diff options
Diffstat (limited to 'drivers')
302 files changed, 16307 insertions, 5514 deletions
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index e6c3ddd92665..ab2cbb51c6aa 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -5,7 +5,7 @@ menuconfig ACPI bool "ACPI (Advanced Configuration and Power Interface) Support" depends on !IA64_HP_SIM - depends on IA64 || X86 + depends on IA64 || X86 || (ARM64 && EXPERT) depends on PCI select PNP default y @@ -48,9 +48,16 @@ config ACPI_LEGACY_TABLES_LOOKUP config ARCH_MIGHT_HAVE_ACPI_PDC bool +config ACPI_GENERIC_GSI + bool + +config ACPI_SYSTEM_POWER_STATES_SUPPORT + bool + config ACPI_SLEEP bool depends on SUSPEND || HIBERNATION + depends on ACPI_SYSTEM_POWER_STATES_SUPPORT default y config ACPI_PROCFS_POWER @@ -163,6 +170,7 @@ config ACPI_PROCESSOR tristate "Processor" select THERMAL select CPU_IDLE + depends on X86 || IA64 default y help This driver installs ACPI as the idle handler for Linux and uses diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 623b117ad1a2..8a063e276530 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -23,7 +23,7 @@ acpi-y += nvs.o # Power management related files acpi-y += wakeup.o -acpi-y += sleep.o +acpi-$(CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT) += sleep.o acpi-y += device_pm.o acpi-$(CONFIG_ACPI_SLEEP) += proc.o @@ -56,6 +56,7 @@ ifdef CONFIG_ACPI_VIDEO acpi-y += video_detect.o endif acpi-y += acpi_lpat.o +acpi-$(CONFIG_ACPI_GENERIC_GSI) += gsi.o # These are (potentially) separate modules diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 1020b1b53a17..58f335ca2e75 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -170,7 +170,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr) acpi_status status; int ret; - if (pr->phys_id == -1) + if (pr->phys_id == PHYS_CPUID_INVALID) return -ENODEV; status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta); @@ -215,7 +215,8 @@ static int acpi_processor_get_info(struct acpi_device *device) union acpi_object object = { 0 }; struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; struct acpi_processor *pr = acpi_driver_data(device); - int phys_id, cpu_index, device_declaration = 0; + phys_cpuid_t phys_id; + int cpu_index, device_declaration = 0; acpi_status status = AE_OK; static int cpu0_initialized; unsigned long long value; @@ -263,7 +264,7 @@ static int acpi_processor_get_info(struct acpi_device *device) } phys_id = acpi_get_phys_id(pr->handle, device_declaration, pr->acpi_id); - if (phys_id < 0) + if (phys_id == PHYS_CPUID_INVALID) acpi_handle_debug(pr->handle, "failed to get CPU physical ID.\n"); pr->phys_id = phys_id; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 8b67bd0f6bb5..c412fdb28d34 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -448,6 +448,9 @@ static int __init acpi_bus_init_irq(void) case ACPI_IRQ_MODEL_IOSAPIC: message = "IOSAPIC"; break; + case ACPI_IRQ_MODEL_GIC: + message = "GIC"; + break; case ACPI_IRQ_MODEL_PLATFORM: message = "platform specific model"; break; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 220d6406c9e9..5e8fed448850 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -861,7 +861,7 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit) } } mutex_unlock(&ec->mutex); - list_for_each_entry(handler, &free_list, node) + list_for_each_entry_safe(handler, tmp, &free_list, node) acpi_ec_put_query_handler(handler); } EXPORT_SYMBOL_GPL(acpi_ec_remove_query_handler); diff --git a/drivers/acpi/gsi.c b/drivers/acpi/gsi.c new file mode 100644 index 000000000000..38208f2d0e69 --- /dev/null +++ b/drivers/acpi/gsi.c @@ -0,0 +1,105 @@ +/* + * ACPI GSI IRQ layer + * + * Copyright (C) 2015 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/acpi.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> + +enum acpi_irq_model_id acpi_irq_model; + +static unsigned int acpi_gsi_get_irq_type(int trigger, int polarity) +{ + switch (polarity) { + case ACPI_ACTIVE_LOW: + return trigger == ACPI_EDGE_SENSITIVE ? + IRQ_TYPE_EDGE_FALLING : + IRQ_TYPE_LEVEL_LOW; + case ACPI_ACTIVE_HIGH: + return trigger == ACPI_EDGE_SENSITIVE ? + IRQ_TYPE_EDGE_RISING : + IRQ_TYPE_LEVEL_HIGH; + case ACPI_ACTIVE_BOTH: + if (trigger == ACPI_EDGE_SENSITIVE) + return IRQ_TYPE_EDGE_BOTH; + default: + return IRQ_TYPE_NONE; + } +} + +/** + * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI + * @gsi: GSI IRQ number to map + * @irq: pointer where linux IRQ number is stored + * + * irq location updated with irq value [>0 on success, 0 on failure] + * + * Returns: linux IRQ number on success (>0) + * -EINVAL on failure + */ +int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) +{ + /* + * Only default domain is supported at present, always find + * the mapping corresponding to default domain by passing NULL + * as irq_domain parameter + */ + *irq = irq_find_mapping(NULL, gsi); + /* + * *irq == 0 means no mapping, that should + * be reported as a failure + */ + return (*irq > 0) ? *irq : -EINVAL; +} +EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); + +/** + * acpi_register_gsi() - Map a GSI to a linux IRQ number + * @dev: device for which IRQ has to be mapped + * @gsi: GSI IRQ number + * @trigger: trigger type of the GSI number to be mapped + * @polarity: polarity of the GSI to be mapped + * + * Returns: a valid linux IRQ number on success + * -EINVAL on failure + */ +int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, + int polarity) +{ + unsigned int irq; + unsigned int irq_type = acpi_gsi_get_irq_type(trigger, polarity); + + /* + * There is no way at present to look-up the IRQ domain on ACPI, + * hence always create mapping referring to the default domain + * by passing NULL as irq_domain parameter + */ + irq = irq_create_mapping(NULL, gsi); + if (!irq) + return -EINVAL; + + /* Set irq type if specified and different than the current one */ + if (irq_type != IRQ_TYPE_NONE && + irq_type != irq_get_trigger_type(irq)) + irq_set_irq_type(irq, irq_type); + return irq; +} +EXPORT_SYMBOL_GPL(acpi_register_gsi); + +/** + * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping + * @gsi: GSI IRQ number + */ +void acpi_unregister_gsi(u32 gsi) +{ + int irq = irq_find_mapping(NULL, gsi); + + irq_dispose_mapping(irq); +} +EXPORT_SYMBOL_GPL(acpi_unregister_gsi); diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 56b321aa2b1c..ba4a61e964be 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -161,7 +161,11 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); /*-------------------------------------------------------------------------- Suspend/Resume -------------------------------------------------------------------------- */ +#ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT extern int acpi_sleep_init(void); +#else +static inline int acpi_sleep_init(void) { return -ENXIO; } +#endif #ifdef CONFIG_ACPI_SLEEP int acpi_sleep_proc_init(void); diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index f9eeae871593..39748bb3a543 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -336,11 +336,11 @@ acpi_map_lookup_virt(void __iomem *virt, acpi_size size) return NULL; } -#ifndef CONFIG_IA64 -#define should_use_kmap(pfn) page_is_ram(pfn) -#else +#if defined(CONFIG_IA64) || defined(CONFIG_ARM64) /* ioremap will take care of cache attributes */ #define should_use_kmap(pfn) 0 +#else +#define should_use_kmap(pfn) page_is_ram(pfn) #endif static void __iomem *acpi_map(acpi_physical_address pg_off, unsigned long pg_sz) diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 7962651cdbd4..b1ec78b8a645 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -32,7 +32,7 @@ static struct acpi_table_madt *get_madt_table(void) } static int map_lapic_id(struct acpi_subtable_header *entry, - u32 acpi_id, int *apic_id) + u32 acpi_id, phys_cpuid_t *apic_id) { struct acpi_madt_local_apic *lapic = container_of(entry, struct acpi_madt_local_apic, header); @@ -48,7 +48,7 @@ static int map_lapic_id(struct acpi_subtable_header *entry, } static int map_x2apic_id(struct acpi_subtable_header *entry, - int device_declaration, u32 acpi_id, int *apic_id) + int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id) { struct acpi_madt_local_x2apic *apic = container_of(entry, struct acpi_madt_local_x2apic, header); @@ -65,7 +65,7 @@ static int map_x2apic_id(struct acpi_subtable_header *entry, } static int map_lsapic_id(struct acpi_subtable_header *entry, - int device_declaration, u32 acpi_id, int *apic_id) + int device_declaration, u32 acpi_id, phys_cpuid_t *apic_id) { struct acpi_madt_local_sapic *lsapic = container_of(entry, struct acpi_madt_local_sapic, header); @@ -83,10 +83,35 @@ static int map_lsapic_id(struct acpi_subtable_header *entry, return 0; } -static int map_madt_entry(int type, u32 acpi_id) +/* + * Retrieve the ARM CPU physical identifier (MPIDR) + */ +static int map_gicc_mpidr(struct acpi_subtable_header *entry, + int device_declaration, u32 acpi_id, phys_cpuid_t *mpidr) +{ + struct acpi_madt_generic_interrupt *gicc = + container_of(entry, struct acpi_madt_generic_interrupt, header); + + if (!(gicc->flags & ACPI_MADT_ENABLED)) + return -ENODEV; + + /* device_declaration means Device object in DSDT, in the + * GIC interrupt model, logical processors are required to + * have a Processor Device object in the DSDT, so we should + * check device_declaration here + */ + if (device_declaration && (gicc->uid == acpi_id)) { + *mpidr = gicc->arm_mpidr; + return 0; + } + + return -EINVAL; +} + +static phys_cpuid_t map_madt_entry(int type, u32 acpi_id) { unsigned long madt_end, entry; - int phys_id = -1; /* CPU hardware ID */ + phys_cpuid_t phys_id = PHYS_CPUID_INVALID; /* CPU hardware ID */ struct acpi_table_madt *madt; madt = get_madt_table(); @@ -111,18 +136,21 @@ static int map_madt_entry(int type, u32 acpi_id) } else if (header->type == ACPI_MADT_TYPE_LOCAL_SAPIC) { if (!map_lsapic_id(header, type, acpi_id, &phys_id)) break; + } else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) { + if (!map_gicc_mpidr(header, type, acpi_id, &phys_id)) + break; } entry += header->length; } return phys_id; } -static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id) +static phys_cpuid_t map_mat_entry(acpi_handle handle, int type, u32 acpi_id) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; struct acpi_subtable_header *header; - int phys_id = -1; + phys_cpuid_t phys_id = PHYS_CPUID_INVALID; if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer))) goto exit; @@ -143,33 +171,35 @@ static int map_mat_entry(acpi_handle handle, int type, u32 acpi_id) map_lsapic_id(header, type, acpi_id, &phys_id); else if (header->type == ACPI_MADT_TYPE_LOCAL_X2APIC) map_x2apic_id(header, type, acpi_id, &phys_id); + else if (header->type == ACPI_MADT_TYPE_GENERIC_INTERRUPT) + map_gicc_mpidr(header, type, acpi_id, &phys_id); exit: kfree(buffer.pointer); return phys_id; } -int acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id) +phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id) { - int phys_id; + phys_cpuid_t phys_id; phys_id = map_mat_entry(handle, type, acpi_id); - if (phys_id == -1) + if (phys_id == PHYS_CPUID_INVALID) phys_id = map_madt_entry(type, acpi_id); return phys_id; } -int acpi_map_cpuid(int phys_id, u32 acpi_id) +int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id) { #ifdef CONFIG_SMP int i; #endif - if (phys_id == -1) { + if (phys_id == PHYS_CPUID_INVALID) { /* * On UP processor, there is no _MAT or MADT table. - * So above phys_id is always set to -1. + * So above phys_id is always set to PHYS_CPUID_INVALID. * * BIOS may define multiple CPU handles even for UP processor. * For example, @@ -190,7 +220,7 @@ int acpi_map_cpuid(int phys_id, u32 acpi_id) if (nr_cpu_ids <= 1 && acpi_id == 0) return acpi_id; else - return phys_id; + return -1; } #ifdef CONFIG_SMP @@ -208,7 +238,7 @@ int acpi_map_cpuid(int phys_id, u32 acpi_id) int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) { - int phys_id; + phys_cpuid_t phys_id; phys_id = acpi_get_phys_id(handle, type, acpi_id); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 69bc0d888c01..03141aa4ea95 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -375,7 +375,11 @@ bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent) struct acpi_device_physical_node *pn; bool offline = true; - mutex_lock(&adev->physical_node_lock); + /* + * acpi_container_offline() calls this for all of the container's + * children under the container's physical_node_lock lock. + */ + mutex_lock_nested(&adev->physical_node_lock, SINGLE_DEPTH_NESTING); list_for_each_entry(pn, &adev->physical_node_list, node) if (device_supports_offline(pn->dev) && !pn->dev->offline) { @@ -2388,9 +2392,6 @@ static void acpi_default_enumeration(struct acpi_device *device) struct list_head resource_list; bool is_spi_i2c_slave = false; - if (!device->pnp.type.platform_id || device->handler) - return; - /* * Do not enemerate SPI/I2C slaves as they will be enuerated by their * respective parents. @@ -2403,6 +2404,29 @@ static void acpi_default_enumeration(struct acpi_device *device) acpi_create_platform_device(device); } +static const struct acpi_device_id generic_device_ids[] = { + {"PRP0001", }, + {"", }, +}; + +static int acpi_generic_device_attach(struct acpi_device *adev, + const struct acpi_device_id *not_used) +{ + /* + * Since PRP0001 is the only ID handled here, the test below can be + * unconditional. + */ + if (adev->data.of_compatible) + acpi_default_enumeration(adev); + + return 1; +} + +static struct acpi_scan_handler generic_device_handler = { + .ids = generic_device_ids, + .attach = acpi_generic_device_attach, +}; + static int acpi_scan_attach_handler(struct acpi_device *device) { struct acpi_hardware_id *hwid; @@ -2428,8 +2452,6 @@ static int acpi_scan_attach_handler(struct acpi_device *device) break; } } - if (!ret) - acpi_default_enumeration(device); return ret; } @@ -2471,6 +2493,9 @@ static void acpi_bus_attach(struct acpi_device *device) ret = device_attach(&device->dev); if (ret < 0) return; + + if (!ret && device->pnp.type.platform_id) + acpi_default_enumeration(device); } device->flags.visited = true; @@ -2629,6 +2654,8 @@ int __init acpi_scan_init(void) acpi_pnp_init(); acpi_int340x_thermal_init(); + acpi_scan_add_handler(&generic_device_handler); + mutex_lock(&acpi_scan_lock); /* * Enumerate devices in the ACPI namespace. diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 93b81523a2fe..2e19189da0ee 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -23,6 +23,8 @@ * */ +/* Uncomment next line to get verbose printout */ +/* #define DEBUG */ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/init.h> @@ -61,9 +63,9 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_local_apic *p = (struct acpi_madt_local_apic *)header; - pr_info("LAPIC (acpi_id[0x%02x] lapic_id[0x%02x] %s)\n", - p->processor_id, p->id, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + pr_debug("LAPIC (acpi_id[0x%02x] lapic_id[0x%02x] %s)\n", + p->processor_id, p->id, + (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); } break; @@ -71,9 +73,9 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_local_x2apic *p = (struct acpi_madt_local_x2apic *)header; - pr_info("X2APIC (apic_id[0x%02x] uid[0x%02x] %s)\n", - p->local_apic_id, p->uid, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + pr_debug("X2APIC (apic_id[0x%02x] uid[0x%02x] %s)\n", + p->local_apic_id, p->uid, + (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); } break; @@ -81,8 +83,8 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_io_apic *p = (struct acpi_madt_io_apic *)header; - pr_info("IOAPIC (id[0x%02x] address[0x%08x] gsi_base[%d])\n", - p->id, p->address, p->global_irq_base); + pr_debug("IOAPIC (id[0x%02x] address[0x%08x] gsi_base[%d])\n", + p->id, p->address, p->global_irq_base); } break; @@ -155,9 +157,9 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_io_sapic *p = (struct acpi_madt_io_sapic *)header; - pr_info("IOSAPIC (id[0x%x] address[%p] gsi_base[%d])\n", - p->id, (void *)(unsigned long)p->address, - p->global_irq_base); + pr_debug("IOSAPIC (id[0x%x] address[%p] gsi_base[%d])\n", + p->id, (void *)(unsigned long)p->address, + p->global_irq_base); } break; @@ -165,9 +167,9 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { struct acpi_madt_local_sapic *p = (struct acpi_madt_local_sapic *)header; - pr_info("LSAPIC (acpi_id[0x%02x] lsapic_id[0x%02x] lsapic_eid[0x%02x] %s)\n", - p->processor_id, p->id, p->eid, - (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + pr_debug("LSAPIC (acpi_id[0x%02x] lsapic_id[0x%02x] lsapic_eid[0x%02x] %s)\n", + p->processor_id, p->id, p->eid, + (p->lapic_flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); } break; @@ -183,6 +185,28 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) } break; + case ACPI_MADT_TYPE_GENERIC_INTERRUPT: + { + struct acpi_madt_generic_interrupt *p = + (struct acpi_madt_generic_interrupt *)header; + pr_debug("GICC (acpi_id[0x%04x] address[%llx] MPIDR[0x%llx] %s)\n", + p->uid, p->base_address, + p->arm_mpidr, + (p->flags & ACPI_MADT_ENABLED) ? "enabled" : "disabled"); + + } + break; + + case ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR: + { + struct acpi_madt_generic_distributor *p = + (struct acpi_madt_generic_distributor *)header; + pr_debug("GIC Distributor (gic_id[0x%04x] address[%llx] gsi_base[%d])\n", + p->gic_id, p->base_address, + p->global_irq_base); + } + break; + default: pr_warn("Found unsupported MADT entry (type = 0x%x)\n", header->type); diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 25798db14553..68f03141e432 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -157,10 +157,10 @@ static int dev_mkdir(const char *name, umode_t mode) if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mkdir(path.dentry->d_inode, dentry, mode); + err = vfs_mkdir(d_inode(path.dentry), dentry, mode); if (!err) /* mark as kernel-created inode */ - dentry->d_inode->i_private = &thread; + d_inode(dentry)->i_private = &thread; done_path_create(&path, dentry); return err; } @@ -207,7 +207,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, if (IS_ERR(dentry)) return PTR_ERR(dentry); - err = vfs_mknod(path.dentry->d_inode, dentry, mode, dev->devt); + err = vfs_mknod(d_inode(path.dentry), dentry, mode, dev->devt); if (!err) { struct iattr newattrs; @@ -215,12 +215,12 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid, newattrs.ia_uid = uid; newattrs.ia_gid = gid; newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID; - mutex_lock(&dentry->d_inode->i_mutex); + mutex_lock(&d_inode(dentry)->i_mutex); notify_change(dentry, &newattrs, NULL); - mutex_unlock(&dentry->d_inode->i_mutex); + mutex_unlock(&d_inode(dentry)->i_mutex); /* mark as kernel-created inode */ - dentry->d_inode->i_private = &thread; + d_inode(dentry)->i_private = &thread; } done_path_create(&path, dentry); return err; @@ -235,16 +235,16 @@ static int dev_rmdir(const char *name) dentry = kern_path_locked(name, &parent); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (dentry->d_inode) { - if (dentry->d_inode->i_private == &thread) - err = vfs_rmdir(parent.dentry->d_inode, dentry); + if (d_really_is_positive(dentry)) { + if (d_inode(dentry)->i_private == &thread) + err = vfs_rmdir(d_inode(parent.dentry), dentry); else err = -EPERM; } else { err = -ENOENT; } dput(dentry); - mutex_unlock(&parent.dentry->d_inode->i_mutex); + mutex_unlock(&d_inode(parent.dentry)->i_mutex); path_put(&parent); return err; } @@ -306,11 +306,11 @@ static int handle_remove(const char *nodename, struct device *dev) if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (dentry->d_inode) { + if (d_really_is_positive(dentry)) { struct kstat stat; struct path p = {.mnt = parent.mnt, .dentry = dentry}; err = vfs_getattr(&p, &stat); - if (!err && dev_mynode(dev, dentry->d_inode, &stat)) { + if (!err && dev_mynode(dev, d_inode(dentry), &stat)) { struct iattr newattrs; /* * before unlinking this node, reset permissions @@ -321,10 +321,10 @@ static int handle_remove(const char *nodename, struct device *dev) newattrs.ia_mode = stat.mode & ~0777; newattrs.ia_valid = ATTR_UID|ATTR_GID|ATTR_MODE; - mutex_lock(&dentry->d_inode->i_mutex); + mutex_lock(&d_inode(dentry)->i_mutex); notify_change(dentry, &newattrs, NULL); - mutex_unlock(&dentry->d_inode->i_mutex); - err = vfs_unlink(parent.dentry->d_inode, dentry, NULL); + mutex_unlock(&d_inode(dentry)->i_mutex); + err = vfs_unlink(d_inode(parent.dentry), dentry, NULL); if (!err || err == -ENOENT) deleted = 1; } @@ -332,7 +332,7 @@ static int handle_remove(const char *nodename, struct device *dev) err = -ENOENT; } dput(dentry); - mutex_unlock(&parent.dentry->d_inode->i_mutex); + mutex_unlock(&d_inode(parent.dentry)->i_mutex); path_put(&parent); if (deleted && strchr(nodename, '/')) diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 9a950022ff88..a6ee3d750c30 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -424,7 +424,7 @@ static int in_flight_summary_show(struct seq_file *m, void *pos) * So we have our own inline version of it above. :-( */ static inline int debugfs_positive(struct dentry *dentry) { - return dentry->d_inode && !d_unhashed(dentry); + return d_really_is_positive(dentry) && !d_unhashed(dentry); } /* make sure at *open* time that the respective object won't go away. */ @@ -439,15 +439,15 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo * or has debugfs_remove() already been called? */ parent = file->f_path.dentry->d_parent; /* not sure if this can happen: */ - if (!parent || !parent->d_inode) + if (!parent || d_really_is_negative(parent)) goto out; /* serialize with d_delete() */ - mutex_lock(&parent->d_inode->i_mutex); + mutex_lock(&d_inode(parent)->i_mutex); /* Make sure the object is still alive */ if (debugfs_positive(file->f_path.dentry) && kref_get_unless_zero(kref)) ret = 0; - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); if (!ret) { ret = single_open(file, show, data); if (ret) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b40af3203089..812523330a78 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3762,8 +3762,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) goto out_tag_set; } - /* We use the default size, but let's be explicit about it. */ - blk_queue_physical_block_size(q, SECTOR_SIZE); + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ /* set io sizes to object size */ segment_size = rbd_obj_bytes(&rbd_dev->header); @@ -5301,8 +5301,13 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) if (mapping) { ret = rbd_dev_header_watch_sync(rbd_dev); - if (ret) + if (ret) { + if (ret == -ENOENT) + pr_info("image %s/%s does not exist\n", + rbd_dev->spec->pool_name, + rbd_dev->spec->image_name); goto out_header_name; + } } ret = rbd_dev_header_info(rbd_dev); @@ -5319,8 +5324,14 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping) ret = rbd_spec_fill_snap_id(rbd_dev); else ret = rbd_spec_fill_names(rbd_dev); - if (ret) + if (ret) { + if (ret == -ENOENT) + pr_info("snap %s/%s@%s does not exist\n", + rbd_dev->spec->pool_name, + rbd_dev->spec->image_name, + rbd_dev->spec->snap_name); goto err_out_probe; + } if (rbd_dev->header.features & RBD_FEATURE_LAYERING) { ret = rbd_dev_v2_parent_info(rbd_dev); @@ -5390,8 +5401,11 @@ static ssize_t do_rbd_add(struct bus_type *bus, /* pick the pool */ rc = rbd_add_get_pool_id(rbdc, spec->pool_name); - if (rc < 0) + if (rc < 0) { + if (rc == -ENOENT) + pr_info("pool %s does not exist\n", spec->pool_name); goto err_out_client; + } spec->pool_id = (u64)rc; /* The ceph file layout needs to fit pool id in 32 bits */ @@ -5673,7 +5687,7 @@ static int __init rbd_init(void) /* * The number of active work items is limited by the number of - * rbd devices, so leave @max_active at default. + * rbd devices * queue depth, so leave @max_active at default. */ rbd_wq = alloc_workqueue(RBD_DRV_NAME, WQ_MEM_RECLAIM, 0); if (!rbd_wq) { diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 266469691e58..0aa135ddbf80 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -22,6 +22,7 @@ #include <linux/io.h> #include <linux/slab.h> #include <linux/sched_clock.h> +#include <linux/acpi.h> #include <asm/arch_timer.h> #include <asm/virt.h> @@ -371,8 +372,12 @@ arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np) if (arch_timer_rate) return; - /* Try to determine the frequency from the device tree or CNTFRQ */ - if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) { + /* + * Try to determine the frequency from the device tree or CNTFRQ, + * if ACPI is enabled, get the frequency from CNTFRQ ONLY. + */ + if (!acpi_disabled || + of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) { if (cntbase) arch_timer_rate = readl_relaxed(cntbase + CNTFRQ); else @@ -691,28 +696,8 @@ static void __init arch_timer_common_init(void) arch_timer_arch_init(); } -static void __init arch_timer_init(struct device_node *np) +static void __init arch_timer_init(void) { - int i; - - if (arch_timers_present & ARCH_CP15_TIMER) { - pr_warn("arch_timer: multiple nodes in dt, skipping\n"); - return; - } - - arch_timers_present |= ARCH_CP15_TIMER; - for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++) - arch_timer_ppi[i] = irq_of_parse_and_map(np, i); - arch_timer_detect_rate(NULL, np); - - /* - * If we cannot rely on firmware initializing the timer registers then - * we should use the physical timers instead. - */ - if (IS_ENABLED(CONFIG_ARM) && - of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) - arch_timer_use_virtual = false; - /* * If HYP mode is available, we know that the physical timer * has been configured to be accessible from PL1. Use it, so @@ -731,13 +716,39 @@ static void __init arch_timer_init(struct device_node *np) } } - arch_timer_c3stop = !of_property_read_bool(np, "always-on"); - arch_timer_register(); arch_timer_common_init(); } -CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_init); -CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_init); + +static void __init arch_timer_of_init(struct device_node *np) +{ + int i; + + if (arch_timers_present & ARCH_CP15_TIMER) { + pr_warn("arch_timer: multiple nodes in dt, skipping\n"); + return; + } + + arch_timers_present |= ARCH_CP15_TIMER; + for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++) + arch_timer_ppi[i] = irq_of_parse_and_map(np, i); + + arch_timer_detect_rate(NULL, np); + + arch_timer_c3stop = !of_property_read_bool(np, "always-on"); + + /* + * If we cannot rely on firmware initializing the timer registers then + * we should use the physical timers instead. + */ + if (IS_ENABLED(CONFIG_ARM) && + of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) + arch_timer_use_virtual = false; + + arch_timer_init(); +} +CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init); +CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init); static void __init arch_timer_mem_init(struct device_node *np) { @@ -804,3 +815,70 @@ static void __init arch_timer_mem_init(struct device_node *np) } CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem", arch_timer_mem_init); + +#ifdef CONFIG_ACPI +static int __init map_generic_timer_interrupt(u32 interrupt, u32 flags) +{ + int trigger, polarity; + + if (!interrupt) + return 0; + + trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE + : ACPI_LEVEL_SENSITIVE; + + polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW + : ACPI_ACTIVE_HIGH; + + return acpi_register_gsi(NULL, interrupt, trigger, polarity); +} + +/* Initialize per-processor generic timer */ +static int __init arch_timer_acpi_init(struct acpi_table_header *table) +{ + struct acpi_table_gtdt *gtdt; + + if (arch_timers_present & ARCH_CP15_TIMER) { + pr_warn("arch_timer: already initialized, skipping\n"); + return -EINVAL; + } + + gtdt = container_of(table, struct acpi_table_gtdt, header); + + arch_timers_present |= ARCH_CP15_TIMER; + + arch_timer_ppi[PHYS_SECURE_PPI] = + map_generic_timer_interrupt(gtdt->secure_el1_interrupt, + gtdt->secure_el1_flags); + + arch_timer_ppi[PHYS_NONSECURE_PPI] = + map_generic_timer_interrupt(gtdt->non_secure_el1_interrupt, + gtdt->non_secure_el1_flags); + + arch_timer_ppi[VIRT_PPI] = + map_generic_timer_interrupt(gtdt->virtual_timer_interrupt, + gtdt->virtual_timer_flags); + + arch_timer_ppi[HYP_PPI] = + map_generic_timer_interrupt(gtdt->non_secure_el2_interrupt, + gtdt->non_secure_el2_flags); + + /* Get the frequency from CNTFRQ */ + arch_timer_detect_rate(NULL, NULL); + + /* Always-on capability */ + arch_timer_c3stop = !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON); + + arch_timer_init(); + return 0; +} + +/* Initialize all the generic timers presented in GTDT */ +void __init acpi_generic_timer_init(void) +{ + if (acpi_disabled) + return; + + acpi_table_parse(ACPI_SIG_GTDT, arch_timer_acpi_init); +} +#endif diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index c5b81beccc8e..6414661ac1c4 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -31,6 +31,7 @@ #include <asm/div64.h> #include <asm/msr.h> #include <asm/cpu_device_id.h> +#include <asm/cpufeature.h> #define BYT_RATIOS 0x66a #define BYT_VIDS 0x66b @@ -649,7 +650,7 @@ static struct cpu_defaults byt_params = { .pid_policy = { .sample_rate_ms = 10, .deadband = 0, - .setpoint = 97, + .setpoint = 60, .p_gain_pct = 14, .d_gain_pct = 0, .i_gain_pct = 4, @@ -1200,8 +1201,7 @@ static int __init intel_pstate_init(void) { int cpu, rc = 0; const struct x86_cpu_id *id; - struct cpu_defaults *cpu_info; - struct cpuinfo_x86 *c = &boot_cpu_data; + struct cpu_defaults *cpu_def; if (no_load) return -ENODEV; @@ -1217,10 +1217,10 @@ static int __init intel_pstate_init(void) if (intel_pstate_platform_pwr_mgmt_exists()) return -ENODEV; - cpu_info = (struct cpu_defaults *)id->driver_data; + cpu_def = (struct cpu_defaults *)id->driver_data; - copy_pid_params(&cpu_info->pid_policy); - copy_cpu_funcs(&cpu_info->funcs); + copy_pid_params(&cpu_def->pid_policy); + copy_cpu_funcs(&cpu_def->funcs); if (intel_pstate_msrs_not_valid()) return -ENODEV; @@ -1231,7 +1231,7 @@ static int __init intel_pstate_init(void) if (!all_cpu_data) return -ENOMEM; - if (cpu_has(c,X86_FEATURE_HWP) && !no_hwp) + if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) intel_pstate_hwp_enable(); if (!hwp_active && hwp_only) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 800bf41718e1..033c0c86f6ec 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -446,8 +446,9 @@ config CRYPTO_DEV_VMX source "drivers/crypto/vmx/Kconfig" config CRYPTO_DEV_IMGTEC_HASH - depends on MIPS || COMPILE_TEST tristate "Imagination Technologies hardware hash accelerator" + depends on MIPS || COMPILE_TEST + depends on HAS_DMA select CRYPTO_ALGAPI select CRYPTO_MD5 select CRYPTO_SHA1 diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 5be225c2ba98..c5a9138a6a8d 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -265,43 +265,40 @@ static inline int is_dma_buf_file(struct file *file) } /** - * dma_buf_export_named - Creates a new dma_buf, and associates an anon file + * dma_buf_export - Creates a new dma_buf, and associates an anon file * with this buffer, so it can be exported. * Also connect the allocator specific data and ops to the buffer. * Additionally, provide a name string for exporter; useful in debugging. * - * @priv: [in] Attach private data of allocator to this buffer - * @ops: [in] Attach allocator-defined dma buf ops to the new buffer. - * @size: [in] Size of the buffer - * @flags: [in] mode flags for the file. - * @exp_name: [in] name of the exporting module - useful for debugging. - * @resv: [in] reservation-object, NULL to allocate default one. + * @exp_info: [in] holds all the export related information provided + * by the exporter. see struct dma_buf_export_info + * for further details. * * Returns, on success, a newly created dma_buf object, which wraps the * supplied private data and operations for dma_buf_ops. On either missing * ops, or error in allocating struct dma_buf, will return negative error. * */ -struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, - size_t size, int flags, const char *exp_name, - struct reservation_object *resv) +struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) { struct dma_buf *dmabuf; + struct reservation_object *resv = exp_info->resv; struct file *file; size_t alloc_size = sizeof(struct dma_buf); - if (!resv) + if (!exp_info->resv) alloc_size += sizeof(struct reservation_object); else /* prevent &dma_buf[1] == dma_buf->resv */ alloc_size += 1; - if (WARN_ON(!priv || !ops - || !ops->map_dma_buf - || !ops->unmap_dma_buf - || !ops->release - || !ops->kmap_atomic - || !ops->kmap - || !ops->mmap)) { + if (WARN_ON(!exp_info->priv + || !exp_info->ops + || !exp_info->ops->map_dma_buf + || !exp_info->ops->unmap_dma_buf + || !exp_info->ops->release + || !exp_info->ops->kmap_atomic + || !exp_info->ops->kmap + || !exp_info->ops->mmap)) { return ERR_PTR(-EINVAL); } @@ -309,10 +306,10 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, if (dmabuf == NULL) return ERR_PTR(-ENOMEM); - dmabuf->priv = priv; - dmabuf->ops = ops; - dmabuf->size = size; - dmabuf->exp_name = exp_name; + dmabuf->priv = exp_info->priv; + dmabuf->ops = exp_info->ops; + dmabuf->size = exp_info->size; + dmabuf->exp_name = exp_info->exp_name; init_waitqueue_head(&dmabuf->poll); dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; @@ -323,7 +320,8 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, } dmabuf->resv = resv; - file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags); + file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, + exp_info->flags); if (IS_ERR(file)) { kfree(dmabuf); return ERR_CAST(file); @@ -341,8 +339,7 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, return dmabuf; } -EXPORT_SYMBOL_GPL(dma_buf_export_named); - +EXPORT_SYMBOL_GPL(dma_buf_export); /** * dma_buf_fd - returns a file descriptor for the given dma_buf diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 91eced044321..fd7ac13f2574 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -112,6 +112,17 @@ config FSL_DMA EloPlus is on mpc85xx and mpc86xx and Pxxx parts, and the Elo3 is on some Txxx and Bxxx parts. +config FSL_RAID + tristate "Freescale RAID engine Support" + depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH + select DMA_ENGINE + select DMA_ENGINE_RAID + ---help--- + Enable support for Freescale RAID Engine. RAID Engine is + available on some QorIQ SoCs (like P5020/P5040). It has + the capability to offload memcpy, xor and pq computation + for raid5/6. + source "drivers/dma/hsu/Kconfig" config MPC512X_DMA @@ -347,6 +358,16 @@ config DMA_JZ4740 select DMA_ENGINE select DMA_VIRTUAL_CHANNELS +config DMA_JZ4780 + tristate "JZ4780 DMA support" + depends on MACH_JZ4780 + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + This selects support for the DMA controller in Ingenic JZ4780 SoCs. + If you have a board based on such a SoC and wish to use DMA for + devices which can use the DMA controller, say Y or M here. + config K3_DMA tristate "Hisilicon K3 DMA support" depends on ARCH_HI3xxx @@ -414,6 +435,14 @@ config IMG_MDC_DMA help Enable support for the IMG multi-threaded DMA controller (MDC). +config XGENE_DMA + tristate "APM X-Gene DMA support" + select DMA_ENGINE + select DMA_ENGINE_RAID + select ASYNC_TX_ENABLE_CHANNEL_SWITCH + help + Enable support for the APM X-Gene SoC DMA engine. + config DMA_ENGINE bool diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 7e8301cb489d..69f77d5ba53b 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -41,9 +41,11 @@ obj-$(CONFIG_DMA_OMAP) += omap-dma.o obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o +obj-$(CONFIG_DMA_JZ4780) += dma-jz4780.o obj-$(CONFIG_TI_CPPI41) += cppi41.o obj-$(CONFIG_K3_DMA) += k3dma.o obj-$(CONFIG_MOXART_DMA) += moxart-dma.o +obj-$(CONFIG_FSL_RAID) += fsl_raid.o obj-$(CONFIG_FSL_EDMA) += fsl-edma.o obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o obj-y += xilinx/ @@ -51,3 +53,4 @@ obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o obj-$(CONFIG_DMA_SUN6I) += sun6i-dma.o obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o +obj-$(CONFIG_XGENE_DMA) += xgene-dma.o diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 83aa55d6fa5d..49d396ec06e5 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -15,10 +15,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is in this distribution in the file * called COPYING. * @@ -1195,11 +1191,6 @@ static void pl08x_free_txd_list(struct pl08x_driver_data *pl08x, /* * The DMA ENGINE API */ -static int pl08x_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void pl08x_free_chan_resources(struct dma_chan *chan) { /* Ensure all queued descriptors are freed */ @@ -2066,7 +2057,6 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) /* Initialize memcpy engine */ dma_cap_set(DMA_MEMCPY, pl08x->memcpy.cap_mask); pl08x->memcpy.dev = &adev->dev; - pl08x->memcpy.device_alloc_chan_resources = pl08x_alloc_chan_resources; pl08x->memcpy.device_free_chan_resources = pl08x_free_chan_resources; pl08x->memcpy.device_prep_dma_memcpy = pl08x_prep_dma_memcpy; pl08x->memcpy.device_prep_dma_interrupt = pl08x_prep_dma_interrupt; @@ -2085,7 +2075,6 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask); dma_cap_set(DMA_CYCLIC, pl08x->slave.cap_mask); pl08x->slave.dev = &adev->dev; - pl08x->slave.device_alloc_chan_resources = pl08x_alloc_chan_resources; pl08x->slave.device_free_chan_resources = pl08x_free_chan_resources; pl08x->slave.device_prep_dma_interrupt = pl08x_prep_dma_interrupt; pl08x->slave.device_tx_status = pl08x_dma_tx_status; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 0b4fc6fb48ce..57b2141ddddc 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -65,6 +65,21 @@ static void atc_issue_pending(struct dma_chan *chan); /*----------------------------------------------------------------------*/ +static inline unsigned int atc_get_xfer_width(dma_addr_t src, dma_addr_t dst, + size_t len) +{ + unsigned int width; + + if (!((src | dst | len) & 3)) + width = 2; + else if (!((src | dst | len) & 1)) + width = 1; + else + width = 0; + + return width; +} + static struct at_desc *atc_first_active(struct at_dma_chan *atchan) { return list_first_entry(&atchan->active_list, @@ -659,16 +674,10 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, * We can be a lot more clever here, but this should take care * of the most common optimization. */ - if (!((src | dest | len) & 3)) { - ctrla = ATC_SRC_WIDTH_WORD | ATC_DST_WIDTH_WORD; - src_width = dst_width = 2; - } else if (!