Type Not Supported. */ ql_dbg(ql_dbg_async, vha, 0x5042, @@ -2658,8 +2790,9 @@ process_err: if (IS_P3P_TYPE(ha)) { struct device_reg_82xx __iomem *reg = &ha->iobase->isp82; WRT_REG_DWORD(®->rsp_q_out[0], rsp->ring_index); - } else + } else { WRT_REG_DWORD(rsp->rsp_q_out, rsp->ring_index); + } } static void diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 67f64db390b0..35079f417417 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -1637,94 +1637,6 @@ qla2x00_init_firmware(scsi_qla_host_t *vha, uint16_t size) return rval; } -/* - * qla2x00_get_node_name_list - * Issue get node name list mailbox command, kmalloc() - * and return the resulting list. Caller must kfree() it! - * - * Input: - * ha = adapter state pointer. - * out_data = resulting list - * out_len = length of the resulting list - * - * Returns: - * qla2x00 local function return status code. - * - * Context: - * Kernel context. - */ -int -qla2x00_get_node_name_list(scsi_qla_host_t *vha, void **out_data, int *out_len) -{ - struct qla_hw_data *ha = vha->hw; - struct qla_port_24xx_data *list = NULL; - void *pmap; - mbx_cmd_t mc; - dma_addr_t pmap_dma; - ulong dma_size; - int rval, left; - - left = 1; - while (left > 0) { - dma_size = left * sizeof(*list); - pmap = dma_alloc_coherent(&ha->pdev->dev, dma_size, - &pmap_dma, GFP_KERNEL); - if (!pmap) { - ql_log(ql_log_warn, vha, 0x113f, - "%s(%ld): DMA Alloc failed of %ld\n", - __func__, vha->host_no, dma_size); - rval = QLA_MEMORY_ALLOC_FAILED; - goto out; - } - - mc.mb[0] = MBC_PORT_NODE_NAME_LIST; - mc.mb[1] = BIT_1 | BIT_3; - mc.mb[2] = MSW(pmap_dma); - mc.mb[3] = LSW(pmap_dma); - mc.mb[6] = MSW(MSD(pmap_dma)); - mc.mb[7] = LSW(MSD(pmap_dma)); - mc.mb[8] = dma_size; - mc.out_mb = MBX_0|MBX_1|MBX_2|MBX_3|MBX_6|MBX_7|MBX_8; - mc.in_mb = MBX_0|MBX_1; - mc.tov = 30; - mc.flags = MBX_DMA_IN; - - rval = qla2x00_mailbox_command(vha, &mc); - if (rval != QLA_SUCCESS) { - if ((mc.mb[0] == MBS_COMMAND_ERROR) && - (mc.mb[1] == 0xA)) { - left += le16_to_cpu(mc.mb[2]) / - sizeof(struct qla_port_24xx_data); - goto restart; - } - goto out_free; - } - - left = 0; - - list = kmemdup(pmap, dma_size, GFP_KERNEL); - if (!list) { - ql_log(ql_log_warn, vha, 0x1140, - "%s(%ld): failed to allocate node names list " - "structure.\n", __func__, vha->host_no); - rval = QLA_MEMORY_ALLOC_FAILED; - goto out_free; - } - -restart: - dma_free_coherent(&ha->pdev->dev, dma_size, pmap, pmap_dma); - } - - *out_data = list; - *out_len = dma_size; - -out: - return rval; - -out_free: - dma_free_coherent(&ha->pdev->dev, dma_size, pmap, pmap_dma); - return rval; -} /* * qla2x00_get_port_database @@ -3687,10 +3599,8 @@ void qla24xx_report_id_acquisition(scsi_qla_host_t *vha, struct vp_rpt_id_entry_24xx *rptid_entry) { - uint8_t vp_idx; - uint16_t stat = le16_to_cpu(rptid_entry->vp_idx); struct qla_hw_data *ha = vha->hw; - scsi_qla_host_t *vp; + scsi_qla_host_t *vp = NULL; unsigned long flags; int found; @@ -3701,80 +3611,124 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha, return; if (rptid_entry->format == 0) { + /* loop */ ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b7, "Format 0 : Number of VPs setup %d, number of " - "VPs acquired %d.\n", - MSB(le16_to_cpu(rptid_entry->vp_count)), - LSB(le16_to_cpu(rptid_entry->vp_count))); + "VPs acquired %d.\n", rptid_entry->vp_setup, + rptid_entry->vp_acquired); ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b8, "Primary port id %02x%02x%02x.\n", rptid_entry->port_id[2], rptid_entry->port_id[1], rptid_entry->port_id[0]); + + vha->d_id.b.domain = rptid_entry->port_id[2]; + vha->d_id.b.area = rptid_entry->port_id[1]; + vha->d_id.b.al_pa = rptid_entry->port_id[0]; + + spin_lock_irqsave(&ha->vport_slock, flags); + qlt_update_vp_map(vha, SET_AL_PA); + spin_unlock_irqrestore(&ha->vport_slock, flags); + } else if (rptid_entry->format == 1) { - vp_idx = LSB(stat); + /* fabric */ ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10b9, "Format 1: VP[%d] enabled - status %d - with " - "port id %02x%02x%02x.\n", vp_idx, MSB(stat), + "port id %02x%02x%02x.\n", rptid_entry->vp_idx, + rptid_entry->vp_status, rptid_entry->port_id[2], rptid_entry->port_id[1], rptid_entry->port_id[0]); /* buffer to buffer credit flag */ - vha->flags.bbcr_enable = (rptid_entry->bbcr & 0xf) != 0; - - /* FA-WWN is only for physical port */ - if (!vp_idx) { - void *wwpn = ha->init_cb->port_name; + vha->flags.bbcr_enable = (rptid_entry->u.f1.bbcr & 0xf) != 0; + + if (rptid_entry->vp_idx == 0) { + if (rptid_entry->vp_status == VP_STAT_COMPL) { + /* FA-WWN is only for physical port */ + if (qla_ini_mode_enabled(vha) && + ha->flags.fawwpn_enabled && + (rptid_entry->u.f1.flags & + VP_FLAGS_NAME_VALID)) { + memcpy(vha->port_name, + rptid_entry->u.f1.port_name, + WWN_SIZE); + } - if (!MSB(stat)) { - if (rptid_entry->vp_idx_map[1] & BIT_6) - wwpn = rptid_entry->reserved_4 + 8; + vha->d_id.b.domain = rptid_entry->port_id[2]; + vha->d_id.b.area = rptid_entry->port_id[1]; + vha->d_id.b.al_pa = rptid_entry->port_id[0]; + spin_lock_irqsave(&ha->vport_slock, flags); + qlt_update_vp_map(vha, SET_AL_PA); + spin_unlock_irqrestore(&ha->vport_slock, flags); } - memcpy(vha->port_name, wwpn, WWN_SIZE); + fc_host_port_name(vha->host) = wwn_to_u64(vha->port_name); - ql_dbg(ql_dbg_mbx, vha, 0x1018, - "FA-WWN portname %016llx (%x)\n", - fc_host_port_name(vha->host), MSB(stat)); - } - - vp = vha; - if (vp_idx == 0) - goto reg_needed; - if (MSB(stat) != 0 && MSB(stat) != 2) { - ql_dbg(ql_dbg_mbx, vha, 0x10ba, - "Could not acquire ID for VP[%d].\n", vp_idx); - return; - } + if (qla_ini_mode_enabled(vha)) + ql_dbg(ql_dbg_mbx, vha, 0x1018, + "FA-WWN portname %016llx (%x)\n", + fc_host_port_name(vha->host), + rptid_entry->vp_status); - found = 0; - spin_lock_irqsave(&ha->vport_slock, flags); - list_for_each_entry(vp, &ha->vp_list, list) { - if (vp_idx == vp->vp_idx) { - found = 1; - break; + set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags); + set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags); + } else { + if (rptid_entry->vp_status != VP_STAT_COMPL && + rptid_entry->vp_status != VP_STAT_ID_CHG) { + ql_dbg(ql_dbg_mbx, vha, 0x10ba, + "Could not acquire ID for VP[%d].\n", + rptid_entry->vp_idx); + return; } - } - spin_unlock_irqrestore(&ha->vport_slock, flags); - if (!found) - return; + found = 0; + spin_lock_irqsave(&ha->vport_slock, flags); + list_for_each_entry(vp, &ha->vp_list, list) { + if (rptid_entry->vp_idx == vp->vp_idx) { + found = 1; + break; + } + } + spin_unlock_irqrestore(&ha->vport_slock, flags); - vp->d_id.b.domain = rptid_entry->port_id[2]; - vp->d_id.b.area = rptid_entry->port_id[1]; - vp->d_id.b.al_pa = rptid_entry->port_id[0]; + if (!found) + return; - /* - * Cannot configure here as we are still sitting on the - * response queue. Handle it in dpc context. - */ - set_bit(VP_IDX_ACQUIRED, &vp->vp_flags); + vp->d_id.b.domain = rptid_entry->port_id[2]; + vp->d_id.b.area = rptid_entry->port_id[1]; + vp->d_id.b.al_pa = rptid_entry->port_id[0]; + spin_lock_irqsave(&ha->vport_slock, flags); + qlt_update_vp_map(vp, SET_AL_PA); + spin_unlock_irqrestore(&ha->vport_slock, flags); -reg_needed: - set_bit(REGISTER_FC4_NEEDED, &vp->dpc_flags); - set_bit(REGISTER_FDMI_NEEDED, &vp->dpc_flags); + /* + * Cannot configure here as we are still sitting on the + * response queue. Handle it in dpc context. + */ + set_bit(VP_IDX_ACQUIRED, &vp->vp_flags); + set_bit(REGISTER_FC4_NEEDED, &vp->dpc_flags); + set_bit(REGISTER_FDMI_NEEDED, &vp->dpc_flags); + } set_bit(VP_DPC_NEEDED, &vha->dpc_flags); qla2xxx_wake_dpc(vha); + } else if (rptid_entry->format == 2) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "RIDA: format 2/N2N Primary port id %02x%02x%02x.\n", + rptid_entry->port_id[2], rptid_entry->port_id[1], + rptid_entry->port_id[0]); + + ql_dbg(ql_dbg_async, vha, 0xffff, + "N2N: Remote WWPN %8phC.\n", + rptid_entry->u.f2.port_name); + + /* N2N. direct connect */ + vha->d_id.b.domain = rptid_entry->port_id[2]; + vha->d_id.b.area = rptid_entry->port_id[1]; + vha->d_id.b.al_pa = rptid_entry->port_id[0]; + + spin_lock_irqsave(&ha->vport_slock, flags); + qlt_update_vp_map(vha, SET_AL_PA); + spin_unlock_irqrestore(&ha->vport_slock, flags); } } diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c index 96c33e292eba..10b742d27e16 100644 --- a/drivers/scsi/qla2xxx/qla_mr.c +++ b/drivers/scsi/qla2xxx/qla_mr.c @@ -1789,16 +1789,16 @@ qlafx00_update_host_attr(scsi_qla_host_t *vha, struct port_info_data *pinfo) static void qla2x00_fxdisc_iocb_timeout(void *data) { - srb_t *sp = (srb_t *)data; + srb_t *sp = data; struct srb_iocb *lio = &sp->u.iocb_cmd; complete(&lio->u.fxiocb.fxiocb_comp); } static void -qla2x00_fxdisc_sp_done(void *data, void *ptr, int res) +qla2x00_fxdisc_sp_done(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct srb_iocb *lio = &sp->u.iocb_cmd; complete(&lio->u.fxiocb.fxiocb_comp); @@ -1999,7 +1999,7 @@ done_unmap_req: dma_free_coherent(&ha->pdev->dev, fdisc->u.fxiocb.req_len, fdisc->u.fxiocb.req_addr, fdisc->u.fxiocb.req_dma_handle); done_free_sp: - sp->free(vha, sp); + sp->free(sp); done: return rval; } @@ -2127,7 +2127,7 @@ static inline void qlafx00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len, uint32_t sense_len, struct rsp_que *rsp, int res) { - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct scsi_cmnd *cp = GET_CMD_SP(sp); uint32_t track_sense_len; @@ -2162,7 +2162,7 @@ qlafx00_handle_sense(srb_t *sp, uint8_t *sense_data, uint32_t par_sense_len, if (sense_len) { ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3039, "Check condition Sense data, nexus%ld:%d:%llu cmd=%p.\n", - sp->fcport->vha->host_no, cp->device->id, cp->device->lun, + sp->vha->host_no, cp->device->id, cp->device->lun, cp); ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x3049, cp->sense_buffer, sense_len); @@ -2181,7 +2181,7 @@ qlafx00_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, (sstatus & cpu_to_le16((uint16_t)SS_RESPONSE_INFO_LEN_VALID))) cpstatus = cpu_to_le16((uint16_t)CS_INCOMPLETE); tmf->u.tmf.comp_status = cpstatus; - sp->done(vha, sp, 0); + sp->done(sp, 0); } static void @@ -2198,7 +2198,7 @@ qlafx00_abort_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, abt = &sp->u.iocb_cmd; abt->u.abt.comp_status = pkt->tgt_id_sts; - sp->done(vha, sp, 0); + sp->done(sp, 0); } static void @@ -2264,7 +2264,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req, bsg_reply->reply_payload_rcv_len = bsg_job->reply_payload.payload_len; } - sp->done(vha, sp, res); + sp->done(sp, res); } /** @@ -2537,7 +2537,7 @@ check_scsi_status: par_sense_len, rsp_info_len); if (rsp->status_srb == NULL) - sp->done(ha, sp, res); + sp->done(sp, res); } /** @@ -2614,7 +2614,7 @@ qlafx00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) /* Place command on done queue. */ if (sense_len == 0) { rsp->status_srb = NULL; - sp->done(ha, sp, cp->result); + sp->done(sp, cp->result); } } @@ -2695,7 +2695,7 @@ qlafx00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); if (sp) { - sp->done(ha, sp, res); + sp->done(sp, res); return; } @@ -2997,7 +2997,7 @@ qlafx00_build_scsi_iocbs(srb_t *sp, struct cmd_type_7_fx00 *cmd_pkt, cont_a64_entry_t lcont_pkt; cont_a64_entry_t *cont_pkt; - vha = sp->fcport->vha; + vha = sp->vha; req = vha->req; cmd = GET_CMD_SP(sp); @@ -3081,7 +3081,7 @@ qlafx00_start_scsi(srb_t *sp) struct req_que *req = NULL; struct rsp_que *rsp = NULL; struct scsi_cmnd *cmd = GET_CMD_SP(sp); - struct scsi_qla_host *vha = sp->fcport->vha; + struct scsi_qla_host *vha = sp->vha; struct qla_hw_data *ha = vha->hw; struct cmd_type_7_fx00 *cmd_pkt; struct cmd_type_7_fx00 lcmd_pkt; @@ -3205,7 +3205,7 @@ void qlafx00_tm_iocb(srb_t *sp, struct tsk_mgmt_entry_fx00 *ptm_iocb) { struct srb_iocb *fxio = &sp->u.iocb_cmd; - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct req_que *req = vha->req; struct tsk_mgmt_entry_fx00 tm_iocb; struct scsi_lun llun; @@ -3232,7 +3232,7 @@ void qlafx00_abort_iocb(srb_t *sp, struct abort_iocb_entry_fx00 *pabt_iocb) { struct srb_iocb *fxio = &sp->u.iocb_cmd; - scsi_qla_host_t *vha = sp->fcport->vha; + scsi_qla_host_t *vha = sp->vha; struct req_que *req = vha->req; struct abort_iocb_entry_fx00 abt_iocb; @@ -3346,8 +3346,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) REQUEST_ENTRY_SIZE); cont_pkt = qlafx00_prep_cont_type1_iocb( - sp->fcport->vha->req, - &lcont_pkt); + sp->vha->req, &lcont_pkt); cur_dsd = (__le32 *) lcont_pkt.dseg_0_address; avail_dsds = 5; @@ -3368,7 +3367,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) &lcont_pkt, REQUEST_ENTRY_SIZE); ql_dump_buffer( ql_dbg_user + ql_dbg_verbose, - sp->fcport->vha, 0x3042, + sp->vha, 0x3042, (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE); } @@ -3377,7 +3376,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) memcpy_toio((void __iomem *)cont_pkt, &lcont_pkt, REQUEST_ENTRY_SIZE); ql_dump_buffer(ql_dbg_user + ql_dbg_verbose, - sp->fcport->vha, 0x3043, + sp->vha, 0x3043, (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE); } } @@ -3409,8 +3408,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) REQUEST_ENTRY_SIZE); cont_pkt = qlafx00_prep_cont_type1_iocb( - sp->fcport->vha->req, - &lcont_pkt); + sp->vha->req, &lcont_pkt); cur_dsd = (__le32 *) lcont_pkt.dseg_0_address; avail_dsds = 5; @@ -3431,7 +3429,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) REQUEST_ENTRY_SIZE); ql_dump_buffer( ql_dbg_user + ql_dbg_verbose, - sp->fcport->vha, 0x3045, + sp->vha, 0x3045, (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE); } @@ -3440,7 +3438,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) memcpy_toio((void __iomem *)cont_pkt, &lcont_pkt, REQUEST_ENTRY_SIZE); ql_dump_buffer(ql_dbg_user + ql_dbg_verbose, - sp->fcport->vha, 0x3046, + sp->vha, 0x3046, (uint8_t *)&lcont_pkt, REQUEST_ENTRY_SIZE); } } @@ -3452,7 +3450,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb) } ql_dump_buffer(ql_dbg_user + ql_dbg_verbose, - sp->fcport->vha, 0x3047, + sp->vha, 0x3047, (uint8_t *)&fx_iocb, sizeof(struct fxdisc_entry_fx00)); memcpy_toio((void __iomem *)pfxiocb, &fx_iocb, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d01c90c7dd04..bbf1ad956251 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -237,6 +237,13 @@ MODULE_PARM_DESC(ql2xfwholdabts, "0 (Default) Do not set fw option. " "1 - Set fw option to hold ABTS."); +int ql2xmvasynctoatio = 1; +module_param(ql2xmvasynctoatio, int, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(ql2xmvasynctoatio, + "Move PUREX, ABTS RX and RIDA IOCBs to ATIOQ" + "0 (Default). Do not move IOCBs" + "1 - Move IOCBs."); + /* * SCSI host template entry points */ @@ -607,11 +614,11 @@ qla24xx_fw_version_str(struct scsi_qla_host *vha, char *str, size_t size) } void -qla2x00_sp_free_dma(void *vha, void *ptr) +qla2x00_sp_free_dma(void *ptr) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; + struct qla_hw_data *ha = sp->vha->hw; struct scsi_cmnd *cmd = GET_CMD_SP(sp); - struct qla_hw_data *ha = sp->fcport->vha->hw; void *ctx = GET_CMD_CTX_SP(sp); if (sp->flags & SRB_DMA_VALID) { @@ -650,20 +657,19 @@ qla2x00_sp_free_dma(void *vha, void *ptr) } CMD_SP(cmd) = NULL; - qla2x00_rel_sp(sp->fcport->vha, sp); + qla2x00_rel_sp(sp); } void -qla2x00_sp_compl(void *data, void *ptr, int res) +qla2x00_sp_compl(void *ptr, int res) { - struct qla_hw_data *ha = (struct qla_hw_data *)data; - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct scsi_cmnd *cmd = GET_CMD_SP(sp); cmd->result = res; if (atomic_read(&sp->ref_count) == 0) { - ql_dbg(ql_dbg_io, sp->fcport->vha, 0x3015, + ql_dbg(ql_dbg_io, sp->vha, 0x3015, "SP reference-count to ZERO -- sp=%p cmd=%p.\n", sp, GET_CMD_SP(sp)); if (ql2xextended_error_logging & ql_dbg_io) @@ -673,12 +679,12 @@ qla2x00_sp_compl(void *data, void *ptr, int res) if (!atomic_dec_and_test(&sp->ref_count)) return; - qla2x00_sp_free_dma(ha, sp); + qla2x00_sp_free_dma(sp); cmd->scsi_done(cmd); } void -qla2xxx_qpair_sp_free_dma(void *vha, void *ptr) +qla2xxx_qpair_sp_free_dma(void *ptr) { srb_t *sp = (srb_t *)ptr; struct scsi_cmnd *cmd = GET_CMD_SP(sp); @@ -724,9 +730,9 @@ qla2xxx_qpair_sp_free_dma(void *vha, void *ptr) } void -qla2xxx_qpair_sp_compl(void *data, void *ptr, int res) +qla2xxx_qpair_sp_compl(void *ptr, int res) { - srb_t *sp = (srb_t *)ptr; + srb_t *sp = ptr; struct scsi_cmnd *cmd = GET_CMD_SP(sp); cmd->result = res; @@ -742,7 +748,7 @@ qla2xxx_qpair_sp_compl(void *data, void *ptr, int res) if (!atomic_dec_and_test(&sp->ref_count)) return; - qla2xxx_qpair_sp_free_dma(sp->fcport->vha, sp); + qla2xxx_qpair_sp_free_dma(sp); cmd->scsi_done(cmd); } @@ -863,7 +869,7 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) return 0; qc24_host_busy_free_sp: - qla2x00_sp_free_dma(ha, sp); + qla2x00_sp_free_dma(sp); qc24_host_busy: return SCSI_MLQUEUE_HOST_BUSY; @@ -952,7 +958,7 @@ qla2xxx_mqueuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd, return 0; qc24_host_busy_free_sp: - qla2xxx_qpair_sp_free_dma(vha, sp); + qla2xxx_qpair_sp_free_dma(sp); qc24_host_busy: return SCSI_MLQUEUE_HOST_BUSY; @@ -1044,6 +1050,34 @@ qla2x00_wait_for_hba_online(scsi_qla_host_t *vha) return (return_status); } +static inline int test_fcport_count(scsi_qla_host_t *vha) +{ + struct qla_hw_data *ha = vha->hw; + unsigned long flags; + int res; + + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + ql_dbg(ql_dbg_init, vha, 0xffff, + "tgt %p, fcport_count=%d\n", + vha, vha->fcport_count); + res = (vha->fcport_count == 0); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + + return res; +} + +/* + * qla2x00_wait_for_sess_deletion can only be called from remove_one. + * it has dependency on UNLOADING flag to stop device discovery + */ +static void +qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) +{ + qla2x00_mark_all_devices_lost(vha, 0); + + wait_event(vha->fcport_waitQ, test_fcport_count(vha)); +} + /* * qla2x00_wait_for_hba_ready * Wait till the HBA is ready before doing driver unload @@ -1204,7 +1238,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd) } spin_lock_irqsave(&ha->hardware_lock, flags); - sp->done(ha, sp, 0); + sp->done(sp, 0); spin_unlock_irqrestore(&ha->hardware_lock, flags); /* Did the command return during mailbox execution? */ @@ -1249,7 +1283,7 @@ qla2x00_eh_wait_for_pending_commands(scsi_qla_host_t *vha, unsigned int t, continue; if (sp->type != SRB_SCSI_CMD) continue; - if (vha->vp_idx != sp->fcport->vha->vp_idx) + if (vha->vp_idx != sp->vha->vp_idx) continue; match = 0; cmd = GET_CMD_SP(sp); @@ -1629,7 +1663,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res) spin_lock_irqsave(&ha->hardware_lock, flags); } req->outstanding_cmds[cnt] = NULL; - sp->done(vha, sp, res); + sp->done(sp, res); } } } @@ -3124,7 +3158,8 @@ skip_dpc: ql_dbg(ql_dbg_init, base_vha, 0x00f2, "Init done and hba is online.\n"); - if (qla_ini_mode_enabled(base_vha)) + if (qla_ini_mode_enabled(base_vha) || + qla_dual_mode_enabled(base_vha)) scsi_scan_host(host); else ql_dbg(ql_dbg_init, base_vha, 0x0122, @@ -3373,21 +3408,26 @@ qla2x00_remove_one(struct pci_dev *pdev) * resources. */ if (!atomic_read(&pdev->enable_cnt)) { + dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size, + base_vha->gnl.l, base_vha->gnl.ldma); + scsi_host_put(base_vha->host); kfree(ha); pci_set_drvdata(pdev, NULL); return; } - qla2x00_wait_for_hba_ready(base_vha); - /* if UNLOAD flag is already set, then continue unload, + /* + * if UNLOAD flag is already set, then continue unload, * where it was set first. */ if (test_bit(UNLOADING, &base_vha->dpc_flags)) return; set_bit(UNLOADING, &base_vha->dpc_flags); + dma_free_coherent(&ha->pdev->dev, + base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); if (IS_QLAFX00(ha)) qlafx00_driver_shutdown(base_vha, 20); @@ -3536,10 +3576,14 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, qla2xxx_wake_dpc(base_vha); } else { int now; - if (rport) + if (rport) { + ql_dbg(ql_dbg_disc, fcport->vha, 0xffff, + "%s %8phN. rport %p roles %x \n", + __func__, fcport->port_name, rport, + rport->roles); fc_remote_port_delete(rport); + } qlt_do_generation_tick(vha, &now); - qlt_fc_port_deleted(vha, fcport, now); } } @@ -3582,7 +3626,7 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport, fcport->login_retry = vha->hw->login_retry_count; ql_dbg(ql_dbg_disc, vha, 0x2067, - "Port login retry %8phN, id = 0x%04x retry cnt=%d.\n", + "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n", fcport->port_name, fcport->loop_id, fcport->login_retry); } } @@ -3605,7 +3649,13 @@ qla2x00_mark_all_devices_lost(scsi_qla_host_t *vha, int defer) { fc_port_t *fcport; + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Mark all dev lost\n"); + list_for_each_entry(fcport, &vha->vp_fcports, list) { + fcport->scan_state = 0; + qlt_schedule_sess_for_deletion_lock(fcport); + if (vha->vp_idx != 0 && vha->vp_idx != fcport->vha->vp_idx) continue; @@ -4195,10 +4245,10 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, struct scsi_qla_host *vha = NULL; host = scsi_host_alloc(sht, sizeof(scsi_qla_host_t)); - if (host == NULL) { + if (!host) { ql_log_pci(ql_log_fatal, ha->pdev, 0x0107, "Failed to allocate host from the scsi layer, aborting.\n"); - goto fail; + return NULL; } /* Clear our data area */ @@ -4217,9 +4267,22 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, INIT_LIST_HEAD(&vha->logo_list); INIT_LIST_HEAD(&vha->plogi_ack_list); INIT_LIST_HEAD(&vha->qp_list); + INIT_LIST_HEAD(&vha->gnl.fcports); spin_lock_init(&vha->work_lock); spin_lock_init(&vha->cmd_list_lock); + init_waitqueue_head(&vha->fcport_waitQ); + + vha->gnl.size = sizeof(struct get_name_list_extended) * + (ha->max_loop_id + 1); + vha->gnl.l = dma_alloc_coherent(&ha->pdev->dev, + vha->gnl.size, &vha->gnl.ldma, GFP_KERNEL); + if (!vha->gnl.l) { + ql_log(ql_log_fatal, vha, 0xffff, + "Alloc failed for name list.\n"); + scsi_remove_host(vha->host); + return NULL; + } sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no); ql_dbg(ql_dbg_init, vha, 0x0041, @@ -4228,12 +4291,9 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, dev_name(&(ha->pdev->dev))); return vha; - -fail: - return vha; } -static struct qla_work_evt * +struct qla_work_evt * qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type) { struct qla_work_evt *e; @@ -4255,7 +4315,7 @@ qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type) return e; } -static int +int qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e) { unsigned long flags; @@ -4316,7 +4376,6 @@ int qla2x00_post_async_##name##_work( \ } qla2x00_post_async_work(login, QLA_EVT_ASYNC_LOGIN); -qla2x00_post_async_work(login_done, QLA_EVT_ASYNC_LOGIN_DONE); qla2x00_post_async_work(logout, QLA_EVT_ASYNC_LOGOUT); qla2x00_post_async_work(logout_done, QLA_EVT_ASYNC_LOGOUT_DONE); qla2x00_post_async_work(adisc, QLA_EVT_ASYNC_ADISC); @@ -4369,6 +4428,67 @@ qlafx00_post_aenfx_work(struct scsi_qla_host *vha, uint32_t evtcode, return qla2x00_post_work(vha, e); } +int qla24xx_post_upd_fcport_work(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + struct qla_work_evt *e; + + e = qla2x00_alloc_work(vha, QLA_EVT_UPD_FCPORT); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.fcport.fcport = fcport; + return qla2x00_post_work(vha, e); +} + +static +void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) +{ + unsigned long flags; + fc_port_t *fcport = NULL; + struct qlt_plogi_ack_t *pla = + (struct qlt_plogi_ack_t *)e->u.new_sess.pla; + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + fcport = qla2x00_find_fcport_by_wwpn(vha, e->u.new_sess.port_name, 1); + if (fcport) { + fcport->d_id = e->u.new_sess.id; + if (pla) { + fcport->fw_login_state = DSC_LS_PLOGI_PEND; + qlt_plogi_ack_link(vha, pla, fcport, QLT_PLOGI_LINK_SAME_WWN); + /* we took an extra ref_count to prevent PLOGI ACK when + * fcport/sess has not been created. + */ + pla->ref_count--; + } + } else { + fcport = qla2x00_alloc_fcport(vha, GFP_KERNEL); + if (fcport) { + fcport->d_id = e->u.new_sess.id; + fcport->scan_state = QLA_FCPORT_FOUND; + fcport->flags |= FCF_FABRIC_DEVICE; + fcport->fw_login_state = DSC_LS_PLOGI_PEND; + + memcpy(fcport->port_name, e->u.new_sess.port_name, + WWN_SIZE); + list_add_tail(&fcport->list, &vha->vp_fcports); + + if (pla) { + qlt_plogi_ack_link(vha, pla, fcport, + QLT_PLOGI_LINK_SAME_WWN); + pla->ref_count--; + } + } + } + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + if (fcport) { + if (pla) + qlt_plogi_ack_unref(vha, pla); + else + qla24xx_async_gnl(vha, fcport); + } +} + void qla2x00_do_work(struct scsi_qla_host *vha) { @@ -4395,10 +4515,6 @@ qla2x00_do_work(struct scsi_qla_host *vha) qla2x00_async_login(vha, e->u.logio.fcport, e->u.logio.data); break; - case QLA_EVT_ASYNC_LOGIN_DONE: - qla2x00_async_login_done(vha, e->u.logio.fcport, - e->u.logio.data); - break; case QLA_EVT_ASYNC_LOGOUT: qla2x00_async_logout(vha, e->u.logio.fcport); break; @@ -4420,6 +4536,34 @@ qla2x00_do_work(struct scsi_qla_host *vha) case QLA_EVT_AENFX: qlafx00_process_aen(vha, e); break; + case QLA_EVT_GIDPN: + qla24xx_async_gidpn(vha, e->u.fcport.fcport); + break; + case QLA_EVT_GPNID: + qla24xx_async_gpnid(vha, &e->u.gpnid.id); + break; + case QLA_EVT_GPNID_DONE: + qla24xx_async_gpnid_done(vha, e->u.iosb.sp); + break; + case QLA_EVT_NEW_SESS: + qla24xx_create_new_sess(vha, e); + break; + case QLA_EVT_GPDB: + qla24xx_async_gpdb(vha, e->u.fcport.fcport, + e->u.fcport.opt); + break; + case QLA_EVT_GPSC: + qla24xx_async_gpsc(vha, e->u.fcport.fcport); + break; + case QLA_EVT_UPD_FCPORT: + qla2x00_update_fcport(vha, e->u.fcport.fcport); + break; + case QLA_EVT_GNL: + qla24xx_async_gnl(vha, e->u.fcport.fcport); + break; + case QLA_EVT_NACK: + qla24xx_do_nack_work(vha, e); + break; } if (e->flags & QLA_EVT_FLAG_FREE) kfree(e); @@ -4436,9 +4580,7 @@ void qla2x00_relogin(struct scsi_qla_host *vha) { fc_port_t *fcport; int status; - uint16_t next_loopid = 0; - struct qla_hw_data *ha = vha->hw; - uint16_t data[2]; + struct event_arg ea; list_for_each_entry(fcport, &vha->vp_fcports, list) { /* @@ -4449,77 +4591,38 @@ void qla2x00_relogin(struct scsi_qla_host *vha) fcport->login_retry && !(fcport->flags & FCF_ASYNC_SENT)) { fcport->login_retry--; if (fcport->flags & FCF_FABRIC_DEVICE) { - if (fcport->flags & FCF_FCP2_DEVICE) - ha->isp_ops->fabric_logout(vha, - fcport->loop_id, - fcport->d_id.b.domain, - fcport->d_id.b.area, - fcport->d_id.b.al_pa); - - if (fcport->loop_id == FC_NO_LOOP_ID) { - fcport->loop_id = next_loopid = - ha->min_external_loopid; - status = qla2x00_find_new_loop_id( - vha, fcport); - if (status != QLA_SUCCESS) { - /* Ran out of IDs to use */ - break; - } - } - - if (IS_ALOGIO_CAPABLE(ha)) { - fcport->flags |= FCF_ASYNC_SENT; - data[0] = 0; - data[1] = QLA_LOGIO_LOGIN_RETRIED; - status = qla2x00_post_async_login_work( - vha, fcport, data); - if (status == QLA_SUCCESS) - continue; - /* Attempt a retry. */ - status = 1; - } else { - status = qla2x00_fabric_login(vha, - fcport, &next_loopid); - if (status == QLA_SUCCESS) { - int status2; - uint8_t opts; - - opts = 0; - if (fcport->flags & - FCF_FCP2_DEVICE) - opts |= BIT_1; - status2 = - qla2x00_get_port_database( - vha, fcport, opts); - if (status2 != QLA_SUCCESS) - status = 1; - } - } - } else + ql_dbg(ql_dbg_disc, fcport->vha, 0xffff, + "%s %8phC DS %d LS %d\n", __func__, + fcport->port_name, fcport->disc_state, + fcport->fw_login_state); + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_RELOGIN; + ea.fcport = fcport; + qla2x00_fcport_event_handler(vha, &ea); + } else { status = qla2x00_local_device_login(vha, fcport); + if (status == QLA_SUCCESS) { + fcport->old_loop_id = fcport->loop_id; + ql_dbg(ql_dbg_disc, vha, 0x2003, + "Port login OK: logged in ID 0x%x.\n", + fcport->loop_id); + qla2x00_update_fcport(vha, fcport); + } else if (status == 1) { + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + /* retry the login again */ + ql_dbg(ql_dbg_disc, vha, 0x2007, + "Retrying %d login again loop_id 0x%x.\n", + fcport->login_retry, + fcport->loop_id); + } else { + fcport->login_retry = 0; + } - if (status == QLA_SUCCESS) { - fcport->old_loop_id = fcport->loop_id; - - ql_dbg(ql_dbg_disc, vha, 0x2003, - "Port login OK: logged in ID 0x%x.\n", - fcport->loop_id); - - qla2x00_update_fcport(vha, fcport); - - } else if (status == 1) { - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - /* retry the login again */ - ql_dbg(ql_dbg_disc, vha, 0x2007, - "Retrying %d login again loop_id 0x%x.\n", - fcport->login_retry, fcport->loop_id); - } else { - fcport->login_retry = 0; + if (fcport->login_retry == 0 && + status != QLA_SUCCESS) + qla2x00_clear_loop_id(fcport); } - - if (fcport->login_retry == 0 && status != QLA_SUCCESS) - qla2x00_clear_loop_id(fcport); } if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)) break; @@ -5183,7 +5286,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work) struct pci_dev *pdev = ha->pdev; scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev); - /* if UNLOAD flag is already set, then continue unload, + /* + * if UNLOAD flag is already set, then continue unload, * where it was set first. */ if (test_bit(UNLOADING, &base_vha->dpc_flags)) @@ -5192,6 +5296,8 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work) ql_log(ql_log_warn, base_vha, 0x015b, "Disabling adapter.\n"); + qla2x00_wait_for_sess_deletion(base_vha); + set_bit(UNLOADING, &base_vha->dpc_flags); qla2x00_delete_all_vps(ha, base_vha); @@ -5410,16 +5516,6 @@ qla2x00_do_dpc(void *data) qla2x00_update_fcports(base_vha); } - if (test_bit(SCR_PENDING, &base_vha->dpc_flags)) { - int ret; - ret = qla2x00_send_change_request(base_vha, 0x3, 0); - if (ret != QLA_SUCCESS) - ql_log(ql_log_warn, base_vha, 0x121, - "Failed to enable receiving of RSCN " - "requests: 0x%x.\n", ret); - clear_bit(SCR_PENDING, &base_vha->dpc_flags); - } - if (IS_QLAFX00(ha)) goto loop_resync_check; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index e4fda84b959e..45f5077684f0 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -55,8 +55,17 @@ MODULE_PARM_DESC(qlini_mode, "disabled on enabling target mode and then on disabling target mode " "enabled back; " "\"disabled\" - initiator mode will never be enabled; " + "\"dual\" - Initiator Modes will be enabled. Target Mode can be activated " + "when ready " "\"enabled\" (default) - initiator mode will always stay enabled."); +static int ql_dm_tgt_ex_pct = 50; +module_param(ql_dm_tgt_ex_pct, int, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(ql_dm_tgt_ex_pct, + "For Dual Mode (qlini_mode=dual), this parameter determines " + "the percentage of exchanges/cmds FW will allocate resources " + "for Target mode."); + int ql2x_ini_mode = QLA2XXX_INI_MODE_EXCLUSIVE; static int temp_sam_status = SAM_STAT_BUSY; @@ -102,12 +111,10 @@ enum fcp_resp_rsp_codes { static void qlt_24xx_atio_pkt(struct scsi_qla_host *ha, struct atio_from_isp *pkt, uint8_t); static void qlt_response_pkt(struct scsi_qla_host *ha, response_t *pkt); -static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, +static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun, int fn, void *iocb, int flags); static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort); -static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha, - struct qla_tgt_srr_imm *imm, int ha_lock); static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd); static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, @@ -120,6 +127,9 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha, uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan); static void qlt_send_term_imm_notif(struct scsi_qla_host *vha, struct imm_ntfy_from_isp *imm, int ha_locked); +static struct fc_port *qlt_create_sess(struct scsi_qla_host *vha, + fc_port_t *fcport, bool local); +void qlt_unreg_sess(struct fc_port *sess); /* * Global Variables */ @@ -140,21 +150,6 @@ void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest) wmb(); } -/* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */ -static struct qla_tgt_sess *qlt_find_sess_by_port_name( - struct qla_tgt *tgt, - const uint8_t *port_name) -{ - struct qla_tgt_sess *sess; - - list_for_each_entry(sess, &tgt->sess_list, sess_list_entry) { - if (!memcmp(sess->port_name, port_name, WWN_SIZE)) - return sess; - } - - return NULL; -} - /* Might release hw lock, then reaquire!! */ static inline int qlt_issue_marker(struct scsi_qla_host *vha, int vha_locked) { @@ -229,6 +224,105 @@ static inline void qlt_decr_num_pend_cmds(struct scsi_qla_host *vha) spin_unlock_irqrestore(&vha->hw->tgt.q_full_lock, flags); } + +static void qlt_queue_unknown_atio(scsi_qla_host_t *vha, + struct atio_from_isp *atio, uint8_t ha_locked) +{ + struct qla_tgt_sess_op *u; + struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + unsigned long flags; + + if (tgt->tgt_stop) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "qla_target(%d): dropping unknown ATIO_TYPE7, " + "because tgt is being stopped", vha->vp_idx); + goto out_term; + } + + u = kzalloc(sizeof(*u), GFP_ATOMIC); + if (u == NULL) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "Alloc of struct unknown_atio (size %zd) failed", sizeof(*u)); + /* It should be harmless and on the next retry should work well */ + goto out_term; + } + + u->vha = vha; + memcpy(&u->atio, atio, sizeof(*atio)); + INIT_LIST_HEAD(&u->cmd_list); + + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_add_tail(&u->cmd_list, &vha->unknown_atio_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); + + schedule_delayed_work(&vha->unknown_atio_work, 1); + +out: + return; + +out_term: + qlt_send_term_exchange(vha, NULL, atio, ha_locked, 0); + goto out; +} + +static void qlt_try_to_dequeue_unknown_atios(struct scsi_qla_host *vha, + uint8_t ha_locked) +{ + struct qla_tgt_sess_op *u, *t; + scsi_qla_host_t *host; + struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + unsigned long flags; + uint8_t queued = 0; + + list_for_each_entry_safe(u, t, &vha->unknown_atio_list, cmd_list) { + if (u->aborted) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "Freeing unknown %s %p, because of Abort", + "ATIO_TYPE7", u); + qlt_send_term_exchange(vha, NULL, &u->atio, + ha_locked, 0); + goto abort; + } + + host = qlt_find_host_by_d_id(vha, u->atio.u.isp24.fcp_hdr.d_id); + if (host != NULL) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "Requeuing unknown ATIO_TYPE7 %p", u); + qlt_24xx_atio_pkt(host, &u->atio, ha_locked); + } else if (tgt->tgt_stop) { + ql_dbg(ql_dbg_async, vha, 0xffff, + "Freeing unknown %s %p, because tgt is being stopped", + "ATIO_TYPE7", u); + qlt_send_term_exchange(vha, NULL, &u->atio, + ha_locked, 0); + } else { + ql_dbg(ql_dbg_async, vha, 0xffff, + "u %p, vha %p, host %p, sched again..", u, + vha, host); + if (!queued) { + queued = 1; + schedule_delayed_work(&vha->unknown_atio_work, + 1); + } + continue; + } + +abort: + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_del(&u->cmd_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); + kfree(u); + } +} + +void qlt_unknown_atio_work_fn(struct work_struct *work) +{ + struct scsi_qla_host *vha = container_of(to_delayed_work(work), + struct scsi_qla_host, unknown_atio_work); + + qlt_try_to_dequeue_unknown_atios(vha, 0); +} + static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha, struct atio_from_isp *atio, uint8_t ha_locked) { @@ -249,8 +343,14 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha, atio->u.isp24.fcp_hdr.d_id[0], atio->u.isp24.fcp_hdr.d_id[1], atio->u.isp24.fcp_hdr.d_id[2]); + + + qlt_queue_unknown_atio(vha, atio, ha_locked); break; } + if (unlikely(!list_empty(&vha->unknown_atio_list))) + qlt_try_to_dequeue_unknown_atios(vha, ha_locked); + qlt_24xx_atio_pkt(host, atio, ha_locked); break; } @@ -278,6 +378,31 @@ static bool qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha, break; } + case VP_RPT_ID_IOCB_TYPE: + qla24xx_report_id_acquisition(vha, + (struct vp_rpt_id_entry_24xx *)atio); + break; + + case ABTS_RECV_24XX: + { + struct abts_recv_from_24xx *entry = + (struct abts_recv_from_24xx *)atio; + struct scsi_qla_host *host = qlt_find_host_by_vp_idx(vha, + entry->vp_index); + if (unlikely(!host)) { + ql_dbg(ql_dbg_tgt, vha, 0xffff, + "qla_target(%d): Response pkt (ABTS_RECV_24XX) " + "received, with unknown vp_index %d\n", + vha->vp_idx, entry->vp_index); + break; + } + qlt_response_pkt(host, (response_t *)atio); + break; + + } + + /* case PUREX_IOCB_TYPE: ql2xmvasynctoatio */ + default: ql_dbg(ql_dbg_tgt, vha, 0xe040, "qla_target(%d): Received unknown ATIO atio " @@ -395,22 +520,263 @@ void qlt_response_pkt_all_vps(struct scsi_qla_host *vha, response_t *pkt) /* * All qlt_plogi_ack_t operations are protected by hardware_lock */ +static int qla24xx_post_nack_work(struct scsi_qla_host *vha, fc_port_t *fcport, + struct imm_ntfy_from_isp *ntfy, int type) +{ + struct qla_work_evt *e; + e = qla2x00_alloc_work(vha, QLA_EVT_NACK); + if (!e) + return QLA_FUNCTION_FAILED; + + e->u.nack.fcport = fcport; + e->u.nack.type = type; + memcpy(e->u.nack.iocb, ntfy, sizeof(struct imm_ntfy_from_isp)); + return qla2x00_post_work(vha, e); +} + +static +void qla2x00_async_nack_sp_done(void *s, int res) +{ + struct srb *sp = (struct srb *)s; + struct scsi_qla_host *vha = sp->vha; + unsigned long flags; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async done-%s res %x %8phC type %d\n", + sp->name, res, sp->fcport->port_name, sp->type); + + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + sp->fcport->flags &= ~FCF_ASYNC_SENT; + sp->fcport->chip_reset = vha->hw->chip_reset; + + switch (sp->type) { + case SRB_NACK_PLOGI: + sp->fcport->login_gen++; + sp->fcport->fw_login_state = DSC_LS_PLOGI_COMP; + sp->fcport->logout_on_delete = 1; + break; + + case SRB_NACK_PRLI: + sp->fcport->fw_login_state = DSC_LS_PRLI_COMP; + sp->fcport->deleted = 0; + + if (!sp->fcport->login_succ && + !IS_SW_RESV_ADDR(sp->fcport->d_id)) { + sp->fcport->login_succ = 1; + + vha->fcport_count++; + + if (!IS_IIDMA_CAPABLE(vha->hw) || + !vha->hw->flags.gpsc_supported) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post upd_fcport fcp_cnt %d\n", + __func__, __LINE__, + sp->fcport->port_name, + vha->fcport_count); + + qla24xx_post_upd_fcport_work(vha, sp->fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpsc fcp_cnt %d\n", + __func__, __LINE__, + sp->fcport->port_name, + vha->fcport_count); + + qla24xx_post_gpsc_work(vha, sp->fcport); + } + } + break; + + case SRB_NACK_LOGO: + sp->fcport->login_gen++; + sp->fcport->fw_login_state = DSC_LS_PORT_UNAVAIL; + qlt_logo_completion_handler(sp->fcport, MBS_COMMAND_COMPLETE); + break; + } + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + sp->free(sp); +} + +int qla24xx_async_notify_ack(scsi_qla_host_t *vha, fc_port_t *fcport, + struct imm_ntfy_from_isp *ntfy, int type) +{ + int rval = QLA_FUNCTION_FAILED; + srb_t *sp; + char *c = NULL; + + fcport->flags |= FCF_ASYNC_SENT; + switch (type) { + case SRB_NACK_PLOGI: + fcport->fw_login_state = DSC_LS_PLOGI_PEND; + c = "PLOGI"; + break; + case SRB_NACK_PRLI: + fcport->fw_login_state = DSC_LS_PRLI_PEND; + c = "PRLI"; + break; + case SRB_NACK_LOGO: + fcport->fw_login_state = DSC_LS_LOGO_PEND; + c = "LOGO"; + break; + } + + sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC); + if (!sp) + goto done; + + sp->type = type; + sp->name = "nack"; + + qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha)+2); + + sp->u.iocb_cmd.u.nack.ntfy = ntfy; + + sp->done = qla2x00_async_nack_sp_done; + + rval = qla2x00_start_sp(sp); + if (rval != QLA_SUCCESS) + goto done_free_sp; + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "Async-%s %8phC hndl %x %s\n", + sp->name, fcport->port_name, sp->handle, c); + + return rval; + +done_free_sp: + sp->free(sp); +done: + fcport->flags &= ~FCF_ASYNC_SENT; + return rval; +} + +void qla24xx_do_nack_work(struct scsi_qla_host *vha, struct qla_work_evt *e) +{ + fc_port_t *t; + unsigned long flags; + + switch (e->u.nack.type) { + case SRB_NACK_PRLI: + mutex_lock(&vha->vha_tgt.tgt_mutex); + t = qlt_create_sess(vha, e->u.nack.fcport, 0); + mutex_unlock(&vha->vha_tgt.tgt_mutex); + if (t) { + ql_log(ql_log_info, vha, 0xffff, + "%s create sess success %p", __func__, t); + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + /* create sess has an extra kref */ + vha->hw->tgt.tgt_ops->put_sess(e->u.nack.fcport); + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + } + break; + } + qla24xx_async_notify_ack(vha, e->u.nack.fcport, + (struct imm_ntfy_from_isp*)e->u.nack.iocb, e->u.nack.type); +} + +void qla24xx_delete_sess_fn(struct work_struct *work) +{ + fc_port_t *fcport = container_of(work, struct fc_port, del_work); + struct qla_hw_data *ha = fcport->vha->hw; + unsigned long flags; + + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + + if (fcport->se_sess) { + ha->tgt.tgt_ops->shutdown_sess(fcport); + ha->tgt.tgt_ops->put_sess(fcport); + } else { + qlt_unreg_sess(fcport); + } + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); +} + +/* + * Called from qla2x00_reg_remote_port() + */ +void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) +{ + struct qla_hw_data *ha = vha->hw; + struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + struct fc_port *sess = fcport; + unsigned long flags; + + if (!vha->hw->tgt.tgt_ops) + return; + + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + if (tgt->tgt_stop) { + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return; + } + + if (fcport->disc_state == DSC_DELETE_PEND) { + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return; + } + + if (!sess->se_sess) { + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + + mutex_lock(&vha->vha_tgt.tgt_mutex); + sess = qlt_create_sess(vha, fcport, false); + mutex_unlock(&vha->vha_tgt.tgt_mutex); + + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + } else { + if (fcport->fw_login_state == DSC_LS_PRLI_COMP) { + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return; + } + + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: kref_get fail sess %8phC \n", + __func__, sess->port_name); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return; + } + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04c, + "qla_target(%u): %ssession for port %8phC " + "(loop ID %d) reappeared\n", vha->vp_idx, + sess->local ? "local " : "", sess->port_name, sess->loop_id); + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf007, + "Reappeared sess %p\n", sess); + + ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, + fcport->loop_id, + (fcport->flags & FCF_CONF_COMP_SUPPORTED)); + } + + if (sess && sess->local) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04d, + "qla_target(%u): local session for " + "port %8phC (loop ID %d) became global\n", vha->vp_idx, + fcport->port_name, sess->loop_id); + sess->local = 0; + } + ha->tgt.tgt_ops->put_sess(sess); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); +} /* * This is a zero-base ref-counting solution, since hardware_lock * guarantees that ref_count is not modified concurrently. * Upon successful return content of iocb is undefined */ -static qlt_plogi_ack_t * +static struct qlt_plogi_ack_t * qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id, struct imm_ntfy_from_isp *iocb) { - qlt_plogi_ack_t *pla; + struct qlt_plogi_ack_t *pla; list_for_each_entry(pla, &vha->plogi_ack_list, list) { if (pla->id.b24 == id->b24) { qlt_send_term_imm_notif(vha, &pla->iocb, 1); - pla->iocb = *iocb; + memcpy(&pla->iocb, iocb, sizeof(pla->iocb)); return pla; } } @@ -423,50 +789,78 @@ qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id, return NULL; } - pla->iocb = *iocb; + memcpy(&pla->iocb, iocb, sizeof(pla->iocb)); pla->id = *id; list_add_tail(&pla->list, &vha->plogi_ack_list); return pla; } -static void qlt_plogi_ack_unref(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla) +void qlt_plogi_ack_unref(struct scsi_qla_host *vha, + struct qlt_plogi_ack_t *pla) { + struct imm_ntfy_from_isp *iocb = &pla->iocb; + port_id_t port_id; + uint16_t loop_id; + fc_port_t *fcport = pla->fcport; + BUG_ON(!pla->ref_count); pla->ref_count--; if (pla->ref_count) return; - ql_dbg(ql_dbg_async, vha, 0x5089, + ql_dbg(ql_dbg_disc, vha, 0x5089, "Sending PLOGI ACK to wwn %8phC s_id %02x:%02x:%02x loop_id %#04x" - " exch %#x ox_id %#x\n", pla->iocb.u.isp24.port_name, - pla->iocb.u.isp24.port_id[2], pla->iocb.u.isp24.port_id[1], - pla->iocb.u.isp24.port_id[0], - le16_to_cpu(pla->iocb.u.isp24.nport_handle), - pla->iocb.u.isp24.exchange_address, pla->iocb.ox_id); - qlt_send_notify_ack(vha, &pla->iocb, 0, 0, 0, 0, 0, 0); + " exch %#x ox_id %#x\n", iocb->u.isp24.port_name, + iocb->u.isp24.port_id[2], iocb->u.isp24.port_id[1], + iocb->u.isp24.port_id[0], + le16_to_cpu(iocb->u.isp24.nport_handle), + iocb->u.isp24.exchange_address, iocb->ox_id); + + port_id.b.domain = iocb->u.isp24.port_id[2]; + port_id.b.area = iocb->u.isp24.port_id[1]; + port_id.b.al_pa = iocb->u.isp24.port_id[0]; + port_id.b.rsvd_1 = 0; + + loop_id = le16_to_cpu(iocb->u.isp24.nport_handle); + + fcport->loop_id = loop_id; + fcport->d_id = port_id; + qla24xx_post_nack_work(vha, fcport, iocb, SRB_NACK_PLOGI); + + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (fcport->plogi_link[QLT_PLOGI_LINK_SAME_WWN] == pla) + fcport->plogi_link[QLT_PLOGI_LINK_SAME_WWN] = NULL; + if (fcport->plogi_link[QLT_PLOGI_LINK_CONFLICT] == pla) + fcport->plogi_link[QLT_PLOGI_LINK_CONFLICT] = NULL; + } list_del(&pla->list); kmem_cache_free(qla_tgt_plogi_cachep, pla); } -static void -qlt_plogi_ack_link(struct scsi_qla_host *vha, qlt_plogi_ack_t *pla, - struct qla_tgt_sess *sess, qlt_plogi_link_t link) +void +qlt_plogi_ack_link(struct scsi_qla_host *vha, struct qlt_plogi_ack_t *pla, + struct fc_port *sess, enum qlt_plogi_link_t link) { + struct imm_ntfy_from_isp *iocb = &pla->iocb; /* Inc ref_count first because link might already be pointing at pla */ pla->ref_count++; + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf097, + "Linking sess %p [%d] wwn %8phC with PLOGI ACK to wwn %8phC" + " s_id %02x:%02x:%02x, ref=%d pla %p link %d\n", + sess, link, sess->port_name, + iocb->u.isp24.port_name, iocb->u.isp24.port_id[2], + iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0], + pla->ref_count, pla, link); + if (sess->plogi_link[link]) qlt_plogi_ack_unref(vha, sess->plogi_link[link]); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf097, - "Linking sess %p [%d] wwn %8phC with PLOGI ACK to wwn %8phC" - " s_id %02x:%02x:%02x, ref=%d\n", sess, link, sess->port_name, - pla->iocb.u.isp24.port_name, pla->iocb.u.isp24.port_id[2], - pla->iocb.u.isp24.port_id[1], pla->iocb.u.isp24.port_id[0], - pla->ref_count); + if (link == QLT_PLOGI_LINK_SAME_WWN) + pla->fcport = sess; sess->plogi_link[link] = pla; } @@ -519,49 +913,45 @@ qlt_send_first_logo(struct scsi_qla_host *vha, qlt_port_logo_t *logo) static void qlt_free_session_done(struct work_struct *work) { - struct qla_tgt_sess *sess = container_of(work, struct qla_tgt_sess, + struct fc_port *sess = container_of(work, struct fc_port, free_work); struct qla_tgt *tgt = sess->tgt; struct scsi_qla_host *vha = sess->vha; struct qla_hw_data *ha = vha->hw; unsigned long flags; bool logout_started = false; - fc_port_t fcport; + struct event_arg ea; + scsi_qla_host_t *base_vha; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084, "%s: se_sess %p / sess %p from port %8phC loop_id %#04x" " s_id %02x:%02x:%02x logout %d keep %d els_logo %d\n", __func__, sess->se_sess, sess, sess->port_name, sess->loop_id, - sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, + sess->d_id.b.domain, sess->d_id.b.area, sess->d_id.b.al_pa, sess->logout_on_delete, sess->keep_nport_handle, sess->send_els_logo); - BUG_ON(!tgt); - if (sess->send_els_logo) { - qlt_port_logo_t logo; - logo.id = sess->s_id; - logo.cmd_count = 0; - qlt_send_first_logo(vha, &logo); - } + if (!IS_SW_RESV_ADDR(sess->d_id)) { + if (sess->send_els_logo) { + qlt_port_logo_t logo; - if (sess->logout_on_delete) { - int rc; + logo.id = sess->d_id; + logo.cmd_count = 0; + qlt_send_first_logo(vha, &logo); + } - memset(&fcport, 0, sizeof(fcport)); - fcport.loop_id = sess->loop_id; - fcport.d_id = sess->s_id; - memcpy(fcport.port_name, sess->port_name, WWN_SIZE); - fcport.vha = vha; - fcport.tgt_session = sess; - - rc = qla2x00_post_async_logout_work(vha, &fcport, NULL); - if (rc != QLA_SUCCESS) - ql_log(ql_log_warn, vha, 0xf085, - "Schedule logo failed sess %p rc %d\n", - sess, rc); - else - logout_started = true; + if (sess->logout_on_delete) { + int rc; + + rc = qla2x00_post_async_logout_work(vha, sess, NULL); + if (rc != QLA_SUCCESS) + ql_log(ql_log_warn, vha, 0xf085, + "Schedule logo failed sess %p rc %d\n", + sess, rc); + else + logout_started = true; + } } /* @@ -583,29 +973,61 @@ static void qlt_free_session_done(struct work_struct *work) msleep(100); } - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087, - "%s: sess %p logout completed\n", - __func__, sess); + ql_dbg(ql_dbg_disc, vha, 0xf087, + "%s: sess %p logout completed\n",__func__, sess); } - spin_lock_irqsave(&ha->hardware_lock, flags); + if (sess->logo_ack_needed) { + sess->logo_ack_needed = 0; + qla24xx_async_notify_ack(vha, sess, + (struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO); + } + + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + if (sess->se_sess) { + sess->se_sess = NULL; + if (tgt && !IS_SW_RESV_ADDR(sess->d_id)) + tgt->sess_count--; + } + + sess->disc_state = DSC_DELETED; + sess->fw_login_state = DSC_LS_PORT_UNAVAIL; + sess->deleted = QLA_SESS_DELETED; + sess->login_retry = vha->hw->login_retry_count; + + if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) { + vha->fcport_count--; + sess->login_succ = 0; + } + + if (sess->chip_reset != sess->vha->hw->chip_reset) + qla2x00_clear_loop_id(sess); + + if (sess->conflict) { + sess->conflict->login_pause = 0; + sess->conflict = NULL; + if (!test_bit(UNLOADING, &vha->dpc_flags)) + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + } { - qlt_plogi_ack_t *own = + struct qlt_plogi_ack_t *own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN]; - qlt_plogi_ack_t *con = + struct qlt_plogi_ack_t *con = sess->plogi_link[QLT_PLOGI_LINK_CONFLICT]; + struct imm_ntfy_from_isp *iocb; if (con) { + iocb = &con->iocb; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf099, - "se_sess %p / sess %p port %8phC is gone," - " %s (ref=%d), releasing PLOGI for %8phC (ref=%d)\n", - sess->se_sess, sess, sess->port_name, - own ? "releasing own PLOGI" : - "no own PLOGI pending", - own ? own->ref_count : -1, - con->iocb.u.isp24.port_name, con->ref_count); + "se_sess %p / sess %p port %8phC is gone," + " %s (ref=%d), releasing PLOGI for %8phC (ref=%d)\n", + sess->se_sess, sess, sess->port_name, + own ? "releasing own PLOGI" : "no own PLOGI pending", + own ? own->ref_count : -1, + iocb->u.isp24.port_name, con->ref_count); qlt_plogi_ack_unref(vha, con); + sess->plogi_link[QLT_PLOGI_LINK_CONFLICT] = NULL; } else { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf09a, "se_sess %p / sess %p port %8phC is gone, %s (ref=%d)\n", @@ -615,59 +1037,64 @@ static void qlt_free_session_done(struct work_struct *work) own ? own->ref_count : -1); } - if (own) + if (own) { + sess->fw_login_state = DSC_LS_PLOGI_PEND; qlt_plogi_ack_unref(vha, own); + sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN] = NULL; + } } - - list_del(&sess->sess_list_entry); - - spin_unlock_irqrestore(&ha->hardware_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, - "Unregistration of sess %p finished\n", sess); + "Unregistration of sess %p %8phC finished fcp_cnt %d\n", + sess, sess->port_name, vha->fcport_count); - kfree(sess); - /* - * We need to protect against race, when tgt is freed before or - * inside wake_up() - */ - tgt->sess_count--; - if (tgt->sess_count == 0) + if (tgt && (tgt->sess_count == 0)) wake_up_all(&tgt->waitQ); + + if (vha->fcport_count == 0) + wake_up_all(&vha->fcport_waitQ); + + base_vha = pci_get_drvdata(ha->pdev); + if (test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags)) + return; + + if (!tgt || !tgt->tgt_stop) { + memset(&ea, 0, sizeof(ea)); + ea.event = FCME_DELETE_DONE; + ea.fcport = sess; + qla2x00_fcport_event_handler(vha, &ea); + } } /* ha->tgt.sess_lock supposed to be held on entry */ -static void qlt_release_session(struct kref *kref) +void qlt_unreg_sess(struct fc_port *sess) { - struct qla_tgt_sess *sess = - container_of(kref, struct qla_tgt_sess, sess_kref); struct scsi_qla_host *vha = sess->vha; + ql_dbg(ql_dbg_disc, sess->vha, 0xffff, + "%s sess %p for deletion %8phC\n", + __func__, sess, sess->port_name); + if (sess->se_sess) vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess); - if (!list_empty(&sess->del_list_entry)) - list_del_init(&sess->del_list_entry); + qla2x00_mark_device_lost(vha, sess, 1, 1); + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; + sess->disc_state = DSC_DELETE_PEND; + sess->last_rscn_gen = sess->rscn_gen; + sess->last_login_gen = sess->login_gen; INIT_WORK(&sess->free_work, qlt_free_session_done); schedule_work(&sess->free_work); } - -void qlt_put_sess(struct qla_tgt_sess *sess) -{ - if (!sess) - return; - - assert_spin_locked(&sess->vha->hw->tgt.sess_lock); - kref_put(&sess->sess_kref, qlt_release_session); -} -EXPORT_SYMBOL(qlt_put_sess); +EXPORT_SYMBOL(qlt_unreg_sess); static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd) { struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; uint16_t loop_id; int res = 0; struct imm_ntfy_from_isp *n = (struct imm_ntfy_from_isp *)iocb; @@ -680,31 +1107,6 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd) spin_lock_irqsave(&ha->tgt.sess_lock, flags); qlt_clear_tgt_db(vha->vha_tgt.qla_tgt); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); -#if 0 /* FIXME: do we need to choose a session here? */ - if (!list_empty(&ha->tgt.qla_tgt->sess_list)) { - sess = list_entry(ha->tgt.qla_tgt->sess_list.next, - typeof(*sess), sess_list_entry); - switch (mcmd) { - case QLA_TGT_NEXUS_LOSS_SESS: - mcmd = QLA_TGT_NEXUS_LOSS; - break; - case QLA_TGT_ABORT_ALL_SESS: - mcmd = QLA_TGT_ABORT_ALL; - break; - case QLA_TGT_NEXUS_LOSS: - case QLA_TGT_ABORT_ALL: - break; - default: - ql_dbg(ql_dbg_tgt, vha, 0xe046, - "qla_target(%d): Not allowed " - "command %x in %s", vha->vp_idx, - mcmd, __func__); - sess = NULL; - break; - } - } else - sess = NULL; -#endif } else { spin_lock_irqsave(&ha->tgt.sess_lock, flags); sess = ha->tgt.tgt_ops->find_sess_by_loop_id(vha, loop_id); @@ -726,57 +1128,69 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd) return qlt_issue_task_mgmt(sess, 0, mcmd, iocb, QLA24XX_MGMT_SEND_NACK); } +static void qla24xx_chk_fcp_state(struct fc_port *sess) +{ + if (sess->chip_reset != sess->vha->hw->chip_reset) { + sess->logout_on_delete = 0; + sess->logo_ack_needed = 0; + sess->fw_login_state = DSC_LS_PORT_UNAVAIL; + sess->scan_state = 0; + } +} + /* ha->tgt.sess_lock supposed to be held on entry */ -static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess, +void qlt_schedule_sess_for_deletion(struct fc_port *sess, bool immediate) { struct qla_tgt *tgt = sess->tgt; - uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5; - if (sess->deleted) { - /* Upgrade to unconditional deletion in case it was temporary */ - if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING) - list_del(&sess->del_list_entry); - else + if (sess->disc_state == DSC_DELETE_PEND) + return; + + if (sess->disc_state == DSC_DELETED) { + if (tgt && tgt->tgt_stop && (tgt->sess_count == 0)) + wake_up_all(&tgt->waitQ); + if (sess->vha->fcport_count == 0) + wake_up_all(&sess->vha->fcport_waitQ); + + if (!sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN] && + !sess->plogi_link[QLT_PLOGI_LINK_CONFLICT]) return; } - ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, - "Scheduling sess %p for deletion\n", sess); + sess->disc_state = DSC_DELETE_PEND; - if (immediate) { - dev_loss_tmo = 0; - sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; - list_add(&sess->del_list_entry, &tgt->del_sess_list); - } else { - sess->deleted = QLA_SESS_DELETION_PENDING; - list_add_tail(&sess->del_list_entry, &tgt->del_sess_list); - } + if (sess->deleted == QLA_SESS_DELETED) + sess->logout_on_delete = 0; - sess->expires = jiffies + dev_loss_tmo * HZ; + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; + qla24xx_chk_fcp_state(sess); - ql_dbg(ql_dbg_tgt, sess->vha, 0xe048, - "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)" - " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n", - sess->vha->vp_idx, sess->port_name, sess->loop_id, - sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, - dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete, - sess->generation); + ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, + "Scheduling sess %p for deletion\n", sess); - if (immediate) - mod_delayed_work(system_wq, &tgt->sess_del_work, 0); - else - schedule_delayed_work(&tgt->sess_del_work, - sess->expires - jiffies); + schedule_work(&sess->del_work); +} + +void qlt_schedule_sess_for_deletion_lock(struct fc_port *sess) +{ + unsigned long flags; + struct qla_hw_data *ha = sess->vha->hw; + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + qlt_schedule_sess_for_deletion(sess, 1); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } /* ha->tgt.sess_lock supposed to be held on entry */ static void qlt_clear_tgt_db(struct qla_tgt *tgt) { - struct qla_tgt_sess *sess; + struct fc_port *sess; + scsi_qla_host_t *vha = tgt->vha; - list_for_each_entry(sess, &tgt->sess_list, sess_list_entry) - qlt_schedule_sess_for_deletion(sess, true); + list_for_each_entry(sess, &vha->vp_fcports, list) { + if (sess->se_sess) + qlt_schedule_sess_for_deletion(sess, 1); + } /* At this point tgt could be already dead */ } @@ -830,240 +1244,84 @@ out_free_id_list: return res; } -/* ha->tgt.sess_lock supposed to be held on entry */ -static void qlt_undelete_sess(struct qla_tgt_sess *sess) -{ - BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING); - - list_del_init(&sess->del_list_entry); - sess->deleted = 0; -} - -static void qlt_del_sess_work_fn(struct delayed_work *work) -{ - struct qla_tgt *tgt = container_of(work, struct qla_tgt, - sess_del_work); - struct scsi_qla_host *vha = tgt->vha; - struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; - unsigned long flags, elapsed; - - spin_lock_irqsave(&ha->tgt.sess_lock, flags); - while (!list_empty(&tgt->del_sess_list)) { - sess = list_entry(tgt->del_sess_list.next, typeof(*sess), - del_list_entry); - elapsed = jiffies; - if (time_after_eq(elapsed, sess->expires)) { - /* No turning back */ - list_del_init(&sess->del_list_entry); - sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004, - "Timeout: sess %p about to be deleted\n", - sess); - if (sess->se_sess) - ha->tgt.tgt_ops->shutdown_sess(sess); - qlt_put_sess(sess); - } else { - schedule_delayed_work(&tgt->sess_del_work, - sess->expires - elapsed); - break; - } - } - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); -} - /* * Adds an extra ref to allow to drop hw lock after adding sess to the list. * Caller must put it. */ -static struct qla_tgt_sess *qlt_create_sess( +static struct fc_port *qlt_create_sess( struct scsi_qla_host *vha, fc_port_t *fcport, bool local) { struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; + struct fc_port *sess = fcport; unsigned long flags; - /* Check to avoid double sessions */ - spin_lock_irqsave(&ha->tgt.sess_lock, flags); - list_for_each_entry(sess, &vha->vha_tgt.qla_tgt->sess_list, - sess_list_entry) { - if (!memcmp(sess->port_name, fcport->port_name, WWN_SIZE)) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf005, - "Double sess %p found (s_id %x:%x:%x, " - "loop_id %d), updating to d_id %x:%x:%x, " - "loop_id %d", sess, sess->s_id.b.domain, - sess->s_id.b.al_pa, sess->s_id.b.area, - sess->loop_id, fcport->d_id.b.domain, - fcport->d_id.b.al_pa, fcport->d_id.b.area, - fcport->loop_id); - - /* Cannot undelete at this point */ - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { - spin_unlock_irqrestore(&ha->tgt.sess_lock, - flags); - return NULL; - } - - if (sess->deleted) - qlt_undelete_sess(sess); - - if (!sess->se_sess) { - if (ha->tgt.tgt_ops->check_initiator_node_acl(vha, - &sess->port_name[0], sess) < 0) { - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - return NULL; - } - } - - kref_get(&sess->sess_kref); - ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, fcport->loop_id, - (fcport->flags & FCF_CONF_COMP_SUPPORTED)); - - if (sess->local && !local) - sess->local = 0; - - qlt_do_generation_tick(vha, &sess->generation); - - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + if (vha->vha_tgt.qla_tgt->tgt_stop) + return NULL; - return sess; + if (fcport->se_sess) { + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: kref_get_unless_zero failed for %8phC\n", + __func__, sess->port_name); + return NULL; } - } - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - - sess = kzalloc(sizeof(*sess), GFP_KERNEL); - if (!sess) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04a, - "qla_target(%u): session allocation failed, all commands " - "from port %8phC will be refused", vha->vp_idx, - fcport->port_name); - - return NULL; + return fcport; } sess->tgt = vha->vha_tgt.qla_tgt; - sess->vha = vha; - sess->s_id = fcport->d_id; - sess->loop_id = fcport->loop_id; sess->local = local; - kref_init(&sess->sess_kref); - INIT_LIST_HEAD(&sess->del_list_entry); - /* Under normal circumstances we want to logout from firmware when + /* + * Under normal circumstances we want to logout from firmware when * session eventually ends and release corresponding nport handle. * In the exception cases (e.g. when new PLOGI is waiting) corresponding - * code will adjust these flags as necessary. */ + * code will adjust these flags as necessary. + */ sess->logout_on_delete = 1; sess->keep_nport_handle = 0; + sess->logout_completed = 0; - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006, - "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n", - sess, vha->vha_tgt.qla_tgt); - - sess->conf_compl_supported = (fcport->flags & FCF_CONF_COMP_SUPPORTED); - BUILD_BUG_ON(sizeof(sess->port_name) != sizeof(fcport->port_name)); - memcpy(sess->port_name, fcport->port_name, sizeof(sess->port_name)); - - spin_lock_irqsave(&ha->tgt.sess_lock, flags); - list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list); - vha->vha_tgt.qla_tgt->sess_count++; - qlt_do_generation_tick(vha, &sess->generation); - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b, - "qla_target(%d): %ssession for wwn %8phC (loop_id %d, " - "s_id %x:%x:%x, confirmed completion %ssupported) added\n", - vha->vp_idx, local ? "local " : "", fcport->port_name, - fcport->loop_id, sess->s_id.b.domain, sess->s_id.b.area, - sess->s_id.b.al_pa, sess->conf_compl_supported ? "" : "not "); - - /* - * Determine if this fc_port->port_name is allowed to access - * target mode using explict NodeACLs+MappedLUNs, or using - * TPG demo mode. If this is successful a target mode FC nexus - * is created. - */ if (ha->tgt.tgt_ops->check_initiator_node_acl(vha, &fcport->port_name[0], sess) < 0) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff, + "(%d) %8phC check_initiator_node_acl failed\n", + vha->vp_idx, fcport->port_name); return NULL; } else { + kref_init(&fcport->sess_kref); /* - * Take an extra reference to ->sess_kref here to handle qla_tgt_sess - * access across ->tgt.sess_lock reaquire. + * Take an extra reference to ->sess_kref here to handle + * fc_port access across ->tgt.sess_lock reaquire. */ - kref_get(&sess->sess_kref); - } - - return sess; -} - -/* - * Called from qla2x00_reg_remote_port() - */ -void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) -{ - struct qla_hw_data *ha = vha->hw; - struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_sess *sess; - unsigned long flags; - - if (!vha->hw->tgt.tgt_ops) - return; - - if (!tgt || (fcport->port_type != FCT_INITIATOR)) - return; + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: kref_get_unless_zero failed for %8phC\n", + __func__, sess->port_name); + return NULL; + } - if (qla_ini_mode_enabled(vha)) - return; + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + if (!IS_SW_RESV_ADDR(sess->d_id)) + vha->vha_tgt.qla_tgt->sess_count++; - spin_lock_irqsave(&ha->tgt.sess_lock, flags); - if (tgt->tgt_stop) { + qlt_do_generation_tick(vha, &sess->generation); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - return; } - sess = qlt_find_sess_by_port_name(tgt, fcport->port_name); - if (!sess) { - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - - mutex_lock(&vha->vha_tgt.tgt_mutex); - sess = qlt_create_sess(vha, fcport, false); - mutex_unlock(&vha->vha_tgt.tgt_mutex); - spin_lock_irqsave(&ha->tgt.sess_lock, flags); - } else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { - /* Point of no return */ - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - return; - } else { - kref_get(&sess->sess_kref); - - if (sess->deleted) { - qlt_undelete_sess(sess); - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04c, - "qla_target(%u): %ssession for port %8phC " - "(loop ID %d) reappeared\n", vha->vp_idx, - sess->local ? "local " : "", sess->port_name, - sess->loop_id); + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006, + "Adding sess %p se_sess %p to tgt %p sess_count %d\n", + sess, sess->se_sess, vha->vha_tgt.qla_tgt, + vha->vha_tgt.qla_tgt->sess_count); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf007, - "Reappeared sess %p\n", sess); - } - ha->tgt.tgt_ops->update_sess(sess, fcport->d_id, fcport->loop_id, - (fcport->flags & FCF_CONF_COMP_SUPPORTED)); - } + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b, + "qla_target(%d): %ssession for wwn %8phC (loop_id %d, " + "s_id %x:%x:%x, confirmed completion %ssupported) added\n", + vha->vp_idx, local ? "local " : "", fcport->port_name, + fcport->loop_id, sess->d_id.b.domain, sess->d_id.b.area, + sess->d_id.b.al_pa, sess->conf_compl_supported ? "" : "not "); - if (sess && sess->local) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04d, - "qla_target(%u): local session for " - "port %8phC (loop ID %d) became global\n", vha->vp_idx, - fcport->port_name, sess->loop_id); - sess->local = 0; - } - qlt_put_sess(sess); - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + return sess; } /* @@ -1074,7 +1332,7 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_sess *sess; + struct fc_port *sess = fcport; unsigned long flags; if (!vha->hw->tgt.tgt_ops) @@ -1088,8 +1346,7 @@ qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); return; } - sess = qlt_find_sess_by_port_name(tgt, fcport->port_name); - if (!sess) { + if (!sess->se_sess) { spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); return; } @@ -1120,12 +1377,12 @@ static