((src | dest | len) & 1)) { - ctrla = ATC_SRC_WIDTH_HALFWORD | ATC_DST_WIDTH_HALFWORD; - src_width = dst_width = 1; - } else { - ctrla = ATC_SRC_WIDTH_BYTE | ATC_DST_WIDTH_BYTE; - src_width = dst_width = 0; - } + src_width = dst_width = atc_get_xfer_width(src, dest, len); + + ctrla = ATC_SRC_WIDTH(src_width) | + ATC_DST_WIDTH(dst_width); for (offset = 0; offset < len; offset += xfer_count << src_width) { xfer_count = min_t(size_t, (len - offset) >> src_width, @@ -862,6 +871,144 @@ err: } /** + * atc_prep_dma_sg - prepare memory to memory scather-gather operation + * @chan: the channel to prepare operation on + * @dst_sg: destination scatterlist + * @dst_nents: number of destination scatterlist entries + * @src_sg: source scatterlist + * @src_nents: number of source scatterlist entries + * @flags: tx descriptor status flags + */ +static struct dma_async_tx_descriptor * +atc_prep_dma_sg(struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags) +{ + struct at_dma_chan *atchan = to_at_dma_chan(chan); + struct at_desc *desc = NULL; + struct at_desc *first = NULL; + struct at_desc *prev = NULL; + unsigned int src_width; + unsigned int dst_width; + size_t xfer_count; + u32 ctrla; + u32 ctrlb; + size_t dst_len = 0, src_len = 0; + dma_addr_t dst = 0, src = 0; + size_t len = 0, total_len = 0; + + if (unlikely(dst_nents == 0 || src_nents == 0)) + return NULL; + + if (unlikely(dst_sg == NULL || src_sg == NULL)) + return NULL; + + ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN + | ATC_SRC_ADDR_MODE_INCR + | ATC_DST_ADDR_MODE_INCR + | ATC_FC_MEM2MEM; + + /* + * loop until there is either no more source or no more destination + * scatterlist entry + */ + while (true) { + + /* prepare the next transfer */ + if (dst_len == 0) { + + /* no more destination scatterlist entries */ + if (!dst_sg || !dst_nents) + break; + + dst = sg_dma_address(dst_sg); + dst_len = sg_dma_len(dst_sg); + + dst_sg = sg_next(dst_sg); + dst_nents--; + } + + if (src_len == 0) { + + /* no more source scatterlist entries */ + if (!src_sg || !src_nents) + break; + + src = sg_dma_address(src_sg); + src_len = sg_dma_len(src_sg); + + src_sg = sg_next(src_sg); + src_nents--; + } + + len = min_t(size_t, src_len, dst_len); + if (len == 0) + continue; + + /* take care for the alignment */ + src_width = dst_width = atc_get_xfer_width(src, dst, len); + + ctrla = ATC_SRC_WIDTH(src_width) | + ATC_DST_WIDTH(dst_width); + + /* + * The number of transfers to set up refer to the source width + * that depends on the alignment. + */ + xfer_count = len >> src_width; + if (xfer_count > ATC_BTSIZE_MAX) { + xfer_count = ATC_BTSIZE_MAX; + len = ATC_BTSIZE_MAX << src_width; + } + + /* create the transfer */ + desc = atc_desc_get(atchan); + if (!desc) + goto err_desc_get; + + desc->lli.saddr = src; + desc->lli.daddr = dst; + desc->lli.ctrla = ctrla | xfer_count; + desc->lli.ctrlb = ctrlb; + + desc->txd.cookie = 0; + desc->len = len; + + /* + * Although we only need the transfer width for the first and + * the last descriptor, its easier to set it to all descriptors. + */ + desc->tx_width = src_width; + + atc_desc_chain(&first, &prev, desc); + + /* update the lengths and addresses for the next loop cycle */ + dst_len -= len; + src_len -= len; + dst += len; + src += len; + + total_len += len; + } + + /* First descriptor of the chain embedds additional information */ + first->txd.cookie = -EBUSY; + first->total_len = total_len; + + /* set end-of-link to the last link descriptor of list*/ + set_desc_eol(desc); + + first->txd.flags = flags; /* client is in control of this ack */ + + return &first->txd; + +err_desc_get: + atc_desc_put(atchan, first); + return NULL; +} + +/** * atc_dma_cyclic_check_values * Check for too big/unaligned periods and unaligned DMA buffer */ @@ -1461,8 +1608,10 @@ static int __init at_dma_probe(struct platform_device *pdev) /* setup platform data for each SoC */ dma_cap_set(DMA_MEMCPY, at91sam9rl_config.cap_mask); + dma_cap_set(DMA_SG, at91sam9rl_config.cap_mask); dma_cap_set(DMA_MEMCPY, at91sam9g45_config.cap_mask); dma_cap_set(DMA_SLAVE, at91sam9g45_config.cap_mask); + dma_cap_set(DMA_SG, at91sam9g45_config.cap_mask); /* get DMA parameters from controller type */ plat_dat = at_dma_get_driver_data(pdev); @@ -1582,11 +1731,15 @@ static int __init at_dma_probe(struct platform_device *pdev) atdma->dma_common.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; } + if (dma_has_cap(DMA_SG, atdma->dma_common.cap_mask)) + atdma->dma_common.device_prep_dma_sg = atc_prep_dma_sg; + dma_writel(atdma, EN, AT_DMA_ENABLE); - dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s), %d channels\n", + dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s), %d channels\n", dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask) ? "cpy " : "", dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask) ? "slave " : "", + dma_has_cap(DMA_SG, atdma->dma_common.cap_mask) ? "sg-cpy " : "", plat_dat->nr_channels); dma_async_device_register(&atdma->dma_common); diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index d9891d3461f6..933e4b338459 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1154,8 +1154,10 @@ static int at_xdmac_device_resume(struct dma_chan *chan) dev_dbg(chan2dev(chan), "%s\n", __func__); spin_lock_bh(&atchan->lock); - if (!at_xdmac_chan_is_paused(atchan)) + if (!at_xdmac_chan_is_paused(atchan)) { + spin_unlock_bh(&atchan->lock); return 0; + } at_xdmac_write(atxdmac, AT_XDMAC_GRWR, atchan->mask); clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); diff --git a/drivers/dma/bestcomm/bestcomm.c b/drivers/dma/bestcomm/bestcomm.c index fa378d88f6c8..180fedb418cc 100644 --- a/drivers/dma/bestcomm/bestcomm.c +++ b/drivers/dma/bestcomm/bestcomm.c @@ -30,7 +30,7 @@ #define DRIVER_NAME "bestcomm-core" /* MPC5200 device tree match tables */ -static struct of_device_id mpc52xx_sram_ids[] = { +static const struct of_device_id mpc52xx_sram_ids[] = { { .compatible = "fsl,mpc5200-sram", }, { .compatible = "mpc5200-sram", }, {} @@ -481,7 +481,7 @@ static int mpc52xx_bcom_remove(struct platform_device *op) return 0; } -static struct of_device_id mpc52xx_bcom_of_match[] = { +static const struct of_device_id mpc52xx_bcom_of_match[] = { { .compatible = "fsl,mpc5200-bestcomm", }, { .compatible = "mpc5200-bestcomm", }, {}, diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c index 84884418fd30..7638b24ce8d0 100644 --- a/drivers/dma/dma-jz4740.c +++ b/drivers/dma/dma-jz4740.c @@ -7,10 +7,6 @@ * Free Software Foundation; either version 2 of the License, or (at your * option) any later version. * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - * */ #include <linux/dmaengine.h> @@ -343,7 +339,7 @@ static void jz4740_dma_chan_irq(struct jz4740_dmaengine_chan *chan) { spin_lock(&chan->vchan.lock); if (chan->desc) { - if (chan->desc && chan->desc->cyclic) { + if (chan->desc->cyclic) { vchan_cyclic_callback(&chan->desc->vdesc); } else { if (chan->next_sg == chan->desc->num_sgs) { @@ -496,11 +492,6 @@ static enum dma_status jz4740_dma_tx_status(struct dma_chan *c, return status; } -static int jz4740_dma_alloc_chan_resources(struct dma_chan *c) -{ - return 0; -} - static void jz4740_dma_free_chan_resources(struct dma_chan *c) { vchan_free_chan_resources(to_virt_chan(c)); @@ -543,7 +534,6 @@ static int jz4740_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_SLAVE, dd->cap_mask); dma_cap_set(DMA_CYCLIC, dd->cap_mask); - dd->device_alloc_chan_resources = jz4740_dma_alloc_chan_resources; dd->device_free_chan_resources = jz4740_dma_free_chan_resources; dd->device_tx_status = jz4740_dma_tx_status; dd->device_issue_pending = jz4740_dma_issue_pending; diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c new file mode 100644 index 000000000000..26d2f0e09ea3 --- /dev/null +++ b/drivers/dma/dma-jz4780.c @@ -0,0 +1,877 @@ +/* + * Ingenic JZ4780 DMA controller + * + * Copyright (c) 2015 Imagination Technologies + * Author: Alex Smith <alex@alex-smith.me.uk> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/clk.h> +#include <linux/dmapool.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_dma.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "dmaengine.h" +#include "virt-dma.h" + +#define JZ_DMA_NR_CHANNELS 32 + +/* Global registers. */ +#define JZ_DMA_REG_DMAC 0x1000 +#define JZ_DMA_REG_DIRQP 0x1004 +#define JZ_DMA_REG_DDR 0x1008 +#define JZ_DMA_REG_DDRS 0x100c +#define JZ_DMA_REG_DMACP 0x101c +#define JZ_DMA_REG_DSIRQP 0x1020 +#define JZ_DMA_REG_DSIRQM 0x1024 +#define JZ_DMA_REG_DCIRQP 0x1028 +#define JZ_DMA_REG_DCIRQM 0x102c + +/* Per-channel registers. */ +#define JZ_DMA_REG_CHAN(n) (n * 0x20) +#define JZ_DMA_REG_DSA(n) (0x00 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DTA(n) (0x04 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DTC(n) (0x08 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DRT(n) (0x0c + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DCS(n) (0x10 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DCM(n) (0x14 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DDA(n) (0x18 + JZ_DMA_REG_CHAN(n)) +#define JZ_DMA_REG_DSD(n) (0x1c + JZ_DMA_REG_CHAN(n)) + +#define JZ_DMA_DMAC_DMAE BIT(0) +#define JZ_DMA_DMAC_AR BIT(2) +#define JZ_DMA_DMAC_HLT BIT(3) +#define JZ_DMA_DMAC_FMSC BIT(31) + +#define JZ_DMA_DRT_AUTO 0x8 + +#define JZ_DMA_DCS_CTE BIT(0) +#define JZ_DMA_DCS_HLT BIT(2) +#define JZ_DMA_DCS_TT BIT(3) +#define JZ_DMA_DCS_AR BIT(4) +#define JZ_DMA_DCS_DES8 BIT(30) + +#define JZ_DMA_DCM_LINK BIT(0) +#define JZ_DMA_DCM_TIE BIT(1) +#define JZ_DMA_DCM_STDE BIT(2) +#define JZ_DMA_DCM_TSZ_SHIFT 8 +#define JZ_DMA_DCM_TSZ_MASK (0x7 << JZ_DMA_DCM_TSZ_SHIFT) +#define JZ_DMA_DCM_DP_SHIFT 12 +#define JZ_DMA_DCM_SP_SHIFT 14 +#define JZ_DMA_DCM_DAI BIT(22) +#define JZ_DMA_DCM_SAI BIT(23) + +#define JZ_DMA_SIZE_4_BYTE 0x0 +#define JZ_DMA_SIZE_1_BYTE 0x1 +#define JZ_DMA_SIZE_2_BYTE 0x2 +#define JZ_DMA_SIZE_16_BYTE 0x3 +#define JZ_DMA_SIZE_32_BYTE 0x4 +#define JZ_DMA_SIZE_64_BYTE 0x5 +#define JZ_DMA_SIZE_128_BYTE 0x6 + +#define JZ_DMA_WIDTH_32_BIT 0x0 +#define JZ_DMA_WIDTH_8_BIT 0x1 +#define JZ_DMA_WIDTH_16_BIT 0x2 + +#define JZ_DMA_BUSWIDTHS (BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \ + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \ + BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)) + +/** + * struct jz4780_dma_hwdesc - descriptor structure read by the DMA controller. + * @dcm: value for the DCM (channel command) register + * @dsa: source address + * @dta: target address + * @dtc: transfer count (number of blocks of the transfer size specified in DCM + * to transfer) in the low 24 bits, offset of the next descriptor from the + * descriptor base address in the upper 8 bits. + * @sd: target/source stride difference (in stride transfer mode). + * @drt: request type + */ +struct jz4780_dma_hwdesc { + uint32_t dcm; + uint32_t dsa; + uint32_t dta; + uint32_t dtc; + uint32_t sd; + uint32_t drt; + uint32_t reserved[2]; +}; + +/* Size of allocations for hardware descriptor blocks. */ +#define JZ_DMA_DESC_BLOCK_SIZE PAGE_SIZE +#define JZ_DMA_MAX_DESC \ + (JZ_DMA_DESC_BLOCK_SIZE / sizeof(struct jz4780_dma_hwdesc)) + +struct jz4780_dma_desc { + struct virt_dma_desc vdesc; + + struct jz4780_dma_hwdesc *desc; + dma_addr_t desc_phys; + unsigned int count; + enum dma_transaction_type type; + uint32_t status; +}; + +struct jz4780_dma_chan { + struct virt_dma_chan vchan; + unsigned int id; + struct dma_pool *desc_pool; + + uint32_t transfer_type; + uint32_t transfer_shift; + struct dma_slave_config config; + + struct jz4780_dma_desc *desc; + unsigned int curr_hwdesc; +}; + +struct jz4780_dma_dev { + struct dma_device dma_device; + void __iomem *base; + struct clk *clk; + unsigned int irq; + + uint32_t chan_reserved; + struct jz4780_dma_chan chan[JZ_DMA_NR_CHANNELS]; +}; + +struct jz4780_dma_data { + uint32_t transfer_type; + int channel; +}; + +static inline struct jz4780_dma_chan *to_jz4780_dma_chan(struct dma_chan *chan) +{ + return container_of(chan, struct jz4780_dma_chan, vchan.chan); +} + +static inline struct jz4780_dma_desc *to_jz4780_dma_desc( + struct virt_dma_desc *vdesc) +{ + return container_of(vdesc, struct jz4780_dma_desc, vdesc); +} + +static inline struct jz4780_dma_dev *jz4780_dma_chan_parent( + struct jz4780_dma_chan *jzchan) +{ + return container_of(jzchan->vchan.chan.device, struct jz4780_dma_dev, + dma_device); +} + +static inline uint32_t jz4780_dma_readl(struct jz4780_dma_dev *jzdma, + unsigned int reg) +{ + return readl(jzdma->base + reg); +} + +static inline void jz4780_dma_writel(struct jz4780_dma_dev *jzdma, + unsigned int reg, uint32_t val) +{ + writel(val, jzdma->base + reg); +} + +static struct jz4780_dma_desc *jz4780_dma_desc_alloc( + struct jz4780_dma_chan *jzchan, unsigned int count, + enum dma_transaction_type type) +{ + struct jz4780_dma_desc *desc; + + if (count > JZ_DMA_MAX_DESC) + return NULL; + + desc = kzalloc(sizeof(*desc), GFP_NOWAIT); + if (!desc) + return NULL; + + desc->desc = dma_pool_alloc(jzchan->desc_pool, GFP_NOWAIT, + &desc->desc_phys); + if (!desc->desc) { + kfree(desc); + return NULL; + } + + desc->count = count; + desc->type = type; + return desc; +} + +static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc) +{ + struct jz4780_dma_desc *desc = to_jz4780_dma_desc(vdesc); + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(vdesc->tx.chan); + + dma_pool_free(jzchan->desc_pool, desc->desc, desc->desc_phys); + kfree(desc); +} + +static uint32_t jz4780_dma_transfer_size(unsigned long val, int *ord) +{ + *ord = ffs(val) - 1; + + switch (*ord) { + case 0: + return JZ_DMA_SIZE_1_BYTE; + case 1: + return JZ_DMA_SIZE_2_BYTE; + case 2: + return JZ_DMA_SIZE_4_BYTE; + case 4: + return JZ_DMA_SIZE_16_BYTE; + case 5: + return JZ_DMA_SIZE_32_BYTE; + case 6: + return JZ_DMA_SIZE_64_BYTE; + case 7: + return JZ_DMA_SIZE_128_BYTE; + default: + return -EINVAL; + } +} + +static uint32_t jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan, + struct jz4780_dma_hwdesc *desc, dma_addr_t addr, size_t len, + enum dma_transfer_direction direction) +{ + struct dma_slave_config *config = &jzchan->config; + uint32_t width, maxburst, tsz; + int ord; + + if (direction == DMA_MEM_TO_DEV) { + desc->dcm = JZ_DMA_DCM_SAI; + desc->dsa = addr; + desc->dta = config->dst_addr; + desc->drt = jzchan->transfer_type; + + width = config->dst_addr_width; + maxburst = config->dst_maxburst; + } else { + desc->dcm = JZ_DMA_DCM_DAI; + desc->dsa = config->src_addr; + desc->dta = addr; + desc->drt = jzchan->transfer_type; + + width = config->src_addr_width; + maxburst = config->src_maxburst; + } + + /* + * This calculates the maximum transfer size that can be used with the + * given address, length, width and maximum burst size. The address + * must be aligned to the transfer size, the total length must be + * divisible by the transfer size, and we must not use more than the + * maximum burst specified by the user. + */ + tsz = jz4780_dma_transfer_size(addr | len | (width * maxburst), &ord); + jzchan->transfer_shift = ord; + + switch (width) { + case DMA_SLAVE_BUSWIDTH_1_BYTE: + case DMA_SLAVE_BUSWIDTH_2_BYTES: + break; + case DMA_SLAVE_BUSWIDTH_4_BYTES: + width = JZ_DMA_WIDTH_32_BIT; + break; + default: + return -EINVAL; + } + + desc->dcm |= tsz << JZ_DMA_DCM_TSZ_SHIFT; + desc->dcm |= width << JZ_DMA_DCM_SP_SHIFT; + desc->dcm |= width << JZ_DMA_DCM_DP_SHIFT; + + desc->dtc = len >> ord; +} + +static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg( + struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, + enum dma_transfer_direction direction, unsigned long flags) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + struct jz4780_dma_desc *desc; + unsigned int i; + int err; + + desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE); + if (!desc) + return NULL; + + for (i = 0; i < sg_len; i++) { + err = jz4780_dma_setup_hwdesc(jzchan, &desc->desc[i], + sg_dma_address(&sgl[i]), + sg_dma_len(&sgl[i]), + direction); + if (err < 0) + return ERR_PTR(err); + + + desc->desc[i].dcm |= JZ_DMA_DCM_TIE; + + if (i != (sg_len - 1)) { + /* Automatically proceeed to the next descriptor. */ + desc->desc[i].dcm |= JZ_DMA_DCM_LINK; + + /* + * The upper 8 bits of the DTC field in the descriptor + * must be set to (offset from descriptor base of next + * descriptor >> 4). + */ + desc->desc[i].dtc |= + (((i + 1) * sizeof(*desc->desc)) >> 4) << 24; + } + } + + return vchan_tx_prep(&jzchan->vchan, &desc->vdesc, flags); +} + +static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic( + struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, + size_t period_len, enum dma_transfer_direction direction, + unsigned long flags) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + struct jz4780_dma_desc *desc; + unsigned int periods, i; + int err; + + if (buf_len % period_len) + return NULL; + + periods = buf_len / period_len; + + desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC); + if (!desc) + return NULL; + + for (i = 0; i < periods; i++) { + err = jz4780_dma_setup_hwdesc(jzchan, &desc->desc[i], buf_addr, + period_len, direction); + if (err < 0) + return ERR_PTR(err); + + buf_addr += period_len; + + /* + * Set the link bit to indicate that the controller should + * automatically proceed to the next descriptor. In + * jz4780_dma_begin(), this will be cleared if we need to issue + * an interrupt after each period. + */ + desc->desc[i].dcm |= JZ_DMA_DCM_TIE | JZ_DMA_DCM_LINK; + + /* + * The upper 8 bits of the DTC field in the descriptor must be + * set to (offset from descriptor base of next descriptor >> 4). + * If this is the last descriptor, link it back to the first, + * i.e. leave offset set to 0, otherwise point to the next one. + */ + if (i != (periods - 1)) { + desc->desc[i].dtc |= + (((i + 1) * sizeof(*desc->desc)) >> 4) << 24; + } + } + + return vchan_tx_prep(&jzchan->vchan, &desc->vdesc, flags); +} + +struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + struct jz4780_dma_desc *desc; + uint32_t tsz; + int ord; + + desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY); + if (!desc) + return NULL; + + tsz = jz4780_dma_transfer_size(dest | src | len, &ord); + if (tsz < 0) + return ERR_PTR(tsz); + + desc->desc[0].dsa = src; + desc->desc[0].dta = dest; + desc->desc[0].drt = JZ_DMA_DRT_AUTO; + desc->desc[0].dcm = JZ_DMA_DCM_TIE | JZ_DMA_DCM_SAI | JZ_DMA_DCM_DAI | + tsz << JZ_DMA_DCM_TSZ_SHIFT | + JZ_DMA_WIDTH_32_BIT << JZ_DMA_DCM_SP_SHIFT | + JZ_DMA_WIDTH_32_BIT << JZ_DMA_DCM_DP_SHIFT; + desc->desc[0].dtc = len >> ord; + + return vchan_tx_prep(&jzchan->vchan, &desc->vdesc, flags); +} + +static void jz4780_dma_begin(struct jz4780_dma_chan *jzchan) +{ + struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan); + struct virt_dma_desc *vdesc; + unsigned int i; + dma_addr_t desc_phys; + + if (!jzchan->desc) { + vdesc = vchan_next_desc(&jzchan->vchan); + if (!vdesc) + return; + + list_del(&vdesc->node); + + jzchan->desc = to_jz4780_dma_desc(vdesc); + jzchan->curr_hwdesc = 0; + + if (jzchan->desc->type == DMA_CYCLIC && vdesc->tx.callback) { + /* + * The DMA controller doesn't support triggering an + * interrupt after processing each descriptor, only + * after processing an entire terminated list of + * descriptors. For a cyclic DMA setup the list of + * descriptors is not terminated so we can never get an + * interrupt. + * + * If the user requested a callback for a cyclic DMA + * setup then we workaround this hardware limitation + * here by degrading to a set of unlinked descriptors + * which we will submit in sequence in response to the + * completion of processing the previous descriptor. + */ + for (i = 0; i < jzchan->desc->count; i++) + jzchan->desc->desc[i].dcm &= ~JZ_DMA_DCM_LINK; + } + } else { + /* + * There is an existing transfer, therefore this must be one + * for which we unlinked the descriptors above. Advance to the + * next one in the list. + */ + jzchan->curr_hwdesc = + (jzchan->curr_hwdesc + 1) % jzchan->desc->count; + } + + /* Use 8-word descriptors. */ + jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), JZ_DMA_DCS_DES8); + + /* Write descriptor address and initiate descriptor fetch. */ + desc_phys = jzchan->desc->desc_phys + + (jzchan->curr_hwdesc * sizeof(*jzchan->desc->desc)); + jz4780_dma_writel(jzdma, JZ_DMA_REG_DDA(jzchan->id), desc_phys); + jz4780_dma_writel(jzdma, JZ_DMA_REG_DDRS, BIT(jzchan->id)); + + /* Enable the channel. */ + jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), + JZ_DMA_DCS_DES8 | JZ_DMA_DCS_CTE); +} + +static void jz4780_dma_issue_pending(struct dma_chan *chan) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&jzchan->vchan.lock, flags); + + if (vchan_issue_pending(&jzchan->vchan) && !jzchan->desc) + jz4780_dma_begin(jzchan); + + spin_unlock_irqrestore(&jzchan->vchan.lock, flags); +} + +static int jz4780_dma_terminate_all(struct jz4780_dma_chan *jzchan) +{ + struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan); + unsigned long flags; + LIST_HEAD(head); + + spin_lock_irqsave(&jzchan->vchan.lock, flags); + + /* Clear the DMA status and stop the transfer. */ + jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0); + if (jzchan->desc) { + jz4780_dma_desc_free(&jzchan->desc->vdesc); + jzchan->desc = NULL; + } + + vchan_get_all_descriptors(&jzchan->vchan, &head); + + spin_unlock_irqrestore(&jzchan->vchan.lock, flags); + + vchan_dma_desc_free_list(&jzchan->vchan, &head); + return 0; +} + +static int jz4780_dma_slave_config(struct jz4780_dma_chan *jzchan, + const struct dma_slave_config *config) +{ + if ((config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES) + || (config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)) + return -EINVAL; + + /* Copy the reset of the slave configuration, it is used later. */ + memcpy(&jzchan->config, config, sizeof(jzchan->config)); + + return 0; +} + +static size_t jz4780_dma_desc_residue(struct jz4780_dma_chan *jzchan, + struct jz4780_dma_desc *desc, unsigned int next_sg) +{ + struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan); + unsigned int residue, count; + unsigned int i; + + residue = 0; + + for (i = next_sg; i < desc->count; i++) + residue += desc->desc[i].dtc << jzchan->transfer_shift; + + if (next_sg != 0) { + count = jz4780_dma_readl(jzdma, + JZ_DMA_REG_DTC(jzchan->id)); + residue += count << jzchan->transfer_shift; + } + + return residue; +} + +static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, struct dma_tx_state *txstate) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + struct virt_dma_desc *vdesc; + enum dma_status status; + unsigned long flags; + + status = dma_cookie_status(chan, cookie, txstate); + if ((status == DMA_COMPLETE) || (txstate == NULL)) + return status; + + spin_lock_irqsave(&jzchan->vchan.lock, flags); + + vdesc = vchan_find_desc(&jzchan->vchan, cookie); + if (vdesc) { + /* On the issued list, so hasn't been processed yet */ + txstate->residue = jz4780_dma_desc_residue(jzchan, + to_jz4780_dma_desc(vdesc), 0); + } else if (cookie == jzchan->desc->vdesc.tx.cookie) { + txstate->residue = jz4780_dma_desc_residue(jzchan, jzchan->desc, + (jzchan->curr_hwdesc + 1) % jzchan->desc->count); + } else + txstate->residue = 0; + + if (vdesc && jzchan->desc && vdesc == &jzchan->desc->vdesc + && jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT)) + status = DMA_ERROR; + + spin_unlock_irqrestore(&jzchan->vchan.lock, flags); + return status; +} + +static void jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma, + struct jz4780_dma_chan *jzchan) +{ + uint32_t dcs; + + spin_lock(&jzchan->vchan.lock); + + dcs = jz4780_dma_readl(jzdma, JZ_DMA_REG_DCS(jzchan->id)); + jz4780_dma_writel(jzdma, JZ_DMA_REG_DCS(jzchan->id), 0); + + if (dcs & JZ_DMA_DCS_AR) { + dev_warn(&jzchan->vchan.chan.dev->device, + "address error (DCS=0x%x)\n", dcs); + } + + if (dcs & JZ_DMA_DCS_HLT) { + dev_warn(&jzchan->vchan.chan.dev->device, + "channel halt (DCS=0x%x)\n", dcs); + } + + if (jzchan->desc) { + jzchan->desc->status = dcs; + + if ((dcs & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT)) == 0) { + if (jzchan->desc->type == DMA_CYCLIC) { + vchan_cyclic_callback(&jzchan->desc->vdesc); + } else { + vchan_cookie_complete(&jzchan->desc->vdesc); + jzchan->desc = NULL; + } + + jz4780_dma_begin(jzchan); + } + } else { + dev_err(&jzchan->vchan.chan.dev->device, + "channel IRQ with no active transfer\n"); + } + + spin_unlock(&jzchan->vchan.lock); +} + +static irqreturn_t jz4780_dma_irq_handler(int irq, void *data) +{ + struct jz4780_dma_dev *jzdma = data; + uint32_t pending, dmac; + int i; + + pending = jz4780_dma_readl(jzdma, JZ_DMA_REG_DIRQP); + + for (i = 0; i < JZ_DMA_NR_CHANNELS; i++) { + if (!(pending & (1<<i))) + continue; + + jz4780_dma_chan_irq(jzdma, &jzdma->chan[i]); + } + + /* Clear halt and address error status of all channels. */ + dmac = jz4780_dma_readl(jzdma, JZ_DMA_REG_DMAC); + dmac &= ~(JZ_DMA_DMAC_HLT | JZ_DMA_DMAC_AR); + jz4780_dma_writel(jzdma, JZ_DMA_REG_DMAC, dmac); + + /* Clear interrupt pending status. */ + jz4780_dma_writel(jzdma, JZ_DMA_REG_DIRQP, 0); + + return IRQ_HANDLED; +} + +static int jz4780_dma_alloc_chan_resources(struct dma_chan *chan) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + + jzchan->desc_pool = dma_pool_create(dev_name(&chan->dev->device), + chan->device->dev, + JZ_DMA_DESC_BLOCK_SIZE, + PAGE_SIZE, 0); + if (!jzchan->desc_pool) { + dev_err(&chan->dev->device, + "failed to allocate descriptor pool\n"); + return -ENOMEM; + } + + return 0; +} + +static void jz4780_dma_free_chan_resources(struct dma_chan *chan) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + + vchan_free_chan_resources(&jzchan->vchan); + dma_pool_destroy(jzchan->desc_pool); + jzchan->desc_pool = NULL; +} + +static bool jz4780_dma_filter_fn(struct dma_chan *chan, void *param) +{ + struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan); + struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan); + struct jz4780_dma_data *data = param; + + if (data->channel > -1) { + if (data->channel != jzchan->id) + return false; + } else if (jzdma->chan_reserved & BIT(jzchan->id)) { + return false; + } + + jzchan->transfer_type = data->transfer_type; + + return true; +} + +static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct jz4780_dma_dev *jzdma = ofdma->of_dma_data; + dma_cap_mask_t mask = jzdma->dma_device.cap_mask; + struct jz4780_dma_data data; + + if (dma_spec->args_count != 2) + return NULL; + + data.transfer_type = dma_spec->args[0]; + data.channel = dma_spec->args[1]; + + if (data.channel > -1) { + if (data.channel >= JZ_DMA_NR_CHANNELS) { + dev_err(jzdma->dma_device.dev, + "device requested non-existent channel %u\n", + data.channel); + return NULL; + } + + /* Can only select a channel marked as reserved. */ + if (!(jzdma->chan_reserved & BIT(data.channel))) { + dev_err(jzdma->dma_device.dev, + "device requested unreserved channel %u\n", + data.channel); + return NULL; + } + } + + return dma_request_channel(mask, jz4780_dma_filter_fn, &data); +} + +static int jz4780_dma_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct jz4780_dma_dev *jzdma; + struct jz4780_dma_chan *jzchan; + struct dma_device *dd; + struct resource *res; + int i, ret; + + jzdma = devm_kzalloc(dev, sizeof(*jzdma), GFP_KERNEL); + if (!jzdma) + return -ENOMEM; + + platform_set_drvdata(pdev, jzdma); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "failed to get I/O memory\n"); + return -EINVAL; + } + + jzdma->base = devm_ioremap_resource(dev, res); + if (IS_ERR(jzdma->base)) + return PTR_ERR(jzdma->base); + + jzdma->irq = platform_get_irq(pdev, 0); + if (jzdma->irq < 0) { + dev_err(dev, "failed to get IRQ: %d\n", ret); + return jzdma->irq; + } + + ret = devm_request_irq(dev, jzdma->irq, jz4780_dma_irq_handler, 0, + dev_name(dev), jzdma); + if (ret) { + dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq); + return -EINVAL; + } + + jzdma->clk = devm_clk_get(dev, NULL); + if (IS_ERR(jzdma->clk)) { + dev_err(dev, "failed to get clock\n"); + return PTR_ERR(jzdma->clk); + } + + clk_prepare_enable(jzdma->clk); + + /* Property is optional, if it doesn't exist the value will remain 0. */ + of_property_read_u32_index(dev->of_node, "ingenic,reserved-channels", + 0, &jzdma->chan_reserved); + + dd = &jzdma->dma_device; + + dma_cap_set(DMA_MEMCPY, dd->cap_mask); + dma_cap_set(DMA_SLAVE, dd->cap_mask); + dma_cap_set(DMA_CYCLIC, dd->cap_mask); + + dd->dev = dev; + dd->copy_align = 2; /* 2^2 = 4 byte alignment */ + dd->device_alloc_chan_resources = jz4780_dma_alloc_chan_resources; + dd->device_free_chan_resources = jz4780_dma_free_chan_resources; + dd->device_prep_slave_sg = jz4780_dma_prep_slave_sg; + dd->device_prep_dma_cyclic = jz4780_dma_prep_dma_cyclic; + dd->device_prep_dma_memcpy = jz4780_dma_prep_dma_memcpy; + dd->device_config = jz4780_dma_slave_config; + dd->device_terminate_all = jz4780_dma_terminate_all; + dd->device_tx_status = jz4780_dma_tx_status; + dd->device_issue_pending = jz4780_dma_issue_pending; + dd->src_addr_widths = JZ_DMA_BUSWIDTHS; + dd->dst_addr_widths = JZ_DMA_BUSWIDTHS; + dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + + + /* + * Enable DMA controller, mark all channels as not programmable. + * Also set the FMSC bit - it increases MSC performance, so it makes + * little sense not to enable it. + */ + jz4780_dma_writel(jzdma, JZ_DMA_REG_DMAC, + JZ_DMA_DMAC_DMAE | JZ_DMA_DMAC_FMSC); + jz4780_dma_writel(jzdma, JZ_DMA_REG_DMACP, 0); + + INIT_LIST_HEAD(&dd->channels); + + for (i = 0; i < JZ_DMA_NR_CHANNELS; i++) { + jzchan = &jzdma->chan[i]; + jzchan->id = i; + + vchan_init(&jzchan->vchan, dd); + jzchan->vchan.desc_free = jz4780_dma_desc_free; + } + + ret = dma_async_device_register(dd); + if (ret) { + dev_err(dev, "failed to register device\n"); + goto err_disable_clk; + } + + /* Register with OF DMA helpers. */ + ret = of_dma_controller_register(dev->of_node, jz4780_of_dma_xlate, + jzdma); + if (ret) { + dev_err(dev, "failed to register OF DMA controller\n"); + goto err_unregister_dev; + } + + dev_info(dev, "JZ4780 DMA controller initialised\n"); + return 0; + +err_unregister_dev: + dma_async_device_unregister(dd); + +err_disable_clk: + clk_disable_unprepare(jzdma->clk); + return ret; +} + +static int jz4780_dma_remove(struct platform_device *pdev) +{ + struct jz4780_dma_dev *jzdma = platform_get_drvdata(pdev); + + of_dma_controller_free(pdev->dev.of_node); + devm_free_irq(&pdev->dev, jzdma->irq, jzdma); + dma_async_device_unregister(&jzdma->dma_device); + return 0; +} + +static const struct of_device_id jz4780_dma_dt_match[] = { + { .compatible = "ingenic,jz4780-dma", .data = NULL }, + {}, +}; +MODULE_DEVICE_TABLE(of, jz4780_dma_dt_match); + +static struct platform_driver jz4780_dma_driver = { + .probe = jz4780_dma_probe, + .remove = jz4780_dma_remove, + .driver = { + .name = "jz4780-dma", + .of_match_table = of_match_ptr(jz4780_dma_dt_match), + }, +}; + +static int __init jz4780_dma_init(void) +{ + return platform_driver_register(&jz4780_dma_driver); +} +subsys_initcall(jz4780_dma_init); + +static void __exit jz4780_dma_exit(void) +{ + platform_driver_unregister(&jz4780_dma_driver); +} +module_exit(jz4780_dma_exit); + +MODULE_AUTHOR("Alex Smith <alex@alex-smith.me.uk>"); +MODULE_DESCRIPTION("Ingenic JZ4780 DMA controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index ac336a961dea..0e035a8cf401 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ @@ -355,20 +351,6 @@ struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) } EXPORT_SYMBOL(dma_find_channel); -/* - * net_dma_find_channel - find a channel for net_dma - * net_dma has alignment requirements - */ -struct dma_chan *net_dma_find_channel(void) -{ - struct dma_chan *chan = dma_find_channel(DMA_MEMCPY); - if (chan && !is_dma_copy_aligned(chan->device, 1, 1, 1)) - return NULL; - - return chan; -} -EXPORT_SYMBOL(net_dma_find_channel); - /** * dma_issue_pending_all - flush all pending operations across all channels */ diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index dcfe964cc8dc..36e02f0f645e 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -3,7 +3,7 @@ # config DW_DMAC_CORE - tristate "Synopsys DesignWare AHB DMA support" + tristate select DMA_ENGINE config DW_DMAC diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index a8ad05291b27..1022c2e1a2b0 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -230,7 +230,8 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first) /* ASSERT: channel is idle */ if (dma_readl(dw, CH_EN) & dwc->mask) { dev_err(chan2dev(&dwc->chan), - "BUG: Attempted to start non-idle channel\n"); + "%s: BUG: Attempted to start non-idle channel\n", + __func__); dwc_dump_chan_regs(dwc); /* The tasklet will hopefully advance the queue... */ @@ -814,11 +815,8 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, slave_sg_todev_fill_desc: desc = dwc_desc_get(dwc); - if (!desc) { - dev_err(chan2dev(chan), - "not enough descriptors available\n"); + if (!desc) goto err_desc_get; - } desc->lli.sar = mem; desc->lli.dar = reg; @@ -874,11 +872,8 @@ slave_sg_todev_fill_desc: slave_sg_fromdev_fill_desc: desc = dwc_desc_get(dwc); - if (!desc) { - dev_err(chan2dev(chan), - "not enough descriptors available\n"); + if (!desc) goto err_desc_get; - } desc->lli.sar = reg; desc->lli.dar = mem; @@ -922,6 +917,8 @@ slave_sg_fromdev_fill_desc: return &first->txd; err_desc_get: + dev_err(chan2dev(chan), + "not enough descriptors available. Direction %d\n", direction); dwc_desc_put(dwc, first); return NULL; } @@ -1261,7 +1258,8 @@ int dw_dma_cyclic_start(struct dma_chan *chan) /* Assert channel is idle */ if (dma_readl(dw, CH_EN) & dwc->mask) { dev_err(chan2dev(&dwc->chan), - "BUG: Attempted to start non-idle channel\n"); + "%s: BUG: Attempted to start non-idle channel\n", + __func__); dwc_dump_chan_regs(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return -EBUSY; diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 53dbd3b3384c..bf09db7ca9ee 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -812,7 +812,7 @@ static int edma_alloc_chan_resources(struct dma_chan *chan) LIST_HEAD(descs); a_ch_num = edma_alloc_channel(echan->ch_num, edma_callback, - chan, EVENTQ_DEFAULT); + echan, EVENTQ_DEFAULT); if (a_ch_num < 0) { ret = -ENODEV; diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c new file mode 100644 index 000000000000..4d9470f16552 --- /dev/null +++ b/drivers/dma/fsl_raid.c @@ -0,0 +1,904 @@ +/* + * drivers/dma/fsl_raid.c + * + * Freescale RAID Engine device driver + * + * Author: + * Harninder Rai <harninder.rai@freescale.com> + * Naveen Burmi <naveenburmi@freescale.com> + * + * Rewrite: + * Xuelin Shi <xuelin.shi@freescale.com> + * + * Copyright (c) 2010-2014 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * Theory of operation: + * + * General capabilities: + * RAID Engine (RE) block is capable of offloading XOR, memcpy and P/Q + * calculations required in RAID5 and RAID6 operations. RE driver + * registers with Linux's ASYNC layer as dma driver. RE hardware + * maintains strict ordering of the requests through chained + * command queueing. + * + * Data flow: + * Software RAID layer of Linux (MD layer) maintains RAID partitions, + * strips, stripes etc. It sends requests to the underlying ASYNC layer + * which further passes it to RE driver. ASYNC layer decides which request + * goes to which job ring of RE hardware. For every request processed by + * RAID Engine, driver gets an interrupt unless coalescing is set. The + * per job ring interrupt handler checks the status register for errors, + * clears the interrupt and leave the post interrupt processing to the irq + * thread. + */ +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/dma-mapping.h> +#include <linux/dmapool.h> +#include <linux/dmaengine.h> +#include <linux/io.h> +#include <linux/spinlock.h> +#include <linux/slab.h> + +#include "dmaengine.h" +#include "fsl_raid.h" + +#define FSL_RE_MAX_XOR_SRCS 16 +#define FSL_RE_MAX_PQ_SRCS 16 +#define FSL_RE_MIN_DESCS 256 +#define FSL_RE_MAX_DESCS (4 * FSL_RE_MIN_DESCS) +#define FSL_RE_FRAME_FORMAT 0x1 +#define FSL_RE_MAX_DATA_LEN (1024*1024) + +#define to_fsl_re_dma_desc(tx) container_of(tx, struct fsl_re_desc, async_tx) + +/* Add descriptors into per chan software queue - submit_q */ +static dma_cookie_t fsl_re_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct fsl_re_desc *desc; + struct fsl_re_chan *re_chan; + dma_cookie_t cookie; + unsigned long flags; + + desc = to_fsl_re_dma_desc(tx); + re_chan = container_of(tx->chan, struct fsl_re_chan, chan); + + spin_lock_irqsave(&re_chan->desc_lock, flags); + cookie = dma_cookie_assign(tx); + list_add_tail(&desc->node, &re_chan->submit_q); + spin_unlock_irqrestore(&re_chan->desc_lock, flags); + + return cookie; +} + +/* Copy descriptor from per chan software queue into hardware job ring */ +static void fsl_re_issue_pending(struct dma_chan *chan) +{ + struct fsl_re_chan *re_chan; + int avail; + struct fsl_re_desc *desc, *_desc; + unsigned long flags; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + + spin_lock_irqsave(&re_chan->desc_lock, flags); + avail = FSL_RE_SLOT_AVAIL( + in_be32(&re_chan->jrregs->inbring_slot_avail)); + + list_for_each_entry_safe(desc, _desc, &re_chan->submit_q, node) { + if (!avail) + break; + + list_move_tail(&desc->node, &re_chan->active_q); + + memcpy(&re_chan->inb_ring_virt_addr[re_chan->inb_count], + &desc->hwdesc, sizeof(struct fsl_re_hw_desc)); + + re_chan->inb_count = (re_chan->inb_count + 1) & + FSL_RE_RING_SIZE_MASK; + out_be32(&re_chan->jrregs->inbring_add_job, FSL_RE_ADD_JOB(1)); + avail--; + } + spin_unlock_irqrestore(&re_chan->desc_lock, flags); +} + +static void fsl_re_desc_done(struct fsl_re_desc *desc) +{ + dma_async_tx_callback callback; + void *callback_param; + + dma_cookie_complete(&desc->async_tx); + + callback = desc->async_tx.callback; + callback_param = desc->async_tx.callback_param; + if (callback) + callback(callback_param); + + dma_descriptor_unmap(&desc->async_tx); +} + +static void fsl_re_cleanup_descs(struct fsl_re_chan *re_chan) +{ + struct fsl_re_desc *desc, *_desc; + unsigned long flags; + + spin_lock_irqsave(&re_chan->desc_lock, flags); + list_for_each_entry_safe(desc, _desc, &re_chan->ack_q, node) { + if (async_tx_test_ack(&desc->async_tx)) + list_move_tail(&desc->node, &re_chan->free_q); + } + spin_unlock_irqrestore(&re_chan->desc_lock, flags); + + fsl_re_issue_pending(&re_chan->chan); +} + +static void fsl_re_dequeue(unsigned long data) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc, *_desc; + struct fsl_re_hw_desc *hwdesc; + unsigned long flags; + unsigned int count, oub_count; + int found; + + re_chan = dev_get_drvdata((struct device *)data); + + fsl_re_cleanup_descs(re_chan); + + spin_lock_irqsave(&re_chan->desc_lock, flags); + count = FSL_RE_SLOT_FULL(in_be32(&re_chan->jrregs->oubring_slot_full)); + while (count--) { + found = 0; + hwdesc = &re_chan->oub_ring_virt_addr[re_chan->oub_count]; + list_for_each_entry_safe(desc, _desc, &re_chan->active_q, + node) { + /* compare the hw dma addr to find the completed */ + if (desc->hwdesc.lbea32 == hwdesc->lbea32 && + desc->hwdesc.addr_low == hwdesc->addr_low) { + found = 1; + break; + } + } + + if (found) { + fsl_re_desc_done(desc); + list_move_tail(&desc->node, &re_chan->ack_q); + } else { + dev_err(re_chan->dev, + "found hwdesc not in sw queue, discard it\n"); + } + + oub_count = (re_chan->oub_count + 1) & FSL_RE_RING_SIZE_MASK; + re_chan->oub_count = oub_count; + + out_be32(&re_chan->jrregs->oubring_job_rmvd, + FSL_RE_RMVD_JOB(1)); + } + spin_unlock_irqrestore(&re_chan->desc_lock, flags); +} + +/* Per Job Ring interrupt handler */ +static irqreturn_t fsl_re_isr(int irq, void *data) +{ + struct fsl_re_chan *re_chan; + u32 irqstate, status; + + re_chan = dev_get_drvdata((struct device *)data); + + irqstate = in_be32(&re_chan->jrregs->jr_interrupt_status); + if (!irqstate) + return IRQ_NONE; + + /* + * There's no way in upper layer (read MD layer) to recover from + * error conditions except restart everything. In long term we + * need to do something more than just crashing + */ + if (irqstate & FSL_RE_ERROR) { + status = in_be32(&re_chan->jrregs->jr_status); + dev_err(re_chan->dev, "chan error irqstate: %x, status: %x\n", + irqstate, status); + } + + /* Clear interrupt */ + out_be32(&re_chan->jrregs->jr_interrupt_status, FSL_RE_CLR_INTR); + + tasklet_schedule(&re_chan->irqtask); + + return IRQ_HANDLED; +} + +static enum dma_status fsl_re_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + return dma_cookie_status(chan, cookie, txstate); +} + +static void fill_cfd_frame(struct fsl_re_cmpnd_frame *cf, u8 index, + size_t length, dma_addr_t addr, bool final) +{ + u32 efrl = length & FSL_RE_CF_LENGTH_MASK; + + efrl |= final << FSL_RE_CF_FINAL_SHIFT; + cf[index].efrl32 = efrl; + cf[index].addr_high = upper_32_bits(addr); + cf[index].addr_low = lower_32_bits(addr); +} + +static struct fsl_re_desc *fsl_re_init_desc(struct fsl_re_chan *re_chan, + struct fsl_re_desc *desc, + void *cf, dma_addr_t paddr) +{ + desc->re_chan = re_chan; + desc->async_tx.tx_submit = fsl_re_tx_submit; + dma_async_tx_descriptor_init(&desc->async_tx, &re_chan->chan); + INIT_LIST_HEAD(&desc->node); + + desc->hwdesc.fmt32 = FSL_RE_FRAME_FORMAT << FSL_RE_HWDESC_FMT_SHIFT; + desc->hwdesc.lbea32 = upper_32_bits(paddr); + desc->hwdesc.addr_low = lower_32_bits(paddr); + desc->cf_addr = cf; + desc->cf_paddr = paddr; + + desc->cdb_addr = (void *)(cf + FSL_RE_CF_DESC_SIZE); + desc->cdb_paddr = paddr + FSL_RE_CF_DESC_SIZE; + + return desc; +} + +static struct fsl_re_desc *fsl_re_chan_alloc_desc(struct fsl_re_chan *re_chan, + unsigned long flags) +{ + struct fsl_re_desc *desc = NULL; + void *cf; + dma_addr_t paddr; + unsigned long lock_flag; + + fsl_re_cleanup_descs(re_chan); + + spin_lock_irqsave(&re_chan->desc_lock, lock_flag); + if (!list_empty(&re_chan->free_q)) { + /* take one desc from free_q */ + desc = list_first_entry(&re_chan->free_q, + struct fsl_re_desc, node); + list_del(&desc->node); + + desc->async_tx.flags = flags; + } + spin_unlock_irqrestore(&re_chan->desc_lock, lock_flag); + + if (!desc) { + desc = kzalloc(sizeof(*desc), GFP_NOWAIT); + if (!desc) + return NULL; + + cf = dma_pool_alloc(re_chan->re_dev->cf_desc_pool, GFP_NOWAIT, + &paddr); + if (!cf) { + kfree(desc); + return NULL; + } + + desc = fsl_re_init_desc(re_chan, desc, cf, paddr); + desc->async_tx.flags = flags; + + spin_lock_irqsave(&re_chan->desc_lock, lock_flag); + re_chan->alloc_count++; + spin_unlock_irqrestore(&re_chan->desc_lock, lock_flag); + } + + return desc; +} + +static struct dma_async_tx_descriptor *fsl_re_prep_dma_genq( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, size_t len, + unsigned long flags) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc; + struct fsl_re_xor_cdb *xor; + struct fsl_re_cmpnd_frame *cf; + u32 cdb; + unsigned int i, j; + unsigned int save_src_cnt = src_cnt; + int cont_q = 0; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + if (len > FSL_RE_MAX_DATA_LEN) { + dev_err(re_chan->dev, "genq tx length %lu, max length %d\n", + len, FSL_RE_MAX_DATA_LEN); + return NULL; + } + + desc = fsl_re_chan_alloc_desc(re_chan, flags); + if (desc <= 0) + return NULL; + + if (scf && (flags & DMA_PREP_CONTINUE)) { + cont_q = 1; + src_cnt += 1; + } + + /* Filling xor CDB */ + cdb = FSL_RE_XOR_OPCODE << FSL_RE_CDB_OPCODE_SHIFT; + cdb |= (src_cnt - 1) << FSL_RE_CDB_NRCS_SHIFT; + cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT; + cdb |= FSL_RE_INTR_ON_ERROR << FSL_RE_CDB_ERROR_SHIFT; + cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT; + xor = desc->cdb_addr; + xor->cdb32 = cdb; + + if (scf) { + /* compute q = src0*coef0^src1*coef1^..., * is GF(8) mult */ + for (i = 0; i < save_src_cnt; i++) + xor->gfm[i] = scf[i]; + if (cont_q) + xor->gfm[i++] = 1; + } else { + /* compute P, that is XOR all srcs */ + for (i = 0; i < src_cnt; i++) + xor->gfm[i] = 1; + } + + /* Filling frame 0 of compound frame descriptor with CDB */ + cf = desc->cf_addr; + fill_cfd_frame(cf, 0, sizeof(*xor), desc->cdb_paddr, 0); + + /* Fill CFD's 1st frame with dest buffer */ + fill_cfd_frame(cf, 1, len, dest, 0); + + /* Fill CFD's rest of the frames with source buffers */ + for (i = 2, j = 0; j < save_src_cnt; i++, j++) + fill_cfd_frame(cf, i, len, src[j], 0); + + if (cont_q) + fill_cfd_frame(cf, i++, len, dest, 0); + + /* Setting the final bit in the last source buffer frame in CFD */ + cf[i - 1].efrl32 |= 1 << FSL_RE_CF_FINAL_SHIFT; + + return &desc->async_tx; +} + +/* + * Prep function for P parity calculation.In RAID Engine terminology, + * XOR calculation is called GenQ calculation done through GenQ command + */ +static struct dma_async_tx_descriptor *fsl_re_prep_dma_xor( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, + unsigned int src_cnt, size_t len, unsigned long flags) +{ + /* NULL let genq take all coef as 1 */ + return fsl_re_prep_dma_genq(chan, dest, src, src_cnt, NULL, len, flags); +} + +/* + * Prep function for P/Q parity calculation.In RAID Engine terminology, + * P/Q calculation is called GenQQ done through GenQQ command + */ +static struct dma_async_tx_descriptor *fsl_re_prep_dma_pq( + struct dma_chan *chan, dma_addr_t *dest, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, size_t len, + unsigned long flags) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc; + struct fsl_re_pq_cdb *pq; + struct fsl_re_cmpnd_frame *cf; + u32 cdb; + u8 *p; + int gfmq_len, i, j; + unsigned int save_src_cnt = src_cnt; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + if (len > FSL_RE_MAX_DATA_LEN) { + dev_err(re_chan->dev, "pq tx length is %lu, max length is %d\n", + len, FSL_RE_MAX_DATA_LEN); + return NULL; + } + + /* + * RE requires at least 2 sources, if given only one source, we pass the + * second source same as the first one. + * With only one source, generating P is meaningless, only generate Q. + */ + if (src_cnt == 1) { + struct dma_async_tx_descriptor *tx; + dma_addr_t dma_src[2]; + unsigned char coef[2]; + + dma_src[0] = *src; + coef[0] = *scf; + dma_src[1] = *src; + coef[1] = 0; + tx = fsl_re_prep_dma_genq(chan, dest[1], dma_src, 2, coef, len, + flags); + if (tx) + desc = to_fsl_re_dma_desc(tx); + + return tx; + } + + /* + * During RAID6 array creation, Linux's MD layer gets P and Q + * calculated separately in two steps. But our RAID Engine has + * the capability to calculate both P and Q with a single command + * Hence to merge well with MD layer, we need to provide a hook + * here and call re_jq_prep_dma_genq() function + */ + + if (flags & DMA_PREP_PQ_DISABLE_P) + return fsl_re_prep_dma_genq(chan, dest[1], src, src_cnt, + scf, len, flags); + + if (flags & DMA_PREP_CONTINUE) + src_cnt += 3; + + desc = fsl_re_chan_alloc_desc(re_chan, flags); + if (desc <= 0) + return NULL; + + /* Filling GenQQ CDB */ + cdb = FSL_RE_PQ_OPCODE << FSL_RE_CDB_OPCODE_SHIFT; + cdb |= (src_cnt - 1) << FSL_RE_CDB_NRCS_SHIFT; + cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT; + cdb |= FSL_RE_BUFFER_OUTPUT << FSL_RE_CDB_BUFFER_SHIFT; + cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT; + + pq = desc->cdb_addr; + pq->cdb32 = cdb; + + p = pq->gfm_q1; + /* Init gfm_q1[] */ + for (i = 0; i < src_cnt; i++) + p[i] = 1; + + /* Align gfm[] to 32bit */ + gfmq_len = ALIGN(src_cnt, 4); + + /* Init gfm_q2[] */ + p += gfmq_len; + for (i = 0; i < src_cnt; i++) + p[i] = scf[i]; + + /* Filling frame 0 of compound frame descriptor with CDB */ + cf = desc->cf_addr; + fill_cfd_frame(cf, 0, sizeof(struct fsl_re_pq_cdb), desc->cdb_paddr, 0); + + /* Fill CFD's 1st & 2nd frame with dest buffers */ + for (i = 1, j = 0; i < 3; i++, j++) + fill_cfd_frame(cf, i, len, dest[j], 0); + + /* Fill CFD's rest of the frames with source buffers */ + for (i = 3, j = 0; j < save_src_cnt; i++, j++) + fill_cfd_frame(cf, i, len, src[j], 0); + + /* PQ computation continuation */ + if (flags & DMA_PREP_CONTINUE) { + if (src_cnt - save_src_cnt == 3) { + p[save_src_cnt] = 0; + p[save_src_cnt + 1] = 0; + p[save_src_cnt + 2] = 1; + fill_cfd_frame(cf, i++, len, dest[0], 0); + fill_cfd_frame(cf, i++, len, dest[1], 0); + fill_cfd_frame(cf, i++, len, dest[1], 0); + } else { + dev_err(re_chan->dev, "PQ tx continuation error!\n"); + return NULL; + } + } + + /* Setting the final bit in the last source buffer frame in CFD */ + cf[i - 1].efrl32 |= 1 << FSL_RE_CF_FINAL_SHIFT; + + return &desc->async_tx; +} + +/* + * Prep function for memcpy. In RAID Engine, memcpy is done through MOVE + * command. Logic of this function will need to be modified once multipage + * support is added in Linux's MD/ASYNC Layer + */ +static struct dma_async_tx_descriptor *fsl_re_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc; + size_t length; + struct fsl_re_cmpnd_frame *cf; + struct fsl_re_move_cdb *move; + u32 cdb; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + + if (len > FSL_RE_MAX_DATA_LEN) { + dev_err(re_chan->dev, "cp tx length is %lu, max length is %d\n", + len, FSL_RE_MAX_DATA_LEN); + return NULL; + } + + desc = fsl_re_chan_alloc_desc(re_chan, flags); + if (desc <= 0) + return NULL; + + /* Filling move CDB */ + cdb = FSL_RE_MOVE_OPCODE << FSL_RE_CDB_OPCODE_SHIFT; + cdb |= FSL_RE_BLOCK_SIZE << FSL_RE_CDB_BLKSIZE_SHIFT; + cdb |= FSL_RE_INTR_ON_ERROR << FSL_RE_CDB_ERROR_SHIFT; + cdb |= FSL_RE_DATA_DEP << FSL_RE_CDB_DEPEND_SHIFT; + + move = desc->cdb_addr; + move->cdb32 = cdb; + + /* Filling frame 0 of CFD with move CDB */ + cf = desc->cf_addr; + fill_cfd_frame(cf, 0, sizeof(*move), desc->cdb_paddr, 0); + + length = min_t(size_t, len, FSL_RE_MAX_DATA_LEN); + + /* Fill CFD's 1st frame with dest buffer */ + fill_cfd_frame(cf, 1, length, dest, 0); + + /* Fill CFD's 2nd frame with src buffer */ + fill_cfd_frame(cf, 2, length, src, 1); + + return &desc->async_tx; +} + +static int fsl_re_alloc_chan_resources(struct dma_chan *chan) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc; + void *cf; + dma_addr_t paddr; + int i; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + for (i = 0; i < FSL_RE_MIN_DESCS; i++) { + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) + break; + + cf = dma_pool_alloc(re_chan->re_dev->cf_desc_pool, GFP_KERNEL, + &paddr); + if (!cf) { + kfree(desc); + break; + } + + INIT_LIST_HEAD(&desc->node); + fsl_re_init_desc(re_chan, desc, cf, paddr); + + list_add_tail(&desc->node, &re_chan->free_q); + re_chan->alloc_count++; + } + return re_chan->alloc_count; +} + +static void fsl_re_free_chan_resources(struct dma_chan *chan) +{ + struct fsl_re_chan *re_chan; + struct fsl_re_desc *desc; + + re_chan = container_of(chan, struct fsl_re_chan, chan); + while (re_chan->alloc_count--) { + desc = list_first_entry(&re_chan->free_q, + struct fsl_re_desc, + node); + + list_del(&desc->node); + dma_pool_free(re_chan->re_dev->cf_desc_pool, desc->cf_addr, + desc->cf_paddr); + kfree(desc); + } + + if (!list_empty(&re_chan->free_q)) + dev_err(re_chan->dev, "chan resource cannot be cleaned!\n"); +} + +static int fsl_re_chan_probe(struct platform_device *ofdev, + struct device_node *np, u8 q, u32 off) +{ + struct device *dev, *chandev; + struct fsl_re_drv_private *re_priv; + struct fsl_re_chan *chan; + struct dma_device *dma_dev; + u32 ptr; + u32 status; + int ret = 0, rc; + struct platform_device *chan_ofdev; + + dev = &ofdev->dev; + re_priv = dev_get_drvdata(dev); + dma_dev = &re_priv->dma_dev; + + chan = devm_kzalloc(dev, sizeof(*chan), GFP_KERNEL); + if (!chan) + return -ENOMEM; + + /* create platform device for chan node */ + chan_ofdev = of_platform_device_create(np, NULL, dev); + if (!chan_ofdev) { + dev_err(dev, "Not able to create ofdev for jr %d\n", q); + ret = -EINVAL; + goto err_free; + } + + /* read reg property from dts */ + rc = of_property_read_u32(np, "reg", &ptr); + if (rc) { + dev_err(dev, "Reg property not found in jr %d\n", q); + ret = -ENODEV; + goto err_free; + } + + chan->jrregs = (struct fsl_re_chan_cfg *)((u8 *)re_priv->re_regs + + off + ptr); + + /* read irq property from dts */ + chan->irq = irq_of_parse_and_map(np, 0); + if (chan->irq == NO_IRQ) { + dev_err(dev, "No IRQ defined for JR %d\n", q); + ret = -ENODEV; + goto err_free; + } + + snprintf(chan->name, sizeof(chan->name), "re_jr%02d", q); + + chandev = &chan_ofdev->dev; + tasklet_init(&chan->irqtask, fsl_re_dequeue, (unsigned long)chandev); + + ret = request_irq(chan->irq, fsl_re_isr, 0, chan->name, chandev); + if (ret) { + dev_err(dev, "Unable to register interrupt for JR %d\n", q); + ret = -EINVAL; + goto err_free; + } + + re_priv->re_jrs[q] = chan; + chan->chan.device = dma_dev; + chan->chan.private = chan; + chan->dev = chandev; + chan->re_dev = re_priv; + + spin_lock_init(&chan->desc_lock); + INIT_LIST_HEAD(&chan->ack_q); + INIT_LIST_HEAD(&chan->active_q); + INIT_LIST_HEAD(&chan->submit_q); + INIT_LIST_HEAD(&chan->free_q); + + chan->inb_ring_virt_addr = dma_pool_alloc(chan->re_dev->hw_desc_pool, + GFP_KERNEL, &chan->inb_phys_addr); + if (!chan->inb_ring_virt_addr) { + dev_err(dev, "No dma memory for inb_ring_virt_addr\n"); + ret = -ENOMEM; + goto err_free; + } + + chan->oub_ring_virt_addr = dma_pool_alloc(chan->re_dev->hw_desc_pool, + GFP_KERNEL, &chan->oub_phys_addr); + if (!chan->oub_ring_virt_addr) { + dev_err(dev, "No dma memory for oub_ring_virt_addr\n"); + ret = -ENOMEM; + goto err_free_1; + } + + /* Program the Inbound/Outbound ring base addresses and size */ + out_be32(&chan->jrregs->inbring_base_h, + chan->inb_phys_addr & FSL_RE_ADDR_BIT_MASK); + out_be32(&chan->jrregs->oubring_base_h, + chan->oub_phys_addr & FSL_RE_ADDR_BIT_MASK); + out_be32(&chan->jrregs->inbring_base_l, + chan->inb_phys_addr >> FSL_RE_ADDR_BIT_SHIFT); + out_be32(&chan->jrregs->oubring_base_l, + chan->oub_phys_addr >> FSL_RE_ADDR_BIT_SHIFT); + out_be32(&chan->jrregs->inbring_size, + FSL_RE_RING_SIZE << FSL_RE_RING_SIZE_SHIFT); + out_be32(&chan->jrregs->oubring_size, + FSL_RE_RING_SIZE << FSL_RE_RING_SIZE_SHIFT); + + /* Read LIODN value from u-boot */ + status = in_be32(&chan->jrregs->jr_config_1) & FSL_RE_REG_LIODN_MASK; + + /* Program the CFG reg */ + out_be32(&chan->jrregs->jr_config_1, + FSL_RE_CFG1_CBSI | FSL_RE_CFG1_CBS0 | status); + + dev_set_drvdata(chandev, chan); + + /* Enable RE/CHAN */ + out_be32(&chan->jrregs->jr_command, FSL_RE_ENABLE); + + return 0; + +err_free_1: + dma_pool_free(chan->re_dev->hw_desc_pool, chan->inb_ring_virt_addr, + chan->inb_phys_addr); +err_free: + return ret; +} + +/* Probe function for RAID Engine */ +static int fsl_re_probe(struct platform_device *ofdev) +{ + struct fsl_re_drv_private *re_priv; + struct device_node *np; + struct device_node *child; + u32 off; + u8 ridx = 0; + struct dma_device *dma_dev; + struct resource *res; + int rc; + struct device *dev = &ofdev->dev; + + re_priv = devm_kzalloc(dev, sizeof(*re_priv), GFP_KERNEL); + if (!re_priv) + return -ENOMEM; + + res = platform_get_resource(ofdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; + + /* IOMAP the entire RAID Engine region */ + re_priv->re_regs = devm_ioremap(dev, res->start, resource_size(res)); + if (!re_priv->re_regs) + return -EBUSY; + + /* Program the RE mode */ + out_be32(&re_priv->re_regs->global_config, FSL_RE_NON_DPAA_MODE); + + /* Program Galois Field polynomial */ + out_be32(&re_priv->re_regs->galois_field_config, FSL_RE_GFM_POLY); + + dev_info(dev, "version %x, mode %x, gfp %x\n", + in_be32(&re_priv->re_regs->re_version_id), + in_be32(&re_priv->re_regs->global_config), + in_be32(&re_priv->re_regs->galois_field_config)); + + dma_dev = &re_priv->dma_dev; + dma_dev->dev = dev; + INIT_LIST_HEAD(&dma_dev->channels); + dma_set_mask(dev, DMA_BIT_MASK(40)); + + dma_dev->device_alloc_chan_resources = fsl_re_alloc_chan_resources; + dma_dev->device_tx_status = fsl_re_tx_status; + dma_dev->device_issue_pending = fsl_re_issue_pending; + + dma_dev->max_xor = FSL_RE_MAX_XOR_SRCS; + dma_dev->device_prep_dma_xor = fsl_re_prep_dma_xor; + dma_cap_set(DMA_XOR, dma_dev->cap_mask); + + dma_dev->max_pq = FSL_RE_MAX_PQ_SRCS; + dma_dev->device_prep_dma_pq = fsl_re_prep_dma_pq; + dma_cap_set(DMA_PQ, dma_dev->cap_mask); + + dma_dev->device_prep_dma_memcpy = fsl_re_prep_dma_memcpy; + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + + dma_dev->device_free_chan_resources = fsl_re_free_chan_resources; + + re_priv->total_chans = 0; + + re_priv->cf_desc_pool = dmam_pool_create("fsl_re_cf_desc_pool", dev, + FSL_RE_CF_CDB_SIZE, + FSL_RE_CF_CDB_ALIGN, 0); + + if (!re_priv->cf_desc_pool) { + dev_err(dev, "No memory for fsl re_cf desc pool\n"); + return -ENOMEM; + } + + re_priv->hw_desc_pool = dmam_pool_create("fsl_re_hw_desc_pool", dev, + sizeof(struct fsl_re_hw_desc) * FSL_RE_RING_SIZE, + FSL_RE_FRAME_ALIGN, 0); + if (!re_priv->hw_desc_pool) { + dev_err(dev, "No memory for fsl re_hw desc pool\n"); + return -ENOMEM; + } + + dev_set_drvdata(dev, re_priv); + + /* Parse Device tree to find out the total number of JQs present */ + for_each_compatible_node(np, NULL, "fsl,raideng-v1.0-job-queue") { + rc = of_property_read_u32(np, "reg", &off); + if (rc) { + dev_err(dev, "Reg property not found in JQ node\n"); + return -ENODEV; + } + /* Find out the Job Rings present under each JQ */ + for_each_child_of_node(np, child) { + rc = of_device_is_compatible(child, + "fsl,raideng-v1.0-job-ring"); + if (rc) { + fsl_re_chan_probe(ofdev, child, ridx++, off); + re_priv->total_chans++; + } + } + } + + dma_async_device_register(dma_dev); + + return 0; +} + +static void fsl_re_remove_chan(struct fsl_re_chan *chan) +{ + dma_pool_free(chan->re_dev->hw_desc_pool, chan->inb_ring_virt_addr, + chan->inb_phys_addr); + + dma_pool_free(chan->re_dev->hw_desc_pool, chan->oub_ring_virt_addr, + chan->oub_phys_addr); +} + +static int fsl_re_remove(struct platform_device *ofdev) +{ + struct fsl_re_drv_private *re_priv; + struct device *dev; + int i; + + dev = &ofdev->dev; + re_priv = dev_get_drvdata(dev); + + /* Cleanup chan related memory areas */ + for (i = 0; i < re_priv->total_chans; i++) + fsl_re_remove_chan(re_priv->re_jrs[i]); + + /* Unregister the driver */ + dma_async_device_unregister(&re_priv->dma_dev); + + return 0; +} + +static struct of_device_id fsl_re_ids[] = { + { .compatible = "fsl,raideng-v1.0", }, + {} +}; + +static struct platform_driver fsl_re_driver = { + .driver = { + .name = "fsl-raideng", + .owner = THIS_MODULE, + .of_match_table = fsl_re_ids, + }, + .probe = fsl_re_probe, + .remove = fsl_re_remove, +}; + +module_platform_driver(fsl_re_driver); + +MODULE_AUTHOR("Harninder Rai <harninder.rai@freescale.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Freescale RAID Engine Device Driver"); diff --git a/drivers/dma/fsl_raid.h b/drivers/dma/fsl_raid.h new file mode 100644 index 000000000000..69d743c04973 --- /dev/null +++ b/drivers/dma/fsl_raid.h @@ -0,0 +1,306 @@ +/* + * drivers/dma/fsl_raid.h + * + * Freescale RAID Engine device driver + * + * Author: + * Harninder Rai <harninder.rai@freescale.com> + * Naveen Burmi <naveenburmi@freescale.com> + * + * Rewrite: + * Xuelin Shi <xuelin.shi@freescale.com> + + * Copyright (c) 2010-2012 Freescale Semiconductor, Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#define FSL_RE_MAX_CHANS 4 +#define FSL_RE_DPAA_MODE BIT(30) +#define FSL_RE_NON_DPAA_MODE BIT(31) +#define FSL_RE_GFM_POLY 0x1d000000 +#define FSL_RE_ADD_JOB(x) ((x) << 16) +#define FSL_RE_RMVD_JOB(x) ((x) << 16) +#define FSL_RE_CFG1_CBSI 0x08000000 +#define FSL_RE_CFG1_CBS0 0x00080000 +#define FSL_RE_SLOT_FULL_SHIFT 8 +#define FSL_RE_SLOT_FULL(x) ((x) >> FSL_RE_SLOT_FULL_SHIFT) +#define FSL_RE_SLOT_AVAIL_SHIFT 8 +#define FSL_RE_SLOT_AVAIL(x) ((x) >> FSL_RE_SLOT_AVAIL_SHIFT) +#define FSL_RE_PQ_OPCODE 0x1B +#define FSL_RE_XOR_OPCODE 0x1A +#define FSL_RE_MOVE_OPCODE 0x8 +#define FSL_RE_FRAME_ALIGN 16 +#define FSL_RE_BLOCK_SIZE 0x3 /* 4096 bytes */ +#define FSL_RE_CACHEABLE_IO 0x0 +#define FSL_RE_BUFFER_OUTPUT 0x0 +#define FSL_RE_INTR_ON_ERROR 0x1 +#define FSL_RE_DATA_DEP 0x1 +#define FSL_RE_ENABLE_DPI 0x0 +#define FSL_RE_RING_SIZE 0x400 +#define FSL_RE_RING_SIZE_MASK (FSL_RE_RING_SIZE - 1) +#define FSL_RE_RING_SIZE_SHIFT 8 +#define FSL_RE_ADDR_BIT_SHIFT 4 +#define FSL_RE_ADDR_BIT_MASK (BIT(FSL_RE_ADDR_BIT_SHIFT) - 1) +#define FSL_RE_ERROR 0x40000000 +#define FSL_RE_INTR 0x80000000 +#define FSL_RE_CLR_INTR 0x80000000 +#define FSL_RE_PAUSE 0x80000000 +#define FSL_RE_ENABLE 0x80000000 +#define FSL_RE_REG_LIODN_MASK 0x00000FFF + +#define FSL_RE_CDB_OPCODE_MASK 0xF8000000 +#define FSL_RE_CDB_OPCODE_SHIFT 27 +#define FSL_RE_CDB_EXCLEN_MASK 0x03000000 +#define FSL_RE_CDB_EXCLEN_SHIFT 24 +#define FSL_RE_CDB_EXCLQ1_MASK 0x00F00000 +#define FSL_RE_CDB_EXCLQ1_SHIFT 20 +#define FSL_RE_CDB_EXCLQ2_MASK 0x000F0000 +#define FSL_RE_CDB_EXCLQ2_SHIFT 16 +#define FSL_RE_CDB_BLKSIZE_MASK 0x0000C000 +#define FSL_RE_CDB_BLKSIZE_SHIFT 14 +#define FSL_RE_CDB_CACHE_MASK 0x00003000 +#define FSL_RE_CDB_CACHE_SHIFT 12 +#define FSL_RE_CDB_BUFFER_MASK 0x00000800 +#define FSL_RE_CDB_BUFFER_SHIFT 11 +#define FSL_RE_CDB_ERROR_MASK 0x00000400 +#define FSL_RE_CDB_ERROR_SHIFT 10 +#define FSL_RE_CDB_NRCS_MASK 0x0000003C +#define FSL_RE_CDB_NRCS_SHIFT 6 +#define FSL_RE_CDB_DEPEND_MASK 0x00000008 +#define FSL_RE_CDB_DEPEND_SHIFT 3 +#define FSL_RE_CDB_DPI_MASK 0x00000004 +#define FSL_RE_CDB_DPI_SHIFT 2 + +/* + * the largest cf block is 19*sizeof(struct cmpnd_frame), which is 304 bytes. + * here 19 = 1(cdb)+2(dest)+16(src), align to 64bytes, that is 320 bytes. + * the largest cdb block: struct pq_cdb which is 180 bytes, adding to cf block + * 320+180=500, align to 64bytes, that is 512 bytes. + */ +#define FSL_RE_CF_DESC_SIZE 320 +#define FSL_RE_CF_CDB_SIZE 512 +#define FSL_RE_CF_CDB_ALIGN 64 + +struct fsl_re_ctrl { + /* General Configuration Registers */ + __be32 global_config; /* Global Configuration Register */ + u8 rsvd1[4]; + __be32 galois_field_config; /* Galois Field Configuration Register */ + u8 rsvd2[4]; + __be32 jq_wrr_config; /* WRR Configuration register */ + u8 rsvd3[4]; + __be32 crc_config; /* CRC Configuration register */ + u8 rsvd4[228]; + __be32 system_reset; /* System Reset Register */ + u8 rsvd5[252]; + __be32 global_status; /* Global Status Register */ + u8 rsvd6[832]; + __be32 re_liodn_base; /* LIODN Base Register */ + u8 rsvd7[1712]; + __be32 re_version_id; /* Version ID register of RE */ + __be32 re_version_id_2; /* Version ID 2 register of RE */ + u8 rsvd8[512]; + __be32 host_config; /* Host I/F Configuration Register */ +}; + +struct fsl_re_chan_cfg { + /* Registers for JR interface */ + __be32 jr_config_0; /* Job Queue Configuration 0 Register */ + __be32 jr_config_1; /* Job Queue Configuration 1 Register */ + __be32 jr_interrupt_status; /* Job Queue Interrupt Status Register */ + u8 rsvd1[4]; + __be32 jr_command; /* Job Queue Command Register */ + u8 rsvd2[4]; + __be32 jr_status; /* Job Queue Status Register */ + u8 rsvd3[228]; + + /* Input Ring */ + __be32 inbring_base_h; /* Inbound Ring Base Address Register - High */ + __be32 inbring_base_l; /* Inbound Ring Base Address Register - Low */ + __be32 inbring_size; /* Inbound Ring Size Register */ + u8 rsvd4[4]; + __be32 inbring_slot_avail; /* Inbound Ring Slot Available Register */ + u8 rsvd5[4]; + __be32 inbring_add_job; /* Inbound Ring Add Job Register */ + u8 rsvd6[4]; + __be32 inbring_cnsmr_indx; /* Inbound Ring Consumer Index Register */ + u8 rsvd7[220]; + + /* Output Ring */ + __be32 oubring_base_h; /* Outbound Ring Base Address Register - High */ + __be32 oubring_base_l; /* Outbound Ring Base Address Register - Low */ + __be32 oubring_size; /* Outbound Ring Size Register */ + u8 rsvd8[4]; + __be32 oubring_job_rmvd; /* Outbound Ring Job Removed Register */ + u8 rsvd9[4]; + __be32 oubring_slot_full; /* Outbound Ring Slot Full Register */ + u8 rsvd10[4]; + __be32 oubring_prdcr_indx; /* Outbound Ring Producer Index */ +}; + +/* + * Command Descriptor Block (CDB) for unicast move command. + * In RAID Engine terms, memcpy is done through move command + */ +struct fsl_re_move_cdb { + __be32 cdb32; +}; + +/* Data protection/integrity related fields */ +#define FSL_RE_DPI_APPS_MASK 0xC0000000 +#define FSL_RE_DPI_APPS_SHIFT 30 +#define FSL_RE_DPI_REF_MASK 0x30000000 +#define FSL_RE_DPI_REF_SHIFT 28 +#define FSL_RE_DPI_GUARD_MASK 0x0C000000 +#define FSL_RE_DPI_GUARD_SHIFT 26 +#define FSL_RE_DPI_ATTR_MASK 0x03000000 +#define FSL_RE_DPI_ATTR_SHIFT 24 +#define FSL_RE_DPI_META_MASK 0x0000FFFF + +struct fsl_re_dpi { + __be32 dpi32; + __be32 ref; +}; + +/* + * CDB for GenQ command. In RAID Engine terminology, XOR is + * done through this command + */ +struct fsl_re_xor_cdb { + __be32 cdb32; + u8 gfm[16]; + struct fsl_re_dpi dpi_dest_spec; + struct fsl_re_dpi dpi_src_spec[16]; +}; + +/* CDB for no-op command */ +struct fsl_re_noop_cdb { + __be32 cdb32; +}; + +/* + * CDB for GenQQ command. In RAID Engine terminology, P/Q is + * done through this command + */ +struct fsl_re_pq_cdb { + __be32 cdb32; + u8 gfm_q1[16]; + u8 gfm_q2[16]; + struct fsl_re_dpi dpi_dest_spec[2]; + struct fsl_re_dpi dpi_src_spec[16]; +}; + +/* Compound frame */ +#define FSL_RE_CF_ADDR_HIGH_MASK 0x000000FF +#define FSL_RE_CF_EXT_MASK 0x80000000 +#define FSL_RE_CF_EXT_SHIFT 31 +#define FSL_RE_CF_FINAL_MASK 0x40000000 +#define FSL_RE_CF_FINAL_SHIFT 30 +#define FSL_RE_CF_LENGTH_MASK 0x000FFFFF +#define FSL_RE_CF_BPID_MASK 0x00FF0000 +#define FSL_RE_CF_BPID_SHIFT 16 +#define FSL_RE_CF_OFFSET_MASK 0x00001FFF + +struct fsl_re_cmpnd_frame { + __be32 addr_high; + __be32 addr_low; + __be32 efrl32; + __be32 rbro32; +}; + +/* Frame descriptor */ +#define FSL_RE_HWDESC_LIODN_MASK 0x3F000000 +#define FSL_RE_HWDESC_LIODN_SHIFT 24 +#define FSL_RE_HWDESC_BPID_MASK 0x00FF0000 +#define FSL_RE_HWDESC_BPID_SHIFT 16 +#define FSL_RE_HWDESC_ELIODN_MASK 0x0000F000 +#define FSL_RE_HWDESC_ELIODN_SHIFT 12 +#define FSL_RE_HWDESC_FMT_SHIFT 29 +#define FSL_RE_HWDESC_FMT_MASK (0x3 << FSL_RE_HWDESC_FMT_SHIFT) + +struct fsl_re_hw_desc { + __be32 lbea32; + __be32 addr_low; + __be32 fmt32; + __be32 status; +}; + +/* Raid Engine device private data */ +struct fsl_re_drv_private { + u8 total_chans; + struct dma_device dma_dev; + struct fsl_re_ctrl *re_regs; + struct fsl_re_chan *re_jrs[FSL_RE_MAX_CHANS]; + struct dma_pool *cf_desc_pool; + struct dma_pool *hw_desc_pool; +}; + +/* Per job ring data structure */ +struct fsl_re_chan { + char name[16]; + spinlock_t desc_lock; /* queue lock */ + struct list_head ack_q; /* wait to acked queue */ + struct list_head active_q; /* already issued on hw, not completed */ + struct list_head submit_q; + struct list_head free_q; /* alloc available queue */ + struct device *dev; + struct fsl_re_drv_private *re_dev; + struct dma_chan chan; + struct fsl_re_chan_cfg *jrregs; + int irq; + struct tasklet_struct irqtask; + u32 alloc_count; + + /* hw descriptor ring for inbound queue*/ + dma_addr_t inb_phys_addr; + struct fsl_re_hw_desc *inb_ring_virt_addr; + u32 inb_count; + + /* hw descriptor ring for outbound queue */ + dma_addr_t oub_phys_addr; + struct fsl_re_hw_desc *oub_ring_virt_addr; + u32 oub_count; +}; + +/* Async transaction descriptor */ +struct fsl_re_desc { + struct dma_async_tx_descriptor async_tx; + struct list_head node; + struct fsl_re_hw_desc hwdesc; + struct fsl_re_chan *re_chan; + + /* hwdesc will point to cf_addr */ + void *cf_addr; + dma_addr_t cf_paddr; + + void *cdb_addr; + dma_addr_t cdb_paddr; + int status; +}; diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c index ed045a9ad634..9ca56830cc63 100644 --- a/drivers/dma/img-mdc-dma.c +++ b/drivers/dma/img-mdc-dma.c @@ -689,11 +689,6 @@ static int mdc_slave_config(struct dma_chan *chan, return 0; } -static int mdc_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void mdc_free_chan_resources(struct dma_chan *chan) { struct mdc_chan *mchan = to_mdc_chan(chan); @@ -910,7 +905,6 @@ static int mdc_dma_probe(struct platform_device *pdev) mdma->dma_dev.device_prep_slave_sg = mdc_prep_slave_sg; mdma->dma_dev.device_prep_dma_cyclic = mdc_prep_dma_cyclic; mdma->dma_dev.device_prep_dma_memcpy = mdc_prep_dma_memcpy; - mdma->dma_dev.device_alloc_chan_resources = mdc_alloc_chan_resources; mdma->dma_dev.device_free_chan_resources = mdc_free_chan_resources; mdma->dma_dev.device_tx_status = mdc_tx_status; mdma->dma_dev.device_issue_pending = mdc_issue_pending; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 66a0efb9651d..62bbd79338e0 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1260,6 +1260,7 @@ static void sdma_issue_pending(struct dma_chan *chan) #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1 34 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V2 38 +#define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3 41 static void sdma_add_scripts(struct sdma_engine *sdma, const struct sdma_script_start_addrs *addr) @@ -1306,6 +1307,9 @@ static void sdma_load_firmware(const struct firmware *fw, void *context) case 2: sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V2; break; + case 3: + sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3; + break; default: dev_err(sdma->dev, "unknown firmware version\n"); goto err_firmware; diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 3b55bb8d969a..ea1e107ae884 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * * The full GNU General Public License is included in this distribution in * the file called "COPYING". * diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 940c1502a8b5..ee0aa9f4ccfa 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * * The full GNU General Public License is included in this distribution in * the file called "COPYING". * diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index d63f68b1aa35..30f5c7eede16 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index 695483e6be32..69c7dfcad023 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * * The full GNU General Public License is included in this distribution in * the file called "COPYING". * diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h index 470292767e68..bf24ebe874b0 100644 --- a/drivers/dma/ioat/dma_v2.h +++ b/drivers/dma/ioat/dma_v2.h @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 194ec20c9408..64790a45ef5d 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -15,10 +15,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * * The full GNU General Public License is included in this distribution in * the file called "COPYING". * diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h index 02177ecf09f8..a3e731edce57 100644 --- a/drivers/dma/ioat/hw.h +++ b/drivers/dma/ioat/hw.h @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c index 5501eb072d69..76f0dc688a19 100644 --- a/drivers/dma/ioat/pci.c +++ b/drivers/dma/ioat/pci.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * * The full GNU General Public License is included in this distribution in * the file called "COPYING". * diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h index 2f1cfa0f1f47..909352f74c89 100644 --- a/drivers/dma/ioat/registers.h +++ b/drivers/dma/ioat/registers.h @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c index 263d9f6a207e..998826854fdd 100644 --- a/drivers/dma/iop-adma.c +++ b/drivers/dma/iop-adma.c @@ -11,10 +11,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - * */ /* diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c index 6f7f43529ccb..647e362f01fd 100644 --- a/drivers/dma/k3dma.c +++ b/drivers/dma/k3dma.c @@ -313,11 +313,6 @@ static void k3_dma_tasklet(unsigned long arg) } } -static int k3_dma_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void k3_dma_free_chan_resources(struct dma_chan *chan) { struct k3_dma_chan *c = to_k3_chan(chan); @@ -654,7 +649,7 @@ static void k3_dma_free_desc(struct virt_dma_desc *vd) kfree(ds); } -static struct of_device_id k3_pdma_dt_ids[] = { +static const struct of_device_id k3_pdma_dt_ids[] = { { .compatible = "hisilicon,k3-dma-1.0", }, {} }; @@ -728,7 +723,6 @@ static int k3_dma_probe(struct platform_device *op) dma_cap_set(DMA_SLAVE, d->slave.cap_mask); dma_cap_set(DMA_MEMCPY, d->slave.cap_mask); d->slave.dev = &op->dev; - d->slave.device_alloc_chan_resources = k3_dma_alloc_chan_resources; d->slave.device_free_chan_resources = k3_dma_free_chan_resources; d->slave.device_tx_status = k3_dma_tx_status; d->slave.device_prep_dma_memcpy = k3_dma_prep_memcpy; diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index eb410044e1af..462a0229a743 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -973,7 +973,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq) return 0; } -static struct of_device_id mmp_pdma_dt_ids[] = { +static const struct of_device_id mmp_pdma_dt_ids[] = { { .compatible = "marvell,pdma-1.0", }, {} }; diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c index b6f4e1fc9c78..449e785def17 100644 --- a/drivers/dma/mmp_tdma.c +++ b/drivers/dma/mmp_tdma.c @@ -613,7 +613,7 @@ struct dma_chan *mmp_tdma_xlate(struct of_phandle_args *dma_spec, return dma_request_channel(mask, mmp_tdma_filter_fn, ¶m); } -static struct of_device_id mmp_tdma_dt_ids[] = { +static const struct of_device_id mmp_tdma_dt_ids[] = { { .compatible = "marvell,adma-1.0", .data = (void *)MMP_AUD_TDMA}, { .compatible = "marvell,pxa910-squ", .data = (void *)PXA910_SQU}, {} diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c index 57d2457545f3..e6281e7aa46e 100644 --- a/drivers/dma/mpc512x_dma.c +++ b/drivers/dma/mpc512x_dma.c @@ -21,10 +21,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ @@ -1072,7 +1068,7 @@ static int mpc_dma_remove(struct platform_device *op) return 0; } -static struct of_device_id mpc_dma_match[] = { +static const struct of_device_id mpc_dma_match[] = { { .compatible = "fsl,mpc5121-dma", }, { .compatible = "fsl,mpc8308-dma", }, {}, diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index b03e8137b918..1c56001df676 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -10,10 +10,6 @@ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ #include <linux/init.h> @@ -1249,7 +1245,7 @@ static int mv_xor_remove(struct platform_device *pdev) } #ifdef CONFIG_OF -static struct of_device_id mv_xor_dt_ids[] = { +static const struct of_device_id mv_xor_dt_ids[] = { { .compatible = "marvell,orion-xor", }, {}, }; diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h index 78edc7e44569..91958dba39a2 100644 --- a/drivers/dma/mv_xor.h +++ b/drivers/dma/mv_xor.h @@ -9,10 +9,6 @@ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software Foundation, - * Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ #ifndef MV_XOR_H diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index 35c143cb88da..b859792dde95 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -949,6 +949,7 @@ err_free_res: err_disable_pdev: pci_disable_device(pdev); err_free_mem: + kfree(pd); return err; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 0e1f56772855..a7d9d3029b14 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -556,7 +556,7 @@ static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[], buf[0] = CMD_DMAADDH; buf[0] |= (da << 1); - *((u16 *)&buf[1]) = val; + *((__le16 *)&buf[1]) = cpu_to_le16(val); PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n", da == 1 ? "DA" : "SA", val); @@ -710,7 +710,7 @@ static inline u32 _emit_MOV(unsigned dry_run, u8 buf[], buf[0] = CMD_DMAMOV; buf[1] = dst; - *((u32 *)&buf[2]) = val; + *((__le32 *)&buf[2]) = cpu_to_le32(val); PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n", dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val); @@ -888,7 +888,7 @@ static inline u32 _emit_GO(unsigned dry_run, u8 buf[], buf[1] = chan & 0x7; - *((u32 *)&buf[2]) = addr; + *((__le32 *)&buf[2]) = cpu_to_le32(addr); return SZ_DMAGO; } @@ -928,7 +928,7 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd, } writel(val, regs + DBGINST0); - val = *((u32 *)&insn[2]); + val = le32_to_cpu(*((__le32 *)&insn[2])); writel(val, regs + DBGINST1); /* If timed out due to halted state-machine */ @@ -2162,7 +2162,7 @@ static int pl330_terminate_all(struct dma_chan *chan) * DMA transfer again. This pause feature was implemented to * allow safely read residue before channel termination. */ -int pl330_pause(struct dma_chan *chan) +static int pl330_pause(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); struct pl330_dmac *pl330 = pch->dmac; @@ -2203,8 +2203,8 @@ static void pl330_free_chan_resources(struct dma_chan *chan) pm_runtime_put_autosuspend(pch->dmac->ddma.dev); } -int pl330_get_current_xferred_count(struct dma_pl330_chan *pch, - struct dma_pl330_desc *desc) +static int pl330_get_current_xferred_count(struct dma_pl330_chan *pch, + struct dma_pl330_desc *desc) { struct pl330_thread *thrd = pch->thread; struct pl330_dmac *pl330 = pch->dmac; @@ -2259,7 +2259,17 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie, transferred = 0; residual += desc->bytes_requested - transferred; if (desc->txd.cookie == cookie) { - ret = desc->status; + switch (desc->status) { + case DONE: + ret = DMA_COMPLETE; + break; + case PREP: + case BUSY: + ret = DMA_IN_PROGRESS; + break; + default: + WARN_ON(1); + } break; } if (desc->last) diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c index fa764a39cd36..9217f893b0d1 100644 --- a/drivers/dma/ppc4xx/adma.c +++ b/drivers/dma/ppc4xx/adma.c @@ -16,10 +16,6 @@ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 59 - * Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * The full GNU General Public License is included in this distribution in the * file called COPYING. */ diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c index 9c914d625906..5a250cdc8376 100644 --- a/drivers/dma/qcom_bam_dma.c +++ b/drivers/dma/qcom_bam_dma.c @@ -171,6 +171,35 @@ static const struct reg_offset_data bam_v1_4_reg_info[] = { [BAM_P_FIFO_SIZES] = { 0x1820, 0x00, 0x1000, 0x00 }, }; +static const struct reg_offset_data bam_v1_7_reg_info[] = { + [BAM_CTRL] = { 0x00000, 0x00, 0x00, 0x00 }, + [BAM_REVISION] = { 0x01000, 0x00, 0x00, 0x00 }, + [BAM_NUM_PIPES] = { 0x01008, 0x00, 0x00, 0x00 }, + [BAM_DESC_CNT_TRSHLD] = { 0x00008, 0x00, 0x00, 0x00 }, + [BAM_IRQ_SRCS] = { 0x03010, 0x00, 0x00, 0x00 }, + [BAM_IRQ_SRCS_MSK] = { 0x03014, 0x00, 0x00, 0x00 }, + [BAM_IRQ_SRCS_UNMASKED] = { 0x03018, 0x00, 0x00, 0x00 }, + [BAM_IRQ_STTS] = { 0x00014, 0x00, 0x00, 0x00 }, + [BAM_IRQ_CLR] = { 0x00018, 0x00, 0x00, 0x00 }, + [BAM_IRQ_EN] = { 0x0001C, 0x00, 0x00, 0x00 }, + [BAM_CNFG_BITS] = { 0x0007C, 0x00, 0x00, 0x00 }, + [BAM_IRQ_SRCS_EE] = { 0x03000, 0x00, 0x00, 0x1000 }, + [BAM_IRQ_SRCS_MSK_EE] = { 0x03004, 0x00, 0x00, 0x1000 }, + [BAM_P_CTRL] = { 0x13000, 0x1000, 0x00, 0x00 }, + [BAM_P_RST] = { 0x13004, 0x1000, 0x00, 0x00 }, + [BAM_P_HALT] = { 0x13008, 0x1000, 0x00, 0x00 }, + [BAM_P_IRQ_STTS] = { 0x13010, 0x1000, 0x00, 0x00 }, + [BAM_P_IRQ_CLR] = { 0x13014, 0x1000, 0x00, 0x00 }, + [BAM_P_IRQ_EN] = { 0x13018, 0x1000, 0x00, 0x00 }, + [BAM_P_EVNT_DEST_ADDR] = { 0x1382C, 0x00, 0x1000, 0x00 }, + [BAM_P_EVNT_REG] = { 0x13818, 0x00, 0x1000, 0x00 }, + [BAM_P_SW_OFSTS] = { 0x13800, 0x00, 0x1000, 0x00 }, + [BAM_P_DATA_FIFO_ADDR] = { 0x13824, 0x00, 0x1000, 0x00 }, + [BAM_P_DESC_FIFO_ADDR] = { 0x1381C, 0x00, 0x1000, 0x00 }, + [BAM_P_EVNT_GEN_TRSHLD] = { 0x13828, 0x00, 0x1000, 0x00 }, + [BAM_P_FIFO_SIZES] = { 0x13820, 0x00, 0x1000, 0x00 }, +}; + /* BAM CTRL */ #define BAM_SW_RST BIT(0) #define BAM_EN BIT(1) @@ -1051,6 +1080,7 @@ static void bam_channel_init(struct bam_device *bdev, struct bam_chan *bchan, static const struct of_device_id bam_of_match[] = { { .compatible = "qcom,bam-v1.3.0", .data = &bam_v1_3_reg_info }, { .compatible = "qcom,bam-v1.4.0", .data = &bam_v1_4_reg_info }, + { .compatible = "qcom,bam-v1.7.0", .data = &bam_v1_7_reg_info }, {} }; @@ -1113,7 +1143,7 @@ static int bam_dma_probe(struct platform_device *pdev) if (!bdev->channels) { ret = -ENOMEM; - goto err_disable_clk; + goto err_tasklet_kill; } /* allocate and initialize channels */ @@ -1125,7 +1155,7 @@ static int bam_dma_probe(struct platform_device *pdev) ret = devm_request_irq(bdev->dev, bdev->irq, bam_dma_irq, IRQF_TRIGGER_HIGH, "bam_dma", bdev); if (ret) - goto err_disable_clk; + goto err_bam_channel_exit; /* set max dma segment size */ bdev->common.dev = bdev->dev; @@ -1133,7 +1163,7 @@ static int bam_dma_probe(struct platform_device *pdev) ret = dma_set_max_seg_size(bdev->common.dev, BAM_MAX_DATA_SIZE); if (ret) { dev_err(bdev->dev, "cannot set maximum segment size\n"); - goto err_disable_clk; + goto err_bam_channel_exit; } platform_set_drvdata(pdev, bdev); @@ -1161,7 +1191,7 @@ static int bam_dma_probe(struct platform_device *pdev) ret = dma_async_device_register(&bdev->common); if (ret) { dev_err(bdev->dev, "failed to register dma async device\n"); - goto err_disable_clk; + goto err_bam_channel_exit; } ret = of_dma_controller_register(pdev->dev.of_node, bam_dma_xlate, @@ -1173,8 +1203,14 @@ static int bam_dma_probe(struct platform_device *pdev) err_unregister_dma: dma_async_device_unregister(&bdev->common); +err_bam_channel_exit: + for (i = 0; i < bdev->num_channels; i++) + tasklet_kill(&bdev->channels[i].vc.task); +err_tasklet_kill: + tasklet_kill(&bdev->task); err_disable_clk: clk_disable_unprepare(bdev->bamclk); + return ret; } diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c index 2f91da3db836..01dcaf21b988 100644 --- a/drivers/dma/s3c24xx-dma.c +++ b/drivers/dma/s3c24xx-dma.c @@ -749,11 +749,6 @@ unlock: return ret; } -static int s3c24xx_dma_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void s3c24xx_dma_free_chan_resources(struct dma_chan *chan) { /* Ensure all queued descriptors are freed */ @@ -1238,7 +1233,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) if (!s3cdma->phy_chans) return -ENOMEM; - /* aquire irqs and clocks for all physical channels */ + /* acquire irqs and clocks for all physical channels */ for (i = 0; i < pdata->num_phy_channels; i++) { struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i]; char clk_name[6]; @@ -1266,7 +1261,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) sprintf(clk_name, "dma.