inline int test_tgt_sess_count(struct qla_tgt *tgt) * We need to protect against race, when tgt is freed before or * inside wake_up() */ - spin_lock_irqsave(&ha->hardware_lock, flags); + spin_lock_irqsave(&ha->tgt.sess_lock, flags); ql_dbg(ql_dbg_tgt, tgt->vha, 0xe002, - "tgt %p, empty(sess_list)=%d sess_count=%d\n", - tgt, list_empty(&tgt->sess_list), tgt->sess_count); + "tgt %p, sess_count=%d\n", + tgt, tgt->sess_count); res = (tgt->sess_count == 0); - spin_unlock_irqrestore(&ha->hardware_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return res; } @@ -1173,8 +1430,6 @@ int qlt_stop_phase1(struct qla_tgt *tgt) mutex_unlock(&vha->vha_tgt.tgt_mutex); mutex_unlock(&qla_tgt_mutex); - flush_delayed_work(&tgt->sess_del_work); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf009, "Waiting for sess works (tgt %p)", tgt); spin_lock_irqsave(&tgt->sess_work_lock, flags); @@ -1186,14 +1441,13 @@ int qlt_stop_phase1(struct qla_tgt *tgt) spin_unlock_irqrestore(&tgt->sess_work_lock, flags); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00a, - "Waiting for tgt %p: list_empty(sess_list)=%d " - "sess_count=%d\n", tgt, list_empty(&tgt->sess_list), - tgt->sess_count); + "Waiting for tgt %p: sess_count=%d\n", tgt, tgt->sess_count); wait_event(tgt->waitQ, test_tgt_sess_count(tgt)); /* Big hammer */ - if (!ha->flags.host_shutting_down && qla_tgt_mode_enabled(vha)) + if (!ha->flags.host_shutting_down && + (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha))) qlt_disable_vha(vha); /* Wait for sessions to clear out (just in case) */ @@ -1320,6 +1574,7 @@ static void qlt_send_notify_ack(struct scsi_qla_host *vha, nack = (struct nack_to_isp *)pkt; nack->ox_id = ntfy->ox_id; + nack->u.isp24.handle = QLA_TGT_SKIP_HANDLE; nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle; if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) { nack->u.isp24.flags = ntfy->u.isp24.flags & @@ -1489,6 +1744,14 @@ static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag) } } + list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) { + if (tag == op->atio.u.isp24.exchange_addr) { + op->aborted = true; + spin_unlock(&vha->cmd_list_lock); + return 1; + } + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { if (tag == cmd->atio.u.isp24.exchange_addr) { cmd->aborted = 1; @@ -1525,6 +1788,18 @@ static void abort_cmds_for_lun(struct scsi_qla_host *vha, if (op_key == key && op_lun == lun) op->aborted = true; } + + list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) { + uint32_t op_key; + u64 op_lun; + + op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + op_lun = scsilun_to_int( + (struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun); + if (op_key == key && op_lun == lun) + op->aborted = true; + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { uint32_t cmd_key; uint32_t cmd_lun; @@ -1540,7 +1815,7 @@ static void abort_cmds_for_lun(struct scsi_qla_host *vha, /* ha->hardware_lock supposed to be held on entry */ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, - struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess) + struct abts_recv_from_24xx *abts, struct fc_port *sess) { struct qla_hw_data *ha = vha->hw; struct se_session *se_sess = sess->se_sess; @@ -1549,8 +1824,9 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, u32 lun = 0; int rc; bool found_lun = false; + unsigned long flags; - spin_lock(&se_sess->sess_cmd_lock); + spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); @@ -1560,7 +1836,7 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, break; } } - spin_unlock(&se_sess->sess_cmd_lock); + spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); /* cmd not in LIO lists, look in qla list */ if (!found_lun) { @@ -1592,8 +1868,9 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, mcmd->sess = sess; memcpy(&mcmd->orig_iocb.abts, abts, sizeof(mcmd->orig_iocb.abts)); mcmd->reset_count = vha->hw->chip_reset; + mcmd->tmr_func = QLA_TGT_ABTS; - rc = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, TMR_ABORT_TASK, + rc = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, mcmd->tmr_func, abts->exchange_addr_to_abort); if (rc != 0) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf052, @@ -1613,7 +1890,7 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha, struct abts_recv_from_24xx *abts) { struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; + struct fc_port *sess; uint32_t tag = abts->exchange_addr_to_abort; uint8_t s_id[3]; int rc; @@ -1665,7 +1942,7 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha, spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + if (sess->deleted) { qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false); return; } @@ -1763,10 +2040,23 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd) return; } - if (mcmd->flags == QLA24XX_MGMT_SEND_NACK) - qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy, - 0, 0, 0, 0, 0, 0); - else { + if (mcmd->flags == QLA24XX_MGMT_SEND_NACK) { + if (mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode == + ELS_LOGO || + mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode == + ELS_PRLO || + mcmd->orig_iocb.imm_ntfy.u.isp24.status_subcode == + ELS_TPRLO) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "TM response logo %phC status %#x state %#x", + mcmd->sess->port_name, mcmd->fc_tm_rsp, + mcmd->flags); + qlt_schedule_sess_for_deletion_lock(mcmd->sess); + } else { + qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy, + 0, 0, 0, 0, 0, 0); + } + } else { if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX) qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts, mcmd->fc_tm_rsp, false); @@ -2182,95 +2472,6 @@ static inline int qlt_need_explicit_conf(struct qla_hw_data *ha, cmd->conf_compl_supported; } -#ifdef CONFIG_QLA_TGT_DEBUG_SRR -/* - * Original taken from the XFS code - */ -static unsigned long qlt_srr_random(void) -{ - static int Inited; - static unsigned long RandomValue; - static DEFINE_SPINLOCK(lock); - /* cycles pseudo-randomly through all values between 1 and 2^31 - 2 */ - register long rv; - register long lo; - register long hi; - unsigned long flags; - - spin_lock_irqsave(&lock, flags); - if (!Inited) { - RandomValue = jiffies; - Inited = 1; - } - rv = RandomValue; - hi = rv / 127773; - lo = rv % 127773; - rv = 16807 * lo - 2836 * hi; - if (rv <= 0) - rv += 2147483647; - RandomValue = rv; - spin_unlock_irqrestore(&lock, flags); - return rv; -} - -static void qlt_check_srr_debug(struct qla_tgt_cmd *cmd, int *xmit_type) -{ -#if 0 /* This is not a real status packets lost, so it won't lead to SRR */ - if ((*xmit_type & QLA_TGT_XMIT_STATUS) && (qlt_srr_random() % 200) - == 50) { - *xmit_type &= ~QLA_TGT_XMIT_STATUS; - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf015, - "Dropping cmd %p (tag %d) status", cmd, se_cmd->tag); - } -#endif - /* - * It's currently not possible to simulate SRRs for FCP_WRITE without - * a physical link layer failure, so don't even try here.. - */ - if (cmd->dma_data_direction != DMA_FROM_DEVICE) - return; - - if (qlt_has_data(cmd) && (cmd->sg_cnt > 1) && - ((qlt_srr_random() % 100) == 20)) { - int i, leave = 0; - unsigned int tot_len = 0; - - while (leave == 0) - leave = qlt_srr_random() % cmd->sg_cnt; - - for (i = 0; i < leave; i++) - tot_len += cmd->sg[i].length; - - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf016, - "Cutting cmd %p (tag %d) buffer" - " tail to len %d, sg_cnt %d (cmd->bufflen %d," - " cmd->sg_cnt %d)", cmd, se_cmd->tag, tot_len, leave, - cmd->bufflen, cmd->sg_cnt); - - cmd->bufflen = tot_len; - cmd->sg_cnt = leave; - } - - if (qlt_has_data(cmd) && ((qlt_srr_random() % 100) == 70)) { - unsigned int offset = qlt_srr_random() % cmd->bufflen; - - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf017, - "Cutting cmd %p (tag %d) buffer head " - "to offset %d (cmd->bufflen %d)", cmd, se_cmd->tag, offset, - cmd->bufflen); - if (offset == 0) - *xmit_type &= ~QLA_TGT_XMIT_DATA; - else if (qlt_set_data_offset(cmd, offset)) { - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf018, - "qlt_set_data_offset() failed (tag %d)", se_cmd->tag); - } - } -} -#else -static inline void qlt_check_srr_debug(struct qla_tgt_cmd *cmd, int *xmit_type) -{} -#endif - static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio, struct qla_tgt_prm *prm) { @@ -2288,7 +2489,7 @@ static void qlt_24xx_init_ctio_to_isp(struct ctio7_to_24xx *ctio, int i; if (qlt_need_explicit_conf(prm->tgt->ha, prm->cmd, 1)) { - if (prm->cmd->se_cmd.scsi_status != 0) { + if ((prm->rq_result & SS_SCSI_STATUS_BYTE) != 0) { ql_dbg(ql_dbg_tgt, prm->cmd->vha, 0xe017, "Skipping EXPLICIT_CONFORM and " "CTIO7_FLAGS_CONFORM_REQ for FCP READ w/ " @@ -2672,7 +2873,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, int res; spin_lock_irqsave(&ha->hardware_lock, flags); - if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + if (cmd->sess && cmd->sess->deleted) { cmd->state = QLA_TGT_STATE_PROCESSED; if (cmd->sess->logout_completed) /* no need to terminate. FW already freed exchange. */ @@ -2685,7 +2886,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, spin_unlock_irqrestore(&ha->hardware_lock, flags); memset(&prm, 0, sizeof(prm)); - qlt_check_srr_debug(cmd, &xmit_type); ql_dbg(ql_dbg_tgt, cmd->vha, 0xe018, "is_send_status=%d, cmd->bufflen=%d, cmd->sg_cnt=%d, cmd->dma_data_direction=%d se_cmd[%p]\n", @@ -2848,7 +3048,7 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&ha->hardware_lock, flags); if (!vha->flags.online || (cmd->reset_count != ha->chip_reset) || - (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) { + (cmd->sess && cmd->sess->deleted)) { /* * Either the port is not online or this request was from * previous life, just abort the processing. @@ -3296,7 +3496,7 @@ int qlt_abort_cmd(struct qla_tgt_cmd *cmd) return EIO; } cmd->aborted = 1; - cmd->cmd_flags |= BIT_6; + cmd->trc_flags |= TRC_ABORT; spin_unlock_irqrestore(&cmd->cmd_lock, flags); qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1); @@ -3306,7 +3506,7 @@ EXPORT_SYMBOL(qlt_abort_cmd); void qlt_free_cmd(struct qla_tgt_cmd *cmd) { - struct qla_tgt_sess *sess = cmd->sess; + struct fc_port *sess = cmd->sess; ql_dbg(ql_dbg_tgt, cmd->vha, 0xe074, "%s: se_cmd[%p] ox_id %04x\n", @@ -3335,90 +3535,6 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd) } EXPORT_SYMBOL(qlt_free_cmd); -/* ha->hardware_lock supposed to be held on entry */ -static int qlt_prepare_srr_ctio(struct scsi_qla_host *vha, - struct qla_tgt_cmd *cmd, void *ctio) -{ - struct qla_tgt_srr_ctio *sc; - struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_srr_imm *imm; - - tgt->ctio_srr_id++; - cmd->cmd_flags |= BIT_15; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf019, - "qla_target(%d): CTIO with SRR status received\n", vha->vp_idx); - - if (!ctio) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf055, - "qla_target(%d): SRR CTIO, but ctio is NULL\n", - vha->vp_idx); - return -EINVAL; - } - - sc = kzalloc(sizeof(*sc), GFP_ATOMIC); - if (sc != NULL) { - sc->cmd = cmd; - /* IRQ is already OFF */ - spin_lock(&tgt->srr_lock); - sc->srr_id = tgt->ctio_srr_id; - list_add_tail(&sc->srr_list_entry, - &tgt->srr_ctio_list); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01a, - "CTIO SRR %p added (id %d)\n", sc, sc->srr_id); - if (tgt->imm_srr_id == tgt->ctio_srr_id) { - int found = 0; - list_for_each_entry(imm, &tgt->srr_imm_list, - srr_list_entry) { - if (imm->srr_id == sc->srr_id) { - found = 1; - break; - } - } - if (found) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01b, - "Scheduling srr work\n"); - schedule_work(&tgt->srr_work); - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf056, - "qla_target(%d): imm_srr_id " - "== ctio_srr_id (%d), but there is no " - "corresponding SRR IMM, deleting CTIO " - "SRR %p\n", vha->vp_idx, - tgt->ctio_srr_id, sc); - list_del(&sc->srr_list_entry); - spin_unlock(&tgt->srr_lock); - - kfree(sc); - return -EINVAL; - } - } - spin_unlock(&tgt->srr_lock); - } else { - struct qla_tgt_srr_imm *ti; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf057, - "qla_target(%d): Unable to allocate SRR CTIO entry\n", - vha->vp_idx); - spin_lock(&tgt->srr_lock); - list_for_each_entry_safe(imm, ti, &tgt->srr_imm_list, - srr_list_entry) { - if (imm->srr_id == tgt->ctio_srr_id) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01c, - "IMM SRR %p deleted (id %d)\n", - imm, imm->srr_id); - list_del(&imm->srr_list_entry); - qlt_reject_free_srr_imm(vha, imm, 1); - } - } - spin_unlock(&tgt->srr_lock); - - return -ENOMEM; - } - - return 0; -} - /* * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire */ @@ -3527,7 +3643,7 @@ qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd) dump_stack(); } - cmd->cmd_flags |= BIT_17; + cmd->trc_flags |= TRC_FLUSH; ha->tgt.tgt_ops->free_cmd(cmd); } @@ -3632,20 +3748,14 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle, */ cmd->sess->logout_on_delete = 0; cmd->sess->send_els_logo = 1; - qlt_schedule_sess_for_deletion(cmd->sess, true); + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, cmd->sess->port_name); + + qlt_schedule_sess_for_deletion_lock(cmd->sess); } break; } - case CTIO_SRR_RECEIVED: - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05a, - "qla_target(%d): CTIO with SRR_RECEIVED" - " status %x received (state %x, se_cmd %p)\n", - vha->vp_idx, status, cmd->state, se_cmd); - if (qlt_prepare_srr_ctio(vha, cmd, ctio) != 0) - break; - else - return; - case CTIO_DIF_ERROR: { struct ctio_crc_from_fw *crc = (struct ctio_crc_from_fw *)ctio; @@ -3693,7 +3803,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle, */ if ((cmd->state != QLA_TGT_STATE_NEED_DATA) && (!cmd->aborted)) { - cmd->cmd_flags |= BIT_13; + cmd->trc_flags |= TRC_CTIO_ERR; if (qlt_term_ctio_exchange(vha, ctio, cmd, status)) return; } @@ -3701,7 +3811,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle, skip_term: if (cmd->state == QLA_TGT_STATE_PROCESSED) { - cmd->cmd_flags |= BIT_12; + cmd->trc_flags |= TRC_CTIO_DONE; } else if (cmd->state == QLA_TGT_STATE_NEED_DATA) { cmd->state = QLA_TGT_STATE_DATA_IN; @@ -3711,11 +3821,11 @@ skip_term: ha->tgt.tgt_ops->handle_data(cmd); return; } else if (cmd->aborted) { - cmd->cmd_flags |= BIT_18; + cmd->trc_flags |= TRC_CTIO_ABORTED; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e, "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag); } else { - cmd->cmd_flags |= BIT_19; + cmd->trc_flags |= TRC_CTIO_STRANGE; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c, "qla_target(%d): A command in state (%d) should " "not return a CTIO complete\n", vha->vp_idx, cmd->state); @@ -3762,7 +3872,7 @@ static inline int qlt_get_fcp_task_attr(struct scsi_qla_host *vha, return fcp_task_attr; } -static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *, +static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *, uint8_t *); /* * Process context for I/O path into tcm_qla2xxx code @@ -3772,7 +3882,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd) scsi_qla_host_t *vha = cmd->vha; struct qla_hw_data *ha = vha->hw; struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_sess *sess = cmd->sess; + struct fc_port *sess = cmd->sess; struct atio_from_isp *atio = &cmd->atio; unsigned char *cdb; unsigned long flags; @@ -3780,7 +3890,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd) int ret, fcp_task_attr, data_dir, bidi = 0; cmd->cmd_in_wq = 0; - cmd->cmd_flags |= BIT_1; + cmd->trc_flags |= TRC_DO_WORK; if (tgt->tgt_stop) goto out_term; @@ -3822,7 +3932,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd) * Drop extra session reference from qla_tgt_handle_cmd_for_atio*( */ spin_lock_irqsave(&ha->tgt.sess_lock, flags); - qlt_put_sess(sess); + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return; @@ -3832,7 +3942,7 @@ out_term: * cmd has not sent to target yet, so pass NULL as the second * argument to qlt_send_term_exchange() and free the memory here. */ - cmd->cmd_flags |= BIT_2; + cmd->trc_flags |= TRC_DO_WORK_ERR; spin_lock_irqsave(&ha->hardware_lock, flags); qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0); @@ -3841,7 +3951,7 @@ out_term: spin_unlock_irqrestore(&ha->hardware_lock, flags); spin_lock_irqsave(&ha->tgt.sess_lock, flags); - qlt_put_sess(sess); + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } @@ -3859,7 +3969,7 @@ static void qlt_do_work(struct work_struct *work) } static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, - struct qla_tgt_sess *sess, + struct fc_port *sess, struct atio_from_isp *atio) { struct se_session *se_sess = sess->se_sess; @@ -3883,7 +3993,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, cmd->loop_id = sess->loop_id; cmd->conf_compl_supported = sess->conf_compl_supported; - cmd->cmd_flags = 0; + cmd->trc_flags = 0; cmd->jiffies_at_alloc = get_jiffies_64(); cmd->reset_count = vha->hw->chip_reset; @@ -3900,7 +4010,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work) struct qla_tgt_sess_op, work); scsi_qla_host_t *vha = op->vha; struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; + struct fc_port *sess; struct qla_tgt_cmd *cmd; unsigned long flags; uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id; @@ -3941,11 +4051,12 @@ static void qlt_create_sess_from_atio(struct work_struct *work) if (!cmd) { spin_lock_irqsave(&ha->hardware_lock, flags); qlt_send_busy(vha, &op->atio, SAM_STAT_BUSY); - qlt_put_sess(sess); + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->hardware_lock, flags); kfree(op); return; } + /* * __qlt_do_work() will call qlt_put_sess() to release * the extra reference taken above by qlt_make_local_sess() @@ -3953,13 +4064,11 @@ static void qlt_create_sess_from_atio(struct work_struct *work) __qlt_do_work(cmd); kfree(op); return; - out_term: spin_lock_irqsave(&ha->hardware_lock, flags); qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0); spin_unlock_irqrestore(&ha->hardware_lock, flags); kfree(op); - } /* ha->hardware_lock supposed to be held on entry */ @@ -3968,8 +4077,9 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, { struct qla_hw_data *ha = vha->hw; struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_sess *sess; + struct fc_port *sess; struct qla_tgt_cmd *cmd; + unsigned long flags; if (unlikely(tgt->tgt_stop)) { ql_dbg(ql_dbg_io, vha, 0x3061, @@ -3998,7 +4108,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, /* Another WWN used to have our s_id. Our PLOGI scheduled its * session deletion, but it's still in sess_del_work wq */ - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + if (sess->deleted) { ql_dbg(ql_dbg_io, vha, 0x3061, "New command while old session %p is being deleted\n", sess); @@ -4008,24 +4118,32 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, /* * Do kref_get() before returning + dropping qla_hw_data->hardware_lock. */ - kref_get(&sess->sess_kref); + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_tgt, vha, 0xffff, + "%s: kref_get fail, %8phC oxid %x \n", + __func__, sess->port_name, + be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id)); + return -EFAULT; + } cmd = qlt_get_tag(vha, sess, atio); if (!cmd) { ql_dbg(ql_dbg_io, vha, 0x3062, "qla_target(%d): Allocation of cmd failed\n", vha->vp_idx); - qlt_put_sess(sess); + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + ha->tgt.tgt_ops->put_sess(sess); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return -ENOMEM; } cmd->cmd_in_wq = 1; - cmd->cmd_flags |= BIT_0; + cmd->trc_flags |= TRC_NEW_CMD; cmd->se_cmd.cpuid = ha->msix_count ? ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND; - spin_lock(&vha->cmd_list_lock); + spin_lock_irqsave(&vha->cmd_list_lock, flags); list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list); - spin_unlock(&vha->cmd_list_lock); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); INIT_WORK(&cmd->work, qlt_do_work); if (ha->msix_count) { @@ -4043,7 +4161,7 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, } /* ha->hardware_lock supposed to be held on entry */ -static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, +static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun, int fn, void *iocb, int flags) { struct scsi_qla_host *vha = sess->vha; @@ -4051,7 +4169,6 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, struct qla_tgt_mgmt_cmd *mcmd; struct atio_from_isp *a = (struct atio_from_isp *)iocb; int res; - uint8_t tmr_func; mcmd = mempool_alloc(qla_tgt_mgmt_cmd_mempool, GFP_ATOMIC); if (!mcmd) { @@ -4073,74 +4190,12 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, mcmd->reset_count = vha->hw->chip_reset; switch (fn) { - case QLA_TGT_CLEAR_ACA: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10000, - "qla_target(%d): CLEAR_ACA received\n", sess->vha->vp_idx); - tmr_func = TMR_CLEAR_ACA; - break; - - case QLA_TGT_TARGET_RESET: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10001, - "qla_target(%d): TARGET_RESET received\n", - sess->vha->vp_idx); - tmr_func = TMR_TARGET_WARM_RESET; - break; - case QLA_TGT_LUN_RESET: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002, - "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx); - tmr_func = TMR_LUN_RESET; - abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); - break; - - case QLA_TGT_CLEAR_TS: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10003, - "qla_target(%d): CLEAR_TS received\n", sess->vha->vp_idx); - tmr_func = TMR_CLEAR_TASK_SET; - break; - - case QLA_TGT_ABORT_TS: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10004, - "qla_target(%d): ABORT_TS received\n", sess->vha->vp_idx); - tmr_func = TMR_ABORT_TASK_SET; - break; -#if 0 - case QLA_TGT_ABORT_ALL: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10005, - "qla_target(%d): Doing ABORT_ALL_TASKS\n", - sess->vha->vp_idx); - tmr_func = 0; - break; - - case QLA_TGT_ABORT_ALL_SESS: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10006, - "qla_target(%d): Doing ABORT_ALL_TASKS_SESS\n", - sess->vha->vp_idx); - tmr_func = 0; - break; - - case QLA_TGT_NEXUS_LOSS_SESS: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10007, - "qla_target(%d): Doing NEXUS_LOSS_SESS\n", - sess->vha->vp_idx); - tmr_func = 0; - break; - - case QLA_TGT_NEXUS_LOSS: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x10008, - "qla_target(%d): Doing NEXUS_LOSS\n", sess->vha->vp_idx); - tmr_func = 0; - break; -#endif - default: - ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000a, - "qla_target(%d): Unknown task mgmt fn 0x%x\n", - sess->vha->vp_idx, fn); - mempool_free(mcmd, qla_tgt_mgmt_cmd_mempool); - return -ENOSYS; + abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); + break; } - res = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, tmr_func, 0); + res = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, mcmd->tmr_func, 0); if (res != 0) { ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000b, "qla_target(%d): tgt.tgt_ops->handle_tmr() failed: %d\n", @@ -4158,7 +4213,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb) struct atio_from_isp *a = (struct atio_from_isp *)iocb; struct qla_hw_data *ha = vha->hw; struct qla_tgt *tgt; - struct qla_tgt_sess *sess; + struct fc_port *sess; uint32_t lun, unpacked_lun; int fn; unsigned long flags; @@ -4183,7 +4238,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb) sizeof(struct atio_from_isp)); } - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) + if (sess->deleted) return -EFAULT; return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0); @@ -4191,7 +4246,7 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb) /* ha->hardware_lock supposed to be held on entry */ static int __qlt_abort_task(struct scsi_qla_host *vha, - struct imm_ntfy_from_isp *iocb, struct qla_tgt_sess *sess) + struct imm_ntfy_from_isp *iocb, struct fc_port *sess) { struct atio_from_isp *a = (struct atio_from_isp *)iocb; struct qla_hw_data *ha = vha->hw; @@ -4215,8 +4270,9 @@ static int __qlt_abort_task(struct scsi_qla_host *vha, lun = a->u.isp24.fcp_cmnd.lun; unpacked_lun = scsilun_to_int((struct scsi_lun *)&lun); mcmd->reset_count = vha->hw->chip_reset; + mcmd->tmr_func = QLA_TGT_2G_ABORT_TASK; - rc = ha->tgt.tgt_ops->handle_tmr(mcmd, unpacked_lun, TMR_ABORT_TASK, + rc = ha->tgt.tgt_ops->handle_tmr(mcmd, unpacked_lun, mcmd->tmr_func, le16_to_cpu(iocb->u.isp2x.seq_id)); if (rc != 0) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf060, @@ -4234,7 +4290,7 @@ static int qlt_abort_task(struct scsi_qla_host *vha, struct imm_ntfy_from_isp *iocb) { struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; + struct fc_port *sess; int loop_id; unsigned long flags; @@ -4257,22 +4313,20 @@ static int qlt_abort_task(struct scsi_qla_host *vha, void qlt_logo_completion_handler(fc_port_t *fcport, int rc) { - if (fcport->tgt_session) { - if (rc != MBS_COMMAND_COMPLETE) { - ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093, - "%s: se_sess %p / sess %p from" - " port %8phC loop_id %#04x s_id %02x:%02x:%02x" - " LOGO failed: %#x\n", - __func__, - fcport->tgt_session->se_sess, - fcport->tgt_session, - fcport->port_name, fcport->loop_id, - fcport->d_id.b.domain, fcport->d_id.b.area, - fcport->d_id.b.al_pa, rc); - } - - fcport->tgt_session->logout_completed = 1; + if (rc != MBS_COMMAND_COMPLETE) { + ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093, + "%s: se_sess %p / sess %p from" + " port %8phC loop_id %#04x s_id %02x:%02x:%02x" + " LOGO failed: %#x\n", + __func__, + fcport->se_sess, + fcport, + fcport->port_name, fcport->loop_id, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa, rc); } + + fcport->logout_completed = 1; } /* @@ -4282,16 +4336,16 @@ void qlt_logo_completion_handler(fc_port_t *fcport, int rc) * deletion. Returns existing session with matching wwn if present. * Null otherwise. */ -static struct qla_tgt_sess * -qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, - port_id_t port_id, uint16_t loop_id, struct qla_tgt_sess **conflict_sess) +struct fc_port * +qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn, + port_id_t port_id, uint16_t loop_id, struct fc_port **conflict_sess) { - struct qla_tgt_sess *sess = NULL, *other_sess; + struct fc_port *sess = NULL, *other_sess; uint64_t other_wwn; *conflict_sess = NULL; - list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) { + list_for_each_entry(other_sess, &vha->vp_fcports, list) { other_wwn = wwn_to_u64(other_sess->port_name); @@ -4302,9 +4356,9 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, } /* find other sess with nport_id collision */ - if (port_id.b24 == other_sess->s_id.b24) { + if (port_id.b24 == other_sess->d_id.b24) { if (loop_id != other_sess->loop_id) { - ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c, + ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000c, "Invalidating sess %p loop_id %d wwn %llx.\n", other_sess, other_sess->loop_id, other_wwn); @@ -4320,6 +4374,11 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, * Another wwn used to have our s_id/loop_id * kill the session, but don't free the loop_id */ + ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff, + "Invalidating sess %p loop_id %d wwn %llx.\n", + other_sess, other_sess->loop_id, other_wwn); + + other_sess->keep_nport_handle = 1; *conflict_sess = other_sess; qlt_schedule_sess_for_deletion(other_sess, @@ -4329,8 +4388,9 @@ qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, } /* find other sess with nport handle collision */ - if (loop_id == other_sess->loop_id) { - ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d, + if ((loop_id == other_sess->loop_id) && + (loop_id != FC_NO_LOOP_ID)) { + ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000d, "Invalidating sess %p loop_id %d wwn %llx.\n", other_sess, other_sess->loop_id, other_wwn); @@ -4358,11 +4418,21 @@ static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id) spin_lock(&vha->cmd_list_lock); list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + if (op_key == key) { op->aborted = true; count++; } } + + list_for_each_entry(op, &vha->unknown_atio_list, cmd_list) { + uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + if (op_key == key) { + op->aborted = true; + count++; + } + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id); if (cmd_key == key) { @@ -4383,13 +4453,13 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess = NULL, *conflict_sess = NULL; + struct fc_port *sess = NULL, *conflict_sess = NULL; uint64_t wwn; port_id_t port_id; uint16_t loop_id; uint16_t wd3_lo; int res = 0; - qlt_plogi_ack_t *pla; + struct qlt_plogi_ack_t *pla; unsigned long flags; wwn = wwn_to_u64(iocb->u.isp24.port_name); @@ -4401,9 +4471,12 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, loop_id = le16_to_cpu(iocb->u.isp24.nport_handle); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026, - "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n", - vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode); + ql_dbg(ql_dbg_disc, vha, 0xf026, + "qla_target(%d): Port ID: %02x:%02x:%02x ELS opcode: 0x%02x lid %d %8phC\n", + vha->vp_idx, iocb->u.isp24.port_id[2], + iocb->u.isp24.port_id[1], iocb->u.isp24.port_id[0], + iocb->u.isp24.status_subcode, loop_id, + iocb->u.isp24.port_name); /* res = 1 means ack at the end of thread * res = 0 means ack async/later. @@ -4416,12 +4489,12 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, if (wwn) { spin_lock_irqsave(&tgt->ha->tgt.sess_lock, flags); - sess = qlt_find_sess_invalidate_other(tgt, wwn, - port_id, loop_id, &conflict_sess); + sess = qlt_find_sess_invalidate_other(vha, wwn, + port_id, loop_id, &conflict_sess); spin_unlock_irqrestore(&tgt->ha->tgt.sess_lock, flags); } - if (IS_SW_RESV_ADDR(port_id) || (!sess && !conflict_sess)) { + if (IS_SW_RESV_ADDR(port_id)) { res = 1; break; } @@ -4429,42 +4502,66 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, pla = qlt_plogi_ack_find_add(vha, &port_id, iocb); if (!pla) { qlt_send_term_imm_notif(vha, iocb, 1); - - res = 0; break; } res = 0; - if (conflict_sess) + if (conflict_sess) { + conflict_sess->login_gen++; qlt_plogi_ack_link(vha, pla, conflict_sess, - QLT_PLOGI_LINK_CONFLICT); + QLT_PLOGI_LINK_CONFLICT); + } - if (!sess) + if (!sess) { + pla->ref_count++; + qla24xx_post_newsess_work(vha, &port_id, + iocb->u.isp24.port_name, pla); + res = 0; break; + } qlt_plogi_ack_link(vha, pla, sess, QLT_PLOGI_LINK_SAME_WWN); - /* - * Under normal circumstances we want to release nport handle - * during LOGO process to avoid nport handle leaks inside FW. - * The exception is when LOGO is done while another PLOGI with - * the same nport handle is waiting as might be the case here. - * Note: there is always a possibily of a race where session - * deletion has already started for other reasons (e.g. ACL - * removal) and now PLOGI arrives: - * 1. if PLOGI arrived in FW after nport handle has been freed, - * FW must have assigned this PLOGI a new/same handle and we - * can proceed ACK'ing it as usual when session deletion - * completes. - * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT - * bit reached it, the handle has now been released. We'll - * get an error when we ACK this PLOGI. Nothing will be sent - * back to initiator. Initiator should eventually retry - * PLOGI and situation will correct itself. - */ - sess->keep_nport_handle = ((sess->loop_id == loop_id) && - (sess->s_id.b24 == port_id.b24)); - qlt_schedule_sess_for_deletion(sess, true); + sess->fw_login_state = DSC_LS_PLOGI_PEND; + sess->d_id = port_id; + sess->login_gen++; + + switch (sess->disc_state) { + case DSC_DELETED: + qlt_plogi_ack_unref(vha, pla); + break; + + default: + /* + * Under normal circumstances we want to release nport handle + * during LOGO process to avoid nport handle leaks inside FW. + * The exception is when LOGO is done while another PLOGI with + * the same nport handle is waiting as might be the case here. + * Note: there is always a possibily of a race where session + * deletion has already started for other reasons (e.g. ACL + * removal) and now PLOGI arrives: + * 1. if PLOGI arrived in FW after nport handle has been freed, + * FW must have assigned this PLOGI a new/same handle and we + * can proceed ACK'ing it as usual when session deletion + * completes. + * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT + * bit reached it, the handle has now been released. We'll + * get an error when we ACK this PLOGI. Nothing will be sent + * back to initiator. Initiator should eventually retry + * PLOGI and situation will correct itself. + */ + sess->keep_nport_handle = ((sess->loop_id == loop_id) && + (sess->d_id.b24 == port_id.b24)); + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post del sess\n", + __func__, __LINE__, sess->port_name); + + + qlt_schedule_sess_for_deletion_lock(sess); + break; + } + break; case ELS_PRLI: @@ -4472,8 +4569,8 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, if (wwn) { spin_lock_irqsave(&tgt->ha->tgt.sess_lock, flags); - sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id, - loop_id, &conflict_sess); + sess = qlt_find_sess_invalidate_other(vha, wwn, port_id, + loop_id, &conflict_sess); spin_unlock_irqrestore(&tgt->ha->tgt.sess_lock, flags); } @@ -4487,7 +4584,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, } if (sess != NULL) { - if (sess->deleted) { + if (sess->fw_login_state == DSC_LS_PLOGI_PEND) { /* * Impatient initiator sent PRLI before last * PLOGI could finish. Will force him to re-try, @@ -4511,11 +4608,16 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, sess->local = 0; sess->loop_id = loop_id; - sess->s_id = port_id; + sess->d_id = port_id; + sess->fw_login_state = DSC_LS_PRLI_PEND; if (wd3_lo & BIT_7) sess->conf_compl_supported = 1; + if ((wd3_lo & BIT_4) == 0) + sess->port_type = FCT_INITIATOR; + else + sess->port_type = FCT_TARGET; } res = 1; /* send notify ack */ @@ -4525,15 +4627,61 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); qla2xxx_wake_dpc(vha); } else { - /* todo: else - create sess here. */ - res = 1; /* send notify ack */ - } + if (sess) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post nack\n", + __func__, __LINE__, sess->port_name); + qla24xx_post_nack_work(vha, sess, iocb, + SRB_NACK_PRLI); + res = 0; + } + } break; + + case ELS_TPRLO: + if (le16_to_cpu(iocb->u.isp24.flags) & + NOTIFY24XX_FLAGS_GLOBAL_TPRLO) { + loop_id = 0xFFFF; + qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS); + res = 1; + break; + } + /* drop through */ case ELS_LOGO: case ELS_PRLO: + spin_lock_irqsave(&ha->tgt.sess_lock, flags); + sess = qla2x00_find_fcport_by_loopid(vha, loop_id); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); + + if (sess) { + sess->login_gen++; + sess->fw_login_state = DSC_LS_LOGO_PEND; + sess->logo_ack_needed = 1; + memcpy(sess->iocb, iocb, IOCB_SIZE); + } + res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS); + + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: logo %llx res %d sess %p ", + __func__, wwn, res, sess); + if (res == 0) { + /* + * cmd went upper layer, look for qlt_xmit_tm_rsp() + * for LOGO_ACK & sess delete + */ + BUG_ON(!sess); + res = 0; + } else { + /* cmd did not go to upper layer. */ + if (sess) { + qlt_schedule_sess_for_deletion_lock(sess); + res = 0; + } + /* else logo will be ack */ + } break; case ELS_PDISC: case ELS_ADISC: @@ -4544,6 +4692,16 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, 0, 0, 0, 0, 0, 0); tgt->link_reinit_iocb_pending = 0; } + + sess = qla2x00_find_fcport_by_wwpn(vha, + iocb->u.isp24.port_name, 1); + if (sess) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "sess %p lid %d|%d DS %d LS %d\n", + sess, sess->loop_id, loop_id, + sess->disc_state, sess->fw_login_state); + } + res = 1; /* send notify ack */ break; } @@ -4560,451 +4718,6 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, return res; } -static int qlt_set_data_offset(struct qla_tgt_cmd *cmd, uint32_t offset) -{ -#if 1 - /* - * FIXME: Reject non zero SRR relative offset until we can test - * this code properly. - */ - pr_debug("Rejecting non zero SRR rel_offs: %u\n", offset); - return -1; -#else - struct scatterlist *sg, *sgp, *sg_srr, *sg_srr_start = NULL; - size_t first_offset = 0, rem_offset = offset, tmp = 0; - int i, sg_srr_cnt, bufflen = 0; - - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe023, - "Entering qla_tgt_set_data_offset: cmd: %p, cmd->sg: %p, " - "cmd->sg_cnt: %u, direction: %d\n", - cmd, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction); - - if (!cmd->sg || !cmd->sg_cnt) { - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe055, - "Missing cmd->sg or zero cmd->sg_cnt in" - " qla_tgt_set_data_offset\n"); - return -EINVAL; - } - /* - * Walk the current cmd->sg list until we locate the new sg_srr_start - */ - for_each_sg(cmd->sg, sg, cmd->sg_cnt, i) { - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe024, - "sg[%d]: %p page: %p, length: %d, offset: %d\n", - i, sg, sg_page(sg), sg->length, sg->offset); - - if ((sg->length + tmp) > offset) { - first_offset = rem_offset; - sg_srr_start = sg; - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe025, - "Found matching sg[%d], using %p as sg_srr_start, " - "and using first_offset: %zu\n", i, sg, - first_offset); - break; - } - tmp += sg->length; - rem_offset -= sg->length; - } - - if (!sg_srr_start) { - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe056, - "Unable to locate sg_srr_start for offset: %u\n", offset); - return -EINVAL; - } - sg_srr_cnt = (cmd->sg_cnt - i); - - sg_srr = kzalloc(sizeof(struct scatterlist) * sg_srr_cnt, GFP_KERNEL); - if (!sg_srr) { - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe057, - "Unable to allocate sgp\n"); - return -ENOMEM; - } - sg_init_table(sg_srr, sg_srr_cnt); - sgp = &sg_srr[0]; - /* - * Walk the remaining list for sg_srr_start, mapping to the newly - * allocated sg_srr taking first_offset into account. - */ - for_each_sg(sg_srr_start, sg, sg_srr_cnt, i) { - if (first_offset) { - sg_set_page(sgp, sg_page(sg), - (sg->length - first_offset), first_offset); - first_offset = 0; - } else { - sg_set_page(sgp, sg_page(sg), sg->length, 0); - } - bufflen += sgp->length; - - sgp = sg_next(sgp); - if (!sgp) - break; - } - - cmd->sg = sg_srr; - cmd->sg_cnt = sg_srr_cnt; - cmd->bufflen = bufflen; - cmd->offset += offset; - cmd->free_sg = 1; - - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe026, "New cmd->sg: %p\n", cmd->sg); - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe027, "New cmd->sg_cnt: %u\n", - cmd->sg_cnt); - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe028, "New cmd->bufflen: %u\n", - cmd->bufflen); - ql_dbg(ql_dbg_tgt, cmd->vha, 0xe029, "New cmd->offset: %u\n", - cmd->offset); - - if (cmd->sg_cnt < 0) - BUG(); - - if (cmd->bufflen < 0) - BUG(); - - return 0; -#endif -} - -static inline int qlt_srr_adjust_data(struct qla_tgt_cmd *cmd, - uint32_t srr_rel_offs, int *xmit_type) -{ - int res = 0, rel_offs; - - rel_offs = srr_rel_offs - cmd->offset; - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf027, "srr_rel_offs=%d, rel_offs=%d", - srr_rel_offs, rel_offs); - - *xmit_type = QLA_TGT_XMIT_ALL; - - if (rel_offs < 0) { - ql_dbg(ql_dbg_tgt_mgt, cmd->vha, 0xf062, - "qla_target(%d): SRR rel_offs (%d) < 0", - cmd->vha->vp_idx, rel_offs); - res = -1; - } else if (rel_offs == cmd->bufflen) - *xmit_type = QLA_TGT_XMIT_STATUS; - else if (rel_offs > 0) - res = qlt_set_data_offset(cmd, rel_offs); - - return res; -} - -/* No locks, thread context */ -static void qlt_handle_srr(struct scsi_qla_host *vha, - struct qla_tgt_srr_ctio *sctio, struct qla_tgt_srr_imm *imm) -{ - struct imm_ntfy_from_isp *ntfy = - (struct imm_ntfy_from_isp *)&imm->imm_ntfy; - struct qla_hw_data *ha = vha->hw; - struct qla_tgt_cmd *cmd = sctio->cmd; - struct se_cmd *se_cmd = &cmd->se_cmd; - unsigned long flags; - int xmit_type = 0, resp = 0; - uint32_t offset; - uint16_t srr_ui; - - offset = le32_to_cpu(ntfy->u.isp24.srr_rel_offs); - srr_ui = ntfy->u.isp24.srr_ui; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf028, "SRR cmd %p, srr_ui %x\n", - cmd, srr_ui); - - switch (srr_ui) { - case SRR_IU_STATUS: - spin_lock_irqsave(&ha->hardware_lock, flags); - qlt_send_notify_ack(vha, ntfy, - 0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - xmit_type = QLA_TGT_XMIT_STATUS; - resp = 1; - break; - case SRR_IU_DATA_IN: - if (!cmd->sg || !cmd->sg_cnt) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf063, - "Unable to process SRR_IU_DATA_IN due to" - " missing cmd->sg, state: %d\n", cmd->state); - dump_stack(); - goto out_reject; - } - if (se_cmd->scsi_status != 0) { - ql_dbg(ql_dbg_tgt, vha, 0xe02a, - "Rejecting SRR_IU_DATA_IN with non GOOD " - "scsi_status\n"); - goto out_reject; - } - cmd->bufflen = se_cmd->data_length; - - if (qlt_has_data(cmd)) { - if (qlt_srr_adjust_data(cmd, offset, &xmit_type) != 0) - goto out_reject; - spin_lock_irqsave(&ha->hardware_lock, flags); - qlt_send_notify_ack(vha, ntfy, - 0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - resp = 1; - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf064, - "qla_target(%d): SRR for in data for cmd without them (tag %lld, SCSI status %d), reject", - vha->vp_idx, se_cmd->tag, - cmd->se_cmd.scsi_status); - goto out_reject; - } - break; - case SRR_IU_DATA_OUT: - if (!cmd->sg || !cmd->sg_cnt) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf065, - "Unable to process SRR_IU_DATA_OUT due to" - " missing cmd->sg\n"); - dump_stack(); - goto out_reject; - } - if (se_cmd->scsi_status != 0) { - ql_dbg(ql_dbg_tgt, vha, 0xe02b, - "Rejecting SRR_IU_DATA_OUT" - " with non GOOD scsi_status\n"); - goto out_reject; - } - cmd->bufflen = se_cmd->data_length; - - if (qlt_has_data(cmd)) { - if (qlt_srr_adjust_data(cmd, offset, &xmit_type) != 0) - goto out_reject; - spin_lock_irqsave(&ha->hardware_lock, flags); - qlt_send_notify_ack(vha, ntfy, - 0, 0, 0, NOTIFY_ACK_SRR_FLAGS_ACCEPT, 0, 0); - spin_unlock_irqrestore(&ha->hardware_lock, flags); - if (xmit_type & QLA_TGT_XMIT_DATA) { - cmd->cmd_flags |= BIT_8; - qlt_rdy_to_xfer(cmd); - } - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf066, - "qla_target(%d): SRR for out data for cmd without them (tag %lld, SCSI status %d), reject", - vha->vp_idx, se_cmd->tag, cmd->se_cmd.scsi_status); - goto out_reject; - } - break; - default: - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf067, - "qla_target(%d): Unknown srr_ui value %x", - vha->vp_idx, srr_ui); - goto out_reject; - } - - /* Transmit response in case of status and data-in cases */ - if (resp) { - cmd->cmd_flags |= BIT_7; - qlt_xmit_response(cmd, xmit_type, se_cmd->scsi_status); - } - - return; - -out_reject: - spin_lock_irqsave(&ha->hardware_lock, flags); - qlt_send_notify_ack(vha, ntfy, 0, 0, 0, - NOTIFY_ACK_SRR_FLAGS_REJECT, - NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM, - NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL); - if (cmd->state == QLA_TGT_STATE_NEED_DATA) { - cmd->state = QLA_TGT_STATE_DATA_IN; - dump_stack(); - } else { - cmd->cmd_flags |= BIT_9; - qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0); - } - spin_unlock_irqrestore(&ha->hardware_lock, flags); -} - -static void qlt_reject_free_srr_imm(struct scsi_qla_host *vha, - struct qla_tgt_srr_imm *imm, int ha_locked) -{ - struct qla_hw_data *ha = vha->hw; - unsigned long flags = 0; - -#ifndef __CHECKER__ - if (!ha_locked) - spin_lock_irqsave(&ha->hardware_lock, flags); -#endif - - qlt_send_notify_ack(vha, (void *)&imm->imm_ntfy, 0, 0, 0, - NOTIFY_ACK_SRR_FLAGS_REJECT, - NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM, - NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL); - -#ifndef __CHECKER__ - if (!ha_locked) - spin_unlock_irqrestore(&ha->hardware_lock, flags); -#endif - - kfree(imm); -} - -static void qlt_handle_srr_work(struct work_struct *work) -{ - struct qla_tgt *tgt = container_of(work, struct qla_tgt, srr_work); - struct scsi_qla_host *vha = tgt->vha; - struct qla_tgt_srr_ctio *sctio; - unsigned long flags; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf029, "Entering SRR work (tgt %p)\n", - tgt); - -restart: - spin_lock_irqsave(&tgt->srr_lock, flags); - list_for_each_entry(sctio, &tgt->srr_ctio_list, srr_list_entry) { - struct qla_tgt_srr_imm *imm, *i, *ti; - struct qla_tgt_cmd *cmd; - struct se_cmd *se_cmd; - - imm = NULL; - list_for_each_entry_safe(i, ti, &tgt->srr_imm_list, - srr_list_entry) { - if (i->srr_id == sctio->srr_id) { - list_del(&i->srr_list_entry); - if (imm) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf068, - "qla_target(%d): There must be " - "only one IMM SRR per CTIO SRR " - "(IMM SRR %p, id %d, CTIO %p\n", - vha->vp_idx, i, i->srr_id, sctio); - qlt_reject_free_srr_imm(tgt->vha, i, 0); - } else - imm = i; - } - } - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02a, - "IMM SRR %p, CTIO SRR %p (id %d)\n", imm, sctio, - sctio->srr_id); - - if (imm == NULL) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02b, - "Not found matching IMM for SRR CTIO (id %d)\n", - sctio->srr_id); - continue; - } else - list_del(&sctio->srr_list_entry); - - spin_unlock_irqrestore(&tgt->srr_lock, flags); - - cmd = sctio->cmd; - /* - * Reset qla_tgt_cmd SRR values and SGL pointer+count to follow - * tcm_qla2xxx_write_pending() and tcm_qla2xxx_queue_data_in() - * logic.. - */ - cmd->offset = 0; - if (cmd->free_sg) { - kfree(cmd->sg); - cmd->sg = NULL; - cmd->free_sg = 0; - } - se_cmd = &cmd->se_cmd; - - cmd->sg_cnt = se_cmd->t_data_nents; - cmd->sg = se_cmd->t_data_sg; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c, - "SRR cmd %p (se_cmd %p, tag %lld, op %x), sg_cnt=%d, offset=%d", - cmd, &cmd->se_cmd, se_cmd->tag, se_cmd->t_task_cdb ? - se_cmd->t_task_cdb[0] : 0, cmd->sg_cnt, cmd->offset); - - qlt_handle_srr(vha, sctio, imm); - - kfree(imm); - kfree(sctio); - goto restart; - } - spin_unlock_irqrestore(&tgt->srr_lock, flags); -} - -/* ha->hardware_lock supposed to be held on entry */ -static void qlt_prepare_srr_imm(struct scsi_qla_host *vha, - struct imm_ntfy_from_isp *iocb) -{ - struct qla_tgt_srr_imm *imm; - struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; - struct qla_tgt_srr_ctio *sctio; - - tgt->imm_srr_id++; - - ql_log(ql_log_warn, vha, 0xf02d, "qla_target(%d): SRR received\n", - vha->vp_idx); - - imm = kzalloc(sizeof(*imm), GFP_ATOMIC); - if (imm != NULL) { - memcpy(&imm->imm_ntfy, iocb, sizeof(imm->imm_ntfy)); - - /* IRQ is already OFF */ - spin_lock(&tgt->srr_lock); - imm->srr_id = tgt->imm_srr_id; - list_add_tail(&imm->srr_list_entry, - &tgt->srr_imm_list); - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02e, - "IMM NTFY SRR %p added (id %d, ui %x)\n", - imm, imm->srr_id, iocb->u.isp24.srr_ui); - if (tgt->imm_srr_id == tgt->ctio_srr_id) { - int found = 0; - list_for_each_entry(sctio, &tgt->srr_ctio_list, - srr_list_entry) { - if (sctio->srr_id == imm->srr_id) { - found = 1; - break; - } - } - if (found) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02f, "%s", - "Scheduling srr work\n"); - schedule_work(&tgt->srr_work); - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf030, - "qla_target(%d): imm_srr_id " - "== ctio_srr_id (%d), but there is no " - "corresponding SRR CTIO, deleting IMM " - "SRR %p\n", vha->vp_idx, tgt->ctio_srr_id, - imm); - list_del(&imm->srr_list_entry); - - kfree(imm); - - spin_unlock(&tgt->srr_lock); - goto out_reject; - } - } - spin_unlock(&tgt->srr_lock); - } else { - struct qla_tgt_srr_ctio *ts; - - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf069, - "qla_target(%d): Unable to allocate SRR IMM " - "entry, SRR request will be rejected\n", vha->vp_idx); - - /* IRQ is already OFF */ - spin_lock(&tgt->srr_lock); - list_for_each_entry_safe(sctio, ts, &tgt->srr_ctio_list, - srr_list_entry) { - if (sctio->srr_id == tgt->imm_srr_id) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf031, - "CTIO SRR %p deleted (id %d)\n", - sctio, sctio->srr_id); - list_del(&sctio->srr_list_entry); - qlt_send_term_exchange(vha, sctio->cmd, - &sctio->cmd->atio, 1, 0); - kfree(sctio); - } - } - spin_unlock(&tgt->srr_lock); - goto out_reject; - } - - return; - -out_reject: - qlt_send_notify_ack(vha, iocb, 0, 0, 0, - NOTIFY_ACK_SRR_FLAGS_REJECT, - NOTIFY_ACK_SRR_REJECT_REASON_UNABLE_TO_PERFORM, - NOTIFY_ACK_SRR_FLAGS_REJECT_EXPL_NO_EXPL); -} - /* * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire */ @@ -5126,12 +4839,6 @@ static void qlt_handle_imm_notify(struct scsi_qla_host *vha, if (qlt_24xx_handle_els(vha, iocb) == 0) send_notify_ack = 0; break; - - case IMM_NTFY_SRR: - qlt_prepare_srr_imm(vha, iocb); - send_notify_ack = 0; - break; - default: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf06d, "qla_target(%d): Received unknown immediate " @@ -5153,7 +4860,7 @@ static int __qlt_send_busy(struct scsi_qla_host *vha, struct ctio7_to_24xx *ctio24; struct qla_hw_data *ha = vha->hw; request_t *pkt; - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; unsigned long flags; spin_lock_irqsave(&ha->tgt.sess_lock, flags); @@ -5214,7 +4921,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess; + struct fc_port *sess; struct se_session *se_sess; struct qla_tgt_cmd *cmd; int tag; @@ -5756,6 +5463,32 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); break; + case MBA_REJECTED_FCP_CMD: + ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff, + "qla_target(%d): Async event LS_REJECT occurred " + "(m[0]=%x, m[1]=%x, m[2]=%x, m[3]=%x)", vha->vp_idx, + le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]), + le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); + + if (le16_to_cpu(mailbox[3]) == 1) { + /* exchange starvation. */ + vha->hw->exch_starvation++; + if (vha->hw->exch_starvation > 5) { + ql_log(ql_log_warn, vha, 0xffff, + "Exchange starvation-. Resetting RISC\n"); + + vha->hw->exch_starvation = 0; + if (IS_P3P_TYPE(vha->hw)) + set_bit(FCOE_CTX_RESET_NEEDED, + &vha->dpc_flags); + else + set_bit(ISP_ABORT_NEEDED, + &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + } + } + break; + case MBA_PORT_UPDATE: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03d, "qla_target(%d): Port update async event %#x " @@ -5765,14 +5498,14 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); login_code = le16_to_cpu(mailbox[2]); - if (login_code == 0x4) + if (login_code == 0x4) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03e, "Async MB 2: Got PLOGI Complete\n"); - else if (login_code == 0x7) + vha->hw->exch_starvation = 0; + } else if (login_code == 0x7) ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03f, "Async MB 2: Port Logged Out\n"); break; - default: break; } @@ -5783,8 +5516,10 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha, uint16_t loop_id) { - fc_port_t *fcport; + fc_port_t *fcport, *tfcp, *del; int rc; + unsigned long flags; + u8 newfcport = 0; fcport = kzalloc(sizeof(*fcport), GFP_KERNEL); if (!fcport) { @@ -5806,18 +5541,82 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha, return NULL; } + del = NULL; + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + tfcp = qla2x00_find_fcport_by_wwpn(vha, fcport->port_name, 1); + + if (tfcp) { + tfcp->d_id = fcport->d_id; + tfcp->port_type = fcport->port_type; + tfcp->supported_classes = fcport->supported_classes; + tfcp->flags |= fcport->flags; + + del = fcport; + fcport = tfcp; + } else { + if (vha->hw->current_topology == ISP_CFG_F) + fcport->flags |= FCF_FABRIC_DEVICE; + + list_add_tail(&fcport->list, &vha->vp_fcports); + if (!IS_SW_RESV_ADDR(fcport->d_id)) + vha->fcport_count++; + fcport->login_gen++; + fcport->disc_state = DSC_LOGIN_COMPLETE; + fcport->login_succ = 1; + newfcport = 1; + } + + fcport->deleted = 0; + spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + + switch (vha->host->active_mode) { + case MODE_INITIATOR: + case MODE_DUAL: + if (newfcport) { + if (!IS_IIDMA_CAPABLE(vha->hw) || !vha->hw->flags.gpsc_supported) { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post upd_fcport fcp_cnt %d\n", + __func__, __LINE__, fcport->port_name, vha->fcport_count); + qla24xx_post_upd_fcport_work(vha, fcport); + } else { + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s %d %8phC post gpsc fcp_cnt %d\n", + __func__, __LINE__, fcport->port_name, vha->fcport_count); + qla24xx_post_gpsc_work(vha, fcport); + } + } + break; + + case MODE_TARGET: + default: + break; + } + if (del) + qla2x00_free_fcport(del); + return fcport; } /* Must be called under tgt_mutex */ -static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *vha, +static struct fc_port *qlt_make_local_sess(struct scsi_qla_host *vha, uint8_t *s_id) { - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; fc_port_t *fcport = NULL; int rc, global_resets; uint16_t loop_id = 0; + if ((s_id[0] == 0xFF) && (s_id[1] == 0xFC)) { + /* + * This is Domain Controller, so it should be + * OK to drop SCSI commands from it. + */ + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf042, + "Unable to find initiator with S_ID %x:%x:%x", + s_id[0], s_id[1], s_id[2]); + return NULL; + } + mutex_lock(&vha->vha_tgt.tgt_mutex); retry: @@ -5828,21 +5627,11 @@ retry: if (rc != 0) { mutex_unlock(&vha->vha_tgt.tgt_mutex); - if ((s_id[0] == 0xFF) && - (s_id[1] == 0xFC)) { - /* - * This is Domain Controller, so it should be - * OK to drop SCSI commands from it. - */ - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf042, - "Unable to find initiator with S_ID %x:%x:%x", - s_id[0], s_id[1], s_id[2]); - } else - ql_log(ql_log_info, vha, 0xf071, - "qla_target(%d): Unable to find " - "initiator with S_ID %x:%x:%x", - vha->vp_idx, s_id[0], s_id[1], - s_id[2]); + ql_log(ql_log_info, vha, 0xf071, + "qla_target(%d): Unable to find " + "initiator with S_ID %x:%x:%x", + vha->vp_idx, s_id[0], s_id[1], + s_id[2]); if (rc == -ENOENT) { qlt_port_logo_t logo; @@ -5875,7 +5664,6 @@ retry: mutex_unlock(&vha->vha_tgt.tgt_mutex); - kfree(fcport); return sess; } @@ -5884,7 +5672,7 @@ static void qlt_abort_work(struct qla_tgt *tgt, { struct scsi_qla_host *vha = tgt->vha; struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; unsigned long flags = 0, flags2 = 0; uint32_t be_s_id; uint8_t s_id[3]; @@ -5911,12 +5699,18 @@ static void qlt_abort_work(struct qla_tgt *tgt, if (!sess) goto out_term2; } else { - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + if (sess->deleted) { sess = NULL; goto out_term2; } - kref_get(&sess->sess_kref); + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff, + "%s: kref_get fail %8phC \n", + __func__, sess->port_name); + sess = NULL; + goto out_term2; + } } spin_lock_irqsave(&ha->hardware_lock, flags); @@ -5928,8 +5722,8 @@ static void qlt_abort_work(struct qla_tgt *tgt, if (rc != 0) goto out_term; spin_unlock_irqrestore(&ha->hardware_lock, flags); - - qlt_put_sess(sess); + if (sess) + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2); return; @@ -5940,7 +5734,8 @@ out_term: qlt_24xx_send_abts_resp(vha, &prm->abts, FCP_TMF_REJECTED, false); spin_unlock_irqrestore(&ha->hardware_lock, flags); - qlt_put_sess(sess); + if (sess) + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags2); } @@ -5950,7 +5745,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt, struct atio_from_isp *a = &prm->tm_iocb2; struct scsi_qla_host *vha = tgt->vha; struct qla_hw_data *ha = vha->hw; - struct qla_tgt_sess *sess = NULL; + struct fc_port *sess = NULL; unsigned long flags; uint8_t *s_id = NULL; /* to hide compiler warnings */ int rc; @@ -5975,12 +5770,18 @@ static void qlt_tmr_work(struct qla_tgt *tgt, if (!sess) goto out_term; } else { - if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + if (sess->deleted) { sess = NULL; goto out_term; } - kref_get(&sess->sess_kref); + if (!kref_get_unless_zero(&sess->sess_kref)) { + ql_dbg(ql_dbg_tgt_tmr, vha, 0xffff, + "%s: kref_get fail %8phC\n", + __func__, sess->port_name); + sess = NULL; + goto out_term; + } } iocb = a; @@ -5992,13 +5793,13 @@ static void qlt_tmr_work(struct qla_tgt *tgt, if (rc != 0) goto out_term; - qlt_put_sess(sess); + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return; out_term: qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0); - qlt_put_sess(sess); + ha->tgt.tgt_ops->put_sess(sess); spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); } @@ -6075,17 +5876,10 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha) tgt->ha = ha; tgt->vha = base_vha; init_waitqueue_head(&tgt->waitQ); - INIT_LIST_HEAD(&tgt->sess_list); INIT_LIST_HEAD(&tgt->del_sess_list); - INIT_DELAYED_WORK(&tgt->sess_del_work, - (void (*)(struct work_struct *))qlt_del_sess_work_fn); spin_lock_init(&tgt->sess_work_lock); INIT_WORK(&tgt->sess_work, qlt_sess_work_fn); INIT_LIST_HEAD(&tgt->sess_works_list); - spin_lock_init(&tgt->srr_lock); - INIT_LIST_HEAD(&tgt->srr_ctio_list); - INIT_LIST_HEAD(&tgt->srr_imm_list); - INIT_WORK(&tgt->srr_work, qlt_handle_srr_work); atomic_set(&tgt->tgt_global_resets_count, 0); base_vha->vha_tgt.qla_tgt = tgt; @@ -6251,29 +6045,25 @@ EXPORT_SYMBOL(qlt_lport_deregister); /* Must be called under HW lock */ static void qlt_set_mode(struct scsi_qla_host *vha) { - struct qla_hw_data *ha = vha->hw; - switch (ql2x_ini_mode) { case QLA2XXX_INI_MODE_DISABLED: case QLA2XXX_INI_MODE_EXCLUSIVE: vha->host->active_mode = MODE_TARGET; break; case QLA2XXX_INI_MODE_ENABLED: - vha->host->active_mode |= MODE_TARGET; + vha->host->active_mode = MODE_UNKNOWN; + break; + case QLA2XXX_INI_MODE_DUAL: + vha->host->active_mode = MODE_DUAL; break; default: break; } - - if (ha->tgt.ini_mode_force_reverse) - qla_reverse_ini_mode(vha); } /* Must be called under HW lock */ static void qlt_clear_mode(struct scsi_qla_host *vha) { - struct qla_hw_data *ha = vha->hw; - switch (ql2x_ini_mode) { case QLA2XXX_INI_MODE_DISABLED: vha->host->active_mode = MODE_UNKNOWN; @@ -6282,14 +6072,12 @@ static void qlt_clear_mode(struct scsi_qla_host *vha) vha->host->active_mode = MODE_INITIATOR; break; case QLA2XXX_INI_MODE_ENABLED: - vha->host->active_mode &= ~MODE_TARGET; + case QLA2XXX_INI_MODE_DUAL: + vha->host->active_mode = MODE_INITIATOR; break; default: break; } - - if (ha->tgt.ini_mode_force_reverse) - qla_reverse_ini_mode(vha); } /* @@ -6377,9 +6165,6 @@ static void qlt_disable_vha(struct scsi_qla_host *vha) void qlt_vport_create(struct scsi_qla_host *vha, struct qla_hw_data *ha) { - if (!qla_tgt_mode_enabled(vha)) - return; - vha->vha_tgt.qla_tgt = NULL; mutex_init(&vha->vha_tgt.tgt_mutex); @@ -6405,13 +6190,11 @@ qlt_rff_id(struct scsi_qla_host *vha, struct ct_sns_req *ct_req) * FC-4 Feature bit 0 indicates target functionality to the name server. */ if (qla_tgt_mode_enabled(vha)) { - if (qla_ini_mode_enabled(vha)) - ct_req->req.rff_id.fc4_feature = BIT_0 | BIT_1; - else - ct_req->req.rff_id.fc4_feature = BIT_0; + ct_req->req.rff_id.fc4_feature = BIT_0; } else if (qla_ini_mode_enabled(vha)) { ct_req->req.rff_id.fc4_feature = BIT_1; - } + } else if (qla_dual_mode_enabled(vha)) + ct_req->req.rff_id.fc4_feature = BIT_0 | BIT_1; } /* @@ -6430,7 +6213,7 @@ qlt_init_atio_q_entries(struct scsi_qla_host *vha) uint16_t cnt; struct atio_from_isp *pkt = (struct atio_from_isp *)ha->tgt.atio_ring; - if (!qla_tgt_mode_enabled(vha)) + if (qla_ini_mode_enabled(vha)) return; for (cnt = 0; cnt < ha->tgt.atio_q_length; cnt++) { @@ -6523,8 +6306,10 @@ void qlt_24xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_24xx *nv) { struct qla_hw_data *ha = vha->hw; + u32 tmp; + u16 t; - if (qla_tgt_mode_enabled(vha)) { + if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) { if (!ha->tgt.saved_set) { /* We save only once */ ha->tgt.saved_exchange_count = nv->exchange_count; @@ -6537,13 +6322,30 @@ qlt_24xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_24xx *nv) ha->tgt.saved_set = 1; } - nv->exchange_count = cpu_to_le16(0xFFFF); + if (qla_tgt_mode_enabled(vha)) { + nv->exchange_count = cpu_to_le16(0xFFFF); + } else { /* dual */ + if (ql_dm_tgt_ex_pct > 100) { + ql_dm_tgt_ex_pct = 50; + } else if (ql_dm_tgt_ex_pct == 100) { + /* leave some for FW */ + ql_dm_tgt_ex_pct = 95; + } + + tmp = ha->orig_fw_xcb_count * ql_dm_tgt_ex_pct; + tmp = tmp/100; + if (tmp > 0xffff) + tmp = 0xffff; + + t = tmp & 0xffff; + nv->exchange_count = cpu_to_le16(t); + } /* Enable target mode */ nv->firmware_options_1 |= cpu_to_le32(BIT_4); /* Disable ini mode, if requested */ - if (!qla_ini_mode_enabled(vha)) + if (qla_tgt_mode_enabled(vha)) nv->firmware_options_1 |= cpu_to_le32(BIT_5); /* Disable Full Login after LIP */ @@ -6622,11 +6424,13 @@ void qlt_81xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_81xx *nv) { struct qla_hw_data *ha = vha->hw; + u32 tmp; + u16 t; if (!QLA_TGT_MODE_ENABLED()) return; - if (qla_tgt_mode_enabled(vha)) { + if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) { if (!ha->tgt.saved_set) { /* We save only once */ ha->tgt.saved_exchange_count = nv->exchange_count; @@ -6639,13 +6443,29 @@ qlt_81xx_config_nvram_stage1(struct scsi_qla_host *vha, struct nvram_81xx *nv) ha->tgt.saved_set = 1; } - nv->exchange_count = cpu_to_le16(0xFFFF); + if (qla_tgt_mode_enabled(vha)) { + nv->exchange_count = cpu_to_le16(0xFFFF); + } else { /* dual */ + if (ql_dm_tgt_ex_pct > 100) { + ql_dm_tgt_ex_pct = 50; + } else if (ql_dm_tgt_ex_pct == 100) { + /* leave some for FW */ + ql_dm_tgt_ex_pct = 95; + } + + tmp = ha->orig_fw_xcb_count * ql_dm_tgt_ex_pct; + tmp = tmp/100; + if (tmp > 0xffff) + tmp = 0xffff; + t = tmp & 0xffff; + nv->exchange_count = cpu_to_le16(t); + } /* Enable target mode */ nv->firmware_options_1 |= cpu_to_le32(BIT_4); /* Disable ini mode, if requested */ - if (!qla_ini_mode_enabled(vha)) + if (qla_tgt_mode_enabled(vha)) nv->firmware_options_1 |= cpu_to_le32(BIT_5); /* Disable Full Login after LIP */ nv->firmware_options_1 &= cpu_to_le32(~BIT_13); @@ -6749,10 +6569,12 @@ void qlt_modify_vp_config(struct scsi_qla_host *vha, struct vp_config_entry_24xx *vpmod) { - if (qla_tgt_mode_enabled(vha)) + /* enable target mode. Bit5 = 1 => disable */ + if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha)) vpmod->options_idx1 &= ~BIT_5; - /* Disable ini mode, if requested */ - if (!qla_ini_mode_enabled(vha)) + + /* Disable ini mode, if requested. bit4 = 1 => disable */ + if (qla_tgt_mode_enabled(vha)) vpmod->options_idx1 &= ~BIT_4; } @@ -6772,6 +6594,11 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha) mutex_init(&base_vha->vha_tgt.tgt_mutex); mutex_init(&base_vha->vha_tgt.tgt_host_action_mutex); + + INIT_LIST_HEAD(&base_vha->unknown_atio_list); + INIT_DELAYED_WORK(&base_vha->unknown_atio_work, + qlt_unknown_atio_work_fn); + qlt_clear_mode(base_vha); } @@ -6906,6 +6733,8 @@ static int __init qlt_parse_ini_mode(void) ql2x_ini_mode = QLA2XXX_INI_MODE_DISABLED; else if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_ENABLED) == 0) ql2x_ini_mode = QLA2XXX_INI_MODE_ENABLED; + else if (strcasecmp(qlini_mode, QLA2XXX_INI_MODE_STR_DUAL) == 0) + ql2x_ini_mode = QLA2XXX_INI_MODE_DUAL; else return false; @@ -6935,9 +6764,8 @@ int __init qlt_init(void) } qla_tgt_plogi_cachep = kmem_cache_create("qla_tgt_plogi_cachep", - sizeof(qlt_plogi_ack_t), - __alignof__(qlt_plogi_ack_t), - 0, NULL); + sizeof(struct qlt_plogi_ack_t), __alignof__(struct qlt_plogi_ack_t), + 0, NULL); if (!qla_tgt_plogi_cachep) { ql_log(ql_log_fatal, NULL, 0xe06d, diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 0824a8164a24..a7f90dcaae37 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -45,10 +45,12 @@ #define QLA2XXX_INI_MODE_STR_EXCLUSIVE "exclusive" #define QLA2XXX_INI_MODE_STR_DISABLED "disabled" #define QLA2XXX_INI_MODE_STR_ENABLED "enabled" +#define QLA2XXX_INI_MODE_STR_DUAL "dual" #define QLA2XXX_INI_MODE_EXCLUSIVE 0 #define QLA2XXX_INI_MODE_DISABLED 1 #define QLA2XXX_INI_MODE_ENABLED 2 +#define QLA2XXX_INI_MODE_DUAL 3 #define QLA2XXX_COMMAND_COUNT_INIT 250 #define QLA2XXX_IMMED_NOTIFY_COUNT_INIT 250 @@ -118,84 +120,6 @@ ? le16_to_cpu((iocb)->u.isp2x.target.extended) \ : (uint16_t)(iocb)->u.isp2x.target.id.standard) -#ifndef IMMED_NOTIFY_TYPE -#define IMMED_NOTIFY_TYPE 0x0D /* Immediate notify entry. */ -/* - * ISP queue - immediate notify entry structure definition. - * This is sent by the ISP to the Target driver. - * This IOCB would have report of events sent by the - * initiator, that needs to be handled by the target - * driver immediately. - */ -struct imm_ntfy_from_isp { - uint8_t entry_type; /* Entry type. */ - uint8_t entry_count; /* Entry count. */ - uint8_t sys_define; /* System defined. */ - uint8_t entry_status; /* Entry Status. */ - union { - struct { - uint32_t sys_define_2; /* System defined. */ - target_id_t target; - uint16_t lun; - uint8_t target_id; - uint8_t reserved_1; - uint16_t status_modifier; - uint16_t status; - uint16_t task_flags; - uint16_t seq_id; - uint16_t srr_rx_id; - uint32_t srr_rel_offs; - uint16_t srr_ui; -#define SRR_IU_DATA_IN 0x1 -#define SRR_IU_DATA_OUT 0x5 -#define SRR_IU_STATUS 0x7 - uint16_t srr_ox_id; - uint8_t reserved_2[28]; - } isp2x; - struct { - uint32_t reserved; - uint16_t nport_handle; - uint16_t reserved_2; - uint16_t flags; -#define NOTIFY24XX_FLAGS_GLOBAL_TPRLO BIT_1 -#define NOTIFY24XX_FLAGS_PUREX_IOCB BIT_0 - uint16_t srr_rx_id; - uint16_t status; - uint8_t status_subcode; - uint8_t fw_handle; - uint32_t exchange_address; - uint32_t srr_rel_offs; - uint16_t srr_ui; - uint16_t srr_ox_id; - union { - struct { - uint8_t node_name[8]; - } plogi; /* PLOGI/ADISC/PDISC */ - struct { - /* PRLI word 3 bit 0-15 */ - uint16_t wd3_lo; - uint8_t resv0[6]; - } prli; - struct { - uint8_t port_id[3]; - uint8_t resv1; - uint16_t nport_handle; - uint16_t resv2; - } req_els; - } u; - uint8_t port_name[8]; - uint8_t resv3[3]; - uint8_t vp_index; - uint32_t reserved_5; - uint8_t port_id[3]; - uint8_t reserved_6; - } isp24; - } u; - uint16_t reserved_7; - uint16_t ox_id; -} __packed; -#endif - #ifndef NOTIFY_ACK_TYPE #define NOTIFY_ACK_TYPE 0x0E /* Notify acknowledge entry. */ /* @@ -731,7 +655,7 @@ struct abts_resp_from_24xx_fw { \********************************************************************/ struct qla_tgt_mgmt_cmd; -struct qla_tgt_sess; +struct fc_port; /* * This structure provides a template of function calls that the @@ -744,21 +668,22 @@ struct qla_tgt_func_tmpl { unsigned char *, uint32_t, int, int, int); void (*handle_data)(struct qla_tgt_cmd *); void (*handle_dif_err)(struct qla_tgt_cmd *); - int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint8_t, + int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint16_t, uint32_t); void (*free_cmd)(struct qla_tgt_cmd *); void (*free_mcmd)(struct qla_tgt_mgmt_cmd *); - void (*free_session)(struct qla_tgt_sess *); + void (*free_session)(struct fc_port *); int (*check_initiator_node_acl)(struct scsi_qla_host *, unsigned char *, - struct qla_tgt_sess *); - void (*update_sess)(struct qla_tgt_sess *, port_id_t, uint16_t, bool); - struct qla_tgt_sess *(*find_sess_by_loop_id)(struct scsi_qla_host *, + struct fc_port *); + void (*update_sess)(struct fc_port *, port_id_t, uint16_t, bool); + struct fc_port *(*find_sess_by_loop_id)(struct scsi_qla_host *, const uint16_t); - struct qla_tgt_sess *(*find_sess_by_s_id)(struct scsi_qla_host *, + struct fc_port *(*find_sess_by_s_id)(struct scsi_qla_host *, const uint8_t *); - void (*clear_nacl_from_fcport_map)(struct qla_tgt_sess *); - void (*shutdown_sess)(struct qla_tgt_sess *); + void (*clear_nacl_from_fcport_map)(struct fc_port *); + void (*put_sess)(struct fc_port *); + void (*shutdown_sess)(struct fc_port *); }; int qla2x00_wait_for_hba_online(struct scsi_qla_host *); @@ -795,6 +720,8 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *); #define QLA_TGT_ABORT_ALL 0xFFFE #define QLA_TGT_NEXUS_LOSS_SESS 0xFFFD #define QLA_TGT_NEXUS_LOSS 0xFFFC +#define QLA_TGT_ABTS 0xFFFB +#define QLA_TGT_2G_ABORT_TASK 0xFFFA /* Notify Acknowledge flags */ #define NOTIFY_ACK_RES_COUNT BIT_8 @@ -872,12 +799,8 @@ struct qla_tgt { /* Count of sessions refering qla_tgt. Protected by hardware_lock. */ int sess_count; - /* Protected by hardware_lock. Addition also protected by tgt_mutex. */ - struct list_head sess_list; - /* Protected by hardware_lock */ struct list_head del_sess_list; - struct delayed_work sess_del_work; spinlock_t sess_work_lock; struct list_head sess_works_list; @@ -888,16 +811,7 @@ struct qla_tgt { int notify_ack_expected; int abts_resp_expected; int modify_lun_expected; - - int ctio_srr_id; - int imm_srr_id; - spinlock_t srr_lock; - struct list_head srr_ctio_list; - struct list_head srr_imm_list; - struct work_struct srr_work; - atomic_t tgt_global_resets_count; - struct list_head tgt_list_entry; }; @@ -910,92 +824,32 @@ struct qla_tgt_sess_op { bool aborted; }; -enum qla_sess_deletion { - QLA_SESS_DELETION_NONE = 0, - QLA_SESS_DELETION_PENDING = 1, /* hopefully we can get rid of - * this one */ - QLA_SESS_DELETION_IN_PROGRESS = 2, -}; - -typedef enum { - QLT_PLOGI_LINK_SAME_WWN, - QLT_PLOGI_LINK_CONFLICT, - QLT_PLOGI_LINK_MAX -} qlt_plogi_link_t; - -typedef struct { - struct list_head list; - struct imm_ntfy_from_isp iocb; - port_id_t id; - int ref_count; -} qlt_plogi_ack_t; - -/* - * Equivilant to IT Nexus (Initiator-Target) - */ -struct qla_tgt_sess { - uint16_t loop_id; - port_id_t s_id; - - unsigned int conf_compl_supported:1; - unsigned int deleted:2; - unsigned int local:1; - unsigned int logout_on_delete:1; - unsigned int keep_nport_handle:1; - unsigned int send_els_logo:1; - - unsigned char logout_completed; - - int generation; - - struct se_session *se_sess; - struct kref sess_kref; - struct scsi_qla_host *vha; - struct qla_tgt *tgt; - - struct list_head sess_list_entry; - unsigned long expires; - struct list_head del_list_entry; - - uint8_t port_name[WWN_SIZE]; - struct work_struct free_work; - - qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX]; +enum trace_flags { + TRC_NEW_CMD = BIT_0, + TRC_DO_WORK = BIT_1, + TRC_DO_WORK_ERR = BIT_2, + TRC_XFR_RDY = BIT_3, + TRC_XMIT_DATA = BIT_4, + TRC_XMIT_STATUS = BIT_5, + TRC_SRR_RSP = BIT_6, + TRC_SRR_XRDY = BIT_7, + TRC_SRR_TERM = BIT_8, + TRC_SRR_CTIO = BIT_9, + TRC_FLUSH = BIT_10, + TRC_CTIO_ERR = BIT_11, + TRC_CTIO_DONE = BIT_12, + TRC_CTIO_ABORTED = BIT_13, + TRC_CTIO_STRANGE= BIT_14, + TRC_CMD_DONE = BIT_15, + TRC_CMD_CHK_STOP = BIT_16, + TRC_CMD_FREE = BIT_17, + TRC_DATA_IN = BIT_18, + TRC_ABORT = BIT_19, }; -typedef enum { - /* - * BIT_0 - Atio Arrival / schedule to work - * BIT_1 - qlt_do_work - * BIT_2 - qlt_do work failed - * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending - * BIT_4 - read respond/tcm_qla2xx_queue_data_in - * BIT_5 - status respond / tcm_qla2xx_queue_status - * BIT_6 - tcm request to abort/Term exchange. - * pre_xmit_response->qlt_send_term_exchange - * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response) - * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer) - * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange) - * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data - - * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd - * BIT_13 - Bad completion - - * qlt_ctio_do_completion --> qlt_term_ctio_exchange - * BIT_14 - Back end data received/sent. - * BIT_15 - SRR prepare ctio - * BIT_16 - complete free - * BIT_17 - flush - qlt_abort_cmd_on_host_reset - * BIT_18 - completion w/abort status - * BIT_19 - completion w/unknown status - * BIT_20 - tcm_qla2xxx_free_cmd - */ - CMD_FLAG_DATA_WORK = BIT_11, - CMD_FLAG_DATA_WORK_FREE = BIT_21, -} cmd_flags_t; - struct qla_tgt_cmd { struct se_cmd se_cmd; - struct qla_tgt_sess *sess; + struct fc_port *sess; int state; struct work_struct free_work; struct work_struct work; @@ -1014,6 +868,8 @@ struct qla_tgt_cmd { unsigned int cmd_sent_to_fw:1; unsigned int cmd_in_wq:1; unsigned int aborted:1; + unsigned int data_work:1; + unsigned int data_work_free:1; struct scatterlist *sg; /* cmd data buffer SG vector */ int sg_cnt; /* SG segments count */ @@ -1038,7 +894,7 @@ struct qla_tgt_cmd { uint64_t jiffies_at_alloc; uint64_t jiffies_at_free; - cmd_flags_t cmd_flags; + enum trace_flags trc_flags; }; struct qla_tgt_sess_work_param { @@ -1056,9 +912,9 @@ struct qla_tgt_sess_work_param { }; struct qla_tgt_mgmt_cmd { - uint8_t tmr_func; + uint16_t tmr_func; uint8_t fc_tm_rsp; - struct qla_tgt_sess *sess; + struct fc_port *sess; struct se_cmd se_cmd; struct work_struct free_work; unsigned int flags; @@ -1090,18 +946,6 @@ struct qla_tgt_prm { uint16_t tot_dsds; }; -struct qla_tgt_srr_imm { - struct list_head srr_list_entry; - int srr_id; - struct imm_ntfy_from_isp imm_ntfy; -}; - -struct qla_tgt_srr_ctio { - struct list_head srr_list_entry; - int srr_id; - struct qla_tgt_cmd *cmd; -}; - /* Check for Switch reserved address */ #define IS_SW_RESV_ADDR(_s_id) \ ((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc)) @@ -1121,7 +965,7 @@ extern int qlt_remove_target(struct qla_hw_data *, struct scsi_qla_host *); extern int qlt_lport_register(void *, u64, u64, u64, int (*callback)(struct scsi_qla_host *, void *, u64, u64)); extern void qlt_lport_deregister(struct scsi_qla_host *); -void qlt_put_sess(struct qla_tgt_sess *sess); +extern void qlt_unreg_sess(struct fc_port *); extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *); extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int); extern int __init qlt_init(void); @@ -1133,24 +977,22 @@ extern void qlt_update_vp_map(struct scsi_qla_host *, int); * is not set. Right now, ha value is ignored. */ #define QLA_TGT_MODE_ENABLED() (ql2x_ini_mode != QLA2XXX_INI_MODE_ENABLED) + extern int ql2x_ini_mode; static inline bool qla_tgt_mode_enabled(struct scsi_qla_host *ha) { - return ha->host->active_mode & MODE_TARGET; + return ha->host->active_mode == MODE_TARGET; } static inline bool qla_ini_mode_enabled(struct scsi_qla_host *ha) { - return ha->host->active_mode & MODE_INITIATOR; + return ha->host->active_mode == MODE_INITIATOR; } -static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha) +static inline bool qla_dual_mode_enabled(struct scsi_qla_host *ha) { - if (ha->host->active_mode & MODE_INITIATOR) - ha->host->active_mode &= ~MODE_INITIATOR; - else - ha->host->active_mode |= MODE_INITIATOR; + return (ha->host->active_mode == MODE_DUAL); } static inline uint32_t sid_to_key(const uint8_t *s_id) diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 3084983c1287..c2f8c3580880 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -282,10 +282,10 @@ static void tcm_qla2xxx_complete_free(struct work_struct *work) cmd->cmd_in_wq = 0; - WARN_ON(cmd->cmd_flags & BIT_16); + WARN_ON(cmd->trc_flags & TRC_CMD_FREE); cmd->vha->tgt_counters.qla_core_ret_sta_ctio++; - cmd->cmd_flags |= BIT_16; + cmd->trc_flags |= TRC_CMD_FREE; transport_generic_free_cmd(&cmd->se_cmd, 0); } @@ -299,8 +299,8 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd) cmd->vha->tgt_counters.core_qla_free_cmd++; cmd->cmd_in_wq = 1; - BUG_ON(cmd->cmd_flags & BIT_20); - cmd->cmd_flags |= BIT_20; + WARN_ON(cmd->trc_flags & TRC_CMD_DONE); + cmd->trc_flags |= TRC_CMD_DONE; INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free); queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work); @@ -315,7 +315,7 @@ static int tcm_qla2xxx_check_stop_free(struct se_cmd *se_cmd) if ((se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) == 0) { cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - cmd->cmd_flags |= BIT_14; + cmd->trc_flags |= TRC_CMD_CHK_STOP; } return target_put_sess_cmd(se_cmd); @@ -339,9 +339,26 @@ static void tcm_qla2xxx_release_cmd(struct se_cmd *se_cmd) qlt_free_cmd(cmd); } +static void tcm_qla2xxx_release_session(struct kref *kref) +{ + struct fc_port *sess = container_of(kref, + struct fc_port, sess_kref); + + qlt_unreg_sess(sess); +} + +static void tcm_qla2xxx_put_sess(struct fc_port *sess) +{ + if (!sess) + return; + + assert_spin_locked(&sess->vha->hw->tgt.sess_lock); + kref_put(&sess->sess_kref, tcm_qla2xxx_release_session); +} + static void tcm_qla2xxx_close_session(struct se_session *se_sess) { - struct qla_tgt_sess *sess = se_sess->fabric_sess_ptr; + struct fc_port *sess = se_sess->fabric_sess_ptr; struct scsi_qla_host *vha; unsigned long flags; @@ -350,7 +367,7 @@ static void tcm_qla2xxx_close_session(struct se_session *se_sess) spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); target_sess_cmd_list_set_waiting(se_sess); - qlt_put_sess(sess); + tcm_qla2xxx_put_sess(sess); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); } @@ -377,7 +394,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) cmd->se_cmd.se_cmd_flags); return 0; } - cmd->cmd_flags |= BIT_3; + cmd->trc_flags |= TRC_XFR_RDY; cmd->bufflen = se_cmd->data_length; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); @@ -441,7 +458,7 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, { struct se_cmd *se_cmd = &cmd->se_cmd; struct se_session *se_sess; - struct qla_tgt_sess *sess; + struct fc_port *sess; #ifdef CONFIG_TCM_QLA2XXX_DEBUG struct se_portal_group *se_tpg; struct tcm_qla2xxx_tpg *tpg; @@ -456,7 +473,7 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, sess = cmd->sess; if (!sess) { - pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n"); + pr_err("Unable to locate struct fc_port from qla_tgt_cmd\n"); return -EINVAL; } @@ -493,9 +510,9 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) cmd->cmd_in_wq = 0; spin_lock_irqsave(&cmd->cmd_lock, flags); - cmd->cmd_flags |= CMD_FLAG_DATA_WORK; + cmd->data_work = 1; if (cmd->aborted) { - cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE; + cmd->data_work_free = 1; spin_unlock_irqrestore(&cmd->cmd_lock, flags); tcm_qla2xxx_free_cmd(cmd); @@ -532,7 +549,7 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) */ static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd) { - cmd->cmd_flags |= BIT_10; + cmd->trc_flags |= TRC_DATA_IN; cmd->cmd_in_wq = 1; INIT_WORK(&cmd->work, tcm_qla2xxx_handle_data_work); queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work); @@ -563,13 +580,49 @@ static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd) * Called from qla_target.c:qlt_issue_task_mgmt() */ static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t lun, - uint8_t tmr_func, uint32_t tag) + uint16_t tmr_func, uint32_t tag) { - struct qla_tgt_sess *sess = mcmd->sess; + struct fc_port *sess = mcmd->sess; struct se_cmd *se_cmd = &mcmd->se_cmd; + int transl_tmr_func = 0; + + switch (tmr_func) { + case QLA_TGT_ABTS: + pr_debug("%ld: ABTS received\n", sess->vha->host_no); + transl_tmr_func = TMR_ABORT_TASK; + break; + case QLA_TGT_2G_ABORT_TASK: + pr_debug("%ld: 2G Abort Task received\n", sess->vha->host_no); + transl_tmr_func = TMR_ABORT_TASK; + break; + case QLA_TGT_CLEAR_ACA: + pr_debug("%ld: CLEAR_ACA received\n", sess->vha->host_no); + transl_tmr_func = TMR_CLEAR_ACA; + break; + case QLA_TGT_TARGET_RESET: + pr_debug("%ld: TARGET_RESET received\n", sess->vha->host_no); + transl_tmr_func = TMR_TARGET_WARM_RESET; + break; + case QLA_TGT_LUN_RESET: + pr_debug("%ld: LUN_RESET received\n", sess->vha->host_no); + transl_tmr_func = TMR_LUN_RESET; + break; + case QLA_TGT_CLEAR_TS: + pr_debug("%ld: CLEAR_TS received\n", sess->vha->host_no); + transl_tmr_func = TMR_CLEAR_TASK_SET; + break; + case QLA_TGT_ABORT_TS: + pr_debug("%ld: ABORT_TS received\n", sess->vha->host_no); + transl_tmr_func = TMR_ABORT_TASK_SET; + break; + default: + pr_debug("%ld: Unknown task mgmt fn 0x%x\n", + sess->vha->host_no, tmr_func); + return -ENOSYS; + } return target_submit_tmr(se_cmd, sess->se_sess, NULL, lun, mcmd, - tmr_func, GFP_ATOMIC, tag, TARGET_SCF_ACK_KREF); + transl_tmr_func, GFP_ATOMIC, tag, TARGET_SCF_ACK_KREF); } static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) @@ -591,7 +644,7 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) return 0; } - cmd->cmd_flags |= BIT_4; + cmd->trc_flags |= TRC_XMIT_DATA; cmd->bufflen = se_cmd->data_length; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); @@ -622,11 +675,11 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) cmd->sg_cnt = 0; cmd->offset = 0; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); - if (cmd->cmd_flags & BIT_5) { - pr_crit("Bit_5 already set for cmd = %p.\n", cmd); + if (cmd->trc_flags & TRC_XMIT_STATUS) { + pr_crit("Multiple calls for status = %p.\n", cmd); dump_stack(); } - cmd->cmd_flags |= BIT_5; + cmd->trc_flags |= TRC_XMIT_STATUS; if (se_cmd->data_direction == DMA_FROM_DEVICE) { /* @@ -682,10 +735,7 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd) qlt_xmit_tm_rsp(mcmd); } - -#define DATA_WORK_NOT_FREE(_flags) \ - (( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \ - CMD_FLAG_DATA_WORK) +#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free) static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, @@ -697,13 +747,13 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) spin_lock_irqsave(&cmd->cmd_lock, flags); if ((cmd->state == QLA_TGT_STATE_NEW)|| - ((cmd->state == QLA_TGT_STATE_DATA_IN) && - DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) { - - cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE; + ((cmd->state == QLA_TGT_STATE_DATA_IN) && + DATA_WORK_NOT_FREE(cmd))) { + cmd->data_work_free = 1; spin_unlock_irqrestore(&cmd->cmd_lock, flags); - /* Cmd have not reached firmware. - * Use this trigger to free it. */ + /* + * cmd has not reached fw, Use this trigger to free it. + */ tcm_qla2xxx_free_cmd(cmd); return; } @@ -713,11 +763,11 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, - struct tcm_qla2xxx_nacl *, struct qla_tgt_sess *); + struct tcm_qla2xxx_nacl *, struct fc_port *); /* * Expected to be called with struct qla_hw_data->tgt.sess_lock held */ -static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess) +static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct fc_port *sess) { struct se_node_acl *se_nacl = sess->se_sess->se_node_acl; struct se_portal_group *se_tpg = se_nacl->se_tpg; @@ -756,7 +806,7 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess) tcm_qla2xxx_clear_sess_lookup(lport, nacl, sess); } -static void tcm_qla2xxx_shutdown_sess(struct qla_tgt_sess *sess) +static void tcm_qla2xxx_shutdown_sess(struct fc_port *sess) { assert_spin_locked(&sess->vha->hw->tgt.sess_lock); target_sess_cmd_list_set_waiting(sess->se_sess); @@ -1141,7 +1191,7 @@ static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg( /* * Expected to be called with struct qla_hw_data->tgt.sess_lock held */ -static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id( +static struct fc_port *tcm_qla2xxx_find_sess_by_s_id( scsi_qla_host_t *vha, const uint8_t *s_id) { @@ -1169,12 +1219,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id( se_nacl, se_nacl->initiatorname); nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl); - if (!nacl->qla_tgt_sess) { - pr_err("Unable to locate struct qla_tgt_sess\n"); + if (!nacl->fc_port) { + pr_err("Unable to locate struct fc_port\n"); return NULL; } - return nacl->qla_tgt_sess; + return nacl->fc_port; } /* @@ -1185,7 +1235,7 @@ static void tcm_qla2xxx_set_sess_by_s_id( struct se_node_acl *new_se_nacl, struct tcm_qla2xxx_nacl *nacl, struct se_session *se_sess, - struct qla_tgt_sess *qla_tgt_sess, + struct fc_port *fc_port, uint8_t *s_id) { u32 key; @@ -1209,22 +1259,22 @@ static void tcm_qla2xxx_set_sess_by_s_id( pr_debug("Wiping nonexisting fc_port entry\n"); } - qla_tgt_sess->se_sess = se_sess; - nacl->qla_tgt_sess = qla_tgt_sess; + fc_port->se_sess = se_sess; + nacl->fc_port = fc_port; return; } - if (nacl->qla_tgt_sess) { + if (nacl->fc_port) { if (new_se_nacl == NULL) { - pr_debug("Clearing existing nacl->qla_tgt_sess and fc_port entry\n"); + pr_debug("Clearing existing nacl->fc_port and fc_port entry\n"); btree_remove32(&lport->lport_fcport_map, key); - nacl->qla_tgt_sess = NULL; + nacl->fc_port = NULL; return; } - pr_debug("Replacing existing nacl->qla_tgt_sess and fc_port entry\n"); + pr_debug("Replacing existing nacl->fc_port and fc_port entry\n"); btree_update32(&lport->lport_fcport_map, key, new_se_nacl); - qla_tgt_sess->se_sess = se_sess; - nacl->qla_tgt_sess = qla_tgt_sess; + fc_port->se_sess = se_sess; + nacl->fc_port = fc_port; return; } @@ -1234,19 +1284,19 @@ static void tcm_qla2xxx_set_sess_by_s_id( return; } - pr_debug("Replacing existing fc_port entry w/o active nacl->qla_tgt_sess\n"); + pr_debug("Replacing existing fc_port entry w/o active nacl->fc_port\n"); btree_update32(&lport->lport_fcport_map, key, new_se_nacl); - qla_tgt_sess->se_sess = se_sess; - nacl->qla_tgt_sess = qla_tgt_sess; + fc_port->se_sess = se_sess; + nacl->fc_port = fc_port; - pr_debug("Setup nacl->qla_tgt_sess %p by s_id for se_nacl: %p, initiatorname: %s\n", - nacl->qla_tgt_sess, new_se_nacl, new_se_nacl->initiatorname); + pr_debug("Setup nacl->fc_port %p by s_id for se_nacl: %p, initiatorname: %s\n", + nacl->fc_port, new_se_nacl, new_se_nacl->initiatorname); } /* * Expected to be called with struct qla_hw_data->tgt.sess_lock held */ -static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_loop_id( +static struct fc_port *tcm_qla2xxx_find_sess_by_loop_id( scsi_qla_host_t *vha, const uint16_t loop_id) { @@ -1274,12 +1324,12 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_loop_id( nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl); - if (!nacl->qla_tgt_sess) { - pr_err("Unable to locate struct qla_tgt_sess\n"); + if (!nacl->fc_port) { + pr_err("Unable to locate struct fc_port\n"); return NULL; } - return nacl->qla_tgt_sess; + return nacl->fc_port; } /* @@ -1290,7 +1340,7 @@ static void tcm_qla2xxx_set_sess_by_loop_id( struct se_node_acl *new_se_nacl, struct tcm_qla2xxx_nacl *nacl, struct se_session *se_sess, - struct qla_tgt_sess *qla_tgt_sess, + struct fc_port *fc_port, uint16_t loop_id) { struct se_node_acl *saved_nacl; @@ -1305,27 +1355,27 @@ static void tcm_qla2xxx_set_sess_by_loop_id( if (!saved_nacl) { pr_debug("Setting up new fc_loopid->se_nacl to new_se_nacl\n"); fc_loopid->se_nacl = new_se_nacl; - if (qla_tgt_sess->se_sess != se_sess) - qla_tgt_sess->se_sess = se_sess; - if (nacl->qla_tgt_sess != qla_tgt_sess) - nacl->qla_tgt_sess = qla_tgt_sess; + if (fc_port->se_sess != se_sess) + fc_port->se_sess = se_sess; + if (nacl->fc_port != fc_port) + nacl->fc_port = fc_port; return; } - if (nacl->qla_tgt_sess) { + if (nacl->fc_port) { if (new_se_nacl == NULL) { - pr_debug("Clearing nacl->qla_tgt_sess and fc_loopid->se_nacl\n"); + pr_debug("Clearing nacl->fc_port and fc_loopid->se_nacl\n"); fc_loopid->se_nacl = NULL; - nacl->qla_tgt_sess = NULL; + nacl->fc_port = NULL; return; } - pr_debug("Replacing existing nacl->qla_tgt_sess and fc_loopid->se_nacl\n"); + pr_debug("Replacing existing nacl->fc_port and fc_loopid->se_nacl\n"); fc_loopid->se_nacl = new_se_nacl; - if (qla_tgt_sess->se_sess != se_sess) - qla_tgt_sess->se_sess = se_sess; - if (nacl->qla_tgt_sess != qla_tgt_sess) - nacl->qla_tgt_sess = qla_tgt_sess; + if (fc_port->se_sess != se_sess) + fc_port->se_sess = se_sess; + if (nacl->fc_port != fc_port) + nacl->fc_port = fc_port; return; } @@ -1335,29 +1385,29 @@ static void tcm_qla2xxx_set_sess_by_loop_id( return; } - pr_debug("Replacing existing fc_loopid->se_nacl w/o active nacl->qla_tgt_sess\n"); + pr_debug("Replacing existing fc_loopid->se_nacl w/o active nacl->fc_port\n"); fc_loopid->se_nacl = new_se_nacl; - if (qla_tgt_sess->se_sess != se_sess) - qla_tgt_sess->se_sess = se_sess; - if (nacl->qla_tgt_sess != qla_tgt_sess) - nacl->qla_tgt_sess = qla_tgt_sess; + if (fc_port->se_sess != se_sess) + fc_port->se_sess = se_sess; + if (nacl->fc_port != fc_port) + nacl->fc_port = fc_port; - pr_debug("Setup nacl->qla_tgt_sess %p by loop_id for se_nacl: %p, initiatorname: %s\n", - nacl->qla_tgt_sess, new_se_nacl, new_se_nacl->initiatorname); + pr_debug("Setup nacl->fc_port %p by loop_id for se_nacl: %p, initiatorname: %s\n", + nacl->fc_port, new_se_nacl, new_se_nacl->initiatorname); } /* * Should always be called with qla_hw_data->tgt.sess_lock held. */ static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *lport, - struct tcm_qla2xxx_nacl *nacl, struct qla_tgt_sess *sess) + struct tcm_qla2xxx_nacl *nacl, struct fc_port *sess) { struct se_session *se_sess = sess->se_sess; unsigned char be_sid[3]; - be_sid[0] = sess->s_id.b.domain; - be_sid[1] = sess->s_id.b.area; - be_sid[2] = sess->s_id.b.al_pa; + be_sid[0] = sess->d_id.b.domain; + be_sid[1] = sess->d_id.b.area; + be_sid[2] = sess->d_id.b.al_pa; tcm_qla2xxx_set_sess_by_s_id(lport, NULL, nacl, se_sess, sess, be_sid); @@ -1365,7 +1415,7 @@ static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *lport, sess, sess->loop_id); } -static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess) +static void tcm_qla2xxx_free_session(struct fc_port *sess) { struct qla_tgt *tgt = sess->tgt; struct qla_hw_data *ha = tgt->ha; @@ -1377,7 +1427,7 @@ static void tcm_qla2xxx_free_session(struct qla_tgt_sess *sess) se_sess = sess->se_sess; if (!se_sess) { - pr_err("struct qla_tgt_sess->se_sess is NULL\n"); + pr_err("struct fc_port->se_sess is NULL\n"); dump_stack(); return; } @@ -1404,14 +1454,14 @@ static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg, struct se_node_acl *se_nacl = se_sess->se_node_acl; struct tcm_qla2xxx_nacl *nacl = container_of(se_nacl, struct tcm_qla2xxx_nacl, se_node_acl); - struct qla_tgt_sess *qlat_sess = p; + struct fc_port *qlat_sess = p; uint16_t loop_id = qlat_sess->loop_id; unsigned long flags; unsigned char be_sid[3]; - be_sid[0] = qlat_sess->s_id.b.domain; - be_sid[1] = qlat_sess->s_id.b.area; - be_sid[2] = qlat_sess->s_id.b.al_pa; + be_sid[0] = qlat_sess->d_id.b.domain; + be_sid[1] = qlat_sess->d_id.b.area; + be_sid[2] = qlat_sess->d_id.b.al_pa; /* * And now setup se_nacl and session pointers into HW lport internal @@ -1434,7 +1484,7 @@ static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg, static int tcm_qla2xxx_check_initiator_node_acl( scsi_qla_host_t *vha, unsigned char *fc_wwpn, - struct qla_tgt_sess *qlat_sess) + struct fc_port *qlat_sess) { struct qla_hw_data *ha = vha->hw; struct tcm_qla2xxx_lport *lport; @@ -1478,7 +1528,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( return 0; } -static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, +static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id, uint16_t loop_id, bool conf_compl_supported) { struct qla_tgt *tgt = sess->tgt; @@ -1491,11 +1541,11 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, u32 key; - if (sess->loop_id != loop_id || sess->s_id.b24 != s_id.b24) + if (sess->loop_id != loop_id || sess->d_id.b24 != s_id.b24) pr_info("Updating session %p from port %8phC loop_id %d -> %d s_id %x:%x:%x -> %x:%x:%x\n", sess, sess->port_name, - sess->loop_id, loop_id, sess->s_id.b.domain, - sess->s_id.b.area, sess->s_id.b.al_pa, s_id.b.domain, + sess->loop_id, loop_id, sess->d_id.b.domain, + sess->d_id.b.area, sess->d_id.b.al_pa, s_id.b.domain, s_id.b.area, s_id.b.al_pa); if (sess->loop_id != loop_id) { @@ -1515,18 +1565,20 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, sess->loop_id = loop_id; } - if (sess->s_id.b24 != s_id.b24) { - key = (((u32) sess->s_id.b.domain << 16) | - ((u32) sess->s_id.b.area << 8) | - ((u32) sess->s_id.b.al_pa)); + if (sess->d_id.b24 != s_id.b24) { + key = (((u32) sess->d_id.b.domain << 16) | + ((u32) sess->d_id.b.area << 8) | + ((u32) sess->d_id.b.al_pa)); if (btree_lookup32(&lport->lport_fcport_map, key)) - WARN(btree_remove32(&lport->lport_fcport_map, key) != se_nacl, - "Found wrong se_nacl when updating s_id %x:%x:%x\n", - sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa); + WARN(btree_remove32(&lport->lport_fcport_map, key) != + se_nacl, "Found wrong se_nacl when updating s_id %x:%x:%x\n", + sess->d_id.b.domain, sess->d_id.b.area, + sess->d_id.b.al_pa); else WARN(1, "No lport_fcport_map entry for s_id %x:%x:%x\n", - sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa); + sess->d_id.b.domain, sess->d_id.b.area, + sess->d_id.b.al_pa); key = (((u32) s_id.b.domain << 16) | ((u32) s_id.b.area << 8) | @@ -1537,10 +1589,11 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, s_id.b.domain, s_id.b.area, s_id.b.al_pa); btree_update32(&lport->lport_fcport_map, key, se_nacl); } else { - btree_insert32(&lport->lport_fcport_map, key, se_nacl, GFP_ATOMIC); + btree_insert32(&lport->lport_fcport_map, key, se_nacl, + GFP_ATOMIC); } - sess->s_id = s_id; + sess->d_id = s_id; nacl->nport_id = key; } @@ -1567,6 +1620,7 @@ static struct qla_tgt_func_tmpl tcm_qla2xxx_template = { .find_sess_by_s_id = tcm_qla2xxx_find_sess_by_s_id, .find_sess_by_loop_id = tcm_qla2xxx_find_sess_by_loop_id, .clear_nacl_from_fcport_map = tcm_qla2xxx_clear_nacl_from_fcport_map, + .put_sess = tcm_qla2xxx_put_sess, .shutdown_sess = tcm_qla2xxx_shutdown_sess, }; @@ -1690,7 +1744,7 @@ static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha, (struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr; struct fc_vport_identifiers vport_id; - if (!qla_tgt_mode_enabled(base_vha)) { + if (qla_ini_mode_enabled(base_vha)) { pr_err("qla2xxx base_vha not enabled for target mode\n"); return -EPERM; } diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h index cf8430be183b..071035dfa99a 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h @@ -20,8 +20,8 @@ struct tcm_qla2xxx_nacl { u64 nport_wwnn; /* ASCII formatted WWPN for FC Initiator Nport */ char nport_name[TCM_QLA2XXX_NAMELEN]; - /* Pointer to qla_tgt_sess */ - struct qla_tgt_sess *qla_tgt_sess; + /* Pointer to fc_port */ + struct fc_port *fc_port; /* Pointer to TCM FC nexus */ struct se_session *nport_nexus; }; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index c680d7641311..939c47df73fa 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/mempool.h> +#include <linux/interrupt.h> #include <linux/virtio.h> #include <linux/virtio_ids.h> #include <linux/virtio_config.h> @@ -29,6 +30,7 @@ #include <scsi/scsi_cmnd.h> #include <scsi/scsi_tcq.h> #include <linux/seqlock.h> +#include <linux/blk-mq-virtio.h> #define VIRTIO_SCSI_MEMPOOL_SZ 64 #define VIRTIO_SCSI_EVENT_LEN 8 @@ -108,7 +110,6 @@ struct virtio_scsi { bool affinity_hint_set; struct hlist_node node; - struct hlist_node node_dead; /* Protected by event_vq lock */ bool stop_events; @@ -118,7 +119,6 @@ struct virtio_scsi { struct virtio_scsi_vq req_vqs[]; }; -static enum cpuhp_state virtioscsi_online; static struct kmem_cache *virtscsi_cmd_cache; static mempool_t *virtscsi_cmd_pool; @@ -766,6 +766,13 @@ static void virtscsi_target_destroy(struct scsi_target *starget) kfree(tgt); } +static int virtscsi_map_queues(struct Scsi_Host *shost) +{ + struct virtio_scsi *vscsi = shost_priv(shost); + + return blk_mq_virtio_map_queues(&shost->tag_set, vscsi->vdev, 2); +} + static struct scsi_host_template virtscsi_host_template_single = { .module = THIS_MODULE, .name = "Virtio SCSI HBA", @@ -801,6 +808,7 @@ static struct scsi_host_template virtscsi_host_template_multi = { .use_clustering = ENABLE_CLUSTERING, .target_alloc = virtscsi_target_alloc, .target_destroy = virtscsi_target_destroy, + .map_queues = virtscsi_map_queues, .track_queue_depth = 1, }; @@ -817,80 +825,6 @@ static struct scsi_host_template virtscsi_host_template_multi = { virtio_cwrite(vdev, struct virtio_scsi_config, fld, &__val); \ } while(0) -static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity) -{ - int i; - int cpu; - - /* In multiqueue mode, when the number of cpu is equal - * to the number of request queues, we let the qeueues - * to be private to one cpu by setting the affinity hint - * to eliminate the contention. - */ - if ((vscsi->num_queues == 1 || - vscsi->num_queues != num_online_cpus()) && affinity) { - if (vscsi->affinity_hint_set) - affinity = false; - else - return; - } - - if (affinity) { - i = 0; - for_each_online_cpu(cpu) { - virtqueue_set_affinity(vscsi->req_vqs[i].vq, cpu); - i++; - } - - vscsi->affinity_hint_set = true; - } else { - for (i = 0; i < vscsi->num_queues; i++) { - if (!vscsi->req_vqs[i].vq) - continue; - - virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1); - } - - vscsi->affinity_hint_set = false; - } -} - -static void virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity) -{ - get_online_cpus(); - __virtscsi_set_affinity(vscsi, affinity); - put_online_cpus(); -} - -static int virtscsi_cpu_online(unsigned int cpu, struct hlist_node *node) -{ - struct virtio_scsi *vscsi = hlist_entry_safe(node, struct virtio_scsi, - node); - __virtscsi_set_affinity(vscsi, true); - return 0; -} - -static int virtscsi_cpu_notif_add(struct virtio_scsi *vi) -{ - int ret; - - ret = cpuhp_state_add_instance(virtioscsi_online, &vi->node); - if (ret) - return ret; - - ret = cpuhp_state_add_instance(CPUHP_VIRT_SCSI_DEAD, &vi->node_dead); - if (ret) - cpuhp_state_remove_instance(virtioscsi_online, &vi->node); - return ret; -} - -static void virtscsi_cpu_notif_remove(struct virtio_scsi *vi) -{ - cpuhp_state_remove_instance_nocalls(virtioscsi_online, &vi->node); - cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_SCSI_DEAD, - &vi->node_dead); -} - static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq, struct virtqueue *vq) { @@ -900,14 +834,8 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq, static void virtscsi_remove_vqs(struct virtio_device *vdev) { - struct Scsi_Host *sh = virtio_scsi_host(vdev); - struct virtio_scsi *vscsi = shost_priv(sh); - - virtscsi_set_affinity(vscsi, false); - /* Stop all the virtqueues. */ vdev->config->reset(vdev); - vdev->config->del_vqs(vdev); } @@ -920,6 +848,7 @@ static int virtscsi_init(struct virtio_device *vdev, vq_callback_t **callbacks; const char **names; struct virtqueue **vqs; + struct irq_affinity desc = { .pre_vectors = 2 }; num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE; vqs = kmalloc(num_vqs * sizeof(struct virtqueue *), GFP_KERNEL); @@ -941,7 +870,8 @@ static int virtscsi_init(struct virtio_device *vdev, } /* Discover virtqueues and write information to configuration. */ - err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names); + err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names, + &desc); if (err) goto out; @@ -1007,10 +937,6 @@ static int virtscsi_probe(struct virtio_device *vdev) if (err) goto virtscsi_init_failed; - err = virtscsi_cpu_notif_add(vscsi); - if (err) - goto scsi_add_host_failed; - cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1; shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue); shost->max_sectors = virtscsi_config_get(vdev, max_sectors) ?: 0xFFFF; @@ -1065,9 +991,6 @@ static void virtscsi_remove(struct virtio_device *vdev) virtscsi_cancel_event_work(vscsi); scsi_remove_host(shost); - - virtscsi_cpu_notif_remove(vscsi); - virtscsi_remove_vqs(vdev); scsi_host_put(shost); } @@ -1075,10 +998,6 @@ static void virtscsi_remove(struct virtio_device *vdev) #ifdef CONFIG_PM_SLEEP static int virtscsi_freeze(struct virtio_device *vdev) { - struct Scsi_Host *sh = virtio_scsi_host(vdev); - struct virtio_scsi *vscsi = shost_priv(sh); - - virtscsi_cpu_notif_remove(vscsi); virtscsi_remove_vqs(vdev); return 0; } @@ -1093,11 +1012,6 @@ static int virtscsi_restore(struct virtio_device *vdev) if (err) return err; - err = virtscsi_cpu_notif_add(vscsi); - if (err) { - vdev->config->del_vqs(vdev); - return err; - } virtio_device_ready(vdev); if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG)) @@ -1152,16 +1066,6 @@ static int __init init(void) pr_err("mempool_create() for virtscsi_cmd_pool failed\n"); goto error; } - ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, - "scsi/virtio:online", - virtscsi_cpu_online, NULL); - if (ret < 0) - goto error; - virtioscsi_online = ret; - ret = cpuhp_setup_state_multi(CPUHP_VIRT_SCSI_DEAD, "scsi/virtio:dead", - NULL, virtscsi_cpu_online); - if (ret) - goto error; ret = register_virtio_driver(&virtio_scsi_driver); if (ret < 0) goto error; @@ -1177,17 +1081,12 @@ error: kmem_cache_destroy(virtscsi_cmd_cache); virtscsi_cmd_cache = NULL; } - if (virtioscsi_online) - cpuhp_remove_multi_state(virtioscsi_online); - cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD); return ret; } static void __exit fini(void) { unregister_virtio_driver(&virtio_scsi_driver); - cpuhp_remove_multi_state(virtioscsi_online); - cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 2fb1bf1a26c5..37a05185dcbe 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -872,7 +872,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip, goto out; csk->mtu = ndev->mtu; csk->tx_chan = cxgb4_port_chan(ndev); - csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1; + csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type, + cxgb4_port_viid(ndev)); step = cdev->lldi.ntxq / cdev->lldi.nchan; csk->txq_idx = cxgb4_port_idx(ndev) * step; @@ -907,7 +908,8 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip, port_id = cxgb4_port_idx(ndev); csk->mtu = dst_mtu(dst); csk->tx_chan = cxgb4_port_chan(ndev); - csk->smac_idx = (cxgb4_port_viid(ndev) & 0x7F) << 1; + csk->smac_idx = cxgb4_tp_smt_idx(cdev->lldi.adapter_type, + cxgb4_port_viid(ndev)); step = cdev->lldi.ntxq / cdev->lldi.nports; csk->txq_idx = (port_id * step) + @@ -1066,6 +1068,7 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) struct sk_buff *skb; const struct tcphdr *tcph; struct cpl_t5_pass_accept_rpl *rpl5; + struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi; unsigned int len = roundup(sizeof(*rpl5), 16); unsigned int mtu_idx; u64 opt0; @@ -1111,6 +1114,9 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) opt2 = RX_CHANNEL_V(0) | RSS_QUEUE_VALID_F | RSS_QUEUE_V(csk->rss_qid); + if (!is_t5(lldi->adapter_type)) + opt2 |= RX_FC_DISABLE_F; + if (req->tcpopt.tstamp) opt2 |= TSTAMPS_EN_F; if (req->tcpopt.sack) @@ -1119,8 +1125,13 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) opt2 |= WND_SCALE_EN_F; hlen = ntohl(req->hdr_len); - tcph = (const void *)(req + 1) + ETH_HDR_LEN_G(hlen) + - IP_HDR_LEN_G(hlen); + + if (is_t5(lldi->adapter_type)) + tcph = (struct tcphdr *)((u8 *)(req + 1) + + ETH_HDR_LEN_G(hlen) + IP_HDR_LEN_G(hlen)); + else + tcph = (struct tcphdr *)((u8 *)(req + 1) + + T6_ETH_HDR_LEN_G(hlen) + T6_IP_HDR_LEN_G(hlen)); if (tcph->ece && tcph->cwr) opt2 |= CCTRL_ECN_V(1); @@ -1726,7 +1737,7 @@ static bool cxgbit_credit_err(const struct cxgbit_sock *csk) } while (skb) { - credit += skb->csum; + credit += (__force u32)skb->csum; skb = cxgbit_skcb_tx_wr_next(skb); } @@ -1753,6 +1764,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb) while (credits) { struct sk_buff *p = cxgbit_sock_peek_wr(csk); + const u32 csum = (__force u32)p->csum; if (unlikely(!p)) { pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n", @@ -1761,17 +1773,17 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb) break; } - if (unlikely(credits < p->csum)) { + if (unlikely(credits < csum)) { pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n", csk, csk->tid, credits, csk->wr_cred, csk->wr_una_cred, - p->csum); - p->csum -= credits; + csum); + p->csum = (__force __wsum)(csum - credits); break; } cxgbit_sock_dequeue_wr(csk); - credits -= p->csum; + credits -= csum; kfree_skb(p); } diff --git a/drivers/target/iscsi/cxgbit/cxgbit_lro.h b/drivers/target/iscsi/cxgbit/cxgbit_lro.h index 28c11bd1b930..dcaed3a1d23f 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_lro.h +++ b/drivers/target/iscsi/cxgbit/cxgbit_lro.h @@ -31,8 +31,9 @@ enum cxgbit_pducb_flags { PDUCBF_RX_DATA = (1 << 1), /* received pdu payload */ PDUCBF_RX_STATUS = (1 << 2), /* received ddp status */ PDUCBF_RX_DATA_DDPD = (1 << 3), /* pdu payload ddp'd */ - PDUCBF_RX_HCRC_ERR = (1 << 4), /* header digest error */ - PDUCBF_RX_DCRC_ERR = (1 << 5), /* data digest error */ + PDUCBF_RX_DDP_CMP = (1 << 4), /* ddp completion */ + PDUCBF_RX_HCRC_ERR = (1 << 5), /* header digest error */ + PDUCBF_RX_DCRC_ERR = (1 << 6), /* data digest error */ }; struct cxgbit_lro_pdu_cb { diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index 96eedfc49c94..4fd775ace541 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -165,29 +165,24 @@ static int cxgbit_uld_state_change(void *handle, enum cxgb4_state state) } static void -cxgbit_proc_ddp_status(unsigned int tid, struct cpl_rx_data_ddp *cpl, - struct cxgbit_lro_pdu_cb *pdu_cb) +cxgbit_process_ddpvld(struct cxgbit_sock *csk, struct cxgbit_lro_pdu_cb *pdu_cb, + u32 ddpvld) { - unsigned int status = ntohl(cpl->ddpvld); - pdu_cb->flags |= PDUCBF_RX_STATUS; - pdu_cb->ddigest = ntohl(cpl->ulp_crc); - pdu_cb->pdulen = ntohs(cpl->len); - - if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) { - pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", tid, status); + if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_HCRC_SHIFT)) { + pr_info("tid 0x%x, status 0x%x, hcrc bad.\n", csk->tid, ddpvld); pdu_cb->flags |= PDUCBF_RX_HCRC_ERR; } - if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) { - pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", tid, status); + if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_DCRC_SHIFT)) { + pr_info("tid 0x%x, status 0x%x, dcrc bad.\n", csk->tid, ddpvld); pdu_cb->flags |= PDUCBF_RX_DCRC_ERR; } - if (status & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT)) - pr_info("tid 0x%x, status 0x%x, pad bad.\n", tid, status); + if (ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_PAD_SHIFT)) + pr_info("tid 0x%x, status 0x%x, pad bad.\n", csk->tid, ddpvld); - if ((status & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) && + if ((ddpvld & (1 << CPL_RX_ISCSI_DDP_STATUS_DDP_SHIFT)) && (!(pdu_cb->flags & PDUCBF_RX_DATA))) { pdu_cb->flags |= PDUCBF_RX_DATA_DDPD; } @@ -201,13 +196,17 @@ cxgbit_lro_add_packet_rsp(struct sk_buff *skb, u8 op, const __be64 *rsp) lro_cb->pdu_idx); struct cpl_rx_iscsi_ddp *cpl = (struct cpl_rx_iscsi_ddp *)(rsp + 1); - cxgbit_proc_ddp_status(lro_cb->csk->tid, cpl, pdu_cb); + cxgbit_process_ddpvld(lro_cb->csk, pdu_cb, be32_to_cpu(cpl->ddpvld)); + + pdu_cb->flags |= PDUCBF_RX_STATUS; + pdu_cb->ddigest = ntohl(cpl->ulp_crc); + pdu_cb->pdulen = ntohs(cpl->len); if (pdu_cb->flags & PDUCBF_RX_HDR) pdu_cb->complete = true; - lro_cb->complete = true; lro_cb->pdu_totallen += pdu_cb->pdulen; + lro_cb->complete = true; lro_cb->pdu_idx++; } @@ -257,7 +256,7 @@ cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl) cxgbit_skcb_flags(skb) = 0; lro_cb->complete = false; - } else { + } else if (op == CPL_ISCSI_DATA) { struct cpl_iscsi_data *cpl = (struct cpl_iscsi_data *)gl->va; offset = sizeof(struct cpl_iscsi_data); @@ -267,6 +266,36 @@ cxgbit_lro_add_packet_gl(struct sk_buff *skb, u8 op, const struct pkt_gl *gl) pdu_cb->doffset = lro_cb->offset; pdu_cb->nr_dfrags = gl->nfrags; pdu_cb->dfrag_idx = skb_shinfo(skb)->nr_frags; + lro_cb->complete = false; + } else { + struct cpl_rx_iscsi_cmp *cpl; + + cpl = (struct cpl_rx_iscsi_cmp *)gl->va; + offset = sizeof(struct cpl_rx_iscsi_cmp); + pdu_cb->flags |= (PDUCBF_RX_HDR | PDUCBF_RX_STATUS); + len = be16_to_cpu(cpl->len); + pdu_cb->hdr = gl->va + offset; + pdu_cb->hlen = len; + pdu_cb->hfrag_idx = skb_shinfo(skb)->nr_frags; + pdu_cb->ddigest = be32_to_cpu(cpl->ulp_crc); + pdu_cb->pdulen = ntohs(cpl->len); + + if (unlikely(gl->nfrags > 1)) + cxgbit_skcb_flags(skb) = 0; + + cxgbit_process_ddpvld(lro_cb->csk, pdu_cb, + be32_to_cpu(cpl->ddpvld)); + + if (pdu_cb->flags & PDUCBF_RX_DATA_DDPD) { + pdu_cb->flags |= PDUCBF_RX_DDP_CMP; + pdu_cb->complete = true; + } else if (pdu_cb->flags & PDUCBF_RX_DATA) { + pdu_cb->complete = true; + } + + lro_cb->pdu_totallen += pdu_cb->hlen + pdu_cb->dlen; + lro_cb->complete = true; + lro_cb->pdu_idx++; } cxgbit_copy_frags(skb, gl, offset); @@ -413,6 +442,7 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp, switch (op) { case CPL_ISCSI_HDR: case CPL_ISCSI_DATA: + case CPL_RX_ISCSI_CMP: case CPL_RX_ISCSI_DDP: case CPL_FW4_ACK: lro_flush = false; @@ -454,12 +484,13 @@ cxgbit_uld_lro_rx_handler(void *hndl, const __be64 *rsp, if (unlikely(op != *(u8 *)gl->va)) { pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n", gl->va, be64_to_cpu(*rsp), - be64_to_cpu(*(u64 *)gl->va), + get_unaligned_be64(gl->va), gl->tot_len); return 0; } - if (op == CPL_ISCSI_HDR || op == CPL_ISCSI_DATA) { + if ((op == CPL_ISCSI_HDR) || (op == CPL_ISCSI_DATA) || + (op == CPL_RX_ISCSI_CMP)) { if (!cxgbit_lro_receive(csk, op, rsp, gl, lro_mgr, napi)) return 0; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 0c3e8fce3695..bdcc8b4c522a 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -164,12 +164,14 @@ cxgbit_tx_data_wr(struct cxgbit_sock *csk, struct sk_buff *skb, u32 dlen, u32 len, u32 credits, u32 compl) { struct fw_ofld_tx_data_wr *req; + const struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi; u32 submode = cxgbit_skcb_submode(skb); u32 wr_ulp_mode = 0; u32 hdr_size = sizeof(*req); u32 opcode = FW_OFLD_TX_DATA_WR; u32 immlen = 0; - u32 force = TX_FORCE_V(!submode); + u32 force = is_t5(lldi->adapter_type) ? TX_FORCE_V(!submode) : + T6_TX_FORCE_F; if (cxgbit_skcb_flags(skb) & SKCBF_TX_ISO) { opcode = FW_ISCSI_TX_DATA_WR; @@ -245,7 +247,7 @@ void cxgbit_push_tx_frames(struct cxgbit_sock *csk) } __skb_unlink(skb, &csk->txq); set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx); - skb->csum = credits_needed + flowclen16; + skb->csum = (__force __wsum)(credits_needed + flowclen16); csk->wr_cred -= credits_needed; csk->wr_una_cred += credits_needed; @@ -653,26 +655,6 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) u32 max_npdu, max_iso_npdu; if (conn->login->leading_connection) { - param = iscsi_find_param_from_key(DATASEQUENCEINORDER, - conn->param_list); - if (!param) { - pr_err("param not found key %s\n", DATASEQUENCEINORDER); - return -1; - } - - if (strcmp(param->value, YES)) - return 0; - - param = iscsi_find_param_from_key(DATAPDUINORDER, - conn->param_list); - if (!param) { - pr_err("param not found key %s\n", DATAPDUINORDER); - return -1; - } - - if (strcmp(param->value, YES)) - return 0; - param = iscsi_find_param_from_key(MAXBURSTLENGTH, conn->param_list); if (!param) { @@ -683,11 +665,6 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) if (kstrtou32(param->value, 0, &mbl) < 0) return -1; } else { - if (!conn->sess->sess_ops->DataSequenceInOrder) - return 0; - if (!conn->sess->sess_ops->DataPDUInOrder) - return 0; - mbl = conn->sess->sess_ops->MaxBurstLength; } @@ -706,6 +683,53 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) return 0; } +/* + * cxgbit_seq_pdu_inorder() + * @csk: pointer to cxgbit socket structure + * + * This function checks whether data sequence and data + * pdu are in order. + * + * Return: returns -1 on error, 0 if data sequence and + * data pdu are in order, 1 if data sequence or data pdu + * is not in order. + */ +static int cxgbit_seq_pdu_inorder(struct cxgbit_sock *csk) +{ + struct iscsi_conn *conn = csk->conn; + struct iscsi_param *param; + + if (conn->login->leading_connection) { + param = iscsi_find_param_from_key(DATASEQUENCEINORDER, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", DATASEQUENCEINORDER); + return -1; + } + + if (strcmp(param->value, YES)) + return 1; + + param = iscsi_find_param_from_key(DATAPDUINORDER, + conn->param_list); + if (!param) { + pr_err("param not found key %s\n", DATAPDUINORDER); + return -1; + } + + if (strcmp(param->value, YES)) + return 1; + + } else { + if (!conn->sess->sess_ops->DataSequenceInOrder) + return 1; + if (!conn->sess->sess_ops->DataPDUInOrder) + return 1; + } + + return 0; +} + static int cxgbit_set_params(struct iscsi_conn *conn) { struct cxgbit_sock *csk = conn->context; @@ -732,11 +756,24 @@ static int cxgbit_set_params(struct iscsi_conn *conn) } if (!erl) { + int ret; + + ret = cxgbit_seq_pdu_inorder(csk); + if (ret < 0) { + return -1; + } else if (ret > 0) { + if (is_t5(cdev->lldi.adapter_type)) + goto enable_ddp; + else + goto enable_digest; + } + if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) { if (cxgbit_set_iso_npdu(csk)) return -1; } +enable_ddp: if (test_bit(CDEV_DDP_ENABLE, &cdev->flags)) { if (cxgbit_setup_conn_pgidx(csk, ppm->tformat.pgsz_idx_dflt)) @@ -745,6 +782,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn) } } +enable_digest: if (cxgbit_set_digest(csk)) return -1; @@ -985,11 +1023,36 @@ static int cxgbit_handle_iscsi_dataout(struct cxgbit_sock *csk) int rc, sg_nents, sg_off; bool dcrc_err = false; - rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd); - if (rc < 0) - return rc; - else if (!cmd) - return 0; + if (pdu_cb->flags & PDUCBF_RX_DDP_CMP) { + u32 offset = be32_to_cpu(hdr->offset); + u32 ddp_data_len; + u32 payload_length = ntoh24(hdr->dlength); + bool success = false; + + cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt, 0); + if (!cmd) + return 0; + + ddp_data_len = offset - cmd->write_data_done; + atomic_long_add(ddp_data_len, &conn->sess->rx_data_octets); + + cmd->write_data_done = offset; + cmd->next_burst_len = ddp_data_len; + cmd->data_sn = be32_to_cpu(hdr->datasn); + + rc = __iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, + cmd, payload_length, &success); + if (rc < 0) + return rc; + else if (!success) + return 0; + } else { + rc = iscsit_check_dataout_hdr(conn, (unsigned char *)hdr, &cmd); + if (rc < 0) + return rc; + else if (!cmd) + return 0; + } if (pdu_cb->flags & PDUCBF_RX_DCRC_ERR) { pr_err("ITT: 0x%08x, Offset: %u, Length: %u," @@ -1353,6 +1416,9 @@ static void cxgbit_lro_hskb_reset(struct cxgbit_sock *csk) for (i = 0; i < ssi->nr_frags; i++) put_page(skb_frag_page(&ssi->frags[i])); ssi->nr_frags = 0; + skb->data_len = 0; + skb->truesize -= skb->len; + skb->len = 0; } static void @@ -1366,39 +1432,42 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx) unsigned int len = 0; if (pdu_cb->flags & PDUCBF_RX_HDR) { - hpdu_cb->flags = pdu_cb->flags; + u8 hfrag_idx = hssi->nr_frags; + + hpdu_cb->flags |= pdu_cb->flags; hpdu_cb->seq = pdu_cb->seq; hpdu_cb->hdr = pdu_cb->hdr; hpdu_cb->hlen = pdu_cb->hlen; - memcpy(&hssi->frags[0], &ssi->frags[pdu_cb->hfrag_idx], + memcpy(&hssi->frags[hfrag_idx], &ssi->frags[pdu_cb->hfrag_idx], sizeof(skb_frag_t)); - get_page(skb_frag_page(&hssi->frags[0])); - hssi->nr_frags = 1; - hpdu_cb->frags = 1; - hpdu_cb->hfrag_idx = 0; + get_page(skb_frag_page(&hssi->frags[hfrag_idx])); + hssi->nr_frags++; + hpdu_cb->frags++; + hpdu_cb->hfrag_idx = hfrag_idx; - len = hssi->frags[0].size; - hskb->len = len; - hskb->data_len = len; - hskb->truesize = len; + len = hssi->frags[hfrag_idx].size; + hskb->len += len; + hskb->data_len += len; + hskb->truesize += len; } if (pdu_cb->flags & PDUCBF_RX_DATA) { - u8 hfrag_idx = 1, i; + u8 dfrag_idx = hssi->nr_frags, i; hpdu_cb->flags |= pdu_cb->flags; + hpdu_cb->dfrag_idx = dfrag_idx; len = 0; - for (i = 0; i < pdu_cb->nr_dfrags; hfrag_idx++, i++) { - memcpy(&hssi->frags[hfrag_idx], + for (i = 0; i < pdu_cb->nr_dfrags; dfrag_idx++, i++) { + memcpy(&hssi->frags[dfrag_idx], &ssi->frags[pdu_cb->dfrag_idx + i], sizeof(skb_frag_t)); - get_page(skb_frag_page(&hssi->frags[hfrag_idx])); + get_page(skb_frag_page(&hssi->frags[dfrag_idx])); - len += hssi->frags[hfrag_idx].size; + len += hssi->frags[dfrag_idx].size; hssi->nr_frags++; hpdu_cb->frags++; @@ -1407,7 +1476,6 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx) hpdu_cb->dlen = pdu_cb->dlen; hpdu_cb->doffset = hpdu_cb->hlen; hpdu_cb->nr_dfrags = pdu_cb->nr_dfrags; - hpdu_cb->dfrag_idx = 1; hskb->len += len; hskb->data_len += len; hskb->truesize += len; @@ -1492,10 +1560,15 @@ static int cxgbit_rx_lro_skb(struct cxgbit_sock *csk, struct sk_buff *skb) static int cxgbit_rx_skb(struct cxgbit_sock *csk, struct sk_buff *skb) { + struct cxgb4_lld_info *lldi = &csk->com.cdev->lldi; int ret = -1; - if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO)) - ret = cxgbit_rx_lro_skb(csk, skb); + if (likely(cxgbit_skcb_flags(skb) & SKCBF_RX_LRO)) { + if (is_t5(lldi->adapter_type)) + ret = cxgbit_rx_lro_skb(csk, skb); + else + ret = cxgbit_process_lro_skb(csk, skb); + } __kfree_skb(skb); return ret; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index fa1d578d56bd..a91802432f2f 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1432,36 +1432,17 @@ static void iscsit_do_crypto_hash_buf( } int -iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf, - struct iscsi_cmd **out_cmd) +__iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, + struct iscsi_cmd *cmd, u32 payload_length, + bool *success) { - struct iscsi_data *hdr = (struct iscsi_data *)buf; - struct iscsi_cmd *cmd = NULL; + struct iscsi_data *hdr = buf; struct se_cmd *se_cmd; - u32 payload_length = ntoh24(hdr->dlength); int rc; - if (!payload_length) { - pr_warn("DataOUT payload is ZERO, ignoring.\n"); - return 0; - } - /* iSCSI write */ atomic_long_add(payload_length, &conn->sess->rx_data_octets); - if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) { - pr_err("DataSegmentLength: %u is greater than" - " MaxXmitDataSegmentLength: %u\n", payload_length, - conn->conn_ops->MaxXmitDataSegmentLength); - return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, - buf); - } - - cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt, - payload_length); - if (!cmd) - return 0; - pr_debug("Got DataOut ITT: 0x%08x, TTT: 0x%08x," " DataSN: 0x%08x, Offset: %u, Length: %u, CID: %hu\n", hdr->itt, hdr->ttt, hdr->datasn, ntohl(hdr->offset), @@ -1546,7 +1527,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf, } } /* - * Preform DataSN, DataSequenceInOrder, DataPDUInOrder, and + * Perform DataSN, DataSequenceInOrder, DataPDUInOrder, and * within-command recovery checks before receiving the payload. */ rc = iscsit_check_pre_dataout(cmd, buf); @@ -1554,10 +1535,44 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf, return 0; else if (rc == DATAOUT_CANNOT_RECOVER) return -1; - - *out_cmd = cmd; + *success = true; return 0; } +EXPORT_SYMBOL(__iscsit_check_dataout_hdr); + +int +iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, + struct iscsi_cmd **out_cmd) +{ + struct iscsi_data *hdr = buf; + struct iscsi_cmd *cmd; + u32 payload_length = ntoh24(hdr->dlength); + int rc; + bool success = false; + + if (!payload_length) { + pr_warn_ratelimited("DataOUT payload is ZERO, ignoring.\n"); + return 0; + } + + if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) { + pr_err_ratelimited("DataSegmentLength: %u is greater than" + " MaxXmitDataSegmentLength: %u\n", payload_length, + conn->conn_ops->MaxXmitDataSegmentLength); + return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, buf); + } + + cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt, payload_length); + if (!cmd) + return 0; + + rc = __iscsit_check_dataout_hdr(conn, buf, cmd, payload_length, &success); + + if (success) + *out_cmd = cmd; + + return rc; +} EXPORT_SYMBOL(iscsit_check_dataout_hdr); static int @@ -1921,6 +1936,28 @@ out: return ret; } +static enum tcm_tmreq_table iscsit_convert_tmf(u8 iscsi_tmf) +{ + switch (iscsi_tmf) { + case ISCSI_TM_FUNC_ABORT_TASK: + return TMR_ABORT_TASK; + case ISCSI_TM_FUNC_ABORT_TASK_SET: + return TMR_ABORT_TASK_SET; + case ISCSI_TM_FUNC_CLEAR_ACA: + return TMR_CLEAR_ACA; + case ISCSI_TM_FUNC_CLEAR_TASK_SET: + return TMR_CLEAR_TASK_SET; + case ISCSI_TM_FUNC_LOGICAL_UNIT_RESET: + return TMR_LUN_RESET; + case ISCSI_TM_FUNC_TARGET_WARM_RESET: + return TMR_TARGET_WARM_RESET; + case ISCSI_TM_FUNC_TARGET_COLD_RESET: + return TMR_TARGET_COLD_RESET; + default: + return TMR_UNKNOWN; + } +} + int iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, unsigned char *buf) @@ -1930,7 +1967,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct iscsi_tm *hdr; int out_of_order_cmdsn = 0, ret; bool sess_ref = false; - u8 function; + u8 function, tcm_function = TMR_UNKNOWN; hdr = (struct iscsi_tm *) buf; hdr->flags &= ~ISCSI_FLAG_CMD_FINAL; @@ -1976,54 +2013,27 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * LIO-Target $FABRIC_MOD */ if (function != ISCSI_TM_FUNC_TASK_REASSIGN) { - - u8 tcm_function; - int ret; - transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); target_get_sess_cmd(&cmd->se_cmd, true); sess_ref = true; - - switch (function) { - case ISCSI_TM_FUNC_ABORT_TASK: - tcm_function = TMR_ABORT_TASK; - break; - case ISCSI_TM_FUNC_ABORT_TASK_SET: - tcm_function = TMR_ABORT_TASK_SET; - break; - case ISCSI_TM_FUNC_CLEAR_ACA: - tcm_function = TMR_CLEAR_ACA; - break; - case ISCSI_TM_FUNC_CLEAR_TASK_SET: - tcm_function = TMR_CLEAR_TASK_SET; - break; - case ISCSI_TM_FUNC_LOGICAL_UNIT_RESET: - tcm_function = TMR_LUN_RESET; - break; - case ISCSI_TM_FUNC_TARGET_WARM_RESET: - tcm_function = TMR_TARGET_WARM_RESET; - break; - case ISCSI_TM_FUNC_TARGET_COLD_RESET: - tcm_function = TMR_TARGET_COLD_RESET; - break; - default: + tcm_function = iscsit_convert_tmf(function); + if (tcm_function == TMR_UNKNOWN) { pr_err("Unknown iSCSI TMR Function:" " 0x%02x\n", function); return iscsit_add_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); } - - ret = core_tmr_alloc_req(&cmd->se_cmd, cmd->tmr_req, - tcm_function, GFP_KERNEL); - if (ret < 0) - return iscsit_add_reject_cmd(cmd, + } + ret = core_tmr_alloc_req(&cmd->se_cmd, cmd->tmr_req, tcm_function, + GFP_KERNEL); + if (ret < 0) + return iscsit_add_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf); - cmd->tmr_req->se_tmr_req = cmd->se_cmd.se_tmr_req; - } + cmd->tmr_req->se_tmr_req = cmd->se_cmd.se_tmr_req; cmd->iscsi_opcode = ISCSI_OP_SCSI_TMFUNC; cmd->i_state = ISTATE_SEND_TASKMGTRSP; @@ -4137,7 +4147,7 @@ int iscsit_close_connection( /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands - * for realligence. + * for reallegiance. * * During normal operation clear the out of order commands (but * do not free the struct iscsi_ooo_cmdsn's) and release all @@ -4145,7 +4155,7 @@ int iscsit_close_connection( */ if (atomic_read(&conn->connection_recovery)) { iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(conn); - iscsit_prepare_cmds_for_realligance(conn); + iscsit_prepare_cmds_for_reallegiance(conn); } else { iscsit_clear_ooo_cmdsns_for_conn(conn); iscsit_release_commands_from_conn(conn); diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c index a4d5e6749932..9a96e17bf7cd 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.c +++ b/drivers/target/iscsi/iscsi_target_erl0.c @@ -46,10 +46,8 @@ void iscsit_set_dataout_sequence_values( */ if (cmd->unsolicited_data) { cmd->seq_start_offset = cmd->write_data_done; - cmd->seq_end_offset = (cmd->write_data_done + - ((cmd->se_cmd.data_length > - conn->sess->sess_ops->FirstBurstLength) ? - conn->sess->sess_ops->FirstBurstLength : cmd->se_cmd.data_length)); + cmd->seq_end_offset = min(cmd->se_cmd.data_length, + conn->sess->sess_ops->FirstBurstLength); return; } diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c index faf9ae014b30..8df9c90f3db3 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.c +++ b/drivers/target/iscsi/iscsi_target_erl2.c @@ -312,7 +312,7 @@ int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *conn) return 0; } -int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) +int iscsit_prepare_cmds_for_reallegiance(struct iscsi_conn *conn) { u32 cmd_count = 0; struct iscsi_cmd *cmd, *cmd_tmp; @@ -347,7 +347,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) if ((cmd->iscsi_opcode != ISCSI_OP_SCSI_CMD) && (cmd->iscsi_opcode != ISCSI_OP_NOOP_OUT)) { - pr_debug("Not performing realligence on" + pr_debug("Not performing reallegiance on" " Opcode: 0x%02x, ITT: 0x%08x, CmdSN: 0x%08x," " CID: %hu\n", cmd->iscsi_opcode, cmd->init_task_tag, cmd->cmd_sn, conn->cid); @@ -382,7 +382,7 @@ int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *conn) cmd_count++; pr_debug("Preparing Opcode: 0x%02x, ITT: 0x%08x," " CmdSN: 0x%08x, StatSN: 0x%08x, CID: %hu for" - " realligence.\n", cmd->iscsi_opcode, + " reallegiance.\n", cmd->iscsi_opcode, cmd->init_task_tag, cmd->cmd_sn, cmd->stat_sn, conn->cid); diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h index 7965f1e86506..634d01e13652 100644 --- a/drivers/target/iscsi/iscsi_target_erl2.h +++ b/drivers/target/iscsi/iscsi_target_erl2.h @@ -19,7 +19,7 @@ extern int iscsit_remove_cmd_from_connection_recovery(struct iscsi_cmd *, struct iscsi_session *); extern void iscsit_discard_cr_cmds_by_expstatsn(struct iscsi_conn_recovery *, u32); extern int iscsit_discard_unacknowledged_ooo_cmdsns_for_conn(struct iscsi_conn *); -extern int iscsit_prepare_cmds_for_realligance(struct iscsi_conn *); +extern int iscsit_prepare_cmds_for_reallegiance(struct iscsi_conn *); extern int iscsit_connection_recovery_transport_reset(struct iscsi_conn *); #endif /*** ISCSI_TARGET_ERL2_H ***/ diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index b03cc03423c1..ad8f3011bdc2 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -224,7 +224,7 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn) return 0; pr_debug("%s iSCSI Session SID %u is still active for %s," - " preforming session reinstatement.\n", (sessiontype) ? + " performing session reinstatement.\n", (sessiontype) ? "Discovery" : "Normal", sess->sid, sess->sess_ops->InitiatorName); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 29eb09e0cd15..7ccc9c1cbfd1 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -1250,16 +1250,16 @@ int iscsi_target_start_negotiation( { int ret; - if (conn->sock) { - struct sock *sk = conn->sock->sk; + if (conn->sock) { + struct sock *sk = conn->sock->sk; - write_lock_bh(&sk->sk_callback_lock); - set_bit(LOGIN_FLAGS_READY, &conn->login_flags); - write_unlock_bh(&sk->sk_callback_lock); - } + write_lock_bh(&sk->sk_callback_lock); + set_bit(LOGIN_FLAGS_READY, &conn->login_flags); + write_unlock_bh(&sk->sk_callback_lock); + } - ret = iscsi_target_do_login(conn, login); - if (ret < 0) { + ret = iscsi_target_do_login(conn, login); + if (ret < 0) { cancel_delayed_work_sync(&conn->login_work); cancel_delayed_work_sync(&conn->login_cleanup_work); iscsi_target_restore_sock_callbacks(conn); diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c index 3d637055c36f..cb231c907d51 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.c +++ b/drivers/target/iscsi/iscsi_target_tmr.c @@ -440,14 +440,14 @@ static int iscsit_task_reassign_complete( break; default: pr_err("Illegal iSCSI Opcode 0x%02x during" - " command realligence\n", cmd->iscsi_opcode); + " command reallegiance\n", cmd->iscsi_opcode); return -1; } if (ret != 0) return ret; - pr_debug("Completed connection realligence for Opcode: 0x%02x," + pr_debug("Completed connection reallegiance for Opcode: 0x%02x," " ITT: 0x%08x to CID: %hu.\n", cmd->iscsi_opcode, cmd->init_task_tag, conn->cid); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index b5a1b4ccba12..5041a9c8bdcb 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -417,6 +417,7 @@ struct iscsi_cmd *iscsit_find_cmd_from_itt_or_dump( return NULL; } +EXPORT_SYMBOL(iscsit_find_cmd_from_itt_or_dump); struct iscsi_cmd *iscsit_find_cmd_from_ttt( struct iscsi_conn *conn, @@ -1304,39 +1305,6 @@ static int iscsit_do_rx_data( return total_rx; } -static int iscsit_do_tx_data( - struct iscsi_conn *conn, - struct iscsi_data_count *count) -{ - int ret, iov_len; - struct kvec *iov_p; - struct msghdr msg; - - if (!conn || !conn->sock || !conn->conn_ops) - return -1; - - if (count->data_length <= 0) { - pr_err("Data length is: %d\n", count->data_length); - return -1; - } - - memset(&msg, 0, sizeof(struct msghdr)); - - iov_p = count->iov; - iov_len = count->iov_count; - - ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len, - count->data_length); - if (ret != count->data_length) { - pr_err("Unexpected ret: %d send data %d\n", - ret, count->data_length); - return -EPIPE; - } - pr_debug("ret: %d, sent data: %d\n", ret, count->data_length); - - return ret; -} - int rx_data( struct iscsi_conn *conn, struct kvec *iov, @@ -1363,45 +1331,35 @@ int tx_data( int iov_count, int data) { - struct iscsi_data_count c; + struct msghdr msg; + int total_tx = 0; if (!conn || !conn->sock || !conn->conn_ops) return -1; - memset(&c, 0, sizeof(struct iscsi_data_count)); - c.iov = iov; - c.iov_count = iov_count; - c.data_length = data; - c.type = ISCSI_TX_DATA; + if (data <= 0) { + pr_err("Data length is: %d\n", data); + return -1; + } - return iscsit_do_tx_data(conn, &c); -} + memset(&msg, 0, sizeof(struct msghdr)); -static bool sockaddr_equal(struct sockaddr_storage *x, struct sockaddr_storage *y) -{ - switch (x->ss_family) { - case AF_INET: { - struct sockaddr_in *sinx = (struct sockaddr_in *)x; - struct sockaddr_in *siny = (struct sockaddr_in *)y; - if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr) - return false; - if (sinx->sin_port != siny->sin_port) - return false; - break; - } - case AF_INET6: { - struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x; - struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y; - if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr)) - return false; - if (sinx->sin6_port != siny->sin6_port) - return false; - break; - } - default: - return false; + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, + iov, iov_count, data); + + while (msg_data_left(&msg)) { + int tx_loop = sock_sendmsg(conn->sock, &msg); + if (tx_loop <= 0) { + pr_debug("tx_loop: %d total_tx %d\n", + tx_loop, total_tx); + return tx_loop; + } + total_tx += tx_loop; + pr_debug("tx_loop: %d, total_tx: %d, data: %d\n", + tx_loop, total_tx, data); } - return true; + + return total_tx; } void iscsit_collect_login_stats( @@ -1420,13 +1378,6 @@ void iscsit_collect_login_stats( ls = &tiqn->login_stats; spin_lock(&ls->lock); - if (sockaddr_equal(&conn->login_sockaddr, &ls->last_intr_fail_sockaddr) && - ((get_jiffies_64() - ls->last_fail_time) < 10)) { - /* We already have the failure info for this login */ - spin_unlock(&ls->lock); - return; - } - if (status_class == ISCSI_STATUS_CLS_SUCCESS) ls->accepts++; else if (status_class == ISCSI_STATUS_CLS_REDIRECT) { @@ -1471,10 +1422,10 @@ struct iscsi_tiqn *iscsit_snmp_get_tiqn(struct iscsi_conn *conn) { struct iscsi_portal_group *tpg; - if (!conn || !conn->sess) + if (!conn) return NULL; - tpg = conn->sess->tpg; + tpg = conn->tpg; if (!tpg) return NULL; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 26929c44d703..c754ae33bf7b 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -78,12 +78,16 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) &deve->read_bytes); se_lun = rcu_dereference(deve->se_lun); + + if (!percpu_ref_tryget_live(&se_lun->lun_ref)) { + se_lun = NULL; + goto out_unlock; + } + se_cmd->se_lun = rcu_dereference(deve->se_lun); se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD; - - percpu_ref_get(&se_lun->lun_ref); se_cmd->lun_ref_active = true; if ((se_cmd->data_direction == DMA_TO_DEVICE) && @@ -97,6 +101,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun) goto ref_dev; } } +out_unlock: rcu_read_unlock(); if (!se_lun) { @@ -163,7 +168,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun) rcu_read_lock(); deve = target_nacl_find_deve(nacl, unpacked_lun); if (deve) { - se_tmr->tmr_lun = rcu_dereference(deve->se_lun); se_cmd->se_lun = rcu_dereference(deve->se_lun); se_lun = rcu_dereference(deve->se_lun); se_cmd->pr_res_key = deve->pr_res_key; @@ -816,6 +820,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) xcopy_lun = &dev->xcopy_lun; rcu_assign_pointer(xcopy_lun->lun_se_dev, dev); init_completion(&xcopy_lun->lun_ref_comp); + init_completion(&xcopy_lun->lun_shutdown_comp); INIT_LIST_HEAD(&xcopy_lun->lun_deve_list); INIT_LIST_HEAD(&xcopy_lun->lun_dev_link); mutex_init(&xcopy_lun->lun_tg_pt_md_mutex); diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index df7b6e95c019..68d8aef7ab78 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -604,7 +604,7 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes spin_lock_irq(&cmd->t_state_lock); cmd->t_state = TRANSPORT_PROCESSING; - cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT; + cmd->transport_state |= CMD_T_ACTIVE | CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); __target_execute_cmd(cmd, false); diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c index 1a39033d2bff..8038255b21e8 100644 --- a/drivers/target/target_core_stat.c +++ b/drivers/target/target_core_stat.c @@ -158,12 +158,28 @@ static ssize_t target_stat_tgt_resets_show(struct config_item *item, atomic_long_read(&to_stat_tgt_dev(item)->num_resets)); } +static ssize_t target_stat_tgt_aborts_complete_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "%lu\n", + atomic_long_read(&to_stat_tgt_dev(item)->aborts_complete)); +} + +static ssize_t target_stat_tgt_aborts_no_task_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "%lu\n", + atomic_long_read(&to_stat_tgt_dev(item)->aborts_no_task)); +} + CONFIGFS_ATTR_RO(target_stat_tgt_, inst); CONFIGFS_ATTR_RO(target_stat_tgt_, indx); CONFIGFS_ATTR_RO(target_stat_tgt_, num_lus); CONFIGFS_ATTR_RO(target_stat_tgt_, status); CONFIGFS_ATTR_RO(target_stat_tgt_, non_access_lus); CONFIGFS_ATTR_RO(target_stat_tgt_, resets); +CONFIGFS_ATTR_RO(target_stat_tgt_, aborts_complete); +CONFIGFS_ATTR_RO(target_stat_tgt_, aborts_no_task); static struct configfs_attribute *target_stat_scsi_tgt_dev_attrs[] = { &target_stat_tgt_attr_inst, @@ -172,6 +188,8 @@ static struct configfs_attribute *target_stat_scsi_tgt_dev_attrs[] = { &target_stat_tgt_attr_status, &target_stat_tgt_attr_non_access_lus, &target_stat_tgt_attr_resets, + &target_stat_tgt_attr_aborts_complete, + &target_stat_tgt_attr_aborts_no_task, NULL, }; @@ -795,16 +813,34 @@ static ssize_t target_stat_transport_dev_name_show(struct config_item *item, return ret; } +static ssize_t target_stat_transport_proto_id_show(struct config_item *item, + char *page) +{ + struct se_lun *lun = to_transport_stat(item); + struct se_device *dev; + struct se_portal_group *tpg = lun->lun_tpg; + ssize_t ret = -ENODEV; + + rcu_read_lock(); + dev = rcu_dereference(lun->lun_se_dev); + if (dev) + ret = snprintf(page, PAGE_SIZE, "%u\n", tpg->proto_id); + rcu_read_unlock(); + return ret; +} + CONFIGFS_ATTR_RO(target_stat_transport_, inst); CONFIGFS_ATTR_RO(target_stat_transport_, device); CONFIGFS_ATTR_RO(target_stat_transport_, indx); CONFIGFS_ATTR_RO(target_stat_transport_, dev_name); +CONFIGFS_ATTR_RO(target_stat_transport_, proto_id); static struct configfs_attribute *target_stat_scsi_transport_attrs[] = { &target_stat_transport_attr_inst, &target_stat_transport_attr_device, &target_stat_transport_attr_indx, &target_stat_transport_attr_dev_name, + &target_stat_transport_attr_proto_id, NULL, }; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 4f229e711e1c..dce1e1b47316 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -175,10 +175,9 @@ void core_tmr_abort_task( printk("ABORT_TASK: Found referenced %s task_tag: %llu\n", se_cmd->se_tfo->get_fabric_name(), ref_tag); - if (!