%d", i); phy->clk = devm_clk_get(&pdev->dev, clk_name); if (IS_ERR(phy->clk) && sdata->has_clocks) { - dev_err(&pdev->dev, "unable to aquire clock for channel %d, error %lu", + dev_err(&pdev->dev, "unable to acquire clock for channel %d, error %lu\n", i, PTR_ERR(phy->clk)); continue; } @@ -1290,8 +1285,6 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_MEMCPY, s3cdma->memcpy.cap_mask); dma_cap_set(DMA_PRIVATE, s3cdma->memcpy.cap_mask); s3cdma->memcpy.dev = &pdev->dev; - s3cdma->memcpy.device_alloc_chan_resources = - s3c24xx_dma_alloc_chan_resources; s3cdma->memcpy.device_free_chan_resources = s3c24xx_dma_free_chan_resources; s3cdma->memcpy.device_prep_dma_memcpy = s3c24xx_dma_prep_memcpy; @@ -1305,8 +1298,6 @@ static int s3c24xx_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_CYCLIC, s3cdma->slave.cap_mask); dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask); s3cdma->slave.dev = &pdev->dev; - s3cdma->slave.device_alloc_chan_resources = - s3c24xx_dma_alloc_chan_resources; s3cdma->slave.device_free_chan_resources = s3c24xx_dma_free_chan_resources; s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status; diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c index 5adf5407a8cb..43db255050d2 100644 --- a/drivers/dma/sa11x0-dma.c +++ b/drivers/dma/sa11x0-dma.c @@ -389,11 +389,6 @@ static void sa11x0_dma_tasklet(unsigned long arg) } -static int sa11x0_dma_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void sa11x0_dma_free_chan_resources(struct dma_chan *chan) { struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan); @@ -835,7 +830,6 @@ static int sa11x0_dma_init_dmadev(struct dma_device *dmadev, INIT_LIST_HEAD(&dmadev->channels); dmadev->dev = dev; - dmadev->device_alloc_chan_resources = sa11x0_dma_alloc_chan_resources; dmadev->device_free_chan_resources = sa11x0_dma_free_chan_resources; dmadev->device_config = sa11x0_dma_device_config; dmadev->device_pause = sa11x0_dma_device_pause; @@ -948,6 +942,12 @@ static int sa11x0_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_CYCLIC, d->slave.cap_mask); d->slave.device_prep_slave_sg = sa11x0_dma_prep_slave_sg; d->slave.device_prep_dma_cyclic = sa11x0_dma_prep_dma_cyclic; + d->slave.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + d->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + d->slave.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES); + d->slave.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | + BIT(DMA_SLAVE_BUSWIDTH_2_BYTES); ret = sa11x0_dma_init_dmadev(&d->slave, &pdev->dev); if (ret) { dev_warn(d->slave.dev, "failed to register slave async device: %d\n", diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig index 8190ad225a1b..0f371524a4d9 100644 --- a/drivers/dma/sh/Kconfig +++ b/drivers/dma/sh/Kconfig @@ -51,12 +51,6 @@ config RCAR_HPB_DMAE help Enable support for the Renesas R-Car series DMA controllers. -config RCAR_AUDMAC_PP - tristate "Renesas R-Car Audio DMAC Peripheral Peripheral support" - depends on SH_DMAE_BASE - help - Enable support for the Renesas R-Car Audio DMAC Peripheral Peripheral controllers. - config RCAR_DMAC tristate "Renesas R-Car Gen2 DMA Controller" depends on ARCH_SHMOBILE || COMPILE_TEST @@ -64,3 +58,12 @@ config RCAR_DMAC help This driver supports the general purpose DMA controller found in the Renesas R-Car second generation SoCs. + +config RENESAS_USB_DMAC + tristate "Renesas USB-DMA Controller" + depends on ARCH_SHMOBILE || COMPILE_TEST + select RENESAS_DMA + select DMA_VIRTUAL_CHANNELS + help + This driver supports the USB-DMA controller found in the Renesas + SoCs. diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile index 2852f9db61a4..b8a598066ce2 100644 --- a/drivers/dma/sh/Makefile +++ b/drivers/dma/sh/Makefile @@ -15,5 +15,5 @@ obj-$(CONFIG_SH_DMAE) += shdma.o obj-$(CONFIG_SUDMAC) += sudmac.o obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o -obj-$(CONFIG_RCAR_AUDMAC_PP) += rcar-audmapp.o obj-$(CONFIG_RCAR_DMAC) += rcar-dmac.o +obj-$(CONFIG_RENESAS_USB_DMAC) += usb-dmac.o diff --git a/drivers/dma/sh/rcar-audmapp.c b/drivers/dma/sh/rcar-audmapp.c deleted file mode 100644 index d95bbdd721f4..000000000000 --- a/drivers/dma/sh/rcar-audmapp.c +++ /dev/null @@ -1,376 +0,0 @@ -/* - * This is for Renesas R-Car Audio-DMAC-peri-peri. - * - * Copyright (C) 2014 Renesas Electronics Corporation - * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> - * - * based on the drivers/dma/sh/shdma.c - * - * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de> - * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com> - * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved. - * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved. - * - * This is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - */ -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/dmaengine.h> -#include <linux/of_dma.h> -#include <linux/platform_data/dma-rcar-audmapp.h> -#include <linux/platform_device.h> -#include <linux/shdma-base.h> - -/* - * DMA register - */ -#define PDMASAR 0x00 -#define PDMADAR 0x04 -#define PDMACHCR 0x0c - -/* PDMACHCR */ -#define PDMACHCR_DE (1 << 0) - -#define AUDMAPP_MAX_CHANNELS 29 - -/* Default MEMCPY transfer size = 2^2 = 4 bytes */ -#define LOG2_DEFAULT_XFER_SIZE 2 -#define AUDMAPP_SLAVE_NUMBER 256 -#define AUDMAPP_LEN_MAX (16 * 1024 * 1024) - -struct audmapp_chan { - struct shdma_chan shdma_chan; - void __iomem *base; - dma_addr_t slave_addr; - u32 chcr; -}; - -struct audmapp_device { - struct shdma_dev shdma_dev; - struct audmapp_pdata *pdata; - struct device *dev; - void __iomem *chan_reg; -}; - -struct audmapp_desc { - struct shdma_desc shdma_desc; - dma_addr_t src; - dma_addr_t dst; -}; - -#define to_shdma_chan(c) container_of(c, struct shdma_chan, dma_chan) - -#define to_chan(chan) container_of(chan, struct audmapp_chan, shdma_chan) -#define to_desc(sdesc) container_of(sdesc, struct audmapp_desc, shdma_desc) -#define to_dev(chan) container_of(chan->shdma_chan.dma_chan.device, \ - struct audmapp_device, shdma_dev.dma_dev) - -static void audmapp_write(struct audmapp_chan *auchan, u32 data, u32 reg) -{ - struct audmapp_device *audev = to_dev(auchan); - struct device *dev = audev->dev; - - dev_dbg(dev, "w %p : %08x\n", auchan->base + reg, data); - - iowrite32(data, auchan->base + reg); -} - -static u32 audmapp_read(struct audmapp_chan *auchan, u32 reg) -{ - return ioread32(auchan->base + reg); -} - -static void audmapp_halt(struct shdma_chan *schan) -{ - struct audmapp_chan *auchan = to_chan(schan); - int i; - - audmapp_write(auchan, 0, PDMACHCR); - - for (i = 0; i < 1024; i++) { - if (0 == audmapp_read(auchan, PDMACHCR)) - return; - udelay(1); - } -} - -static void audmapp_start_xfer(struct shdma_chan *schan, - struct shdma_desc *sdesc) -{ - struct audmapp_chan *auchan = to_chan(schan); - struct audmapp_device *audev = to_dev(auchan); - struct audmapp_desc *desc = to_desc(sdesc); - struct device *dev = audev->dev; - u32 chcr = auchan->chcr | PDMACHCR_DE; - - dev_dbg(dev, "src/dst/chcr = %pad/%pad/%08x\n", - &desc->src, &desc->dst, chcr); - - audmapp_write(auchan, desc->src, PDMASAR); - audmapp_write(auchan, desc->dst, PDMADAR); - audmapp_write(auchan, chcr, PDMACHCR); -} - -static int audmapp_get_config(struct audmapp_chan *auchan, int slave_id, - u32 *chcr, dma_addr_t *dst) -{ - struct audmapp_device *audev = to_dev(auchan); - struct audmapp_pdata *pdata = audev->pdata; - struct audmapp_slave_config *cfg; - int i; - - *chcr = 0; - *dst = 0; - - if (!pdata) { /* DT */ - *chcr = ((u32)slave_id) << 16; - auchan->shdma_chan.slave_id = (slave_id) >> 8; - return 0; - } - - /* non-DT */ - - if (slave_id >= AUDMAPP_SLAVE_NUMBER) - return -ENXIO; - - for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++) - if (cfg->slave_id == slave_id) { - *chcr = cfg->chcr; - *dst = cfg->dst; - return 0; - } - - return -ENXIO; -} - -static int audmapp_set_slave(struct shdma_chan *schan, int slave_id, - dma_addr_t slave_addr, bool try) -{ - struct audmapp_chan *auchan = to_chan(schan); - u32 chcr; - dma_addr_t dst; - int ret; - - ret = audmapp_get_config(auchan, slave_id, &chcr, &dst); - if (ret < 0) - return ret; - - if (try) - return 0; - - auchan->chcr = chcr; - auchan->slave_addr = slave_addr ? : dst; - - return 0; -} - -static int audmapp_desc_setup(struct shdma_chan *schan, - struct shdma_desc *sdesc, - dma_addr_t src, dma_addr_t dst, size_t *len) -{ - struct audmapp_desc *desc = to_desc(sdesc); - - if (*len > (size_t)AUDMAPP_LEN_MAX) - *len = (size_t)AUDMAPP_LEN_MAX; - - desc->src = src; - desc->dst = dst; - - return 0; -} - -static void audmapp_setup_xfer(struct shdma_chan *schan, - int slave_id) -{ -} - -static dma_addr_t audmapp_slave_addr(struct shdma_chan *schan) -{ - struct audmapp_chan *auchan = to_chan(schan); - - return auchan->slave_addr; -} - -static bool audmapp_channel_busy(struct shdma_chan *schan) -{ - struct audmapp_chan *auchan = to_chan(schan); - u32 chcr = audmapp_read(auchan, PDMACHCR); - - return chcr & ~PDMACHCR_DE; -} - -static bool audmapp_desc_completed(struct shdma_chan *schan, - struct shdma_desc *sdesc) -{ - return true; -} - -static struct shdma_desc *audmapp_embedded_desc(void *buf, int i) -{ - return &((struct audmapp_desc *)buf)[i].shdma_desc; -} - -static const struct shdma_ops audmapp_shdma_ops = { - .halt_channel = audmapp_halt, - .desc_setup = audmapp_desc_setup, - .set_slave = audmapp_set_slave, - .start_xfer = audmapp_start_xfer, - .embedded_desc = audmapp_embedded_desc, - .setup_xfer = audmapp_setup_xfer, - .slave_addr = audmapp_slave_addr, - .channel_busy = audmapp_channel_busy, - .desc_completed = audmapp_desc_completed, -}; - -static int audmapp_chan_probe(struct platform_device *pdev, - struct audmapp_device *audev, int id) -{ - struct shdma_dev *sdev = &audev->shdma_dev; - struct audmapp_chan *auchan; - struct shdma_chan *schan; - struct device *dev = audev->dev; - - auchan = devm_kzalloc(dev, sizeof(*auchan), GFP_KERNEL); - if (!auchan) - return -ENOMEM; - - schan = &auchan->shdma_chan; - schan->max_xfer_len = AUDMAPP_LEN_MAX; - - shdma_chan_probe(sdev, schan, id); - - auchan->base = audev->chan_reg + 0x20 + (0x10 * id); - dev_dbg(dev, "%02d : %p / %p", id, auchan->base, audev->chan_reg); - - return 0; -} - -static void audmapp_chan_remove(struct audmapp_device *audev) -{ - struct shdma_chan *schan; - int i; - - shdma_for_each_chan(schan, &audev->shdma_dev, i) { - BUG_ON(!schan); - shdma_chan_remove(schan); - } -} - -static struct dma_chan *audmapp_of_xlate(struct of_phandle_args *dma_spec, - struct of_dma *ofdma) -{ - dma_cap_mask_t mask; - struct dma_chan *chan; - u32 chcr = dma_spec->args[0]; - - if (dma_spec->args_count != 1) - return NULL; - - dma_cap_zero(mask); - dma_cap_set(DMA_SLAVE, mask); - - chan = dma_request_channel(mask, shdma_chan_filter, NULL); - if (chan) - to_shdma_chan(chan)->hw_req = chcr; - - return chan; -} - -static int audmapp_probe(struct platform_device *pdev) -{ - struct audmapp_pdata *pdata = pdev->dev.platform_data; - struct device_node *np = pdev->dev.of_node; - struct audmapp_device *audev; - struct shdma_dev *sdev; - struct dma_device *dma_dev; - struct resource *res; - int err, i; - - if (np) - of_dma_controller_register(np, audmapp_of_xlate, pdev); - else if (!pdata) - return -ENODEV; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - audev = devm_kzalloc(&pdev->dev, sizeof(*audev), GFP_KERNEL); - if (!audev) - return -ENOMEM; - - audev->dev = &pdev->dev; - audev->pdata = pdata; - audev->chan_reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(audev->chan_reg)) - return PTR_ERR(audev->chan_reg); - - sdev = &audev->shdma_dev; - sdev->ops = &audmapp_shdma_ops; - sdev->desc_size = sizeof(struct audmapp_desc); - - dma_dev = &sdev->dma_dev; - dma_dev->copy_align = LOG2_DEFAULT_XFER_SIZE; - dma_cap_set(DMA_SLAVE, dma_dev->cap_mask); - - err = shdma_init(&pdev->dev, sdev, AUDMAPP_MAX_CHANNELS); - if (err < 0) - return err; - - platform_set_drvdata(pdev, audev); - - /* Create DMA Channel */ - for (i = 0; i < AUDMAPP_MAX_CHANNELS; i++) { - err = audmapp_chan_probe(pdev, audev, i); - if (err) - goto chan_probe_err; - } - - err = dma_async_device_register(dma_dev); - if (err < 0) - goto chan_probe_err; - - return err; - -chan_probe_err: - audmapp_chan_remove(audev); - shdma_cleanup(sdev); - - return err; -} - -static int audmapp_remove(struct platform_device *pdev) -{ - struct audmapp_device *audev = platform_get_drvdata(pdev); - struct dma_device *dma_dev = &audev->shdma_dev.dma_dev; - - dma_async_device_unregister(dma_dev); - - audmapp_chan_remove(audev); - shdma_cleanup(&audev->shdma_dev); - - return 0; -} - -static const struct of_device_id audmapp_of_match[] = { - { .compatible = "renesas,rcar-audmapp", }, - {}, -}; - -static struct platform_driver audmapp_driver = { - .probe = audmapp_probe, - .remove = audmapp_remove, - .driver = { - .name = "rcar-audmapp-engine", - .of_match_table = audmapp_of_match, - }, -}; -module_platform_driver(audmapp_driver); - -MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); -MODULE_DESCRIPTION("Renesas R-Car Audio DMAC peri-peri driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c index 8ee383d339a5..10fcabad80f3 100644 --- a/drivers/dma/sh/shdma-base.c +++ b/drivers/dma/sh/shdma-base.c @@ -171,8 +171,7 @@ static struct shdma_desc *shdma_get_desc(struct shdma_chan *schan) return NULL; } -static int shdma_setup_slave(struct shdma_chan *schan, int slave_id, - dma_addr_t slave_addr) +static int shdma_setup_slave(struct shdma_chan *schan, dma_addr_t slave_addr) { struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device); const struct shdma_ops *ops = sdev->ops; @@ -183,25 +182,23 @@ static int shdma_setup_slave(struct shdma_chan *schan, int slave_id, ret = ops->set_slave(schan, match, slave_addr, true); if (ret < 0) return ret; - - slave_id = schan->slave_id; } else { - match = slave_id; + match = schan->real_slave_id; } - if (slave_id < 0 || slave_id >= slave_num) + if (schan->real_slave_id < 0 || schan->real_slave_id >= slave_num) return -EINVAL; - if (test_and_set_bit(slave_id, shdma_slave_used)) + if (test_and_set_bit(schan->real_slave_id, shdma_slave_used)) return -EBUSY; ret = ops->set_slave(schan, match, slave_addr, false); if (ret < 0) { - clear_bit(slave_id, shdma_slave_used); + clear_bit(schan->real_slave_id, shdma_slave_used); return ret; } - schan->slave_id = slave_id; + schan->slave_id = schan->real_slave_id; return 0; } @@ -221,10 +218,12 @@ static int shdma_alloc_chan_resources(struct dma_chan *chan) */ if (slave) { /* Legacy mode: .private is set in filter */ - ret = shdma_setup_slave(schan, slave->slave_id, 0); + schan->real_slave_id = slave->slave_id; + ret = shdma_setup_slave(schan, 0); if (ret < 0) goto esetslave; } else { + /* Normal mode: real_slave_id was set by filter */ schan->slave_id = -EINVAL; } @@ -258,11 +257,14 @@ esetslave: /* * This is the standard shdma filter function to be used as a replacement to the - * "old" method, using the .private pointer. If for some reason you allocate a - * channel without slave data, use something like ERR_PTR(-EINVAL) as a filter + * "old" method, using the .private pointer. + * You always have to pass a valid slave id as the argument, old drivers that + * pass ERR_PTR(-EINVAL) as a filter parameter and set it up in dma_slave_config + * need to be updated so we can remove the slave_id field from dma_slave_config. * parameter. If this filter is used, the slave driver, after calling * dma_request_channel(), will also have to call dmaengine_slave_config() with - * .slave_id, .direction, and either .src_addr or .dst_addr set. + * .direction, and either .src_addr or .dst_addr set. + * * NOTE: this filter doesn't support multiple DMAC drivers with the DMA_SLAVE * capability! If this becomes a requirement, hardware glue drivers, using this * services would have to provide their own filters, which first would check @@ -276,7 +278,7 @@ bool shdma_chan_filter(struct dma_chan *chan, void *arg) { struct shdma_chan *schan; struct shdma_dev *sdev; - int match = (long)arg; + int slave_id = (long)arg; int ret; /* Only support channels handled by this driver. */ @@ -284,19 +286,39 @@ bool shdma_chan_filter(struct dma_chan *chan, void *arg) shdma_alloc_chan_resources) return false; - if (match < 0) + schan = to_shdma_chan(chan); + sdev = to_shdma_dev(chan->device); + + /* + * For DT, the schan->slave_id field is generated by the + * set_slave function from the slave ID that is passed in + * from xlate. For the non-DT case, the slave ID is + * directly passed into the filter function by the driver + */ + if (schan->dev->of_node) { + ret = sdev->ops->set_slave(schan, slave_id, 0, true); + if (ret < 0) + return false; + + schan->real_slave_id = schan->slave_id; + return true; + } + + if (slave_id < 0) { /* No slave requested - arbitrary channel */ + dev_warn(sdev->dma_dev.dev, "invalid slave ID passed to dma_request_slave\n"); return true; + } - schan = to_shdma_chan(chan); - if (!schan->dev->of_node && match >= slave_num) + if (slave_id >= slave_num) return false; - sdev = to_shdma_dev(schan->dma_chan.device); - ret = sdev->ops->set_slave(schan, match, 0, true); + ret = sdev->ops->set_slave(schan, slave_id, 0, true); if (ret < 0) return false; + schan->real_slave_id = slave_id; + return true; } EXPORT_SYMBOL(shdma_chan_filter); @@ -452,6 +474,8 @@ static void shdma_free_chan_resources(struct dma_chan *chan) chan->private = NULL; } + schan->real_slave_id = 0; + spin_lock_irq(&schan->chan_lock); list_splice_init(&schan->ld_free, &list); @@ -764,11 +788,20 @@ static int shdma_config(struct dma_chan *chan, */ if (!config) return -EINVAL; + + /* + * overriding the slave_id through dma_slave_config is deprecated, + * but possibly some out-of-tree drivers still do it. + */ + if (WARN_ON_ONCE(config->slave_id && + config->slave_id != schan->real_slave_id)) + schan->real_slave_id = config->slave_id; + /* * We could lock this, but you shouldn't be configuring the * channel, while using it... */ - return shdma_setup_slave(schan, config->slave_id, + return shdma_setup_slave(schan, config->direction == DMA_DEV_TO_MEM ? config->src_addr : config->dst_addr); } diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c index 9f1d4c7dbab8..11707df1a689 100644 --- a/drivers/dma/sh/shdmac.c +++ b/drivers/dma/sh/shdmac.c @@ -443,7 +443,7 @@ static bool sh_dmae_reset(struct sh_dmae_device *shdev) return ret; } -#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM) +#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE) static irqreturn_t sh_dmae_err(int irq, void *data) { struct sh_dmae_device *shdev = data; @@ -689,7 +689,7 @@ static int sh_dmae_probe(struct platform_device *pdev) const struct sh_dmae_pdata *pdata; unsigned long chan_flag[SH_DMAE_MAX_CHANNELS] = {}; int chan_irq[SH_DMAE_MAX_CHANNELS]; -#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM) +#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE) unsigned long irqflags = 0; int errirq; #endif diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c new file mode 100644 index 000000000000..f705798ce3eb --- /dev/null +++ b/drivers/dma/sh/usb-dmac.c @@ -0,0 +1,910 @@ +/* + * Renesas USB DMA Controller Driver + * + * Copyright (C) 2015 Renesas Electronics Corporation + * + * based on rcar-dmac.c + * Copyright (C) 2014 Renesas Electronics Inc. + * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com> + * + * This is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ + +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/dmaengine.h> +#include <linux/interrupt.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_dma.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "../dmaengine.h" +#include "../virt-dma.h" + +/* + * struct usb_dmac_sg - Descriptor for a hardware transfer + * @mem_addr: memory address + * @size: transfer size in bytes + */ +struct usb_dmac_sg { + dma_addr_t mem_addr; + u32 size; +}; + +/* + * struct usb_dmac_desc - USB DMA Transfer Descriptor + * @vd: base virtual channel DMA transaction descriptor + * @direction: direction of the DMA transfer + * @sg_allocated_len: length of allocated sg + * @sg_len: length of sg + * @sg_index: index of sg + * @residue: residue after the DMAC completed a transfer + * @node: node for desc_got and desc_freed + * @done_cookie: cookie after the DMAC completed a transfer + * @sg: information for the transfer + */ +struct usb_dmac_desc { + struct virt_dma_desc vd; + enum dma_transfer_direction direction; + unsigned int sg_allocated_len; + unsigned int sg_len; + unsigned int sg_index; + u32 residue; + struct list_head node; + dma_cookie_t done_cookie; + struct usb_dmac_sg sg[0]; +}; + +#define to_usb_dmac_desc(vd) container_of(vd, struct usb_dmac_desc, vd) + +/* + * struct usb_dmac_chan - USB DMA Controller Channel + * @vc: base virtual DMA channel object + * @iomem: channel I/O memory base + * @index: index of this channel in the controller + * @irq: irq number of this channel + * @desc: the current descriptor + * @descs_allocated: number of descriptors allocated + * @desc_got: got descriptors + * @desc_freed: freed descriptors after the DMAC completed a transfer + */ +struct usb_dmac_chan { + struct virt_dma_chan vc; + void __iomem *iomem; + unsigned int index; + int irq; + struct usb_dmac_desc *desc; + int descs_allocated; + struct list_head desc_got; + struct list_head desc_freed; +}; + +#define to_usb_dmac_chan(c) container_of(c, struct usb_dmac_chan, vc.chan) + +/* + * struct usb_dmac - USB DMA Controller + * @engine: base DMA engine object + * @dev: the hardware device + * @iomem: remapped I/O memory base + * @n_channels: number of available channels + * @channels: array of DMAC channels + */ +struct usb_dmac { + struct dma_device engine; + struct device *dev; + void __iomem *iomem; + + unsigned int n_channels; + struct usb_dmac_chan *channels; +}; + +#define to_usb_dmac(d) container_of(d, struct usb_dmac, engine) + +/* ----------------------------------------------------------------------------- + * Registers + */ + +#define USB_DMAC_CHAN_OFFSET(i) (0x20 + 0x20 * (i)) + +#define USB_DMASWR 0x0008 +#define USB_DMASWR_SWR (1 << 0) +#define USB_DMAOR 0x0060 +#define USB_DMAOR_AE (1 << 2) +#define USB_DMAOR_DME (1 << 0) + +#define USB_DMASAR 0x0000 +#define USB_DMADAR 0x0004 +#define USB_DMATCR 0x0008 +#define USB_DMATCR_MASK 0x00ffffff +#define USB_DMACHCR 0x0014 +#define USB_DMACHCR_FTE (1 << 24) +#define USB_DMACHCR_NULLE (1 << 16) +#define USB_DMACHCR_NULL (1 << 12) +#define USB_DMACHCR_TS_8B ((0 << 7) | (0 << 6)) +#define USB_DMACHCR_TS_16B ((0 << 7) | (1 << 6)) +#define USB_DMACHCR_TS_32B ((1 << 7) | (0 << 6)) +#define USB_DMACHCR_IE (1 << 5) +#define USB_DMACHCR_SP (1 << 2) +#define USB_DMACHCR_TE (1 << 1) +#define USB_DMACHCR_DE (1 << 0) +#define USB_DMATEND 0x0018 + +/* Hardcode the xfer_shift to 5 (32bytes) */ +#define USB_DMAC_XFER_SHIFT 5 +#define USB_DMAC_XFER_SIZE (1 << USB_DMAC_XFER_SHIFT) +#define USB_DMAC_CHCR_TS USB_DMACHCR_TS_32B +#define USB_DMAC_SLAVE_BUSWIDTH DMA_SLAVE_BUSWIDTH_32_BYTES + +/* for descriptors */ +#define USB_DMAC_INITIAL_NR_DESC 16 +#define USB_DMAC_INITIAL_NR_SG 8 + +/* ----------------------------------------------------------------------------- + * Device access + */ + +static void usb_dmac_write(struct usb_dmac *dmac, u32 reg, u32 data) +{ + writel(data, dmac->iomem + reg); +} + +static u32 usb_dmac_read(struct usb_dmac *dmac, u32 reg) +{ + return readl(dmac->iomem + reg); +} + +static u32 usb_dmac_chan_read(struct usb_dmac_chan *chan, u32 reg) +{ + return readl(chan->iomem + reg); +} + +static void usb_dmac_chan_write(struct usb_dmac_chan *chan, u32 reg, u32 data) +{ + writel(data, chan->iomem + reg); +} + +/* ----------------------------------------------------------------------------- + * Initialization and configuration + */ + +static bool usb_dmac_chan_is_busy(struct usb_dmac_chan *chan) +{ + u32 chcr = usb_dmac_chan_read(chan, USB_DMACHCR); + + return (chcr & (USB_DMACHCR_DE | USB_DMACHCR_TE)) == USB_DMACHCR_DE; +} + +static u32 usb_dmac_calc_tend(u32 size) +{ + /* + * Please refer to the Figure "Example of Final Transaction Valid + * Data Transfer Enable (EDTEN) Setting" in the data sheet. + */ + return 0xffffffff << (32 - (size % USB_DMAC_XFER_SIZE ? : + USB_DMAC_XFER_SIZE)); +} + +/* This function is already held by vc.lock */ +static void usb_dmac_chan_start_sg(struct usb_dmac_chan *chan, + unsigned int index) +{ + struct usb_dmac_desc *desc = chan->desc; + struct usb_dmac_sg *sg = desc->sg + index; + dma_addr_t src_addr = 0, dst_addr = 0; + + WARN_ON_ONCE(usb_dmac_chan_is_busy(chan)); + + if (desc->direction == DMA_DEV_TO_MEM) + dst_addr = sg->mem_addr; + else + src_addr = sg->mem_addr; + + dev_dbg(chan->vc.chan.device->dev, + "chan%u: queue sg %p: %u@%pad -> %pad\n", + chan->index, sg, sg->size, &src_addr, &dst_addr); + + usb_dmac_chan_write(chan, USB_DMASAR, src_addr & 0xffffffff); + usb_dmac_chan_write(chan, USB_DMADAR, dst_addr & 0xffffffff); + usb_dmac_chan_write(chan, USB_DMATCR, + DIV_ROUND_UP(sg->size, USB_DMAC_XFER_SIZE)); + usb_dmac_chan_write(chan, USB_DMATEND, usb_dmac_calc_tend(sg->size)); + + usb_dmac_chan_write(chan, USB_DMACHCR, USB_DMAC_CHCR_TS | + USB_DMACHCR_NULLE | USB_DMACHCR_IE | USB_DMACHCR_DE); +} + +/* This function is already held by vc.lock */ +static void usb_dmac_chan_start_desc(struct usb_dmac_chan *chan) +{ + struct virt_dma_desc *vd; + + vd = vchan_next_desc(&chan->vc); + if (!vd) { + chan->desc = NULL; + return; + } + + /* + * Remove this request from vc->desc_issued. Otherwise, this driver + * will get the previous value from vchan_next_desc() after a transfer + * was completed. + */ + list_del(&vd->node); + + chan->desc = to_usb_dmac_desc(vd); + chan->desc->sg_index = 0; + usb_dmac_chan_start_sg(chan, 0); +} + +static int usb_dmac_init(struct usb_dmac *dmac) +{ + u16 dmaor; + + /* Clear all channels and enable the DMAC globally. */ + usb_dmac_write(dmac, USB_DMAOR, USB_DMAOR_DME); + + dmaor = usb_dmac_read(dmac, USB_DMAOR); + if ((dmaor & (USB_DMAOR_AE | USB_DMAOR_DME)) != USB_DMAOR_DME) { + dev_warn(dmac->dev, "DMAOR initialization failed.\n"); + return -EIO; + } + + return 0; +} + +/* ----------------------------------------------------------------------------- + * Descriptors allocation and free + */ +static int usb_dmac_desc_alloc(struct usb_dmac_chan *chan, unsigned int sg_len, + gfp_t gfp) +{ + struct usb_dmac_desc *desc; + unsigned long flags; + + desc = kzalloc(sizeof(*desc) + sg_len * sizeof(desc->sg[0]), gfp); + if (!desc) + return -ENOMEM; + + desc->sg_allocated_len = sg_len; + INIT_LIST_HEAD(&desc->node); + + spin_lock_irqsave(&chan->vc.lock, flags); + list_add_tail(&desc->node, &chan->desc_freed); + spin_unlock_irqrestore(&chan->vc.lock, flags); + + return 0; +} + +static void usb_dmac_desc_free(struct usb_dmac_chan *chan) +{ + struct usb_dmac_desc *desc, *_desc; + LIST_HEAD(list); + + list_splice_init(&chan->desc_freed, &list); + list_splice_init(&chan->desc_got, &list); + + list_for_each_entry_safe(desc, _desc, &list, node) { + list_del(&desc->node); + kfree(desc); + } + chan->descs_allocated = 0; +} + +static struct usb_dmac_desc *usb_dmac_desc_get(struct usb_dmac_chan *chan, + unsigned int sg_len, gfp_t gfp) +{ + struct usb_dmac_desc *desc = NULL; + unsigned long flags; + + /* Get a freed descritpor */ + spin_lock_irqsave(&chan->vc.lock, flags); + list_for_each_entry(desc, &chan->desc_freed, node) { + if (sg_len <= desc->sg_allocated_len) { + list_move_tail(&desc->node, &chan->desc_got); + spin_unlock_irqrestore(&chan->vc.lock, flags); + return desc; + } + } + spin_unlock_irqrestore(&chan->vc.lock, flags); + + /* Allocate a new descriptor */ + if (!usb_dmac_desc_alloc(chan, sg_len, gfp)) { + /* If allocated the desc, it was added to tail of the list */ + spin_lock_irqsave(&chan->vc.lock, flags); + desc = list_last_entry(&chan->desc_freed, struct usb_dmac_desc, + node); + list_move_tail(&desc->node, &chan->desc_got); + spin_unlock_irqrestore(&chan->vc.lock, flags); + return desc; + } + + return NULL; +} + +static void usb_dmac_desc_put(struct usb_dmac_chan *chan, + struct usb_dmac_desc *desc) +{ + unsigned long flags; + + spin_lock_irqsave(&chan->vc.lock, flags); + list_move_tail(&desc->node, &chan->desc_freed); + spin_unlock_irqrestore(&chan->vc.lock, flags); +} + +/* ----------------------------------------------------------------------------- + * Stop and reset + */ + +static void usb_dmac_soft_reset(struct usb_dmac_chan *uchan) +{ + struct dma_chan *chan = &uchan->vc.chan; + struct usb_dmac *dmac = to_usb_dmac(chan->device); + int i; + + /* Don't issue soft reset if any one of channels is busy */ + for (i = 0; i < dmac->n_channels; ++i) { + if (usb_dmac_chan_is_busy(uchan)) + return; + } + + usb_dmac_write(dmac, USB_DMAOR, 0); + usb_dmac_write(dmac, USB_DMASWR, USB_DMASWR_SWR); + udelay(100); + usb_dmac_write(dmac, USB_DMASWR, 0); + usb_dmac_write(dmac, USB_DMAOR, 1); +} + +static void usb_dmac_chan_halt(struct usb_dmac_chan *chan) +{ + u32 chcr = usb_dmac_chan_read(chan, USB_DMACHCR); + + chcr &= ~(USB_DMACHCR_IE | USB_DMACHCR_TE | USB_DMACHCR_DE); + usb_dmac_chan_write(chan, USB_DMACHCR, chcr); + + usb_dmac_soft_reset(chan); +} + +static void usb_dmac_stop(struct usb_dmac *dmac) +{ + usb_dmac_write(dmac, USB_DMAOR, 0); +} + +/* ----------------------------------------------------------------------------- + * DMA engine operations + */ + +static int usb_dmac_alloc_chan_resources(struct dma_chan *chan) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + int ret; + + while (uchan->descs_allocated < USB_DMAC_INITIAL_NR_DESC) { + ret = usb_dmac_desc_alloc(uchan, USB_DMAC_INITIAL_NR_SG, + GFP_KERNEL); + if (ret < 0) { + usb_dmac_desc_free(uchan); + return ret; + } + uchan->descs_allocated++; + } + + return pm_runtime_get_sync(chan->device->dev); +} + +static void usb_dmac_free_chan_resources(struct dma_chan *chan) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + unsigned long flags; + + /* Protect against ISR */ + spin_lock_irqsave(&uchan->vc.lock, flags); + usb_dmac_chan_halt(uchan); + spin_unlock_irqrestore(&uchan->vc.lock, flags); + + usb_dmac_desc_free(uchan); + vchan_free_chan_resources(&uchan->vc); + + pm_runtime_put(chan->device->dev); +} + +static struct dma_async_tx_descriptor * +usb_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, + unsigned int sg_len, enum dma_transfer_direction dir, + unsigned long dma_flags, void *context) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + struct usb_dmac_desc *desc; + struct scatterlist *sg; + int i; + + if (!sg_len) { + dev_warn(chan->device->dev, + "%s: bad parameter: len=%d\n", __func__, sg_len); + return NULL; + } + + desc = usb_dmac_desc_get(uchan, sg_len, GFP_NOWAIT); + if (!desc) + return NULL; + + desc->direction = dir; + desc->sg_len = sg_len; + for_each_sg(sgl, sg, sg_len, i) { + desc->sg[i].mem_addr = sg_dma_address(sg); + desc->sg[i].size = sg_dma_len(sg); + } + + return vchan_tx_prep(&uchan->vc, &desc->vd, dma_flags); +} + +static int usb_dmac_chan_terminate_all(struct dma_chan *chan) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + struct usb_dmac_desc *desc; + unsigned long flags; + LIST_HEAD(head); + LIST_HEAD(list); + + spin_lock_irqsave(&uchan->vc.lock, flags); + usb_dmac_chan_halt(uchan); + vchan_get_all_descriptors(&uchan->vc, &head); + if (uchan->desc) + uchan->desc = NULL; + list_splice_init(&uchan->desc_got, &list); + list_for_each_entry(desc, &list, node) + list_move_tail(&desc->node, &uchan->desc_freed); + spin_unlock_irqrestore(&uchan->vc.lock, flags); + vchan_dma_desc_free_list(&uchan->vc, &head); + + return 0; +} + +static unsigned int usb_dmac_get_current_residue(struct usb_dmac_chan *chan, + struct usb_dmac_desc *desc, + int sg_index) +{ + struct usb_dmac_sg *sg = desc->sg + sg_index; + u32 mem_addr = sg->mem_addr & 0xffffffff; + unsigned int residue = sg->size; + + /* + * We cannot use USB_DMATCR to calculate residue because USB_DMATCR + * has unsuited value to calculate. + */ + if (desc->direction == DMA_DEV_TO_MEM) + residue -= usb_dmac_chan_read(chan, USB_DMADAR) - mem_addr; + else + residue -= usb_dmac_chan_read(chan, USB_DMASAR) - mem_addr; + + return residue; +} + +static u32 usb_dmac_chan_get_residue_if_complete(struct usb_dmac_chan *chan, + dma_cookie_t cookie) +{ + struct usb_dmac_desc *desc; + u32 residue = 0; + + list_for_each_entry_reverse(desc, &chan->desc_freed, node) { + if (desc->done_cookie == cookie) { + residue = desc->residue; + break; + } + } + + return residue; +} + +static u32 usb_dmac_chan_get_residue(struct usb_dmac_chan *chan, + dma_cookie_t cookie) +{ + u32 residue = 0; + struct virt_dma_desc *vd; + struct usb_dmac_desc *desc = chan->desc; + int i; + + if (!desc) { + vd = vchan_find_desc(&chan->vc, cookie); + if (!vd) + return 0; + desc = to_usb_dmac_desc(vd); + } + + /* Compute the size of all usb_dmac_sg still to be transferred */ + for (i = desc->sg_index + 1; i < desc->sg_len; i++) + residue += desc->sg[i].size; + + /* Add the residue for the current sg */ + residue += usb_dmac_get_current_residue(chan, desc, desc->sg_index); + + return residue; +} + +static enum dma_status usb_dmac_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + enum dma_status status; + unsigned int residue = 0; + unsigned long flags; + + status = dma_cookie_status(chan, cookie, txstate); + /* a client driver will get residue after DMA_COMPLETE */ + if (!txstate) + return status; + + spin_lock_irqsave(&uchan->vc.lock, flags); + if (status == DMA_COMPLETE) + residue = usb_dmac_chan_get_residue_if_complete(uchan, cookie); + else + residue = usb_dmac_chan_get_residue(uchan, cookie); + spin_unlock_irqrestore(&uchan->vc.lock, flags); + + dma_set_residue(txstate, residue); + + return status; +} + +static void usb_dmac_issue_pending(struct dma_chan *chan) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + unsigned long flags; + + spin_lock_irqsave(&uchan->vc.lock, flags); + if (vchan_issue_pending(&uchan->vc) && !uchan->desc) + usb_dmac_chan_start_desc(uchan); + spin_unlock_irqrestore(&uchan->vc.lock, flags); +} + +static void usb_dmac_virt_desc_free(struct virt_dma_desc *vd) +{ + struct usb_dmac_desc *desc = to_usb_dmac_desc(vd); + struct usb_dmac_chan *chan = to_usb_dmac_chan(vd->tx.chan); + + usb_dmac_desc_put(chan, desc); +} + +/* ----------------------------------------------------------------------------- + * IRQ handling + */ + +static void usb_dmac_isr_transfer_end(struct usb_dmac_chan *chan) +{ + struct usb_dmac_desc *desc = chan->desc; + + BUG_ON(!desc); + + if (++desc->sg_index < desc->sg_len) { + usb_dmac_chan_start_sg(chan, desc->sg_index); + } else { + desc->residue = usb_dmac_get_current_residue(chan, desc, + desc->sg_index - 1); + desc->done_cookie = desc->vd.tx.cookie; + vchan_cookie_complete(&desc->vd); + + /* Restart the next transfer if this driver has a next desc */ + usb_dmac_chan_start_desc(chan); + } +} + +static irqreturn_t usb_dmac_isr_channel(int irq, void *dev) +{ + struct usb_dmac_chan *chan = dev; + irqreturn_t ret = IRQ_NONE; + u32 mask = USB_DMACHCR_TE; + u32 check_bits = USB_DMACHCR_TE | USB_DMACHCR_SP; + u32 chcr; + + spin_lock(&chan->vc.lock); + + chcr = usb_dmac_chan_read(chan, USB_DMACHCR); + if (chcr & check_bits) + mask |= USB_DMACHCR_DE | check_bits; + if (chcr & USB_DMACHCR_NULL) { + /* An interruption of TE will happen after we set FTE */ + mask |= USB_DMACHCR_NULL; + chcr |= USB_DMACHCR_FTE; + ret |= IRQ_HANDLED; + } + usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask); + + if (chcr & check_bits) { + usb_dmac_isr_transfer_end(chan); + ret |= IRQ_HANDLED; + } + + spin_unlock(&chan->vc.lock); + + return ret; +} + +/* ----------------------------------------------------------------------------- + * OF xlate and channel filter + */ + +static bool usb_dmac_chan_filter(struct dma_chan *chan, void *arg) +{ + struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan); + struct of_phandle_args *dma_spec = arg; + + if (dma_spec->np != chan->device->dev->of_node) + return false; + + /* USB-DMAC should be used with fixed usb controller's FIFO */ + if (uchan->index != dma_spec->args[0]) + return false; + + return true; +} + +static struct dma_chan *usb_dmac_of_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct usb_dmac_chan *uchan; + struct dma_chan *chan; + dma_cap_mask_t mask; + + if (dma_spec->args_count != 1) + return NULL; + + /* Only slave DMA channels can be allocated via DT */ + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + chan = dma_request_channel(mask, usb_dmac_chan_filter, dma_spec); + if (!chan) + return NULL; + + uchan = to_usb_dmac_chan(chan); + + return chan; +} + +/* ----------------------------------------------------------------------------- + * Power management + */ + +static int usb_dmac_runtime_suspend(struct device *dev) +{ + struct usb_dmac *dmac = dev_get_drvdata(dev); + int i; + + for (i = 0; i < dmac->n_channels; ++i) + usb_dmac_chan_halt(&dmac->channels[i]); + + return 0; +} + +static int usb_dmac_runtime_resume(struct device *dev) +{ + struct usb_dmac *dmac = dev_get_drvdata(dev); + + return usb_dmac_init(dmac); +} + +static const struct dev_pm_ops usb_dmac_pm = { + SET_RUNTIME_PM_OPS(usb_dmac_runtime_suspend, usb_dmac_runtime_resume, + NULL) +}; + +/* ----------------------------------------------------------------------------- + * Probe and remove + */ + +static int usb_dmac_chan_probe(struct usb_dmac *dmac, + struct usb_dmac_chan *uchan, + unsigned int index) +{ + struct platform_device *pdev = to_platform_device(dmac->dev); + char pdev_irqname[5]; + char *irqname; + int ret; + + uchan->index = index; + uchan->iomem = dmac->iomem + USB_DMAC_CHAN_OFFSET(index); + + /* Request the channel interrupt. */ + sprintf(pdev_irqname, "ch%u", index); + uchan->irq = platform_get_irq_byname(pdev, pdev_irqname); + if (uchan->irq < 0) { + dev_err(dmac->dev, "no IRQ specified for channel %u\n", index); + return -ENODEV; + } + + irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:%u", + dev_name(dmac->dev), index); + if (!irqname) + return -ENOMEM; + + ret = devm_request_irq(dmac->dev, uchan->irq, usb_dmac_isr_channel, + IRQF_SHARED, irqname, uchan); + if (ret) { + dev_err(dmac->dev, "failed to request IRQ %u (%d)\n", + uchan->irq, ret); + return ret; + } + + uchan->vc.desc_free = usb_dmac_virt_desc_free; + vchan_init(&uchan->vc, &dmac->engine); + INIT_LIST_HEAD(&uchan->desc_freed); + INIT_LIST_HEAD(&uchan->desc_got); + + return 0; +} + +static int usb_dmac_parse_of(struct device *dev, struct usb_dmac *dmac) +{ + struct device_node *np = dev->of_node; + int ret; + + ret = of_property_read_u32(np, "dma-channels", &dmac->n_channels); + if (ret < 0) { + dev_err(dev, "unable to read dma-channels property\n"); + return ret; + } + + if (dmac->n_channels <= 0 || dmac->n_channels >= 100) { + dev_err(dev, "invalid number of channels %u\n", + dmac->n_channels); + return -EINVAL; + } + + return 0; +} + +static int usb_dmac_probe(struct platform_device *pdev) +{ + const enum dma_slave_buswidth widths = USB_DMAC_SLAVE_BUSWIDTH; + struct dma_device *engine; + struct usb_dmac *dmac; + struct resource *mem; + unsigned int i; + int ret; + + dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL); + if (!dmac) + return -ENOMEM; + + dmac->dev = &pdev->dev; + platform_set_drvdata(pdev, dmac); + + ret = usb_dmac_parse_of(&pdev->dev, dmac); + if (ret < 0) + return ret; + + dmac->channels = devm_kcalloc(&pdev->dev, dmac->n_channels, + sizeof(*dmac->channels), GFP_KERNEL); + if (!dmac->channels) + return -ENOMEM; + + /* Request resources. */ + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + dmac->iomem = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(dmac->iomem)) + return PTR_ERR(dmac->iomem); + + /* Enable runtime PM and initialize the device. */ + pm_runtime_enable(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret); + return ret; + } + + ret = usb_dmac_init(dmac); + pm_runtime_put(&pdev->dev); + + if (ret) { + dev_err(&pdev->dev, "failed to reset device\n"); + goto error; + } + + /* Initialize the channels. */ + INIT_LIST_HEAD(&dmac->engine.channels); + + for (i = 0; i < dmac->n_channels; ++i) { + ret = usb_dmac_chan_probe(dmac, &dmac->channels[i], i); + if (ret < 0) + goto error; + } + + /* Register the DMAC as a DMA provider for DT. */ + ret = of_dma_controller_register(pdev->dev.of_node, usb_dmac_of_xlate, + NULL); + if (ret < 0) + goto error; + + /* + * Register the DMA engine device. + * + * Default transfer size of 32 bytes requires 32-byte alignment. + */ + engine = &dmac->engine; + dma_cap_set(DMA_SLAVE, engine->cap_mask); + + engine->dev = &pdev->dev; + + engine->src_addr_widths = widths; + engine->dst_addr_widths = widths; + engine->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); + engine->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST; + + engine->device_alloc_chan_resources = usb_dmac_alloc_chan_resources; + engine->device_free_chan_resources = usb_dmac_free_chan_resources; + engine->device_prep_slave_sg = usb_dmac_prep_slave_sg; + engine->device_terminate_all = usb_dmac_chan_terminate_all; + engine->device_tx_status = usb_dmac_tx_status; + engine->device_issue_pending = usb_dmac_issue_pending; + + ret = dma_async_device_register(engine); + if (ret < 0) + goto error; + + return 0; + +error: + of_dma_controller_free(pdev->dev.of_node); + pm_runtime_disable(&pdev->dev); + return ret; +} + +static void usb_dmac_chan_remove(struct usb_dmac *dmac, + struct usb_dmac_chan *uchan) +{ + usb_dmac_chan_halt(uchan); + devm_free_irq(dmac->dev, uchan->irq, uchan); +} + +static int usb_dmac_remove(struct platform_device *pdev) +{ + struct usb_dmac *dmac = platform_get_drvdata(pdev); + int i; + + for (i = 0; i < dmac->n_channels; ++i) + usb_dmac_chan_remove(dmac, &dmac->channels[i]); + of_dma_controller_free(pdev->dev.of_node); + dma_async_device_unregister(&dmac->engine); + + pm_runtime_disable(&pdev->dev); + + return 0; +} + +static void usb_dmac_shutdown(struct platform_device *pdev) +{ + struct usb_dmac *dmac = platform_get_drvdata(pdev); + + usb_dmac_stop(dmac); +} + +static const struct of_device_id usb_dmac_of_ids[] = { + { .compatible = "renesas,usb-dmac", }, + { /* Sentinel */ } +}; +MODULE_DEVICE_TABLE(of, usb_dmac_of_ids); + +static struct platform_driver usb_dmac_driver = { + .driver = { + .pm = &usb_dmac_pm, + .name = "usb-dmac", + .of_match_table = usb_dmac_of_ids, + }, + .probe = usb_dmac_probe, + .remove = usb_dmac_remove, + .shutdown = usb_dmac_shutdown, +}; + +module_platform_driver(usb_dmac_driver); + +MODULE_DESCRIPTION("Renesas USB DMA Controller Driver"); +MODULE_AUTHOR("Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c index d0086e9f2082..a1afda43b8ef 100644 --- a/drivers/dma/sirf-dma.c +++ b/drivers/dma/sirf-dma.c @@ -896,7 +896,7 @@ static const struct dev_pm_ops sirfsoc_dma_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(sirfsoc_dma_pm_suspend, sirfsoc_dma_pm_resume) }; -static struct of_device_id sirfsoc_dma_match[] = { +static const struct of_device_id sirfsoc_dma_match[] = { { .compatible = "sirf,prima2-dmac", }, { .compatible = "sirf,marco-dmac", }, {}, diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 1332b1d4d541..3c10f034d4b9 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -2514,7 +2514,8 @@ static struct dma_async_tx_descriptor *d40_prep_memcpy(struct dma_chan *chan, sg_dma_len(&dst_sg) = size; sg_dma_len(&src_sg) = size; - return d40_prep_sg(chan, &src_sg, &dst_sg, 1, DMA_NONE, dma_flags); + return d40_prep_sg(chan, &src_sg, &dst_sg, 1, + DMA_MEM_TO_MEM, dma_flags); } static struct dma_async_tx_descriptor * @@ -2526,7 +2527,8 @@ d40_prep_memcpy_sg(struct dma_chan *chan, if (dst_nents != src_nents) return NULL; - return d40_prep_sg(chan, src_sg, dst_sg, src_nents, DMA_NONE, dma_flags); + return d40_prep_sg(chan, src_sg, dst_sg, src_nents, + DMA_MEM_TO_MEM, dma_flags); } static struct dma_async_tx_descriptor * diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c index 7ebcf9bec698..11e536586812 100644 --- a/drivers/dma/sun6i-dma.c +++ b/drivers/dma/sun6i-dma.c @@ -796,11 +796,6 @@ static void sun6i_dma_issue_pending(struct dma_chan *chan) spin_unlock_irqrestore(&vchan->vc.lock, flags); } -static int sun6i_dma_alloc_chan_resources(struct dma_chan *chan) -{ - return 0; -} - static void sun6i_dma_free_chan_resources(struct dma_chan *chan) { struct sun6i_dma_dev *sdev = to_sun6i_dma_dev(chan->device); @@ -896,7 +891,7 @@ static struct sun6i_dma_config sun8i_a23_dma_cfg = { .nr_max_vchans = 37, }; -static struct of_device_id sun6i_dma_match[] = { +static const struct of_device_id sun6i_dma_match[] = { { .compatible = "allwinner,sun6i-a31-dma", .data = &sun6i_a31_dma_cfg }, { .compatible = "allwinner,sun8i-a23-dma", .data = &sun8i_a23_dma_cfg }, { /* sentinel */ } @@ -957,7 +952,6 @@ static int sun6i_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_SLAVE, sdc->slave.cap_mask); INIT_LIST_HEAD(&sdc->slave.channels); - sdc->slave.device_alloc_chan_resources = sun6i_dma_alloc_chan_resources; sdc->slave.device_free_chan_resources = sun6i_dma_free_chan_resources; sdc->slave.device_tx_status = sun6i_dma_tx_status; sdc->slave.device_issue_pending = sun6i_dma_issue_pending; diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c new file mode 100755 index 000000000000..f52e37502254 --- /dev/null +++ b/drivers/dma/xgene-dma.c @@ -0,0 +1,2089 @@ +/* + * Applied Micro X-Gene SoC DMA engine Driver + * + * Copyright (c) 2015, Applied Micro Circuits Corporation + * Authors: Rameshwar Prasad Sahu <rsahu@apm.com> + * Loc Ho <lho@apm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + * + * NOTE: PM support is currently not available. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/dmaengine.h> +#include <linux/dmapool.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_device.h> + +#include "dmaengine.h" + +/* X-Gene DMA ring csr registers and bit definations */ +#define XGENE_DMA_RING_CONFIG 0x04 +#define XGENE_DMA_RING_ENABLE BIT(31) +#define XGENE_DMA_RING_ID 0x08 +#define XGENE_DMA_RING_ID_SETUP(v) ((v) | BIT(31)) +#define XGENE_DMA_RING_ID_BUF 0x0C +#define XGENE_DMA_RING_ID_BUF_SETUP(v) (((v) << 9) | BIT(21)) +#define XGENE_DMA_RING_THRESLD0_SET1 0x30 +#define XGENE_DMA_RING_THRESLD0_SET1_VAL 0X64 +#define XGENE_DMA_RING_THRESLD1_SET1 0x34 +#define XGENE_DMA_RING_THRESLD1_SET1_VAL 0xC8 +#define XGENE_DMA_RING_HYSTERESIS 0x68 +#define XGENE_DMA_RING_HYSTERESIS_VAL 0xFFFFFFFF +#define XGENE_DMA_RING_STATE 0x6C +#define XGENE_DMA_RING_STATE_WR_BASE 0x70 +#define XGENE_DMA_RING_NE_INT_MODE 0x017C +#define XGENE_DMA_RING_NE_INT_MODE_SET(m, v) \ + ((m) = ((m) & ~BIT(31 - (v))) | BIT(31 - (v))) +#define XGENE_DMA_RING_NE_INT_MODE_RESET(m, v) \ + ((m) &= (~BIT(31 - (v)))) +#define XGENE_DMA_RING_CLKEN 0xC208 +#define XGENE_DMA_RING_SRST 0xC200 +#define XGENE_DMA_RING_MEM_RAM_SHUTDOWN 0xD070 +#define XGENE_DMA_RING_BLK_MEM_RDY 0xD074 +#define XGENE_DMA_RING_BLK_MEM_RDY_VAL 0xFFFFFFFF +#define XGENE_DMA_RING_DESC_CNT(v) (((v) & 0x0001FFFE) >> 1) +#define XGENE_DMA_RING_ID_GET(owner, num) (((owner) << 6) | (num)) +#define XGENE_DMA_RING_DST_ID(v) ((1 << 10) | (v)) +#define XGENE_DMA_RING_CMD_OFFSET 0x2C +#define XGENE_DMA_RING_CMD_BASE_OFFSET(v) ((v) << 6) +#define XGENE_DMA_RING_COHERENT_SET(m) \ + (((u32 *)(m))[2] |= BIT(4)) +#define XGENE_DMA_RING_ADDRL_SET(m, v) \ + (((u32 *)(m))[2] |= (((v) >> 8) << 5)) +#define XGENE_DMA_RING_ADDRH_SET(m, v) \ + (((u32 *)(m))[3] |= ((v) >> 35)) +#define XGENE_DMA_RING_ACCEPTLERR_SET(m) \ + (((u32 *)(m))[3] |= BIT(19)) +#define XGENE_DMA_RING_SIZE_SET(m, v) \ + (((u32 *)(m))[3] |= ((v) << 23)) +#define XGENE_DMA_RING_RECOMBBUF_SET(m) \ + (((u32 *)(m))[3] |= BIT(27)) +#define XGENE_DMA_RING_RECOMTIMEOUTL_SET(m) \ + (((u32 *)(m))[3] |= (0x7 << 28)) +#define XGENE_DMA_RING_RECOMTIMEOUTH_SET(m) \ + (((u32 *)(m))[4] |= 0x3) +#define XGENE_DMA_RING_SELTHRSH_SET(m) \ + (((u32 *)(m))[4] |= BIT(3)) +#define XGENE_DMA_RING_TYPE_SET(m, v) \ + (((u32 *)(m))[4] |= ((v) << 19)) + +/* X-Gene DMA device csr registers and bit definitions */ +#define XGENE_DMA_IPBRR 0x0 +#define XGENE_DMA_DEV_ID_RD(v) ((v) & 0x00000FFF) +#define XGENE_DMA_BUS_ID_RD(v) (((v) >> 12) & 3) +#define XGENE_DMA_REV_NO_RD(v) (((v) >> 14) & 3) +#define XGENE_DMA_GCR 0x10 +#define XGENE_DMA_CH_SETUP(v) \ + ((v) = ((v) & ~0x000FFFFF) | 0x000AAFFF) +#define XGENE_DMA_ENABLE(v) ((v) |= BIT(31)) +#define XGENE_DMA_DISABLE(v) ((v) &= ~BIT(31)) +#define XGENE_DMA_RAID6_CONT 0x14 +#define XGENE_DMA_RAID6_MULTI_CTRL(v) ((v) << 24) +#define XGENE_DMA_INT 0x70 +#define XGENE_DMA_INT_MASK 0x74 +#define XGENE_DMA_INT_ALL_MASK 0xFFFFFFFF +#define XGENE_DMA_INT_ALL_UNMASK 0x0 +#define XGENE_DMA_INT_MASK_SHIFT 0x14 +#define XGENE_DMA_RING_INT0_MASK 0x90A0 +#define XGENE_DMA_RING_INT1_MASK 0x90A8 +#define XGENE_DMA_RING_INT2_MASK 0x90B0 +#define XGENE_DMA_RING_INT3_MASK 0x90B8 +#define XGENE_DMA_RING_INT4_MASK 0x90C0 +#define XGENE_DMA_CFG_RING_WQ_ASSOC 0x90E0 +#define XGENE_DMA_ASSOC_RING_MNGR1 0xFFFFFFFF +#define XGENE_DMA_MEM_RAM_SHUTDOWN 0xD070 +#define XGENE_DMA_BLK_MEM_RDY 0xD074 +#define XGENE_DMA_BLK_MEM_RDY_VAL 0xFFFFFFFF + +/* X-Gene SoC EFUSE csr register and bit defination */ +#define XGENE_SOC_JTAG1_SHADOW 0x18 +#define XGENE_DMA_PQ_DISABLE_MASK BIT(13) + +/* X-Gene DMA Descriptor format */ +#define XGENE_DMA_DESC_NV_BIT BIT_ULL(50) +#define XGENE_DMA_DESC_IN_BIT BIT_ULL(55) +#define XGENE_DMA_DESC_C_BIT BIT_ULL(63) +#define XGENE_DMA_DESC_DR_BIT BIT_ULL(61) +#define XGENE_DMA_DESC_ELERR_POS 46 +#define XGENE_DMA_DESC_RTYPE_POS 56 +#define XGENE_DMA_DESC_LERR_POS 60 +#define XGENE_DMA_DESC_FLYBY_POS 4 +#define XGENE_DMA_DESC_BUFLEN_POS 48 +#define XGENE_DMA_DESC_HOENQ_NUM_POS 48 + +#define XGENE_DMA_DESC_NV_SET(m) \ + (((u64 *)(m))[0] |= XGENE_DMA_DESC_NV_BIT) +#define XGENE_DMA_DESC_IN_SET(m) \ + (((u64 *)(m))[0] |= XGENE_DMA_DESC_IN_BIT) +#define XGENE_DMA_DESC_RTYPE_SET(m, v) \ + (((u64 *)(m))[0] |= ((u64)(v) << XGENE_DMA_DESC_RTYPE_POS)) +#define XGENE_DMA_DESC_BUFADDR_SET(m, v) \ + (((u64 *)(m))[0] |= (v)) +#define XGENE_DMA_DESC_BUFLEN_SET(m, v) \ + (((u64 *)(m))[0] |= ((u64)(v) << XGENE_DMA_DESC_BUFLEN_POS)) +#define XGENE_DMA_DESC_C_SET(m) \ + (((u64 *)(m))[1] |= XGENE_DMA_DESC_C_BIT) +#define XGENE_DMA_DESC_FLYBY_SET(m, v) \ + (((u64 *)(m))[2] |= ((v) << XGENE_DMA_DESC_FLYBY_POS)) +#define XGENE_DMA_DESC_MULTI_SET(m, v, i) \ + (((u64 *)(m))[2] |= ((u64)(v) << (((i) + 1) * 8))) +#define XGENE_DMA_DESC_DR_SET(m) \ + (((u64 *)(m))[2] |= XGENE_DMA_DESC_DR_BIT) +#define XGENE_DMA_DESC_DST_ADDR_SET(m, v) \ + (((u64 *)(m))[3] |= (v)) +#define XGENE_DMA_DESC_H0ENQ_NUM_SET(m, v) \ + (((u64 *)(m))[3] |= ((u64)(v) << XGENE_DMA_DESC_HOENQ_NUM_POS)) +#define XGENE_DMA_DESC_ELERR_RD(m) \ + (((m) >> XGENE_DMA_DESC_ELERR_POS) & 0x3) +#define XGENE_DMA_DESC_LERR_RD(m) \ + (((m) >> XGENE_DMA_DESC_LERR_POS) & 0x7) +#define XGENE_DMA_DESC_STATUS(elerr, lerr) \ + (((elerr) << 4) | (lerr)) + +/* X-Gene DMA descriptor empty s/w signature */ +#define XGENE_DMA_DESC_EMPTY_INDEX 0 +#define XGENE_DMA_DESC_EMPTY_SIGNATURE ~0ULL +#define XGENE_DMA_DESC_SET_EMPTY(m) \ + (((u64 *)(m))[XGENE_DMA_DESC_EMPTY_INDEX] = \ + XGENE_DMA_DESC_EMPTY_SIGNATURE) +#define XGENE_DMA_DESC_IS_EMPTY(m) \ + (((u64 *)(m))[XGENE_DMA_DESC_EMPTY_INDEX] == \ + XGENE_DMA_DESC_EMPTY_SIGNATURE) + +/* X-Gene DMA configurable parameters defines */ +#define XGENE_DMA_RING_NUM 512 +#define XGENE_DMA_BUFNUM 0x0 +#define XGENE_DMA_CPU_BUFNUM 0x18 +#define XGENE_DMA_RING_OWNER_DMA 0x03 +#define XGENE_DMA_RING_OWNER_CPU 0x0F +#define XGENE_DMA_RING_TYPE_REGULAR 0x01 +#define XGENE_DMA_RING_WQ_DESC_SIZE 32 /* 32 Bytes */ +#define XGENE_DMA_RING_NUM_CONFIG 5 +#define XGENE_DMA_MAX_CHANNEL 4 +#define XGENE_DMA_XOR_CHANNEL 0 +#define XGENE_DMA_PQ_CHANNEL 1 +#define XGENE_DMA_MAX_BYTE_CNT 0x4000 /* 16 KB */ +#define XGENE_DMA_MAX_64B_DESC_BYTE_CNT 0x14000 /* 80 KB */ +#define XGENE_DMA_XOR_ALIGNMENT 6 /* 64 Bytes */ +#define XGENE_DMA_MAX_XOR_SRC 5 +#define XGENE_DMA_16K_BUFFER_LEN_CODE 0x0 +#define XGENE_DMA_INVALID_LEN_CODE 0x7800 + +/* X-Gene DMA descriptor error codes */ +#define ERR_DESC_AXI 0x01 +#define ERR_BAD_DESC 0x02 +#define ERR_READ_DATA_AXI 0x03 +#define ERR_WRITE_DATA_AXI 0x04 +#define ERR_FBP_TIMEOUT 0x05 +#define ERR_ECC 0x06 +#define ERR_DIFF_SIZE 0x08 +#define ERR_SCT_GAT_LEN 0x09 +#define ERR_CRC_ERR 0x11 +#define ERR_CHKSUM 0x12 +#define ERR_DIF 0x13 + +/* X-Gene DMA error interrupt codes */ +#define ERR_DIF_SIZE_INT 0x0 +#define ERR_GS_ERR_INT 0x1 +#define ERR_FPB_TIMEO_INT 0x2 +#define ERR_WFIFO_OVF_INT 0x3 +#define ERR_RFIFO_OVF_INT 0x4 +#define ERR_WR_TIMEO_INT 0x5 +#define ERR_RD_TIMEO_INT 0x6 +#define ERR_WR_ERR_INT 0x7 +#define ERR_RD_ERR_INT 0x8 +#define ERR_BAD_DESC_INT 0x9 +#define ERR_DESC_DST_INT 0xA +#define ERR_DESC_SRC_INT 0xB + +/* X-Gene DMA flyby operation code */ +#define FLYBY_2SRC_XOR 0x8 +#define FLYBY_3SRC_XOR 0x9 +#define FLYBY_4SRC_XOR 0xA +#define FLYBY_5SRC_XOR 0xB + +/* X-Gene DMA SW descriptor flags */ +#define XGENE_DMA_FLAG_64B_DESC BIT(0) + +/* Define to dump X-Gene DMA descriptor */ +#define XGENE_DMA_DESC_DUMP(desc, m) \ + print_hex_dump(KERN_ERR, (m), \ + DUMP_PREFIX_ADDRESS, 16, 8, (desc), 32, 0) + +#define to_dma_desc_sw(tx) \ + container_of(tx, struct xgene_dma_desc_sw, tx) +#define to_dma_chan(dchan) \ + container_of(dchan, struct xgene_dma_chan, dma_chan) + +#define chan_dbg(chan, fmt, arg...) \ + dev_dbg(chan->dev, "%s: " fmt, chan->name, ##arg) +#define chan_err(chan, fmt, arg...) \ + dev_err(chan->dev, "%s: " fmt, chan->name, ##arg) + +struct xgene_dma_desc_hw { + u64 m0; + u64 m1; + u64 m2; + u64 m3; +}; + +enum xgene_dma_ring_cfgsize { + XGENE_DMA_RING_CFG_SIZE_512B, + XGENE_DMA_RING_CFG_SIZE_2KB, + XGENE_DMA_RING_CFG_SIZE_16KB, + XGENE_DMA_RING_CFG_SIZE_64KB, + XGENE_DMA_RING_CFG_SIZE_512KB, + XGENE_DMA_RING_CFG_SIZE_INVALID +}; + +struct xgene_dma_ring { + struct xgene_dma *pdma; + u8 buf_num; + u16 id; + u16 num; + u16 head; + u16 owner; + u16 slots; + u16 dst_ring_num; + u32 size; + void __iomem *cmd; + void __iomem *cmd_base; + dma_addr_t desc_paddr; + u32 state[XGENE_DMA_RING_NUM_CONFIG]; + enum xgene_dma_ring_cfgsize cfgsize; + union { + void *desc_vaddr; + struct xgene_dma_desc_hw *desc_hw; + }; +}; + +struct xgene_dma_desc_sw { + struct xgene_dma_desc_hw desc1; + struct xgene_dma_desc_hw desc2; + u32 flags; + struct list_head node; + struct list_head tx_list; + struct dma_async_tx_descriptor tx; +}; + +/** + * struct xgene_dma_chan - internal representation of an X-Gene DMA channel + * @dma_chan: dmaengine channel object member + * @pdma: X-Gene DMA device structure reference + * @dev: struct device reference for dma mapping api + * @id: raw id of this channel + * @rx_irq: channel IRQ + * @name: name of X-Gene DMA channel + * @lock: serializes enqueue/dequeue operations to the descriptor pool + * @pending: number of transaction request pushed to DMA controller for + * execution, but still waiting for completion, + * @max_outstanding: max number of outstanding request we can push to channel + * @ld_pending: descriptors which are queued to run, but have not yet been + * submitted to the hardware for execution + * @ld_running: descriptors which are currently being executing by the hardware + * @ld_completed: descriptors which have finished execution by the hardware. + * These descriptors have already had their cleanup actions run. They + * are waiting for the ACK bit to be set by the async tx API. + * @desc_pool: descriptor pool for DMA operations + * @tasklet: bottom half where all completed descriptors cleans + * @tx_ring: transmit ring descriptor that we use to prepare actual + * descriptors for further executions + * @rx_ring: receive ring descriptor that we use to get completed DMA + * descriptors during cleanup time + */ +struct xgene_dma_chan { + struct dma_chan dma_chan; + struct xgene_dma *pdma; + struct device *dev; + int id; + int rx_irq; + char name[10]; + spinlock_t lock; + int pending; + int max_outstanding; + struct list_head ld_pending; + struct list_head ld_running; + struct list_head ld_completed; + struct dma_pool *desc_pool; + struct tasklet_struct tasklet; + struct xgene_dma_ring tx_ring; + struct xgene_dma_ring rx_ring; +}; + +/** + * struct xgene_dma - internal representation of an X-Gene DMA device + * @err_irq: DMA error irq number + * @ring_num: start id number for DMA ring + * @csr_dma: base for DMA register access + * @csr_ring: base for DMA ring register access + * @csr_ring_cmd: base for DMA ring command register access + * @csr_efuse: base for efuse register access + * @dma_dev: embedded struct dma_device + * @chan: reference to X-Gene DMA channels + */ +struct xgene_dma { + struct device *dev; + struct clk *clk; + int err_irq; + int ring_num; + void __iomem *csr_dma; + void __iomem *csr_ring; + void __iomem *csr_ring_cmd; + void __iomem *csr_efuse; + struct dma_device dma_dev[XGENE_DMA_MAX_CHANNEL]; + struct xgene_dma_chan chan[XGENE_DMA_MAX_CHANNEL]; +}; + +static const char * const xgene_dma_desc_err[] = { + [ERR_DESC_AXI] = "AXI error when reading src/dst link list", + [ERR_BAD_DESC] = "ERR or El_ERR fields not set to zero in desc", + [ERR_READ_DATA_AXI] = "AXI error when reading data", + [ERR_WRITE_DATA_AXI] = "AXI error when writing data", + [ERR_FBP_TIMEOUT] = "Timeout on bufpool fetch", + [ERR_ECC] = "ECC double bit error", + [ERR_DIFF_SIZE] = "Bufpool too small to hold all the DIF result", + [ERR_SCT_GAT_LEN] = "Gather and scatter data length not same", + [ERR_CRC_ERR] = "CRC error", + [ERR_CHKSUM] = "Checksum error", + [ERR_DIF] = "DIF error", +}; + +static const char * const xgene_dma_err[] = { + [ERR_DIF_SIZE_INT] = "DIF size error", + [ERR_GS_ERR_INT] = "Gather scatter not same size error", + [ERR_FPB_TIMEO_INT] = "Free pool time out error", + [ERR_WFIFO_OVF_INT] = "Write FIFO over flow error", + [ERR_RFIFO_OVF_INT] = "Read FIFO over flow error", + [ERR_WR_TIMEO_INT] = "Write time out error", + [ERR_RD_TIMEO_INT] = "Read time out error", + [ERR_WR_ERR_INT] = "HBF bus write error", + [ERR_RD_ERR_INT] = "HBF bus read error", + [ERR_BAD_DESC_INT] = "Ring descriptor HE0 not set error", + [ERR_DESC_DST_INT] = "HFB reading dst link address error", + [ERR_DESC_SRC_INT] = "HFB reading src link address error", +}; + +static bool is_pq_enabled(struct xgene_dma *pdma) +{ + u32 val; + + val = ioread32(pdma->csr_efuse + XGENE_SOC_JTAG1_SHADOW); + return !(val & XGENE_DMA_PQ_DISABLE_MASK); +} + +static void xgene_dma_cpu_to_le64(u64 *desc, int count) +{ + int i; + + for (i = 0; i < count; i++) + desc[i] = cpu_to_le64(desc[i]); +} + +static u16 xgene_dma_encode_len(u32 len) +{ + return (len < XGENE_DMA_MAX_BYTE_CNT) ? + len : XGENE_DMA_16K_BUFFER_LEN_CODE; +} + +static u8 xgene_dma_encode_xor_flyby(u32 src_cnt) +{ + static u8 flyby_type[] = { + FLYBY_2SRC_XOR, /* Dummy */ + FLYBY_2SRC_XOR, /* Dummy */ + FLYBY_2SRC_XOR, + FLYBY_3SRC_XOR, + FLYBY_4SRC_XOR, + FLYBY_5SRC_XOR + }; + + return flyby_type[src_cnt]; +} + +static u32 xgene_dma_ring_desc_cnt(struct xgene_dma_ring *ring) +{ + u32 __iomem *cmd_base = ring->cmd_base; + u32 ring_state = ioread32(&cmd_base[1]); + + return XGENE_DMA_RING_DESC_CNT(ring_state); +} + +static void xgene_dma_set_src_buffer(void *ext8, size_t *len, + dma_addr_t *paddr) +{ + size_t nbytes = (*len < XGENE_DMA_MAX_BYTE_CNT) ? + *len : XGENE_DMA_MAX_BYTE_CNT; + + XGENE_DMA_DESC_BUFADDR_SET(ext8, *paddr); + XGENE_DMA_DESC_BUFLEN_SET(ext8, xgene_dma_encode_len(nbytes)); + *len -= nbytes; + *paddr += nbytes; +} + +static void xgene_dma_invalidate_buffer(void *ext8) +{ + XGENE_DMA_DESC_BUFLEN_SET(ext8, XGENE_DMA_INVALID_LEN_CODE); +} + +static void *xgene_dma_lookup_ext8(u64 *desc, int idx) +{ + return (idx % 2) ? (desc + idx - 1) : (desc + idx + 1); +} + +static void xgene_dma_init_desc(void *desc, u16 dst_ring_num) +{ + XGENE_DMA_DESC_C_SET(desc); /* Coherent IO */ + XGENE_DMA_DESC_IN_SET(desc); + XGENE_DMA_DESC_H0ENQ_NUM_SET(desc, dst_ring_num); + XGENE_DMA_DESC_RTYPE_SET(desc, XGENE_DMA_RING_OWNER_DMA); +} + +static void xgene_dma_prep_cpy_desc(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc_sw, + dma_addr_t dst, dma_addr_t src, + size_t len) +{ + void *desc1, *desc2; + int i; + + /* Get 1st descriptor */ + desc1 = &desc_sw->desc1; + xgene_dma_init_desc(desc1, chan->tx_ring.dst_ring_num); + + /* Set destination address */ + XGENE_DMA_DESC_DR_SET(desc1); + XGENE_DMA_DESC_DST_ADDR_SET(desc1, dst); + + /* Set 1st source address */ + xgene_dma_set_src_buffer(desc1 + 8, &len, &src); + + if (len <= 0) { + desc2 = NULL; + goto skip_additional_src; + } + + /* + * We need to split this source buffer, + * and need to use 2nd descriptor + */ + desc2 = &desc_sw->desc2; + XGENE_DMA_DESC_NV_SET(desc1); + + /* Set 2nd to 5th source address */ + for (i = 0; i < 4 && len; i++) + xgene_dma_set_src_buffer(xgene_dma_lookup_ext8(desc2, i), + &len, &src); + + /* Invalidate unused source address field */ + for (; i < 4; i++) + xgene_dma_invalidate_buffer(xgene_dma_lookup_ext8(desc2, i)); + + /* Updated flag that we have prepared 64B descriptor */ + desc_sw->flags |= XGENE_DMA_FLAG_64B_DESC; + +skip_additional_src: + /* Hardware stores descriptor in little endian format */ + xgene_dma_cpu_to_le64(desc1, 4); + if (desc2) + xgene_dma_cpu_to_le64(desc2, 4); +} + +static void xgene_dma_prep_xor_desc(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc_sw, + dma_addr_t *dst, dma_addr_t *src, + u32 src_cnt, size_t *nbytes, + const u8 *scf) +{ + void *desc1, *desc2; + size_t len = *nbytes; + int i; + + desc1 = &desc_sw->desc1; + desc2 = &desc_sw->desc2; + + /* Initialize DMA descriptor */ + xgene_dma_init_desc(desc1, chan->tx_ring.dst_ring_num); + + /* Set destination address */ + XGENE_DMA_DESC_DR_SET(desc1); + XGENE_DMA_DESC_DST_ADDR_SET(desc1, *dst); + + /* We have multiple source addresses, so need to set NV bit*/ + XGENE_DMA_DESC_NV_SET(desc1); + + /* Set flyby opcode */ + XGENE_DMA_DESC_FLYBY_SET(desc1, xgene_dma_encode_xor_flyby(src_cnt)); + + /* Set 1st to 5th source addresses */ + for (i = 0; i < src_cnt; i++) { + len = *nbytes; + xgene_dma_set_src_buffer((i == 0) ? (desc1 + 8) : + xgene_dma_lookup_ext8(desc2, i - 1), + &len, &src[i]); + XGENE_DMA_DESC_MULTI_SET(desc1, scf[i], i); + } + + /* Hardware stores descriptor in little endian format */ + xgene_dma_cpu_to_le64(desc1, 4); + xgene_dma_cpu_to_le64(desc2, 4); + + /* Update meta data */ + *nbytes = len; + *dst += XGENE_DMA_MAX_BYTE_CNT; + + /* We need always 64B descriptor to perform xor or pq operations */ + desc_sw->flags |= XGENE_DMA_FLAG_64B_DESC; +} + +static dma_cookie_t xgene_dma_tx_submit(struct dma_async_tx_descriptor *tx) +{ + struct xgene_dma_desc_sw *desc; + struct xgene_dma_chan *chan; + dma_cookie_t cookie; + + if (unlikely(!tx)) + return -EINVAL; + + chan = to_dma_chan(tx->chan); + desc = to_dma_desc_sw(tx); + + spin_lock_bh(&chan->lock); + + cookie = dma_cookie_assign(tx); + + /* Add this transaction list onto the tail of the pending queue */ + list_splice_tail_init(&desc->tx_list, &chan->ld_pending); + + spin_unlock_bh(&chan->lock); + + return cookie; +} + +static void xgene_dma_clean_descriptor(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc) +{ + list_del(&desc->node); + chan_dbg(chan, "LD %p free\n", desc); + dma_pool_free(chan->desc_pool, desc, desc->tx.phys); +} + +static struct xgene_dma_desc_sw *xgene_dma_alloc_descriptor( + struct xgene_dma_chan *chan) +{ + struct xgene_dma_desc_sw *desc; + dma_addr_t phys; + + desc = dma_pool_alloc(chan->desc_pool, GFP_NOWAIT, &phys); + if (!desc) { + chan_err(chan, "Failed to allocate LDs\n"); + return NULL; + } + + memset(desc, 0, sizeof(*desc)); + + INIT_LIST_HEAD(&desc->tx_list); + desc->tx.phys = phys; + desc->tx.tx_submit = xgene_dma_tx_submit; + dma_async_tx_descriptor_init(&desc->tx, &chan->dma_chan); + + chan_dbg(chan, "LD %p allocated\n", desc); + + return desc; +} + +/** + * xgene_dma_clean_completed_descriptor - free all descriptors which + * has been completed and acked + * @chan: X-Gene DMA channel + * + * This function is used on all completed and acked descriptors. + */ +static void xgene_dma_clean_completed_descriptor(struct xgene_dma_chan *chan) +{ + struct xgene_dma_desc_sw *desc, *_desc; + + /* Run the callback for each descriptor, in order */ + list_for_each_entry_safe(desc, _desc, &chan->ld_completed, node) { + if (async_tx_test_ack(&desc->tx)) + xgene_dma_clean_descriptor(chan, desc); + } +} + +/** + * xgene_dma_run_tx_complete_actions - cleanup a single link descriptor + * @chan: X-Gene DMA channel + * @desc: descriptor to cleanup and free + * + * This function is used on a descriptor which has been executed by the DMA + * controller. It will run any callbacks, submit any dependencies. + */ +static void xgene_dma_run_tx_complete_actions(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc) +{ + struct dma_async_tx_descriptor *tx = &desc->tx; + + /* + * If this is not the last transaction in the group, + * then no need to complete cookie and run any callback as + * this is not the tx_descriptor which had been sent to caller + * of this DMA request + */ + + if (tx->cookie == 0) + return; + + dma_cookie_complete(tx); + + /* Run the link descriptor callback function */ + if (tx->callback) + tx->callback(tx->callback_param); + + dma_descriptor_unmap(tx); + + /* Run any dependencies */ + dma_run_dependencies(tx); +} + +/** + * xgene_dma_clean_running_descriptor - move the completed descriptor from + * ld_running to ld_completed + * @chan: X-Gene DMA channel + * @desc: the descriptor which is completed + * + * Free the descriptor directly if acked by async_tx api, + * else move it to queue ld_completed. + */ +static void xgene_dma_clean_running_descriptor(struct xgene_dma_chan *chan, + struct xgene_dma_desc_sw *desc) +{ + /* Remove from the list of running transactions */ + list_del(&desc->node); + + /* + * the client is allowed to attach dependent operations + * until 'ack' is set + */ + if (!async_tx_test_ack(&desc->tx)) { + /* + * Move this descriptor to the list of descriptors which is + * completed, but still awaiting the 'ack' bit to be set. + */ + list_add_tail(&desc->node, &chan->ld_completed); + return; + } + + chan_dbg(chan, "LD %p free\n", desc); + dma_pool_free(chan->desc_pool, desc, desc->tx.phys); +} + +static int xgene_chan_xfer_request(struct xgene_dma_ring *ring, + struct xgene_dma_desc_sw *desc_sw) +{ + struct xgene_dma_desc_hw *desc_hw; + + /* Check if can push more descriptor to hw for execution */ + if (xgene_dma_ring_desc_cnt(ring) > (ring->slots - 2)) + return -EBUSY; + + /* Get hw descriptor from DMA tx ring */ + desc_hw = &ring->desc_hw[ring->head]; + + /* + * Increment the head count to point next + * descriptor for next time + */ + if (++ring->head == ring->slots) + ring->head = 0; + + /* Copy prepared sw descriptor data to hw descriptor */ + memcpy(desc_hw, &desc_sw->desc1, sizeof(*desc_hw)); + + /* + * Check if we have prepared 64B descriptor, + * in this case we need one more hw descriptor + */ + if (desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) { + desc_hw = &ring->desc_hw[ring->head]; + + if (++ring->head == ring->slots) + ring->head = 0; + + memcpy(desc_hw, &desc_sw->desc2, sizeof(*desc_hw)); + } + + /* Notify the hw that we have descriptor ready for execution */ + iowrite32((desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) ? + 2 : 1, ring->cmd); + + return 0; +} + +/** + * xgene_chan_xfer_ld_pending - push any pending transactions to hw + * @chan : X-Gene DMA channel + * + * LOCKING: must hold chan->desc_lock + */ +static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan) +{ + struct xgene_dma_desc_sw *desc_sw, *_desc_sw; + int ret; + + /* + * If the list of pending descriptors is empty, then we + * don't need to do any work at all + */ + if (list_empty(&chan->ld_pending)) { + chan_dbg(chan, "No pending LDs\n"); + return; + } + + /* + * Move elements from the queue of pending transactions onto the list + * of running transactions and push it to hw for further executions + */ + list_for_each_entry_safe(desc_sw, _desc_sw, &chan->ld_pending, node) { + /* + * Check if have pushed max number of transactions to hw + * as capable, so let's stop here and will push remaining + * elements from pening ld queue after completing some + * descriptors that we have already pushed + */ + if (chan->pending >= chan->max_outstanding) + return; + + ret = xgene_chan_xfer_request(&chan->tx_ring, desc_sw); + if (ret) + return; + + /* + * Delete this element from ld pending queue and append it to + * ld running queue + */ + list_move_tail(&desc_sw->node, &chan->ld_running); + + /* Increment the pending transaction count */ + chan->pending++; + } +} + +/** + * xgene_dma_cleanup_descriptors - cleanup link descriptors which are completed + * and move them to ld_completed to free until flag 'ack' is set + * @chan: X-Gene DMA channel + * + * This function is used on descriptors which have been executed by the DMA + * controller. It will run any callbacks, submit any dependencies, then + * free these descriptors if flag 'ack' is set. + */ +static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan) +{ + struct xgene_dma_ring *ring = &chan->rx_ring; + struct xgene_dma_desc_sw *desc_sw, *_desc_sw; + struct xgene_dma_desc_hw *desc_hw; + u8 status; + + /* Clean already completed and acked descriptors */ + xgene_dma_clean_completed_descriptor(chan); + + /* Run the callback for each descriptor, in order */ + list_for_each_entry_safe(desc_sw, _desc_sw, &chan->ld_running, node) { + /* Get subsequent hw descriptor from DMA rx ring */ + desc_hw = &ring->desc_hw[ring->head]; + + /* Check if this descriptor has been completed */ + if (unlikely(XGENE_DMA_DESC_IS_EMPTY(desc_hw))) + break; + + if (++ring->head == ring->slots) + ring->head = 0; + + /* Check if we have any error with DMA transactions */ + status = XGENE_DMA_DESC_STATUS( + XGENE_DMA_DESC_ELERR_RD(le64_to_cpu( + desc_hw->m0)), + XGENE_DMA_DESC_LERR_RD(le64_to_cpu( + desc_hw->m0))); + if (status) { + /* Print the DMA error type */ + chan_err(chan, "%s\n", xgene_dma_desc_err[status]); + + /* + * We have DMA transactions error here. Dump DMA Tx + * and Rx descriptors for this request */ + XGENE_DMA_DESC_DUMP(&desc_sw->desc1, + "X-Gene DMA TX DESC1: "); + + if (desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) + XGENE_DMA_DESC_DUMP(&desc_sw->desc2, + "X-Gene DMA TX DESC2: "); + + XGENE_DMA_DESC_DUMP(desc_hw, + "X-Gene DMA RX ERR DESC: "); + } + + /* Notify the hw about this completed descriptor */ + iowrite32(-1, ring->cmd); + + /* Mark this hw descriptor as processed */ + XGENE_DMA_DESC_SET_EMPTY(desc_hw); + + xgene_dma_run_tx_complete_actions(chan, desc_sw); + + xgene_dma_clean_running_descriptor(chan, desc_sw); + + /* + * Decrement the pending transaction count + * as we have processed one + */ + chan->pending--; + } + + /* + * Start any pending transactions automatically + * In the ideal case, we keep the DMA controller busy while we go + * ahead and free the descriptors below. + */ + xgene_chan_xfer_ld_pending(chan); +} + +static int xgene_dma_alloc_chan_resources(struct dma_chan *dchan) +{ + struct xgene_dma_chan *chan = to_dma_chan(dchan); + + /* Has this channel already been allocated? */ + if (chan->desc_pool) + return 1; + + chan->desc_pool = dma_pool_create(chan->name, chan->dev, + sizeof(struct xgene_dma_desc_sw), + 0, 0); + if (!chan->desc_pool) { + chan_err(chan, "Failed to allocate descriptor pool\n"); + return -ENOMEM; + } + + chan_dbg(chan, "Allocate descripto pool\n"); + + return 1; +} + +/** + * xgene_dma_free_desc_list - Free all descriptors in a queue + * @chan: X-Gene DMA channel + * @list: the list to free + * + * LOCKING: must hold chan->desc_lock + */ +static void xgene_dma_free_desc_list(struct xgene_dma_chan *chan, + struct list_head *list) +{ + struct xgene_dma_desc_sw *desc, *_desc; + + list_for_each_entry_safe(desc, _desc, list, node) + xgene_dma_clean_descriptor(chan, desc); +} + +static void xgene_dma_free_tx_desc_list(struct xgene_dma_chan *chan, + struct list_head *list) +{ + struct xgene_dma_desc_sw *desc, *_desc; + + list_for_each_entry_safe(desc, _desc, list, node) + xgene_dma_clean_descriptor(chan, desc); +} + +static void xgene_dma_free_chan_resources(struct dma_chan *dchan) +{ + struct xgene_dma_chan *chan = to_dma_chan(dchan); + + chan_dbg(chan, "Free all resources\n"); + + if (!chan->desc_pool) + return; + + spin_lock_bh(&chan->lock); + + /* Process all running descriptor */ + xgene_dma_cleanup_descriptors(chan); + + /* Clean all link descriptor queues */ + xgene_dma_free_desc_list(chan, &chan->ld_pending); + xgene_dma_free_desc_list(chan, &chan->ld_running); + xgene_dma_free_desc_list(chan, &chan->ld_completed); + + spin_unlock_bh(&chan->lock); + + /* Delete this channel DMA pool */ + dma_pool_destroy(chan->desc_pool); + chan->desc_pool = NULL; +} + +static struct dma_async_tx_descriptor *xgene_dma_prep_memcpy( + struct dma_chan *dchan, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags) +{ + struct xgene_dma_desc_sw *first = NULL, *new; + struct xgene_dma_chan *chan; + size_t copy; + + if (unlikely(!dchan || !len)) + return NULL; + + chan = to_dma_chan(dchan); + + do { + /* Allocate the link descriptor from DMA pool */ + new = xgene_dma_alloc_descriptor(chan); + if (!new) + goto fail; + + /* Create the largest transaction possible */ + copy = min_t(size_t, len, XGENE_DMA_MAX_64B_DESC_BYTE_CNT); + + /* Prepare DMA descriptor */ + xgene_dma_prep_cpy_desc(chan, new, dst, src, copy); + + if (!first) + first = new; + + new->tx.cookie = 0; + async_tx_ack(&new->tx); + + /* Update metadata */ + len -= copy; + dst += copy; + src += copy; + + /* Insert the link descriptor to the LD ring */ + list_add_tail(&new->node, &first->tx_list); + } while (len); + + new->tx.flags = flags; /* client is in control of this ack */ + new->tx.cookie = -EBUSY; + list_splice(&first->tx_list, &new->tx_list); + + return &new->tx; + +fail: + if (!first) + return NULL; + + xgene_dma_free_tx_desc_list(chan, &first->tx_list); + return NULL; +} + +static struct dma_async_tx_descriptor *xgene_dma_prep_sg( + struct dma_chan *dchan, struct scatterlist *dst_sg, + u32 dst_nents, struct scatterlist *src_sg, + u32 src_nents, unsigned long flags) +{ + struct xgene_dma_desc_sw *first = NULL, *new = NULL; + struct xgene_dma_chan *chan; + size_t dst_avail, src_avail; + dma_addr_t dst, src; + size_t len; + + if (unlikely(!dchan)) + return NULL; + + if (unlikely(!dst_nents || !src_nents)) + return NULL; + + if (unlikely(!dst_sg || !src_sg)) + return NULL; + + chan = to_dma_chan(dchan); + + /* Get prepared for the loop */ + dst_avail = sg_dma_len(dst_sg); + src_avail = sg_dma_len(src_sg); + dst_nents--; + src_nents--; + + /* Run until we are out of scatterlist entries */ + while (true) { + /* Create the largest transaction possible */ + len = min_t(size_t, src_avail, dst_avail); + len = min_t(size_t, len, XGENE_DMA_MAX_64B_DESC_BYTE_CNT); + if (len == 0) + goto fetch; + + dst = sg_dma_address(dst_sg) + sg_dma_len(dst_sg) - dst_avail; + src = sg_dma_address(src_sg) + sg_dma_len(src_sg) - src_avail; + + /* Allocate the link descriptor from DMA pool */ + new = xgene_dma_alloc_descriptor(chan); + if (!new) + goto fail; + + /* Prepare DMA descriptor */ + xgene_dma_prep_cpy_desc(chan, new, dst, src, len); + + if (!first) + first = new; + + new->tx.cookie = 0; + async_tx_ack(&new->tx); + + /* update metadata */ + dst_avail -= len; + src_avail -= len; + + /* Insert the link descriptor to the LD ring */ + list_add_tail(&new->node, &first->tx_list); + +fetch: + /* fetch the next dst scatterlist entry */ + if (dst_avail == 0) { + /* no more entries: we're done */ + if (dst_nents == 0) + break; + + /* fetch the next entry: if there are no more: done */ + dst_sg = sg_next(dst_sg); + if (!dst_sg) + break; + + dst_nents--; + dst_avail = sg_dma_len(dst_sg); + } + + /* fetch the next src scatterlist entry */ + if (src_avail == 0) { + /* no more entries: we're done */ + if (src_nents == 0) + break; + + /* fetch the next entry: if there are no more: done */ + src_sg = sg_next(src_sg); + if (!src_sg) + break; + + src_nents--; + src_avail = sg_dma_len(src_sg); + } + } + + if (!new) + return NULL; + + new->tx.flags = flags; /* client is in control of this ack */ + new->tx.cookie = -EBUSY; + list_splice(&first->tx_list, &new->tx_list); + + return &new->tx; +fail: + if (!first) + return NULL; + + xgene_dma_free_tx_desc_list(chan, &first->tx_list); + return NULL; +} + +static struct dma_async_tx_descriptor *xgene_dma_prep_xor( + struct