__target_check_io_state(se_cmd, se_sess, 0)) { - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - goto out; - } + if (!__target_check_io_state(se_cmd, se_sess, 0)) + continue; + list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); @@ -191,14 +190,15 @@ void core_tmr_abort_task( printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" " ref_tag: %llu\n", ref_tag); tmr->response = TMR_FUNCTION_COMPLETE; + atomic_long_inc(&dev->aborts_complete); return; } spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); -out: printk("ABORT_TASK: Sending TMR_TASK_DOES_NOT_EXIST for ref_tag: %lld\n", tmr->ref_task_tag); tmr->response = TMR_TASK_DOES_NOT_EXIST; + atomic_long_inc(&dev->aborts_no_task); } static void core_tmr_drain_tmr_list( @@ -217,13 +217,8 @@ static void core_tmr_drain_tmr_list( * LUN_RESET tmr.. */ spin_lock_irqsave(&dev->se_tmr_lock, flags); + list_del_init(&tmr->tmr_list); list_for_each_entry_safe(tmr_p, tmr_pp, &dev->dev_tmr_list, tmr_list) { - /* - * Allow the received TMR to return with FUNCTION_COMPLETE. - */ - if (tmr_p == tmr) - continue; - cmd = tmr_p->task_cmd; if (!cmd) { pr_err("Unable to locate struct se_cmd for TMR\n"); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 4a8b180c478b..c0dbfa016575 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -445,7 +445,7 @@ static void core_tpg_lun_ref_release(struct percpu_ref *ref) { struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); - complete(&lun->lun_ref_comp); + complete(&lun->lun_shutdown_comp); } /* Does not change se_wwn->priv. */ @@ -572,6 +572,7 @@ struct se_lun *core_tpg_alloc_lun( lun->lun_link_magic = SE_LUN_LINK_MAGIC; atomic_set(&lun->lun_acl_count, 0); init_completion(&lun->lun_ref_comp); + init_completion(&lun->lun_shutdown_comp); INIT_LIST_HEAD(&lun->lun_deve_list); INIT_LIST_HEAD(&lun->lun_dev_link); atomic_set(&lun->lun_tg_pt_secondary_offline, 0); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 437591bc7c08..434d9d693989 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -593,9 +593,6 @@ static void target_remove_from_state_list(struct se_cmd *cmd) if (!dev) return; - if (cmd->transport_state & CMD_T_BUSY) - return; - spin_lock_irqsave(&dev->execute_task_lock, flags); if (cmd->state_active) { list_del(&cmd->state_list); @@ -604,24 +601,18 @@ static void target_remove_from_state_list(struct se_cmd *cmd) spin_unlock_irqrestore(&dev->execute_task_lock, flags); } -static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, - bool write_pending) +static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) { unsigned long flags; - if (remove_from_lists) { - target_remove_from_state_list(cmd); + target_remove_from_state_list(cmd); - /* - * Clear struct se_cmd->se_lun before the handoff to FE. - */ - cmd->se_lun = NULL; - } + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; spin_lock_irqsave(&cmd->t_state_lock, flags); - if (write_pending) - cmd->t_state = TRANSPORT_WRITE_PENDING; - /* * Determine if frontend context caller is requesting the stopping of * this command for frontend exceptions. @@ -635,31 +626,18 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, complete_all(&cmd->t_transport_stop_comp); return 1; } - cmd->transport_state &= ~CMD_T_ACTIVE; - if (remove_from_lists) { - /* - * Some fabric modules like tcm_loop can release - * their internally allocated I/O reference now and - * struct se_cmd now. - * - * Fabric modules are expected to return '1' here if the - * se_cmd being passed is released at this point, - * or zero if not being released. - */ - if (cmd->se_tfo->check_stop_free != NULL) { - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - return cmd->se_tfo->check_stop_free(cmd); - } - } - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - return 0; -} -static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) -{ - return transport_cmd_check_stop(cmd, true, false); + /* + * Some fabric modules like tcm_loop can release their internally + * allocated I/O reference and struct se_cmd now. + * + * Fabric modules are expected to return '1' here if the se_cmd being + * passed is released at this point, or zero if not being released. + */ + return cmd->se_tfo->check_stop_free ? cmd->se_tfo->check_stop_free(cmd) + : 0; } static void transport_lun_remove_cmd(struct se_cmd *cmd) @@ -733,7 +711,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->transport_state &= ~CMD_T_BUSY; if (dev && dev->transport->transport_complete) { dev->transport->transport_complete(cmd, @@ -1246,7 +1223,6 @@ void transport_init_se_cmd( init_completion(&cmd->cmd_wait_comp); spin_lock_init(&cmd->t_state_lock); kref_init(&cmd->cmd_kref); - cmd->transport_state = CMD_T_DEV_ACTIVE; cmd->se_tfo = tfo; cmd->se_sess = se_sess; @@ -1671,6 +1647,9 @@ void transport_generic_request_failure(struct se_cmd *cmd, { int ret = 0, post_ret = 0; + if (transport_check_aborted_status(cmd, 1)) + return; + pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx" " CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]); pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n", @@ -1801,7 +1780,7 @@ void __target_execute_cmd(struct se_cmd *cmd, bool do_checks) return; err: spin_lock_irq(&cmd->t_state_lock); - cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT); + cmd->transport_state &= ~CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); transport_generic_request_failure(cmd, ret); @@ -1829,7 +1808,7 @@ static int target_write_prot_action(struct se_cmd *cmd) sectors, 0, cmd->t_prot_sg, 0); if (unlikely(cmd->pi_err)) { spin_lock_irq(&cmd->t_state_lock); - cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT); + cmd->transport_state &= ~CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); transport_generic_request_failure(cmd, cmd->pi_err); return -1; @@ -1918,7 +1897,7 @@ void target_execute_cmd(struct se_cmd *cmd) } cmd->t_state = TRANSPORT_PROCESSING; - cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT; + cmd->transport_state |= CMD_T_ACTIVE | CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); if (target_write_prot_action(cmd)) @@ -1926,7 +1905,7 @@ void target_execute_cmd(struct se_cmd *cmd) if (target_handle_task_attr(cmd)) { spin_lock_irq(&cmd->t_state_lock); - cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT); + cmd->transport_state &= ~CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); return; } @@ -1979,8 +1958,6 @@ static void transport_complete_task_attr(struct se_cmd *cmd) if (cmd->sam_task_attr == TCM_SIMPLE_TAG) { atomic_dec_mb(&dev->simple_cmds); dev->dev_cur_ordered_id++; - pr_debug("Incremented dev->dev_cur_ordered_id: %u for SIMPLE\n", - dev->dev_cur_ordered_id); } else if (cmd->sam_task_attr == TCM_HEAD_TAG) { dev->dev_cur_ordered_id++; pr_debug("Incremented dev_cur_ordered_id: %u for HEAD_OF_QUEUE\n", @@ -2387,6 +2364,7 @@ EXPORT_SYMBOL(target_alloc_sgl); sense_reason_t transport_generic_new_cmd(struct se_cmd *cmd) { + unsigned long flags; int ret = 0; bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); @@ -2452,7 +2430,24 @@ transport_generic_new_cmd(struct se_cmd *cmd) target_execute_cmd(cmd); return 0; } - transport_cmd_check_stop(cmd, false, true); + + spin_lock_irqsave(&cmd->t_state_lock, flags); + cmd->t_state = TRANSPORT_WRITE_PENDING; + /* + * Determine if frontend context caller is requesting the stopping of + * this command for frontend exceptions. + */ + if (cmd->transport_state & CMD_T_STOP) { + pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n", + __func__, __LINE__, cmd->tag); + + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + + complete_all(&cmd->t_transport_stop_comp); + return 0; + } + cmd->transport_state &= ~CMD_T_ACTIVE; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); ret = cmd->se_tfo->write_pending(cmd); if (ret == -EAGAIN || ret == -ENOMEM) @@ -2595,39 +2590,38 @@ static void target_release_cmd_kref(struct kref *kref) unsigned long flags; bool fabric_stop; - spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); + if (se_sess) { + spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); - spin_lock(&se_cmd->t_state_lock); - fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) && - (se_cmd->transport_state & CMD_T_ABORTED); - spin_unlock(&se_cmd->t_state_lock); + spin_lock(&se_cmd->t_state_lock); + fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) && + (se_cmd->transport_state & CMD_T_ABORTED); + spin_unlock(&se_cmd->t_state_lock); - if (se_cmd->cmd_wait_set || fabric_stop) { + if (se_cmd->cmd_wait_set || fabric_stop) { + list_del_init(&se_cmd->se_cmd_list); + spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + target_free_cmd_mem(se_cmd); + complete(&se_cmd->cmd_wait_comp); + return; + } list_del_init(&se_cmd->se_cmd_list); spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - target_free_cmd_mem(se_cmd); - complete(&se_cmd->cmd_wait_comp); - return; } - list_del_init(&se_cmd->se_cmd_list); - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); target_free_cmd_mem(se_cmd); se_cmd->se_tfo->release_cmd(se_cmd); } -/* target_put_sess_cmd - Check for active I/O shutdown via kref_put - * @se_cmd: command descriptor to drop +/** + * target_put_sess_cmd - decrease the command reference count + * @se_cmd: command to drop a reference from + * + * Returns 1 if and only if this target_put_sess_cmd() call caused the + * refcount to drop to zero. Returns zero otherwise. */ int target_put_sess_cmd(struct se_cmd *se_cmd) { - struct se_session *se_sess = se_cmd->se_sess; - - if (!se_sess) { - target_free_cmd_mem(se_cmd); - se_cmd->se_tfo->release_cmd(se_cmd); - return 1; - } return kref_put(&se_cmd->cmd_kref, target_release_cmd_kref); } EXPORT_SYMBOL(target_put_sess_cmd); @@ -2706,10 +2700,39 @@ void target_wait_for_sess_cmds(struct se_session *se_sess) } EXPORT_SYMBOL(target_wait_for_sess_cmds); +static void target_lun_confirm(struct percpu_ref *ref) +{ + struct se_lun *lun = container_of(ref, struct se_lun, lun_ref); + + complete(&lun->lun_ref_comp); +} + void transport_clear_lun_ref(struct se_lun *lun) { - percpu_ref_kill(&lun->lun_ref); + /* + * Mark the percpu-ref as DEAD, switch to atomic_t mode, drop + * the initial reference and schedule confirm kill to be + * executed after one full RCU grace period has completed. + */ + percpu_ref_kill_and_confirm(&lun->lun_ref, target_lun_confirm); + /* + * The first completion waits for percpu_ref_switch_to_atomic_rcu() + * to call target_lun_confirm after lun->lun_ref has been marked + * as __PERCPU_REF_DEAD on all CPUs, and switches to atomic_t + * mode so that percpu_ref_tryget_live() lookup of lun->lun_ref + * fails for all new incoming I/O. + */ wait_for_completion(&lun->lun_ref_comp); + /* + * The second completion waits for percpu_ref_put_many() to + * invoke ->release() after lun->lun_ref has switched to + * atomic_t mode, and lun->lun_ref.count has reached zero. + * + * At this point all target-core lun->lun_ref references have + * been dropped via transport_lun_remove_cmd(), and it's safe + * to proceed with the remaining LUN shutdown. + */ + wait_for_completion(&lun->lun_shutdown_comp); } static bool @@ -2765,11 +2788,8 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop, } /** - * transport_wait_for_tasks - wait for completion to occur - * @cmd: command to wait - * - * Called from frontend fabric context to wait for storage engine - * to pause and/or release frontend generated struct se_cmd. + * transport_wait_for_tasks - set CMD_T_STOP and wait for t_transport_stop_comp + * @cmd: command to wait on */ bool transport_wait_for_tasks(struct se_cmd *cmd) { diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index 9af7842b8178..ec372860106f 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -83,14 +83,12 @@ void ft_dump_cmd(struct ft_cmd *cmd, const char *caller) static void ft_free_cmd(struct ft_cmd *cmd) { struct fc_frame *fp; - struct fc_lport *lport; struct ft_sess *sess; if (!cmd) return; sess = cmd->sess; fp = cmd->req_frame; - lport = fr_dev(fp); if (fr_seq(fp)) fc_seq_release(fr_seq(fp)); fc_frame_free(fp); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 1a6f78d7d027..cab2b71a80d0 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -327,13 +327,11 @@ EXPORT_SYMBOL_GPL(usbip_dump_header); int usbip_recv(struct socket *sock, void *buf, int size) { int result; - struct msghdr msg; - struct kvec iov; + struct kvec iov = {.iov_base = buf, .iov_len = size}; + struct msghdr msg = {.msg_flags = MSG_NOSIGNAL}; int total = 0; - /* for blocks of if (usbip_dbg_flag_xmit) */ - char *bp = buf; - int osize = size; + iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size); usbip_dbg_xmit("enter\n"); @@ -344,26 +342,18 @@ int usbip_recv(struct socket *sock, void *buf, int size) } do { + int sz = msg_data_left(&msg); sock->sk->sk_allocation = GFP_NOIO; - iov.iov_base = buf; - iov.iov_len = size; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = MSG_NOSIGNAL; - - result = kernel_recvmsg(sock, &msg, &iov, 1, size, MSG_WAITALL); + + result = sock_recvmsg(sock, &msg, MSG_WAITALL); if (result <= 0) { pr_debug("receive sock %p buf %p size %u ret %d total %d\n", - sock, buf, size, result, total); + sock, buf + total, sz, result, total); goto err; } - size -= result; - buf += result; total += result; - } while (size > 0); + } while (msg_data_left(&msg)); if (usbip_dbg_flag_xmit) { if (!in_interrupt()) @@ -372,9 +362,9 @@ int usbip_recv(struct socket *sock, void *buf, int size) pr_debug("interrupt :"); pr_debug("receiving....\n"); - usbip_dump_buffer(bp, osize); - pr_debug("received, osize %d ret %d size %d total %d\n", - osize, result, size, total); + usbip_dump_buffer(buf, size); + pr_debug("received, osize %d ret %d size %zd total %d\n", + size, result, msg_data_left(&msg), total); } return total; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index dcbe2e29bf17..f0ba362d4c10 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -284,6 +284,22 @@ void vhost_poll_queue(struct vhost_poll *poll) } EXPORT_SYMBOL_GPL(vhost_poll_queue); +static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq) +{ + int j; + + for (j = 0; j < VHOST_NUM_ADDRS; j++) + vq->meta_iotlb[j] = NULL; +} + +static void vhost_vq_meta_reset(struct vhost_dev *d) +{ + int i; + + for (i = 0; i < d->nvqs; ++i) + __vhost_vq_meta_reset(d->vqs[i]); +} + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { @@ -314,6 +330,7 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; + __vhost_vq_meta_reset(vq); } static int vhost_worker(void *data) @@ -693,6 +710,18 @@ static int vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem, return 1; } +static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq, + u64 addr, unsigned int size, + int type) +{ + const struct vhost_umem_node *node = vq->meta_iotlb[type]; + + if (!node) + return NULL; + + return (void *)(uintptr_t)(node->userspace_addr + addr - node->start); +} + /* Can we switch to this memory table? */ /* Caller should have device mutex but not vq mutex */ static int memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem, @@ -735,8 +764,14 @@ static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to, * could be access through iotlb. So -EAGAIN should * not happen in this case. */ - /* TODO: more fast path */ struct iov_iter t; + void __user *uaddr = vhost_vq_meta_fetch(vq, + (u64)(uintptr_t)to, size, + VHOST_ADDR_DESC); + + if (uaddr) + return __copy_to_user(uaddr, from, size); + ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_WO); @@ -764,8 +799,14 @@ static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, * could be access through iotlb. So -EAGAIN should * not happen in this case. */ - /* TODO: more fast path */ + void __user *uaddr = vhost_vq_meta_fetch(vq, + (u64)(uintptr_t)from, size, + VHOST_ADDR_DESC); struct iov_iter f; + + if (uaddr) + return __copy_from_user(to, uaddr, size); + ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -785,17 +826,12 @@ out: return ret; } -static void __user *__vhost_get_user(struct vhost_virtqueue *vq, - void __user *addr, unsigned size) +static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, + void __user *addr, unsigned int size, + int type) { int ret; - /* This function should be called after iotlb - * prefetch, which means we're sure that vq - * could be access through iotlb. So -EAGAIN should - * not happen in this case. - */ - /* TODO: more fast path */ ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); @@ -816,14 +852,32 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq, return vq->iotlb_iov[0].iov_base; } -#define vhost_put_user(vq, x, ptr) \ +/* This function should be called after iotlb + * prefetch, which means we're sure that vq + * could be access through iotlb. So -EAGAIN should + * not happen in this case. + */ +static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, + void *addr, unsigned int size, + int type) +{ + void __user *uaddr = vhost_vq_meta_fetch(vq, + (u64)(uintptr_t)addr, size, type); + if (uaddr) + return uaddr; + + return __vhost_get_user_slow(vq, addr, size, type); +} + +#define vhost_put_user(vq, x, ptr) \ ({ \ int ret = -EFAULT; \ if (!vq->iotlb) { \ ret = __put_user(x, ptr); \ } else { \ __typeof__(ptr) to = \ - (__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \ + (__typeof__(ptr)) __vhost_get_user(vq, ptr, \ + sizeof(*ptr), VHOST_ADDR_USED); \ if (to != NULL) \ ret = __put_user(x, to); \ else \ @@ -832,14 +886,16 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq, ret; \ }) -#define vhost_get_user(vq, x, ptr) \ +#define vhost_get_user(vq, x, ptr, type) \ ({ \ int ret; \ if (!vq->iotlb) { \ ret = __get_user(x, ptr); \ } else { \ __typeof__(ptr) from = \ - (__typeof__(ptr)) __vhost_get_user(vq, ptr, sizeof(*ptr)); \ + (__typeof__(ptr)) __vhost_get_user(vq, ptr, \ + sizeof(*ptr), \ + type); \ if (from != NULL) \ ret = __get_user(x, from); \ else \ @@ -848,6 +904,12 @@ static void __user *__vhost_get_user(struct vhost_virtqueue *vq, ret; \ }) +#define vhost_get_avail(vq, x, ptr) \ + vhost_get_user(vq, x, ptr, VHOST_ADDR_AVAIL) + +#define vhost_get_used(vq, x, ptr) \ + vhost_get_user(vq, x, ptr, VHOST_ADDR_USED) + static void vhost_dev_lock_vqs(struct vhost_dev *d) { int i = 0; @@ -953,6 +1015,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, ret = -EFAULT; break; } + vhost_vq_meta_reset(dev); if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size, msg->iova + msg->size - 1, msg->uaddr, msg->perm)) { @@ -962,6 +1025,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, vhost_iotlb_notify_vq(dev, msg); break; case VHOST_IOTLB_INVALIDATE: + vhost_vq_meta_reset(dev); vhost_del_umem_range(dev->iotlb, msg->iova, msg->iova + msg->size - 1); break; @@ -1105,12 +1169,26 @@ static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, sizeof *used + num * sizeof *used->ring + s); } +static void vhost_vq_meta_update(struct vhost_virtqueue *vq, + const struct vhost_umem_node *node, + int type) +{ + int access = (type == VHOST_ADDR_USED) ? + VHOST_ACCESS_WO : VHOST_ACCESS_RO; + + if (likely(node->perm & access)) + vq->meta_iotlb[type] = node; +} + static int iotlb_access_ok(struct vhost_virtqueue *vq, - int access, u64 addr, u64 len) + int access, u64 addr, u64 len, int type) { const struct vhost_umem_node *node; struct vhost_umem *umem = vq->iotlb; - u64 s = 0, size; + u64 s = 0, size, orig_addr = addr; + + if (vhost_vq_meta_fetch(vq, addr, len, type)) + return true; while (len > s) { node = vhost_umem_interval_tree_iter_first(&umem->umem_tree, @@ -1127,6 +1205,10 @@ static int iotlb_access_ok(struct vhost_virtqueue *vq, } size = node->size - addr + node->start; + + if (orig_addr == addr && size >= len) + vhost_vq_meta_update(vq, node, type); + s += size; addr += size; } @@ -1143,13 +1225,15 @@ int vq_iotlb_prefetch(struct vhost_virtqueue *vq) return 1; return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc, - num * sizeof *vq->desc) && + num * sizeof(*vq->desc), VHOST_ADDR_DESC) && iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail, sizeof *vq->avail + - num * sizeof *vq->avail->ring + s) && + num * sizeof(*vq->avail->ring) + s, + VHOST_ADDR_AVAIL) && iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used, sizeof *vq->used + - num * sizeof *vq->used->ring + s); + num * sizeof(*vq->used->ring) + s, + VHOST_ADDR_USED); } EXPORT_SYMBOL_GPL(vq_iotlb_prefetch); @@ -1730,7 +1814,7 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq) r = -EFAULT; goto err; } - r = vhost_get_user(vq, last_used_idx, &vq->used->idx); + r = vhost_get_used(vq, last_used_idx, &vq->used->idx); if (r) { vq_err(vq, "Can't access used idx at %p\n", &vq->used->idx); @@ -1932,29 +2016,36 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* Check it isn't doing very strange things with descriptor numbers. */ last_avail_idx = vq->last_avail_idx; - if (unlikely(vhost_get_user(vq, avail_idx, &vq->avail->idx))) { - vq_err(vq, "Failed to access avail idx at %p\n", - &vq->avail->idx); - return -EFAULT; - } - vq->avail_idx = vhost16_to_cpu(vq, avail_idx); - if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) { - vq_err(vq, "Guest moved used index from %u to %u", - last_avail_idx, vq->avail_idx); - return -EFAULT; - } + if (vq->avail_idx == vq->last_avail_idx) { + if (unlikely(vhost_get_avail(vq, avail_idx, &vq->avail->idx))) { + vq_err(vq, "Failed to access avail idx at %p\n", + &vq->avail->idx); + return -EFAULT; + } + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); - /* If there's nothing new since last we looked, return invalid. */ - if (vq->avail_idx == last_avail_idx) - return vq->num; + if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) { + vq_err(vq, "Guest moved used index from %u to %u", + last_avail_idx, vq->avail_idx); + return -EFAULT; + } + + /* If there's nothing new since last we looked, return + * invalid. + */ + if (vq->avail_idx == last_avail_idx) + return vq->num; - /* Only get avail ring entries after they have been exposed by guest. */ - smp_rmb(); + /* Only get avail ring entries after they have been + * exposed by guest. + */ + smp_rmb(); + } /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ - if (unlikely(vhost_get_user(vq, ring_head, + if (unlikely(vhost_get_avail(vq, ring_head, &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, @@ -2170,7 +2261,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) * with the barrier that the Guest executes when enabling * interrupts. */ smp_mb(); - if (vhost_get_user(vq, flags, &vq->avail->flags)) { + if (vhost_get_avail(vq, flags, &vq->avail->flags)) { vq_err(vq, "Failed to get flags"); return true; } @@ -2197,7 +2288,7 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) * interrupts. */ smp_mb(); - if (vhost_get_user(vq, event, vhost_used_event(vq))) { + if (vhost_get_avail(vq, event, vhost_used_event(vq))) { vq_err(vq, "Failed to get used event idx"); return true; } @@ -2244,7 +2335,7 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) if (vq->avail_idx != vq->last_avail_idx) return false; - r = vhost_get_user(vq, avail_idx, &vq->avail->idx); + r = vhost_get_avail(vq, avail_idx, &vq->avail->idx); if (unlikely(r)) return false; vq->avail_idx = vhost16_to_cpu(vq, avail_idx); @@ -2280,7 +2371,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) /* They could have slipped one in as we were doing that: make * sure it's written, then check again. */ smp_mb(); - r = vhost_get_user(vq, avail_idx, &vq->avail->idx); + r = vhost_get_avail(vq, avail_idx, &vq->avail->idx); if (r) { vq_err(vq, "Failed to check avail idx at %p: %d\n", &vq->avail->idx, r); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index a9cbbb148f46..f55671d53f28 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -76,6 +76,13 @@ struct vhost_umem { int numem; }; +enum vhost_uaddr_type { + VHOST_ADDR_DESC = 0, + VHOST_ADDR_AVAIL = 1, + VHOST_ADDR_USED = 2, + VHOST_NUM_ADDRS = 3, +}; + /* The virtqueue structure describes a queue attached to a device. */ struct vhost_virtqueue { struct vhost_dev *dev; @@ -86,6 +93,7 @@ struct vhost_virtqueue { struct vring_desc __user *desc; struct vring_avail __user *avail; struct vring_used __user *used; + const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; struct file *call; struct file *error; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index a610061fabf6..4e1191508228 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -414,7 +414,8 @@ static int init_vqs(struct virtio_balloon *vb) * optionally stat. */ nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2; - err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names); + err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names, + NULL); if (err) return err; diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 350a2a5a49db..79f1293cda93 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -173,7 +173,8 @@ static int virtinput_init_vqs(struct virtio_input *vi) static const char * const names[] = { "events", "status" }; int err; - err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names); + err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names, + NULL); if (err) return err; vi->evt = vqs[0]; diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index c71fde5fe835..78343b8f9034 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -70,7 +70,7 @@ #include <linux/spinlock.h> #include <linux/virtio.h> #include <linux/virtio_config.h> -#include <linux/virtio_mmio.h> +#include <uapi/linux/virtio_mmio.h> #include <linux/virtio_ring.h> @@ -446,7 +446,8 @@ error_available: static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], + struct irq_affinity *desc) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); unsigned int irq = platform_get_irq(vm_dev->pdev, 0); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 186cbab327b8..df548a6fb844 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -33,10 +33,8 @@ void vp_synchronize_vectors(struct virtio_device *vdev) struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; - if (vp_dev->intx_enabled) - synchronize_irq(vp_dev->pci_dev->irq); - - for (i = 0; i < vp_dev->msix_vectors; ++i) + synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0)); + for (i = 1; i < vp_dev->msix_vectors; i++) synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } @@ -62,16 +60,13 @@ static irqreturn_t vp_config_changed(int irq, void *opaque) static irqreturn_t vp_vring_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; - struct virtio_pci_vq_info *info; irqreturn_t ret = IRQ_NONE; - unsigned long flags; + struct virtqueue *vq; - spin_lock_irqsave(&vp_dev->lock, flags); - list_for_each_entry(info, &vp_dev->virtqueues, node) { - if (vring_interrupt(irq, info->vq) == IRQ_HANDLED) + list_for_each_entry(vq, &vp_dev->vdev.vqs, list) { + if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED) ret = IRQ_HANDLED; } - spin_unlock_irqrestore(&vp_dev->lock, flags); return ret; } @@ -102,237 +97,185 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) return vp_vring_interrupt(irq, opaque); } -static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, - bool per_vq_vectors) +static void vp_remove_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - const char *name = dev_name(&vp_dev->vdev.dev); - unsigned i, v; - int err = -ENOMEM; - - vp_dev->msix_vectors = nvectors; - - vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names, - GFP_KERNEL); - if (!vp_dev->msix_names) - goto error; - vp_dev->msix_affinity_masks - = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks, - GFP_KERNEL); - if (!vp_dev->msix_affinity_masks) - goto error; - for (i = 0; i < nvectors; ++i) - if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], - GFP_KERNEL)) - goto error; - - err = pci_alloc_irq_vectors(vp_dev->pci_dev, nvectors, nvectors, - PCI_IRQ_MSIX); - if (err < 0) - goto error; - vp_dev->msix_enabled = 1; - - /* Set the vector used for configuration */ - v = vp_dev->msix_used_vectors; - snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, - "%s-config", name); - err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), - vp_config_changed, 0, vp_dev->msix_names[v], - vp_dev); - if (err) - goto error; - ++vp_dev->msix_used_vectors; - - v = vp_dev->config_vector(vp_dev, v); - /* Verify we had enough resources to assign the vector */ - if (v == VIRTIO_MSI_NO_VECTOR) { - err = -EBUSY; - goto error; - } - - if (!per_vq_vectors) { - /* Shared vector for all VQs */ - v = vp_dev->msix_used_vectors; - snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, - "%s-virtqueues", name); - err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), - vp_vring_interrupt, 0, vp_dev->msix_names[v], - vp_dev); - if (err) - goto error; - ++vp_dev->msix_used_vectors; - } - return 0; -error: - return err; -} - -static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index, - void (*callback)(struct virtqueue *vq), - const char *name, - u16 msix_vec) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); - struct virtqueue *vq; - unsigned long flags; - - /* fill out our structure that represents an active queue */ - if (!info) - return ERR_PTR(-ENOMEM); + struct virtqueue *vq, *n; - vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec); - if (IS_ERR(vq)) - goto out_info; + list_for_each_entry_safe(vq, n, &vdev->vqs, list) { + if (vp_dev->msix_vector_map) { + int v = vp_dev->msix_vector_map[vq->index]; - info->vq = vq; - if (callback) { - spin_lock_irqsave(&vp_dev->lock, flags); - list_add(&info->node, &vp_dev->virtqueues); - spin_unlock_irqrestore(&vp_dev->lock, flags); - } else { - INIT_LIST_HEAD(&info->node); + if (v != VIRTIO_MSI_NO_VECTOR) + free_irq(pci_irq_vector(vp_dev->pci_dev, v), + vq); + } + vp_dev->del_vq(vq); } - - vp_dev->vqs[index] = info; - return vq; - -out_info: - kfree(info); - return vq; -} - -static void vp_del_vq(struct virtqueue *vq) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); - struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; - unsigned long flags; - - spin_lock_irqsave(&vp_dev->lock, flags); - list_del(&info->node); - spin_unlock_irqrestore(&vp_dev->lock, flags); - - vp_dev->del_vq(info); - kfree(info); } /* the config->del_vqs() implementation */ void vp_del_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtqueue *vq, *n; int i; - list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - if (vp_dev->per_vq_vectors) { - int v = vp_dev->vqs[vq->index]->msix_vector; - - if (v != VIRTIO_MSI_NO_VECTOR) - free_irq(pci_irq_vector(vp_dev->pci_dev, v), - vq); - } - vp_del_vq(vq); - } - vp_dev->per_vq_vectors = false; - - if (vp_dev->intx_enabled) { - free_irq(vp_dev->pci_dev->irq, vp_dev); - vp_dev->intx_enabled = 0; - } + if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs))) + return; - for (i = 0; i < vp_dev->msix_used_vectors; ++i) - free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev); + vp_remove_vqs(vdev); - for (i = 0; i < vp_dev->msix_vectors; i++) - if (vp_dev->msix_affinity_masks[i]) + if (vp_dev->pci_dev->msix_enabled) { + for (i = 0; i < vp_dev->msix_vectors; i++) free_cpumask_var(vp_dev->msix_affinity_masks[i]); - if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); - pci_free_irq_vectors(vp_dev->pci_dev); - vp_dev->msix_enabled = 0; + kfree(vp_dev->msix_affinity_masks); + kfree(vp_dev->msix_names); + kfree(vp_dev->msix_vector_map); } - vp_dev->msix_vectors = 0; - vp_dev->msix_used_vectors = 0; - kfree(vp_dev->msix_names); - vp_dev->msix_names = NULL; - kfree(vp_dev->msix_affinity_masks); - vp_dev->msix_affinity_masks = NULL; - kfree(vp_dev->vqs); - vp_dev->vqs = NULL; + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); + pci_free_irq_vectors(vp_dev->pci_dev); } static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[], - bool per_vq_vectors) + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + const char *name = dev_name(&vp_dev->vdev.dev); + int i, err = -ENOMEM, allocated_vectors, nvectors; + unsigned flags = PCI_IRQ_MSIX; + bool shared = false; u16 msix_vec; - int i, err, nvectors, allocated_vectors; - vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); - if (!vp_dev->vqs) - return -ENOMEM; + if (desc) { + flags |= PCI_IRQ_AFFINITY; + desc->pre_vectors++; /* virtio config vector */ + } - if (per_vq_vectors) { - /* Best option: one for change interrupt, one per vq. */ - nvectors = 1; - for (i = 0; i < nvqs; ++i) - if (callbacks[i]) - ++nvectors; - } else { - /* Second best: one for change, shared for all vqs. */ - nvectors = 2; + nvectors = 1; + for (i = 0; i < nvqs; i++) + if (callbacks[i]) + nvectors++; + + /* Try one vector per queue first. */ + err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, + nvectors, flags, desc); + if (err < 0) { + /* Fallback to one vector for config, one shared for queues. */ + shared = true; + err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2, + PCI_IRQ_MSIX); + if (err < 0) + return err; + } + if (err < 0) + return err; + + vp_dev->msix_vectors = nvectors; + vp_dev->msix_names = kmalloc_array(nvectors, + sizeof(*vp_dev->msix_names), GFP_KERNEL); + if (!vp_dev->msix_names) + goto out_free_irq_vectors; + + vp_dev->msix_affinity_masks = kcalloc(nvectors, + sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL); + if (!vp_dev->msix_affinity_masks) + goto out_free_msix_names; + + for (i = 0; i < nvectors; ++i) { + if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], + GFP_KERNEL)) + goto out_free_msix_affinity_masks; } - err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors); + /* Set the vector used for configuration */ + snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names), + "%s-config", name); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed, + 0, vp_dev->msix_names[0], vp_dev); if (err) - goto error_find; + goto out_free_msix_affinity_masks; + + /* Verify we had enough resources to assign the vector */ + if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) { + err = -EBUSY; + goto out_free_config_irq; + } + + vp_dev->msix_vector_map = kmalloc_array(nvqs, + sizeof(*vp_dev->msix_vector_map), GFP_KERNEL); + if (!vp_dev->msix_vector_map) + goto out_disable_config_irq; - vp_dev->per_vq_vectors = per_vq_vectors; - allocated_vectors = vp_dev->msix_used_vectors; + allocated_vectors = 1; /* vector 0 is the config interrupt */ for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } - if (!callbacks[i]) - msix_vec = VIRTIO_MSI_NO_VECTOR; - else if (vp_dev->per_vq_vectors) - msix_vec = allocated_vectors++; + if (callbacks[i]) + msix_vec = allocated_vectors; else - msix_vec = VP_MSIX_VQ_VECTOR; - vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec); + msix_vec = VIRTIO_MSI_NO_VECTOR; + + vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], + msix_vec); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); - goto error_find; + goto out_remove_vqs; } - if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR) + if (msix_vec == VIRTIO_MSI_NO_VECTOR) { + vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; continue; + } - /* allocate per-vq irq if available and necessary */ - snprintf(vp_dev->msix_names[msix_vec], - sizeof *vp_dev->msix_names, - "%s-%s", + snprintf(vp_dev->msix_names[i + 1], + sizeof(*vp_dev->msix_names), "%s-%s", dev_name(&vp_dev->vdev.dev), names[i]); err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), - vring_interrupt, 0, - vp_dev->msix_names[msix_vec], - vqs[i]); - if (err) - goto error_find; + vring_interrupt, IRQF_SHARED, + vp_dev->msix_names[i + 1], vqs[i]); + if (err) { + /* don't free this irq on error */ + vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; + goto out_remove_vqs; + } + vp_dev->msix_vector_map[i] = msix_vec; + + /* + * Use a different vector for each queue if they are available, + * else share the same vector for all VQs. + */ + if (!shared) + allocated_vectors++; } + return 0; -error_find: - vp_del_vqs(vdev); +out_remove_vqs: + vp_remove_vqs(vdev); + kfree(vp_dev->msix_vector_map); +out_disable_config_irq: + vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); +out_free_config_irq: + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); +out_free_msix_affinity_masks: + for (i = 0; i < nvectors; i++) { + if (vp_dev->msix_affinity_masks[i]) + free_cpumask_var(vp_dev->msix_affinity_masks[i]); + } + kfree(vp_dev->msix_affinity_masks); +out_free_msix_names: + kfree(vp_dev->msix_names); +out_free_irq_vectors: + pci_free_irq_vectors(vp_dev->pci_dev); return err; } @@ -343,53 +286,42 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs, struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i, err; - vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); - if (!vp_dev->vqs) - return -ENOMEM; - err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) - goto out_del_vqs; + return err; - vp_dev->intx_enabled = 1; - vp_dev->per_vq_vectors = false; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; } - vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], + vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], VIRTIO_MSI_NO_VECTOR); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); - goto out_del_vqs; + goto out_remove_vqs; } } return 0; -out_del_vqs: - vp_del_vqs(vdev); + +out_remove_vqs: + vp_remove_vqs(vdev); + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); return err; } /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]) + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { int err; - /* Try MSI-X with one vector per queue. */ - err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true); + err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc); if (!err) return 0; - /* Fallback: MSI-X with one vector for config, one shared for queues. */ - err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false); - if (!err) - return 0; - /* Finally fall back to regular interrupts. */ return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names); } @@ -409,16 +341,15 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; - struct cpumask *mask; - unsigned int irq; if (!vq->callback) return -EINVAL; - if (vp_dev->msix_enabled) { - mask = vp_dev->msix_affinity_masks[info->msix_vector]; - irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector); + if (vp_dev->pci_dev->msix_enabled) { + int vec = vp_dev->msix_vector_map[vq->index]; + struct cpumask *mask = vp_dev->msix_affinity_masks[vec]; + unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec); + if (cpu == -1) irq_set_affinity_hint(irq, NULL); else { @@ -430,6 +361,17 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) return 0; } +const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + unsigned int *map = vp_dev->msix_vector_map; + + if (!map || map[index] == VIRTIO_MSI_NO_VECTOR) + return NULL; + + return pci_irq_get_affinity(vp_dev->pci_dev, map[index]); +} + #ifdef CONFIG_PM_SLEEP static int virtio_pci_freeze(struct device *dev) { @@ -498,8 +440,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; - INIT_LIST_HEAD(&vp_dev->virtqueues); - spin_lock_init(&vp_dev->lock); /* enable the device */ rc = pci_enable_device(pci_dev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index b2f666250ae0..ac8c9d788964 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -31,17 +31,6 @@ #include <linux/highmem.h> #include <linux/spinlock.h> -struct virtio_pci_vq_info { - /* the actual virtqueue */ - struct virtqueue *vq; - - /* the list node for the virtqueues list */ - struct list_head node; - - /* MSI-X vector (or none) */ - unsigned msix_vector; -}; - /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; @@ -75,47 +64,25 @@ struct virtio_pci_device { /* the IO mapping for the PCI config space */ void __iomem *ioaddr; - /* a list of queues so we can dispatch IRQs */ - spinlock_t lock; - struct list_head virtqueues; - - /* array of all queues for house-keeping */ - struct virtio_pci_vq_info **vqs; - - /* MSI-X support */ - int msix_enabled; - int intx_enabled; cpumask_var_t *msix_affinity_masks; /* Name strings for interrupts. This size should be enough, * and I'm too lazy to allocate each name separately. */ char (*msix_names)[256]; - /* Number of available vectors */ - unsigned msix_vectors; - /* Vectors allocated, excluding per-vq vectors if any */ - unsigned msix_used_vectors; - - /* Whether we have vector per vq */ - bool per_vq_vectors; + /* Total Number of MSI-X vectors (including per-VQ ones). */ + int msix_vectors; + /* Map of per-VQ MSI-X vectors, may be NULL */ + unsigned *msix_vector_map; struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned idx, void (*callback)(struct virtqueue *vq), const char *name, u16 msix_vec); - void (*del_vq)(struct virtio_pci_vq_info *info); + void (*del_vq)(struct virtqueue *vq); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); }; -/* Constants for MSI-X */ -/* Use first vector for configuration changes, second and the rest for - * virtqueues Thus, we need at least 2 vectors for MSI. */ -enum { - VP_MSIX_CONFIG_VECTOR = 0, - VP_MSIX_VQ_VECTOR = 1, -}; - /* Convert a generic virtio device to our structure */ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev) { @@ -130,9 +97,8 @@ bool vp_notify(struct virtqueue *vq); void vp_del_vqs(struct virtio_device *vdev); /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]); + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc); const char *vp_bus_name(struct virtio_device *vdev); /* Setup the affinity for a virtqueue: @@ -142,6 +108,8 @@ const char *vp_bus_name(struct virtio_device *vdev); */ int vp_set_vq_affinity(struct virtqueue *vq, int cpu); +const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index); + #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY) int virtio_pci_legacy_probe(struct virtio_pci_device *); void virtio_pci_legacy_remove(struct virtio_pci_device *); diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index 6d9e5173d5fa..f7362c5fe18a 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -112,7 +112,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -130,8 +129,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN)) return ERR_PTR(-ENOENT); - info->msix_vector = msix_vec; - /* create the vring */ vq = vring_create_virtqueue(index, num, VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev, @@ -162,14 +159,13 @@ out_deactivate: return ERR_PTR(err); } -static void del_vq(struct virtio_pci_vq_info *info) +static void del_vq(struct virtqueue *vq) { - struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL); - if (vp_dev->msix_enabled) { + if (vp_dev->pci_dev->msix_enabled) { iowrite16(VIRTIO_MSI_NO_VECTOR, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); /* Flush the write out to device */ @@ -194,6 +190,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; /* the PCI probing function */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 4bf7ab375894..7bc3004b840e 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -293,7 +293,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -323,8 +322,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, /* get offset of notification word for this vq */ off = vp_ioread16(&cfg->queue_notify_off); - info->msix_vector = msix_vec; - /* create the vring */ vq = vring_create_virtqueue(index, num, SMP_CACHE_BYTES, &vp_dev->vdev, @@ -387,13 +384,12 @@ err_map_notify: } static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]) + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtqueue *vq; - int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names); + int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc); if (rc) return rc; @@ -409,14 +405,13 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, return 0; } -static void del_vq(struct virtio_pci_vq_info *info) +static void del_vq(struct virtqueue *vq) { - struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); vp_iowrite16(vq->index, &vp_dev->common->queue_select); - if (vp_dev->msix_enabled) { + if (vp_dev->pci_dev->msix_enabled) { vp_iowrite16(VIRTIO_MSI_NO_VECTOR, &vp_dev->common->queue_msix_vector); /* Flush the write out to device */ @@ -442,6 +437,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -457,6 +453,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; /** diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index c831b7967bf9..52a70ee6014f 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -142,6 +142,7 @@ config GPIO_WATCHDOG_ARCH_INITCALL config MENF21BMC_WATCHDOG tristate "MEN 14F021P00 BMC Watchdog" depends on MFD_MENF21BMC || COMPILE_TEST + depends on I2C select WATCHDOG_CORE help Say Y here to include support for the MEN 14F021P00 BMC Watchdog. @@ -176,7 +177,7 @@ config WDAT_WDT config WM831X_WATCHDOG tristate "WM831x watchdog" - depends on MFD_WM831X || COMPILE_TEST + depends on MFD_WM831X select WATCHDOG_CORE help Support for the watchdog in the WM831x AudioPlus PMICs. When @@ -217,7 +218,7 @@ config ZIIRAVE_WATCHDOG config ARM_SP805_WATCHDOG tristate "ARM SP805 Watchdog" - depends on (ARM || ARM64) && (ARM_AMBA || COMPILE_TEST) + depends on (ARM || ARM64 || COMPILE_TEST) && ARM_AMBA select WATCHDOG_CORE help ARM Primecell SP805 Watchdog timer. This will reboot your system when @@ -573,7 +574,7 @@ config IMX2_WDT config UX500_WATCHDOG tristate "ST-Ericsson Ux500 watchdog" - depends on MFD_DB8500_PRCMU || (ARM && COMPILE_TEST) + depends on MFD_DB8500_PRCMU select WATCHDOG_CORE default y help @@ -585,7 +586,7 @@ config UX500_WATCHDOG config RETU_WATCHDOG tristate "Retu watchdog" - depends on MFD_RETU || COMPILE_TEST + depends on MFD_RETU select WATCHDOG_CORE help Retu watchdog driver for Nokia Internet Tablets (770, N800, @@ -851,7 +852,7 @@ config SP5100_TCO config GEODE_WDT tristate "AMD Geode CS5535/CS5536 Watchdog" - depends on CS5535_MFGPT || (X86 && COMPILE_TEST) + depends on CS5535_MFGPT help This driver enables a watchdog capability built into the CS5535/CS5536 companion chips for the AMD Geode GX and LX @@ -1063,7 +1064,7 @@ config HP_WATCHDOG config KEMPLD_WDT tristate "Kontron COM Watchdog Timer" - depends on MFD_KEMPLD || COMPILE_TEST + depends on MFD_KEMPLD select WATCHDOG_CORE help Support for the PLD watchdog on some Kontron ETX and COMexpress @@ -1495,7 +1496,7 @@ config BCM63XX_WDT config BCM2835_WDT tristate "Broadcom BCM2835 hardware watchdog" - depends on ARCH_BCM2835 || COMPILE_TEST + depends on ARCH_BCM2835 || (OF && COMPILE_TEST) select WATCHDOG_CORE help Watchdog driver for the built in watchdog hardware in Broadcom diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c index 73c46b3a09ab..2f3b049ea301 100644 --- a/drivers/watchdog/kempld_wdt.c +++ b/drivers/watchdog/kempld_wdt.c @@ -140,12 +140,19 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data, unsigned int timeout) { struct kempld_device_data *pld = wdt_data->pld; - u32 prescaler = kempld_prescaler[PRESCALER_21]; + u32 prescaler; u64 stage_timeout64; u32 stage_timeout; u32 remainder; u8 stage_cfg; +#if GCC_VERSION < 40400 + /* work around a bug compiling do_div() */ + prescaler = READ_ONCE(kempld_prescaler[PRESCALER_21]); +#else + prescaler = kempld_prescaler[PRESCALER_21]; +#endif + if (!stage) return -EINVAL; diff --git a/drivers/watchdog/softdog.c b/drivers/watchdog/softdog.c index 7983029852ab..060740625485 100644 --- a/drivers/watchdog/softdog.c +++ b/drivers/watchdog/softdog.c @@ -21,13 +21,12 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/hrtimer.h> #include <linux/init.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/reboot.h> -#include <linux/timer.h> #include <linux/types.h> #include <linux/watchdog.h> @@ -54,7 +53,10 @@ module_param(soft_panic, int, 0); MODULE_PARM_DESC(soft_panic, "Softdog action, set to 1 to panic, 0 to reboot (default=0)"); -static void softdog_fire(unsigned long data) +static struct hrtimer softdog_ticktock; +static struct hrtimer softdog_preticktock; + +static enum hrtimer_restart softdog_fire(struct hrtimer *timer) { module_put(THIS_MODULE); if (soft_noboot) { @@ -67,32 +69,33 @@ static void softdog_fire(unsigned long data) emergency_restart(); pr_crit("Reboot didn't ?????\n"); } -} -static struct timer_list softdog_ticktock = - TIMER_INITIALIZER(softdog_fire, 0, 0); + return HRTIMER_NORESTART; +} static struct watchdog_device softdog_dev; -static void softdog_pretimeout(unsigned long data) +static enum hrtimer_restart softdog_pretimeout(struct hrtimer *timer) { watchdog_notify_pretimeout(&softdog_dev); -} -static struct timer_list softdog_preticktock = - TIMER_INITIALIZER(softdog_pretimeout, 0, 0); + return HRTIMER_NORESTART; +} static int softdog_ping(struct watchdog_device *w) { - if (!mod_timer(&softdog_ticktock, jiffies + (w->timeout * HZ))) + if (!hrtimer_active(&softdog_ticktock)) __module_get(THIS_MODULE); + hrtimer_start(&softdog_ticktock, ktime_set(w->timeout, 0), + HRTIMER_MODE_REL); if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) { if (w->pretimeout) - mod_timer(&softdog_preticktock, jiffies + - (w->timeout - w->pretimeout) * HZ); + hrtimer_start(&softdog_preticktock, + ktime_set(w->timeout - w->pretimeout, 0), + HRTIMER_MODE_REL); else - del_timer(&softdog_preticktock); + hrtimer_cancel(&softdog_preticktock); } return 0; @@ -100,11 +103,11 @@ static int softdog_ping(struct watchdog_device *w) static int softdog_stop(struct watchdog_device *w) { - if (del_timer(&softdog_ticktock)) + if (hrtimer_cancel(&softdog_ticktock)) module_put(THIS_MODULE); if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) - del_timer(&softdog_preticktock); + hrtimer_cancel(&softdog_preticktock); return 0; } @@ -136,8 +139,15 @@ static int __init softdog_init(void) watchdog_set_nowayout(&softdog_dev, nowayout); watchdog_stop_on_reboot(&softdog_dev); - if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) + hrtimer_init(&softdog_ticktock, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + softdog_ticktock.function = softdog_fire; + + if (IS_ENABLED(CONFIG_SOFT_WATCHDOG_PRETIMEOUT)) { softdog_info.options |= WDIOF_PRETIMEOUT; + hrtimer_init(&softdog_preticktock, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + softdog_preticktock.function = softdog_pretimeout; + } ret = watchdog_register_device(&softdog_dev); if (ret) diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 4f6b00efc27c..419ef05dcb5e 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -262,8 +262,7 @@ void afs_flat_call_destructor(struct afs_call *call) /* * attach the data from a bunch of pages on an inode to a call */ -static int afs_send_pages(struct afs_call *call, struct msghdr *msg, - struct kvec *iov) +static int afs_send_pages(struct afs_call *call, struct msghdr *msg) { struct page *pages[8]; unsigned count, n, loop, offset, to; @@ -286,20 +285,21 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, loop = 0; do { + struct bio_vec bvec = {.bv_page = pages[loop], + .bv_offset = offset}; msg->msg_flags = 0; to = PAGE_SIZE; if (first + loop >= last) to = call->last_to; else msg->msg_flags = MSG_MORE; - iov->iov_base = kmap(pages[loop]) + offset; - iov->iov_len = to - offset; + bvec.bv_len = to - offset; offset = 0; _debug("- range %u-%u%s", offset, to, msg->msg_flags ? " [more]" : ""); - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, - iov, 1, to - offset); + iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, + &bvec, 1, to - offset); /* have to change the state *before* sending the last * packet as RxRPC might give us the reply before it @@ -308,7 +308,6 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, call->state = AFS_CALL_AWAIT_REPLY; ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, msg, to - offset); - kunmap(pages[loop]); if (ret < 0) break; } while (++loop < count); @@ -393,7 +392,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, goto error_do_abort; if (call->send_pages) { - ret = afs_send_pages(call, &msg, iov); + ret = afs_send_pages(call, &msg); if (ret < 0) goto error_do_abort; } @@ -1495,7 +1495,7 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored, return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) - ret = aio_ret(req, file->f_op->read_iter(req, &iter)); + ret = aio_ret(req, call_read_iter(file, req, &iter)); kfree(iovec); return ret; } @@ -1520,7 +1520,7 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored, if (!ret) { req->ki_flags |= IOCB_WRITE; file_start_write(file); - ret = aio_ret(req, file->f_op->write_iter(req, &iter)); + ret = aio_ret(req, call_write_iter(file, req, &iter)); /* * We release freeze protection in aio_complete(). Fool lockdep * by telling it the lock got released so that it doesn't diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 819a6d27218a..0c6baaba0651 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -237,20 +237,20 @@ static inline u64 btrfs_ino(struct btrfs_inode *inode) return ino; } -static inline void btrfs_i_size_write(struct inode *inode, u64 size) +static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size) { - i_size_write(inode, size); - BTRFS_I(inode)->disk_i_size = size; + i_size_write(&inode->vfs_inode, size); + inode->disk_i_size = size; } -static inline bool btrfs_is_free_space_inode(struct inode *inode) +static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; if (root == root->fs_info->tree_root && - btrfs_ino(BTRFS_I(inode)) != BTRFS_BTREE_INODE_OBJECTID) + btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID) return true; - if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID) + if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID) return true; return false; } @@ -311,34 +311,33 @@ struct btrfs_dio_private { * to grab i_mutex. It is used to avoid the endless truncate due to * nonlocked dio read. */ -static inline void btrfs_inode_block_unlocked_dio(struct inode *inode) +static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode) { - set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags); smp_mb(); } -static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode) +static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode) { smp_mb__before_atomic(); - clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, - &BTRFS_I(inode)->runtime_flags); + clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags); } -static inline void btrfs_print_data_csum_error(struct inode *inode, +static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode, u64 logical_start, u32 csum, u32 csum_expected, int mirror_num) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; /* Output minus objectid, which is more meaningful */ if (root->objectid >= BTRFS_LAST_FREE_OBJECTID) btrfs_warn_rl(root->fs_info, "csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d", - root->objectid, btrfs_ino(BTRFS_I(inode)), + root->objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); else btrfs_warn_rl(root->fs_info, "csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d", - root->objectid, btrfs_ino(BTRFS_I(inode)), + root->objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 903c32c9eb22..c7721a6aa3bb 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -100,7 +100,7 @@ static struct bio *compressed_bio_alloc(struct block_device *bdev, return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags); } -static int check_compressed_csum(struct inode *inode, +static int check_compressed_csum(struct btrfs_inode *inode, struct compressed_bio *cb, u64 disk_start) { @@ -111,7 +111,7 @@ static int check_compressed_csum(struct inode *inode, u32 csum; u32 *cb_sum = &cb->sums; - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + if (inode->flags & BTRFS_INODE_NODATASUM) return 0; for (i = 0; i < cb->nr_pages; i++) { @@ -125,7 +125,7 @@ static int check_compressed_csum(struct inode *inode, if (csum != *cb_sum) { btrfs_print_data_csum_error(inode, disk_start, csum, - *cb_sum, cb->mirror_num); + *cb_sum, cb->mirror_num); ret = -EIO; goto fail; } @@ -165,7 +165,7 @@ static void end_compressed_bio_read(struct bio *bio) goto out; inode = cb->inode; - ret = check_compressed_csum(inode, cb, + ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); if (ret) goto csum_failed; @@ -911,32 +911,28 @@ static void free_workspaces(void) } /* - * given an address space and start/len, compress the bytes. + * Given an address space and start and length, compress the bytes into @pages + * that are allocated on demand. * - * pages are allocated to hold the compressed result and stored - * in 'pages' + * @out_pages is an in/out parameter, holds maximum number of pages to allocate + * and returns number of actually allocated pages * - * out_pages is used to return the number of pages allocated. There - * may be pages allocated even if we return an error - * - * total_in is used to return the number of bytes actually read. It - * may be smaller then len if we had to exit early because we + * @total_in is used to return the number of bytes actually read. It + * may be smaller than the input length if we had to exit early because we * ran out of room in the pages array or because we cross the * max_out threshold. * - * total_out is used to return the total number of compressed bytes + * @total_out is an in/out parameter, must be set to the input length and will + * be also used to return the total number of compressed bytes * - * max_out tells us the max number of bytes that we're allowed to + * @max_out tells us the max number of bytes that we're allowed to * stuff into pages */ int btrfs_compress_pages(int type, struct address_space *mapping, - u64 start, unsigned long len, - struct page **pages, - unsigned long nr_dest_pages, + u64 start, struct page **pages, unsigned long *out_pages, unsigned long *total_in, - unsigned long *total_out, - unsigned long max_out) + unsigned long *total_out) { struct list_head *workspace; int ret; @@ -944,10 +940,9 @@ int btrfs_compress_pages(int type, struct address_space *mapping, workspace = find_workspace(type); ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping, - start, len, pages, - nr_dest_pages, out_pages, - total_in, total_out, - max_out); + start, pages, + out_pages, + total_in, total_out); free_workspace(type, workspace); return ret; } @@ -1015,7 +1010,7 @@ void btrfs_exit_compress(void) * * total_out is the last byte of the buffer */ -int btrfs_decompress_buf2page(char *buf, unsigned long buf_start, +int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, unsigned long total_out, u64 disk_start, struct bio *bio) { diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 09879579fbc8..39ec43ab8df1 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -19,20 +19,32 @@ #ifndef __BTRFS_COMPRESSION_ #define __BTRFS_COMPRESSION_ +/* + * We want to make sure that amount of RAM required to uncompress an extent is + * reasonable, so we limit the total size in ram of a compressed extent to + * 128k. This is a crucial number because it also controls how easily we can + * spread reads across cpus for decompression. + * + * We also want to make sure the amount of IO required to do a random read is + * reasonably small, so we limit the size of a compressed extent to 128k. + */ + +/* Maximum length of compressed data stored on disk */ +#define BTRFS_MAX_COMPRESSED (SZ_128K) +/* Maximum size of data before compression */ +#define BTRFS_MAX_UNCOMPRESSED (SZ_128K) + void btrfs_init_compress(void); void btrfs_exit_compress(void); int btrfs_compress_pages(int type, struct address_space *mapping, - u64 start, unsigned long len, - struct page **pages, - unsigned long nr_dest_pages, + u64 start, struct page **pages, unsigned long *out_pages, unsigned long *total_in, - unsigned long *total_out, - unsigned long max_out); + unsigned long *total_out); int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page, unsigned long start_byte, size_t srclen, size_t destlen); -int btrfs_decompress_buf2page(char *buf, unsigned long buf_start, +int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, unsigned long total_out, u64 disk_start, struct bio *bio); @@ -59,13 +71,11 @@ struct btrfs_compress_op { int (*compress_pages)(struct list_head *workspace, struct address_space *mapping, - u64 start, unsigned long len, + u64 start, struct page **pages, - unsigned long nr_dest_pages, unsigned long *out_pages, unsigned long *total_in, - unsigned long *total_out, - unsigned long max_out); + unsigned long *total_out); int (*decompress_bio)(struct list_head *workspace, struct page **pages_in, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 1192bc7d2ee7..7dc8844037e0 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -453,8 +453,6 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) struct rb_node *parent = NULL; struct tree_mod_elem *cur; - BUG_ON(!tm); - tm->seq = btrfs_inc_tree_mod_seq(fs_info); tm_root = &fs_info->tree_mod_log; @@ -4159,6 +4157,9 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, /* try to push all the items before our slot into the next leaf */ slot = path->slots[0]; + space_needed = data_size; + if (slot > 0) + space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]); ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; @@ -4214,6 +4215,10 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, if (wret < 0) return wret; if (wret) { + space_needed = data_size; + if (slot > 0) + space_needed -= btrfs_leaf_free_space(fs_info, + l); wret = push_leaf_left(trans, root, path, space_needed, space_needed, 0, (u32)-1); if (wret < 0) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a8812d95359d..29b7fc28c607 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2688,7 +2688,7 @@ enum btrfs_flush_state { }; int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); -int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes); +int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes); void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, u64 len); @@ -2696,16 +2696,16 @@ void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans); int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, - struct inode *inode); -void btrfs_orphan_release_metadata(struct inode *inode); + struct btrfs_inode *inode); +void btrfs_orphan_release_metadata(struct btrfs_inode *inode); int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int nitems, u64 *qgroup_reserved, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); -int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes); -void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes); +int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes); +void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes); int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type); @@ -2983,7 +2983,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, const char *name, int name_len); int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, - int name_len, struct inode *dir, + int name_len, struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index); struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3082,7 +3082,7 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit); -void btrfs_extent_item_to_extent_map(struct inode *inode, +void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, const struct btrfs_path *path, struct btrfs_file_extent_item *fi, const bool new_inline, @@ -3101,9 +3101,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, int delay_iput); void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work); -struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page, - size_t pg_offset, u64 start, u64 len, - int create); +struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, + struct page *page, size_t pg_offset, u64 start, + u64 len, int create); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes); @@ -3124,13 +3124,13 @@ static inline void btrfs_force_ra(struct address_space *mapping, } struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); -int btrfs_set_inode_index(struct inode *dir, u64 *index); +int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_inode *dir, struct btrfs_inode *inode, const char *name, int name_len); int btrfs_add_link(struct btrfs_trans_handle *trans, - struct inode *parent_inode, struct inode *inode, + struct btrfs_inode *parent_inode, struct btrfs_inode *inode, const char *name, int name_len, int add_backref, u64 index); int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3167,15 +3167,16 @@ void btrfs_destroy_cachep(void); long btrfs_ioctl_trans_end(struct file *file); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); -struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, - size_t pg_offset, u64 start, u64 end, - int create); +struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, + struct page *page, size_t pg_offset, + u64 start, u64 end, int create); int btrfs_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); -int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode); +int btrfs_orphan_add(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@ -3216,11 +3217,11 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, int btrfs_auto_defrag_init(void); void btrfs_auto_defrag_exit(void); int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct inode *inode); + struct btrfs_inode *inode); int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info); void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); -void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, +void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, int skip_pinned); extern const struct file_operations btrfs_file_operations; int __btrfs_drop_extents(struct btrfs_trans_handle *trans, @@ -3234,7 +3235,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, u64 start, u64 end, int drop_cache); int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, - struct inode *inode, u64 start, u64 end); + struct btrfs_inode *inode, u64 start, u64 end); int btrfs_release_file(struct inode *inode, struct file *file); int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index f7a6ee5ccc80..1aff676f0e5b 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1790,7 +1790,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) i_uid_write(inode, btrfs_stack_inode_uid(inode_item)); i_gid_write(inode, btrfs_stack_inode_gid(inode_item)); - btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); + btrfs_i_size_write(BTRFS_I(inode), btrfs_stack_inode_size(inode_item)); inode->i_mode = btrfs_stack_inode_mode(inode_item); set_nlink(inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5de280b9ad73..e653921f05d9 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -304,8 +304,9 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info) dev_replace->cursor_left_last_write_of_item; } -int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name, - u64 srcdevid, char *srcdev_name, int read_src) +int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, + const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, + int read_src) { struct btrfs_root *root = fs_info->dev_root; struct btrfs_trans_handle *trans; diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 54ea12bda15b..f94a76844ae7 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -27,8 +27,9 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans, void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info); int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args); -int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name, - u64 srcdevid, char *srcdev_name, int read_src); +int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, + const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, + int read_src); void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args); int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 724504a2d7ac..60a750678a82 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -80,7 +80,8 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; u32 data_size; - BUG_ON(name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info)); + if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info)) + return -ENOSPC; key.objectid = objectid; key.type = BTRFS_XATTR_ITEM_KEY; @@ -120,7 +121,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, */ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *name, int name_len, - struct inode *dir, struct btrfs_key *location, + struct btrfs_inode *dir, struct btrfs_key *location, u8 type, u64 index) { int ret = 0; @@ -133,7 +134,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root struct btrfs_disk_key disk_key; u32 data_size; - key.objectid = btrfs_ino(BTRFS_I(dir)); + key.objectid = btrfs_ino(dir); key.type = BTRFS_DIR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); @@ -174,7 +175,7 @@ second_insert: btrfs_release_path(path); ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name, - name_len, BTRFS_I(dir), &disk_key, type, index); + name_len, dir, &disk_key, type, index); out_free: btrfs_free_path(path); if (ret) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 207db0270b15..08b74daf35d0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -219,12 +219,12 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, * extents on the btree inode are pretty simple, there's one extent * that covers the entire device */ -static struct extent_map *btree_get_extent(struct inode *inode, +static struct extent_map *btree_get_extent(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, int create) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map *em; int ret; @@ -265,7 +265,7 @@ out: return em; } -u32 btrfs_csum_data(char *data, u32 seed, size_t len) +u32 btrfs_csum_data(const char *data, u32 seed, size_t len) { return btrfs_crc32c(seed, data, len); } @@ -2205,11 +2205,9 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) btrfs_destroy_workqueue(fs_info->delalloc_workers); btrfs_destroy_workqueue(fs_info->workers); btrfs_destroy_workqueue(fs_info->endio_workers); - btrfs_destroy_workqueue(fs_info->endio_meta_workers); btrfs_destroy_workqueue(fs_info->endio_raid56_workers); btrfs_destroy_workqueue(fs_info->endio_repair_workers); btrfs_destroy_workqueue(fs_info->rmw_workers); - btrfs_destroy_workqueue(fs_info->endio_meta_write_workers); btrfs_destroy_workqueue(fs_info->endio_write_workers); btrfs_destroy_workqueue(fs_info->endio_freespace_worker); btrfs_destroy_workqueue(fs_info->submit_workers); @@ -2219,6 +2217,13 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); btrfs_destroy_workqueue(fs_info->extent_workers); + /* + * Now that all other work queues are destroyed, we can safely destroy + * the queues used for metadata I/O, since tasks from those other work + * queues can do metadata I/O operations. + */ + btrfs_destroy_workqueue(fs_info->endio_meta_workers); + btrfs_destroy_workqueue(fs_info->endio_meta_write_workers); } static void free_root_extent_buffers(struct btrfs_root *root) @@ -3261,7 +3266,6 @@ fail_fsdev_sysfs: fail_block_groups: btrfs_put_block_group_cache(fs_info); - btrfs_free_block_groups(fs_info); fail_tree_roots: free_root_pointers(fs_info, 1); @@ -3269,6 +3273,7 @@ fail_tree_roots: fail_sb_buffer: btrfs_stop_all_workers(fs_info); + btrfs_free_block_groups(fs_info); fail_alloc: fail_iput: btrfs_mapping_tree_free(&fs_info->mapping_tree); @@ -3448,7 +3453,7 @@ static int write_dev_supers(struct btrfs_device *device, btrfs_set_super_bytenr(sb, bytenr); crc = ~(u32)0; - crc = btrfs_csum_data((char *)sb + + crc = btrfs_csum_data((const char *)sb + BTRFS_CSUM_SIZE, crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); @@ -3977,8 +3982,6 @@ void close_ctree(struct btrfs_fs_info *fs_info) btrfs_put_block_group_cache(fs_info); - btrfs_free_block_groups(fs_info); - /* * we must make sure there is not any read request to * submit after we stopping all workers. @@ -3986,6 +3989,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); + btrfs_free_block_groups(fs_info); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, 1); @@ -4653,9 +4658,12 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) } static const struct extent_io_ops btree_extent_io_ops = { - .readpage_end_io_hook = btree_readpage_end_io_hook, - .readpage_io_failed_hook = btree_io_failed_hook, + /* mandatory callbacks */ .submit_bio_hook = btree_submit_bio_hook, + .readpage_end_io_hook = btree_readpage_end_io_hook, /* note we're sharing with inode.c for the merge bio hook */ .merge_bio_hook = btrfs_merge_bio_hook, + .readpage_io_failed_hook = btree_io_failed_hook, + + /* optional callbacks */ }; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 0be2d4fe705b..2e0ec29bfd69 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -116,7 +116,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf); int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int atomic); int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); -u32 btrfs_csum_data(char *data, u32 seed, size_t len); +u32 btrfs_csum_data(const char *data, u32 seed, size_t len); void btrfs_csum_final(u32 crc, u8 *result); int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index dad395b0b9fc..be5477676cc8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4136,10 +4136,10 @@ static u64 btrfs_space_info_used(struct btrfs_space_info *s_info, (may_use_included ? s_info->bytes_may_use : 0); } -int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes) +int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes) { struct btrfs_space_info *data_sinfo; - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; u64 used; int ret = 0; @@ -4282,7 +4282,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) round_down(start, fs_info->sectorsize); start = round_down(start, fs_info->sectorsize); - ret = btrfs_alloc_data_chunk_ondemand(inode, len); + ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len); if (ret < 0) return ret; @@ -5743,10 +5743,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) /* Can only return 0 or -ENOSPC */ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; /* * We always use trans->block_rsv here as we will have reserved space * for our orphan when starting the transaction, using get_block_rsv() @@ -5763,19 +5763,19 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, */ u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - trace_btrfs_space_reservation(fs_info, "orphan", - btrfs_ino(BTRFS_I(inode)), num_bytes, 1); + trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), + num_bytes, 1); return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1); } -void btrfs_orphan_release_metadata(struct inode *inode) +void btrfs_orphan_release_metadata(struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - trace_btrfs_space_reservation(fs_info, "orphan", - btrfs_ino(BTRFS_I(inode)), num_bytes, 0); + trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), + num_bytes, 0); btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes); } @@ -5847,7 +5847,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, * reserved extents that need to be freed. This must be called with * BTRFS_I(inode)->lock held. */ -static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) +static unsigned drop_outstanding_extent(struct btrfs_inode *inode, + u64 num_bytes) { unsigned drop_inode_space = 0; unsigned dropped_extents = 0; @@ -5855,25 +5856,23 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) num_extents = count_max_extents(num_bytes); ASSERT(num_extents); - ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents); - BTRFS_I(inode)->outstanding_extents -= num_extents; + ASSERT(inode->outstanding_extents >= num_extents); + inode->outstanding_extents -= num_extents; - if (BTRFS_I(inode)->outstanding_extents == 0 && + if (inode->outstanding_extents == 0 && test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) drop_inode_space = 1; /* * If we have more or the same amount of outstanding extents than we have * reserved then we need to leave the reserved extents count alone. */ - if (BTRFS_I(inode)->outstanding_extents >= - BTRFS_I(inode)->reserved_extents) + if (inode->outstanding_extents >= inode->reserved_extents) return drop_inode_space; - dropped_extents = BTRFS_I(inode)->reserved_extents - - BTRFS_I(inode)->outstanding_extents; - BTRFS_I(inode)->reserved_extents -= dropped_extents; + dropped_extents = inode->reserved_extents - inode->outstanding_extents; + inode->reserved_extents -= dropped_extents; return dropped_extents + drop_inode_space; } @@ -5895,24 +5894,21 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes) * * This must be called with BTRFS_I(inode)->lock held. */ -static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes, +static u64 calc_csum_metadata_size(struct btrfs_inode *inode, u64 num_bytes, int reserve) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 old_csums, num_csums; - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM && - BTRFS_I(inode)->csum_bytes == 0) + if (inode->flags & BTRFS_INODE_NODATASUM && inode->csum_bytes == 0) return 0; - old_csums = btrfs_csum_bytes_to_leaves(fs_info, - BTRFS_I(inode)->csum_bytes); + old_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); if (reserve) - BTRFS_I(inode)->csum_bytes += num_bytes; + inode->csum_bytes += num_bytes; else - BTRFS_I(inode)->csum_bytes -= num_bytes; - num_csums = btrfs_csum_bytes_to_leaves(fs_info, - BTRFS_I(inode)->csum_bytes); + inode->csum_bytes -= num_bytes; + num_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); /* No change, no need to reserve more */ if (old_csums == num_csums) @@ -5925,10 +5921,10 @@ static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes, return btrfs_calc_trans_metadata_size(fs_info, old_csums - num_csums); } -int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) +int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct btrfs_block_rsv *block_rsv = &fs_info->delalloc_block_rsv; u64 to_reserve = 0; u64 csum_bytes; @@ -5960,25 +5956,24 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) schedule_timeout(1); if (delalloc_lock) - mutex_lock(&BTRFS_I(inode)->delalloc_mutex); + mutex_lock(&inode->delalloc_mutex); num_bytes = ALIGN(num_bytes, fs_info->sectorsize); - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); nr_extents = count_max_extents(num_bytes); - BTRFS_I(inode)->outstanding_extents += nr_extents; + inode->outstanding_extents += nr_extents; nr_extents = 0; - if (BTRFS_I(inode)->outstanding_extents > - BTRFS_I(inode)->reserved_extents) - nr_extents += BTRFS_I(inode)->outstanding_extents - - BTRFS_I(inode)->reserved_extents; + if (inode->outstanding_extents > inode->reserved_extents) + nr_extents += inode->outstanding_extents - + inode->reserved_extents; /* We always want to reserve a slot for updating the inode. */ to_reserve = btrfs_calc_trans_metadata_size(fs_info, nr_extents + 1); to_reserve += calc_csum_metadata_size(inode, num_bytes, 1); - csum_bytes = BTRFS_I(inode)->csum_bytes; - spin_unlock(&BTRFS_I(inode)->lock); + csum_bytes = inode->csum_bytes; + spin_unlock(&inode->lock); if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { ret = btrfs_qgroup_reserve_meta(root, @@ -5994,38 +5989,38 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) goto out_fail; } - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); if (test_and_set_bit(BTRFS_INODE_DELALLOC_META_RESERVED, - &BTRFS_I(inode)->runtime_flags)) { + &inode->runtime_flags)) { to_reserve -= btrfs_calc_trans_metadata_size(fs_info, 1); release_extra = true; } - BTRFS_I(inode)->reserved_extents += nr_extents; - spin_unlock(&BTRFS_I(inode)->lock); + inode->reserved_extents += nr_extents; + spin_unlock(&inode->lock); if (delalloc_lock) - mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); + mutex_unlock(&inode->delalloc_mutex); if (to_reserve) trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(BTRFS_I(inode)), to_reserve, 1); + btrfs_ino(inode), to_reserve, 1); if (release_extra) btrfs_block_rsv_release(fs_info, block_rsv, btrfs_calc_trans_metadata_size(fs_info, 1)); return 0; out_fail: - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); dropped = drop_outstanding_extent(inode, num_bytes); /* * If the inodes csum_bytes is the same as the original * csum_bytes then we know we haven't raced with any free()ers * so we can just reduce our inodes csum bytes and carry on. */ - if (BTRFS_I(inode)->csum_bytes == csum_bytes) { + if (inode->csum_bytes == csum_bytes) { calc_csum_metadata_size(inode, num_bytes, 0); } else { - u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes; + u64 orig_csum_bytes = inode->csum_bytes; u64 bytes; /* @@ -6036,8 +6031,8 @@ out_fail: * number of bytes that were freed while we were trying our * reservation. */ - bytes = csum_bytes - BTRFS_I(inode)->csum_bytes; - BTRFS_I(inode)->csum_bytes = csum_bytes; + bytes = csum_bytes - inode->csum_bytes; + inode->csum_bytes = csum_bytes; to_free = calc_csum_metadata_size(inode, bytes, 0); @@ -6046,7 +6041,7 @@ out_fail: * been making this reservation and our ->csum_bytes were not * artificially inflated. */ - BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes; + inode->csum_bytes = csum_bytes - num_bytes; bytes = csum_bytes - orig_csum_bytes; bytes = calc_csum_metadata_size(inode, bytes, 0); @@ -6058,23 +6053,23 @@ out_fail: * need to do anything, the other free-ers did the correct * thing. */ - BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes; + inode->csum_bytes = orig_csum_bytes - num_bytes; if (bytes > to_free) to_free = bytes - to_free; else to_free = 0; } - spin_unlock(&BTRFS_I(inode)->lock); + spin_unlock(&inode->lock); if (dropped) to_free += btrfs_calc_trans_metadata_size(fs_info, dropped); if (to_free) { btrfs_block_rsv_release(fs_info, block_rsv, to_free); trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(BTRFS_I(inode)), to_free, 0); + btrfs_ino(inode), to_free, 0); } if (delalloc_lock) - mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); + mutex_unlock(&inode->delalloc_mutex); return ret; } @@ -6087,27 +6082,27 @@ out_fail: * once we complete IO for a given set of bytes to release their metadata * reservations. */ -void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) +void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 to_free = 0; unsigned dropped; num_bytes = ALIGN(num_bytes, fs_info->sectorsize); - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); dropped = drop_outstanding_extent(inode, num_bytes); if (num_bytes) to_free = calc_csum_metadata_size(inode, num_bytes, 0); - spin_unlock(&BTRFS_I(inode)->lock); + spin_unlock(&inode->lock); if (dropped > 0) to_free += btrfs_calc_trans_metadata_size(fs_info, dropped); if (btrfs_is_testing(fs_info)) return; - trace_btrfs_space_reservation(fs_info, "delalloc", - btrfs_ino(BTRFS_I(inode)), to_free, 0); + trace_btrfs_space_reservation(fs_info, "delalloc", btrfs_ino(inode), + to_free, 0); btrfs_block_rsv_release(fs_info, &fs_info->delalloc_block_rsv, to_free); } @@ -6142,7 +6137,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) ret = btrfs_check_data_free_space(inode, start, len); if (ret < 0) return ret; - ret = btrfs_delalloc_reserve_metadata(inode, len); + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len); if (ret < 0) btrfs_free_reserved_data_space(inode, start, len); return ret; @@ -6165,7 +6160,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) */ void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) { - btrfs_delalloc_release_metadata(inode, len); + btrfs_delalloc_release_metadata(BTRFS_I(inode), len); btrfs_free_reserved_data_space(inode, start, len); } @@ -9741,6 +9736,11 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) } } +/* + * Must be called only after stopping all workers, since we could have block + * group caching kthreads running, and therefore they could race with us if we + * freed the block groups before stopping them. + */ int btrfs_free_block_groups(struct btrfs_fs_info *info) { struct btrfs_block_group_cache *block_group; @@ -9780,9 +9780,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) list_del(&block_group->list); up_write(&block_group->space_info->groups_sem); - if (block_group->cached == BTRFS_CACHE_STARTED) - wait_block_group_cache_done(block_group); - /* * We haven't cached this block group, which means we could * possibly have excluded extents on this block group. @@ -9792,6 +9789,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) free_excluded_extents(info, block_group); btrfs_remove_free_space_cache(block_group); + ASSERT(block_group->cached != BTRFS_CACHE_STARTED); ASSERT(list_empty(&block_group->dirty_list)); ASSERT(list_empty(&block_group->io_list)); ASSERT(list_empty(&block_group->bg_list)); @@ -10343,7 +10341,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, mutex_unlock(&trans->transaction->cache_write_mutex); if (!IS_ERR(inode)) { - ret = btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); goto out; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d15b5ddb6732..28e81922a21c 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -428,7 +428,8 @@ static void clear_state_cb(struct extent_io_tree *tree, struct extent_state *state, unsigned *bits) { if (tree->ops && tree->ops->clear_bit_hook) - tree->ops->clear_bit_hook(tree->mapping->host, state, bits); + tree->ops->clear_bit_hook(BTRFS_I(tree->mapping->host), + state, bits); } static void set_state_bits(struct extent_io_tree *tree, @@ -1959,11 +1960,11 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page) SetPageUptodate(page); } -int free_io_failure(struct inode *inode, struct io_failure_record *rec) +int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) { int ret; int err = 0; - struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; + struct extent_io_tree *failure_tree = &inode->io_failure_tree; set_state_failrec(failure_tree, rec->start, NULL); ret = clear_extent_bits(failure_tree, rec->start, @@ -1972,7 +1973,7 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec) if (ret) err = ret; - ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start, + ret = clear_extent_bits(&inode->io_tree, rec->start, rec->start + rec->len - 1, EXTENT_DAMAGED); if (ret && !err) @@ -1992,10 +1993,11 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec) * currently, there can be no more than two copies of every data bit. thus, * exactly one rewrite is required. */ -int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, - struct page *page, unsigned int pg_offset, int mirror_num) +int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, + u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num) { - struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio; struct btrfs_device *dev; u64 map_length = 0; @@ -2054,7 +2056,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", - btrfs_ino(BTRFS_I(inode)), start, + btrfs_ino(inode), start, rcu_str_deref(dev->name), sector); btrfs_bio_counter_dec(fs_info); bio_put(bio); @@ -2074,7 +2076,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, for (i = 0; i < num_pages; i++) { struct page *p = eb->pages[i]; - ret = repair_io_failure(fs_info->btree_inode, start, + ret = repair_io_failure(BTRFS_I(fs_info->btree_inode), start, PAGE_SIZE, start, p, start - page_offset(p), mirror_num); if (ret) @@ -2089,23 +2091,23 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, * each time an IO finishes, we do a fast check in the IO failure tree * to see if we need to process or clean up an io_failure_record */ -int clean_io_failure(struct inode *inode, u64 start, struct page *page, +int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page, unsigned int pg_offset) { u64 private; struct io_failure_record *failrec; - struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_state *state; int num_copies; int ret; private = 0; - ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private, + ret = count_range_bits(&inode->io_failure_tree, &private, (u64)-1, 1, EXTENT_DIRTY, 0); if (!ret) return 0; - ret = get_state_failrec(&BTRFS_I(inode)->io_failure_tree, start, + ret = get_state_failrec(&inode->io_failure_tree, start, &failrec); if (ret) return 0; @@ -2122,11 +2124,11 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page, if (fs_info->sb->s_flags & MS_RDONLY) goto out; - spin_lock(&BTRFS_I(inode)->io_tree.lock); - state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree, + spin_lock(&inode->io_tree.lock); + state = find_first_extent_bit_state(&inode->io_tree, failrec->start, EXTENT_LOCKED); - spin_unlock(&BTRFS_I(inode)->io_tree.lock); + spin_unlock(&inode->io_tree.lock); if (state && state->start <= failrec->start && state->end >= failrec->start + failrec->len - 1) { @@ -2151,9 +2153,9 @@ out: * - under ordered extent * - the inode is freeing */ -void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end) +void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end) { - struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; + struct extent_io_tree *failure_tree = &inode->io_failure_tree; struct io_failure_record *failrec; struct extent_state *state, *next; @@ -2393,7 +2395,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); return -EIO; } @@ -2406,7 +2408,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, (int)phy_offset, failed_bio->bi_end_io, NULL); if (!bio) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); return -EIO; } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); @@ -2418,7 +2420,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, failrec->bio_flags, 0); if (ret) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); bio_put(bio); } @@ -2435,12 +2437,9 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) tree = &BTRFS_I(page->mapping->host)->io_tree; - if (tree->ops && tree->ops->writepage_end_io_hook) { - ret = tree->ops->writepage_end_io_hook(page, start, - end, NULL, uptodate); - if (ret) - uptodate = 0; - } + if (tree->ops && tree->ops->writepage_end_io_hook) + tree->ops->writepage_end_io_hook(page, start, end, NULL, + uptodate); if (!uptodate) { ClearPageUptodate(page); @@ -2568,21 +2567,21 @@ static void end_bio_extent_readpage(struct bio *bio) len = bvec->bv_len; mirror = io_bio->mirror_num; - if (likely(uptodate && tree->ops && - tree->ops->readpage_end_io_hook)) { + if (likely(uptodate && tree->ops)) { ret = tree->ops->readpage_end_io_hook(io_bio, offset, page, start, end, mirror); if (ret) uptodate = 0; else - clean_io_failure(inode, start, page, 0); + clean_io_failure(BTRFS_I(inode), start, + page, 0); } if (likely(uptodate)) goto readpage_ok; - if (tree->ops && tree->ops->readpage_io_failed_hook) { + if (tree->ops) { ret = tree->ops->readpage_io_failed_hook(page, mirror); if (!ret && !bio->bi_error) uptodate = 1; @@ -2731,7 +2730,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num, bio->bi_private = NULL; bio_get(bio); - if (tree->ops && tree->ops->submit_bio_hook) + if (tree->ops) ret = tree->ops->submit_bio_hook(page->mapping->host, bio, mirror_num, bio_flags, start); else @@ -2746,7 +2745,7 @@ static int merge_bio(struct extent_io_tree *tree, struct page *page, unsigned long bio_flags) { int ret = 0; - if (tree->ops && tree->ops->merge_bio_hook) + if (tree->ops) ret = tree->ops->merge_bio_hook(page, offset, size, bio, bio_flags); return ret; @@ -2857,7 +2856,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset, *em_cached = NULL; } - em = get_extent(inode, page, pg_offset, start, len, 0); + em = get_extent(BTRFS_I(inode), page, pg_offset, start, len, 0); if (em_cached && !IS_ERR_OR_NULL(em)) { BUG_ON(*em_cached); atomic_inc(&em->refs); @@ -3101,7 +3100,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, inode = pages[0]->mapping->host; while (1) { lock_extent(tree, start, end); - ordered = btrfs_lookup_ordered_range(inode, start, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start, end - start + 1); if (!ordered) break; @@ -3173,7 +3172,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, while (1) { lock_extent(tree, start, end); - ordered = btrfs_lookup_ordered_range(inode, start, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start, PAGE_SIZE); if (!ordered) break; @@ -3370,7 +3369,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, page_end, NULL, 1); break; } - em = epd->get_extent(inode, page, pg_offset, cur, + em = epd->get_extent(BTRFS_I(inode), page, pg_offset, cur, end - cur + 1, 1); if (IS_ERR_OR_NULL(em)) { SetPageError(page); @@ -4335,7 +4334,7 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode, if (len == 0) break; len = ALIGN(len, sectorsize); - em = get_extent(inode, NULL, 0, offset, len, 0); + em = get_extent(BTRFS_I(inode), NULL, 0, offset, len, 0); if (IS_ERR_OR_NULL(em)) return em; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 270d03be290e..3e4fad4a909d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -84,6 +84,7 @@ extern void le_bitmap_clear(u8 *map, unsigned int start, int len); struct extent_state; struct btrfs_root; +struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; @@ -91,24 +92,34 @@ typedef int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset); struct extent_io_ops { - int (*fill_delalloc)(struct inode *inode, struct page *locked_page, - u64 start, u64 end, int *page_started, - unsigned long *nr_written); - int (*writepage_start_hook)(struct page *page, u64 start, u64 end); + /* + * The following callbacks must be allways defined, the function + * pointer will be called unconditionally. + */ extent_submit_bio_hook_t *submit_bio_hook; + int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset, + struct page *page, u64 start, u64 end, + int mirror); int (*merge_bio_hook)(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); - int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset, - struct page *page, u64 start, u64 end, - int mirror); - int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, + + /* + * Optional hooks, called if the pointer is not NULL + */ + int (*fill_delalloc)(struct inode *inode, struct page *locked_page, + u64 start, u64 end, int *page_started, + unsigned long *nr_written); + + int (*writepage_start_hook)(struct page *page, u64 start, u64 end); + void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); void (*set_bit_hook)(struct inode *inode, struct extent_state *state, unsigned *bits); - void (*clear_bit_hook)(struct inode *inode, struct extent_state *state, - unsigned *bits); + void (*clear_bit_hook)(struct btrfs_inode *inode, + struct extent_state *state, + unsigned *bits); void (*merge_extent_hook)(struct inode *inode, struct extent_state *new, struct extent_state *other); @@ -209,7 +220,7 @@ static inline int extent_compress_type(unsigned long bio_flags) struct extent_map_tree; -typedef struct extent_map *(get_extent_t)(struct inode *inode, +typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, @@ -451,12 +462,13 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs); struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask); struct btrfs_fs_info; +struct btrfs_inode; -int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, - struct page *page, unsigned int pg_offset, - int mirror_num); -int clean_io_failure(struct inode *inode, u64 start, struct page *page, - unsigned int pg_offset); +int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, + u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num); +int clean_io_failure(struct btrfs_inode *inode, u64 start, + struct page *page, unsigned int pg_offset); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); int repair_eb_io_failure(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int mirror_num); @@ -480,7 +492,9 @@ struct io_failure_record { int in_validation; }; -void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end); + +void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, + u64 end); int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, struct io_failure_record **failrec_ret); int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, @@ -489,7 +503,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, bio_end_io_t *endio_func, void *data); -int free_io_failure(struct inode *inode, struct io_failure_record *rec); +int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS noinline u64 find_lock_delalloc_range(struct inode *inode, struct extent_io_tree *tree, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index f7b9a92ad56d..64fcb31d7163 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -214,7 +214,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, * read from the commit root and sidestep a nasty deadlock * between reading the free space cache and updating the csum tree. */ - if (btrfs_is_free_space_inode(inode)) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) { path->search_commit_root = 1; path->skip_locking = 1; } @@ -643,7 +643,33 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, /* delete the entire item, it is inside our range */ if (key.offset >= bytenr && csum_end <= end_byte) { - ret = btrfs_del_item(trans, root, path); + int del_nr = 1; + + /* + * Check how many csum items preceding this one in this + * leaf correspond to our range and then delete them all + * at once. + */ + if (key.offset > bytenr && path->slots[0] > 0) { + int slot = path->slots[0] - 1; + + while (slot >= 0) { + struct btrfs_key pk; + + btrfs_item_key_to_cpu(leaf, &pk, slot); + if (pk.offset < bytenr || + pk.type != BTRFS_EXTENT_CSUM_KEY || + pk.objectid != + BTRFS_EXTENT_CSUM_OBJECTID) + break; + path->slots[0] = slot; + del_nr++; + key.offset = pk.offset; + slot--; + } + } + ret = btrfs_del_items(trans, root, path, + path->slots[0], del_nr); if (ret) goto out; if (key.offset == bytenr) @@ -904,14 +930,14 @@ fail_unlock: goto out; } -void btrfs_extent_item_to_extent_map(struct inode *inode, +void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, const struct btrfs_path *path, struct btrfs_file_extent_item *fi, const bool new_inline, struct extent_map *em) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct extent_buffer *leaf = path->nodes[0]; const int slot = path->slots[0]; struct btrfs_key key; @@ -976,8 +1002,8 @@ void btrfs_extent_item_to_extent_map(struct inode *inode, } } else { btrfs_err(fs_info, - "unknown file extent item type %d, inode %llu, offset %llu, root %llu", - type, btrfs_ino(BTRFS_I(inode)), extent_start, + "unknown file extent item type %d, inode %llu, offset %llu, " + "root %llu", type, btrfs_ino(inode), extent_start, root->root_key.objectid); } } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index c1d2a07205da..520cb7230b2d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -92,10 +92,10 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1, * If an existing record is found the defrag item you * pass in is freed */ -static int __btrfs_add_inode_defrag(struct inode *inode, +static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, struct inode_defrag *defrag) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); struct inode_defrag *entry; struct rb_node **p; struct rb_node *parent = NULL; @@ -123,7 +123,7 @@ static int __btrfs_add_inode_defrag(struct inode *inode, return -EEXIST; } } - set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags); rb_link_node(&defrag->rb_node, parent, p); rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes); return 0; @@ -145,10 +145,10 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) * enabled */ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct inode_defrag *defrag; u64 transid; int ret; @@ -156,24 +156,24 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, if (!__need_auto_defrag(fs_info)) return 0; - if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) + if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) return 0; if (trans) transid = trans->transid; else - transid = BTRFS_I(inode)->root->last_trans; + transid = inode->root->last_trans; defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS); if (!defrag) return -ENOMEM; - defrag->ino = btrfs_ino(BTRFS_I(inode)); + defrag->ino = btrfs_ino(inode); defrag->transid = transid; defrag->root = root->root_key.objectid; spin_lock(&fs_info->defrag_inodes_lock); - if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) { + if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) { /* * If we set IN_DEFRAG flag and evict the inode from memory, * and then re-read this inode, this new inode doesn't have @@ -194,10 +194,10 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, * the same inode in the tree, we will merge them together (by * __btrfs_add_inode_defrag()) and free the one that we want to requeue. */ -static void btrfs_requeue_inode_defrag(struct inode *inode, +static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode, struct inode_defrag *defrag) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); int ret; if (!__need_auto_defrag(fs_info)) @@ -334,7 +334,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, */ if (num_defrag == BTRFS_DEFRAG_BATCH) { defrag->last_offset = range.start; - btrfs_requeue_inode_defrag(inode, defrag); + btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); } else if (defrag->last_offset && !defrag->cycled) { /* * we didn't fill our defrag batch, but @@ -343,7 +343,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, */ defrag->last_offset = 0; defrag->cycled = 1; - btrfs_requeue_inode_defrag(inode, defrag); + btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); } else { kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } @@ -529,13 +529,13 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, * this drops all the extents in the cache that intersect the range * [start, end]. Existing extents are split as required. */ -void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, +void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, int skip_pinned) { struct extent_map *em; struct extent_map *split = NULL; struct extent_map *split2 = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; u64 len = end - start + 1; u64 gen; int ret; @@ -720,7 +720,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, int leafs_visited = 0; if (drop_cache) - btrfs_drop_extent_cache(inode, start, end - 1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0); if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent) modify_tree = 0; @@ -1082,10 +1082,10 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot, * two or three. */ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, - struct inode *inode, u64 start, u64 end) + struct btrfs_inode *inode, u64 start, u64 end) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_path *path; struct btrfs_file_extent_item *fi; @@ -1102,7 +1102,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int del_slot = 0; int recow; int ret; - u64 ino = btrfs_ino(BTRFS_I(inode)); + u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) @@ -1415,13 +1415,13 @@ fail: * the other < 0 number - Something wrong happens */ static noinline int -lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages, +lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, u64 *lockstart, u64 *lockend, struct extent_state **cached_state) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 start_pos; u64 last_pos; int i; @@ -1432,30 +1432,30 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages, + round_up(pos + write_bytes - start_pos, fs_info->sectorsize) - 1; - if (start_pos < inode->i_size) { + if (start_pos < inode->vfs_inode.i_size) { struct btrfs_ordered_extent *ordered; - lock_extent_bits(&BTRFS_I(inode)->io_tree, - start_pos, last_pos, cached_state); + lock_extent_bits(&inode->io_tree, start_pos, last_pos, + cached_state); ordered = btrfs_lookup_ordered_range(inode, start_pos, last_pos - start_pos + 1); if (ordered && ordered->file_offset + ordered->len > start_pos && ordered->file_offset <= last_pos) { - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - start_pos, last_pos, - cached_state, GFP_NOFS); + unlock_extent_cached(&inode->io_tree, start_pos, + last_pos, cached_state, GFP_NOFS); for (i = 0; i < num_pages; i++) { unlock_page(pages[i]); put_page(pages[i]); } - btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_start_ordered_extent(&inode->vfs_inode, + ordered, 1); btrfs_put_ordered_extent(ordered); return -EAGAIN; } if (ordered) btrfs_put_ordered_extent(ordered); - clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, + clear_extent_bit(&inode->io_tree, start_pos, last_pos, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached_state, GFP_NOFS); @@ -1474,11 +1474,11 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct inode *inode, loff_t pos, +static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, size_t *write_bytes) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct btrfs_ordered_extent *ordered; u64 lockstart, lockend; u64 num_bytes; @@ -1493,19 +1493,20 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos, fs_info->sectorsize) - 1; while (1) { - lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend); + lock_extent(&inode->io_tree, lockstart, lockend); ordered = btrfs_lookup_ordered_range(inode, lockstart, lockend - lockstart + 1); if (!ordered) { break; } - unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend); - btrfs_start_ordered_extent(inode, ordered, 1); + unlock_extent(&inode->io_tree, lockstart, lockend); + btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } num_bytes = lockend - lockstart + 1; - ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL); + ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, + NULL, NULL, NULL); if (ret <= 0) { ret = 0; btrfs_end_write_no_snapshoting(root); @@ -1514,7 +1515,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos, num_bytes - pos + lockstart); } - unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend); + unlock_extent(&inode->io_tree, lockstart, lockend); return ret; } @@ -1579,7 +1580,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && - check_can_nocow(inode, pos, &write_bytes) > 0) { + check_can_nocow(BTRFS_I(inode), pos, + &write_bytes) > 0) { /* * For nodata cow case, no need to reserve * data space. @@ -1599,7 +1601,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, } } - ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes); + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), + reserve_bytes); if (ret) { if (!only_release_metadata) btrfs_free_reserved_data_space(inode, pos, @@ -1623,9 +1626,9 @@ again: if (ret) break; - ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages, - pos, write_bytes, &lockstart, - &lockend, &cached_state); + ret = lock_and_cleanup_extent_if_need(BTRFS_I(inode), pages, + num_pages, pos, write_bytes, &lockstart, + &lockend, &cached_state); if (ret < 0) { if (ret == -EAGAIN) goto again; @@ -1677,7 +1680,7 @@ again: spin_unlock(&BTRFS_I(inode)->lock); } if (only_release_metadata) { - btrfs_delalloc_release_metadata(inode, + btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes); } else { u64 __pos; @@ -1738,7 +1741,8 @@ again: if (release_bytes) { if (only_release_metadata) { btrfs_end_write_no_snapshoting(root); - btrfs_delalloc_release_metadata(inode, release_bytes); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + release_bytes); } else { btrfs_delalloc_release_space(inode, round_down(pos, fs_info->sectorsize), @@ -2193,7 +2197,7 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) return 0; } -static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf, +static int hole_mergeable(struct btrfs_inode *inode, struct extent_buffer *leaf, int slot, u64 start, u64 end) { struct btrfs_file_extent_item *fi; @@ -2203,7 +2207,7 @@ static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf, return 0; btrfs_item_key_to_cpu(leaf, &key, slot); - if (key.objectid != btrfs_ino(BTRFS_I(inode)) || + if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY) return 0; @@ -2222,22 +2226,23 @@ static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf, return 0; } -static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, - struct btrfs_path *path, u64 offset, u64 end) +static int fill_holes(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct btrfs_path *path, u64 offset, u64 end) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; struct extent_map *hole_em; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; struct btrfs_key key; int ret; if (btrfs_fs_incompat(fs_info, NO_HOLES)) goto out; - key.objectid = btrfs_ino(BTRFS_I(inode)); + key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = offset; @@ -2253,7 +2258,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, } leaf = path->nodes[0]; - if (hole_mergeable(inode, leaf, path->slots[0]-1, offset, end)) { + if (hole_mergeable(inode, leaf, path->slots[0] - 1, offset, end)) { u64 num_bytes; path->slots[0]--; @@ -2285,7 +2290,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode, } btrfs_release_path(path); - ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)), + ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0); if (ret) return ret; @@ -2296,8 +2301,7 @@ out: hole_em = alloc_extent_map(); if (!hole_em) { btrfs_drop_extent_cache(inode, offset, end - 1, 0); - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); } else { hole_em->start = offset; hole_em->len = end - offset; @@ -2320,7 +2324,7 @@ out: free_extent_map(hole_em); if (ret) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); } return 0; @@ -2337,7 +2341,7 @@ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) struct extent_map *em; int ret = 0; - em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, *start, *len, 0); if (IS_ERR_OR_NULL(em)) { if (!em) ret = -ENOMEM; @@ -2550,8 +2554,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) trans->block_rsv = &fs_info->trans_block_rsv; if (cur_offset < drop_end && cur_offset < ino_size) { - ret = fill_holes(trans, inode, path, cur_offset, - drop_end); + ret = fill_holes(trans, BTRFS_I(inode), path, + cur_offset, drop_end); if (ret) { /* * If we failed then we didn't insert our hole @@ -2622,7 +2626,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) * cur_offset == drop_end). */ if (cur_offset < ino_size && cur_offset < drop_end) { - ret = fill_holes(trans, inode, path, cur_offset, drop_end); + ret = fill_holes(trans, BTRFS_I(inode), path, + cur_offset, drop_end); if (ret) { /* Same comment as above. */ btrfs_abort_transaction(trans, ret); @@ -2747,7 +2752,8 @@ static long btrfs_fallocate(struct file *file, int mode, * * For qgroup space, it will be checked later. */ - ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start); + ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), + alloc_end - alloc_start); if (ret < 0) return ret; @@ -2827,7 +2833,7 @@ static long btrfs_fallocate(struct file *file, int mode, /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); while (1) { - em = btrfs_get_extent(inode, NULL, 0, cur_offset, + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset, alloc_end - cur_offset, 0); if (IS_ERR_OR_NULL(em)) { if (!em) @@ -2954,7 +2960,8 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence) &cached_state); while (start < inode->i_size) { - em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0); + em = btrfs_get_extent_fiemap(BTRFS_I(inode), NULL, 0, + start, len, 0); if (IS_ERR(em)) { ret = PTR_ERR(em); em = NULL; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 493a654b6012..da6841efac26 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -261,7 +261,7 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, btrfs_free_path(path); } - btrfs_i_size_write(inode, 0); + btrfs_i_size_write(BTRFS_I(inode), 0); truncate_pagecache(inode, 0); /* @@ -3546,7 +3546,8 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root, if (ret) { if (release_metadata) - btrfs_delalloc_release_metadata(inode, inode->i_size); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + inode->i_size); #ifdef DEBUG btrfs_err(fs_info, "failed to write free ino cache for root %llu", diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 3bbb8f095953..5c6c20ec64d8 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -499,7 +499,7 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_metadata(inode, prealloc); + btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc); goto out_put; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f02823f088c2..ee6978d80491 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -316,8 +316,8 @@ static noinline int cow_file_range_inline(struct btrfs_root *root, } set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); - btrfs_delalloc_release_metadata(inode, end + 1 - start); - btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); + btrfs_delalloc_release_metadata(BTRFS_I(inode), end + 1 - start); + btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0); out: /* * Don't forget to free the reserved space, as for inlined extent @@ -389,12 +389,12 @@ static inline int inode_need_compress(struct inode *inode) return 0; } -static inline void inode_should_defrag(struct inode *inode, +static inline void inode_should_defrag(struct btrfs_inode *inode, u64 start, u64 end, u64 num_bytes, u64 small_write) { /* If this is a small write inside eof, kick off a defrag */ if (num_bytes < small_write && - (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) + (start > 0 || end + 1 < inode->disk_i_size)) btrfs_add_inode_defrag(NULL, inode); } @@ -430,23 +430,23 @@ static noinline void compress_file_range(struct inode *inode, int ret = 0; struct page **pages = NULL; unsigned long nr_pages; - unsigned long nr_pages_ret = 0; unsigned long total_compressed = 0; unsigned long total_in = 0; - unsigned long max_compressed = SZ_128K; - unsigned long max_uncompressed = SZ_128K; int i; int will_compress; int compress_type = fs_info->compress_type; int redirty = 0; - inode_should_defrag(inode, start, end, end - start + 1, SZ_16K); + inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1, + SZ_16K); actual_end = min_t(u64, isize, end + 1); again: will_compress = 0; nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1; - nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE); + BUILD_BUG_ON((BTRFS_MAX_COMPRESSED % PAGE_SIZE) != 0); + nr_pages = min_t(unsigned long, nr_pages, + BTRFS_MAX_COMPRESSED / PAGE_SIZE); /* * we don't want to send crud past the end of i_size through @@ -471,17 +471,8 @@ again: (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) goto cleanup_and_bail_uncompressed; - /* we want to make sure that amount of ram required to uncompress - * an extent is reasonable, so we limit the total size in ram - * of a compressed extent to 128k. This is a crucial number - * because it also controls how easily we can spread reads across - * cpus for decompression. - * - * We also want to make sure the amount of IO required to do - * a random read is reasonably small, so we limit the size of - * a compressed extent to 128k. - */ - total_compressed = min(total_compressed, max_uncompressed); + total_compressed = min_t(unsigned long, total_compressed, + BTRFS_MAX_UNCOMPRESSED); num_bytes = ALIGN(end - start + 1, blocksize); num_bytes = max(blocksize, num_bytes); total_in = 0; @@ -516,16 +507,15 @@ again: redirty = 1; ret = btrfs_compress_pages(compress_type, inode->i_mapping, start, - total_compressed, pages, - nr_pages, &nr_pages_ret, + pages, + &nr_pages, &total_in, - &total_compressed, - max_compressed); + &total_compressed); if (!ret) { unsigned long offset = total_compressed & (PAGE_SIZE - 1); - struct page *page = pages[nr_pages_ret - 1]; + struct page *page = pages[nr_pages - 1]; char *kaddr; /* zero the tail end of the last page, we might be @@ -606,7 +596,7 @@ cont: * will submit them to the elevator. */ add_async_extent(async_cow, start, num_bytes, - total_compressed, pages, nr_pages_ret, + total_compressed, pages, nr_pages, compress_type); if (start + num_bytes < end) { @@ -623,14 +613,14 @@ cont: * the compression code ran but failed to make things smaller, * free any pages it allocated and our page pointer array */ - for (i = 0; i < nr_pages_ret; i++) { + for (i = 0; i < nr_pages; i++) { WARN_ON(pages[i]->mapping); put_page(pages[i]); } kfree(pages); pages = NULL; total_compressed = 0; - nr_pages_ret = 0; + nr_pages = 0; /* flag the file so we don't compress in the future */ if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) && @@ -659,7 +649,7 @@ cleanup_and_bail_uncompressed: return; free_pages_out: - for (i = 0; i < nr_pages_ret; i++) { + for (i = 0; i < nr_pages; i++) { WARN_ON(pages[i]->mapping); put_page(pages[i]); } @@ -806,7 +796,8 @@ retry: BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); if (ret) { - btrfs_drop_extent_cache(inode, async_extent->start, + btrfs_drop_extent_cache(BTRFS_I(inode), + async_extent->start, async_extent->start + async_extent->ram_size - 1, 0); goto out_free_reserve; @@ -933,7 +924,7 @@ static noinline int cow_file_range(struct inode *inode, struct extent_map *em; int ret = 0; - if (btrfs_is_free_space_inode(inode)) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) { WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; @@ -943,7 +934,7 @@ static noinline int cow_file_range(struct inode *inode, num_bytes = max(blocksize, num_bytes); disk_num_bytes = num_bytes; - inode_should_defrag(inode, start, end, num_bytes, SZ_64K); + inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K); if (start == 0) { /* lets try to make an inline extent */ @@ -971,7 +962,8 @@ static noinline int cow_file_range(struct inode *inode, btrfs_super_total_bytes(fs_info->super_copy)); alloc_hint = get_extent_allocation_hint(inode, start, num_bytes); - btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), start, + start + num_bytes - 1, 0); while (disk_num_bytes > 0) { unsigned long op; @@ -1039,7 +1031,7 @@ out: return ret; out_drop_extent_cache: - btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0); out_reserve: btrfs_dec_block_group_reservations(fs_info, ins.objectid); btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1); @@ -1231,7 +1223,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, return -ENOMEM; } - nolock = btrfs_is_free_space_inode(inode); + nolock = btrfs_is_free_space_inode(BTRFS_I(inode)); cow_start = (u64)-1; cur_offset = start; @@ -1331,10 +1323,16 @@ next_slot: * either valid or do not exist. */ if (csum_exist_in_range(fs_info, disk_bytenr, - num_bytes)) + num_bytes)) { + if (!nolock) + btrfs_end_write_no_snapshoting(root); goto out_check; - if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) + } + if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) { + if (!nolock) + btrfs_end_write_no_snapshoting(root); goto out_check; + } nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1629,15 +1627,15 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root, } static void btrfs_del_delalloc_inode(struct btrfs_root *root, - struct inode *inode) + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); spin_lock(&root->delalloc_lock); - if (!list_empty(&BTRFS_I(inode)->delalloc_inodes)) { - list_del_init(&BTRFS_I(inode)->delalloc_inodes); + if (!list_empty(&inode->delalloc_inodes)) { + list_del_init(&inode->delalloc_inodes); clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); root->nr_delalloc_inodes--; if (!root->nr_delalloc_inodes) { spin_lock(&fs_info->delalloc_root_lock); @@ -1670,7 +1668,7 @@ static void btrfs_set_bit_hook(struct inode *inode, if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) { struct btrfs_root *root = BTRFS_I(inode)->root; u64 len = state->end + 1 - state->start; - bool do_list = !btrfs_is_free_space_inode(inode); + bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode)); if (*bits & EXTENT_FIRST_DELALLOC) { *bits &= ~EXTENT_FIRST_DELALLOC; @@ -1700,18 +1698,18 @@ static void btrfs_set_bit_hook(struct inode *inode, /* * extent_io.c clear_bit_hook, see set_bit_hook for why */ -static void btrfs_clear_bit_hook(struct inode *inode, +static void btrfs_clear_bit_hook(struct btrfs_inode *inode, struct extent_state *state, unsigned *bits) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 len = state->end + 1 - state->start; u32 num_extents = count_max_extents(len); - spin_lock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) - BTRFS_I(inode)->defrag_bytes -= len; - spin_unlock(&BTRFS_I(inode)->lock); + inode->defrag_bytes -= len; + spin_unlock(&inode->lock); /* * set_bit and clear bit hooks normally require _irqsave/restore @@ -1719,15 +1717,15 @@ static void btrfs_clear_bit_hook(struct inode *inode, * bit, which is only set or cleared with irqs on */ if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; bool do_list = !btrfs_is_free_space_inode(inode); if (*bits & EXTENT_FIRST_DELALLOC) { *bits &= ~EXTENT_FIRST_DELALLOC; } else if (!(*bits & EXTENT_DO_ACCOUNTING)) { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents -= num_extents; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->outstanding_extents -= num_extents; + spin_unlock(&inode->lock); } /* @@ -1747,18 +1745,19 @@ static void btrfs_clear_bit_hook(struct inode *inode, && do_list && !(state->state & EXTENT_NORESERVE) && (*bits & (EXTENT_DO_ACCOUNTING | EXTENT_CLEAR_DATA_RESV))) - btrfs_free_reserved_data_space_noquota(inode, + btrfs_free_reserved_data_space_noquota( + &inode->vfs_inode, state->start, len); __percpu_counter_add(&fs_info->delalloc_bytes, -len, fs_info->delalloc_batch); - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->delalloc_bytes -= len; - if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 && + spin_lock(&inode->lock); + inode->delalloc_bytes -= len; + if (do_list && inode->delalloc_bytes == 0 && test_bit(BTRFS_INODE_IN_DELALLOC_LIST, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) btrfs_del_delalloc_inode(root, inode); - spin_unlock(&BTRFS_I(inode)->lock); + spin_unlock(&inode->lock); } } @@ -1854,7 +1853,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; - if (btrfs_is_free_space_inode(inode)) + if (btrfs_is_free_space_inode(BTRFS_I(inode))) metadata = BTRFS_WQ_ENDIO_FREE_SPACE; if (bio_op(bio) != REQ_OP_WRITE) { @@ -1963,7 +1962,7 @@ again: if (PagePrivate2(page)) goto out; - ordered = btrfs_lookup_ordered_range(inode, page_start, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, PAGE_SIZE); if (ordered) { unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, @@ -2793,16 +2792,17 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) bool nolock; bool truncated = false; - nolock = btrfs_is_free_space_inode(inode); + nolock = btrfs_is_free_space_inode(BTRFS_I(inode)); if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) { ret = -EIO; goto out; } - btrfs_free_io_failure_record(inode, ordered_extent->file_offset, - ordered_extent->file_offset + - ordered_extent->len - 1); + btrfs_free_io_failure_record(BTRFS_I(inode), + ordered_extent->file_offset, + ordered_extent->file_offset + + ordered_extent->len - 1); if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { truncated = true; @@ -2873,7 +2873,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { BUG_ON(compress_type); - ret = btrfs_mark_extent_written(trans, inode, + ret = btrfs_mark_extent_written(trans, BTRFS_I(inode), ordered_extent->file_offset, ordered_extent->file_offset + logical_len); @@ -2914,7 +2914,8 @@ out_unlock: ordered_extent->len - 1, &cached_state, GFP_NOFS); out: if (root != fs_info->tree_root) - btrfs_delalloc_release_metadata(inode, ordered_extent->len); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + ordered_extent->len); if (trans) btrfs_end_transaction(trans); @@ -2929,7 +2930,7 @@ out: clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS); /* Drop the cache for the part of the extent we didn't write. */ - btrfs_drop_extent_cache(inode, start, end, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0); /* * If the ordered extent had an IOERR or something else went @@ -2977,7 +2978,7 @@ static void finish_ordered_fn(struct btrfs_work *work) btrfs_finish_ordered_io(ordered_extent); } -static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, +static void btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate) { struct inode *inode = page->mapping->host; @@ -2991,9 +2992,9 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, ClearPagePrivate2(page); if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start, end - start + 1, uptodate)) - return 0; + return; - if (btrfs_is_free_space_inode(inode)) { + if (btrfs_is_free_space_inode(BTRFS_I(inode))) { wq = fs_info->endio_freespace_worker; func = btrfs_freespace_write_helper; } else { @@ -3004,8 +3005,6 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered_extent->work); - - return 0; } static int __readpage_endio_check(struct inode *inode, @@ -3028,7 +3027,7 @@ static int __readpage_endio_check(struct inode *inode, kunmap_atomic(kaddr); return 0; zeroit: - btrfs_print_data_csum_error(inode, start, csum, csum_expected, + btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, io_bio->mirror_num); memset(kaddr + pgoff, 1, len); flush_dcache_page(page); @@ -3167,10 +3166,11 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, * NOTE: caller of this function should reserve 5 units of metadata for * this function. */ -int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) +int btrfs_orphan_add(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); + struct btrfs_root *root = inode->root; struct btrfs_block_rsv *block_rsv = NULL; int reserve = 0; int insert = 0; @@ -3192,7 +3192,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) } if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags)) { + &inode->runtime_flags)) { #if 0 /* * For proper ENOSPC handling, we should do orphan @@ -3209,7 +3209,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) } if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) reserve = 1; spin_unlock(&root->orphan_lock); @@ -3220,28 +3220,27 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) if (ret) { atomic_dec(&root->orphan_inodes); clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); if (insert) clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); return ret; } } /* insert an orphan item to track this unlinked/truncated file */ if (insert >= 1) { - ret = btrfs_insert_orphan_item(trans, root, - btrfs_ino(BTRFS_I(inode))); + ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { atomic_dec(&root->orphan_inodes); if (reserve) { clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); btrfs_orphan_release_metadata(inode); } if (ret != -EEXIST) { clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); btrfs_abort_transaction(trans, ret); return ret; } @@ -3266,20 +3265,20 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) * item for this particular inode. */ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, - struct inode *inode) + struct btrfs_inode *inode) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; int delete_item = 0; int release_rsv = 0; int ret = 0; spin_lock(&root->orphan_lock); if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) delete_item = 1; if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &BTRFS_I(inode)->runtime_flags)) + &inode->runtime_flags)) release_rsv = 1; spin_unlock(&root->orphan_lock); @@ -3287,7 +3286,7 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, atomic_dec(&root->orphan_inodes); if (trans) ret = btrfs_del_orphan_item(trans, root, - btrfs_ino(BTRFS_I(inode))); + btrfs_ino(inode)); } if (release_rsv) @@ -3453,7 +3452,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) ret = PTR_ERR(trans); goto out; } - ret = btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); btrfs_end_transaction(trans); if (ret) { iput(inode); @@ -3462,7 +3461,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) ret = btrfs_truncate(inode); if (ret) - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); } else { nr_unlink++; } @@ -3617,7 +3616,7 @@ static int btrfs_read_locked_inode(struct inode *inode) set_nlink(inode, btrfs_inode_nlink(leaf, inode_item)); i_uid_write(inode, btrfs_inode_uid(leaf, inode_item)); i_gid_write(inode, btrfs_inode_gid(leaf, inode_item)); - btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); + btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item)); inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime); inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime); @@ -3865,7 +3864,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * The data relocation inode should also be directly updated * without delay */ - if (!btrfs_is_free_space_inode(inode) + if (!btrfs_is_free_space_inode(BTRFS_I(inode)) && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) { btrfs_update_root_times(trans, root); @@ -3988,8 +3987,7 @@ err: if (ret) goto out; - btrfs_i_size_write(&dir->vfs_inode, - dir->vfs_inode.i_size - name_len * 2); + btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2); inode_inc_iversion(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime = @@ -4056,7 +4054,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) goto out; if (inode->i_nlink == 0) { - ret = btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) goto out; } @@ -4137,7 +4135,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, goto out; } - btrfs_i_size_write(dir, dir->i_size - name_len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2); inode_inc_iversion(dir); dir->i_mtime = dir->i_ctime = current_time(dir); ret = btrfs_update_inode_fallback(trans, root, dir); @@ -4173,7 +4171,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) goto out; } - err = btrfs_orphan_add(trans, inode); + err = btrfs_orphan_add(trans, BTRFS_I(inode)); if (err) goto out; @@ -4184,7 +4182,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) BTRFS_I(d_inode(dentry)), dentry->d_name.name, dentry->d_name.len); if (!err) { - btrfs_i_size_write(inode, 0); + btrfs_i_size_write(BTRFS_I(inode), 0); /* * Propagate the last_unlink_trans value of the deleted dir to * its parent directory. This is to prevent an unrecoverable @@ -4320,7 +4318,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, * for non-free space inodes and ref cows, we want to back off from * time to time */ - if (!btrfs_is_free_space_inode(inode) && + if (!btrfs_is_free_space_inode(BTRFS_I(inode)) && test_bit(BTRFS_ROOT_REF_COWS, &root->state)) be_nice = 1; @@ -4336,7 +4334,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, */ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) || root == fs_info->tree_root) - btrfs_drop_extent_cache(inode, ALIGN(new_size, + btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size, fs_info->sectorsize), (u64)-1, 0); @@ -4412,19 +4410,8 @@ search_again: if (found_type > min_type) { del_item = 1; } else { - if (item_end < new_size) { - /* - * With NO_HOLES mode, for the following mapping - * - * [0-4k][hole][8k-12k] - * - * if truncating isize down to 6k, it ends up - * isize being 8k. - */ - if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) - last_size = new_size; + if (item_end < new_size) break; - } if (found_key.offset >= new_size) del_item = 1; else @@ -4607,8 +4594,12 @@ out: btrfs_abort_transaction(trans, ret); } error: - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + ASSERT(last_size >= new_size); + if (!err && last_size > new_size) + last_size = new_size; btrfs_ordered_update_i_size(inode, last_size, NULL); + } btrfs_free_path(path); @@ -4835,7 +4826,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) lock_extent_bits(io_tree, hole_start, block_end - 1, &cached_state); - ordered = btrfs_lookup_ordered_range(inode, hole_start, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), hole_start, block_end - hole_start); if (!ordered) break; @@ -4847,7 +4838,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) cur_offset = hole_start; while (1) { - em = btrfs_get_extent(inode, NULL, 0, cur_offset, + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset, block_end - cur_offset, 0); if (IS_ERR(em)) { err = PTR_ERR(em); @@ -4864,7 +4855,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) hole_size); if (err) break; - btrfs_drop_extent_cache(inode, cur_offset, + btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset, cur_offset + hole_size - 1, 0); hole_em = alloc_extent_map(); if (!hole_em) { @@ -4890,7 +4881,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) write_unlock(&em_tree->lock); if (err != -EEXIST) break; - btrfs_drop_extent_cache(inode, cur_offset, + btrfs_drop_extent_cache(BTRFS_I(inode), + cur_offset, cur_offset + hole_size - 1, 0); } @@ -4987,7 +4979,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) * so we need to guarantee from this point on that everything * will be consistent. */ - ret = btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); btrfs_end_transaction(trans); if (ret) return ret; @@ -4996,9 +4988,9 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) truncate_setsize(inode, newsize); /* Disable