dma_chan *dchan, dma_addr_t dst, dma_addr_t *src, + u32 src_cnt, size_t len, unsigned long flags) +{ + struct xgene_dma_desc_sw *first = NULL, *new; + struct xgene_dma_chan *chan; + static u8 multi[XGENE_DMA_MAX_XOR_SRC] = { + 0x01, 0x01, 0x01, 0x01, 0x01}; + + if (unlikely(!dchan || !len)) + return NULL; + + chan = to_dma_chan(dchan); + + do { + /* Allocate the link descriptor from DMA pool */ + new = xgene_dma_alloc_descriptor(chan); + if (!new) + goto fail; + + /* Prepare xor DMA descriptor */ + xgene_dma_prep_xor_desc(chan, new, &dst, src, + src_cnt, &len, multi); + + if (!first) + first = new; + + new->tx.cookie = 0; + async_tx_ack(&new->tx); + + /* Insert the link descriptor to the LD ring */ + list_add_tail(&new->node, &first->tx_list); + } while (len); + + new->tx.flags = flags; /* client is in control of this ack */ + new->tx.cookie = -EBUSY; + list_splice(&first->tx_list, &new->tx_list); + + return &new->tx; + +fail: + if (!first) + return NULL; + + xgene_dma_free_tx_desc_list(chan, &first->tx_list); + return NULL; +} + +static struct dma_async_tx_descriptor *xgene_dma_prep_pq( + struct dma_chan *dchan, dma_addr_t *dst, dma_addr_t *src, + u32 src_cnt, const u8 *scf, size_t len, unsigned long flags) +{ + struct xgene_dma_desc_sw *first = NULL, *new; + struct xgene_dma_chan *chan; + size_t _len = len; + dma_addr_t _src[XGENE_DMA_MAX_XOR_SRC]; + static u8 multi[XGENE_DMA_MAX_XOR_SRC] = {0x01, 0x01, 0x01, 0x01, 0x01}; + + if (unlikely(!dchan || !len)) + return NULL; + + chan = to_dma_chan(dchan); + + /* + * Save source addresses on local variable, may be we have to + * prepare two descriptor to generate P and Q if both enabled + * in the flags by client + */ + memcpy(_src, src, sizeof(*src) * src_cnt); + + if (flags & DMA_PREP_PQ_DISABLE_P) + len = 0; + + if (flags & DMA_PREP_PQ_DISABLE_Q) + _len = 0; + + do { + /* Allocate the link descriptor from DMA pool */ + new = xgene_dma_alloc_descriptor(chan); + if (!new) + goto fail; + + if (!first) + first = new; + + new->tx.cookie = 0; + async_tx_ack(&new->tx); + + /* Insert the link descriptor to the LD ring */ + list_add_tail(&new->node, &first->tx_list); + + /* + * Prepare DMA descriptor to generate P, + * if DMA_PREP_PQ_DISABLE_P flag is not set + */ + if (len) { + xgene_dma_prep_xor_desc(chan, new, &dst[0], src, + src_cnt, &len, multi); + continue; + } + + /* + * Prepare DMA descriptor to generate Q, + * if DMA_PREP_PQ_DISABLE_Q flag is not set + */ + if (_len) { + xgene_dma_prep_xor_desc(chan, new, &dst[1], _src, + src_cnt, &_len, scf); + } + } while (len || _len); + + new->tx.flags = flags; /* client is in control of this ack */ + new->tx.cookie = -EBUSY; + list_splice(&first->tx_list, &new->tx_list); + + return &new->tx; + +fail: + if (!first) + return NULL; + + xgene_dma_free_tx_desc_list(chan, &first->tx_list); + return NULL; +} + +static void xgene_dma_issue_pending(struct dma_chan *dchan) +{ + struct xgene_dma_chan *chan = to_dma_chan(dchan); + + spin_lock_bh(&chan->lock); + xgene_chan_xfer_ld_pending(chan); + spin_unlock_bh(&chan->lock); +} + +static enum dma_status xgene_dma_tx_status(struct dma_chan *dchan, + dma_cookie_t cookie, + struct dma_tx_state *txstate) +{ + return dma_cookie_status(dchan, cookie, txstate); +} + +static void xgene_dma_tasklet_cb(unsigned long data) +{ + struct xgene_dma_chan *chan = (struct xgene_dma_chan *)data; + + spin_lock_bh(&chan->lock); + + /* Run all cleanup for descriptors which have been completed */ + xgene_dma_cleanup_descriptors(chan); + + /* Re-enable DMA channel IRQ */ + enable_irq(chan->rx_irq); + + spin_unlock_bh(&chan->lock); +} + +static irqreturn_t xgene_dma_chan_ring_isr(int irq, void *id) +{ + struct xgene_dma_chan *chan = (struct xgene_dma_chan *)id; + + BUG_ON(!chan); + + /* + * Disable DMA channel IRQ until we process completed + * descriptors + */ + disable_irq_nosync(chan->rx_irq); + + /* + * Schedule the tasklet to handle all cleanup of the current + * transaction. It will start a new transaction if there is + * one pending. + */ + tasklet_schedule(&chan->tasklet); + + return IRQ_HANDLED; +} + +static irqreturn_t xgene_dma_err_isr(int irq, void *id) +{ + struct xgene_dma *pdma = (struct xgene_dma *)id; + unsigned long int_mask; + u32 val, i; + + val = ioread32(pdma->csr_dma + XGENE_DMA_INT); + + /* Clear DMA interrupts */ + iowrite32(val, pdma->csr_dma + XGENE_DMA_INT); + + /* Print DMA error info */ + int_mask = val >> XGENE_DMA_INT_MASK_SHIFT; + for_each_set_bit(i, &int_mask, ARRAY_SIZE(xgene_dma_err)) + dev_err(pdma->dev, + "Interrupt status 0x%08X %s\n", val, xgene_dma_err[i]); + + return IRQ_HANDLED; +} + +static void xgene_dma_wr_ring_state(struct xgene_dma_ring *ring) +{ + int i; + + iowrite32(ring->num, ring->pdma->csr_ring + XGENE_DMA_RING_STATE); + + for (i = 0; i < XGENE_DMA_RING_NUM_CONFIG; i++) + iowrite32(ring->state[i], ring->pdma->csr_ring + + XGENE_DMA_RING_STATE_WR_BASE + (i * 4)); +} + +static void xgene_dma_clr_ring_state(struct xgene_dma_ring *ring) +{ + memset(ring->state, 0, sizeof(u32) * XGENE_DMA_RING_NUM_CONFIG); + xgene_dma_wr_ring_state(ring); +} + +static void xgene_dma_setup_ring(struct xgene_dma_ring *ring) +{ + void *ring_cfg = ring->state; + u64 addr = ring->desc_paddr; + void *desc; + u32 i, val; + + ring->slots = ring->size / XGENE_DMA_RING_WQ_DESC_SIZE; + + /* Clear DMA ring state */ + xgene_dma_clr_ring_state(ring); + + /* Set DMA ring type */ + XGENE_DMA_RING_TYPE_SET(ring_cfg, XGENE_DMA_RING_TYPE_REGULAR); + + if (ring->owner == XGENE_DMA_RING_OWNER_DMA) { + /* Set recombination buffer and timeout */ + XGENE_DMA_RING_RECOMBBUF_SET(ring_cfg); + XGENE_DMA_RING_RECOMTIMEOUTL_SET(ring_cfg); + XGENE_DMA_RING_RECOMTIMEOUTH_SET(ring_cfg); + } + + /* Initialize DMA ring state */ + XGENE_DMA_RING_SELTHRSH_SET(ring_cfg); + XGENE_DMA_RING_ACCEPTLERR_SET(ring_cfg); + XGENE_DMA_RING_COHERENT_SET(ring_cfg); + XGENE_DMA_RING_ADDRL_SET(ring_cfg, addr); + XGENE_DMA_RING_ADDRH_SET(ring_cfg, addr); + XGENE_DMA_RING_SIZE_SET(ring_cfg, ring->cfgsize); + + /* Write DMA ring configurations */ + xgene_dma_wr_ring_state(ring); + + /* Set DMA ring id */ + iowrite32(XGENE_DMA_RING_ID_SETUP(ring->id), + ring->pdma->csr_ring + XGENE_DMA_RING_ID); + + /* Set DMA ring buffer */ + iowrite32(XGENE_DMA_RING_ID_BUF_SETUP(ring->num), + ring->pdma->csr_ring + XGENE_DMA_RING_ID_BUF); + + if (ring->owner != XGENE_DMA_RING_OWNER_CPU) + return; + + /* Set empty signature to DMA Rx ring descriptors */ + for (i = 0; i < ring->slots; i++) { + desc = &ring->desc_hw[i]; + XGENE_DMA_DESC_SET_EMPTY(desc); + } + + /* Enable DMA Rx ring interrupt */ + val = ioread32(ring->pdma->csr_ring + XGENE_DMA_RING_NE_INT_MODE); + XGENE_DMA_RING_NE_INT_MODE_SET(val, ring->buf_num); + iowrite32(val, ring->pdma->csr_ring + XGENE_DMA_RING_NE_INT_MODE); +} + +static void xgene_dma_clear_ring(struct xgene_dma_ring *ring) +{ + u32 ring_id, val; + + if (ring->owner == XGENE_DMA_RING_OWNER_CPU) { + /* Disable DMA Rx ring interrupt */ + val = ioread32(ring->pdma->csr_ring + + XGENE_DMA_RING_NE_INT_MODE); + XGENE_DMA_RING_NE_INT_MODE_RESET(val, ring->buf_num); + iowrite32(val, ring->pdma->csr_ring + + XGENE_DMA_RING_NE_INT_MODE); + } + + /* Clear DMA ring state */ + ring_id = XGENE_DMA_RING_ID_SETUP(ring->id); + iowrite32(ring_id, ring->pdma->csr_ring + XGENE_DMA_RING_ID); + + iowrite32(0, ring->pdma->csr_ring + XGENE_DMA_RING_ID_BUF); + xgene_dma_clr_ring_state(ring); +} + +static void xgene_dma_set_ring_cmd(struct xgene_dma_ring *ring) +{ + ring->cmd_base = ring->pdma->csr_ring_cmd + + XGENE_DMA_RING_CMD_BASE_OFFSET((ring->num - + XGENE_DMA_RING_NUM)); + + ring->cmd = ring->cmd_base + XGENE_DMA_RING_CMD_OFFSET; +} + +static int xgene_dma_get_ring_size(struct xgene_dma_chan *chan, + enum xgene_dma_ring_cfgsize cfgsize) +{ + int size; + + switch (cfgsize) { + case XGENE_DMA_RING_CFG_SIZE_512B: + size = 0x200; + break; + case XGENE_DMA_RING_CFG_SIZE_2KB: + size = 0x800; + break; + case XGENE_DMA_RING_CFG_SIZE_16KB: + size = 0x4000; + break; + case XGENE_DMA_RING_CFG_SIZE_64KB: + size = 0x10000; + break; + case XGENE_DMA_RING_CFG_SIZE_512KB: + size = 0x80000; + break; + default: + chan_err(chan, "Unsupported cfg ring size %d\n", cfgsize); + return -EINVAL; + } + + return size; +} + +static void xgene_dma_delete_ring_one(struct xgene_dma_ring *ring) +{ + /* Clear DMA ring configurations */ + xgene_dma_clear_ring(ring); + + /* De-allocate DMA ring descriptor */ + if (ring->desc_vaddr) { + dma_free_coherent(ring->pdma->dev, ring->size, + ring->desc_vaddr, ring->desc_paddr); + ring->desc_vaddr = NULL; + } +} + +static void xgene_dma_delete_chan_rings(struct xgene_dma_chan *chan) +{ + xgene_dma_delete_ring_one(&chan->rx_ring); + xgene_dma_delete_ring_one(&chan->tx_ring); +} + +static int xgene_dma_create_ring_one(struct xgene_dma_chan *chan, + struct xgene_dma_ring *ring, + enum xgene_dma_ring_cfgsize cfgsize) +{ + /* Setup DMA ring descriptor variables */ + ring->pdma = chan->pdma; + ring->cfgsize = cfgsize; + ring->num = chan->pdma->ring_num++; + ring->id = XGENE_DMA_RING_ID_GET(ring->owner, ring->buf_num); + + ring->size = xgene_dma_get_ring_size(chan, cfgsize); + if (ring->size <= 0) + return ring->size; + + /* Allocate memory for DMA ring descriptor */ + ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size, + &ring->desc_paddr, GFP_KERNEL); + if (!ring->desc_vaddr) { + chan_err(chan, "Failed to allocate ring desc\n"); + return -ENOMEM; + } + + /* Configure and enable DMA ring */ + xgene_dma_set_ring_cmd(ring); + xgene_dma_setup_ring(ring); + + return 0; +} + +static int xgene_dma_create_chan_rings(struct xgene_dma_chan *chan) +{ + struct xgene_dma_ring *rx_ring = &chan->rx_ring; + struct xgene_dma_ring *tx_ring = &chan->tx_ring; + int ret; + + /* Create DMA Rx ring descriptor */ + rx_ring->owner = XGENE_DMA_RING_OWNER_CPU; + rx_ring->buf_num = XGENE_DMA_CPU_BUFNUM + chan->id; + + ret = xgene_dma_create_ring_one(chan, rx_ring, + XGENE_DMA_RING_CFG_SIZE_64KB); + if (ret) + return ret; + + chan_dbg(chan, "Rx ring id 0x%X num %d desc 0x%p\n", + rx_ring->id, rx_ring->num, rx_ring->desc_vaddr); + + /* Create DMA Tx ring descriptor */ + tx_ring->owner = XGENE_DMA_RING_OWNER_DMA; + tx_ring->buf_num = XGENE_DMA_BUFNUM + chan->id; + + ret = xgene_dma_create_ring_one(chan, tx_ring, + XGENE_DMA_RING_CFG_SIZE_64KB); + if (ret) { + xgene_dma_delete_ring_one(rx_ring); + return ret; + } + + tx_ring->dst_ring_num = XGENE_DMA_RING_DST_ID(rx_ring->num); + + chan_dbg(chan, + "Tx ring id 0x%X num %d desc 0x%p\n", + tx_ring->id, tx_ring->num, tx_ring->desc_vaddr); + + /* Set the max outstanding request possible to this channel */ + chan->max_outstanding = rx_ring->slots; + + return ret; +} + +static int xgene_dma_init_rings(struct xgene_dma *pdma) +{ + int ret, i, j; + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { + ret = xgene_dma_create_chan_rings(&pdma->chan[i]); + if (ret) { + for (j = 0; j < i; j++) + xgene_dma_delete_chan_rings(&pdma->chan[j]); + return ret; + } + } + + return ret; +} + +static void xgene_dma_enable(struct xgene_dma *pdma) +{ + u32 val; + + /* Configure and enable DMA engine */ + val = ioread32(pdma->csr_dma + XGENE_DMA_GCR); + XGENE_DMA_CH_SETUP(val); + XGENE_DMA_ENABLE(val); + iowrite32(val, pdma->csr_dma + XGENE_DMA_GCR); +} + +static void xgene_dma_disable(struct xgene_dma *pdma) +{ + u32 val; + + val = ioread32(pdma->csr_dma + XGENE_DMA_GCR); + XGENE_DMA_DISABLE(val); + iowrite32(val, pdma->csr_dma + XGENE_DMA_GCR); +} + +static void xgene_dma_mask_interrupts(struct xgene_dma *pdma) +{ + /* + * Mask DMA ring overflow, underflow and + * AXI write/read error interrupts + */ + iowrite32(XGENE_DMA_INT_ALL_MASK, + pdma->csr_dma + XGENE_DMA_RING_INT0_MASK); + iowrite32(XGENE_DMA_INT_ALL_MASK, + pdma->csr_dma + XGENE_DMA_RING_INT1_MASK); + iowrite32(XGENE_DMA_INT_ALL_MASK, + pdma->csr_dma + XGENE_DMA_RING_INT2_MASK); + iowrite32(XGENE_DMA_INT_ALL_MASK, + pdma->csr_dma + XGENE_DMA_RING_INT3_MASK); + iowrite32(XGENE_DMA_INT_ALL_MASK, + pdma->csr_dma + XGENE_DMA_RING_INT4_MASK); + + /* Mask DMA error interrupts */ + iowrite32(XGENE_DMA_INT_ALL_MASK, pdma->csr_dma + XGENE_DMA_INT_MASK); +} + +static void xgene_dma_unmask_interrupts(struct xgene_dma *pdma) +{ + /* + * Unmask DMA ring overflow, underflow and + * AXI write/read error interrupts + */ + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_RING_INT0_MASK); + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_RING_INT1_MASK); + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_RING_INT2_MASK); + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_RING_INT3_MASK); + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_RING_INT4_MASK); + + /* Unmask DMA error interrupts */ + iowrite32(XGENE_DMA_INT_ALL_UNMASK, + pdma->csr_dma + XGENE_DMA_INT_MASK); +} + +static void xgene_dma_init_hw(struct xgene_dma *pdma) +{ + u32 val; + + /* Associate DMA ring to corresponding ring HW */ + iowrite32(XGENE_DMA_ASSOC_RING_MNGR1, + pdma->csr_dma + XGENE_DMA_CFG_RING_WQ_ASSOC); + + /* Configure RAID6 polynomial control setting */ + if (is_pq_enabled(pdma)) + iowrite32(XGENE_DMA_RAID6_MULTI_CTRL(0x1D), + pdma->csr_dma + XGENE_DMA_RAID6_CONT); + else + dev_info(pdma->dev, "PQ is disabled in HW\n"); + + xgene_dma_enable(pdma); + xgene_dma_unmask_interrupts(pdma); + + /* Get DMA id and version info */ + val = ioread32(pdma->csr_dma + XGENE_DMA_IPBRR); + + /* DMA device info */ + dev_info(pdma->dev, + "X-Gene DMA v%d.%02d.%02d driver registered %d channels", + XGENE_DMA_REV_NO_RD(val), XGENE_DMA_BUS_ID_RD(val), + XGENE_DMA_DEV_ID_RD(val), XGENE_DMA_MAX_CHANNEL); +} + +static int xgene_dma_init_ring_mngr(struct xgene_dma *pdma) +{ + if (ioread32(pdma->csr_ring + XGENE_DMA_RING_CLKEN) && + (!ioread32(pdma->csr_ring + XGENE_DMA_RING_SRST))) + return 0; + + iowrite32(0x3, pdma->csr_ring + XGENE_DMA_RING_CLKEN); + iowrite32(0x0, pdma->csr_ring + XGENE_DMA_RING_SRST); + + /* Bring up memory */ + iowrite32(0x0, pdma->csr_ring + XGENE_DMA_RING_MEM_RAM_SHUTDOWN); + + /* Force a barrier */ + ioread32(pdma->csr_ring + XGENE_DMA_RING_MEM_RAM_SHUTDOWN); + + /* reset may take up to 1ms */ + usleep_range(1000, 1100); + + if (ioread32(pdma->csr_ring + XGENE_DMA_RING_BLK_MEM_RDY) + != XGENE_DMA_RING_BLK_MEM_RDY_VAL) { + dev_err(pdma->dev, + "Failed to release ring mngr memory from shutdown\n"); + return -ENODEV; + } + + /* program threshold set 1 and all hysteresis */ + iowrite32(XGENE_DMA_RING_THRESLD0_SET1_VAL, + pdma->csr_ring + XGENE_DMA_RING_THRESLD0_SET1); + iowrite32(XGENE_DMA_RING_THRESLD1_SET1_VAL, + pdma->csr_ring + XGENE_DMA_RING_THRESLD1_SET1); + iowrite32(XGENE_DMA_RING_HYSTERESIS_VAL, + pdma->csr_ring + XGENE_DMA_RING_HYSTERESIS); + + /* Enable QPcore and assign error queue */ + iowrite32(XGENE_DMA_RING_ENABLE, + pdma->csr_ring + XGENE_DMA_RING_CONFIG); + + return 0; +} + +static int xgene_dma_init_mem(struct xgene_dma *pdma) +{ + int ret; + + ret = xgene_dma_init_ring_mngr(pdma); + if (ret) + return ret; + + /* Bring up memory */ + iowrite32(0x0, pdma->csr_dma + XGENE_DMA_MEM_RAM_SHUTDOWN); + + /* Force a barrier */ + ioread32(pdma->csr_dma + XGENE_DMA_MEM_RAM_SHUTDOWN); + + /* reset may take up to 1ms */ + usleep_range(1000, 1100); + + if (ioread32(pdma->csr_dma + XGENE_DMA_BLK_MEM_RDY) + != XGENE_DMA_BLK_MEM_RDY_VAL) { + dev_err(pdma->dev, + "Failed to release DMA memory from shutdown\n"); + return -ENODEV; + } + + return 0; +} + +static int xgene_dma_request_irqs(struct xgene_dma *pdma) +{ + struct xgene_dma_chan *chan; + int ret, i, j; + + /* Register DMA error irq */ + ret = devm_request_irq(pdma->dev, pdma->err_irq, xgene_dma_err_isr, + 0, "dma_error", pdma); + if (ret) { + dev_err(pdma->dev, + "Failed to register error IRQ %d\n", pdma->err_irq); + return ret; + } + + /* Register DMA channel rx irq */ + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { + chan = &pdma->chan[i]; + ret = devm_request_irq(chan->dev, chan->rx_irq, + xgene_dma_chan_ring_isr, + 0, chan->name, chan); + if (ret) { + chan_err(chan, "Failed to register Rx IRQ %d\n", + chan->rx_irq); + devm_free_irq(pdma->dev, pdma->err_irq, pdma); + + for (j = 0; j < i; j++) { + chan = &pdma->chan[i]; + devm_free_irq(chan->dev, chan->rx_irq, chan); + } + + return ret; + } + } + + return 0; +} + +static void xgene_dma_free_irqs(struct xgene_dma *pdma) +{ + struct xgene_dma_chan *chan; + int i; + + /* Free DMA device error irq */ + devm_free_irq(pdma->dev, pdma->err_irq, pdma); + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { + chan = &pdma->chan[i]; + devm_free_irq(chan->dev, chan->rx_irq, chan); + } +} + +static void xgene_dma_set_caps(struct xgene_dma_chan *chan, + struct dma_device *dma_dev) +{ + /* Initialize DMA device capability mask */ + dma_cap_zero(dma_dev->cap_mask); + + /* Set DMA device capability */ + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + dma_cap_set(DMA_SG, dma_dev->cap_mask); + + /* Basically here, the X-Gene SoC DMA engine channel 0 supports XOR + * and channel 1 supports XOR, PQ both. First thing here is we have + * mechanism in hw to enable/disable PQ/XOR supports on channel 1, + * we can make sure this by reading SoC Efuse register. + * Second thing, we have hw errata that if we run channel 0 and + * channel 1 simultaneously with executing XOR and PQ request, + * suddenly DMA engine hangs, So here we enable XOR on channel 0 only + * if XOR and PQ supports on channel 1 is disabled. + */ + if ((chan->id == XGENE_DMA_PQ_CHANNEL) && + is_pq_enabled(chan->pdma)) { + dma_cap_set(DMA_PQ, dma_dev->cap_mask); + dma_cap_set(DMA_XOR, dma_dev->cap_mask); + } else if ((chan->id == XGENE_DMA_XOR_CHANNEL) && + !is_pq_enabled(chan->pdma)) { + dma_cap_set(DMA_XOR, dma_dev->cap_mask); + } + + /* Set base and prep routines */ + dma_dev->dev = chan->dev; + dma_dev->device_alloc_chan_resources = xgene_dma_alloc_chan_resources; + dma_dev->device_free_chan_resources = xgene_dma_free_chan_resources; + dma_dev->device_issue_pending = xgene_dma_issue_pending; + dma_dev->device_tx_status = xgene_dma_tx_status; + dma_dev->device_prep_dma_memcpy = xgene_dma_prep_memcpy; + dma_dev->device_prep_dma_sg = xgene_dma_prep_sg; + + if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_xor = xgene_dma_prep_xor; + dma_dev->max_xor = XGENE_DMA_MAX_XOR_SRC; + dma_dev->xor_align = XGENE_DMA_XOR_ALIGNMENT; + } + + if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) { + dma_dev->device_prep_dma_pq = xgene_dma_prep_pq; + dma_dev->max_pq = XGENE_DMA_MAX_XOR_SRC; + dma_dev->pq_align = XGENE_DMA_XOR_ALIGNMENT; + } +} + +static int xgene_dma_async_register(struct xgene_dma *pdma, int id) +{ + struct xgene_dma_chan *chan = &pdma->chan[id]; + struct dma_device *dma_dev = &pdma->dma_dev[id]; + int ret; + + chan->dma_chan.device = dma_dev; + + spin_lock_init(&chan->lock); + INIT_LIST_HEAD(&chan->ld_pending); + INIT_LIST_HEAD(&chan->ld_running); + INIT_LIST_HEAD(&chan->ld_completed); + tasklet_init(&chan->tasklet, xgene_dma_tasklet_cb, + (unsigned long)chan); + + chan->pending = 0; + chan->desc_pool = NULL; + dma_cookie_init(&chan->dma_chan); + + /* Setup dma device capabilities and prep routines */ + xgene_dma_set_caps(chan, dma_dev); + + /* Initialize DMA device list head */ + INIT_LIST_HEAD(&dma_dev->channels); + list_add_tail(&chan->dma_chan.device_node, &dma_dev->channels); + + /* Register with Linux async DMA framework*/ + ret = dma_async_device_register(dma_dev); + if (ret) { + chan_err(chan, "Failed to register async device %d", ret); + tasklet_kill(&chan->tasklet); + + return ret; + } + + /* DMA capability info */ + dev_info(pdma->dev, + "%s: CAPABILITY ( %s%s%s%s)\n", dma_chan_name(&chan->dma_chan), + dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "MEMCPY " : "", + dma_has_cap(DMA_SG, dma_dev->cap_mask) ? "SGCPY " : "", + dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "XOR " : "", + dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "PQ " : ""); + + return 0; +} + +static int xgene_dma_init_async(struct xgene_dma *pdma) +{ + int ret, i, j; + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL ; i++) { + ret = xgene_dma_async_register(pdma, i); + if (ret) { + for (j = 0; j < i; j++) { + dma_async_device_unregister(&pdma->dma_dev[j]); + tasklet_kill(&pdma->chan[j].tasklet); + } + + return ret; + } + } + + return ret; +} + +static void xgene_dma_async_unregister(struct xgene_dma *pdma) +{ + int i; + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) + dma_async_device_unregister(&pdma->dma_dev[i]); +} + +static void xgene_dma_init_channels(struct xgene_dma *pdma) +{ + struct xgene_dma_chan *chan; + int i; + + pdma->ring_num = XGENE_DMA_RING_NUM; + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { + chan = &pdma->chan[i]; + chan->dev = pdma->dev; + chan->pdma = pdma; + chan->id = i; + snprintf(chan->name, sizeof(chan->name), "dmachan%d", chan->id); + } +} + +static int xgene_dma_get_resources(struct platform_device *pdev, + struct xgene_dma *pdma) +{ + struct resource *res; + int irq, i; + + /* Get DMA csr region */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(&pdev->dev, "Failed to get csr region\n"); + return -ENXIO; + } + + pdma->csr_dma = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!pdma->csr_dma) { + dev_err(&pdev->dev, "Failed to ioremap csr region"); + return -ENOMEM; + } + + /* Get DMA ring csr region */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) { + dev_err(&pdev->dev, "Failed to get ring csr region\n"); + return -ENXIO; + } + + pdma->csr_ring = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!pdma->csr_ring) { + dev_err(&pdev->dev, "Failed to ioremap ring csr region"); + return -ENOMEM; + } + + /* Get DMA ring cmd csr region */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + if (!res) { + dev_err(&pdev->dev, "Failed to get ring cmd csr region\n"); + return -ENXIO; + } + + pdma->csr_ring_cmd = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!pdma->csr_ring_cmd) { + dev_err(&pdev->dev, "Failed to ioremap ring cmd csr region"); + return -ENOMEM; + } + + /* Get efuse csr region */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 3); + if (!res) { + dev_err(&pdev->dev, "Failed to get efuse csr region\n"); + return -ENXIO; + } + + pdma->csr_efuse = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!pdma->csr_efuse) { + dev_err(&pdev->dev, "Failed to ioremap efuse csr region"); + return -ENOMEM; + } + + /* Get DMA error interrupt */ + irq = platform_get_irq(pdev, 0); + if (irq <= 0) { + dev_err(&pdev->dev, "Failed to get Error IRQ\n"); + return -ENXIO; + } + + pdma->err_irq = irq; + + /* Get DMA Rx ring descriptor interrupts for all DMA channels */ + for (i = 1; i <= XGENE_DMA_MAX_CHANNEL; i++) { + irq = platform_get_irq(pdev, i); + if (irq <= 0) { + dev_err(&pdev->dev, "Failed to get Rx IRQ\n"); + return -ENXIO; + } + + pdma->chan[i - 1].rx_irq = irq; + } + + return 0; +} + +static int xgene_dma_probe(struct platform_device *pdev) +{ + struct xgene_dma *pdma; + int ret, i; + + pdma = devm_kzalloc(&pdev->dev, sizeof(*pdma), GFP_KERNEL); + if (!pdma) + return -ENOMEM; + + pdma->dev = &pdev->dev; + platform_set_drvdata(pdev, pdma); + + ret = xgene_dma_get_resources(pdev, pdma); + if (ret) + return ret; + + pdma->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdma->clk)) { + dev_err(&pdev->dev, "Failed to get clk\n"); + return PTR_ERR(pdma->clk); + } + + /* Enable clk before accessing registers */ + ret = clk_prepare_enable(pdma->clk); + if (ret) { + dev_err(&pdev->dev, "Failed to enable clk %d\n", ret); + return ret; + } + + /* Remove DMA RAM out of shutdown */ + ret = xgene_dma_init_mem(pdma); + if (ret) + goto err_clk_enable; + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(42)); + if (ret) { + dev_err(&pdev->dev, "No usable DMA configuration\n"); + goto err_dma_mask; + } + + /* Initialize DMA channels software state */ + xgene_dma_init_channels(pdma); + + /* Configue DMA rings */ + ret = xgene_dma_init_rings(pdma); + if (ret) + goto err_clk_enable; + + ret = xgene_dma_request_irqs(pdma); + if (ret) + goto err_request_irq; + + /* Configure and enable DMA engine */ + xgene_dma_init_hw(pdma); + + /* Register DMA device with linux async framework */ + ret = xgene_dma_init_async(pdma); + if (ret) + goto err_async_init; + + return 0; + +err_async_init: + xgene_dma_free_irqs(pdma); + +err_request_irq: + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) + xgene_dma_delete_chan_rings(&pdma->chan[i]); + +err_dma_mask: +err_clk_enable: + clk_disable_unprepare(pdma->clk); + + return ret; +} + +static int xgene_dma_remove(struct platform_device *pdev) +{ + struct xgene_dma *pdma = platform_get_drvdata(pdev); + struct xgene_dma_chan *chan; + int i; + + xgene_dma_async_unregister(pdma); + + /* Mask interrupts and disable DMA engine */ + xgene_dma_mask_interrupts(pdma); + xgene_dma_disable(pdma); + xgene_dma_free_irqs(pdma); + + for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { + chan = &pdma->chan[i]; + tasklet_kill(&chan->tasklet); + xgene_dma_delete_chan_rings(chan); + } + + clk_disable_unprepare(pdma->clk); + + return 0; +} + +static const struct of_device_id xgene_dma_of_match_ptr[] = { + {.compatible = "apm,xgene-storm-dma",}, + {}, +}; +MODULE_DEVICE_TABLE(of, xgene_dma_of_match_ptr); + +static struct platform_driver xgene_dma_driver = { + .probe = xgene_dma_probe, + .remove = xgene_dma_remove, + .driver = { + .name = "X-Gene-DMA", + .of_match_table = xgene_dma_of_match_ptr, + }, +}; + +module_platform_driver(xgene_dma_driver); + +MODULE_DESCRIPTION("APM X-Gene SoC DMA driver"); +MODULE_AUTHOR("Rameshwar Prasad Sahu <rsahu@apm.com>"); +MODULE_AUTHOR("Loc Ho <lho@apm.com>"); +MODULE_LICENSE("GPL"); +MODULE_VERSION("1.0"); diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c index bdd2a5dd7220..d8434d465885 100644 --- a/drivers/dma/xilinx/xilinx_vdma.c +++ b/drivers/dma/xilinx/xilinx_vdma.c @@ -22,9 +22,9 @@ * (at your option) any later version. */ -#include <linux/amba/xilinx_dma.h> #include <linux/bitops.h> #include <linux/dmapool.h> +#include <linux/dma/xilinx_dma.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index ef5feeecec84..580e10acaa3a 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -538,8 +538,14 @@ struct dma_buf * armada_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &armada_gem_prime_dmabuf_ops, obj->size, - O_RDWR, NULL); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &armada_gem_prime_dmabuf_ops; + exp_info.size = obj->size; + exp_info.flags = O_RDWR; + exp_info.priv = obj; + + return dma_buf_export(&exp_info); } struct drm_gem_object * diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7482b06cd08f..7fec191b45f7 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -339,13 +339,17 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { struct dma_buf *drm_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - struct reservation_object *robj = NULL; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &drm_gem_prime_dmabuf_ops; + exp_info.size = obj->size; + exp_info.flags = flags; + exp_info.priv = obj; if (dev->driver->gem_prime_res_obj) - robj = dev->driver->gem_prime_res_obj(obj); + exp_info.resv = dev->driver->gem_prime_res_obj(obj); - return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, - flags, robj); + return dma_buf_export(&exp_info); } EXPORT_SYMBOL(drm_gem_prime_export); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c index 3833bf8ca025..cd485c091b30 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c @@ -185,9 +185,14 @@ struct dma_buf *exynos_dmabuf_prime_export(struct drm_device *drm_dev, struct drm_gem_object *obj, int flags) { struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - return dma_buf_export(obj, &exynos_dmabuf_ops, - exynos_gem_obj->base.size, flags, NULL); + exp_info.ops = &exynos_dmabuf_ops; + exp_info.size = exynos_gem_obj->base.size; + exp_info.flags = flags; + exp_info.priv = obj; + + return dma_buf_export(&exp_info); } struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index c24c3f1ff8a3..c302ffb5a168 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1038,7 +1038,7 @@ static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4); s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); - s->gfx_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); + s->gfx_max_req_count = I915_READ(GEN7_GFX_MAX_REQ_COUNT); s->render_hwsp = I915_READ(RENDER_HWS_PGA_GEN7); s->ecochk = I915_READ(GAM_ECOCHK); @@ -1120,7 +1120,7 @@ static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]); I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count); - I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count); + I915_WRITE(GEN7_GFX_MAX_REQ_COUNT, s->gfx_max_req_count); I915_WRITE(RENDER_HWS_PGA_GEN7, s->render_hwsp); I915_WRITE(GAM_ECOCHK, s->ecochk); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d07c0b1fb498..53394f998a1f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2377,10 +2377,11 @@ int __i915_add_request(struct intel_engine_cs *ring, ret = ring->add_request(ring); if (ret) return ret; + + request->tail = intel_ring_get_tail(ringbuf); } request->head = request_start; - request->tail = intel_ring_get_tail(ringbuf); /* Whilst this request exists, batch_obj will be on the * active_list, and so will hold the active reference. Only when this diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 82a1f4b57778..7998da27c500 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -230,6 +230,13 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags) { struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &i915_dmabuf_ops; + exp_info.size = gem_obj->size; + exp_info.flags = flags; + exp_info.priv = gem_obj; + if (obj->ops->dmabuf_export) { int ret = obj->ops->dmabuf_export(obj); @@ -237,8 +244,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev, return ERR_PTR(ret); } - return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags, - NULL); + return dma_buf_export(&exp_info); } static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b522eb6e59a4..3da1af46625c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1807,6 +1807,7 @@ enum skl_disp_power_wells { #define GMBUS_CYCLE_INDEX (2<<25) #define GMBUS_CYCLE_STOP (4<<25) #define GMBUS_BYTE_COUNT_SHIFT 16 +#define GMBUS_BYTE_COUNT_MAX 256U #define GMBUS_SLAVE_INDEX_SHIFT 8 #define GMBUS_SLAVE_ADDR_SHIFT 1 #define GMBUS_SLAVE_READ (1<<0) diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index b31088a551f2..56e437e31580 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -270,18 +270,17 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) } static int -gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, - u32 gmbus1_index) +gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, + unsigned short addr, u8 *buf, unsigned int len, + u32 gmbus1_index) { int reg_offset = dev_priv->gpio_mmio_base; - u16 len = msg->len; - u8 *buf = msg->buf; I915_WRITE(GMBUS1 + reg_offset, gmbus1_index | GMBUS_CYCLE_WAIT | (len << GMBUS_BYTE_COUNT_SHIFT) | - (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | + (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_READ | GMBUS_SW_RDY); while (len) { int ret; @@ -303,11 +302,35 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, } static int -gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) +gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, + u32 gmbus1_index) { - int reg_offset = dev_priv->gpio_mmio_base; - u16 len = msg->len; u8 *buf = msg->buf; + unsigned int rx_size = msg->len; + unsigned int len; + int ret; + + do { + len = min(rx_size, GMBUS_BYTE_COUNT_MAX); + + ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, + buf, len, gmbus1_index); + if (ret) + return ret; + + rx_size -= len; + buf += len; + } while (rx_size != 0); + + return 0; +} + +static int +gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, + unsigned short addr, u8 *buf, unsigned int len) +{ + int reg_offset = dev_priv->gpio_mmio_base; + unsigned int chunk_size = len; u32 val, loop; val = loop = 0; @@ -319,8 +342,8 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) I915_WRITE(GMBUS3 + reg_offset, val); I915_WRITE(GMBUS1 + reg_offset, GMBUS_CYCLE_WAIT | - (msg->len << GMBUS_BYTE_COUNT_SHIFT) | - (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) | + (chunk_size << GMBUS_BYTE_COUNT_SHIFT) | + (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_WRITE | GMBUS_SW_RDY); while (len) { int ret; @@ -337,6 +360,29 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) if (ret) return ret; } + + return 0; +} + +static int +gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg) +{ + u8 *buf = msg->buf; + unsigned int tx_size = msg->len; + unsigned int len; + int ret; + + do { + len = min(tx_size, GMBUS_BYTE_COUNT_MAX); + + ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len); + if (ret) + return ret; + + buf += len; + tx_size -= len; + } while (tx_size != 0); + return 0; } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index fcb074bd55dc..09df74b8e917 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -393,6 +393,26 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) } } + if (IS_GEN8(ring->dev) || IS_GEN9(ring->dev)) { + /* + * WaIdleLiteRestore: make sure we never cause a lite + * restore with HEAD==TAIL + */ + if (req0 && req0->elsp_submitted) { + /* + * Apply the wa NOOPS to prevent ring:HEAD == req:TAIL + * as we resubmit the request. See gen8_emit_request() + * for where we prepare the padding after the end of the + * request. + */ + struct intel_ringbuffer *ringbuf; + + ringbuf = req0->ctx->engine[ring->id].ringbuf; + req0->tail += 8; + req0->tail &= ringbuf->size - 1; + } + } + WARN_ON(req1 && req1->elsp_submitted); execlists_submit_contexts(ring, req0->ctx, req0->tail, @@ -1315,7 +1335,12 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf, u32 cmd; int ret; - ret = intel_logical_ring_begin(ringbuf, request->ctx, 6); + /* + * Reserve space for 2 NOOPs at the end of each request to be + * used as a workaround for not being allowed to do lite + * restore with HEAD==TAIL (WaIdleLiteRestore). + */ + ret = intel_logical_ring_begin(ringbuf, request->ctx, 8); if (ret) return ret; @@ -1333,6 +1358,14 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf, intel_logical_ring_emit(ringbuf, MI_NOOP); intel_logical_ring_advance_and_submit(ringbuf, request->ctx, request); + /* + * Here we add two extra NOOPs as padding to avoid + * lite restore of a context with HEAD==TAIL. + */ + intel_logical_ring_emit(ringbuf, MI_NOOP); + intel_logical_ring_emit(ringbuf, MI_NOOP); + intel_logical_ring_advance(ringbuf); + return 0; } diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index b46dabd9faf7..344fd789170d 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -171,7 +171,14 @@ static struct dma_buf_ops omap_dmabuf_ops = { struct dma_buf *omap_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &omap_dmabuf_ops, obj->size, flags, NULL); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &omap_dmabuf_ops; + exp_info.size = obj->size; + exp_info.flags = flags; + exp_info.priv = obj; + + return dma_buf_export(&exp_info); } struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev, diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index cfb481943b6b..1217272a51f2 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -627,8 +627,14 @@ struct dma_buf *tegra_gem_prime_export(struct drm_device *drm, struct drm_gem_object *gem, int flags) { - return dma_buf_export(gem, &tegra_gem_prime_dmabuf_ops, gem->size, - flags, NULL); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &tegra_gem_prime_dmabuf_ops; + exp_info.size = gem->size; + exp_info.flags = flags; + exp_info.priv = gem; + + return dma_buf_export(&exp_info); } struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm, diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c index 12c87110db3a..4f5fa8d65fe9 100644 --- a/drivers/gpu/drm/ttm/ttm_object.c +++ b/drivers/gpu/drm/ttm/ttm_object.c @@ -683,6 +683,12 @@ int ttm_prime_handle_to_fd(struct ttm_object_file *tfile, dma_buf = prime->dma_buf; if (!dma_buf || !get_dma_buf_unless_doomed(dma_buf)) { + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &tdev->ops; + exp_info.size = prime->size; + exp_info.flags = flags; + exp_info.priv = prime; /* * Need to create a new dma_buf, with memory accounting. @@ -694,8 +700,7 @@ int ttm_prime_handle_to_fd(struct ttm_object_file *tfile, goto out_unref; } - dma_buf = dma_buf_export(prime, &tdev->ops, - prime->size, flags, NULL); + dma_buf = dma_buf_export(&exp_info); if (IS_ERR(dma_buf)) { ret = PTR_ERR(dma_buf); ttm_mem_global_free(tdev->mem_glob, diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index ac8a66b4dfc2..e2243edd1ce3 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -202,7 +202,14 @@ static struct dma_buf_ops udl_dmabuf_ops = { struct dma_buf *udl_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags) { - return dma_buf_export(obj, &udl_dmabuf_ops, obj->size, flags, NULL); + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &udl_dmabuf_ops; + exp_info.size = obj->size; + exp_info.flags = flags; + exp_info.priv = obj; + + return dma_buf_export(&exp_info); } static int udl_prime_create(struct drm_device *dev, diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c index 875c22ae5400..fa8dedd8c3a2 100644 --- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c +++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c @@ -182,72 +182,41 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[], const u16 bus_num = bus->remote_bus; int request_len; int response_len; - u8 *request = NULL; - u8 *response = NULL; int result; - struct cros_ec_command msg; + struct cros_ec_command msg = { }; request_len = ec_i2c_count_message(i2c_msgs, num); if (request_len < 0) { dev_warn(dev, "Error constructing message %d\n", request_len); - result = request_len; - goto exit; + return request_len; } + response_len = ec_i2c_count_response(i2c_msgs, num); if (response_len < 0) { /* Unexpected; no errors should come when NULL response */ dev_warn(dev, "Error preparing response %d\n", response_len); - result = response_len; - goto exit; - } - - if (request_len <= ARRAY_SIZE(bus->request_buf)) { - request = bus->request_buf; - } else { - request = kzalloc(request_len, GFP_KERNEL); - if (request == NULL) { - result = -ENOMEM; - goto exit; - } - } - if (response_len <= ARRAY_SIZE(bus->response_buf)) { - response = bus->response_buf; - } else { - response = kzalloc(response_len, GFP_KERNEL); - if (response == NULL) { - result = -ENOMEM; - goto exit; - } + return response_len; } - result = ec_i2c_construct_message(request, i2c_msgs, num, bus_num); + result = ec_i2c_construct_message(msg.outdata, i2c_msgs, num, bus_num); if (result) - goto exit; + return result; msg.version = 0; msg.command = EC_CMD_I2C_PASSTHRU; - msg.outdata = request; msg.outsize = request_len; - msg.indata = response; msg.insize = response_len; result = cros_ec_cmd_xfer(bus->ec, &msg); if (result < 0) - goto exit; + return result; - result = ec_i2c_parse_response(response, i2c_msgs, &num); + result = ec_i2c_parse_response(msg.indata, i2c_msgs, &num); if (result < 0) - goto exit; + return result; /* Indicate success by saying how many messages were sent */ - result = num; -exit: - if (request != bus->request_buf) - kfree(request); - if (response != bus->response_buf) - kfree(response); - - return result; + return num; } static u32 ec_i2c_functionality(struct i2c_adapter *adap) diff --git a/drivers/i2c/busses/i2c-digicolor.c b/drivers/i2c/busses/i2c-digicolor.c index 03f1e5549896..9604024e0eb0 100644 --- a/drivers/i2c/busses/i2c-digicolor.c +++ b/drivers/i2c/busses/i2c-digicolor.c @@ -12,11 +12,10 @@ #include <linux/clk.h> #include <linux/completion.h> +#include <linux/delay.h> #include <linux/i2c.h> #include <linux/interrupt.h> #include <linux/io.h> -#include <linux/clk.h> -#include <linux/delay.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index 56fceff6ba14..3e84f6c090a5 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -913,7 +913,7 @@ static void __exit mxs_i2c_exit(void) module_exit(mxs_i2c_exit); MODULE_AUTHOR("Marek Vasut <marex@denx.de>"); -MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>"); +MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>"); MODULE_DESCRIPTION("MXS I2C Bus Driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/i2c/busses/i2c-pca-platform.c b/drivers/i2c/busses/i2c-pca-platform.c index 6336f02ec566..3bd2e7d06e4b 100644 --- a/drivers/i2c/busses/i2c-pca-platform.c +++ b/drivers/i2c/busses/i2c-pca-platform.c @@ -285,6 +285,6 @@ static struct platform_driver i2c_pca_pf_driver = { module_platform_driver(i2c_pca_pf_driver); -MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>"); +MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>"); MODULE_DESCRIPTION("I2C-PCA9564/PCA9665 platform driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 5f96b1b3e3a5..019d5426fe52 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -833,7 +833,7 @@ static int rk3x_i2c_xfer(struct i2c_adapter *adap, clk_disable(i2c->clk); spin_unlock_irqrestore(&i2c->lock, flags); - return ret; + return ret < 0 ? ret : num; } static u32 rk3x_i2c_func(struct i2c_adapter *adap) diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index 88057fad9dfe..ea72dca32fdf 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -10,17 +10,18 @@ * published by the Free Software Foundation. */ -#include <linux/module.h> -#include <linux/platform_device.h> -#include <linux/i2c.h> #include <linux/clk.h> -#include <linux/io.h> #include <linux/delay.h> -#include <linux/interrupt.h> #include <linux/err.h> -#include <linux/of.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/of.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> /* SSC registers */ #define SSC_BRG 0x000 diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 098f698fe8f4..987c124432c5 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -1413,6 +1413,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) dev_dbg(&adap->dev, "adapter [%s] registered\n", adap->name); + pm_runtime_no_callbacks(&adap->dev); + #ifdef CONFIG_I2C_COMPAT res = class_compat_create_link(i2c_adapter_compat_class, &adap->dev, adap->dev.parent); diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 593f7ca9adc7..06cc1ff088f1 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -32,8 +32,9 @@ struct i2c_mux_priv { struct i2c_algorithm algo; struct i2c_adapter *parent; - void *mux_priv; /* the mux chip/device */ - u32 chan_id; /* the channel id */ + struct device *mux_dev; + void *mux_priv; + u32 chan_id; int (*select)(struct i2c_adapter *, void *mux_priv, u32 chan_id); int (*deselect)(struct i2c_adapter *, void *mux_priv, u32 chan_id); @@ -119,6 +120,7 @@ struct i2c_adapter *i2c_add_mux_adapter(struct i2c_adapter *parent, /* Set up private adapter data */ priv->parent = parent; + priv->mux_dev = mux_dev; priv->mux_priv = mux_priv; priv->chan_id = chan_id; priv->select = select; @@ -203,7 +205,7 @@ void i2c_del_mux_adapter(struct i2c_adapter *adap) char symlink_name[20]; snprintf(symlink_name, sizeof(symlink_name), "channel-%u", priv->chan_id); - sysfs_remove_link(&adap->dev.parent->kobj, symlink_name); + sysfs_remove_link(&priv->mux_dev->kobj, symlink_name); sysfs_remove_link(&priv->adap.dev.kobj, "mux_device"); i2c_del_adapter(adap); diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 8c014b5dab4c..38acb3cfc545 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -99,12 +99,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, if (dmasync) dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs); + if (!size) + return ERR_PTR(-EINVAL); + /* * If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. */ - if ((PAGE_ALIGN(addr + size) <= size) || - (PAGE_ALIGN(addr + size) <= addr)) + if (((addr + size) < addr) || + PAGE_ALIGN(addr + size) < (addr + size)) return ERR_PTR(-EINVAL); if (!can_do_mlock()) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 259dcc7779f5..88cce9bb72fe 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -246,6 +246,17 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, kfree(uqp); } + list_for_each_entry_safe(uobj, tmp, &context->srq_list, list) { + struct ib_srq *srq = uobj->object; + struct ib_uevent_object *uevent = + container_of(uobj, struct ib_uevent_object, uobject); + + idr_remove_uobj(&ib_uverbs_srq_idr, uobj); + ib_destroy_srq(srq); + ib_uverbs_release_uevent(file, uevent); + kfree(uevent); + } + list_for_each_entry_safe(uobj, tmp, &context->cq_list, list) { struct ib_cq *cq = uobj->object; struct ib_uverbs_event_file *ev_file = cq->cq_context; @@ -258,17 +269,6 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, kfree(ucq); } - list_for_each_entry_safe(uobj, tmp, &context->srq_list, list) { - struct ib_srq *srq = uobj->object; - struct ib_uevent_object *uevent = - container_of(uobj, struct ib_uevent_object, uobject); - - idr_remove_uobj(&ib_uverbs_srq_idr, uobj); - ib_destroy_srq(srq); - ib_uverbs_release_uevent(file, uevent); - kfree(uevent); - } - list_for_each_entry_safe(uobj, tmp, &context->mr_list, list) { struct ib_mr *mr = uobj->object; diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c index 33c45dfcbd88..1ca8e32a9592 100644 --- a/drivers/infiniband/hw/ipath/ipath_fs.c +++ b/drivers/infiniband/hw/ipath/ipath_fs.c @@ -82,14 +82,14 @@ static int create_file(const char *name, umode_t mode, { int error; - mutex_lock(&parent->d_inode->i_mutex); + mutex_lock(&d_inode(parent)->i_mutex); *dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(*dentry)) - error = ipathfs_mknod(parent->d_inode, *dentry, + error = ipathfs_mknod(d_inode(parent), *dentry, mode, fops, data); else error = PTR_ERR(*dentry); - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); return error; } @@ -277,11 +277,11 @@ static int remove_file(struct dentry *parent, char *name) } spin_lock(&tmp->d_lock); - if (!d_unhashed(tmp) && tmp->d_inode) { + if (!d_unhashed(tmp) && d_really_is_positive(tmp)) { dget_dlock(tmp); __d_drop(tmp); spin_unlock(&tmp->d_lock); - simple_unlink(parent->d_inode, tmp); + simple_unlink(d_inode(parent), tmp); } else spin_unlock(&tmp->d_lock); @@ -302,7 +302,7 @@ static int remove_device_files(struct super_block *sb, int ret; root = dget(sb->s_root); - mutex_lock(&root->d_inode->i_mutex); + mutex_lock(&d_inode(root)->i_mutex); snprintf(unit, sizeof unit, "%02d", dd->ipath_unit); dir = lookup_one_len(unit, root, strlen(unit)); @@ -315,10 +315,10 @@ static int remove_device_files(struct super_block *sb, remove_file(dir, "flash"); remove_file(dir, "atomic_counters"); d_delete(dir); - ret = simple_rmdir(root->d_inode, dir); + ret = simple_rmdir(d_inode(root), dir); bail: - mutex_unlock(&root->d_inode->i_mutex); + mutex_unlock(&d_inode(root)->i_mutex); dput(root); return ret; } diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c index a31e031afd87..0f00204d2ece 100644 --- a/drivers/infiniband/hw/mlx4/alias_GUID.c +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -58,14 +58,19 @@ struct mlx4_alias_guid_work_context { int query_id; struct list_head list; int block_num; + ib_sa_comp_mask guid_indexes; + u8 method; }; struct mlx4_next_alias_guid_work { u8 port; u8 block_num; + u8 method; struct mlx4_sriov_alias_guid_info_rec_det rec_det; }; +static int get_low_record_time_index(struct mlx4_ib_dev *dev, u8 port, + int *resched_delay_sec); void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, int block_num, u8 port_num, u8 *p_data) @@ -118,6 +123,57 @@ ib_sa_comp_mask mlx4_ib_get_aguid_comp_mask_from_ix(int index) return IB_SA_COMP_MASK(4 + index); } +void mlx4_ib_slave_alias_guid_event(struct mlx4_ib_dev *dev, int slave, + int port, int slave_init) +{ + __be64 curr_guid, required_guid; + int record_num = slave / 8; + int index = slave % 8; + int port_index = port - 1; + unsigned long flags; + int do_work = 0; + + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); + if (dev->sriov.alias_guid.ports_guid[port_index].state_flags & + GUID_STATE_NEED_PORT_INIT) + goto unlock; + if (!slave_init) { + curr_guid = *(__be64 *)&dev->sriov. + alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num]. + all_recs[GUID_REC_SIZE * index]; + if (curr_guid == cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL) || + !curr_guid) + goto unlock; + required_guid = cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL); + } else { + required_guid = mlx4_get_admin_guid(dev->dev, slave, port); + if (required_guid == cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL)) + goto unlock; + } + *(__be64 *)&dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num]. + all_recs[GUID_REC_SIZE * index] = required_guid; + dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num].guid_indexes + |= mlx4_ib_get_aguid_comp_mask_from_ix(index); + dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num].status + = MLX4_GUID_INFO_STATUS_IDLE; + /* set to run immediately */ + dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num].time_to_run = 0; + dev->sriov.alias_guid.ports_guid[port_index]. + all_rec_per_port[record_num]. + guids_retry_schedule[index] = 0; + do_work = 1; +unlock: + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); + + if (do_work) + mlx4_ib_init_alias_guid_work(dev, port_index); +} + /* * Whenever new GUID is set/unset (guid table change) create event and * notify the relevant slave (master also should be notified). @@ -138,10 +194,15 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, enum slave_port_state prev_state; __be64 tmp_cur_ag, form_cache_ag; enum slave_port_gen_event gen_event; + struct mlx4_sriov_alias_guid_info_rec_det *rec; + unsigned long flags; + __be64 required_value; if (!mlx4_is_master(dev->dev)) return; + rec = &dev->sriov.alias_guid.ports_guid[port_num - 1]. + all_rec_per_port[block_num]; guid_indexes = be64_to_cpu((__force __be64) dev->sriov.alias_guid. ports_guid[port_num - 1]. all_rec_per_port[block_num].guid_indexes); @@ -166,8 +227,27 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, */ if (tmp_cur_ag != form_cache_ag) continue; - mlx4_gen_guid_change_eqe(dev->dev, slave_id, port_num); + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); + required_value = *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE]; + + if (required_value == cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL)) + required_value = 0; + + if (tmp_cur_ag == required_value) { + rec->guid_indexes = rec->guid_indexes & + ~mlx4_ib_get_aguid_comp_mask_from_ix(i); + } else { + /* may notify port down if value is 0 */ + if (tmp_cur_ag != MLX4_NOT_SET_GUID) { + spin_unlock_irqrestore(&dev->sriov. + alias_guid.ag_work_lock, flags); + continue; + } + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, + flags); + mlx4_gen_guid_change_eqe(dev->dev, slave_id, port_num); /*2 cases: Valid GUID, and Invalid Guid*/ if (tmp_cur_ag != MLX4_NOT_SET_GUID) { /*valid GUID*/ @@ -188,10 +268,14 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, set_and_calc_slave_port_state(dev->dev, slave_id, port_num, MLX4_PORT_STATE_IB_EVENT_GID_INVALID, &gen_event); - pr_debug("sending PORT DOWN event to slave: %d, port: %d\n", - slave_id, port_num); - mlx4_gen_port_state_change_eqe(dev->dev, slave_id, port_num, - MLX4_PORT_CHANGE_SUBTYPE_DOWN); + if (gen_event == SLAVE_PORT_GEN_EVENT_DOWN) { + pr_debug("sending PORT DOWN event to slave: %d, port: %d\n", + slave_id, port_num); + mlx4_gen_port_state_change_eqe(dev->dev, + slave_id, + port_num, + MLX4_PORT_CHANGE_SUBTYPE_DOWN); + } } } } @@ -206,6 +290,9 @@ static void aliasguid_query_handler(int status, int i; struct mlx4_sriov_alias_guid_info_rec_det *rec; unsigned long flags, flags1; + ib_sa_comp_mask declined_guid_indexes = 0; + ib_sa_comp_mask applied_guid_indexes = 0; + unsigned int resched_delay_sec = 0; if (!context) return; @@ -216,9 +303,9 @@ static void aliasguid_query_handler(int status, all_rec_per_port[cb_ctx->block_num]; if (status) { - rec->status = MLX4_GUID_INFO_STATUS_IDLE; pr_debug("(port: %d) failed: status = %d\n", cb_ctx->port, status); + rec->time_to_run = ktime_get_real_ns() + 1 * NSEC_PER_SEC; goto out; } @@ -235,57 +322,101 @@ static void aliasguid_query_handler(int status, rec = &dev->sriov.alias_guid.ports_guid[port_index]. all_rec_per_port[guid_rec->block_num]; - rec->status = MLX4_GUID_INFO_STATUS_SET; - rec->method = MLX4_GUID_INFO_RECORD_SET; - + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); for (i = 0 ; i < NUM_ALIAS_GUID_IN_REC; i++) { - __be64 tmp_cur_ag; - tmp_cur_ag = *(__be64 *)&guid_rec->guid_info_list[i * GUID_REC_SIZE]; + __be64 sm_response, required_val; + + if (!(cb_ctx->guid_indexes & + mlx4_ib_get_aguid_comp_mask_from_ix(i))) + continue; + sm_response = *(__be64 *)&guid_rec->guid_info_list + [i * GUID_REC_SIZE]; + required_val = *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE]; + if (cb_ctx->method == MLX4_GUID_INFO_RECORD_DELETE) { + if (required_val == + cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL)) + goto next_entry; + + /* A new value was set till we got the response */ + pr_debug("need to set new value %llx, record num %d, block_num:%d\n", + be64_to_cpu(required_val), + i, guid_rec->block_num); + goto entry_declined; + } + /* check if the SM didn't assign one of the records. - * if it didn't, if it was not sysadmin request: - * ask the SM to give a new GUID, (instead of the driver request). + * if it didn't, re-ask for. */ - if (tmp_cur_ag == MLX4_NOT_SET_GUID) { - mlx4_ib_warn(&dev->ib_dev, "%s:Record num %d in " - "block_num: %d was declined by SM, " - "ownership by %d (0 = driver, 1=sysAdmin," - " 2=None)\n", __func__, i, - guid_rec->block_num, rec->ownership); - if (rec->ownership == MLX4_GUID_DRIVER_ASSIGN) { - /* if it is driver assign, asks for new GUID from SM*/ - *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE] = - MLX4_NOT_SET_GUID; - - /* Mark the record as not assigned, and let it - * be sent again in the next work sched.*/ - rec->status = MLX4_GUID_INFO_STATUS_IDLE; - rec->guid_indexes |= mlx4_ib_get_aguid_comp_mask_from_ix(i); - } + if (sm_response == MLX4_NOT_SET_GUID) { + if (rec->guids_retry_schedule[i] == 0) + mlx4_ib_warn(&dev->ib_dev, + "%s:Record num %d in block_num: %d was declined by SM\n", + __func__, i, + guid_rec->block_num); + goto entry_declined; } else { /* properly assigned record. */ /* We save the GUID we just got from the SM in the * admin_guid in order to be persistent, and in the * request from the sm the process will ask for the same GUID */ - if (rec->ownership == MLX4_GUID_SYSADMIN_ASSIGN && - tmp_cur_ag != *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE]) { - /* the sysadmin assignment failed.*/ - mlx4_ib_warn(&dev->ib_dev, "%s: Failed to set" - " admin guid after SysAdmin " - "configuration. " - "Record num %d in block_num:%d " - "was declined by SM, " - "new val(0x%llx) was kept\n", - __func__, i, - guid_rec->block_num, - be64_to_cpu(*(__be64 *) & - rec->all_recs[i * GUID_REC_SIZE])); + if (required_val && + sm_response != required_val) { + /* Warn only on first retry */ + if (rec->guids_retry_schedule[i] == 0) + mlx4_ib_warn(&dev->ib_dev, "%s: Failed to set" + " admin guid after SysAdmin " + "configuration. " + "Record num %d in block_num:%d " + "was declined by SM, " + "new val(0x%llx) was kept, SM returned (0x%llx)\n", + __func__, i, + guid_rec->block_num, + be64_to_cpu(required_val), + be64_to_cpu(sm_response)); + goto entry_declined; } else { - memcpy(&rec->all_recs[i * GUID_REC_SIZE], - &guid_rec->guid_info_list[i * GUID_REC_SIZE], - GUID_REC_SIZE); + *(__be64 *)&rec->all_recs[i * GUID_REC_SIZE] = + sm_response; + if (required_val == 0) + mlx4_set_admin_guid(dev->dev, + sm_response, + (guid_rec->block_num + * NUM_ALIAS_GUID_IN_REC) + i, + cb_ctx->port); + goto next_entry; } } +entry_declined: + declined_guid_indexes |= mlx4_ib_get_aguid_comp_mask_from_ix(i); + rec->guids_retry_schedule[i] = + (rec->guids_retry_schedule[i] == 0) ? 1 : + min((unsigned int)60, + rec->guids_retry_schedule[i] * 2); + /* using the minimum value among all entries in that record */ + resched_delay_sec = (resched_delay_sec == 0) ? + rec->guids_retry_schedule[i] : + min(resched_delay_sec, + rec->guids_retry_schedule[i]); + continue; + +next_entry: + rec->guids_retry_schedule[i] = 0; } + + applied_guid_indexes = cb_ctx->guid_indexes & ~declined_guid_indexes; + if (declined_guid_indexes || + rec->guid_indexes & ~(applied_guid_indexes)) { + pr_debug("record=%d wasn't fully set, guid_indexes=0x%llx applied_indexes=0x%llx, declined_indexes=0x%llx\n", + guid_rec->block_num, + be64_to_cpu((__force __be64)rec->guid_indexes), + be64_to_cpu((__force __be64)applied_guid_indexes), + be64_to_cpu((__force __be64)declined_guid_indexes)); + rec->time_to_run = ktime_get_real_ns() + + resched_delay_sec * NSEC_PER_SEC; + } else { + rec->status = MLX4_GUID_INFO_STATUS_SET; + } + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); /* The func is call here to close the cases when the sm doesn't send smp, so in the sa response the driver @@ -297,10 +428,13 @@ static void aliasguid_query_handler(int status, out: spin_lock_irqsave(&dev->sriov.going_down_lock, flags); spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); - if (!dev->sriov.is_going_down) + if (!dev->sriov.is_going_down) { + get_low_record_time_index(dev, port_index, &resched_delay_sec); queue_delayed_work(dev->sriov.alias_guid.ports_guid[port_index].wq, &dev->sriov.alias_guid.ports_guid[port_index]. - alias_guid_work, 0); + alias_guid_work, + msecs_to_jiffies(resched_delay_sec * 1000)); + } if (cb_ctx->sa_query) { list_del(&cb_ctx->list); kfree(cb_ctx); @@ -317,9 +451,7 @@ static void invalidate_guid_record(struct mlx4_ib_dev *dev, u8 port, int index) ib_sa_comp_mask comp_mask = 0; dev->sriov.alias_guid.ports_guid[port - 1].all_rec_per_port[index].status - = MLX4_GUID_INFO_STATUS_IDLE; - dev->sriov.alias_guid.ports_guid[port - 1].all_rec_per_port[index].method - = MLX4_GUID_INFO_RECORD_SET; + = MLX4_GUID_INFO_STATUS_SET; /* calculate the comp_mask for that record.*/ for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { @@ -333,19 +465,21 @@ static void invalidate_guid_record(struct mlx4_ib_dev *dev, u8 port, int index) need to assign GUIDs, then don't put it up for assignment. */ if (MLX4_GUID_FOR_DELETE_VAL == cur_admin_val || - (!index && !i) || - MLX4_GUID_NONE_ASSIGN == dev->sriov.alias_guid. - ports_guid[port - 1].all_rec_per_port[index].ownership) + (!index && !i)) continue; comp_mask |= mlx4_ib_get_aguid_comp_mask_from_ix(i); } dev->sriov.alias_guid.ports_guid[port - 1]. - all_rec_per_port[index].guid_indexes = comp_mask; + all_rec_per_port[index].guid_indexes |= comp_mask; + if (dev->sriov.alias_guid.ports_guid[port - 1]. + all_rec_per_port[index].guid_indexes) + dev->sriov.alias_guid.ports_guid[port - 1]. + all_rec_per_port[index].status = MLX4_GUID_INFO_STATUS_IDLE; + } static int set_guid_rec(struct ib_device *ibdev, - u8 port, int index, - struct mlx4_sriov_alias_guid_info_rec_det *rec_det) + struct mlx4_next_alias_guid_work *rec) { int err; struct mlx4_ib_dev *dev = to_mdev(ibdev); @@ -354,6 +488,9 @@ static int set_guid_rec(struct ib_device *ibdev, struct ib_port_attr attr; struct mlx4_alias_guid_work_context *callback_context; unsigned long resched_delay, flags, flags1; + u8 port = rec->port + 1; + int index = rec->block_num; + struct mlx4_sriov_alias_guid_info_rec_det *rec_det = &rec->rec_det; struct list_head *head = &dev->sriov.alias_guid.ports_guid[port - 1].cb_list; @@ -380,6 +517,8 @@ static int set_guid_rec(struct ib_device *ibdev, callback_context->port = port; callback_context->dev = dev; callback_context->block_num = index; + callback_context->guid_indexes = rec_det->guid_indexes; + callback_context->method = rec->method; memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec)); @@ -399,7 +538,7 @@ static int set_guid_rec(struct ib_device *ibdev, callback_context->query_id = ib_sa_guid_info_rec_query(dev->sriov.alias_guid.sa_client, ibdev, port, &guid_info_rec, - comp_mask, rec_det->method, 1000, + comp_mask, rec->method, 1000, GFP_KERNEL, aliasguid_query_handler, callback_context, &callback_context->sa_query); @@ -434,6 +573,30 @@ out: return err; } +static void mlx4_ib_guid_port_init(struct mlx4_ib_dev *dev, int port) +{ + int j, k, entry; + __be64 guid; + + /*Check if the SM doesn't need to assign the GUIDs*/ + for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { + for (k = 0; k < NUM_ALIAS_GUID_IN_REC; k++) { + entry = j * NUM_ALIAS_GUID_IN_REC + k; + /* no request for the 0 entry (hw guid) */ + if (!entry || entry > dev->dev->persist->num_vfs || + !mlx4_is_slave_active(dev->dev, entry)) + continue; + guid = mlx4_get_admin_guid(dev->dev, entry, port); + *(__be64 *)&dev->sriov.alias_guid.ports_guid[port - 1]. + all_rec_per_port[j].all_recs + [GUID_REC_SIZE * k] = guid; + pr_debug("guid was set, entry=%d, val=0x%llx, port=%d\n", + entry, + be64_to_cpu(guid), + port); + } + } +} void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port) { int i; @@ -443,6 +606,13 @@ void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port) spin_lock_irqsave(&dev->sriov.going_down_lock, flags); spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); + + if (dev->sriov.alias_guid.ports_guid[port - 1].state_flags & + GUID_STATE_NEED_PORT_INIT) { + mlx4_ib_guid_port_init(dev, port); + dev->sriov.alias_guid.ports_guid[port - 1].state_flags &= + (~GUID_STATE_NEED_PORT_INIT); + } for (i = 0; i < NUM_ALIAS_GUID_REC_IN_PORT; i++) invalidate_guid_record(dev, port, i); @@ -462,60 +632,107 @@ void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port) spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags); } -/* The function returns the next record that was - * not configured (or failed to be configured) */ -static int get_next_record_to_update(struct mlx4_ib_dev *dev, u8 port, - struct mlx4_next_alias_guid_work *rec) +static void set_required_record(struct mlx4_ib_dev *dev, u8 port, + struct mlx4_next_alias_guid_work *next_rec, + int record_index) { - int j; - unsigned long flags; + int i; + int lowset_time_entry = -1; + int lowest_time = 0; + ib_sa_comp_mask delete_guid_indexes = 0; + ib_sa_comp_mask set_guid_indexes = 0; + struct mlx4_sriov_alias_guid_info_rec_det *rec = + &dev->sriov.alias_guid.ports_guid[port]. + all_rec_per_port[record_index]; - for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { - spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); - if (dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j].status == - MLX4_GUID_INFO_STATUS_IDLE) { - memcpy(&rec->rec_det, - &dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j], - sizeof (struct mlx4_sriov_alias_guid_info_rec_det)); - rec->port = port; - rec->block_num = j; - dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[j].status = - MLX4_GUID_INFO_STATUS_PENDING; - spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); - return 0; + for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { + if (!(rec->guid_indexes & + mlx4_ib_get_aguid_comp_mask_from_ix(i))) + continue; + + if (*(__be64 *)&rec->all_recs[i * GUID_REC_SIZE] == + cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL)) + delete_guid_indexes |= + mlx4_ib_get_aguid_comp_mask_from_ix(i); + else + set_guid_indexes |= + mlx4_ib_get_aguid_comp_mask_from_ix(i); + + if (lowset_time_entry == -1 || rec->guids_retry_schedule[i] <= + lowest_time) { + lowset_time_entry = i; + lowest_time = rec->guids_retry_schedule[i]; } - spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); } - return -ENOENT; + + memcpy(&next_rec->rec_det, rec, sizeof(*rec)); + next_rec->port = port; + next_rec->block_num = record_index; + + if (*(__be64 *)&rec->all_recs[lowset_time_entry * GUID_REC_SIZE] == + cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL)) { + next_rec->rec_det.guid_indexes = delete_guid_indexes; + next_rec->method = MLX4_GUID_INFO_RECORD_DELETE; + } else { + next_rec->rec_det.guid_indexes = set_guid_indexes; + next_rec->method = MLX4_GUID_INFO_RECORD_SET; + } } -static void set_administratively_guid_record(struct mlx4_ib_dev *dev, int port, - int rec_index, - struct mlx4_sriov_alias_guid_info_rec_det *rec_det) +/* return index of record that should be updated based on lowest + * rescheduled time + */ +static int get_low_record_time_index(struct mlx4_ib_dev *dev, u8 port, + int *resched_delay_sec) { - dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].guid_indexes = - rec_det->guid_indexes; - memcpy(dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].all_recs, - rec_det->all_recs, NUM_ALIAS_GUID_IN_REC * GUID_REC_SIZE); - dev->sriov.alias_guid.ports_guid[port].all_rec_per_port[rec_index].status = - rec_det->status; + int record_index = -1; + u64 low_record_time = 0; + struct mlx4_sriov_alias_guid_info_rec_det rec; + int j; + + for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { + rec = dev->sriov.alias_guid.ports_guid[port]. + all_rec_per_port[j]; + if (rec.status == MLX4_GUID_INFO_STATUS_IDLE && + rec.guid_indexes) { + if (record_index == -1 || + rec.time_to_run < low_record_time) { + record_index = j; + low_record_time = rec.time_to_run; + } + } + } + if (resched_delay_sec) { + u64 curr_time = ktime_get_real_ns(); + + *resched_delay_sec = (low_record_time < curr_time) ? 0 : + div_u64((low_record_time - curr_time), NSEC_PER_SEC); + } + + return record_index; } -static void set_all_slaves_guids(struct mlx4_ib_dev *dev, int port) +/* The function returns the next record that was + * not configured (or failed to be configured) */ +static int get_next_record_to_update(struct mlx4_ib_dev *dev, u8 port, + struct mlx4_next_alias_guid_work *rec) { - int j; - struct mlx4_sriov_alias_guid_info_rec_det rec_det ; - - for (j = 0 ; j < NUM_ALIAS_GUID_REC_IN_PORT ; j++) { - memset(rec_det.all_recs, 0, NUM_ALIAS_GUID_IN_REC * GUID_REC_SIZE); - rec_det.guid_indexes = (!j ? 0 : IB_SA_GUIDINFO_REC_GID0) | - IB_SA_GUIDINFO_REC_GID1 | IB_SA_GUIDINFO_REC_GID2 | - IB_SA_GUIDINFO_REC_GID3 | IB_SA_GUIDINFO_REC_GID4 | - IB_SA_GUIDINFO_REC_GID5 | IB_SA_GUIDINFO_REC_GID6 | - IB_SA_GUIDINFO_REC_GID7; - rec_det.status = MLX4_GUID_INFO_STATUS_IDLE; - set_administratively_guid_record(dev, port, j, &rec_det); + unsigned long flags; + int record_index; + int ret = 0; + + spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags); + record_index = get_low_record_time_index(dev, port, NULL); + + if (record_index < 0) { + ret = -ENOENT; + goto out; } + + set_required_record(dev, port, rec, record_index); +out: + spin_unlock_irqrestore(&dev->sriov.alias_guid.ag_work_lock, flags); + return ret; } static void alias_guid_work(struct work_struct *work) @@ -545,9 +762,7 @@ static void alias_guid_work(struct work_struct *work) goto out; } - set_guid_rec(&dev->ib_dev, rec->port + 1, rec->block_num, - &rec->rec_det); - + set_guid_rec(&dev->ib_dev, rec); out: kfree(rec); } @@ -562,6 +777,12 @@ void mlx4_ib_init_alias_guid_work(struct mlx4_ib_dev *dev, int port) spin_lock_irqsave(&dev->sriov.going_down_lock, flags); spin_lock_irqsave(&dev->sriov.alias_guid.ag_work_lock, flags1); if (!dev->sriov.is_going_down) { + /* If there is pending one should cancell then run, otherwise + * won't run till previous one is ended as same work + * struct is used. + */ + cancel_delayed_work(&dev->sriov.alias_guid.ports_guid[port]. + alias_guid_work); queue_delayed_work(dev->sriov.alias_guid.ports_guid[port].wq, &dev->sriov.alias_guid.ports_guid[port].alias_guid_work, 0); } @@ -609,7 +830,7 @@ int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev) { char alias_wq_name[15]; int ret = 0; - int i, j, k; + int i, j; union ib_gid gid; if (!mlx4_is_master(dev->dev)) @@ -633,33 +854,25 @@ int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev) for (i = 0 ; i < dev->num_ports; i++) { memset(&dev->sriov.alias_guid.ports_guid[i], 0, sizeof (struct mlx4_sriov_alias_guid_port_rec_det)); - /*Check if the SM doesn't need to assign the GUIDs*/ + dev->sriov.alias_guid.ports_guid[i].state_flags |= + GUID_STATE_NEED_PORT_INIT; for (j = 0; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) { - if (mlx4_ib_sm_guid_assign) { - dev->sriov.alias_guid.ports_guid[i]. - all_rec_per_port[j]. - ownership = MLX4_GUID_DRIVER_ASSIGN; - continue; - } - dev->sriov.alias_guid.ports_guid[i].all_rec_per_port[j]. - ownership = MLX4_GUID_NONE_ASSIGN; - /*mark each val as it was deleted, - till the sysAdmin will give it valid val*/ - for (k = 0; k < NUM_ALIAS_GUID_IN_REC; k++) { - *(__be64 *)&dev->sriov.alias_guid.ports_guid[i]. - all_rec_per_port[j].all_recs[GUID_REC_SIZE * k] = - cpu_to_be64(MLX4_GUID_FOR_DELETE_VAL); - } + /* mark each val as it was deleted */ + memset(dev->sriov.alias_guid.ports_guid[i]. + all_rec_per_port[j].all_recs, 0xFF, + sizeof(dev->sriov.alias_guid.ports_guid[i]. + all_rec_per_port[j].all_recs)); } INIT_LIST_HEAD(&dev->sriov.alias_guid.ports_guid[i].cb_list); /*prepare the records, set them to be allocated by sm*/ + if (mlx4_ib_sm_guid_assign) + for (j = 1; j < NUM_ALIAS_GUID_PER_PORT; j++) + mlx4_set_admin_guid(dev->dev, 0, j, i + 1); for (j = 0 ; j < NUM_ALIAS_GUID_REC_IN_PORT; j++) invalidate_guid_record(dev, i + 1, j); dev->sriov.alias_guid.ports_guid[i].parent = &dev->sriov.alias_guid; dev->sriov.alias_guid.ports_guid[i].port = i; - if (mlx4_ib_sm_guid_assign) - set_all_slaves_guids(dev, i); snprintf(alias_wq_name, sizeof alias_wq_name, "alias_guid%d", i); dev->sriov.alias_guid.ports_guid[i].wq = diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 59040265e361..9cd2b002d7ae 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -1430,6 +1430,10 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, tun_qp->ring[i].addr, rx_buf_size, DMA_FROM_DEVICE); + if (ib_dma_mapping_error(ctx->ib_dev, tun_qp->ring[i].map)) { + kfree(tun_qp->ring[i].addr); + goto err; + } } for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) { @@ -1442,6 +1446,11 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, tun_qp->tx_ring[i].buf.addr, tx_buf_size, DMA_TO_DEVICE); + if (ib_dma_mapping_error(ctx->ib_dev, + tun_qp->tx_ring[i].buf.map)) { + kfree(tun_qp->tx_ring[i].buf.addr); + goto tx_err; + } tun_qp->tx_ring[i].ah = NULL; } spin_lock_init(&tun_qp->tx_lock); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 976bea794b5f..57070c529dfb 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -66,9 +66,9 @@ MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(DRV_VERSION); -int mlx4_ib_sm_guid_assign = 1; +int mlx4_ib_sm_guid_assign = 0; module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444); -MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 1)"); +MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 0)"); static const char mlx4_ib_version[] = DRV_NAME ": Mellanox ConnectX InfiniBand driver v" @@ -2791,9 +2791,31 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_SLAVE_INIT: /* here, p is the slave id */ do_slave_init(ibdev, p, 1); + if (mlx4_is_master(dev)) { + int i; + + for (i = 1; i <= ibdev->num_ports; i++) { + if (rdma_port_get_link_layer(&ibdev->ib_dev, i) + == IB_LINK_LAYER_INFINIBAND) + mlx4_ib_slave_alias_guid_event(ibdev, + p, i, + 1); + } + } return; case MLX4_DEV_EVENT_SLAVE_SHUTDOWN: + if (mlx4_is_master(dev)) { + int i; + + for (i = 1; i <= ibdev->num_ports; i++) { + if (rdma_port_get_link_layer(&ibdev->ib_dev, i) + == IB_LINK_LAYER_INFINIBAND) + mlx4_ib_slave_alias_guid_event(ibdev, + p, i, + 0); + } + } /* here, p is the slave id */ do_slave_init(ibdev, p, 0); return; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index f829fd935b79..fce3934372a1 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -342,14 +342,9 @@ struct mlx4_ib_ah { enum mlx4_guid_alias_rec_status { MLX4_GUID_INFO_STATUS_IDLE, MLX4_GUID_INFO_STATUS_SET, - MLX4_GUID_INFO_STATUS_PENDING, }; -enum mlx4_guid_alias_rec_ownership { - MLX4_GUID_DRIVER_ASSIGN, - MLX4_GUID_SYSADMIN_ASSIGN, - MLX4_GUID_NONE_ASSIGN, /*init state of each record*/ -}; +#define GUID_STATE_NEED_PORT_INIT 0x01 enum mlx4_guid_alias_rec_method { MLX4_GUID_INFO_RECORD_SET = IB_MGMT_METHOD_SET, @@ -360,8 +355,8 @@ struct mlx4_sriov_alias_guid_info_rec_det { u8 all_recs[GUID_REC_SIZE * NUM_ALIAS_GUID_IN_REC]; ib_sa_comp_mask guid_indexes; /*indicates what from the 8 records are valid*/ enum mlx4_guid_alias_rec_status status; /*indicates the administraively status of the record.*/ - u8 method; /*set or delete*/ - enum mlx4_guid_alias_rec_ownership ownership; /*indicates who assign that alias_guid record*/ + unsigned int guids_retry_schedule[NUM_ALIAS_GUID_IN_REC]; + u64 time_to_run; }; struct mlx4_sriov_alias_guid_port_rec_det { @@ -369,6 +364,7 @@ struct mlx4_sriov_alias_guid_port_rec_det { struct workqueue_struct *wq; struct delayed_work alias_guid_work; u8 port; + u32 state_flags; struct mlx4_sriov_alias_guid *parent; struct list_head cb_list; }; @@ -802,6 +798,8 @@ int add_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num, void del_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num, struct attribute *attr); ib_sa_comp_mask mlx4_ib_get_aguid_comp_mask_from_ix(int index); +void mlx4_ib_slave_alias_guid_event(struct mlx4_ib_dev *dev, int slave, + int port, int slave_init); int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *device) ; diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index ed2bd6701f9b..02fc91c68027 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -566,6 +566,10 @@ static int alloc_proxy_bufs(struct ib_device *dev, struct mlx4_ib_qp *qp) ib_dma_map_single(dev, qp->sqp_proxy_rcv[i].addr, sizeof (struct mlx4_ib_proxy_sqp_hdr), DMA_FROM_DEVICE); + if (ib_dma_mapping_error(dev, qp->sqp_proxy_rcv[i].map)) { + kfree(qp->sqp_proxy_rcv[i].addr); + goto err; + } } return 0; @@ -2605,8 +2609,7 @@ static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe, struct ib_send_wr *wr, memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen); - *lso_hdr_sz = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 | - wr->wr.ud.hlen); + *lso_hdr_sz = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen); *lso_seg_len = halign; return 0; } diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c index d10c2b8a5dad..6797108ce873 100644 --- a/drivers/infiniband/hw/mlx4/sysfs.c +++ b/drivers/infiniband/hw/mlx4/sysfs.c @@ -46,21 +46,17 @@ static ssize_t show_admin_alias_guid(struct device *dev, struct device_attribute *attr, char *buf) { - int record_num;/*0-15*/ - int guid_index_in_rec; /*0 - 7*/ struct mlx4_ib_iov_sysfs_attr *mlx4_ib_iov_dentry = container_of(attr, struct mlx4_ib_iov_sysfs_attr, dentry); struct mlx4_ib_iov_port *port = mlx4_ib_iov_dentry->ctx; struct mlx4_ib_dev *mdev = port->dev; + __be64 sysadmin_ag_val; - record_num = mlx4_ib_iov_dentry->entry_num / 8 ; - guid_index_in_rec = mlx4_ib_iov_dentry->entry_num % 8 ; + sysadmin_ag_val = mlx4_get_admin_guid(mdev->dev, + mlx4_ib_iov_dentry->entry_num, + port->num); - return sprintf(buf, "%llx\n", - be64_to_cpu(*(__be64 *)&mdev->sriov.alias_guid. - ports_guid[port->num - 1]. - all_rec_per_port[record_num]. - all_recs[8 * guid_index_in_rec])); + return sprintf(buf, "%llx\n", be64_to_cpu(sysadmin_ag_val)); } /* store_admin_alias_guid stores the (new) administratively assigned value of that GUID. @@ -80,6 +76,7 @@ static ssize_t store_admin_alias_guid(struct device *dev, struct mlx4_ib_iov_port *port = mlx4_ib_iov_dentry->ctx; struct mlx4_ib_dev *mdev = port->dev; u64 sysadmin_ag_val; + unsigned long flags; record_num = mlx4_ib_iov_dentry->entry_num / 8; guid_index_in_rec = mlx4_ib_iov_dentry->entry_num % 8; @@ -87,6 +84,7 @@ static ssize_t store_admin_alias_guid(struct device *dev, pr_err("GUID 0 block 0 is RO\n"); return count; } + spin_lock_irqsave(&mdev->sriov.alias_guid.ag_work_lock, flags); sscanf(buf, "%llx", &sysadmin_ag_val); *(__be64 *)&mdev->sriov.alias_guid.ports_guid[port->num - 1]. all_rec_per_port[record_num]. @@ -96,33 +94,15 @@ static ssize_t store_admin_alias_guid(struct device *dev, /* Change the state to be pending for update */ mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].status = MLX4_GUID_INFO_STATUS_IDLE ; - - mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].method - = MLX4_GUID_INFO_RECORD_SET; - - switch (sysadmin_ag_val) { - case MLX4_GUID_FOR_DELETE_VAL: - mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].method - = MLX4_GUID_INFO_RECORD_DELETE; - mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership - = MLX4_GUID_SYSADMIN_ASSIGN; - break; - /* The sysadmin requests the SM to re-assign */ - case MLX4_NOT_SET_GUID: - mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership - = MLX4_GUID_DRIVER_ASSIGN; - break; - /* The sysadmin requests a specific value.