nonlocked read DIO to avoid the end less truncate */ - btrfs_inode_block_unlocked_dio(inode); + btrfs_inode_block_unlocked_dio(BTRFS_I(inode)); inode_dio_wait(inode); - btrfs_inode_resume_unlocked_dio(inode); + btrfs_inode_resume_unlocked_dio(BTRFS_I(inode)); ret = btrfs_truncate(inode); if (ret && inode->i_nlink) { @@ -5007,7 +4999,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) /* To get a stable disk_i_size */ err = btrfs_wait_ordered_range(inode, 0, (u64)-1); if (err) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); return err; } @@ -5019,11 +5011,11 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) */ trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); return ret; } i_size_write(inode, BTRFS_I(inode)->disk_i_size); - err = btrfs_orphan_del(trans, inode); + err = btrfs_orphan_del(trans, BTRFS_I(inode)); if (err) btrfs_abort_transaction(trans, err); btrfs_end_transaction(trans); @@ -5181,18 +5173,18 @@ void btrfs_evict_inode(struct inode *inode) if (inode->i_nlink && ((btrfs_root_refs(&root->root_item) != 0 && root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) || - btrfs_is_free_space_inode(inode))) + btrfs_is_free_space_inode(BTRFS_I(inode)))) goto no_delete; if (is_bad_inode(inode)) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); goto no_delete; } /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ if (!special_file(inode->i_mode)) btrfs_wait_ordered_range(inode, 0, (u64)-1); - btrfs_free_io_failure_record(inode, 0, (u64)-1); + btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1); if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) { BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, @@ -5208,20 +5200,20 @@ void btrfs_evict_inode(struct inode *inode) ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode)); if (ret) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); goto no_delete; } rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP); if (!rsv) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); goto no_delete; } rsv->size = min_size; rsv->failfast = 1; global_rsv = &fs_info->global_block_rsv; - btrfs_i_size_write(inode, 0); + btrfs_i_size_write(BTRFS_I(inode), 0); /* * This is a bit simpler than btrfs_truncate since we've already @@ -5256,14 +5248,14 @@ void btrfs_evict_inode(struct inode *inode) btrfs_warn(fs_info, "Could not get space for a delete, will truncate on mount %d", ret); - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); btrfs_free_block_rsv(fs_info, rsv); goto no_delete; } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); btrfs_free_block_rsv(fs_info, rsv); goto no_delete; } @@ -5289,7 +5281,7 @@ void btrfs_evict_inode(struct inode *inode) if (ret) { ret = btrfs_commit_transaction(trans); if (ret) { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); btrfs_free_block_rsv(fs_info, rsv); goto no_delete; } @@ -5318,9 +5310,9 @@ void btrfs_evict_inode(struct inode *inode) */ if (ret == 0) { trans->block_rsv = root->orphan_block_rsv; - btrfs_orphan_del(trans, inode); + btrfs_orphan_del(trans, BTRFS_I(inode)); } else { - btrfs_orphan_del(NULL, inode); + btrfs_orphan_del(NULL, BTRFS_I(inode)); } trans->block_rsv = &fs_info->trans_block_rsv; @@ -5898,7 +5890,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags)) return 0; - if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(inode)) + if (btrfs_fs_closing(root->fs_info) && + btrfs_is_free_space_inode(BTRFS_I(inode))) nolock = true; if (wbc->sync_mode == WB_SYNC_ALL) { @@ -5978,15 +5971,15 @@ static int btrfs_update_time(struct inode *inode, struct timespec *now, * and then set the in-memory index_cnt variable to reflect * free sequence numbers */ -static int btrfs_set_inode_index_count(struct inode *inode) +static int btrfs_set_inode_index_count(struct btrfs_inode *inode) { - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; struct btrfs_key key, found_key; struct btrfs_path *path; struct extent_buffer *leaf; int ret; - key.objectid = btrfs_ino(BTRFS_I(inode)); + key.objectid = btrfs_ino(inode); key.type = BTRFS_DIR_INDEX_KEY; key.offset = (u64)-1; @@ -6009,7 +6002,7 @@ static int btrfs_set_inode_index_count(struct inode *inode) * else has to start at 2 */ if (path->slots[0] == 0) { - BTRFS_I(inode)->index_cnt = 2; + inode->index_cnt = 2; goto out; } @@ -6018,13 +6011,13 @@ static int btrfs_set_inode_index_count(struct inode *inode) leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) || + if (found_key.objectid != btrfs_ino(inode) || found_key.type != BTRFS_DIR_INDEX_KEY) { - BTRFS_I(inode)->index_cnt = 2; + inode->index_cnt = 2; goto out; } - BTRFS_I(inode)->index_cnt = found_key.offset + 1; + inode->index_cnt = found_key.offset + 1; out: btrfs_free_path(path); return ret; @@ -6034,12 +6027,12 @@ out: * helper to find a free sequence number in a given directory. This current * code is very simple, later versions will do smarter things in the btree */ -int btrfs_set_inode_index(struct inode *dir, u64 *index) +int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index) { int ret = 0; - if (BTRFS_I(dir)->index_cnt == (u64)-1) { - ret = btrfs_inode_delayed_dir_index_count(BTRFS_I(dir)); + if (dir->index_cnt == (u64)-1) { + ret = btrfs_inode_delayed_dir_index_count(dir); if (ret) { ret = btrfs_set_inode_index_count(dir); if (ret) @@ -6047,8 +6040,8 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index) } } - *index = BTRFS_I(dir)->index_cnt; - BTRFS_I(dir)->index_cnt++; + *index = dir->index_cnt; + dir->index_cnt++; return ret; } @@ -6109,7 +6102,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, if (dir && name) { trace_btrfs_inode_request(dir); - ret = btrfs_set_inode_index(dir, index); + ret = btrfs_set_inode_index(BTRFS_I(dir), index); if (ret) { btrfs_free_path(path); iput(inode); @@ -6244,18 +6237,18 @@ static inline u8 btrfs_inode_type(struct inode *inode) * inode to the parent directory. */ int btrfs_add_link(struct btrfs_trans_handle *trans, - struct inode *parent_inode, struct inode *inode, + struct btrfs_inode *parent_inode, struct btrfs_inode *inode, const char *name, int name_len, int add_backref, u64 index) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); int ret = 0; struct btrfs_key key; - struct btrfs_root *root = BTRFS_I(parent_inode)->root; - u64 ino = btrfs_ino(BTRFS_I(inode)); - u64 parent_ino = btrfs_ino(BTRFS_I(parent_inode)); + struct btrfs_root *root = parent_inode->root; + u64 ino = btrfs_ino(inode); + u64 parent_ino = btrfs_ino(parent_inode); if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) { - memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key)); + memcpy(&key, &inode->root->root_key, sizeof(key)); } else { key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; @@ -6277,7 +6270,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, ret = btrfs_insert_dir_item(trans, root, name, name_len, parent_inode, &key, - btrfs_inode_type(inode), index); + btrfs_inode_type(&inode->vfs_inode), index); if (ret == -EEXIST || ret == -EOVERFLOW) goto fail_dir_item; else if (ret) { @@ -6285,12 +6278,12 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, return ret; } - btrfs_i_size_write(parent_inode, parent_inode->i_size + + btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + name_len * 2); - inode_inc_iversion(parent_inode); - parent_inode->i_mtime = parent_inode->i_ctime = - current_time(parent_inode); - ret = btrfs_update_inode(trans, root, parent_inode); + inode_inc_iversion(&parent_inode->vfs_inode); + parent_inode->vfs_inode.i_mtime = parent_inode->vfs_inode.i_ctime = + current_time(&parent_inode->vfs_inode); + ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode); if (ret) btrfs_abort_transaction(trans, ret); return ret; @@ -6314,8 +6307,8 @@ fail_dir_item: } static int btrfs_add_nondir(struct btrfs_trans_handle *trans, - struct inode *dir, struct dentry *dentry, - struct inode *inode, int backref, u64 index) + struct btrfs_inode *dir, struct dentry *dentry, + struct btrfs_inode *inode, int backref, u64 index) { int err = btrfs_add_link(trans, dir, inode, dentry->d_name.name, dentry->d_name.len, @@ -6371,7 +6364,8 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (err) goto out_unlock_inode; - err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), + 0, index); if (err) { goto out_unlock_inode; } else { @@ -6448,7 +6442,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (err) goto out_unlock_inode; - err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), + 0, index); if (err) goto out_unlock_inode; @@ -6490,7 +6485,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink >= BTRFS_LINK_MAX) return -EMLINK; - err = btrfs_set_inode_index(dir, &index); + err = btrfs_set_inode_index(BTRFS_I(dir), &index); if (err) goto fail; @@ -6514,7 +6509,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, ihold(inode); set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); - err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index); + err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode), + 1, index); if (err) { drop_inode = 1; @@ -6528,7 +6524,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, * If new hard link count is 1, it's a file created * with open(2) O_TMPFILE flag. */ - err = btrfs_orphan_del(trans, inode); + err = btrfs_orphan_del(trans, BTRFS_I(inode)); if (err) goto fail; } @@ -6589,13 +6585,14 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (err) goto out_fail_inode; - btrfs_i_size_write(inode, 0); + btrfs_i_size_write(BTRFS_I(inode), 0); err = btrfs_update_inode(trans, root, inode); if (err) goto out_fail_inode; - err = btrfs_add_link(trans, dir, inode, dentry->d_name.name, - dentry->d_name.len, 0, index); + err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), + dentry->d_name.name, + dentry->d_name.len, 0, index); if (err) goto out_fail_inode; @@ -6725,25 +6722,26 @@ static noinline int uncompress_inline(struct btrfs_path *path, * This also copies inline extents directly into the page. */ -struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, - size_t pg_offset, u64 start, u64 len, - int create) +struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, + struct page *page, + size_t pg_offset, u64 start, u64 len, + int create) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); int ret; int err = 0; u64 extent_start = 0; u64 extent_end = 0; - u64 objectid = btrfs_ino(BTRFS_I(inode)); + u64 objectid = btrfs_ino(inode); u32 found_type; struct btrfs_path *path = NULL; - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *item; struct extent_buffer *leaf; struct btrfs_key found_key; struct extent_map *em = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_io_tree *io_tree = &inode->io_tree; struct btrfs_trans_handle *trans = NULL; const bool new_inline = !page || create; @@ -6856,7 +6854,8 @@ next: goto not_found_em; } - btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em); + btrfs_extent_item_to_extent_map(inode, path, item, + new_inline, em); if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { @@ -6992,7 +6991,7 @@ insert: write_unlock(&em_tree->lock); out: - trace_btrfs_get_extent(root, BTRFS_I(inode), em); + trace_btrfs_get_extent(root, inode, em); btrfs_free_path(path); if (trans) { @@ -7008,9 +7007,10 @@ out: return em; } -struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page, - size_t pg_offset, u64 start, u64 len, - int create) +struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, + struct page *page, + size_t pg_offset, u64 start, u64 len, + int create) { struct extent_map *em; struct extent_map *hole_em = NULL; @@ -7047,7 +7047,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag em = NULL; /* ok, we didn't find anything, lets look for delalloc */ - found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start, + found = count_range_bits(&inode->io_tree, &range_start, end, len, EXTENT_DELALLOC, 1); found_end = range_start + found; if (found_end < range_start) @@ -7162,7 +7162,7 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, if (ret) { if (em) { free_extent_map(em); - btrfs_drop_extent_cache(inode, start, + btrfs_drop_extent_cache(BTRFS_I(inode), start, start + len - 1, 0); } em = ERR_PTR(ret); @@ -7423,7 +7423,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, * doing DIO to, so we need to make sure there's no ordered * extents in this range. */ - ordered = btrfs_lookup_ordered_range(inode, lockstart, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart, lockend - lockstart + 1); /* @@ -7529,7 +7529,7 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, } do { - btrfs_drop_extent_cache(inode, em->start, + btrfs_drop_extent_cache(BTRFS_I(inode), em->start, em->start + em->len - 1, 0); write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em, 1); @@ -7617,7 +7617,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, goto err; } - em = btrfs_get_extent(inode, NULL, 0, start, len, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0); if (IS_ERR(em)) { ret = PTR_ERR(em); goto unlock_err; @@ -7854,7 +7854,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, ret = btrfs_check_dio_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); return -EIO; } @@ -7868,7 +7868,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, pgoff, isector, repair_endio, repair_arg); if (!bio) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); return -EIO; } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); @@ -7879,7 +7879,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror); if (ret) { - free_io_failure(inode, failrec); + free_io_failure(BTRFS_I(inode), failrec); bio_put(bio); } @@ -7909,7 +7909,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) done->uptodate = 1; bio_for_each_segment_all(bvec, bio, i) - clean_io_failure(done->inode, done->start, bvec->bv_page, 0); + clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0); end: complete(&done->done); bio_put(bio); @@ -7995,7 +7995,7 @@ static void btrfs_retry_endio(struct bio *bio) bvec->bv_page, bvec->bv_offset, done->start, bvec->bv_len); if (!ret) - clean_io_failure(done->inode, done->start, + clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, bvec->bv_offset); else uptodate = 0; @@ -8796,7 +8796,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, lock_extent_bits(tree, page_start, page_end, &cached_state); again: start = page_start; - ordered = btrfs_lookup_ordered_range(inode, start, + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start, page_end - start + 1); if (ordered) { end = min(page_end, ordered->file_offset + ordered->len - 1); @@ -8962,7 +8962,8 @@ again: * we can't set the delalloc bits if there are pending ordered * extents. Drop our locks and wait for them to finish */ - ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); + ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, + PAGE_SIZE); if (ordered) { unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); @@ -9160,7 +9161,7 @@ static int btrfs_truncate(struct inode *inode) if (ret == 0 && inode->i_nlink > 0) { trans->block_rsv = root->orphan_block_rsv; - ret = btrfs_orphan_del(trans, inode); + ret = btrfs_orphan_del(trans, BTRFS_I(inode)); if (ret) err = ret; } @@ -9205,7 +9206,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, inode->i_fop = &btrfs_dir_file_operations; set_nlink(inode, 1); - btrfs_i_size_write(inode, 0); + btrfs_i_size_write(BTRFS_I(inode), 0); unlock_new_inode(inode); err = btrfs_subvol_inherit_props(trans, new_root, parent_root); @@ -9278,7 +9279,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS void btrfs_test_destroy_inode(struct inode *inode) { - btrfs_drop_extent_cache(inode, 0, (u64)-1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode)); } #endif @@ -9333,7 +9334,7 @@ void btrfs_destroy_inode(struct inode *inode) } btrfs_qgroup_check_reserved_leak(inode); inode_tree_del(inode); - btrfs_drop_extent_cache(inode, 0, (u64)-1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); free: call_rcu(&inode->i_rcu, btrfs_i_callback); } @@ -9480,10 +9481,10 @@ static int btrfs_rename_exchange(struct inode *old_dir, * We need to find a free sequence number both in the source and * in the destination directory for the exchange. */ - ret = btrfs_set_inode_index(new_dir, &old_idx); + ret = btrfs_set_inode_index(BTRFS_I(new_dir), &old_idx); if (ret) goto out_fail; - ret = btrfs_set_inode_index(old_dir, &new_idx); + ret = btrfs_set_inode_index(BTRFS_I(old_dir), &new_idx); if (ret) goto out_fail; @@ -9581,7 +9582,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, goto out_fail; } - ret = btrfs_add_link(trans, new_dir, old_inode, + ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), new_dentry->d_name.name, new_dentry->d_name.len, 0, old_idx); if (ret) { @@ -9589,7 +9590,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, goto out_fail; } - ret = btrfs_add_link(trans, old_dir, new_inode, + ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode), old_dentry->d_name.name, old_dentry->d_name.len, 0, new_idx); if (ret) { @@ -9691,8 +9692,8 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, if (ret) goto out; - ret = btrfs_add_nondir(trans, dir, dentry, - inode, 0, index); + ret = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, + BTRFS_I(inode), 0, index); if (ret) goto out; @@ -9791,7 +9792,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (dest != root) btrfs_record_root_in_trans(trans, dest); - ret = btrfs_set_inode_index(new_dir, &index); + ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index); if (ret) goto out_fail; @@ -9858,14 +9859,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry->d_name.len); } if (!ret && new_inode->i_nlink == 0) - ret = btrfs_orphan_add(trans, d_inode(new_dentry)); + ret = btrfs_orphan_add(trans, + BTRFS_I(d_inode(new_dentry))); if (ret) { btrfs_abort_transaction(trans, ret); goto out_fail; } } - ret = btrfs_add_link(trans, new_dir, old_inode, + ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode), new_dentry->d_name.name, new_dentry->d_name.len, 0, index); if (ret) { @@ -10232,7 +10234,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; inode_set_bytes(inode, name_len); - btrfs_i_size_write(inode, name_len); + btrfs_i_size_write(BTRFS_I(inode), name_len); err = btrfs_update_inode(trans, root, inode); /* * Last step, add directory indexes for our symlink inode. This is the @@ -10240,7 +10242,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, * elsewhere above. */ if (!err) - err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, + BTRFS_I(inode), 0, index); if (err) { drop_inode = 1; goto out_unlock_inode; @@ -10326,7 +10329,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, break; } - btrfs_drop_extent_cache(inode, cur_offset, + btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset, cur_offset + ins.offset -1, 0); em = alloc_extent_map(); @@ -10353,7 +10356,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, write_unlock(&em_tree->lock); if (ret != -EEXIST) break; - btrfs_drop_extent_cache(inode, cur_offset, + btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset, cur_offset + ins.offset - 1, 0); } @@ -10475,7 +10478,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) ret = btrfs_update_inode(trans, root, inode); if (ret) goto out_inode; - ret = btrfs_orphan_add(trans, inode); + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) goto out_inode; @@ -10505,6 +10508,12 @@ out_inode: } +__attribute__((const)) +static int dummy_readpage_io_failed_hook(struct page *page, int failed_mirror) +{ + return 0; +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, @@ -10543,10 +10552,14 @@ static const struct file_operations btrfs_dir_file_operations = { }; static const struct extent_io_ops btrfs_extent_io_ops = { - .fill_delalloc = run_delalloc_range, + /* mandatory callbacks */ .submit_bio_hook = btrfs_submit_bio_hook, - .merge_bio_hook = btrfs_merge_bio_hook, .readpage_end_io_hook = btrfs_readpage_end_io_hook, + .merge_bio_hook = btrfs_merge_bio_hook, + .readpage_io_failed_hook = dummy_readpage_io_failed_hook, + + /* optional callbacks */ + .fill_delalloc = run_delalloc_range, .writepage_end_io_hook = btrfs_writepage_end_io_hook, .writepage_start_hook = btrfs_writepage_start_hook, .set_bit_hook = btrfs_set_bit_hook, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d8539979b44f..dabfc7ac48a6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -434,7 +434,7 @@ int btrfs_is_empty_uuid(u8 *uuid) static noinline int create_subvol(struct inode *dir, struct dentry *dentry, - char *name, int namelen, + const char *name, int namelen, u64 *async_transid, struct btrfs_qgroup_inherit *inherit) { @@ -580,21 +580,21 @@ static noinline int create_subvol(struct inode *dir, /* * insert the directory item */ - ret = btrfs_set_inode_index(dir, &index); + ret = btrfs_set_inode_index(BTRFS_I(dir), &index); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; } ret = btrfs_insert_dir_item(trans, root, - name, namelen, dir, &key, + name, namelen, BTRFS_I(dir), &key, BTRFS_FT_DIR, index); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; } - btrfs_i_size_write(dir, dir->i_size + namelen * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); BUG_ON(ret); @@ -832,7 +832,7 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child) * inside this filesystem so it's quite a bit simpler. */ static noinline int btrfs_mksubvol(const struct path *parent, - char *name, int namelen, + const char *name, int namelen, struct btrfs_root *snap_src, u64 *async_transid, bool readonly, struct btrfs_qgroup_inherit *inherit) @@ -1009,7 +1009,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) /* get the big lock and read metadata off disk */ lock_extent_bits(io_tree, start, end, &cached); - em = btrfs_get_extent(inode, NULL, 0, start, len, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0); unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS); if (IS_ERR(em)) @@ -1625,7 +1625,7 @@ out: } static noinline int btrfs_ioctl_snap_create_transid(struct file *file, - char *name, unsigned long fd, int subvol, + const char *name, unsigned long fd, int subvol, u64 *transid, bool readonly, struct btrfs_qgroup_inherit *inherit) { @@ -3298,7 +3298,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans, if (endoff > destoff + olen) endoff = destoff + olen; if (endoff > inode->i_size) - btrfs_i_size_write(inode, endoff); + btrfs_i_size_write(BTRFS_I(inode), endoff); ret = btrfs_update_inode(trans, root, inode); if (ret) { @@ -3311,20 +3311,19 @@ out: return ret; } -static void clone_update_extent_map(struct inode *inode, +static void clone_update_extent_map(struct btrfs_inode *inode, const struct btrfs_trans_handle *trans, const struct btrfs_path *path, const u64 hole_offset, const u64 hole_len) { - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map *em; int ret; em = alloc_extent_map(); if (!em) { - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); return; } @@ -3338,7 +3337,7 @@ static void clone_update_extent_map(struct inode *inode, if (btrfs_file_extent_type(path->nodes[0], fi) == BTRFS_FILE_EXTENT_INLINE) set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); } else { em->start = hole_offset; em->len = hole_len; @@ -3364,8 +3363,7 @@ static void clone_update_extent_map(struct inode *inode, } if (ret) - set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); } /* @@ -3791,11 +3789,12 @@ process_slot: /* If we have an implicit hole (NO_HOLES feature). */ if (drop_start < new_key.offset) - clone_update_extent_map(inode, trans, + clone_update_extent_map(BTRFS_I(inode), trans, NULL, drop_start, new_key.offset - drop_start); - clone_update_extent_map(inode, trans, path, 0, 0); + clone_update_extent_map(BTRFS_I(inode), trans, + path, 0, 0); btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); @@ -3845,8 +3844,9 @@ process_slot: btrfs_end_transaction(trans); goto out; } - clone_update_extent_map(inode, trans, NULL, last_dest_end, - destoff + len - last_dest_end); + clone_update_extent_map(BTRFS_I(inode), trans, NULL, + last_dest_end, + destoff + len - last_dest_end); ret = clone_finish_inode_update(trans, inode, destoff + len, destoff, olen, no_time_update); } diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 45d26980caf9..f48c8c14dc14 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -76,7 +76,7 @@ static inline void write_compress_length(char *buf, size_t len) memcpy(buf, &dlen, LZO_LEN); } -static inline size_t read_compress_length(char *buf) +static inline size_t read_compress_length(const char *buf) { __le32 dlen; @@ -86,13 +86,11 @@ static inline size_t read_compress_length(char *buf) static int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, - u64 start, unsigned long len, + u64 start, struct page **pages, - unsigned long nr_dest_pages, unsigned long *out_pages, unsigned long *total_in, - unsigned long *total_out, - unsigned long max_out) + unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0; @@ -102,7 +100,9 @@ static int lzo_compress_pages(struct list_head *ws, struct page *in_page = NULL; struct page *out_page = NULL; unsigned long bytes_left; - + unsigned long len = *total_out; + unsigned long nr_dest_pages = *out_pages; + const unsigned long max_out = nr_dest_pages * PAGE_SIZE; size_t in_len; size_t out_len; char *buf; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index bc2aba810629..9a46878ba60f 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -879,15 +879,14 @@ out: /* Since the DIO code tries to lock a wide area we need to look for any ordered * extents that exist in the range, rather than just the start of the range. */ -struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode, - u64 file_offset, - u64 len) +struct btrfs_ordered_extent *btrfs_lookup_ordered_range( + struct btrfs_inode *inode, u64 file_offset, u64 len) { struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; - tree = &BTRFS_I(inode)->ordered_tree; + tree = &inode->ordered_tree; spin_lock_irq(&tree->lock); node = tree_search(tree, file_offset); if (!node) { @@ -923,7 +922,7 @@ bool btrfs_have_ordered_extents_in_range(struct inode *inode, { struct btrfs_ordered_extent *oe; - oe = btrfs_lookup_ordered_range(inode, file_offset, len); + oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len); if (oe) { btrfs_put_ordered_extent(oe); return true; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index a8cb8efe6fae..195c93b67fe0 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -189,9 +189,10 @@ void btrfs_start_ordered_extent(struct inode *inode, int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len); struct btrfs_ordered_extent * btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset); -struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode, - u64 file_offset, - u64 len); +struct btrfs_ordered_extent *btrfs_lookup_ordered_range( + struct btrfs_inode *inode, + u64 file_offset, + u64 len); bool btrfs_have_ordered_extents_in_range(struct inode *inode, u64 file_offset, u64 len); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ddbde0f08365..d60df51959f7 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1714,8 +1714,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans, if (!ret) continue; - btrfs_drop_extent_cache(inode, key.offset, end, - 1); + btrfs_drop_extent_cache(BTRFS_I(inode), + key.offset, end, 1); unlock_extent(&BTRFS_I(inode)->io_tree, key.offset, end); } @@ -2130,7 +2130,7 @@ static int invalidate_extent_cache(struct btrfs_root *root, /* the lock_extent waits for readpage to complete */ lock_extent(&BTRFS_I(inode)->io_tree, start, end); - btrfs_drop_extent_cache(inode, start, end, 1); + btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 1); unlock_extent(&BTRFS_I(inode)->io_tree, start, end); } return 0; @@ -3161,7 +3161,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, free_extent_map(em); break; } - btrfs_drop_extent_cache(inode, start, end, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0); } unlock_extent(&BTRFS_I(inode)->io_tree, start, end); return ret; @@ -3203,7 +3203,8 @@ static int relocate_file_extent_cluster(struct inode *inode, index = (cluster->start - offset) >> PAGE_SHIFT; last_index = (cluster->end - offset) >> PAGE_SHIFT; while (index <= last_index) { - ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE); + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), + PAGE_SIZE); if (ret) goto out; @@ -3215,7 +3216,7 @@ static int relocate_file_extent_cluster(struct inode *inode, page = find_or_create_page(inode->i_mapping, index, mask); if (!page) { - btrfs_delalloc_release_metadata(inode, + btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE); ret = -ENOMEM; goto out; @@ -3234,7 +3235,7 @@ static int relocate_file_extent_cluster(struct inode *inode, if (!PageUptodate(page)) { unlock_page(page); put_page(page); - btrfs_delalloc_release_metadata(inode, + btrfs_delalloc_release_metadata(BTRFS_I(inode), PAGE_SIZE); ret = -EIO; goto out; @@ -4245,7 +4246,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, BUG_ON(IS_ERR(inode) || is_bad_inode(inode)); BTRFS_I(inode)->index_cnt = group->key.objectid; - err = btrfs_orphan_add(trans, inode); + err = btrfs_orphan_add(trans, BTRFS_I(inode)); out: btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ff9a11c39f5e..b0251eb1239f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -731,7 +731,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) ret = -EIO; goto out; } - ret = repair_io_failure(inode, offset, PAGE_SIZE, + ret = repair_io_failure(BTRFS_I(inode), offset, PAGE_SIZE, fixup->logical, page, offset - page_offset(page), fixup->mirror_num); @@ -4236,7 +4236,7 @@ out: scrub_pending_trans_workers_dec(sctx); } -static int check_extent_to_block(struct inode *inode, u64 start, u64 len, +static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len, u64 logical) { struct extent_state *cached_state = NULL; @@ -4246,7 +4246,7 @@ static int check_extent_to_block(struct inode *inode, u64 start, u64 len, u64 lockstart = start, lockend = start + len - 1; int ret = 0; - io_tree = &BTRFS_I(inode)->io_tree; + io_tree = &inode->io_tree; lock_extent_bits(io_tree, lockstart, lockend, &cached_state); ordered = btrfs_lookup_ordered_range(inode, lockstart, len); @@ -4325,7 +4325,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, io_tree = &BTRFS_I(inode)->io_tree; nocow_ctx_logical = nocow_ctx->logical; - ret = check_extent_to_block(inode, offset, len, nocow_ctx_logical); + ret = check_extent_to_block(BTRFS_I(inode), offset, len, + nocow_ctx_logical); if (ret) { ret = ret > 0 ? 0 : ret; goto out; @@ -4372,7 +4373,7 @@ again: } } - ret = check_extent_to_block(inode, offset, len, + ret = check_extent_to_block(BTRFS_I(inode), offset, len, nocow_ctx_logical); if (ret) { ret = ret > 0 ? 0 : ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d145ce804620..456c8901489b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1681,6 +1681,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen) { int ret; + if (ino == BTRFS_FIRST_FREE_OBJECTID) + return 1; + ret = get_cur_inode_state(sctx, ino, gen); if (ret < 0) goto out; @@ -1866,7 +1869,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, * not deleted and then re-created, if it was then we have no overwrite * and we can just unlink this entry. */ - if (sctx->parent_root) { + if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) { ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL, NULL, NULL, NULL); if (ret < 0 && ret != -ENOENT) @@ -1934,6 +1937,19 @@ static int did_overwrite_ref(struct send_ctx *sctx, if (ret <= 0) goto out; + if (dir != BTRFS_FIRST_FREE_OBJECTID) { + ret = get_inode_info(sctx->send_root, dir, NULL, &gen, NULL, + NULL, NULL, NULL); + if (ret < 0 && ret != -ENOENT) + goto out; + if (ret) { + ret = 0; + goto out; + } + if (gen != dir_gen) + goto out; + } + /* check if the ref was overwritten by another ref */ ret = lookup_dir_item_inode(sctx->send_root, dir, name, name_len, &ow_inode, &other_type); @@ -3556,6 +3572,7 @@ static int wait_for_parent_move(struct send_ctx *sctx, { int ret = 0; u64 ino = parent_ref->dir; + u64 ino_gen = parent_ref->dir_gen; u64 parent_ino_before, parent_ino_after; struct fs_path *path_before = NULL; struct fs_path *path_after = NULL; @@ -3576,6 +3593,8 @@ static int wait_for_parent_move(struct send_ctx *sctx, * at get_cur_path()). */ while (ino > BTRFS_FIRST_FREE_OBJECTID) { + u64 parent_ino_after_gen; + if (is_waiting_for_move(sctx, ino)) { /* * If the current inode is an ancestor of ino in the @@ -3598,7 +3617,7 @@ static int wait_for_parent_move(struct send_ctx *sctx, fs_path_reset(path_after); ret = get_first_ref(sctx->send_root, ino, &parent_ino_after, - NULL, path_after); + &parent_ino_after_gen, path_after); if (ret < 0) goto out; ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before, @@ -3615,10 +3634,20 @@ static int wait_for_parent_move(struct send_ctx *sctx, if (ino > sctx->cur_ino && (parent_ino_before != parent_ino_after || len1 != len2 || memcmp(path_before->start, path_after->start, len1))) { - ret = 1; - break; + u64 parent_ino_gen; + + ret = get_inode_info(sctx->parent_root, ino, NULL, + &parent_ino_gen, NULL, NULL, NULL, + NULL); + if (ret < 0) + goto out; + if (ino_gen == parent_ino_gen) { + ret = 1; + break; + } } ino = parent_ino_after; + ino_gen = parent_ino_after_gen; } out: @@ -5277,6 +5306,81 @@ out: return ret; } +static int range_is_hole_in_parent(struct send_ctx *sctx, + const u64 start, + const u64 end) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_root *root = sctx->parent_root; + u64 search_start = start; + int ret; + + path = alloc_path_for_send(); + if (!path) + return -ENOMEM; + + key.objectid = sctx->cur_ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = search_start; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + if (ret > 0 && path->slots[0] > 0) + path->slots[0]--; + + while (search_start < end) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_file_extent_item *fi; + u64 extent_end; + + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto out; + else if (ret > 0) + break; + continue; + } + + btrfs_item_key_to_cpu(leaf, &key, slot); + if (key.objectid < sctx->cur_ino || + key.type < BTRFS_EXTENT_DATA_KEY) + goto next; + if (key.objectid > sctx->cur_ino || + key.type > BTRFS_EXTENT_DATA_KEY || + key.offset >= end) + break; + + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + if (btrfs_file_extent_type(leaf, fi) == + BTRFS_FILE_EXTENT_INLINE) { + u64 size = btrfs_file_extent_inline_len(leaf, slot, fi); + + extent_end = ALIGN(key.offset + size, + root->fs_info->sectorsize); + } else { + extent_end = key.offset + + btrfs_file_extent_num_bytes(leaf, fi); + } + if (extent_end <= start) + goto next; + if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { + search_start = extent_end; + goto next; + } + ret = 0; + goto out; +next: + path->slots[0]++; + } + ret = 1; +out: + btrfs_free_path(path); + return ret; +} + static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path, struct btrfs_key *key) { @@ -5321,8 +5425,17 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path, return ret; } - if (sctx->cur_inode_last_extent < key->offset) - ret = send_hole(sctx, key->offset); + if (sctx->cur_inode_last_extent < key->offset) { + ret = range_is_hole_in_parent(sctx, + sctx->cur_inode_last_extent, + key->offset); + if (ret < 0) + return ret; + else if (ret == 0) + ret = send_hole(sctx, key->offset); + else + ret = 0; + } sctx->cur_inode_last_extent = extent_end; return ret; } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 4d0f038e14f1..8c91d03cc82d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -278,7 +278,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) /* First with no extents */ BTRFS_I(inode)->root = root; - em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize, 0); if (IS_ERR(em)) { em = NULL; test_msg("Got an error when we shouldn't have\n"); @@ -293,7 +293,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) goto out; } free_extent_map(em); - btrfs_drop_extent_cache(inode, 0, (u64)-1, 0); + btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0); /* * All of the magic numbers are based on the mapping setup in @@ -302,7 +302,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) */ setup_file_extents(root, sectorsize); - em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -323,7 +323,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -350,7 +350,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -372,7 +372,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* Regular extent */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -399,7 +399,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* The next 3 are split extents */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -428,7 +428,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -450,7 +450,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -484,7 +484,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* Prealloc extent */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -513,7 +513,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* The next 3 are a half written prealloc extent */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -543,7 +543,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -576,7 +576,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -611,7 +611,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* Now for the compressed extent */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -645,7 +645,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* Split compressed extent */ - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -680,7 +680,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -707,7 +707,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -742,7 +742,8 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) free_extent_map(em); /* A hole between regular extents but no hole extent */ - em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6, + sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -769,7 +770,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, 4096 * 1024, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, 4096 * 1024, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -802,7 +803,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) offset = em->start + em->len; free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -885,7 +886,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) insert_inode_item_key(root); insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize, sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1); - em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; @@ -907,7 +908,8 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) } free_extent_map(em); - em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize, + 2 * sectorsize, 0); if (IS_ERR(em)) { test_msg("Got an error when we shouldn't have\n"); goto out; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 6b3e0fc2fe7a..61b807de3e16 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1505,7 +1505,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, /* * insert the directory item */ - ret = btrfs_set_inode_index(parent_inode, &index); + ret = btrfs_set_inode_index(BTRFS_I(parent_inode), &index); BUG_ON(ret); /* -ENOMEM */ /* check if there is a file/dir which has the same name. */ @@ -1644,7 +1644,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_insert_dir_item(trans, parent_root, dentry->d_name.name, dentry->d_name.len, - parent_inode, &key, + BTRFS_I(parent_inode), &key, BTRFS_FT_DIR, index); /* We have check then name at the beginning, so it is impossible. */ BUG_ON(ret == -EEXIST || ret == -EOVERFLOW); @@ -1653,7 +1653,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - btrfs_i_size_write(parent_inode, parent_inode->i_size + + btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size + dentry->d_name.len * 2); parent_inode->i_mtime = parent_inode->i_ctime = current_time(parent_inode); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3806853cde08..a59674c3e69e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -673,6 +673,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, unsigned long dest_offset; struct btrfs_key ins; + if (btrfs_file_extent_disk_bytenr(eb, item) == 0 && + btrfs_fs_incompat(fs_info, NO_HOLES)) + goto update_inode; + ret = btrfs_insert_empty_item(trans, root, path, key, sizeof(*item)); if (ret) @@ -825,6 +829,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, } inode_add_bytes(inode, nbytes); +update_inode: ret = btrfs_update_inode(trans, root, inode); out: if (inode) @@ -1322,8 +1327,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } /* insert our name */ - ret = btrfs_add_link(trans, dir, inode, name, namelen, - 0, ref_index); + ret = btrfs_add_link(trans, BTRFS_I(dir), + BTRFS_I(inode), + name, namelen, 0, ref_index); if (ret) goto out; @@ -1641,7 +1647,8 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, return -EIO; } - ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index); + ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, + name_len, 1, index); /* FIXME, put inode into FIXUP list */ @@ -1780,7 +1787,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, out: btrfs_release_path(path); if (!ret && update_size) { - btrfs_i_size_write(dir, dir->i_size + name_len * 2); + btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2); ret = btrfs_update_inode(trans, root, dir); } kfree(name); @@ -5045,14 +5052,14 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, * a full commit is required. */ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, - struct inode *inode, + struct btrfs_inode *inode, struct dentry *parent, struct super_block *sb, u64 last_committed) { int ret = 0; struct dentry *old_parent = NULL; - struct inode *orig_inode = inode; + struct btrfs_inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -5060,15 +5067,15 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, * we can use the last_unlink_trans field to record renames * and other fun in this file. */ - if (S_ISREG(inode->i_mode) && - BTRFS_I(inode)->generation <= last_committed && - BTRFS_I(inode)->last_unlink_trans <= last_committed) - goto out; + if (S_ISREG(inode->vfs_inode.i_mode) && + inode->generation <= last_committed && + inode->last_unlink_trans <= last_committed) + goto out; - if (!S_ISDIR(inode->i_mode)) { + if (!S_ISDIR(inode->vfs_inode.i_mode)) { if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) goto out; - inode = d_inode(parent); + inode = BTRFS_I(d_inode(parent)); } while (1) { @@ -5079,10 +5086,10 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, * think this inode has already been logged. */ if (inode != orig_inode) - BTRFS_I(inode)->logged_trans = trans->transid; + inode->logged_trans = trans->transid; smp_mb(); - if (btrfs_must_commit_transaction(trans, BTRFS_I(inode))) { + if (btrfs_must_commit_transaction(trans, inode)) { ret = 1; break; } @@ -5091,8 +5098,8 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, break; if (IS_ROOT(parent)) { - inode = d_inode(parent); - if (btrfs_must_commit_transaction(trans, BTRFS_I(inode))) + inode = BTRFS_I(d_inode(parent)); + if (btrfs_must_commit_transaction(trans, inode)) ret = 1; break; } @@ -5100,7 +5107,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, parent = dget_parent(parent); dput(old_parent); old_parent = parent; - inode = d_inode(parent); + inode = BTRFS_I(d_inode(parent)); } dput(old_parent); @@ -5287,15 +5294,15 @@ next_dir_inode: } static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_log_ctx *ctx) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_root *root = BTRFS_I(inode)->root; - const u64 ino = btrfs_ino(BTRFS_I(inode)); + struct btrfs_root *root = inode->root; + const u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) @@ -5390,7 +5397,8 @@ out: * the last committed transaction */ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, + struct btrfs_root *root, + struct btrfs_inode *inode, struct dentry *parent, const loff_t start, const loff_t end, @@ -5404,9 +5412,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, int ret = 0; u64 last_committed = fs_info->last_trans_committed; bool log_dentries = false; - struct inode *orig_inode = inode; + struct btrfs_inode *orig_inode = inode; - sb = inode->i_sb; + sb = inode->vfs_inode.i_sb; if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = 1; @@ -5423,18 +5431,17 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, goto end_no_trans; } - if (root != BTRFS_I(inode)->root || - btrfs_root_refs(&root->root_item) == 0) { + if (root != inode->root || btrfs_root_refs(&root->root_item) == 0) { ret = 1; goto end_no_trans; } - ret = check_parent_dirs_for_sync(trans, inode, parent, - sb, last_committed); + ret = check_parent_dirs_for_sync(trans, inode, parent, sb, + last_committed); if (ret) goto end_no_trans; - if (btrfs_inode_in_log(BTRFS_I(inode), trans->transid)) { + if (btrfs_inode_in_log(inode, trans->transid)) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } @@ -5443,8 +5450,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (ret) goto end_no_trans; - ret = btrfs_log_inode(trans, root, BTRFS_I(inode), inode_only, - start, end, ctx); + ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx); if (ret) goto end_trans; @@ -5454,14 +5460,14 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * we can use the last_unlink_trans field to record renames * and other fun in this file. */ - if (S_ISREG(inode->i_mode) && - BTRFS_I(inode)->generation <= last_committed && - BTRFS_I(inode)->last_unlink_trans <= last_committed) { + if (S_ISREG(inode->vfs_inode.i_mode) && + inode->generation <= last_committed && + inode->last_unlink_trans <= last_committed) { ret = 0; goto end_trans; } - if (S_ISDIR(inode->i_mode) && ctx && ctx->log_new_dentries) + if (S_ISDIR(inode->vfs_inode.i_mode) && ctx && ctx->log_new_dentries) log_dentries = true; /* @@ -5505,7 +5511,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * but the file inode does not have a matching BTRFS_INODE_REF_KEY item * and has a link count of 2. */ - if (BTRFS_I(inode)->last_unlink_trans > last_committed) { + if (inode->last_unlink_trans > last_committed) { ret = btrfs_log_all_parents(trans, orig_inode, ctx); if (ret) goto end_trans; @@ -5515,14 +5521,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; - inode = d_inode(parent); - if (root != BTRFS_I(inode)->root) + inode = BTRFS_I(d_inode(parent)); + if (root != inode->root) break; - if (BTRFS_I(inode)->generation > last_committed) { - ret = btrfs_log_inode(trans, root, BTRFS_I(inode), - LOG_INODE_EXISTS, - 0, LLONG_MAX, ctx); + if (inode->generation > last_committed) { + ret = btrfs_log_inode(trans, root, inode, + LOG_INODE_EXISTS, 0, LLONG_MAX, ctx); if (ret) goto end_trans; } @@ -5534,7 +5539,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, old_parent = parent; } if (log_dentries) - ret = log_new_dir_dentries(trans, root, BTRFS_I(orig_inode), ctx); + ret = log_new_dir_dentries(trans, root, orig_inode, ctx); else ret = 0; end_trans: @@ -5566,8 +5571,8 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct dentry *parent = dget_parent(dentry); int ret; - ret = btrfs_log_inode_parent(trans, root, d_inode(dentry), parent, - start, end, 0, ctx); + ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)), + parent, start, end, 0, ctx); dput(parent); return ret; @@ -5829,7 +5834,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) return 0; - return btrfs_log_inode_parent(trans, root, &inode->vfs_inode, parent, 0, + return btrfs_log_inode_parent(trans, root, inode, parent, 0, LLONG_MAX, 1, NULL); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 13e55d13045d..73d56eef5e60 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1725,7 +1725,7 @@ out: * Function to update ctime/mtime for a given device path. * Mainly used for ctime/mtime based probe like libblkid. */ -static void update_dev_time(char *path_name) +static void update_dev_time(const char *path_name) { struct file *filp; @@ -1851,7 +1851,8 @@ void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info, fs_info->fs_devices->latest_bdev = next_device->bdev; } -int btrfs_rm_device(struct btrfs_fs_info *fs_info, char *device_path, u64 devid) +int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, + u64 devid) { struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; @@ -2091,7 +2092,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, } static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info, - char *device_path, + const char *device_path, struct btrfs_device **device) { int ret = 0; @@ -2118,7 +2119,7 @@ static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info, } int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, - char *device_path, + const char *device_path, struct btrfs_device **device) { *device = NULL; @@ -2151,7 +2152,8 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, * Lookup a device given by device id, or the path if the id is 0. */ int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid, - char *devpath, struct btrfs_device **device) + const char *devpath, + struct btrfs_device **device) { int ret; @@ -2307,7 +2309,7 @@ error: return ret; } -int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path) +int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path) { struct btrfs_root *root = fs_info->dev_root; struct request_queue *q; @@ -2515,7 +2517,7 @@ error: } int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, - char *device_path, + const char *device_path, struct btrfs_device *srcdev, struct btrfs_device **device_out) { @@ -6954,7 +6956,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, key.offset = device->devid; path = btrfs_alloc_path(); - BUG_ON(!path); + if (!path) + return -ENOMEM; ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); if (ret < 0) { btrfs_warn_in_rcu(fs_info, @@ -7102,7 +7105,7 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info, return 0; } -void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path) +void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path) { struct buffer_head *bh; struct btrfs_super_block *disk_super; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 24ba6bc3ec34..59be81206dd7 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -422,16 +422,16 @@ void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step); void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info, struct btrfs_device *device, struct btrfs_device *this_dev); int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info, - char *device_path, + const char *device_path, struct btrfs_device **device); int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid, - char *devpath, + const char *devpath, struct btrfs_device **device); struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, const u64 *devid, const u8 *uuid); int btrfs_rm_device(struct btrfs_fs_info *fs_info, - char *device_path, u64 devid); + const char *device_path, u64 devid); void btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, @@ -439,9 +439,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid, u8 *uuid, u8 *fsid); int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); -int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *path); +int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path); int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, - char *device_path, + const char *device_path, struct btrfs_device *srcdev, struct btrfs_device **device_out); int btrfs_balance(struct btrfs_balance_control *bctl, @@ -474,7 +474,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev); void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev); -void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path); +void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path); int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len, int mirror_num); unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index da497f184ff4..135b10823c6d 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -73,13 +73,11 @@ fail: static int zlib_compress_pages(struct list_head *ws, struct address_space *mapping, - u64 start, unsigned long len, + u64 start, struct page **pages, - unsigned long nr_dest_pages, unsigned long *out_pages, unsigned long *total_in, - unsigned long *total_out, - unsigned long max_out) + unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret; @@ -89,6 +87,9 @@ static int zlib_compress_pages(struct list_head *ws, struct page *in_page = NULL; struct page *out_page = NULL; unsigned long bytes_left; + unsigned long len = *total_out; + unsigned long nr_dest_pages = *out_pages; + const unsigned long max_out = nr_dest_pages * PAGE_SIZE; *out_pages = 0; *total_out = 0; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9bf25be05636..3aa457f83214 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2456,7 +2456,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) } down_read(&key->sem); - upayload = user_key_payload(key); + upayload = user_key_payload_locked(key); if (IS_ERR_OR_NULL(upayload)) { rc = upayload ? PTR_ERR(upayload) : -EINVAL; goto out_key_put; diff --git a/fs/coda/file.c b/fs/coda/file.c index 6e0154eb6fcc..9d956cd6d46f 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -96,7 +96,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) cfi->cfi_mapcount++; spin_unlock(&cii->c_lock); - return host_file->f_op->mmap(host_file, vma); + return call_mmap(host_file, vma); } int coda_open(struct inode *coda_inode, struct file *coda_file) diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 02eb6b9e4438..d5d896fa5a71 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -103,7 +103,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info, goto out; } down_read(&keyring_key->sem); - ukp = user_key_payload(keyring_key); + ukp = user_key_payload_locked(keyring_key); if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; up_read(&keyring_key->sem); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 599a29237cfe..95c1c8d34539 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -117,7 +117,7 @@ ecryptfs_get_key_payload_data(struct key *key) auth_tok = ecryptfs_get_encrypted_key_payload_data(key); if (!auth_tok) - return (struct ecryptfs_auth_tok *)user_key_payload(key)->data; + return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data; else return auth_tok; } diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 5d5ddaa84b21..67f940892ef8 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -329,7 +329,7 @@ static void fscache_objlist_config(struct fscache_objlist_data *data) config = 0; rcu_read_lock(); - confkey = user_key_payload(key); + confkey = user_key_payload_rcu(key); buf = confkey->data; for (len = confkey->datalen - 1; len >= 0; len--) { diff --git a/fs/namei.c b/fs/namei.c index da689c9c005e..d41fab78798b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -672,17 +672,15 @@ static bool legitimize_links(struct nameidata *nd) /** * unlazy_walk - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry or NULL - * @seq: seq number to check dentry against * Returns: 0 on success, -ECHILD on failure * - * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd or NULL. Must be called from rcu-walk context. + * unlazy_walk attempts to legitimize the current nd->path and nd->root + * for ref-walk mode. + * Must be called from rcu-walk context. * Nothing should touch nameidata between unlazy_walk() failure and * terminate_walk(). */ -static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static int unlazy_walk(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; @@ -691,33 +689,66 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; + if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) + goto out1; + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { + if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq))) + goto out; + } + rcu_read_unlock(); + BUG_ON(nd->inode != parent->d_inode); + return 0; + +out2: + nd->path.mnt = NULL; + nd->path.dentry = NULL; +out1: + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; +out: + rcu_read_unlock(); + return -ECHILD; +} + +/** + * unlazy_child - try to switch to ref-walk mode. + * @nd: nameidata pathwalk data + * @dentry: child of nd->path.dentry + * @seq: seq number to check dentry against + * Returns: 0 on success, -ECHILD on failure + * + * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry + * for ref-walk mode. @dentry must be a path found by a do_lookup call on + * @nd. Must be called from rcu-walk context. + * Nothing should touch nameidata between unlazy_child() failure and + * terminate_walk(). + */ +static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +{ + BUG_ON(!(nd->flags & LOOKUP_RCU)); + + nd->flags &= ~LOOKUP_RCU; + if (unlikely(!legitimize_links(nd))) + goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) goto out2; - if (unlikely(!lockref_get_not_dead(&parent->d_lockref))) + if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* - * For a negative lookup, the lookup sequence point is the parents - * sequence point, and it only needs to revalidate the parent dentry. - * - * For a positive lookup, we need to move both the parent and the - * dentry from the RCU domain to be properly refcounted. And the - * sequence number in the dentry validates *both* dentry counters, - * since we checked the sequence number of the parent after we got - * the child sequence number. So we know the parent must still - * be valid if the child sequence number is still valid. + * We need to move both the parent and the dentry from the RCU domain + * to be properly refcounted. And the sequence number in the dentry + * validates *both* dentry counters, since we checked the sequence + * number of the parent after we got the child sequence number. So we + * know the parent must still be valid if the child sequence number is */ - if (!dentry) { - if (read_seqcount_retry(&parent->d_seq, nd->seq)) - goto out; - BUG_ON(nd->inode != parent->d_inode); - } else { - if (!lockref_get_not_dead(&dentry->d_lockref)) - goto out; - if (read_seqcount_retry(&dentry->d_seq, seq)) - goto drop_dentry; + if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) + goto out; + if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) { + rcu_read_unlock(); + dput(dentry); + goto drop_root_mnt; } - /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. @@ -733,10 +764,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq rcu_read_unlock(); return 0; -drop_dentry: - rcu_read_unlock(); - dput(dentry); - goto drop_root_mnt; out2: nd->path.mnt = NULL; out1: @@ -749,27 +776,12 @@ drop_root_mnt: return -ECHILD; } -static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq) -{ - if (unlikely(!legitimize_path(nd, link, seq))) { - drop_links(nd); - nd->depth = 0; - nd->flags &= ~LOOKUP_RCU; - nd->path.mnt = NULL; - nd->path.dentry = NULL; - if (!(nd->flags & LOOKUP_ROOT)) - nd->root.mnt = NULL; - rcu_read_unlock(); - } else if (likely(unlazy_walk(nd, NULL, 0)) == 0) { - return 0; - } - path_put(link); - return -ECHILD; -} - static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { - return dentry->d_op->d_revalidate(dentry, flags); + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) + return dentry->d_op->d_revalidate(dentry, flags); + else + return 1; } /** @@ -790,7 +802,7 @@ static int complete_walk(struct nameidata *nd) if (nd->flags & LOOKUP_RCU) { if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - if (unlikely(unlazy_walk(nd, NULL, 0))) + if (unlikely(unlazy_walk(nd))) return -ECHILD; } @@ -1016,7 +1028,7 @@ const char *get_link(struct nameidata *nd) touch_atime(&last->link); cond_resched(); } else if (atime_needs_update_rcu(&last->link, inode)) { - if (unlikely(unlazy_walk(nd, NULL, 0))) + if (unlikely(unlazy_walk(nd))) return ERR_PTR(-ECHILD); touch_atime(&last->link); } @@ -1035,7 +1047,7 @@ const char *get_link(struct nameidata *nd) if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD)) { - if (unlikely(unlazy_walk(nd, NULL, 0))) + if (unlikely(unlazy_walk(nd))) return ERR_PTR(-ECHILD); res = get(dentry, inode, &last->done); } @@ -1469,19 +1481,14 @@ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { - struct dentry *dentry; - int error; - - dentry = d_lookup(dir, name); + struct dentry *dentry = d_lookup(dir, name); if (dentry) { - if (dentry->d_flags & DCACHE_OP_REVALIDATE) { - error = d_revalidate(dentry, flags); - if (unlikely(error <= 0)) { - if (!error) - d_invalidate(dentry); - dput(dentry); - return ERR_PTR(error); - } + int error = d_revalidate(dentry, flags); + if (unlikely(error <= 0)) { + if (!error) + d_invalidate(dentry); + dput(dentry); + return ERR_PTR(error); } } return dentry; @@ -1546,7 +1553,7 @@ static int lookup_fast(struct nameidata *nd, bool negative; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { - if (unlazy_walk(nd, NULL, 0)) + if (unlazy_walk(nd)) return -ECHILD; return 0; } @@ -1571,14 +1578,8 @@ static int lookup_fast(struct nameidata *nd, return -ECHILD; *seqp = seq; - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) - status = d_revalidate(dentry, nd->flags); - if (unlikely(status <= 0)) { - if (unlazy_walk(nd, dentry, seq)) - return -ECHILD; - if (status == -ECHILD) - status = d_revalidate(dentry, nd->flags); - } else { + status = d_revalidate(dentry, nd->flags); + if (likely(status > 0)) { /* * Note: do negative dentry check after revalidation in * case that drops it. @@ -1589,15 +1590,17 @@ static int lookup_fast(struct nameidata *nd, path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 1; - if (unlazy_walk(nd, dentry, seq)) - return -ECHILD; } + if (unlazy_child(nd, dentry, seq)) + return -ECHILD; + if (unlikely(status == -ECHILD)) + /* we'd been told to redo it in non-rcu mode */ + status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return 0; - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) @@ -1636,8 +1639,7 @@ again: if (IS_ERR(dentry)) goto out; if (unlikely(!d_in_lookup(dentry))) { - if ((dentry->d_flags & DCACHE_OP_REVALIDATE) && - !(flags & LOOKUP_NO_REVAL)) { + if (!(flags & LOOKUP_NO_REVAL)) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) { @@ -1668,7 +1670,7 @@ static inline int may_lookup(struct nameidata *nd) int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD) return err; - if (unlazy_walk(nd, NULL, 0)) + if (unlazy_walk(nd)) return -ECHILD; } return inode_permission(nd->inode, MAY_EXEC); @@ -1703,9 +1705,17 @@ static int pick_link(struct nameidata *nd, struct path *link, error = nd_alloc_stack(nd); if (unlikely(error)) { if (error == -ECHILD) { - if (unlikely(unlazy_link(nd, link, seq))) - return -ECHILD; - error = nd_alloc_stack(nd); + if (unlikely(!legitimize_path(nd, link, seq))) { + drop_links(nd); + nd->depth = 0; + nd->flags &= ~LOOKUP_RCU; + nd->path.mnt = NULL; + nd->path.dentry = NULL; + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; + rcu_read_unlock(); + } else if (likely(unlazy_walk(nd)) == 0) + error = nd_alloc_stack(nd); } if (error) { path_put(link); @@ -2122,7 +2132,7 @@ OK: } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd, NULL, 0)) + if (unlazy_walk(nd)) return -ECHILD; } return -ENOTDIR; @@ -2579,7 +2589,7 @@ mountpoint_last(struct nameidata *nd) /* If we're in rcuwalk, drop out of it to handle last component */ if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd, NULL, 0)) + if (unlazy_walk(nd)) return -ECHILD; } @@ -3072,9 +3082,6 @@ static int lookup_open(struct nameidata *nd, struct path *path, if (d_in_lookup(dentry)) break; - if (!(dentry->d_flags & DCACHE_OP_REVALIDATE)) - break; - error = d_revalidate(dentry, nd->flags); if (likely(error > 0)) break; @@ -3356,13 +3363,50 @@ out: return error; } +struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) +{ + static const struct qstr name = QSTR_INIT("/", 1); + struct dentry *child = NULL; + struct inode *dir = dentry->d_inode; + struct inode *inode; + int error; + + /* we want directory to be writable */ + error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (error) + goto out_err; + error = -EOPNOTSUPP; + if (!dir->i_op->tmpfile) + goto out_err; + error = -ENOMEM; + child = d_alloc(dentry, &name); + if (unlikely(!child)) + goto out_err; + error = dir->i_op->tmpfile(dir, child, mode); + if (error) + goto out_err; + error = -ENOENT; + inode = child->d_inode; + if (unlikely(!inode)) + goto out_err; + if (!(open_flag & O_EXCL)) { + spin_lock(&inode->i_lock); + inode->i_state |= I_LINKABLE; + spin_unlock(&inode->i_lock); + } + return child; + +out_err: + dput(child); + return ERR_PTR(error); +} +EXPORT_SYMBOL(vfs_tmpfile); + static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file, int *opened) { - static const struct qstr name = QSTR_INIT("/", 1); struct dentry *child; - struct inode *dir; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) @@ -3370,25 +3414,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; - dir = path.dentry->d_inode; - /* we want directory to be writable */ - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); - if (error) + child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); + error = PTR_ERR(child); + if (unlikely(IS_ERR(child))) goto out2; - if (!dir->i_op->tmpfile) { - error = -EOPNOTSUPP; - goto out2; - } - child = d_alloc(path.dentry, &name); - if (unlikely(!child)) { - error = -ENOMEM; - goto out2; - } dput(path.dentry); path.dentry = child; - error = dir->i_op->tmpfile(dir, child, op->mode); - if (error) - goto out2; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); @@ -3399,14 +3430,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, if (error) goto out2; error = open_check_o_direct(file); - if (error) { + if (error) fput(file); - } else if (!(op->open_flag & O_EXCL)) { - struct inode *inode = file_inode(file); - spin_lock(&inode->i_lock); - inode->i_state |= I_LINKABLE; - spin_unlock(&inode->i_lock); - } out2: mnt_drop_write(path.mnt); out: diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c index bdea177aa405..98b6db0ed63e 100644 --- a/fs/ncpfs/sock.c +++ b/fs/ncpfs/sock.c @@ -41,19 +41,12 @@ static int _recv(struct socket *sock, void *buf, int size, unsigned flags) return kernel_recvmsg(sock, &msg, &iov, 1, size, flags); } -static inline int do_send(struct socket *sock, struct kvec *vec, int count, - int len, unsigned flags) -{ - struct msghdr msg = { .msg_flags = flags }; - return kernel_sendmsg(sock, &msg, vec, count, len); -} - static int _send(struct socket *sock, const void *buff, int len) { - struct kvec vec; - vec.iov_base = (void *) buff; - vec.iov_len = len; - return do_send(sock, &vec, 1, len, 0); + struct msghdr msg = { .msg_flags = 0 }; + struct kvec vec = {.iov_base = (void *)buff, .iov_len = len}; + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &vec, 1, len); + return sock_sendmsg(sock, &msg); } struct ncp_request_reply { @@ -64,9 +57,7 @@ struct ncp_request_reply { size_t datalen; int result; enum { RQ_DONE, RQ_INPROGRESS, RQ_QUEUED, RQ_IDLE, RQ_ABANDONED } status; - struct kvec* tx_ciov; - size_t tx_totallen; - size_t tx_iovlen; + struct iov_iter from; struct kvec tx_iov[3]; u_int16_t tx_type; u_int32_t sign[6]; @@ -206,28 +197,22 @@ static inline void __ncptcp_abort(struct ncp_server *server) static int ncpdgram_send(struct socket *sock, struct ncp_request_reply *req) { - struct kvec vec[3]; - /* sock_sendmsg updates iov pointers for us :-( */ - memcpy(vec, req->tx_ciov, req->tx_iovlen * sizeof(vec[0])); - return do_send(sock, vec, req->tx_iovlen, - req->tx_totallen, MSG_DONTWAIT); + struct msghdr msg = { .msg_iter = req->from, .msg_flags = MSG_DONTWAIT }; + return sock_sendmsg(sock, &msg); } static void __ncptcp_try_send(struct ncp_server *server) { struct ncp_request_reply *rq; - struct kvec *iov; - struct kvec iovc[3]; + struct msghdr msg = { .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT }; int result; rq = server->tx.creq; if (!rq) return; - /* sock_sendmsg updates iov pointers for us :-( */ - memcpy(iovc, rq->tx_ciov, rq->tx_iovlen * sizeof(iov[0])); - result = do_send(server->ncp_sock, iovc, rq->tx_iovlen, - rq->tx_totallen, MSG_NOSIGNAL | MSG_DONTWAIT); + msg.msg_iter = rq->from; + result = sock_sendmsg(server->ncp_sock, &msg); if (result == -EAGAIN) return; @@ -237,21 +222,12 @@ static void __ncptcp_try_send(struct ncp_server *server) __ncp_abort_request(server, rq, result); return; } - if (result >= rq->tx_totallen) { + if (!msg_data_left(&msg)) { server->rcv.creq = rq; server->tx.creq = NULL; return; } - rq->tx_totallen -= result; - iov = rq->tx_ciov; - while (iov->iov_len <= result) { - result -= iov->iov_len; - iov++; - rq->tx_iovlen--; - } - iov->iov_base += result; - iov->iov_len -= result; - rq->tx_ciov = iov; + rq->from = msg.msg_iter; } static inline void ncp_init_header(struct ncp_server *server, struct ncp_request_reply *req, struct ncp_request_header *h) @@ -264,22 +240,21 @@ static inline void ncp_init_header(struct ncp_server *server, struct ncp_request static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request_reply *req) { - size_t signlen; - struct ncp_request_header* h; + size_t signlen, len = req->tx_iov[1].iov_len; + struct ncp_request_header *h = req->tx_iov[1].iov_base; - req->tx_ciov = req->tx_iov + 1; - - h = req->tx_iov[1].iov_base; ncp_init_header(server, req, h); - signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, - req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1, - cpu_to_le32(req->tx_totallen), req->sign); + signlen = sign_packet(server, + req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, + len - sizeof(struct ncp_request_header) + 1, + cpu_to_le32(len), req->sign); if (signlen) { - req->tx_ciov[1].iov_base = req->sign; - req->tx_ciov[1].iov_len = signlen; - req->tx_iovlen += 1; - req->tx_totallen += signlen; + /* NCP over UDP appends signature */ + req->tx_iov[2].iov_base = req->sign; + req->tx_iov[2].iov_len = signlen; } + iov_iter_kvec(&req->from, WRITE | ITER_KVEC, + req->tx_iov + 1, signlen ? 2 : 1, len + signlen); server->rcv.creq = req; server->timeout_last = server->m.time_out; server->timeout_retries = server->m.retry_count; @@ -293,24 +268,23 @@ static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request static void ncptcp_start_request(struct ncp_server *server, struct ncp_request_reply *req) { - size_t signlen; - struct ncp_request_header* h; + size_t signlen, len = req->tx_iov[1].iov_len; + struct ncp_request_header *h = req->tx_iov[1].iov_base; - req->tx_ciov = req->tx_iov; - h = req->tx_iov[1].iov_base; ncp_init_header(server, req, h); signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, - req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1, - cpu_to_be32(req->tx_totallen + 24), req->sign + 4) + 16; + len - sizeof(struct ncp_request_header) + 1, + cpu_to_be32(len + 24), req->sign + 4) + 16; req->sign[0] = htonl(NCP_TCP_XMIT_MAGIC); - req->sign[1] = htonl(req->tx_totallen + signlen); + req->sign[1] = htonl(len + signlen); req->sign[2] = htonl(NCP_TCP_XMIT_VERSION); req->sign[3] = htonl(req->datalen + 8); + /* NCP over TCP prepends signature */ req->tx_iov[0].iov_base = req->sign; req->tx_iov[0].iov_len = signlen; - req->tx_iovlen += 1; - req->tx_totallen += signlen; + iov_iter_kvec(&req->from, WRITE | ITER_KVEC, + req->tx_iov, 2, len + signlen); server->tx.creq = req; __ncptcp_try_send(server); @@ -365,18 +339,17 @@ static void __ncp_next_request(struct ncp_server *server) static void info_server(struct ncp_server *server, unsigned int id, const void * data, size_t len) { if (server->info_sock) { - struct kvec iov[2]; - __be32 hdr[2]; - - hdr[0] = cpu_to_be32(len + 8); - hdr[1] = cpu_to_be32(id); - - iov[0].iov_base = hdr; - iov[0].iov_len = 8; - iov[1].iov_base = (void *) data; - iov[1].iov_len = len; + struct msghdr msg = { .msg_flags = MSG_NOSIGNAL }; + __be32 hdr[2] = {cpu_to_be32(len + 8), cpu_to_be32(id)}; + struct kvec iov[2] = { + {.iov_base = hdr, .iov_len = 8}, + {.iov_base = (void *)data, .iov_len = len}, + }; + + iov_iter_kvec(&msg.msg_iter, ITER_KVEC | WRITE, + iov, 2, len + 8); - do_send(server->info_sock, iov, 2, len + 8, MSG_NOSIGNAL); + sock_sendmsg(server->info_sock, &msg); } } @@ -712,8 +685,6 @@ static int do_ncp_rpc_call(struct ncp_server *server, int size, req->datalen = max_reply_size; req->tx_iov[1].iov_base = server->packet; req->tx_iov[1].iov_len = size; - req->tx_iovlen = 1; - req->tx_totallen = size; req->tx_type = *(u_int16_t*)server->packet; result = ncp_add_request(server, req); diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index c444285bb1b1..835c163f61af 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -316,7 +316,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, if (ret < 0) goto out_up; - payload = user_key_payload(rkey); + payload = user_key_payload_rcu(rkey); if (IS_ERR_OR_NULL(payload)) { ret = PTR_ERR(payload); goto out_up; diff --git a/fs/open.c b/fs/open.c index 9921f70bc5ca..949cef29c3bb 100644 --- a/fs/open.c +++ b/fs/open.c @@ -301,12 +301,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (S_ISFIFO(inode->i_mode)) return -ESPIPE; - /* - * Let individual file system decide if it supports preallocation - * for directories or not. - */ - if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) && - !S_ISBLK(inode->i_mode)) + if (S_ISDIR(inode->i_mode)) + return -EISDIR; + + if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ @@ -316,7 +314,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!file->f_op->fallocate) return -EOPNOTSUPP; - sb_start_write(inode->i_sb); + file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* @@ -329,7 +327,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (ret == 0) fsnotify_modify(file); - sb_end_write(inode->i_sb); + file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index c48859f16e7b..67c24351a67f 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -115,6 +115,13 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb) return &orangefs_inode->vfs_inode; } +static void orangefs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); + kmem_cache_free(orangefs_inode_cache, orangefs_inode); +} + static void orangefs_destroy_inode(struct inode *inode) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); @@ -123,7 +130,7 @@ static void orangefs_destroy_inode(struct inode *inode) "%s: deallocated %p destroying inode %pU\n", __func__, orangefs_inode, get_khandle_from_ino(inode)); - kmem_cache_free(orangefs_inode_cache, orangefs_inode); + call_rcu(&inode->i_rcu, orangefs_i_callback); } /* diff --git a/fs/read_write.c b/fs/read_write.c index dc60075653a8..c4f88afbc67f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -24,9 +24,6 @@ #include <linux/uaccess.h> #include <asm/unistd.h> -typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); -typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *); - const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, @@ -371,7 +368,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) kiocb.ki_pos = *ppos; iter->type |= READ; - ret = file->f_op->read_iter(&kiocb, iter); + ret = call_read_iter(file, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; @@ -391,7 +388,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) kiocb.ki_pos = *ppos; iter->type |= WRITE; - ret = file->f_op->write_iter(&kiocb, iter); + ret = call_write_iter(file, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; @@ -440,7 +437,7 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo kiocb.ki_pos = *ppos; iov_iter_init(&iter, READ, &iov, 1, len); - ret = filp->f_op->read_iter(&kiocb, &iter); + ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; @@ -497,7 +494,7 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t kiocb.ki_pos = *ppos; iov_iter_init(&iter, WRITE, &iov, 1, len); - ret = filp->f_op->write_iter(&kiocb, &iter); + ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0) *ppos = kiocb.ki_pos; @@ -676,7 +673,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, iter_fn_t fn, int flags) + loff_t *ppos, int type, int flags) { struct kiocb kiocb; ssize_t ret; @@ -693,7 +690,10 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC); kiocb.ki_pos = *ppos; - ret = fn(&kiocb, iter); + if (type == READ) + ret = call_read_iter(filp, &kiocb, iter); + else + ret = call_write_iter(filp, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); *ppos = kiocb.ki_pos; return ret; @@ -701,7 +701,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, io_fn_t fn, int flags) + loff_t *ppos, int type, int flags) { ssize_t ret = 0; @@ -712,7 +712,13 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; - nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos); + if (type == READ) { + nr = filp->f_op->read(filp, iovec.iov_base, + iovec.iov_len, ppos); + } else { + nr = filp->f_op->write(filp, iovec.iov_base, + iovec.iov_len, ppos); + } if (nr < 0) { if (!ret) @@ -835,50 +841,32 @@ out: return ret; } -static ssize_t do_readv_writev(int type, struct file *file, - const struct iovec __user * uvector, - unsigned long nr_segs, loff_t *pos, - int flags) +static ssize_t __do_readv_writev(int type, struct file *file, + struct iov_iter *iter, loff_t *pos, int flags) { size_t tot_len; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; - ssize_t ret; - io_fn_t fn; - iter_fn_t iter_fn; - - ret = import_iovec(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), &iov, &iter); - if (ret < 0) - return ret; + ssize_t ret = 0; - tot_len = iov_iter_count(&iter); + tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; - if (type == READ) { - fn = file->f_op->read; - iter_fn = file->f_op->read_iter; - } else { - fn = (io_fn_t)file->f_op->write; - iter_fn = file->f_op->write_iter; + if (type != READ) file_start_write(file); - } - if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); + if ((type == READ && file->f_op->read_iter) || + (type == WRITE && file->f_op->write_iter)) + ret = do_iter_readv_writev(file, iter, pos, type, flags); else - ret = do_loop_readv_writev(file, &iter, pos, fn, flags); + ret = do_loop_readv_writev(file, iter, pos, type, flags); if (type != READ) file_end_write(file); out: - kfree(iov); if ((ret + (type == READ)) > 0) { if (type == READ) fsnotify_access(file); @@ -888,6 +876,27 @@ out: return ret; } +static ssize_t do_readv_writev(int type, struct file *file, + const struct iovec __user *uvector, + unsigned long nr_segs, loff_t *pos, + int flags) +{ + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; + + ret = import_iovec(type, uvector, nr_segs, + ARRAY_SIZE(iovstack), &iov, &iter); + if (ret < 0) + return ret; + + ret = __do_readv_writev(type, file, &iter, pos, flags); + kfree(iov); + + return ret; +} + ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, int flags) { @@ -1065,51 +1074,19 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, unsigned long nr_segs, loff_t *pos, int flags) { - compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; - io_fn_t fn; - iter_fn_t iter_fn; ret = compat_import_iovec(type, uvector, nr_segs, UIO_FASTIOV, &iov, &iter); if (ret < 0) return ret; - tot_len = iov_iter_count(&iter); - if (!tot_len) - goto out; - ret = rw_verify_area(type, file, pos, tot_len); - if (ret < 0) - goto out; - - if (type == READ) { - fn = file->f_op->read; - iter_fn = file->f_op->read_iter; - } else { - fn = (io_fn_t)file->f_op->write; - iter_fn = file->f_op->write_iter; - file_start_write(file); - } - - if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); - else - ret = do_loop_readv_writev(file, &iter, pos, fn, flags); - - if (type != READ) - file_end_write(file); - -out: + ret = __do_readv_writev(type, file, &iter, pos, flags); kfree(iov); - if ((ret + (type == READ)) > 0) { - if (type == READ) - fsnotify_access(file); - else - fsnotify_modify(file); - } + return ret; } @@ -1519,6 +1496,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (flags != 0) return -EINVAL; + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + return -EISDIR; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + return -EINVAL; + ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; @@ -1539,7 +1521,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (len == 0) return 0; - sb_start_write(inode_out->i_sb); + file_start_write(file_out); /* * Try cloning first, this is supported by more file systems, and @@ -1575,7 +1557,7 @@ done: inc_syscr(current); inc_syscw(current); - sb_end_write(inode_out->i_sb); + file_end_write(file_out); return ret; } diff --git a/fs/splice.c b/fs/splice.c index e49336555739..006ba50f4ece 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -309,7 +309,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, idx = to.idx; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; - ret = in->f_op->read_iter(&kiocb, &to); + ret = call_read_iter(in, &kiocb, &to); if (ret > 0) { *ppos = kiocb.ki_pos; file_accessed(in); diff --git a/fs/sync.c b/fs/sync.c index 2a54c1f22035..11ba023434b1 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -192,7 +192,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) spin_unlock(&inode->i_lock); mark_inode_dirty_sync(inode); } - return file->f_op->fsync(file, start, end, datasync); + return call_fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); diff --git a/include/keys/user-type.h b/include/keys/user-type.h index c56fef40f53e..e098cbe27db5 100644 --- a/include/keys/user-type.h +++ b/include/keys/user-type.h @@ -48,9 +48,14 @@ extern void user_describe(const struct key *user, struct seq_file *m); extern long user_read(const struct key *key, char __user *buffer, size_t buflen); -static inline const struct user_key_payload *user_key_payload(const struct key *key) +static inline const struct user_key_payload *user_key_payload_rcu(const struct key *key) { - return (struct user_key_payload *)rcu_dereference_key(key); + return (struct user_key_payload *)dereference_key_rcu(key); +} + +static inline struct user_key_payload *user_key_payload_locked(const struct key *key) +{ + return (struct user_key_payload *)dereference_key_locked((struct key *)key); } #endif /* CONFIG_KEYS */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h new file mode 100644 index 000000000000..b1ef6e14744f --- /dev/null +++ b/include/linux/blk-mq-virtio.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BLK_MQ_VIRTIO_H +#define _LINUX_BLK_MQ_VIRTIO_H + +struct blk_mq_tag_set; +struct virtio_device; + +int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set, + struct virtio_device *vdev, int first_vec); + +#endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index bb790c4db0c5..62d240e962f0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -26,7 +26,6 @@ enum cpuhp_state { CPUHP_ARM_OMAP_WAKE_DEAD, CPUHP_IRQ_POLL_DEAD, CPUHP_BLOCK_SOFTIRQ_DEAD, - CPUHP_VIRT_SCSI_DEAD, CPUHP_ACPI_CPUDRV_DEAD, CPUHP_S390_PFAULT_DEAD, CPUHP_BLK_MQ_DEAD, diff --git a/include/linux/fs.h b/include/linux/fs.h index c64f2cb7d364..52350947c670 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1567,6 +1567,9 @@ extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); +extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, + int open_flag); + /* * VFS file helper functions. */ @@ -1718,6 +1721,29 @@ struct inode_operations { int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; +static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, + struct iov_iter *iter) +{ + return file->f_op->read_iter(kio, iter); +} + +static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, + struct iov_iter *iter) +{ + return file->f_op->write_iter(kio, iter); +} + +static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +{ + return file->f_op->mmap(file, vma); +} + +static inline int call_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + return file->f_op->fsync(file, start, end, datasync); +} + ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, @@ -1744,19 +1770,6 @@ extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len) -{ - int ret; - - sb_start_write(file_inode(file_out)->i_sb); - ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); - sb_end_write(file_inode(file_out)->i_sb); - - return ret; -} - struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); @@ -2568,6 +2581,19 @@ static inline void file_end_write(struct file *file) __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } +static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len) +{ + int ret; + + file_start_write(file_out); + ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); + file_end_write(file_out); + + return ret; +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. diff --git a/include/linux/key.h b/include/linux/key.h index 722914798f37..e45212f2777e 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -354,7 +354,10 @@ static inline bool key_is_instantiated(const struct key *key) !test_bit(KEY_FLAG_NEGATIVE, &key->flags); } -#define rcu_dereference_key(KEY) \ +#define dereference_key_rcu(KEY) \ + (rcu_dereference((KEY)->payload.rcu_data0)) + +#define dereference_key_locked(KEY) \ (rcu_dereference_protected((KEY)->payload.rcu_data0, \ rwsem_is_locked(&((struct key *)(KEY))->sem))) diff --git a/include/linux/log2.h b/include/linux/log2.h index ef3d4f67118c..c373295f359f 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -16,12 +16,6 @@ #include <linux/bitops.h> /* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - -/* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() @@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index d4d34791e463..032b55909145 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -146,8 +146,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier); int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier); -int dev_pm_qos_add_global_notifier(struct notifier_block *notifier); -int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier); void dev_pm_qos_constraints_init(struct device *dev); void dev_pm_qos_constraints_destroy(struct device *dev); int dev_pm_qos_add_ancestor_request(struct device *dev, @@ -172,6 +170,12 @@ static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return dev->power.qos->flags_req->data.flr.flags; } + +static inline s32 dev_pm_qos_raw_read_value(struct device *dev) +{ + return IS_ERR_OR_NULL(dev->power.qos) ? + 0 : pm_qos_read_value(&dev->power.qos->resume_latency); +} #else static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) @@ -199,12 +203,6 @@ static inline int dev_pm_qos_add_notifier(struct device *dev, static inline int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier) { return 0; } -static inline int dev_pm_qos_add_global_notifier( - struct notifier_block *notifier) - { return 0; } -static inline int dev_pm_qos_remove_global_notifier( - struct notifier_block *notifier) - { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) { dev->power.power_state = PMSG_ON; @@ -236,6 +234,7 @@ static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {} static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; } static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; } +static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return 0; } #endif #endif diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 26c155bb639b..8355bab175e1 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -7,6 +7,8 @@ #include <linux/virtio_byteorder.h> #include <uapi/linux/virtio_config.h> +struct irq_affinity; + /** * virtio_config_ops - operations for configuring a virtio device * @get: read the value of a configuration field @@ -56,6 +58,7 @@ * This returns a pointer to the bus name a la pci_name from which * the caller can then copy. * @set_vq_affinity: set the affinity for a virtqueue. + * @get_vq_affinity: get the affinity for a virtqueue (optional). */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { @@ -68,14 +71,15 @@ struct virtio_config_ops { void (*set_status)(struct virtio_device *vdev, u8 status); void (*reset)(struct virtio_device *vdev); int (*find_vqs)(struct virtio_device *, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]); + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); int (*set_vq_affinity)(struct virtqueue *vq, int cpu); + const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, + int index); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -169,7 +173,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *callbacks[] = { c }; const char *names[] = { n }; struct virtqueue *vq; - int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names); + int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL); if (err < 0) return ERR_PTR(err); return vq; diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 1277e9ba0318..ff1a4f4cd66d 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -55,8 +55,12 @@ extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *); extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, struct iscsi_scsi_req *); -extern int iscsit_check_dataout_hdr(struct iscsi_conn *, unsigned char *, - struct iscsi_cmd **); +extern int +__iscsit_check_dataout_hdr(struct iscsi_conn *, void *, + struct iscsi_cmd *, u32, bool *); +extern int +iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, + struct iscsi_cmd **out_cmd); extern int iscsit_check_dataout_payload(struct iscsi_cmd *, struct iscsi_data *, bool); extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsi_cmd *, @@ -125,6 +129,9 @@ extern void iscsit_release_cmd(struct iscsi_cmd *); extern void iscsit_free_cmd(struct iscsi_cmd *, bool); extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8); +extern struct iscsi_cmd * +iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn, + itt_t init_task_tag, u32 length); /* * From iscsi_target_nego.c diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 774c29b57e82..37c274e61acc 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -199,6 +199,7 @@ enum tcm_tmreq_table { TMR_LUN_RESET = 5, TMR_TARGET_WARM_RESET = 6, TMR_TARGET_COLD_RESET = 7, + TMR_UNKNOWN = 0xff, }; /* fabric independent task management response values */ @@ -399,7 +400,6 @@ struct se_tmr_req { void *fabric_tmr_ptr; struct se_cmd *task_cmd; struct se_device *tmr_dev; - struct se_lun *tmr_lun; struct list_head tmr_list; }; @@ -490,8 +490,6 @@ struct se_cmd { #define CMD_T_COMPLETE (1 << 2) #define CMD_T_SENT (1 << 4) #define CMD_T_STOP (1 << 5) -#define CMD_T_DEV_ACTIVE (1 << 7) -#define CMD_T_BUSY (1 << 9) #define CMD_T_TAS (1 << 10) #define CMD_T_FABRIC_STOP (1 << 11) spinlock_t t_state_lock; @@ -734,6 +732,7 @@ struct se_lun { struct config_group lun_group; struct se_port_stat_grps port_stat_grps; struct completion lun_ref_comp; + struct completion lun_shutdown_comp; struct percpu_ref lun_ref; struct list_head lun_dev_link; struct hlist_node link; @@ -769,6 +768,8 @@ struct se_device { u32 dev_index; u64 creation_time; atomic_long_t num_resets; + atomic_long_t aborts_complete; + atomic_long_t aborts_no_task; atomic_long_t num_cmds; atomic_long_t read_bytes; atomic_long_t write_bytes; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 358041bad1da..d7dd1427fe0d 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -47,7 +47,7 @@ struct target_core_fabric_ops { u32 (*tpg_get_inst_index)(struct se_portal_group *); /* * Optional to release struct se_cmd and fabric dependent allocated - * I/O descriptor in transport_cmd_check_stop(). + * I/O descriptor after command execution has finished. * * Returning 1 will signal a descriptor has been released. * Returning 0 will signal a descriptor has not been released. diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 1c80efb67d10..dd9820b1c779 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -466,6 +466,7 @@ header-y += virtio_console.h header-y += virtio_gpu.h header-y += virtio_ids.h header-y += virtio_input.h +header-y += virtio_mmio.h header-y += virtio_net.h header-y += virtio_pci.h header-y += virtio_ring.h diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index c506cddb8165..af17b4154ef6 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -105,26 +105,26 @@ struct tcmu_cmd_entry { union { struct { - uint32_t iov_cnt; - uint32_t iov_bidi_cnt; - uint32_t iov_dif_cnt; - uint64_t cdb_off; - uint64_t __pad1; - uint64_t __pad2; + __u32 iov_cnt; + __u32 iov_bidi_cnt; + __u32 iov_dif_cnt; + __u64 cdb_off; + __u64 __pad1; + __u64 __pad2; struct iovec iov[0]; } req; struct { - uint8_t scsi_status; - uint8_t __pad1; - uint16_t __pad2; - uint32_t __pad3; + __u8 scsi_status; + __u8 __pad1; + __u16 __pad2; + __u32 __pad3; char sense_buffer[TCMU_SENSE_BUFFERSIZE]; } rsp; }; } __packed; -#define TCMU_OP_ALIGN_SIZE sizeof(uint64_t) +#define TCMU_OP_ALIGN_SIZE sizeof(__u64) enum tcmu_genl_cmd { TCMU_CMD_UNSPEC, diff --git a/include/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h index c4b09689ab64..c4b09689ab64 100644 --- a/include/linux/virtio_mmio.h +++ b/include/uapi/linux/virtio_mmio.h diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index 90007a1abcab..15b4385a2be1 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -79,7 +79,7 @@ * configuration space */ #define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20) /* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */ -#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled) +#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled) /* Virtio ABI version, this must match exactly */ #define VIRTIO_PCI_ABI_VERSION 0 diff --git a/ipc/shm.c b/ipc/shm.c index 06ea9ef7f54a..481d2a9c298a 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -423,7 +423,7 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) if (ret) return ret; - ret = sfd->file->f_op->mmap(sfd->file, vma); + ret = call_mmap(sfd->file, vma); if (ret) { shm_close(vma); return ret; @@ -452,7 +452,7 @@ static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) if (!sfd->file->f_op->fsync) return -EINVAL; - return sfd->file->f_op->fsync(sfd->file, start, end, datasync); + return call_fsync(sfd->file, start, end, datasync); } static long shm_fallocate(struct file *file, int mode, loff_t offset, diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b8be5c803cdd..a8b978c35a6a 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -10,6 +10,8 @@ * This file is released under the GPLv2. */ +#define pr_fmt(fmt) "PM: " fmt + #include <linux/export.h> #include <linux/suspend.h> #include <linux/syscalls.h> @@ -105,7 +107,7 @@ EXPORT_SYMBOL(system_entering_hibernation); #ifdef CONFIG_PM_DEBUG static void hibernation_debug_sleep(void) { - printk(KERN_INFO "hibernation debug: Waiting for 5 seconds.\n"); + pr_info("hibernation debug: Waiting for 5 seconds.\n"); mdelay(5000); } @@ -251,10 +253,9 @@ void swsusp_show_speed(ktime_t start, ktime_t stop, centisecs = 1; /* avoid div-by-zero */ k = nr_pages * (PAGE_SIZE / 1024); kps = (k * 100) / centisecs; - printk(KERN_INFO "PM: %s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n", - msg, k, - centisecs / 100, centisecs % 100, - kps / 1000, (kps % 1000) / 10); + pr_info("%s %u kbytes in %u.%02u seconds (%u.%02u MB/s)\n", + msg, k, centisecs / 100, centisecs % 100, kps / 1000, + (kps % 1000) / 10); } /** @@ -272,8 +273,7 @@ static int create_image(int platform_mode) error = dpm_suspend_end(PMSG_FREEZE); if (error) { - printk(KERN_ERR "PM: Some devices failed to power down, " - "aborting hibernation\n"); + pr_err("Some devices failed to power down, aborting hibernation\n"); return error; } @@ -289,8 +289,7 @@ static int create_image(int platform_mode) error = syscore_suspend(); if (error) { - printk(KERN_ERR "PM: Some system devices failed to power down, " - "aborting hibernation\n"); + pr_err("Some system devices failed to power down, aborting hibernation\n"); goto Enable_irqs; } @@ -305,8 +304,8 @@ static int create_image(int platform_mode) restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) - printk(KERN_ERR "PM: Error %d creating hibernation image\n", - error); + pr_err("Error %d creating hibernation image\n", error); + if (!in_suspend) { events_check_enabled = false; clear_free_pages(); @@ -433,8 +432,7 @@ static int resume_target_kernel(bool platform_mode) error = dpm_suspend_end(PMSG_QUIESCE); if (error) { - printk(KERN_ERR "PM: Some devices failed to power down, " - "aborting resume\n"); + pr_err("Some devices failed to power down, aborting resume\n"); return error; } @@ -609,6 +607,22 @@ static void power_down(void) { #ifdef CONFIG_SUSPEND int error; + + if (hibernation_mode == HIBERNATION_SUSPEND) { + error = suspend_devices_and_enter(PM_SUSPEND_MEM); + if (error) { + hibernation_mode = hibernation_ops ? + HIBERNATION_PLATFORM : + HIBERNATION_SHUTDOWN; + } else { + /* Restore swap signature. */ + error = swsusp_unmark(); + if (error) + pr_err("Swap will be unusable! Try swapon -a.\n"); + + return; + } + } #endif switch (hibernation_mode) { @@ -621,32 +635,13 @@ static void power_down(void) if (pm_power_off) kernel_power_off(); break; -#ifdef CONFIG_SUSPEND - case HIBERNATION_SUSPEND: - error = suspend_devices_and_enter(PM_SUSPEND_MEM); - if (error) { - if (hibernation_ops) - hibernation_mode = HIBERNATION_PLATFORM; - else - hibernation_mode = HIBERNATION_SHUTDOWN; - power_down(); - } - /* - * Restore swap signature. - */ - error = swsusp_unmark(); - if (error) - printk(KERN_ERR "PM: Swap will be unusable! " - "Try swapon -a.\n"); - return; -#endif } kernel_halt(); /* * Valid image is on the disk, if we continue we risk serious data * corruption after resume. */ - printk(KERN_CRIT "PM: Please power down manually\n"); + pr_crit("Power down manually\n"); while (1) cpu_relax(); } @@ -656,7 +651,7 @@ static int load_image_and_restore(void) int error; unsigned int flags; - pr_debug("PM: Loading hibernation image.\n"); + pr_debug("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); @@ -668,7 +663,7 @@ static int load_image_and_restore(void) if (!error) hibernation_restore(flags & SF_PLATFORM_MODE); - printk(KERN_ERR "PM: Failed to load hibernation image, recovering.\n"); + pr_err("Failed to load hibernation image, recovering.\n"); swsusp_free(); free_basic_memory_bitmaps(); Unlock: @@ -686,7 +681,7 @@ int hibernate(void) bool snapshot_test = false; if (!hibernation_available()) { - pr_debug("PM: Hibernation not available.\n"); + pr_debug("Hibernation not available.\n"); return -EPERM; } @@ -704,9 +699,9 @@ int hibernate(void) goto Exit; } - printk(KERN_INFO "PM: Syncing filesystems ... "); + pr_info("Syncing filesystems ... \n"); sys_sync(); - printk("done.\n"); + pr_info("done.\n"); error = freeze_processes(); if (error) @@ -732,7 +727,7 @@ int hibernate(void) else flags |= SF_CRC32_MODE; - pr_debug("PM: writing image.\n"); + pr_debug("Writing image.\n"); error = swsusp_write(flags); swsusp_free(); if (!error) { @@ -744,7 +739,7 @@ int hibernate(void) in_suspend = 0; pm_restore_gfp_mask(); } else { - pr_debug("PM: Image restored successfully.\n"); + pr_debug("Image restored successfully.\n"); } Free_bitmaps: @@ -752,7 +747,7 @@ int hibernate(void) Thaw: unlock_device_hotplug(); if (snapshot_test) { - pr_debug("PM: Checking hibernation image\n"); + pr_debug("Checking hibernation image\n"); error = swsusp_check(); if (!error) error = load_image_and_restore(); @@ -816,10 +811,10 @@ static int software_resume(void) goto Unlock; } - pr_debug("PM: Checking hibernation image partition %s\n", resume_file); + pr_debug("Checking hibernation image partition %s\n", resume_file); if (resume_delay) { - printk(KERN_INFO "Waiting %dsec before reading resume device...\n", + pr_info("Waiting %dsec before reading resume device ...\n", resume_delay); ssleep(resume_delay); } @@ -858,10 +853,10 @@ static int software_resume(void) } Check_image: - pr_debug("PM: Hibernation image partition %d:%d present\n", + pr_debug("Hibernation image partition %d:%d present\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); - pr_debug("PM: Looking for hibernation image.\n"); + pr_debug("Looking for hibernation image.\n"); error = swsusp_check(); if (error) goto Unlock; @@ -880,7 +875,7 @@ static int software_resume(void) goto Close_Finish; } - pr_debug("PM: Preparing processes for restore.\n"); + pr_debug("Preparing processes for restore.\n"); error = freeze_processes(); if (error) goto Close_Finish; @@ -893,7 +888,7 @@ static int software_resume(void) /* For success case, the suspend path will release the lock */ Unlock: mutex_unlock(&pm_mutex); - pr_debug("PM: Hibernation image not present or could not be loaded.\n"); + pr_debug("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: swsusp_close(FMODE_READ); @@ -1017,7 +1012,7 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, error = -EINVAL; if (!error) - pr_debug("PM: Hibernation mode set to '%s'\n", + pr_debug("Hibernation mode set to '%s'\n", hibernation_modes[mode]); unlock_system_sleep(); return error ? error : n; @@ -1053,7 +1048,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, lock_system_sleep(); swsusp_resume_device = res; unlock_system_sleep(); - printk(KERN_INFO "PM: Starting manual resume from disk\n"); + pr_info("Starting manual resume from disk\n"); noresume = 0; software_resume(); return n; diff --git a/lib/digsig.c b/lib/digsig.c index 55b8b2f41a9e..03d7c63837ae 100644 --- a/lib/digsig.c +++ b/lib/digsig.c @@ -85,7 +85,7 @@ static int digsig_verify_rsa(struct key *key, struct pubkey_hdr *pkh; down_read(&key->sem); - ukp = user_key_payload(key); + ukp = user_key_payload_locked(key); if (ukp->datalen < sizeof(*pkh)) goto err1; diff --git a/mm/mmap.c b/mm/mmap.c index 499b988b1639..bfbe8856d134 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1672,7 +1672,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); - error = file->f_op->mmap(file, vma); + error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; diff --git a/mm/nommu.c b/mm/nommu.c index 79abed514a4b..2d131b97a851 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1085,7 +1085,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + ret = call_mmap(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -1116,7 +1116,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * - VM_MAYSHARE will be set if it may attempt to share */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); + ret = call_mmap(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index bad3d4ae43f6..38dcf1eb427d 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -520,7 +520,8 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; int r; - r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len); + r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; return r; @@ -529,17 +530,20 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int page_offset, size_t length) { - void *kaddr; - int ret; + struct bio_vec bvec = { + .bv_page = page, + .bv_offset = page_offset, + .bv_len = length + }; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; BUG_ON(page_offset + length > PAGE_SIZE); - - kaddr = kmap(page); - BUG_ON(!kaddr); - ret = ceph_tcp_recvmsg(sock, kaddr + page_offset, length); - kunmap(page); - - return ret; + iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length); + r = sock_recvmsg(sock, &msg, msg.msg_flags); + if (r == -EAGAIN) + r = 0; + return r; } /* @@ -579,18 +583,28 @@ static int __ceph_tcp_sendpage(struct socket *sock, struct page *page, static int ceph_tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, bool more) { + struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + struct bio_vec bvec; int ret; - struct kvec iov; /* sendpage cannot properly handle pages with page_count == 0, * we need to fallback to sendmsg if that's the case */ if (page_count(page) >= 1) return __ceph_tcp_sendpage(sock, page, offset, size, more); - iov.iov_base = kmap(page) + offset; - iov.iov_len = size; - ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more); - kunmap(page); + bvec.bv_page = page; + bvec.bv_offset = offset; + bvec.bv_len = size; + + if (more) + msg.msg_flags |= MSG_MORE; + else + msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ + + iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size); + ret = sock_sendmsg(sock, &msg); + if (ret == -EAGAIN) + ret = 0; return ret; } diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index ab9fec00a788..af781010753b 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -72,7 +72,7 @@ int dns_query(const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry) { struct key *rkey; - const struct user_key_payload *upayload; + struct user_key_payload *upayload; const struct cred *saved_cred; size_t typelen, desclen; char *desc, *cp; @@ -143,7 +143,7 @@ int dns_query(const char *type, const char *name, size_t namelen, if (ret) goto put; - upayload = user_key_payload(rkey); + upayload = user_key_payload_locked(rkey); len = upayload->datalen; ret = -ENOMEM; diff --git a/net/rds/page.c b/net/rds/page.c index e2b5a5832d3d..7cc57e098ddb 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -45,35 +45,6 @@ struct rds_page_remainder { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders); -/* - * returns 0 on success or -errno on failure. - * - * We don't have to worry about flush_dcache_page() as this only works - * with private pages. If, say, we were to do directed receive to pinned - * user pages we'd have to worry more about cache coherence. (Though - * the flush_dcache_page() in get_user_pages() would probably be enough). - */ -int rds_page_copy_user(struct page *page, unsigned long offset, - void __user *ptr, unsigned long bytes, - int to_user) -{ - unsigned long ret; - void *addr; - - addr = kmap(page); - if (to_user) { - rds_stats_add(s_copy_to_user, bytes); - ret = copy_to_user(ptr, addr + offset, bytes); - } else { - rds_stats_add(s_copy_from_user, bytes); - ret = copy_from_user(addr + offset, ptr, bytes); - } - kunmap(page); - - return ret ? -EFAULT : 0; -} -EXPORT_SYMBOL_GPL(rds_page_copy_user); - /** * rds_page_remainder_alloc - build up regions of a message. * diff --git a/net/rds/rds.h b/net/rds/rds.h index 07fff73dd4f3..966d2ee1f107 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -798,13 +798,6 @@ static inline int rds_message_verify_checksum(const struct rds_header *hdr) /* page.c */ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes, gfp_t gfp); -int rds_page_copy_user(struct page *page, unsigned long offset, - void __user *ptr, unsigned long bytes, - int to_user); -#define rds_page_copy_to_user(page, offset, ptr, bytes) \ - rds_page_copy_user(page, offset, ptr, bytes, 1) -#define rds_page_copy_from_user(page, offset, ptr, bytes) \ - rds_page_copy_user(page, offset, ptr, bytes, 0) void rds_page_exit(void); /* recv.c */ diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 6788264acc63..9d24c0e958b1 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -532,7 +532,8 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->vdev = vdev; ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX, - vsock->vqs, callbacks, names); + vsock->vqs, callbacks, names, + NULL); if (ret < 0) goto out; diff --git a/security/keys/dh.c b/security/keys/dh.c index 531ed2ec132f..893af4c45038 100644 --- a/security/keys/dh.c +++ b/security/keys/dh.c @@ -55,7 +55,7 @@ static ssize_t mpi_from_key(key_serial_t keyid, size_t maxlen, MPI *mpi) if (status == 0) { const struct user_key_payload *payload; - payload = user_key_payload(key); + payload = user_key_payload_locked(key); if (maxlen == 0) { *mpi = NULL; diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c index 4fb315cddf5b..0010955d7876 100644 --- a/security/keys/encrypted-keys/encrypted.c +++ b/security/keys/encrypted-keys/encrypted.c @@ -314,7 +314,7 @@ static struct key *request_user_key(const char *master_desc, const u8 **master_k goto error; down_read(&ukey->sem); - upayload = user_key_payload(ukey); + upayload = user_key_payload_locked(ukey); *master_key = upayload->data; *master_keylen = upayload->datalen; error: @@ -926,7 +926,7 @@ static long encrypted_read(const struct key *key, char __user *buffer, size_t asciiblob_len; int ret; - epayload = rcu_dereference_key(key); + epayload = dereference_key_locked(key); /* returns the hex encoded iv, encrypted-data, and hmac as ascii */ asciiblob_len = epayload->datablob_len + ivsize + 1 diff --git a/security/keys/trusted.c b/security/keys/trusted.c index 90d61751ff12..2ae31c5a87de 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -1140,12 +1140,12 @@ out: static long trusted_read(const struct key *key, char __user *buffer, size_t buflen) { - struct trusted_key_payload *p; + const struct trusted_key_payload *p; char *ascii_buf; char *bufp; int i; - p = rcu_dereference_key(key); + p = dereference_key_locked(key); if (!p) return -EINVAL; if (!buffer || buflen <= 0) diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c index e187c8909d9d..26605134f17a 100644 --- a/security/keys/user_defined.c +++ b/security/keys/user_defined.c @@ -107,7 +107,7 @@ int user_update(struct key *key, struct key_preparsed_payload *prep) /* attach the new data, displacing the old */ key->expiry = prep->expiry; if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags)) - zap = rcu_dereference_key(key); + zap = dereference_key_locked(key); rcu_assign_keypointer(key, prep->payload.data[0]); prep->payload.data[0] = NULL; @@ -123,7 +123,7 @@ EXPORT_SYMBOL_GPL(user_update); */ void user_revoke(struct key *key) { - struct user_key_payload *upayload = key->payload.data[0]; + struct user_key_payload *upayload = user_key_payload_locked(key); /* clear the quota */ key_payload_reserve(key, 0); @@ -169,7 +169,7 @@ long user_read(const struct key *key, char __user *buffer, size_t buflen) const struct user_key_payload *upayload; long ret; - upayload = user_key_payload(key); + upayload = user_key_payload_locked(key); ret = upayload->datalen; /* we can return the data as is */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 57ff53696144..0c2ac318aa7f 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -481,12 +481,13 @@ static int selinux_is_sblabel_mnt(struct super_block *sb) sbsec->behavior == SECURITY_FS_USE_NATIVE || /* Special handling. Genfs but also in-core setxattr handler */ !strcmp(sb->s_type->name, "sysfs") || - !strcmp(sb->s_type->name, "cgroup") || - !strcmp(sb->s_type->name, "cgroup2") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || - !strcmp(sb->s_type->name, "rootfs"); + !strcmp(sb->s_type->name, "rootfs") || + (selinux_policycap_cgroupseclabel && + (!strcmp(sb->s_type->name, "cgroup") || + !strcmp(sb->s_type->name, "cgroup2"))); } static int sb_finish_set_opts(struct super_block *sb) diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index beaa14b8b6cf..f979c35e037e 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -71,6 +71,7 @@ enum { POLICYDB_CAPABILITY_OPENPERM, POLICYDB_CAPABILITY_EXTSOCKCLASS, POLICYDB_CAPABILITY_ALWAYSNETWORK, + POLICYDB_CAPABILITY_CGROUPSECLABEL, __POLICYDB_CAPABILITY_MAX }; #define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1) @@ -79,6 +80,7 @@ extern int selinux_policycap_netpeer; extern int selinux_policycap_openperm; extern int selinux_policycap_extsockclass; extern int selinux_policycap_alwaysnetwork; +extern int selinux_policycap_cgroupseclabel; /* * type_datum properties diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index c9e8a9898ce4..cb3fd98fb05a 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -46,7 +46,8 @@ static char *policycap_names[] = { "network_peer_controls", "open_perms", "extended_socket_class", - "always_check_network" + "always_check_network", + "cgroup_seclabel" }; unsigned int selinux_checkreqprot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index a70fcee9824b..b4aa491a0a23 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -74,6 +74,7 @@ int selinux_policycap_netpeer; int selinux_policycap_openperm; int selinux_policycap_extsockclass; int selinux_policycap_alwaysnetwork; +int selinux_policycap_cgroupseclabel; static DEFINE_RWLOCK(policy_rwlock); @@ -1993,6 +1994,9 @@ static void security_load_policycaps(void) POLICYDB_CAPABILITY_EXTSOCKCLASS); selinux_policycap_alwaysnetwork = ebitmap_get_bit(&policydb.policycaps, POLICYDB_CAPABILITY_ALWAYSNETWORK); + selinux_policycap_cgroupseclabel = + ebitmap_get_bit(&policydb.policycaps, + POLICYDB_CAPABILITY_CGROUPSECLABEL); } static int security_preserve_bools(struct policydb *p); diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h index 41446668ccce..d5677d39c1e4 100644 --- a/tools/include/linux/log2.h +++ b/tools/include/linux/log2.h @@ -13,12 +13,6 @@ #define _TOOLS_LINUX_LOG2_H /* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - -/* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented * more efficiently than using fls() and fls64() @@ -78,7 +72,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -141,10 +135,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 03cb639b292e..fedca3285326 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -16,9 +16,9 @@ idle power-state statistics, temperature and power on X86 processors. There are two ways to invoke turbostat. The first method is to supply a \fBcommand\fP, which is forked and statistics are printed -upon its completion. +in one-shot upon its completion. The second method is to omit the command, -and turbostat displays statistics every 5 seconds. +and turbostat displays statistics every 5 seconds interval. The 5-second interval can be changed using the --interval option. .PP Some information is not available on older processors. @@ -28,9 +28,10 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--add attributes\fP add column with counter having specified 'attributes'. The 'location' attribute is required, all others are optional. .nf - location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP} + location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP} msrDDD is a decimal offset, eg. msr16 msr0xXXX is a hex offset, eg. msr0x10 + /sys/path... is an absolute path to a sysfs attribute scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP} sample and print the counter for every cpu, core, or package. @@ -45,12 +46,21 @@ name as necessary to disambiguate it from others is necessary. Note that option 'delta' shows the difference in values during the measurement interval. 'percent' shows the delta as a percentage of the cycles elapsed. default: delta + + name: "name_string" + Any string that does not match a key-word above is used + as the column header. .fi .PP +\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set. If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed. Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed. Otherwise, the system summary plus the specified set of CPUs are printed. The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44 +.PP +\fB--hide column\fP do not show the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. +.PP +\fB--show column\fP show only the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. +.PP \fB--Dump\fP displays the raw counter values. .PP -\fB--debug\fP displays additional system configuration information. Invoking this parameter -more than once may also enable internal turbostat debug information. +\fB--quiet\fP Do not decode and print the system configuration header information. .PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP @@ -61,9 +71,7 @@ The file is truncated if it already exists, and it is created if it does not exi .PP \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts. .PP -\fB--Package\fP limits output to the system summary plus the 1st thread in each Package. -.PP -\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package. Ie. it skips hyper-threaded siblings. +\fB--list\fP display column header names available for use by --show and --hide, then exit. .PP \fB--Summary\fP limits output to a 1-line System Summary for each interval. .PP @@ -74,24 +82,25 @@ The file is truncated if it already exists, and it is created if it does not exi The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit, displays the statistics gathered since it was forked. .PP -.SH DEFAULT FIELD DESCRIPTIONS +.SH ROW DESCRIPTIONS +The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. +.SH COLUMN DESCRIPTIONS .nf +\fBCore\fP processor core number. Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT). \fBCPU\fP Linux CPU (logical processor) number. Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together. -\fBAVG_MHz\fP number of cycles executed divided by time elapsed. -\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state. -\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state). +\fBPackage\fP processor package number -- not present on systems with a single processor package. +\fBAvg_MHz\fP number of cycles executed divided by time elapsed. Note that this includes idle-time when 0 instructions are executed. +\fBBusy%\fP percent of the measurement interval that the CPU executes instructions, aka. % of time in "C0" state. +\fBBzy_MHz\fP average clock rate while the CPU was not idle (ie. in "c0" state). \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval. -.fi -.PP -.SH DEBUG FIELD DESCRIPTIONS -.nf -\fBPackage\fP processor package number. -\fBCore\fP processor core number. -Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT). -\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. +\fBIRQ\fP The number of interrupts serviced by that CPU during the measurement interval. The system total line is the sum of interrupts serviced across all CPUs. turbostat parses /proc/interrupts to generate this summary. +\fBSMI\fP The number of System Management Interrupts serviced CPU during the measurement interval. While this counter is actually per-CPU, SMI are triggered on all processors, so the number should be the same for all CPUs. +\fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval. The system summary line shows the sum for all CPUs. These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name. While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system. +\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. +\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. -\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. +\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. \fBPkgWatt\fP Watts consumed by the whole package. \fBCorWatt\fP Watts consumed by the core part of the package. \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors. @@ -99,51 +108,110 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. .fi +.SH TOO MUCH INFORMATION EXAMPLE +By default, turbostat dumps all possible information -- a system configuration header, followed by columns for all counters. +This is ideal for remote debugging, use the "--out" option to save everything to a text file, and get that file to the expert helping you debug. .PP -.SH PERIODIC EXAMPLE -Without any parameters, turbostat displays statistics ever 5 seconds. -Periodic output goes to stdout, by default, unless --out is used to specify an output file. -The 5-second interval can be changed with th "-i sec" option. -Or a command may be specified as in "FORK EXAMPLE" below. +When you are not interested in all that information, and there are several ways to see only what you want. First the "--quiet" option will skip the configuration information, and turbostat will show only the counter columns. Second, you can reduce the columns with the "--hide" and "--show" options. If you use the "--show" option, then turbostat will show only the columns you list. If you use the "--hide" option, turbostat will show all columns, except the ones you list. +.PP +To find out what columns are available for --show and --hide, the "--list" option is available. For convenience, the special strings "sysfs" can be used to refer to all of the sysfs C-state counters at once: +.nf +sudo ./turbostat --show sysfs --quiet sleep 10 +10.003837 sec + C1 C1E C3 C6 C7s C1% C1E% C3% C6% C7s% + 4 21 2 2 459 0.14 0.82 0.00 0.00 98.93 + 1 17 2 2 130 0.00 0.02 0.00 0.00 99.80 + 0 0 0 0 31 0.00 0.00 0.00 0.00 99.95 + 2 1 0 0 52 1.14 6.49 0.00 0.00 92.21 + 1 2 0 0 52 0.00 0.08 0.00 0.00 99.86 + 0 0 0 0 71 0.00 0.00 0.00 0.00 99.89 + 0 0 0 0 25 0.00 0.00 0.00 0.00 99.96 + 0 0 0 0 74 0.00 0.00 0.00 0.00 99.94 + 0 1 0 0 24 0.00 0.00 0.00 0.00 99.84 +.fi +.PP +.SH ONE SHOT COMMAND EXAMPLE +If turbostat is invoked with a command, it will fork that command +and output the statistics gathered after the command exits. +In this case, turbostat output goes to stderr, by default. +Output can instead be saved to a file using the --out option. +In this example, the "sleep 10" command is forked, and turbostat waits for it to complete before saving all statistics into "ts.out". Note that "sleep 10" is not part of turbostat, but is simply an example of a command that turbostat can fork. The "ts.out" file is what you want to edit in a very wide window, paste into a spreadsheet, or attach to a bugzilla entry. + .nf -[root@hsw]# ./turbostat - CPU Avg_MHz Busy% Bzy_MHz TSC_MHz - - 488 12.51 3898 3498 - 0 0 0.01 3885 3498 - 4 3897 99.99 3898 3498 - 1 0 0.00 3861 3498 - 5 0 0.00 3882 3498 - 2 1 0.02 3894 3498 - 6 2 0.06 3898 3498 - 3 0 0.00 3849 3498 - 7 0 0.00 3877 3498 +[root@hsw]# ./turbostat -o ts.out sleep 10 +[root@hsw]# +.fi +.SH PERIODIC INTERVAL EXAMPLE +Without a command to fork, turbostat displays statistics ever 5 seconds. +Periodic output goes to stdout, by default, unless --out is used to specify an output file. +The 5-second interval can be changed with the "-i sec" option. +.nf +sudo ./turbostat --quiet --hide sysfs,IRQ,SMI,CoreTmp,PkgTmp,GFX%rc6,GFXMHz,PkgWatt,CorWatt,GFXWatt + Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz CPU%c1 CPU%c3 CPU%c6 CPU%c7 + - - 488 12.52 3900 3498 12.50 0.00 0.00 74.98 + 0 0 5 0.13 3900 3498 99.87 0.00 0.00 0.00 + 0 4 3897 99.99 3900 3498 0.01 + 1 1 0 0.00 3856 3498 0.01 0.00 0.00 99.98 + 1 5 0 0.00 3861 3498 0.01 + 2 2 1 0.02 3889 3498 0.03 0.00 0.00 99.95 + 2 6 0 0.00 3863 3498 0.05 + 3 3 0 0.01 3869 3498 0.02 0.00 0.00 99.97 + 3 7 0 0.00 3878 3498 0.03 + Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz CPU%c1 CPU%c3 CPU%c6 CPU%c7 + - - 491 12.59 3900 3498 12.42 0.00 0.00 74.99 + 0 0 27 0.69 3900 3498 99.31 0.00 0.00 0.00 + 0 4 3898 99.99 3900 3498 0.01 + 1 1 0 0.00 3883 3498 0.01 0.00 0.00 99.99 + 1 5 0 0.00 3898 3498 0.01 + 2 2 0 0.01 3889 3498 0.02 0.00 0.00 99.98 + 2 6 0 0.00 3889 3498 0.02 + 3 3 0 0.00 3856 3498 0.01 0.00 0.00 99.99 + 3 7 0 0.00 3897 3498 0.01 .fi -.SH DEBUG EXAMPLE -The "--debug" option prints additional system information before measurements: +This example also shows the use of the --hide option to skip columns that are not wanted. +Note that cpu4 in this example is 99.99% busy, while the other CPUs are all under 1% busy. +Notice that cpu4's HT sibling is cpu0, which is under 1% busy, but can get into CPU%c1 only, +because its cpu4's activity on shared hardware keeps it from entering a deeper C-state. -The first row of statistics is a summary for the entire system. -For residency % columns, the summary is a weighted average. -For Temperature columns, the summary is the column maximum. -For Watts columns, the summary is a system total. -Subsequent rows show per-CPU statistics. +.SH SYSTEM CONFIGURATION INFORMATION EXAMPLE + +By default, turbostat always dumps system configuration information +before taking measurements. In the example above, "--quiet" is used +to suppress that output. Here is an example of the configuration information: .nf -turbostat version 4.1 10-Feb, 2015 - Len Brown <lenb@kernel.org> +turbostat version 2017.02.15 - Len Brown <lenb@kernel.org> CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3c:3 (6:60:3) -CPUID(6): APERF, DTS, PTM, EPB +CPUID(1): SSE3 MONITOR - EIST TM2 TSC MSR ACPI-TM TM +CPUID(6): APERF, TURBO, DTS, PTM, No-HWP, No-HWPnotify, No-HWPwindow, No-HWPepp, No-HWPpkg, EPB +cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST No-MWAIT PREFETCH TURBO) +CPUID(7): No-SGX +cpu4: MSR_MISC_PWR_MGMT: 0x00400000 (ENable-EIST_Coordination DISable-EPB DISable-OOB) RAPL: 3121 sec. Joule Counter Range, at 84 Watts -cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300 -8 * 100 = 800 MHz max efficiency -35 * 100 = 3500 MHz TSC frequency -cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled) -cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0) -cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727 -37 * 100 = 3700 MHz max turbo 4 active cores -38 * 100 = 3800 MHz max turbo 3 active cores -39 * 100 = 3900 MHz max turbo 2 active cores -39 * 100 = 3900 MHz max turbo 1 active cores +cpu4: MSR_PLATFORM_INFO: 0x80838f3012300 +8 * 100.0 = 800.0 MHz max efficiency frequency +35 * 100.0 = 3500.0 MHz base frequency +cpu4: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled) +cpu4: MSR_TURBO_RATIO_LIMIT: 0x25262727 +37 * 100.0 = 3700.0 MHz max turbo 4 active cores +38 * 100.0 = 3800.0 MHz max turbo 3 active cores +39 * 100.0 = 3900.0 MHz max turbo 2 active cores +39 * 100.0 = 3900.0 MHz max turbo 1 active cores +cpu4: MSR_CONFIG_TDP_NOMINAL: 0x00000023 (base_ratio=35) +cpu4: MSR_CONFIG_TDP_LEVEL_1: 0x00000000 () +cpu4: MSR_CONFIG_TDP_LEVEL_2: 0x00000000 () +cpu4: MSR_CONFIG_TDP_CONTROL: 0x80000000 ( lock=1) +cpu4: MSR_TURBO_ACTIVATION_RATIO: 0x00000000 (MAX_NON_TURBO_RATIO=0 lock=0) +cpu4: MSR_PKG_CST_CONFIG_CONTROL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0) +cpu4: POLL: CPUIDLE CORE POLL IDLE +cpu4: C1: MWAIT 0x00 +cpu4: C1E: MWAIT 0x01 +cpu4: C3: MWAIT 0x10 +cpu4: C6: MWAIT 0x20 +cpu4: C7s: MWAIT 0x32 +cpu4: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch) cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced) -cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Auto-HWP, Amps, MultiCoreTurbo, Transitions, ) +cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Transitions, MultiCoreTurbo, Amps, Auto-HWP, ) cpu0: MSR_GFX_PERF_LIMIT_REASONS, 0x00000000 (Active: ) (Logged: ) cpu0: MSR_RING_PERF_LIMIT_REASONS, 0x0d000000 (Active: ) (Logged: Amps, PkgPwrL1, PkgPwrL2, ) cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.) @@ -158,23 +226,14 @@ cpu0: MSR_PP1_POLICY: 0 cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked) cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled) cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00641400 (100 C) -cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88340800 (48 C) -cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1) -cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1) -cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1) -cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1) - Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp PkgWatt CorWatt GFXWatt - - - 493 12.64 3898 3498 0 12.64 0.00 0.00 74.72 47 47 21.62 13.74 0.00 - 0 0 4 0.11 3894 3498 0 99.89 0.00 0.00 0.00 47 47 21.62 13.74 0.00 - 0 4 3897 99.98 3898 3498 0 0.02 - 1 1 7 0.17 3887 3498 0 0.04 0.00 0.00 99.79 32 - 1 5 0 0.00 3885 3498 0 0.21 - 2 2 29 0.76 3895 3498 0 0.10 0.01 0.01 99.13 32 - 2 6 2 0.06 3896 3498 0 0.80 - 3 3 1 0.02 3832 3498 0 0.03 0.00 0.00 99.95 28 - 3 7 0 0.00 3879 3498 0 0.04 -^C - +cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884c0800 (24 C) +cpu0: MSR_IA32_THERM_STATUS: 0x884c0000 (24 C +/- 1) +cpu1: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1) +cpu2: MSR_IA32_THERM_STATUS: 0x884e0000 (22 C +/- 1) +cpu3: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1) +cpu4: MSR_PKGC3_IRTL: 0x00008842 (valid, 67584 ns) +cpu4: MSR_PKGC6_IRTL: 0x00008873 (valid, 117760 ns) +cpu4: MSR_PKGC7_IRTL: 0x00008891 (valid, 148480 ns) .fi The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency available at the minimum package voltage. The \fBTSC frequency\fP is the base @@ -184,42 +243,22 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling. The remaining rows show what maximum turbo frequency is possible depending on the number of idle cores. Note that not all information is available on all processors. -.PP -The --debug option adds additional columns to the measurement ouput, including CPU idle power-state residency processor temperature sensor readinds. -See the field definitions above. -.SH FORK EXAMPLE -If turbostat is invoked with a command, it will fork that command -and output the statistics gathered after the command exits. -In this case, turbostat output goes to stderr, by default. -Output can instead be saved to a file using the --out option. -eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds -until ^C while the other CPUs are mostly idle: - +.SH ADD COUNTER EXAMPLE +Here we limit turbostat to showing just the CPU number for cpu0 - cpu3. +We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL), +labeling it with the column header, "PRF_CTRL", and display it only once, +afte the conclusion of a 0.1 second sleep. .nf -root@hsw: turbostat cat /dev/zero > /dev/null -^C - CPU Avg_MHz Busy% Bzy_MHz TSC_MHz - - 482 12.51 3854 3498 - 0 0 0.01 1960 3498 - 4 0 0.00 2128 3498 - 1 0 0.00 3003 3498 - 5 3854 99.98 3855 3498 - 2 0 0.01 3504 3498 - 6 3 0.08 3884 3498 - 3 0 0.00 2553 3498 - 7 0 0.00 2126 3498 -10.783983 sec +sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1 +0.101604 sec +CPU PRF_CTRL +- 0x00000000 +0 0x00000c00 +1 0x00000800 +2 0x00000a00 +3 0x00000800 .fi -Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit. -The first row shows the average MHz and Busy% across all the processors in the system. - -Note that the Avg_MHz column reflects the total number of cycles executed -divided by the measurement interval. If the Busy% column is 100%, -then the processor was running at that speed the entire interval. -The Avg_MHz multiplied by the Busy% results in the Bzy_MHz -- -which is the average frequency while the processor was executing -- -not including any non-busy idle time. .SH NOTES diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index f13f61b065c6..828dccd3f01e 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -49,17 +49,14 @@ FILE *outf; int *fd_percpu; struct timespec interval_ts = {5, 0}; unsigned int debug; +unsigned int quiet; +unsigned int sums_need_wide_columns; unsigned int rapl_joules; unsigned int summary_only; +unsigned int list_header_only; unsigned int dump_only; -unsigned int do_nhm_cstates; unsigned int do_snb_cstates; unsigned int do_knl_cstates; -unsigned int do_pc2; -unsigned int do_pc3; -unsigned int do_pc6; -unsigned int do_pc7; -unsigned int do_c8_c9_c10; unsigned int do_skl_residency; unsigned int do_slm_cstates; unsigned int use_c1_residency_msr; @@ -71,25 +68,19 @@ unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; +unsigned int no_MSR_MISC_PWR_MGMT; unsigned int aperf_mperf_multiplier = 1; -int do_irq = 1; -int do_smi; double bclk; double base_hz; unsigned int has_base_hz; double tsc_tweak = 1.0; -unsigned int show_pkg; -unsigned int show_core; -unsigned int show_cpu; unsigned int show_pkg_only; unsigned int show_core_only; char *output_buffer, *outp; unsigned int do_rapl; unsigned int do_dts; unsigned int do_ptm; -unsigned int do_gfx_rc6_ms; unsigned long long gfx_cur_rc6_ms; -unsigned int do_gfx_mhz; unsigned int gfx_cur_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; @@ -109,6 +100,7 @@ unsigned int has_hwp_notify; /* IA32_HWP_INTERRUPT */ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ +unsigned int has_misc_feature_control; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -148,34 +140,38 @@ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters */ #define NAME_BYTES 20 +#define PATH_BYTES 128 int backwards_count; char *progname; -cpu_set_t *cpu_present_set, *cpu_affinity_set; -size_t cpu_present_setsize, cpu_affinity_setsize; +#define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ +cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; +#define MAX_ADDED_COUNTERS 16 struct thread_data { unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; unsigned long long c1; - unsigned int irq_count; + unsigned long long irq_count; unsigned int smi_count; unsigned int cpu_id; unsigned int flags; #define CPU_IS_FIRST_THREAD_IN_CORE 0x2 #define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *thread_even, *thread_odd; struct core_data { unsigned long long c3; unsigned long long c6; unsigned long long c7; + unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; unsigned int core_id; - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *core_even, *core_odd; struct pkg_data { @@ -200,7 +196,7 @@ struct pkg_data { unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; #define ODD_COUNTERS thread_odd, core_odd, package_odd @@ -215,22 +211,27 @@ struct pkg_data { #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no) enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE}; -enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS}; +enum counter_type {COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC}; enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT}; struct msr_counter { unsigned int msr_num; char name[NAME_BYTES]; + char path[PATH_BYTES]; unsigned int width; enum counter_type type; enum counter_format format; struct msr_counter *next; + unsigned int flags; +#define FLAGS_HIDE (1 << 0) +#define FLAGS_SHOW (1 << 1) +#define SYSFS_PERCPU (1 << 1) }; struct sys_counters { - unsigned int thread_counter_bytes; - unsigned int core_counter_bytes; - unsigned int package_counter_bytes; + unsigned int added_thread_counters; + unsigned int added_core_counters; + unsigned int added_package_counters; struct msr_counter *tp; struct msr_counter *cp; struct msr_counter *pp; @@ -334,147 +335,333 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset); if (retval != sizeof *msr) - err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset); + err(-1, "cpu%d: msr offset 0x%llx read failed", cpu, (unsigned long long)offset); return 0; } /* - * Example Format w/ field column widths: - * - * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz IRQ SMI Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp CoreCnt PkgTmp GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt - * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678 + * Each string in this array is compared in --show and --hide cmdline. + * Thus, strings that are proper sub-sets must follow their more specific peers. + */ +struct msr_counter bic[] = { + { 0x0, "Package" }, + { 0x0, "Avg_MHz" }, + { 0x0, "Bzy_MHz" }, + { 0x0, "TSC_MHz" }, + { 0x0, "IRQ" }, + { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL}, + { 0x0, "Busy%" }, + { 0x0, "CPU%c1" }, + { 0x0, "CPU%c3" }, + { 0x0, "CPU%c6" }, + { 0x0, "CPU%c7" }, + { 0x0, "ThreadC" }, + { 0x0, "CoreTmp" }, + { 0x0, "CoreCnt" }, + { 0x0, "PkgTmp" }, + { 0x0, "GFX%rc6" }, + { 0x0, "GFXMHz" }, + { 0x0, "Pkg%pc2" }, + { 0x0, "Pkg%pc3" }, + { 0x0, "Pkg%pc6" }, + { 0x0, "Pkg%pc7" }, + { 0x0, "Pkg%pc8" }, + { 0x0, "Pkg%pc9" }, + { 0x0, "Pkg%pc10" }, + { 0x0, "PkgWatt" }, + { 0x0, "CorWatt" }, + { 0x0, "GFXWatt" }, + { 0x0, "PkgCnt" }, + { 0x0, "RAMWatt" }, + { 0x0, "PKG_%" }, + { 0x0, "RAM_%" }, + { 0x0, "Pkg_J" }, + { 0x0, "Cor_J" }, + { 0x0, "GFX_J" }, + { 0x0, "RAM_J" }, + { 0x0, "Core" }, + { 0x0, "CPU" }, + { 0x0, "Mod%c6" }, + { 0x0, "sysfs" }, +}; + +#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) +#define BIC_Package (1ULL << 0) +#define BIC_Avg_MHz (1ULL << 1) +#define BIC_Bzy_MHz (1ULL << 2) +#define BIC_TSC_MHz (1ULL << 3) +#define BIC_IRQ (1ULL << 4) +#define BIC_SMI (1ULL << 5) +#define BIC_Busy (1ULL << 6) +#define BIC_CPU_c1 (1ULL << 7) +#define BIC_CPU_c3 (1ULL << 8) +#define BIC_CPU_c6 (1ULL << 9) +#define BIC_CPU_c7 (1ULL << 10) +#define BIC_ThreadC (1ULL << 11) +#define BIC_CoreTmp (1ULL << 12) +#define BIC_CoreCnt (1ULL << 13) +#define BIC_PkgTmp (1ULL << 14) +#define BIC_GFX_rc6 (1ULL << 15) +#define BIC_GFXMHz (1ULL << 16) +#define BIC_Pkgpc2 (1ULL << 17) +#define BIC_Pkgpc3 (1ULL << 18) +#define BIC_Pkgpc6 (1ULL << 19) +#define BIC_Pkgpc7 (1ULL << 20) +#define BIC_Pkgpc8 (1ULL << 21) +#define BIC_Pkgpc9 (1ULL << 22) +#define BIC_Pkgpc10 (1ULL << 23) +#define BIC_PkgWatt (1ULL << 24) +#define BIC_CorWatt (1ULL << 25) +#define BIC_GFXWatt (1ULL << 26) +#define BIC_PkgCnt (1ULL << 27) +#define BIC_RAMWatt (1ULL << 28) +#define BIC_PKG__ (1ULL << 29) +#define BIC_RAM__ (1ULL << 30) +#define BIC_Pkg_J (1ULL << 31) +#define BIC_Cor_J (1ULL << 32) +#define BIC_GFX_J (1ULL << 33) +#define BIC_RAM_J (1ULL << 34) +#define BIC_Core (1ULL << 35) +#define BIC_CPU (1ULL << 36) +#define BIC_Mod_c6 (1ULL << 37) +#define BIC_sysfs (1ULL << 38) + +unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL; +unsigned long long bic_present = BIC_sysfs; + +#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) +#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) + +#define MAX_DEFERRED 16 +char *deferred_skip_names[MAX_DEFERRED]; +int deferred_skip_index; + +/* + * HIDE_LIST - hide this list of counters, show the rest [default] + * SHOW_LIST - show this list of counters, hide the rest */ +enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST; -void print_header(void) +void help(void) { - struct msr_counter *mp; + fprintf(outf, + "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n" + "\n" + "Turbostat forks the specified COMMAND and prints statistics\n" + "when COMMAND completes.\n" + "If no COMMAND is specified, turbostat wakes every 5-seconds\n" + "to print statistics, until interrupted.\n" + "--add add a counter\n" + " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" + "--cpu cpu-set limit output to summary plus cpu-set:\n" + " {core | package | j,k,l..m,n-p }\n" + "--quiet skip decoding system configuration header\n" + "--interval sec Override default 5-second measurement interval\n" + "--help print this help message\n" + "--list list column headers only\n" + "--out file create or truncate \"file\" for all output\n" + "--version print version information\n" + "\n" + "For more help, run \"man turbostat\"\n"); +} - if (show_pkg) - outp += sprintf(outp, "\tPackage"); - if (show_core) - outp += sprintf(outp, "\tCore"); - if (show_cpu) - outp += sprintf(outp, "\tCPU"); - if (has_aperf) - outp += sprintf(outp, "\tAvg_MHz"); - if (has_aperf) - outp += sprintf(outp, "\tBusy%%"); - if (has_aperf) - outp += sprintf(outp, "\tBzy_MHz"); - outp += sprintf(outp, "\tTSC_MHz"); +/* + * bic_lookup + * for all the strings in comma separate name_list, + * set the approprate bit in return value. + */ +unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) +{ + int i; + unsigned long long retval = 0; - if (!debug) - goto done; + while (name_list) { + char *comma; - if (do_irq) - outp += sprintf(outp, "\tIRQ"); - if (do_smi) - outp += sprintf(outp, "\tSMI"); - - if (do_nhm_cstates) - outp += sprintf(outp, "\tCPU%%c1"); - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) - outp += sprintf(outp, "\tCPU%%c3"); - if (do_nhm_cstates) - outp += sprintf(outp, "\tCPU%%c6"); - if (do_snb_cstates) - outp += sprintf(outp, "\tCPU%%c7"); + comma = strchr(name_list, ','); + + if (comma) + *comma = '\0'; + + for (i = 0; i < MAX_BIC; ++i) { + if (!strcmp(name_list, bic[i].name)) { + retval |= (1ULL << i); + break; + } + } + if (i == MAX_BIC) { + if (mode == SHOW_LIST) { + fprintf(stderr, "Invalid counter name: %s\n", name_list); + exit(-1); + } + deferred_skip_names[deferred_skip_index++] = name_list; + if (debug) + fprintf(stderr, "deferred \"%s\"\n", name_list); + if (deferred_skip_index >= MAX_DEFERRED) { + fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n", + MAX_DEFERRED, name_list); + help(); + exit(1); + } + } + + name_list = comma; + if (name_list) + name_list++; + + } + return retval; +} + + +void print_header(char *delim) +{ + struct msr_counter *mp; + int printed = 0; + + if (DO_BIC(BIC_Package)) + outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); + if (DO_BIC(BIC_Core)) + outp += sprintf(outp, "%sCore", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%sCPU", (printed++ ? delim : "")); + if (DO_BIC(BIC_Avg_MHz)) + outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Busy)) + outp += sprintf(outp, "%sBusy%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_Bzy_MHz)) + outp += sprintf(outp, "%sBzy_MHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_TSC_MHz)) + outp += sprintf(outp, "%sTSC_MHz", (printed++ ? delim : "")); + + if (DO_BIC(BIC_IRQ)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s IRQ", (printed++ ? delim : "")); + else + outp += sprintf(outp, "%sIRQ", (printed++ ? delim : "")); + } + + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "%sSMI", (printed++ ? delim : "")); for (mp = sys.tp; mp; mp = mp->next) { + if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), mp->name); + else + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), mp->name); } } - if (do_dts) - outp += sprintf(outp, "\tCoreTmp"); + if (DO_BIC(BIC_CPU_c1)) + outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c6)) + outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c7)) + outp += sprintf(outp, "%sCPU%%c7", (printed++ ? delim : "")); + + if (DO_BIC(BIC_Mod_c6)) + outp += sprintf(outp, "%sMod%%c6", (printed++ ? delim : "")); + + if (DO_BIC(BIC_CoreTmp)) + outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : "")); for (mp = sys.cp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", delim, mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", delim, mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", delim, mp->name); + else + outp += sprintf(outp, "%s%s", delim, mp->name); } } - if (do_ptm) - outp += sprintf(outp, "\tPkgTmp"); + if (DO_BIC(BIC_PkgTmp)) + outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : "")); - if (do_gfx_rc6_ms) - outp += sprintf(outp, "\tGFX%%rc6"); + if (DO_BIC(BIC_GFX_rc6)) + outp += sprintf(outp, "%sGFX%%rc6", (printed++ ? delim : "")); - if (do_gfx_mhz) - outp += sprintf(outp, "\tGFXMHz"); + if (DO_BIC(BIC_GFXMHz)) + outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); if (do_skl_residency) { - outp += sprintf(outp, "\tTotl%%C0"); - outp += sprintf(outp, "\tAny%%C0"); - outp += sprintf(outp, "\tGFX%%C0"); - outp += sprintf(outp, "\tCPUGFX%%"); - } - - if (do_pc2) - outp += sprintf(outp, "\tPkg%%pc2"); - if (do_pc3) - outp += sprintf(outp, "\tPkg%%pc3"); - if (do_pc6) - outp += sprintf(outp, "\tPkg%%pc6"); - if (do_pc7) - outp += sprintf(outp, "\tPkg%%pc7"); - if (do_c8_c9_c10) { - outp += sprintf(outp, "\tPkg%%pc8"); - outp += sprintf(outp, "\tPkg%%pc9"); - outp += sprintf(outp, "\tPk%%pc10"); + outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sAny%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sGFX%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sCPUGFX%%", (printed++ ? delim : "")); } + if (DO_BIC(BIC_Pkgpc2)) + outp += sprintf(outp, "%sPkg%%pc2", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc3)) + outp += sprintf(outp, "%sPkg%%pc3", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc6)) + outp += sprintf(outp, "%sPkg%%pc6", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc7)) + outp += sprintf(outp, "%sPkg%%pc7", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc8)) + outp += sprintf(outp, "%sPkg%%pc8", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc9)) + outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc10)) + outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : "")); + if (do_rapl && !rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "\tPkgWatt"); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, "\tCorWatt"); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "\tGFXWatt"); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "\tRAMWatt"); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, "\tPKG_%%"); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, "\tRAM_%%"); + if (DO_BIC(BIC_PkgWatt)) + outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_CorWatt)) + outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXWatt)) + outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAMWatt)) + outp += sprintf(outp, "%sRAMWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : "")); } else if (do_rapl && rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "\tPkg_J"); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, "\tCor_J"); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "\tGFX_J"); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "\tRAM_J"); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, "\tPKG_%%"); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, "\tRAM_%%"); + if (DO_BIC(BIC_Pkg_J)) + outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_Cor_J)) + outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFX_J)) + outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM_J)) + outp += sprintf(outp, "%sRAM_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : "")); } for (mp = sys.pp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", delim, mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", delim, mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", delim, mp->name); + else + outp += sprintf(outp, "%s%s", delim, mp->name); } } -done: outp += sprintf(outp, "\n"); } @@ -494,10 +681,10 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "mperf: %016llX\n", t->mperf); outp += sprintf(outp, "c1: %016llX\n", t->c1); - if (do_irq) - outp += sprintf(outp, "IRQ: %08X\n", t->irq_count); - if (do_smi) - outp += sprintf(outp, "SMI: %08X\n", t->smi_count); + if (DO_BIC(BIC_IRQ)) + outp += sprintf(outp, "IRQ: %lld\n", t->irq_count); + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "SMI: %d\n", t->smi_count); for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", @@ -516,6 +703,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]); } + outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us); } if (p) { @@ -527,11 +715,11 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "CPU + GFX: %016llX\n", p->pkg_both_core_gfxe_c0); outp += sprintf(outp, "pc2: %016llX\n", p->pc2); - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) outp += sprintf(outp, "pc3: %016llX\n", p->pc3); - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) outp += sprintf(outp, "pc6: %016llX\n", p->pc6); - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) outp += sprintf(outp, "pc7: %016llX\n", p->pc7); outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); @@ -563,10 +751,12 @@ int dump_counters(struct thread_data *t, struct core_data *c, int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { - double interval_float; + double interval_float, tsc; char *fmt8; int i; struct msr_counter *mp; + char *delim = "\t"; + int printed = 0; /* if showing only 1st thread in core and this isn't one, bail out */ if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) @@ -576,106 +766,126 @@ int format_counters(struct thread_data *t, struct core_data *c, if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; + /*if not summary line and --cpu is used */ + if ((t != &average.threads) && + (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset))) + return 0; + interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; + tsc = t->tsc * tsc_tweak; + /* topo columns, print blanks on 1st (average) line */ if (t == &average.threads) { - if (show_pkg) - outp += sprintf(outp, "\t-"); - if (show_core) - outp += sprintf(outp, "\t-"); - if (show_cpu) - outp += sprintf(outp, "\t-"); + if (DO_BIC(BIC_Package)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_Core)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } else { - if (show_pkg) { + if (DO_BIC(BIC_Package)) { if (p) - outp += sprintf(outp, "\t%d", p->package_id); + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->package_id); else - outp += sprintf(outp, "\t-"); + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } - if (show_core) { + if (DO_BIC(BIC_Core)) { if (c) - outp += sprintf(outp, "\t%d", c->core_id); + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id); else - outp += sprintf(outp, "\t-"); + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } - if (show_cpu) - outp += sprintf(outp, "\t%d", t->cpu_id); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id); } - /* Avg_MHz */ - if (has_aperf) - outp += sprintf(outp, "\t%.0f", + if (DO_BIC(BIC_Avg_MHz)) + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 / units * t->aperf / interval_float); - /* Busy% */ - if (has_aperf) - outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak); + if (DO_BIC(BIC_Busy)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->mperf/tsc); - /* Bzy_MHz */ - if (has_aperf) { + if (DO_BIC(BIC_Bzy_MHz)) { if (has_base_hz) - outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf); + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), base_hz / units * t->aperf / t->mperf); else - outp += sprintf(outp, "\t%.0f", - 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), + tsc / units * t->aperf / t->mperf / interval_float); } - /* TSC_MHz */ - outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float); - - if (!debug) - goto done; + if (DO_BIC(BIC_TSC_MHz)) + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 * t->tsc/units/interval_float); /* IRQ */ - if (do_irq) - outp += sprintf(outp, "\t%d", t->irq_count); + if (DO_BIC(BIC_IRQ)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->irq_count); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count); + } /* SMI */ - if (do_smi) - outp += sprintf(outp, "\t%d", t->smi_count); - - if (do_nhm_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc); - - /* print per-core data only for 1st thread in core */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) - goto done; - - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc); - if (do_nhm_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc); - if (do_snb_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc); + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count); + /* Added counters */ for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) t->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", t->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", t->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc); + if (mp->type == COUNTER_USEC) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), t->counter[i]/interval_float/10000); + else + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->counter[i]/tsc); } } + /* C1 */ + if (DO_BIC(BIC_CPU_c1)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1/tsc); - if (do_dts) - outp += sprintf(outp, "\t%d", c->core_temp_c); + + /* print per-core data only for 1st thread in core */ + if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + goto done; + + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc); + if (DO_BIC(BIC_CPU_c6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc); + if (DO_BIC(BIC_CPU_c7)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c7/tsc); + + /* Mod%c6 */ + if (DO_BIC(BIC_Mod_c6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->mc6_us / tsc); + + if (DO_BIC(BIC_CoreTmp)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) c->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", c->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", c->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->counter[i]/tsc); } } @@ -684,95 +894,89 @@ int format_counters(struct thread_data *t, struct core_data *c, goto done; /* PkgTmp */ - if (do_ptm) - outp += sprintf(outp, "\t%d", p->pkg_temp_c); + if (DO_BIC(BIC_PkgTmp)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->pkg_temp_c); /* GFXrc6 */ - if (do_gfx_rc6_ms) { + if (DO_BIC(BIC_GFX_rc6)) { if (p->gfx_rc6_ms == -1) { /* detect GFX counter reset */ - outp += sprintf(outp, "\t**.**"); + outp += sprintf(outp, "%s**.**", (printed++ ? delim : "")); } else { - outp += sprintf(outp, "\t%.2f", + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), p->gfx_rc6_ms / 10.0 / interval_float); } } /* GFXMHz */ - if (do_gfx_mhz) - outp += sprintf(outp, "\t%d", p->gfx_mhz); + if (DO_BIC(BIC_GFXMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (do_skl_residency) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc); - } - - if (do_pc2) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc); - if (do_pc3) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc); - if (do_pc6) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc); - if (do_pc7) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc); - if (do_c8_c9_c10) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_core_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_gfxe_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_both_core_gfxe_c0/tsc); } + if (DO_BIC(BIC_Pkgpc2)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc2/tsc); + if (DO_BIC(BIC_Pkgpc3)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc3/tsc); + if (DO_BIC(BIC_Pkgpc6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc6/tsc); + if (DO_BIC(BIC_Pkgpc7)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc7/tsc); + if (DO_BIC(BIC_Pkgpc8)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc8/tsc); + if (DO_BIC(BIC_Pkgpc9)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc9/tsc); + if (DO_BIC(BIC_Pkgpc10)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc); + /* * If measurement interval exceeds minimum RAPL Joule Counter range, * indicate that results are suspect by printing "**" in fraction place. */ if (interval_float < rapl_joule_counter_range) - fmt8 = "\t%.2f"; + fmt8 = "%s%.2f"; else fmt8 = "%6.0f**"; - if (do_rapl && !rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } else if (do_rapl && rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, fmt8, - p->energy_pkg * rapl_energy_units); - if (do_rapl & RAPL_CORES) - outp += sprintf(outp, fmt8, - p->energy_cores * rapl_energy_units); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, fmt8, - p->energy_gfx * rapl_energy_units); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, fmt8, - p->energy_dram * rapl_dram_energy_units); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } + if (DO_BIC(BIC_PkgWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); + if (DO_BIC(BIC_CorWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); + if (DO_BIC(BIC_GFXWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); + if (DO_BIC(BIC_RAMWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float); + if (DO_BIC(BIC_Pkg_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); + if (DO_BIC(BIC_Cor_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); + if (DO_BIC(BIC_GFX_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); + if (DO_BIC(BIC_RAM_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) p->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", p->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", p->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->counter[i]/tsc); } } @@ -807,7 +1011,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ static int printed; if (!printed || !summary_only) - print_header(); + print_header("\t"); if (topo.num_cpus > 1) format_counters(&average.threads, &average.cores, @@ -841,11 +1045,11 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0; } old->pc2 = new->pc2 - old->pc2; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) old->pc3 = new->pc3 - old->pc3; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) old->pc6 = new->pc6 - old->pc6; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) old->pc7 = new->pc7 - old->pc7; old->pc8 = new->pc8 - old->pc8; old->pc9 = new->pc9 - old->pc9; @@ -887,6 +1091,7 @@ delta_core(struct core_data *new, struct core_data *old) old->c6 = new->c6 - old->c6; old->c7 = new->c7 - old->c7; old->core_temp_c = new->core_temp_c; + old->mc6_us = new->mc6_us - old->mc6_us; for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -916,7 +1121,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if (has_aperf) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { old->aperf = new->aperf - old->aperf; old->mperf = new->mperf - old->mperf; @@ -941,7 +1146,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = 0; else { /* normal case, derive c1 */ - old->c1 = old->tsc - old->mperf - core_delta->c3 + old->c1 = (old->tsc * tsc_tweak) - old->mperf - core_delta->c3 - core_delta->c6 - core_delta->c7; } } @@ -952,10 +1157,10 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->mperf = 1; /* divide by 0 protection */ } - if (do_irq) + if (DO_BIC(BIC_IRQ)) old->irq_count = new->irq_count - old->irq_count; - if (do_smi) + if (DO_BIC(BIC_SMI)) old->smi_count = new->smi_count - old->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { @@ -1008,6 +1213,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c3 = 0; c->c6 = 0; c->c7 = 0; + c->mc6_us = 0; c->core_temp_c = 0; p->pkg_wtd_core_c0 = 0; @@ -1016,11 +1222,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->pkg_both_core_gfxe_c0 = 0; p->pc2 = 0; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) p->pc3 = 0; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) p->pc6 = 0; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) p->pc7 = 0; p->pc8 = 0; p->pc9 = 0; @@ -1036,7 +1242,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; - for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1073,6 +1278,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.cores.c3 += c->c3; average.cores.c6 += c->c6; average.cores.c7 += c->c7; + average.cores.mc6_us += c->mc6_us; average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); @@ -1094,11 +1300,11 @@ int sum_counters(struct thread_data *t, struct core_data *c, } average.packages.pc2 += p->pc2; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) average.packages.pc3 += p->pc3; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) average.packages.pc6 += p->pc6; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) average.packages.pc7 += p->pc7; average.packages.pc8 += p->pc8; average.packages.pc9 += p->pc9; @@ -1143,9 +1349,13 @@ void compute_average(struct thread_data *t, struct core_data *c, average.threads.mperf /= topo.num_cpus; average.threads.c1 /= topo.num_cpus; + if (average.threads.irq_count > 9999999) + sums_need_wide_columns = 1; + average.cores.c3 /= topo.num_cores; average.cores.c6 /= topo.num_cores; average.cores.c7 /= topo.num_cores; + average.cores.mc6_us /= topo.num_cores; if (do_skl_residency) { average.packages.pkg_wtd_core_c0 /= topo.num_packages; @@ -1155,11 +1365,11 @@ void compute_average(struct thread_data *t, struct core_data *c, } average.packages.pc2 /= topo.num_packages; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) average.packages.pc3 /= topo.num_packages; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) average.packages.pc6 /= topo.num_packages; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) average.packages.pc7 /= topo.num_packages; average.packages.pc8 /= topo.num_packages; @@ -1169,16 +1379,29 @@ void compute_average(struct thread_data *t, struct core_data *c, for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.threads.counter[i] > 9999999) + sums_need_wide_columns = 1; + continue; + } average.threads.counter[i] /= topo.num_cpus; } for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.cores.counter[i] > 9999999) + sums_need_wide_columns = 1; + } average.cores.counter[i] /= topo.num_cores; } for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.packages.counter[i] > 9999999) + sums_need_wide_columns = 1; + } average.packages.counter[i] /= topo.num_packages; } } @@ -1193,6 +1416,60 @@ static unsigned long long rdtsc(void) } /* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, mode); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} +/* + * snapshot_sysfs_counter() + * + * return snapshot of given counter + */ +unsigned long long snapshot_sysfs_counter(char *path) +{ + FILE *fp; + int retval; + unsigned long long counter; + + fp = fopen_or_die(path, "r"); + + retval = fscanf(fp, "%lld", &counter); + if (retval != 1) + err(1, "snapshot_sysfs_counter(%s)", path); + + fclose(fp); + + return counter; +} + +int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) +{ + if (mp->msr_num != 0) { + if (get_msr(cpu, mp->msr_num, counterp)) + return -1; + } else { + char path[128]; + + if (mp->flags & SYSFS_PERCPU) { + sprintf(path, "/sys/devices/system/cpu/cpu%d/%s", + cpu, mp->path); + + *counterp = snapshot_sysfs_counter(path); + } else { + *counterp = snapshot_sysfs_counter(mp->path); + } + } + + return 0; +} + +/* * get_counters(...) * migrate to cpu * acquire and record local counters for that cpu @@ -1213,7 +1490,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (has_aperf) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; /* @@ -1269,35 +1546,33 @@ retry: t->mperf = t->mperf * aperf_mperf_multiplier; } - if (do_irq) + if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; - if (do_smi) { + if (DO_BIC(BIC_SMI)) { if (get_msr(cpu, MSR_SMI_COUNT, &msr)) return -5; t->smi_count = msr & 0xFFFFFFFF; } - - if (use_c1_residency_msr) { + if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) { if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1)) return -6; } for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &t->counter[i])) + if (get_mp(cpu, mp, &t->counter[i])) return -10; } - /* collect core counters only for 1st thread in core */ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) return 0; - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) { + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (do_nhm_cstates && !do_knl_cstates) { + if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; } else if (do_knl_cstates) { @@ -1305,18 +1580,22 @@ retry: return -7; } - if (do_snb_cstates) + if (DO_BIC(BIC_CPU_c7)) if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7)) return -8; - if (do_dts) { + if (DO_BIC(BIC_Mod_c6)) + if (get_msr(cpu, MSR_MODULE_C6_RES_MS, &c->mc6_us)) + return -8; + + if (DO_BIC(BIC_CoreTmp)) { if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) return -9; c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &c->counter[i])) + if (get_mp(cpu, mp, &c->counter[i])) return -10; } @@ -1334,26 +1613,35 @@ retry: if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0)) return -13; } - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3)) return -9; - if (do_pc6) - if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) - return -10; - if (do_pc2) + if (DO_BIC(BIC_Pkgpc6)) { + if (do_slm_cstates) { + if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6)) + return -10; + } else { + if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) + return -10; + } + } + + if (DO_BIC(BIC_Pkgpc2)) if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2)) return -11; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7)) return -12; - if (do_c8_c9_c10) { + if (DO_BIC(BIC_Pkgpc8)) if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8)) return -13; + if (DO_BIC(BIC_Pkgpc9)) if (get_msr(cpu, MSR_PKG_C9_RESIDENCY, &p->pc9)) return -13; + if (DO_BIC(BIC_Pkgpc10)) if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10)) return -13; - } + if (do_rapl & RAPL_PKG) { if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; @@ -1384,20 +1672,20 @@ retry: return -16; p->rapl_dram_perf_status = msr & 0xFFFFFFFF; } - if (do_ptm) { + if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } - if (do_gfx_rc6_ms) + if (DO_BIC(BIC_GFX_rc6)) p->gfx_rc6_ms = gfx_cur_rc6_ms; - if (do_gfx_mhz) + if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &p->counter[i])) + if (get_mp(cpu, mp, &p->counter[i])) return -10; } @@ -1433,8 +1721,8 @@ char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2", int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; +int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7}; +int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; @@ -1457,11 +1745,11 @@ dump_nhm_platform_info(void) fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr); ratio = (msr >> 40) & 0xFF; - fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n", + fprintf(outf, "%d * %.1f = %.1f MHz max efficiency frequency\n", ratio, bclk, ratio * bclk); ratio = (msr >> 8) & 0xFF; - fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n", + fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", ratio, bclk, ratio * bclk); get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); @@ -1483,12 +1771,12 @@ dump_hsw_turbo_ratio_limits(void) ratio = (msr >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 18 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 17 active cores\n", ratio, bclk, ratio * bclk); return; } @@ -1505,99 +1793,175 @@ dump_ivt_turbo_ratio_limits(void) ratio = (msr >> 56) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 16 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 48) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 15 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 40) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 14 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 32) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 13 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 24) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 12 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 16) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 11 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 10 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 9 active cores\n", ratio, bclk, ratio * bclk); return; } +int has_turbo_ratio_group_limits(int family, int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: + return 1; + } + return 0; +} static void -dump_nhm_turbo_ratio_limits(void) +dump_turbo_ratio_limits(int family, int model) { - unsigned long long msr; - unsigned int ratio; + unsigned long long msr, core_counts; + unsigned int ratio, group_size; get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); - fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr); + if (has_turbo_ratio_group_limits(family, model)) { + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts); + fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts); + } else { + core_counts = 0x0807060504030201; + } + ratio = (msr >> 56) & 0xFF; + group_size = (core_counts >> 56) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 48) & 0xFF; + group_size = (core_counts >> 48) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 40) & 0xFF; + group_size = (core_counts >> 40) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 32) & 0xFF; + group_size = (core_counts >> 32) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 24) & 0xFF; + group_size = (core_counts >> 24) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 16) & 0xFF; + group_size = (core_counts >> 16) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 8) & 0xFF; + group_size = (core_counts >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 0) & 0xFF; + group_size = (core_counts >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); return; } static void +dump_atom_turbo_ratio_limits(void) +{ + unsigned long long msr; + unsigned int ratio; + + get_msr(base_cpu, MSR_ATOM_CORE_RATIOS, &msr); + fprintf(outf, "cpu%d: MSR_ATOM_CORE_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF); + + ratio = (msr >> 0) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz minimum operating frequency\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 8) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz low frequency mode (LFM)\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 16) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", + ratio, bclk, ratio * bclk); + + get_msr(base_cpu, MSR_ATOM_CORE_TURBO_RATIOS, &msr); + fprintf(outf, "cpu%d: MSR_ATOM_CORE_TURBO_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF); + + ratio = (msr >> 24) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 16) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 8) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 0) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active core\n", + ratio, bclk, ratio * bclk); +} + +static void dump_knl_turbo_ratio_limits(void) { const unsigned int buckets_no = 7; @@ -1652,7 +2016,7 @@ dump_knl_turbo_ratio_limits(void) for (i = buckets_no - 1; i >= 0; i--) if (i > 0 ? ratio[i] != ratio[i - 1] : 1) fprintf(outf, - "%d * %.0f = %.0f MHz max turbo %d active cores\n", + "%d * %.1f = %.1f MHz max turbo %d active cores\n", ratio[i], bclk, ratio[i] * bclk, cores[i]); } @@ -1661,12 +2025,12 @@ dump_nhm_cst_cfg(void) { unsigned long long msr; - get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) - fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr); + fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr); fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n", (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "", @@ -1810,16 +2174,6 @@ void free_all_buffers(void) free(irqs_per_cpu); } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, mode); - if (!filep) - err(1, "%s: open failed", path); - return filep; -} /* * Parse a file containing a single int. @@ -2148,13 +2502,14 @@ int snapshot_gfx_mhz(void) */ int snapshot_proc_sysfs_files(void) { - if (snapshot_proc_interrupts()) - return 1; + if (DO_BIC(BIC_IRQ)) + if (snapshot_proc_interrupts()) + return 1; - if (do_gfx_rc6_ms) + if (DO_BIC(BIC_GFX_rc6)) snapshot_gfx_rc6_ms(); - if (do_gfx_mhz) + if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); return 0; @@ -2283,7 +2638,9 @@ void check_permissions() * MSR_SMI_COUNT 0x00000034 * * MSR_PLATFORM_INFO 0x000000ce - * MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 + * MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 + * + * MSR_MISC_PWR_MGMT 0x000001aa * * MSR_PKG_C3_RESIDENCY 0x000003f8 * MSR_PKG_C6_RESIDENCY 0x000003f9 @@ -2291,7 +2648,8 @@ void check_permissions() * MSR_CORE_C6_RESIDENCY 0x000003fd * * Side effect: - * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL + * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL + * sets has_misc_feature_control */ int probe_nhm_msrs(unsigned int family, unsigned int model) { @@ -2322,6 +2680,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE: /* IVB */ case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ pkg_cstate_limits = snb_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -2336,29 +2695,34 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ pkg_cstate_limits = hsw_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_SKYLAKE_X: /* SKX */ pkg_cstate_limits = skx_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ + no_MSR_MISC_PWR_MGMT = 1; case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ pkg_cstate_limits = slv_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_AIRMONT: /* AMT */ pkg_cstate_limits = amt_pkg_cstate_limits; + no_MSR_MISC_PWR_MGMT = 1; break; case INTEL_FAM6_XEON_PHI_KNL: /* PHI */ case INTEL_FAM6_XEON_PHI_KNM: pkg_cstate_limits = phi_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ pkg_cstate_limits = bxt_pkg_cstate_limits; break; default: return 0; } - get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); @@ -2368,8 +2732,69 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) has_base_hz = 1; return 1; } -int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) +/* + * SLV client has support for unique MSRs: + * + * MSR_CC6_DEMOTION_POLICY_CONFIG + * MSR_MC6_DEMOTION_POLICY_CONFIG + */ + +int has_slv_msrs(unsigned int family, unsigned int model) { + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_SILVERMONT1: + case INTEL_FAM6_ATOM_MERRIFIELD: + case INTEL_FAM6_ATOM_MOOREFIELD: + return 1; + } + return 0; +} +int is_dnv(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_DENVERTON: + return 1; + } + return 0; +} +int is_bdx(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_BROADWELL_XEON_D: + return 1; + } + return 0; +} +int is_skx(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_SKYLAKE_X: + return 1; + } + return 0; +} + +int has_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (has_slv_msrs(family, model)) + return 0; + switch (model) { /* Nehalem compatible, but do not include turbo-ratio limit support */ case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ @@ -2381,6 +2806,13 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) return 1; } } +int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (has_slv_msrs(family, model)) + return 1; + + return 0; +} int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -2429,6 +2861,22 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) return 0; } } +int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + if (family != 6) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_SKYLAKE_X: + return 1; + default: + return 0; + } +} int has_config_tdp(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -2475,8 +2923,11 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model) if (has_ivt_turbo_ratio_limit(family, model)) dump_ivt_turbo_ratio_limits(); - if (has_nhm_turbo_ratio_limit(family, model)) - dump_nhm_turbo_ratio_limits(); + if (has_turbo_ratio_limit(family, model)) + dump_turbo_ratio_limits(family, model); + + if (has_atom_turbo_ratio_limit(family, model)) + dump_atom_turbo_ratio_limits(); if (has_knl_turbo_ratio_limit(family, model)) dump_knl_turbo_ratio_limits(); @@ -2487,6 +2938,96 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model) dump_nhm_cst_cfg(); } +static void +dump_sysfs_cstate_config(void) +{ + char path[64]; + char name_buf[16]; + char desc[64]; + FILE *input; + int state; + char *sp; + + if (!DO_BIC(BIC_sysfs)) + return; + + for (state = 0; state < 10; ++state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '\0'; + + fclose(input); + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(desc, sizeof(desc), input); + + fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc); + fclose(input); + } +} +static void +dump_sysfs_pstate_config(void) +{ + char path[64]; + char driver_buf[64]; + char governor_buf[64]; + FILE *input; + int turbo; + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_driver", + base_cpu); + input = fopen(path, "r"); + if (input == NULL) { + fprintf(stderr, "NSFOD %s\n", path); + return; + } + fgets(driver_buf, sizeof(driver_buf), input); + fclose(input); + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor", + base_cpu); + input = fopen(path, "r"); + if (input == NULL) { + fprintf(stderr, "NSFOD %s\n", path); + return; + } + fgets(governor_buf, sizeof(governor_buf), input); + fclose(input); + + fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf); + fprintf(outf, "cpu%d: cpufreq governor: %s", base_cpu, governor_buf); + + sprintf(path, "/sys/devices/system/cpu/cpufreq/boost"); + input = fopen(path, "r"); + if (input != NULL) { + fscanf(input, "%d", &turbo); + fprintf(outf, "cpufreq boost: %d\n", turbo); + fclose(input); + } + + sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo"); + input = fopen(path, "r"); + if (input != NULL) { + fscanf(input, "%d", &turbo); + fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo); + fclose(input); + } +} + /* * print_epb() @@ -2790,15 +3331,40 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_GFX_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_GFXWatt); + } break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO; + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); break; case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; case INTEL_FAM6_HASWELL_X: /* HSX */ case INTEL_FAM6_BROADWELL_X: /* BDX */ @@ -2807,17 +3373,55 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ case INTEL_FAM6_XEON_PHI_KNM: do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; case INTEL_FAM6_SANDYBRIDGE_X: case INTEL_FAM6_IVYBRIDGE_X: do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ do_rapl = RAPL_PKG | RAPL_CORES; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + } break; case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; default: return; @@ -2844,7 +3448,7 @@ void rapl_probe(unsigned int family, unsigned int model) tdp = get_tdp(model); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; - if (debug) + if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); return; @@ -2969,11 +3573,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) return -1; - if (debug) { - fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx " - "(%f Watts, %f Joules, %f sec.)\n", cpu, msr, - rapl_power_units, rapl_energy_units, rapl_time_units); - } + fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr, + rapl_power_units, rapl_energy_units, rapl_time_units); + if (do_rapl & RAPL_PKG_POWER_INFO) { if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr)) @@ -2994,7 +3596,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -9; fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 63) & 1 ? "": "UN"); + cpu, msr, (msr >> 63) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "PKG Limit #1"); fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n", @@ -3020,40 +3622,34 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr)) return -9; fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "DRAM Limit"); } if (do_rapl & RAPL_CORE_POLICY) { - if (debug) { - if (get_msr(cpu, MSR_PP0_POLICY, &msr)) - return -7; + if (get_msr(cpu, MSR_PP0_POLICY, &msr)) + return -7; - fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); - } + fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); } if (do_rapl & RAPL_CORES_POWER_LIMIT) { - if (debug) { - if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) - return -9; - fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); - print_power_limit_msr(cpu, msr, "Cores Limit"); - } + if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) + return -9; + fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n", + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); + print_power_limit_msr(cpu, msr, "Cores Limit"); } if (do_rapl & RAPL_GFX) { - if (debug) { - if (get_msr(cpu, MSR_PP1_POLICY, &msr)) - return -8; + if (get_msr(cpu, MSR_PP1_POLICY, &msr)) + return -8; - fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF); + fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF); - if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr)) - return -9; - fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); - print_power_limit_msr(cpu, msr, "GFX Limit"); - } + if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr)) + return -9; + fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n", + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); + print_power_limit_msr(cpu, msr, "GFX Limit"); } return 0; } @@ -3090,6 +3686,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ return 1; } @@ -3121,6 +3718,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: return 1; } return 0; @@ -3149,8 +3747,6 @@ int has_skl_msrs(unsigned int family, unsigned int model) return 0; } - - int is_slm(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -3201,7 +3797,8 @@ double slm_bclk(void) } freq = slm_freq_table[i]; - fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); + if (!quiet) + fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); return freq; } @@ -3264,7 +3861,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk target_c_local = (msr >> 16) & 0xFF; - if (debug) + if (!quiet) fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, target_c_local); @@ -3299,13 +3896,30 @@ void decode_misc_enable_msr(void) unsigned long long msr; if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr)) - fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n", + fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%sTCC %sEIST %sMWAIT %sPREFETCH %sTURBO)\n", base_cpu, msr, - msr & (1 << 3) ? "TCC" : "", - msr & (1 << 16) ? "EIST" : "", - msr & (1 << 18) ? "MONITOR" : ""); + msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-", + msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-", + msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "", + msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "", + msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : ""); } +void decode_misc_feature_control(void) +{ + unsigned long long msr; + + if (!has_misc_feature_control) + return; + + if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr)) + fprintf(outf, "cpu%d: MSR_MISC_FEATURE_CONTROL: 0x%08llx (%sL2-Prefetch %sL2-Prefetch-pair %sL1-Prefetch %sL1-IP-Prefetch)\n", + base_cpu, msr, + msr & (0 << 0) ? "No-" : "", + msr & (1 << 0) ? "No-" : "", + msr & (2 << 0) ? "No-" : "", + msr & (3 << 0) ? "No-" : ""); +} /* * Decode MSR_MISC_PWR_MGMT * @@ -3320,6 +3934,9 @@ void decode_misc_pwr_mgmt_msr(void) if (!do_nhm_platform_info) return; + if (no_MSR_MISC_PWR_MGMT) + return; + if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr)) fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n", base_cpu, msr, @@ -3327,11 +3944,30 @@ void decode_misc_pwr_mgmt_msr(void) msr & (1 << 1) ? "EN" : "DIS", msr & (1 << 8) ? "EN" : "DIS"); } +/* + * Decode MSR_CC6_DEMOTION_POLICY_CONFIG, MSR_MC6_DEMOTION_POLICY_CONFIG + * + * This MSRs are present on Silvermont processors, + * Intel Atom processor E3000 series (Baytrail), and friends. + */ +void decode_c6_demotion_policy_msr(void) +{ + unsigned long long msr; + + if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr)) + fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n", + base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); + + if (!get_msr(base_cpu, MSR_MC6_DEMOTION_POLICY_CONFIG, &msr)) + fprintf(outf, "cpu%d: MSR_MC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-MC6-Demotion)\n", + base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); +} void process_cpuid() { unsigned int eax, ebx, ecx, edx, max_level, max_extended_level; unsigned int fms, family, model, stepping; + unsigned int has_turbo; eax = ebx = ecx = edx = 0; @@ -3340,7 +3976,7 @@ void process_cpuid() if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; - if (debug) + if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); @@ -3351,7 +3987,7 @@ void process_cpuid() if (family == 6 || family == 0xf) model += ((fms >> 16) & 0xf) << 4; - if (debug) { + if (!quiet) { fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n", @@ -3394,8 +4030,18 @@ void process_cpuid() __cpuid(0x6, eax, ebx, ecx, edx); has_aperf = ecx & (1 << 0); + if (has_aperf) { + BIC_PRESENT(BIC_Avg_MHz); + BIC_PRESENT(BIC_Busy); + BIC_PRESENT(BIC_Bzy_MHz); + } do_dts = eax & (1 << 0); + if (do_dts) + BIC_PRESENT(BIC_CoreTmp); + has_turbo = eax & (1 << 1); do_ptm = eax & (1 << 6); + if (do_ptm) + BIC_PRESENT(BIC_PkgTmp); has_hwp = eax & (1 << 7); has_hwp_notify = eax & (1 << 8); has_hwp_activity_window = eax & (1 << 9); @@ -3403,10 +4049,11 @@ void process_cpuid() has_hwp_pkg = eax & (1 << 11); has_epb = ecx & (1 << 3); - if (debug) - fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, " + if (!quiet) + fprintf(outf, "CPUID(6): %sAPERF, %sTURBO, %sDTS, %sPTM, %sHWP, " "%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n", has_aperf ? "" : "No-", + has_turbo ? "" : "No-", do_dts ? "" : "No-", do_ptm ? "" : "No-", has_hwp ? "" : "No-", @@ -3416,10 +4063,11 @@ void process_cpuid() has_hwp_pkg ? "" : "No-", has_epb ? "" : "No-"); - if (debug) + if (!quiet) decode_misc_enable_msr(); - if (max_level >= 0x7 && debug) { + + if (max_level >= 0x7 && !quiet) { int has_sgx; ecx = 0; @@ -3445,7 +4093,7 @@ void process_cpuid() if (ebx_tsc != 0) { - if (debug && (ebx != 0)) + if (!quiet && (ebx != 0)) fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n", eax_crystal, ebx_tsc, crystal_hz); @@ -3462,6 +4110,7 @@ void process_cpuid() crystal_hz = 25000000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: crystal_hz = 19200000; /* 19.2 MHz */ break; default: @@ -3470,7 +4119,7 @@ void process_cpuid() if (crystal_hz) { tsc_hz = (unsigned long long) crystal_hz * ebx_tsc / eax_crystal; - if (debug) + if (!quiet) fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n", tsc_hz / 1000000, crystal_hz, ebx_tsc, eax_crystal); } @@ -3485,7 +4134,7 @@ void process_cpuid() base_mhz = max_mhz = bus_mhz = edx = 0; __cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx); - if (debug) + if (!quiet) fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n", base_mhz, max_mhz, bus_mhz); } @@ -3493,56 +4142,96 @@ void process_cpuid() if (has_aperf) aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); - do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); + BIC_PRESENT(BIC_IRQ); + BIC_PRESENT(BIC_TSC_MHz); + + if (probe_nhm_msrs(family, model)) { + do_nhm_platform_info = 1; + BIC_PRESENT(BIC_CPU_c1); + BIC_PRESENT(BIC_CPU_c3); + BIC_PRESENT(BIC_CPU_c6); + BIC_PRESENT(BIC_SMI); + } do_snb_cstates = has_snb_msrs(family, model); + + if (do_snb_cstates) + BIC_PRESENT(BIC_CPU_c7); + do_irtl_snb = has_snb_msrs(family, model); - do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); - do_pc3 = (pkg_cstate_limit >= PCL__3); - do_pc6 = (pkg_cstate_limit >= PCL__6); - do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7); - do_c8_c9_c10 = has_hsw_msrs(family, model); + if (do_snb_cstates && (pkg_cstate_limit >= PCL__2)) + BIC_PRESENT(BIC_Pkgpc2); + if (pkg_cstate_limit >= PCL__3) + BIC_PRESENT(BIC_Pkgpc3); + if (pkg_cstate_limit >= PCL__6) + BIC_PRESENT(BIC_Pkgpc6); + if (do_snb_cstates && (pkg_cstate_limit >= PCL__7)) + BIC_PRESENT(BIC_Pkgpc7); + if (has_slv_msrs(family, model)) { + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + BIC_PRESENT(BIC_Mod_c6); + use_c1_residency_msr = 1; + } + if (is_dnv(family, model)) { + BIC_PRESENT(BIC_CPU_c1); + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + use_c1_residency_msr = 1; + } + if (is_skx(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } + if (is_bdx(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } + if (has_hsw_msrs(family, model)) { + BIC_PRESENT(BIC_Pkgpc8); + BIC_PRESENT(BIC_Pkgpc9); + BIC_PRESENT(BIC_Pkgpc10); + } do_irtl_hsw = has_hsw_msrs(family, model); do_skl_residency = has_skl_msrs(family, model); do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - if (debug) + if (!quiet) decode_misc_pwr_mgmt_msr(); + if (!quiet && has_slv_msrs(family, model)) + decode_c6_demotion_policy_msr(); + rapl_probe(family, model); perf_limit_reasons_probe(family, model); - if (debug) + if (!quiet) dump_cstate_pstate_config_info(family, model); + if (!quiet) + dump_sysfs_cstate_config(); + if (!quiet) + dump_sysfs_pstate_config(); + if (has_skl_msrs(family, model)) calculate_tsc_tweak(); - do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK); + if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) + BIC_PRESENT(BIC_GFX_rc6); - do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXMHz); - return; -} + if (!quiet) + decode_misc_feature_control(); -void help() -{ - fprintf(outf, - "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n" - "\n" - "Turbostat forks the specified COMMAND and prints statistics\n" - "when COMMAND completes.\n" - "If no COMMAND is specified, turbostat wakes every 5-seconds\n" - "to print statistics, until interrupted.\n" - "--add add a counter\n" - " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" - "--debug run in \"debug\" mode\n" - "--interval sec Override default 5-second measurement interval\n" - "--help print this help message\n" - "--out file create or truncate \"file\" for all output\n" - "--version print version information\n" - "\n" - "For more help, run \"man turbostat\"\n"); + return; } @@ -3579,7 +4268,7 @@ void topology_probe() topo.max_cpu_num = 0; for_all_proc_cpus(count_cpus); if (!summary_only && topo.num_cpus > 1) - show_cpu = 1; + BIC_PRESENT(BIC_CPU); if (debug > 1) fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num); @@ -3599,6 +4288,15 @@ void topology_probe() for_all_proc_cpus(mark_cpu_present); /* + * Validate that all cpus in cpu_subset are also in cpu_present_set + */ + for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) { + if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset)) + if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) + err(1, "cpu%d not present", i); + } + + /* * Allocate and initialize cpu_affinity_set */ cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1)); @@ -3639,15 +4337,15 @@ void topology_probe() if (debug > 1) fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.num_cores_per_pkg); - if (debug && !summary_only && topo.num_cores_per_pkg > 1) - show_core = 1; + if (!summary_only && topo.num_cores_per_pkg > 1) + BIC_PRESENT(BIC_Core); topo.num_packages = max_package_id + 1; if (debug > 1) fprintf(outf, "max_package_id %d, sizing for %d packages\n", max_package_id, topo.num_packages); - if (debug && !summary_only && topo.num_packages > 1) - show_pkg = 1; + if (!summary_only && topo.num_packages > 1) + BIC_PRESENT(BIC_Package); topo.num_threads_per_core = max_siblings; if (debug > 1) @@ -3662,7 +4360,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data int i; *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg * - topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes); + topo.num_packages, sizeof(struct thread_data)); if (*t == NULL) goto error; @@ -3671,14 +4369,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data (*t)[i].cpu_id = -1; *c = calloc(topo.num_cores_per_pkg * topo.num_packages, - sizeof(struct core_data) + sys.core_counter_bytes); + sizeof(struct core_data)); if (*c == NULL) goto error; for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++) (*c)[i].core_id = -1; - *p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes); + *p = calloc(topo.num_packages, sizeof(struct pkg_data)); if (*p == NULL) goto error; @@ -3789,24 +4487,24 @@ void turbostat_init() process_cpuid(); - if (debug) + if (!quiet) for_all_cpus(print_hwp, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_epb, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_perf_limit, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_rapl, ODD_COUNTERS); for_all_cpus(set_temperature_target, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_thermal, ODD_COUNTERS); - if (debug && do_irtl_snb) + if (!quiet && do_irtl_snb) print_irtl(); } @@ -3815,6 +4513,7 @@ int fork_it(char **argv) pid_t child_pid; int status; + snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, EVEN_COUNTERS); if (status) exit(status); @@ -3826,6 +4525,7 @@ int fork_it(char **argv) if (!child_pid) { /* child */ execvp(argv[0], argv); + err(errno, "exec %s", argv[0]); } else { /* parent */ @@ -3841,6 +4541,7 @@ int fork_it(char **argv) * n.b. fork_it() does not check for errors from for_all_cpus() * because re-starting is problematic when forking */ + snapshot_proc_sysfs_files(); for_all_cpus(get_counters, ODD_COUNTERS); gettimeofday(&tv_odd, (struct timezone *)NULL); timersub(&tv_odd, &tv_even, &tv_delta); @@ -3862,6 +4563,7 @@ int get_and_dump_counters(void) { int status; + snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, ODD_COUNTERS); if (status) return status; @@ -3876,13 +4578,13 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 4.16 24 Dec 2016" + fprintf(outf, "turbostat version 17.02.24" " - Len Brown <lenb@kernel.org>\n"); } -int add_counter(unsigned int msr_num, char *name, unsigned int width, - enum counter_scope scope, enum counter_type type, - enum counter_format format) +int add_counter(unsigned int msr_num, char *path, char *name, + unsigned int width, enum counter_scope scope, + enum counter_type type, enum counter_format format, int flags) { struct msr_counter *msrp; @@ -3894,31 +4596,46 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width, msrp->msr_num = msr_num; strncpy(msrp->name, name, NAME_BYTES); + if (path) + strncpy(msrp->path, path, PATH_BYTES); msrp->width = width; msrp->type = type; msrp->format = format; + msrp->flags = flags; switch (scope) { case SCOPE_CPU: - sys.thread_counter_bytes += 64; msrp->next = sys.tp; sys.tp = msrp; - sys.thread_counter_bytes += sizeof(unsigned long long); + sys.added_thread_counters++; + if (sys.added_thread_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added thread counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; case SCOPE_CORE: - sys.core_counter_bytes += 64; msrp->next = sys.cp; sys.cp = msrp; - sys.core_counter_bytes += sizeof(unsigned long long); + sys.added_core_counters++; + if (sys.added_core_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added core counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; case SCOPE_PACKAGE: - sys.package_counter_bytes += 64; msrp->next = sys.pp; sys.pp = msrp; - sys.package_counter_bytes += sizeof(unsigned long long); + sys.added_package_counters++; + if (sys.added_package_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added package counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; } @@ -3928,7 +4645,8 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width, void parse_add_command(char *add_command) { int msr_num = 0; - char name_buffer[NAME_BYTES]; + char *path = NULL; + char name_buffer[NAME_BYTES] = ""; int width = 64; int fail = 0; enum counter_scope scope = SCOPE_CPU; @@ -3943,6 +4661,11 @@ void parse_add_command(char *add_command) if (sscanf(add_command, "msr%d", &msr_num) == 1) goto next; + if (*add_command == '/') { + path = add_command; + goto next; + } + if (sscanf(add_command, "u%d", &width) == 1) { if ((width == 32) || (width == 64)) goto next; @@ -3968,6 +4691,10 @@ void parse_add_command(char *add_command) type = COUNTER_SECONDS; goto next; } + if (!strncmp(add_command, "usec", strlen("usec"))) { + type = COUNTER_USEC; + goto next; + } if (!strncmp(add_command, "raw", strlen("raw"))) { format = FORMAT_RAW; goto next; @@ -3992,36 +4719,26 @@ void parse_add_command(char *add_command) next: add_command = strchr(add_command, ','); - if (add_command) + if (add_command) { + *add_command = '\0'; add_command++; + } } - if (msr_num == 0) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n"); + if ((msr_num == 0) && (path == NULL)) { + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n"); fail++; } /* generate default column header */ if (*name_buffer == '\0') { - if (format == FORMAT_RAW) { - if (width == 32) - sprintf(name_buffer, "msr%d", msr_num); - else - sprintf(name_buffer, "MSR%d", msr_num); - } else if (format == FORMAT_DELTA) { - if (width == 32) - sprintf(name_buffer, "cnt%d", msr_num); - else - sprintf(name_buffer, "CNT%d", msr_num); - } else if (format == FORMAT_PERCENT) { - if (width == 32) - sprintf(name_buffer, "msr%d%%", msr_num); - else - sprintf(name_buffer, "MSR%d%%", msr_num); - } + if (width == 32) + sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); + else + sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); } - if (add_counter(msr_num, name_buffer, width, scope, type, format)) + if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0)) fail++; if (fail) { @@ -4029,20 +4746,214 @@ next: exit(1); } } + +int is_deferred_skip(char *name) +{ + int i; + + for (i = 0; i < deferred_skip_index; ++i) + if (!strcmp(name, deferred_skip_names[i])) + return 1; + return 0; +} + +void probe_sysfs(void) +{ + char path[64]; + char name_buf[16]; + FILE *input; + int state; + char *sp; + + if (!DO_BIC(BIC_sysfs)) + return; + + for (state = 10; state > 0; --state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '%'; + *(sp + 1) = '\0'; + + fclose(input); + + sprintf(path, "cpuidle/state%d/time", state); + + if (is_deferred_skip(name_buf)) + continue; + + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC, + FORMAT_PERCENT, SYSFS_PERCPU); + } + + for (state = 10; state > 0; --state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '\0'; + fclose(input); + + sprintf(path, "cpuidle/state%d/usage", state); + + if (is_deferred_skip(name_buf)) + continue; + + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, + FORMAT_DELTA, SYSFS_PERCPU); + } + +} + + +/* + * parse cpuset with following syntax + * 1,2,4..6,8-10 and set bits in cpu_subset + */ +void parse_cpu_command(char *optarg) +{ + unsigned int start, end; + char *next; + + if (!strcmp(optarg, "core")) { + if (cpu_subset) + goto error; + show_core_only++; + return; + } + if (!strcmp(optarg, "package")) { + if (cpu_subset) + goto error; + show_pkg_only++; + return; + } + if (show_core_only || show_pkg_only) + goto error; + + cpu_subset = CPU_ALLOC(CPU_SUBSET_MAXCPUS); + if (cpu_subset == NULL) + err(3, "CPU_ALLOC"); + cpu_subset_size = CPU_ALLOC_SIZE(CPU_SUBSET_MAXCPUS); + + CPU_ZERO_S(cpu_subset_size, cpu_subset); + + next = optarg; + + while (next && *next) { + + if (*next == '-') /* no negative cpu numbers */ + goto error; + + start = strtoul(next, &next, 10); + + if (start >= CPU_SUBSET_MAXCPUS) + goto error; + CPU_SET_S(start, cpu_subset_size, cpu_subset); + + if (*next == '\0') + break; + + if (*next == ',') { + next += 1; + continue; + } + + if (*next == '-') { + next += 1; /* start range */ + } else if (*next == '.') { + next += 1; + if (*next == '.') + next += 1; /* start range */ + else + goto error; + } + + end = strtoul(next, &next, 10); + if (end <= start) + goto error; + + while (++start <= end) { + if (start >= CPU_SUBSET_MAXCPUS) + goto error; + CPU_SET_S(start, cpu_subset_size, cpu_subset); + } + + if (*next == ',') + next += 1; + else if (*next != '\0') + goto error; + } + + return; + +error: + fprintf(stderr, "\"--cpu %s\" malformed\n", optarg); + help(); + exit(-1); +} + +int shown; +/* + * parse_show_hide() - process cmdline to set default counter action + */ +void parse_show_hide(char *optarg, enum show_hide_mode new_mode) +{ + /* + * --show: show only those specified + * The 1st invocation will clear and replace the enabled mask + * subsequent invocations can add to it. + */ + if (new_mode == SHOW_LIST) { + if (shown == 0) + bic_enabled = bic_lookup(optarg, new_mode); + else + bic_enabled |= bic_lookup(optarg, new_mode); + shown = 1; + + return; + } + + /* + * --hide: do not show those specified + * multiple invocations simply clear more bits in enabled mask + */ + bic_enabled &= ~bic_lookup(optarg, new_mode); + +} + void cmdline(int argc, char **argv) { int opt; int option_index = 0; static struct option long_options[] = { {"add", required_argument, 0, 'a'}, + {"cpu", required_argument, 0, 'c'}, {"Dump", no_argument, 0, 'D'}, - {"debug", no_argument, 0, 'd'}, + {"debug", no_argument, 0, 'd'}, /* internal, not documented */ {"interval", required_argument, 0, 'i'}, {"help", no_argument, 0, 'h'}, + {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help {"Joules", no_argument, 0, 'J'}, + {"list", no_argument, 0, 'l'}, {"out", required_argument, 0, 'o'}, - {"Package", no_argument, 0, 'p'}, - {"processor", no_argument, 0, 'p'}, + {"quiet", no_argument, 0, 'q'}, + {"show", required_argument, 0, 's'}, {"Summary", no_argument, 0, 'S'}, {"TCC", required_argument, 0, 'T'}, {"version", no_argument, 0, 'v' }, @@ -4051,18 +4962,24 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v", + while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); break; + case 'c': + parse_cpu_command(optarg); + break; case 'D': dump_only++; break; case 'd': debug++; break; + case 'H': + parse_show_hide(optarg, HIDE_LIST); + break; case 'h': default: help(); @@ -4084,14 +5001,18 @@ void cmdline(int argc, char **argv) case 'J': rapl_joules++; break; + case 'l': + list_header_only++; + quiet++; + break; case 'o': outf = fopen_or_die(optarg, "w"); break; - case 'P': - show_pkg_only++; + case 'q': + quiet = 1; break; - case 'p': - show_core_only++; + case 's': + parse_show_hide(optarg, SHOW_LIST); break; case 'S': summary_only++; @@ -4113,15 +5034,24 @@ int main(int argc, char **argv) cmdline(argc, argv); - if (debug) + if (!quiet) print_version(); + probe_sysfs(); + turbostat_init(); /* dump counters and exit */ if (dump_only) return get_and_dump_counters(); + /* list header and exit */ + if (list_header_only) { + print_header(","); + flush_output_stdout(); + return 0; + } + /* * if any params left, it must be a command to fork */ diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index ce96d80ad64f..775c589ac3c0 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -2,6 +2,10 @@ # Makefile can operate with or without the kbuild infrastructure. CC := $(CROSS_COMPILE)gcc +ifeq (0,$(MAKELEVEL)) +OUTPUT := $(shell pwd) +endif + TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) |