*/ - default: - mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].ownership - = MLX4_GUID_SYSADMIN_ASSIGN; - break; - } + mlx4_set_admin_guid(mdev->dev, cpu_to_be64(sysadmin_ag_val), + mlx4_ib_iov_dentry->entry_num, + port->num); /* set the record index */ mdev->sriov.alias_guid.ports_guid[port->num - 1].all_rec_per_port[record_num].guid_indexes - = mlx4_ib_get_aguid_comp_mask_from_ix(guid_index_in_rec); + |= mlx4_ib_get_aguid_comp_mask_from_ix(guid_index_in_rec); + spin_unlock_irqrestore(&mdev->sriov.alias_guid.ag_work_lock, flags); mlx4_ib_init_alias_guid_work(mdev, port->num - 1); return count; diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index 650897a8591e..bdd5d3857203 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -89,14 +89,14 @@ static int create_file(const char *name, umode_t mode, { int error; - mutex_lock(&parent->d_inode->i_mutex); + mutex_lock(&d_inode(parent)->i_mutex); *dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(*dentry)) - error = qibfs_mknod(parent->d_inode, *dentry, + error = qibfs_mknod(d_inode(parent), *dentry, mode, fops, data); else error = PTR_ERR(*dentry); - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); return error; } @@ -455,10 +455,10 @@ static int remove_file(struct dentry *parent, char *name) } spin_lock(&tmp->d_lock); - if (!d_unhashed(tmp) && tmp->d_inode) { + if (!d_unhashed(tmp) && d_really_is_positive(tmp)) { __d_drop(tmp); spin_unlock(&tmp->d_lock); - simple_unlink(parent->d_inode, tmp); + simple_unlink(d_inode(parent), tmp); } else { spin_unlock(&tmp->d_lock); } @@ -481,7 +481,7 @@ static int remove_device_files(struct super_block *sb, int ret, i; root = dget(sb->s_root); - mutex_lock(&root->d_inode->i_mutex); + mutex_lock(&d_inode(root)->i_mutex); snprintf(unit, sizeof(unit), "%u", dd->unit); dir = lookup_one_len(unit, root, strlen(unit)); @@ -491,7 +491,7 @@ static int remove_device_files(struct super_block *sb, goto bail; } - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock(&d_inode(dir)->i_mutex); remove_file(dir, "counters"); remove_file(dir, "counter_names"); remove_file(dir, "portcounter_names"); @@ -506,13 +506,13 @@ static int remove_device_files(struct super_block *sb, } } remove_file(dir, "flash"); - mutex_unlock(&dir->d_inode->i_mutex); - ret = simple_rmdir(root->d_inode, dir); + mutex_unlock(&d_inode(dir)->i_mutex); + ret = simple_rmdir(d_inode(root), dir); d_delete(dir); dput(dir); bail: - mutex_unlock(&root->d_inode->i_mutex); + mutex_unlock(&d_inode(root)->i_mutex); dput(root); return ret; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index d7562beb5423..bd94b0a6e9e5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -87,7 +87,6 @@ enum { IPOIB_FLAG_ADMIN_UP = 2, IPOIB_PKEY_ASSIGNED = 3, IPOIB_FLAG_SUBINTERFACE = 5, - IPOIB_MCAST_RUN = 6, IPOIB_STOP_REAPER = 7, IPOIB_FLAG_ADMIN_CM = 9, IPOIB_FLAG_UMCAST = 10, @@ -98,9 +97,15 @@ enum { IPOIB_MCAST_FLAG_FOUND = 0, /* used in set_multicast_list */ IPOIB_MCAST_FLAG_SENDONLY = 1, - IPOIB_MCAST_FLAG_BUSY = 2, /* joining or already joined */ + /* + * For IPOIB_MCAST_FLAG_BUSY + * When set, in flight join and mcast->mc is unreliable + * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or + * haven't started yet + * When clear and mcast->mc is valid pointer, join was successful + */ + IPOIB_MCAST_FLAG_BUSY = 2, IPOIB_MCAST_FLAG_ATTACHED = 3, - IPOIB_MCAST_JOIN_STARTED = 4, MAX_SEND_CQE = 16, IPOIB_CM_COPYBREAK = 256, @@ -148,6 +153,7 @@ struct ipoib_mcast { unsigned long created; unsigned long backoff; + unsigned long delay_until; unsigned long flags; unsigned char logcount; @@ -292,6 +298,11 @@ struct ipoib_neigh_table { struct completion deleted; }; +struct ipoib_qp_state_validate { + struct work_struct work; + struct ipoib_dev_priv *priv; +}; + /* * Device private locking: network stack tx_lock protects members used * in TX fast path, lock protects everything else. lock nests inside @@ -317,6 +328,7 @@ struct ipoib_dev_priv { struct list_head multicast_list; struct rb_root multicast_tree; + struct workqueue_struct *wq; struct delayed_work mcast_task; struct work_struct carrier_on_task; struct work_struct flush_light; @@ -426,11 +438,6 @@ struct ipoib_neigh { #define IPOIB_UD_MTU(ib_mtu) (ib_mtu - IPOIB_ENCAP_LEN) #define IPOIB_UD_BUF_SIZE(ib_mtu) (ib_mtu + IB_GRH_BYTES) -static inline int ipoib_ud_need_sg(unsigned int ib_mtu) -{ - return IPOIB_UD_BUF_SIZE(ib_mtu) > PAGE_SIZE; -} - void ipoib_neigh_dtor(struct ipoib_neigh *neigh); static inline void ipoib_neigh_put(struct ipoib_neigh *neigh) { @@ -477,10 +484,10 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work); void ipoib_pkey_event(struct work_struct *work); void ipoib_ib_dev_cleanup(struct net_device *dev); -int ipoib_ib_dev_open(struct net_device *dev, int flush); +int ipoib_ib_dev_open(struct net_device *dev); int ipoib_ib_dev_up(struct net_device *dev); -int ipoib_ib_dev_down(struct net_device *dev, int flush); -int ipoib_ib_dev_stop(struct net_device *dev, int flush); +int ipoib_ib_dev_down(struct net_device *dev); +int ipoib_ib_dev_stop(struct net_device *dev); void ipoib_pkey_dev_check_presence(struct net_device *dev); int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port); @@ -492,7 +499,7 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb); void ipoib_mcast_restart_task(struct work_struct *work); int ipoib_mcast_start_thread(struct net_device *dev); -int ipoib_mcast_stop_thread(struct net_device *dev, int flush); +int ipoib_mcast_stop_thread(struct net_device *dev); void ipoib_mcast_dev_down(struct net_device *dev); void ipoib_mcast_dev_flush(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 933efcea0d03..56959adb6c7d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -474,7 +474,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even } spin_lock_irq(&priv->lock); - queue_delayed_work(ipoib_workqueue, + queue_delayed_work(priv->wq, &priv->cm.stale_task, IPOIB_CM_RX_DELAY); /* Add this entry to passive ids list head, but do not re-add it * if IB_EVENT_QP_LAST_WQE_REACHED has moved it to flush list. */ @@ -576,7 +576,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->cm.rx_drain_list, &priv->cm.rx_reap_list); ipoib_cm_start_rx_drain(priv); - queue_work(ipoib_workqueue, &priv->cm.rx_reap_task); + queue_work(priv->wq, &priv->cm.rx_reap_task); spin_unlock_irqrestore(&priv->lock, flags); } else ipoib_warn(priv, "cm recv completion event with wrid %d (> %d)\n", @@ -603,7 +603,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) spin_lock_irqsave(&priv->lock, flags); list_move(&p->list, &priv->cm.rx_reap_list); spin_unlock_irqrestore(&priv->lock, flags); - queue_work(ipoib_workqueue, &priv->cm.rx_reap_task); + queue_work(priv->wq, &priv->cm.rx_reap_task); } return; } @@ -827,7 +827,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { list_move(&tx->list, &priv->cm.reap_list); - queue_work(ipoib_workqueue, &priv->cm.reap_task); + queue_work(priv->wq, &priv->cm.reap_task); } clear_bit(IPOIB_FLAG_OPER_UP, &tx->flags); @@ -1255,7 +1255,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id, if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { list_move(&tx->list, &priv->cm.reap_list); - queue_work(ipoib_workqueue, &priv->cm.reap_task); + queue_work(priv->wq, &priv->cm.reap_task); } spin_unlock_irqrestore(&priv->lock, flags); @@ -1284,7 +1284,7 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path tx->dev = dev; list_add(&tx->list, &priv->cm.start_list); set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags); - queue_work(ipoib_workqueue, &priv->cm.start_task); + queue_work(priv->wq, &priv->cm.start_task); return tx; } @@ -1295,7 +1295,7 @@ void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx) if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { spin_lock_irqsave(&priv->lock, flags); list_move(&tx->list, &priv->cm.reap_list); - queue_work(ipoib_workqueue, &priv->cm.reap_task); + queue_work(priv->wq, &priv->cm.reap_task); ipoib_dbg(priv, "Reap connection for gid %pI6\n", tx->neigh->daddr + 4); tx->neigh = NULL; @@ -1417,7 +1417,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, skb_queue_tail(&priv->cm.skb_queue, skb); if (e) - queue_work(ipoib_workqueue, &priv->cm.skb_task); + queue_work(priv->wq, &priv->cm.skb_task); } static void ipoib_cm_rx_reap(struct work_struct *work) @@ -1450,7 +1450,7 @@ static void ipoib_cm_stale_task(struct work_struct *work) } if (!list_empty(&priv->cm.passive_ids)) - queue_delayed_work(ipoib_workqueue, + queue_delayed_work(priv->wq, &priv->cm.stale_task, IPOIB_CM_RX_DELAY); spin_unlock_irq(&priv->lock); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 72626c348174..63b92cbb29ad 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -94,39 +94,9 @@ void ipoib_free_ah(struct kref *kref) static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv, u64 mapping[IPOIB_UD_RX_SG]) { - if (ipoib_ud_need_sg(priv->max_ib_mtu)) { - ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_UD_HEAD_SIZE, - DMA_FROM_DEVICE); - ib_dma_unmap_page(priv->ca, mapping[1], PAGE_SIZE, - DMA_FROM_DEVICE); - } else - ib_dma_unmap_single(priv->ca, mapping[0], - IPOIB_UD_BUF_SIZE(priv->max_ib_mtu), - DMA_FROM_DEVICE); -} - -static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv, - struct sk_buff *skb, - unsigned int length) -{ - if (ipoib_ud_need_sg(priv->max_ib_mtu)) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; - unsigned int size; - /* - * There is only two buffers needed for max_payload = 4K, - * first buf size is IPOIB_UD_HEAD_SIZE - */ - skb->tail += IPOIB_UD_HEAD_SIZE; - skb->len += length; - - size = length - IPOIB_UD_HEAD_SIZE; - - skb_frag_size_set(frag, size); - skb->data_len += size; - skb->truesize += PAGE_SIZE; - } else - skb_put(skb, length); - + ib_dma_unmap_single(priv->ca, mapping[0], + IPOIB_UD_BUF_SIZE(priv->max_ib_mtu), + DMA_FROM_DEVICE); } static int ipoib_ib_post_receive(struct net_device *dev, int id) @@ -156,18 +126,11 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) struct ipoib_dev_priv *priv = netdev_priv(dev); struct sk_buff *skb; int buf_size; - int tailroom; u64 *mapping; - if (ipoib_ud_need_sg(priv->max_ib_mtu)) { - buf_size = IPOIB_UD_HEAD_SIZE; - tailroom = 128; /* reserve some tailroom for IP/TCP headers */ - } else { - buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); - tailroom = 0; - } + buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); - skb = dev_alloc_skb(buf_size + tailroom + 4); + skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN); if (unlikely(!skb)) return NULL; @@ -184,23 +147,8 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0]))) goto error; - if (ipoib_ud_need_sg(priv->max_ib_mtu)) { - struct page *page = alloc_page(GFP_ATOMIC); - if (!page) - goto partial_error; - skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE); - mapping[1] = - ib_dma_map_page(priv->ca, page, - 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1]))) - goto partial_error; - } - priv->rx_ring[id].skb = skb; return skb; - -partial_error: - ib_dma_unmap_single(priv->ca, mapping[0], buf_size, DMA_FROM_DEVICE); error: dev_kfree_skb_any(skb); return NULL; @@ -278,7 +226,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) wc->byte_len, wc->slid); ipoib_ud_dma_unmap_rx(priv, mapping); - ipoib_ud_skb_put_frags(priv, skb, wc->byte_len); + + skb_put(skb, wc->byte_len); /* First byte of dgid signals multicast when 0xff */ dgid = &((struct ib_grh *)skb->data)->dgid; @@ -296,6 +245,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) skb_reset_mac_header(skb); skb_pull(skb, IPOIB_ENCAP_LEN); + skb->truesize = SKB_TRUESIZE(skb->len); + ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; @@ -376,6 +327,51 @@ static void ipoib_dma_unmap_tx(struct ib_device *ca, } } +/* + * As the result of a completion error the QP Can be transferred to SQE states. + * The function checks if the (send)QP is in SQE state and + * moves it back to RTS state, that in order to have it functional again. + */ +static void ipoib_qp_state_validate_work(struct work_struct *work) +{ + struct ipoib_qp_state_validate *qp_work = + container_of(work, struct ipoib_qp_state_validate, work); + + struct ipoib_dev_priv *priv = qp_work->priv; + struct ib_qp_attr qp_attr; + struct ib_qp_init_attr query_init_attr; + int ret; + + ret = ib_query_qp(priv->qp, &qp_attr, IB_QP_STATE, &query_init_attr); + if (ret) { + ipoib_warn(priv, "%s: Failed to query QP ret: %d\n", + __func__, ret); + goto free_res; + } + pr_info("%s: QP: 0x%x is in state: %d\n", + __func__, priv->qp->qp_num, qp_attr.qp_state); + + /* currently support only in SQE->RTS transition*/ + if (qp_attr.qp_state == IB_QPS_SQE) { + qp_attr.qp_state = IB_QPS_RTS; + + ret = ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE); + if (ret) { + pr_warn("failed(%d) modify QP:0x%x SQE->RTS\n", + ret, priv->qp->qp_num); + goto free_res; + } + pr_info("%s: QP: 0x%x moved from IB_QPS_SQE to IB_QPS_RTS\n", + __func__, priv->qp->qp_num); + } else { + pr_warn("QP (%d) will stay in state: %d\n", + priv->qp->qp_num, qp_attr.qp_state); + } + +free_res: + kfree(qp_work); +} + static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -407,10 +403,22 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) netif_wake_queue(dev); if (wc->status != IB_WC_SUCCESS && - wc->status != IB_WC_WR_FLUSH_ERR) + wc->status != IB_WC_WR_FLUSH_ERR) { + struct ipoib_qp_state_validate *qp_work; ipoib_warn(priv, "failed send event " "(status=%d, wrid=%d vend_err %x)\n", wc->status, wr_id, wc->vendor_err); + qp_work = kzalloc(sizeof(*qp_work), GFP_ATOMIC); + if (!qp_work) { + ipoib_warn(priv, "%s Failed alloc ipoib_qp_state_validate for qp: 0x%x\n", + __func__, priv->qp->qp_num); + return; + } + + INIT_WORK(&qp_work->work, ipoib_qp_state_validate_work); + qp_work->priv = priv; + queue_work(priv->wq, &qp_work->work); + } } static int poll_tx(struct ipoib_dev_priv *priv) @@ -655,16 +663,33 @@ void ipoib_reap_ah(struct work_struct *work) __ipoib_reap_ah(dev); if (!test_bit(IPOIB_STOP_REAPER, &priv->flags)) - queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, + queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); } +static void ipoib_flush_ah(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + + cancel_delayed_work(&priv->ah_reap_task); + flush_workqueue(priv->wq); + ipoib_reap_ah(&priv->ah_reap_task.work); +} + +static void ipoib_stop_ah(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + + set_bit(IPOIB_STOP_REAPER, &priv->flags); + ipoib_flush_ah(dev); +} + static void ipoib_ib_tx_timer_func(unsigned long ctx) { drain_tx_cq((struct net_device *)ctx); } -int ipoib_ib_dev_open(struct net_device *dev, int flush) +int ipoib_ib_dev_open(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); int ret; @@ -696,7 +721,7 @@ int ipoib_ib_dev_open(struct net_device *dev, int flush) } clear_bit(IPOIB_STOP_REAPER, &priv->flags); - queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task, + queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) @@ -706,7 +731,7 @@ int ipoib_ib_dev_open(struct net_device *dev, int flush) dev_stop: if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) napi_enable(&priv->napi); - ipoib_ib_dev_stop(dev, flush); + ipoib_ib_dev_stop(dev); return -1; } @@ -738,7 +763,7 @@ int ipoib_ib_dev_up(struct net_device *dev) return ipoib_mcast_start_thread(dev); } -int ipoib_ib_dev_down(struct net_device *dev, int flush) +int ipoib_ib_dev_down(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -747,7 +772,7 @@ int ipoib_ib_dev_down(struct net_device *dev, int flush) clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags); netif_carrier_off(dev); - ipoib_mcast_stop_thread(dev, flush); + ipoib_mcast_stop_thread(dev); ipoib_mcast_dev_flush(dev); ipoib_flush_paths(dev); @@ -807,7 +832,7 @@ void ipoib_drain_cq(struct net_device *dev) local_bh_enable(); } -int ipoib_ib_dev_stop(struct net_device *dev, int flush) +int ipoib_ib_dev_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_qp_attr qp_attr; @@ -877,24 +902,7 @@ timeout: if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) ipoib_warn(priv, "Failed to modify QP to RESET state\n"); - /* Wait for all AHs to be reaped */ - set_bit(IPOIB_STOP_REAPER, &priv->flags); - cancel_delayed_work(&priv->ah_reap_task); - if (flush) - flush_workqueue(ipoib_workqueue); - - begin = jiffies; - - while (!list_empty(&priv->dead_ahs)) { - __ipoib_reap_ah(dev); - - if (time_after(jiffies, begin + HZ)) { - ipoib_warn(priv, "timing out; will leak address handles\n"); - break; - } - - msleep(1); - } + ipoib_flush_ah(dev); ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP); @@ -918,7 +926,7 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port) (unsigned long) dev); if (dev->flags & IFF_UP) { - if (ipoib_ib_dev_open(dev, 1)) { + if (ipoib_ib_dev_open(dev)) { ipoib_transport_dev_cleanup(dev); return -ENODEV; } @@ -1037,15 +1045,16 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, if (level == IPOIB_FLUSH_LIGHT) { ipoib_mark_paths_invalid(dev); ipoib_mcast_dev_flush(dev); + ipoib_flush_ah(dev); } if (level >= IPOIB_FLUSH_NORMAL) - ipoib_ib_dev_down(dev, 0); + ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - ipoib_ib_dev_stop(dev, 0); - if (ipoib_ib_dev_open(dev, 0) != 0) + ipoib_ib_dev_stop(dev); + if (ipoib_ib_dev_open(dev) != 0) return; if (netif_queue_stopped(dev)) netif_start_queue(dev); @@ -1097,9 +1106,17 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) */ ipoib_flush_paths(dev); - ipoib_mcast_stop_thread(dev, 1); + ipoib_mcast_stop_thread(dev); ipoib_mcast_dev_flush(dev); + /* + * All of our ah references aren't free until after + * ipoib_mcast_dev_flush(), ipoib_flush_paths, and + * the neighbor garbage collection is stopped and reaped. + * That should all be done now, so make a final ah flush. + */ + ipoib_stop_ah(dev); + ipoib_transport_dev_cleanup(dev); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 915ad04a827e..9e1b203d756d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -108,7 +108,7 @@ int ipoib_open(struct net_device *dev) set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); - if (ipoib_ib_dev_open(dev, 1)) { + if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; @@ -139,7 +139,7 @@ int ipoib_open(struct net_device *dev) return 0; err_stop: - ipoib_ib_dev_stop(dev, 1); + ipoib_ib_dev_stop(dev); err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); @@ -157,8 +157,8 @@ static int ipoib_stop(struct net_device *dev) netif_stop_queue(dev); - ipoib_ib_dev_down(dev, 1); - ipoib_ib_dev_stop(dev, 0); + ipoib_ib_dev_down(dev); + ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; @@ -640,8 +640,10 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, if (!path->query && path_rec_start(dev, path)) goto err_path; - - __skb_queue_tail(&neigh->queue, skb); + if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) + __skb_queue_tail(&neigh->queue, skb); + else + goto err_drop; } spin_unlock_irqrestore(&priv->lock, flags); @@ -676,7 +678,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, new_path = 1; } if (path) { - __skb_queue_tail(&path->queue, skb); + if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { + __skb_queue_tail(&path->queue, skb); + } else { + ++dev->stats.tx_dropped; + dev_kfree_skb_any(skb); + } if (!path->query && path_rec_start(dev, path)) { spin_unlock_irqrestore(&priv->lock, flags); @@ -839,7 +846,7 @@ static void ipoib_set_mcast_list(struct net_device *dev) return; } - queue_work(ipoib_workqueue, &priv->restart_task); + queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) @@ -966,7 +973,7 @@ static void ipoib_reap_neigh(struct work_struct *work) __ipoib_reap_neigh(priv); if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags)) - queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task, + queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } @@ -1145,7 +1152,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) /* start garbage collection */ clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); - queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task, + queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; @@ -1274,15 +1281,13 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) { struct ipoib_dev_priv *priv = netdev_priv(dev); - if (ipoib_neigh_hash_init(priv) < 0) - goto out; /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring, GFP_KERNEL); if (!priv->rx_ring) { printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n", ca->name, ipoib_recvq_size); - goto out_neigh_hash_cleanup; + goto out; } priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring); @@ -1297,16 +1302,24 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) if (ipoib_ib_dev_init(dev, ca, port)) goto out_tx_ring_cleanup; + /* + * Must be after ipoib_ib_dev_init so we can allocate a per + * device wq there and use it here + */ + if (ipoib_neigh_hash_init(priv) < 0) + goto out_dev_uninit; + return 0; +out_dev_uninit: + ipoib_ib_dev_cleanup(dev); + out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); -out_neigh_hash_cleanup: - ipoib_neigh_hash_uninit(dev); out: return -ENOMEM; } @@ -1329,6 +1342,12 @@ void ipoib_dev_cleanup(struct net_device *dev) } unregister_netdevice_many(&head); + /* + * Must be before ipoib_ib_dev_cleanup or we delete an in use + * work queue + */ + ipoib_neigh_hash_uninit(dev); + ipoib_ib_dev_cleanup(dev); kfree(priv->rx_ring); @@ -1336,8 +1355,6 @@ void ipoib_dev_cleanup(struct net_device *dev) priv->rx_ring = NULL; priv->tx_ring = NULL; - - ipoib_neigh_hash_uninit(dev); } static const struct header_ops ipoib_header_ops = { @@ -1646,10 +1663,11 @@ sysfs_failed: register_failed: ib_unregister_event_handler(&priv->event_handler); + flush_workqueue(ipoib_workqueue); /* Stop GC if started before flush */ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); cancel_delayed_work(&priv->neigh_reap_task); - flush_workqueue(ipoib_workqueue); + flush_workqueue(priv->wq); event_failed: ipoib_dev_cleanup(priv->dev); @@ -1712,6 +1730,7 @@ static void ipoib_remove_one(struct ib_device *device) list_for_each_entry_safe(priv, tmp, dev_list, list) { ib_unregister_event_handler(&priv->event_handler); + flush_workqueue(ipoib_workqueue); rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP); @@ -1720,7 +1739,7 @@ static void ipoib_remove_one(struct ib_device *device) /* Stop GC */ set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); cancel_delayed_work(&priv->neigh_reap_task); - flush_workqueue(ipoib_workqueue); + flush_workqueue(priv->wq); unregister_netdev(priv->dev); free_netdev(priv->dev); @@ -1755,14 +1774,16 @@ static int __init ipoib_init_module(void) return ret; /* - * We create our own workqueue mainly because we want to be - * able to flush it when devices are being removed. We can't - * use schedule_work()/flush_scheduled_work() because both - * unregister_netdev() and linkwatch_event take the rtnl lock, - * so flush_scheduled_work() can deadlock during device - * removal. + * We create a global workqueue here that is used for all flush + * operations. However, if you attempt to flush a workqueue + * from a task on that same workqueue, it deadlocks the system. + * We want to be able to flush the tasks associated with a + * specific net device, so we also create a workqueue for each + * netdevice. We queue up the tasks for that device only on + * its private workqueue, and we only queue up flush events + * on our global flush workqueue. This avoids the deadlocks. */ - ipoib_workqueue = create_singlethread_workqueue("ipoib"); + ipoib_workqueue = create_singlethread_workqueue("ipoib_flush"); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index ffb83b5f7e80..0d23e0568deb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -55,8 +55,6 @@ MODULE_PARM_DESC(mcast_debug_level, "Enable multicast debug tracing if > 0"); #endif -static DEFINE_MUTEX(mcast_mutex); - struct ipoib_mcast_iter { struct net_device *dev; union ib_gid mgid; @@ -66,6 +64,48 @@ struct ipoib_mcast_iter { unsigned int send_only; }; +/* + * This should be called with the priv->lock held + */ +static void __ipoib_mcast_schedule_join_thread(struct ipoib_dev_priv *priv, + struct ipoib_mcast *mcast, + bool delay) +{ + if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + return; + + /* + * We will be scheduling *something*, so cancel whatever is + * currently scheduled first + */ + cancel_delayed_work(&priv->mcast_task); + if (mcast && delay) { + /* + * We had a failure and want to schedule a retry later + */ + mcast->backoff *= 2; + if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) + mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; + mcast->delay_until = jiffies + (mcast->backoff * HZ); + /* + * Mark this mcast for its delay, but restart the + * task immediately. The join task will make sure to + * clear out all entries without delays, and then + * schedule itself to run again when the earliest + * delay expires + */ + queue_delayed_work(priv->wq, &priv->mcast_task, 0); + } else if (delay) { + /* + * Special case of retrying after a failure to + * allocate the broadcast multicast group, wait + * 1 second and try again + */ + queue_delayed_work(priv->wq, &priv->mcast_task, HZ); + } else + queue_delayed_work(priv->wq, &priv->mcast_task, 0); +} + static void ipoib_mcast_free(struct ipoib_mcast *mcast) { struct net_device *dev = mcast->dev; @@ -103,6 +143,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev, mcast->dev = dev; mcast->created = jiffies; + mcast->delay_until = jiffies; mcast->backoff = 1; INIT_LIST_HEAD(&mcast->list); @@ -185,17 +226,27 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, spin_unlock_irq(&priv->lock); return -EAGAIN; } - priv->mcast_mtu = IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu)); + /*update priv member according to the new mcast*/ + priv->broadcast->mcmember.qkey = mcmember->qkey; + priv->broadcast->mcmember.mtu = mcmember->mtu; + priv->broadcast->mcmember.traffic_class = mcmember->traffic_class; + priv->broadcast->mcmember.rate = mcmember->rate; + priv->broadcast->mcmember.sl = mcmember->sl; + priv->broadcast->mcmember.flow_label = mcmember->flow_label; + priv->broadcast->mcmember.hop_limit = mcmember->hop_limit; + /* assume if the admin and the mcast are the same both can be changed */ + if (priv->mcast_mtu == priv->admin_mtu) + priv->admin_mtu = + priv->mcast_mtu = + IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu)); + else + priv->mcast_mtu = + IPOIB_UD_MTU(ib_mtu_enum_to_int(priv->broadcast->mcmember.mtu)); + priv->qkey = be32_to_cpu(priv->broadcast->mcmember.qkey); spin_unlock_irq(&priv->lock); priv->tx_wr.wr.ud.remote_qkey = priv->qkey; set_qkey = 1; - - if (!ipoib_cm_admin_enabled(dev)) { - rtnl_lock(); - dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu)); - rtnl_unlock(); - } } if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) { @@ -270,107 +321,35 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, return 0; } -static int -ipoib_mcast_sendonly_join_complete(int status, - struct ib_sa_multicast *multicast) -{ - struct ipoib_mcast *mcast = multicast->context; - struct net_device *dev = mcast->dev; - - /* We trap for port events ourselves. */ - if (status == -ENETRESET) - return 0; - - if (!status) - status = ipoib_mcast_join_finish(mcast, &multicast->rec); - - if (status) { - if (mcast->logcount++ < 20) - ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for %pI6, status %d\n", - mcast->mcmember.mgid.raw, status); - - /* Flush out any queued packets */ - netif_tx_lock_bh(dev); - while (!skb_queue_empty(&mcast->pkt_queue)) { - ++dev->stats.tx_dropped; - dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue)); - } - netif_tx_unlock_bh(dev); - - /* Clear the busy flag so we try again */ - status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, - &mcast->flags); - } - return status; -} - -static int ipoib_mcast_sendonly_join(struct ipoib_mcast *mcast) -{ - struct net_device *dev = mcast->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); - struct ib_sa_mcmember_rec rec = { -#if 0 /* Some SMs don't support send-only yet */ - .join_state = 4 -#else - .join_state = 1 -#endif - }; - int ret = 0; - - if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { - ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n"); - return -ENODEV; - } - - if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) { - ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n"); - return -EBUSY; - } - - rec.mgid = mcast->mcmember.mgid; - rec.port_gid = priv->local_gid; - rec.pkey = cpu_to_be16(priv->pkey); - - mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, - priv->port, &rec, - IB_SA_MCMEMBER_REC_MGID | - IB_SA_MCMEMBER_REC_PORT_GID | - IB_SA_MCMEMBER_REC_PKEY | - IB_SA_MCMEMBER_REC_JOIN_STATE, - GFP_ATOMIC, - ipoib_mcast_sendonly_join_complete, - mcast); - if (IS_ERR(mcast->mc)) { - ret = PTR_ERR(mcast->mc); - clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - ipoib_warn(priv, "ib_sa_join_multicast failed (ret = %d)\n", - ret); - } else { - ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting join\n", - mcast->mcmember.mgid.raw); - } - - return ret; -} - void ipoib_mcast_carrier_on_task(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, carrier_on_task); struct ib_port_attr attr; - /* - * Take rtnl_lock to avoid racing with ipoib_stop() and - * turning the carrier back on while a device is being - * removed. - */ if (ib_query_port(priv->ca, priv->port, &attr) || attr.state != IB_PORT_ACTIVE) { ipoib_dbg(priv, "Keeping carrier off until IB port is active\n"); return; } - rtnl_lock(); + /* + * Take rtnl_lock to avoid racing with ipoib_stop() and + * turning the carrier back on while a device is being + * removed. However, ipoib_stop() will attempt to flush + * the workqueue while holding the rtnl lock, so loop + * on trylock until either we get the lock or we see + * FLAG_OPER_UP go away as that signals that we are bailing + * and can safely ignore the carrier on work. + */ + while (!rtnl_trylock()) { + if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + return; + else + msleep(20); + } + if (!ipoib_cm_admin_enabled(priv->dev)) + dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu)); netif_carrier_on(priv->dev); rtnl_unlock(); } @@ -382,7 +361,9 @@ static int ipoib_mcast_join_complete(int status, struct net_device *dev = mcast->dev; struct ipoib_dev_priv *priv = netdev_priv(dev); - ipoib_dbg_mcast(priv, "join completion for %pI6 (status %d)\n", + ipoib_dbg_mcast(priv, "%sjoin completion for %pI6 (status %d)\n", + test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? + "sendonly " : "", mcast->mcmember.mgid.raw, status); /* We trap for port events ourselves. */ @@ -396,49 +377,74 @@ static int ipoib_mcast_join_complete(int status, if (!status) { mcast->backoff = 1; - mutex_lock(&mcast_mutex); - if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(ipoib_workqueue, - &priv->mcast_task, 0); - mutex_unlock(&mcast_mutex); + mcast->delay_until = jiffies; /* - * Defer carrier on work to ipoib_workqueue to avoid a - * deadlock on rtnl_lock here. + * Defer carrier on work to priv->wq to avoid a + * deadlock on rtnl_lock here. Requeue our multicast + * work too, which will end up happening right after + * our carrier on task work and will allow us to + * send out all of the non-broadcast joins */ - if (mcast == priv->broadcast) - queue_work(ipoib_workqueue, &priv->carrier_on_task); - - status = 0; - goto out; - } + if (mcast == priv->broadcast) { + spin_lock_irq(&priv->lock); + queue_work(priv->wq, &priv->carrier_on_task); + __ipoib_mcast_schedule_join_thread(priv, NULL, 0); + goto out_locked; + } + } else { + if (mcast->logcount++ < 20) { + if (status == -ETIMEDOUT || status == -EAGAIN) { + ipoib_dbg_mcast(priv, "%smulticast join failed for %pI6, status %d\n", + test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "", + mcast->mcmember.mgid.raw, status); + } else { + ipoib_warn(priv, "%smulticast join failed for %pI6, status %d\n", + test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "", + mcast->mcmember.mgid.raw, status); + } + } - if (mcast->logcount++ < 20) { - if (status == -ETIMEDOUT || status == -EAGAIN) { - ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n", - mcast->mcmember.mgid.raw, status); + if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) && + mcast->backoff >= 2) { + /* + * We only retry sendonly joins once before we drop + * the packet and quit trying to deal with the + * group. However, we leave the group in the + * mcast list as an unjoined group. If we want to + * try joining again, we simply queue up a packet + * and restart the join thread. The empty queue + * is why the join thread ignores this group. + */ + mcast->backoff = 1; + netif_tx_lock_bh(dev); + while (!skb_queue_empty(&mcast->pkt_queue)) { + ++dev->stats.tx_dropped; + dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue)); + } + netif_tx_unlock_bh(dev); } else { - ipoib_warn(priv, "multicast join failed for %pI6, status %d\n", - mcast->mcmember.mgid.raw, status); + spin_lock_irq(&priv->lock); + /* Requeue this join task with a backoff delay */ + __ipoib_mcast_schedule_join_thread(priv, mcast, 1); + goto out_locked; } } - - mcast->backoff *= 2; - if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) - mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; - - /* Clear the busy flag so we try again */ - status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - - mutex_lock(&mcast_mutex); +out: spin_lock_irq(&priv->lock); - if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(ipoib_workqueue, &priv->mcast_task, - mcast->backoff * HZ); +out_locked: + /* + * Make sure to set mcast->mc before we clear the busy flag to avoid + * racing with code that checks for BUSY before checking mcast->mc + */ + if (status) + mcast->mc = NULL; + else + mcast->mc = multicast; + clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); spin_unlock_irq(&priv->lock); - mutex_unlock(&mcast_mutex); -out: complete(&mcast->done); + return status; } @@ -446,6 +452,7 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast, int create) { struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ib_sa_multicast *multicast; struct ib_sa_mcmember_rec rec = { .join_state = 1 }; @@ -487,29 +494,18 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast, rec.hop_limit = priv->broadcast->mcmember.hop_limit; } - set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - init_completion(&mcast->done); - set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags); - - mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, + multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, comp_mask, GFP_KERNEL, ipoib_mcast_join_complete, mcast); - if (IS_ERR(mcast->mc)) { + if (IS_ERR(multicast)) { + ret = PTR_ERR(multicast); + ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); + spin_lock_irq(&priv->lock); + /* Requeue this join task with a backoff delay */ + __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + spin_unlock_irq(&priv->lock); complete(&mcast->done); - ret = PTR_ERR(mcast->mc); - ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); - - mcast->backoff *= 2; - if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) - mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; - - mutex_lock(&mcast_mutex); - if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(ipoib_workqueue, - &priv->mcast_task, - mcast->backoff * HZ); - mutex_unlock(&mcast_mutex); } } @@ -519,8 +515,11 @@ void ipoib_mcast_join_task(struct work_struct *work) container_of(work, struct ipoib_dev_priv, mcast_task.work); struct net_device *dev = priv->dev; struct ib_port_attr port_attr; + unsigned long delay_until = 0; + struct ipoib_mcast *mcast = NULL; + int create = 1; - if (!test_bit(IPOIB_MCAST_RUN, &priv->flags)) + if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) return; if (ib_query_port(priv->ca, priv->port, &port_attr) || @@ -536,93 +535,118 @@ void ipoib_mcast_join_task(struct work_struct *work) else memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid)); + spin_lock_irq(&priv->lock); + if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + goto out; + if (!priv->broadcast) { struct ipoib_mcast *broadcast; - if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) - return; - - broadcast = ipoib_mcast_alloc(dev, 1); + broadcast = ipoib_mcast_alloc(dev, 0); if (!broadcast) { ipoib_warn(priv, "failed to allocate broadcast group\n"); - mutex_lock(&mcast_mutex); - if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(ipoib_workqueue, - &priv->mcast_task, HZ); - mutex_unlock(&mcast_mutex); - return; + /* + * Restart us after a 1 second delay to retry + * creating our broadcast group and attaching to + * it. Until this succeeds, this ipoib dev is + * completely stalled (multicast wise). + */ + __ipoib_mcast_schedule_join_thread(priv, NULL, 1); + goto out; } - spin_lock_irq(&priv->lock); memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4, sizeof (union ib_gid)); priv->broadcast = broadcast; __ipoib_mcast_add(dev, priv->broadcast); - spin_unlock_irq(&priv->lock); } if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) { - if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) - ipoib_mcast_join(dev, priv->broadcast, 0); - return; - } - - while (1) { - struct ipoib_mcast *mcast = NULL; - - spin_lock_irq(&priv->lock); - list_for_each_entry(mcast, &priv->multicast_list, list) { - if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) - && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) - && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) { - /* Found the next unjoined group */ - break; + if (IS_ERR_OR_NULL(priv->broadcast->mc) && + !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) { + mcast = priv->broadcast; + create = 0; + if (mcast->backoff > 1 && + time_before(jiffies, mcast->delay_until)) { + delay_until = mcast->delay_until; + mcast = NULL; } } - spin_unlock_irq(&priv->lock); + goto out; + } - if (&mcast->list == &priv->multicast_list) { - /* All done */ - break; + /* + * We'll never get here until the broadcast group is both allocated + * and attached + */ + list_for_each_entry(mcast, &priv->multicast_list, list) { + if (IS_ERR_OR_NULL(mcast->mc) && + !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) && + (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) || + !skb_queue_empty(&mcast->pkt_queue))) { + if (mcast->backoff == 1 || + time_after_eq(jiffies, mcast->delay_until)) { + /* Found the next unjoined group */ + init_completion(&mcast->done); + set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) + create = 0; + else + create = 1; + spin_unlock_irq(&priv->lock); + ipoib_mcast_join(dev, mcast, create); + spin_lock_irq(&priv->lock); + } else if (!delay_until || + time_before(mcast->delay_until, delay_until)) + delay_until = mcast->delay_until; } - - ipoib_mcast_join(dev, mcast, 1); - return; } - ipoib_dbg_mcast(priv, "successfully joined all multicast groups\n"); + mcast = NULL; + ipoib_dbg_mcast(priv, "successfully started all multicast joins\n"); - clear_bit(IPOIB_MCAST_RUN, &priv->flags); +out: + if (delay_until) { + cancel_delayed_work(&priv->mcast_task); + queue_delayed_work(priv->wq, &priv->mcast_task, + delay_until - jiffies); + } + if (mcast) { + init_completion(&mcast->done); + set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + } + spin_unlock_irq(&priv->lock); + if (mcast) + ipoib_mcast_join(dev, mcast, create); } int ipoib_mcast_start_thread(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); + unsigned long flags; ipoib_dbg_mcast(priv, "starting multicast thread\n"); - mutex_lock(&mcast_mutex); - if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags)) - queue_delayed_work(ipoib_workqueue, &priv->mcast_task, 0); - mutex_unlock(&mcast_mutex); + spin_lock_irqsave(&priv->lock, flags); + __ipoib_mcast_schedule_join_thread(priv, NULL, 0); + spin_unlock_irqrestore(&priv->lock, flags); return 0; } -int ipoib_mcast_stop_thread(struct net_device *dev, int flush) +int ipoib_mcast_stop_thread(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); + unsigned long flags; ipoib_dbg_mcast(priv, "stopping multicast thread\n"); - mutex_lock(&mcast_mutex); - clear_bit(IPOIB_MCAST_RUN, &priv->flags); + spin_lock_irqsave(&priv->lock, flags); cancel_delayed_work(&priv->mcast_task); - mutex_unlock(&mcast_mutex); + spin_unlock_irqrestore(&priv->lock, flags); - if (flush) - flush_workqueue(ipoib_workqueue); + flush_workqueue(priv->wq); return 0; } @@ -633,6 +657,9 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) int ret = 0; if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) + ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n"); + + if (!IS_ERR_OR_NULL(mcast->mc)) ib_sa_free_multicast(mcast->mc); if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) { @@ -644,7 +671,9 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) be16_to_cpu(mcast->mcmember.mlid)); if (ret) ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret); - } + } else if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) + ipoib_dbg(priv, "leaving with no mcmember but not a " + "SENDONLY join\n"); return 0; } @@ -667,49 +696,37 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) } mcast = __ipoib_mcast_find(dev, mgid); - if (!mcast) { - /* Let's create a new send only group now */ - ipoib_dbg_mcast(priv, "setting up send only multicast group for %pI6\n", - mgid); - - mcast = ipoib_mcast_alloc(dev, 0); + if (!mcast || !mcast->ah) { if (!mcast) { - ipoib_warn(priv, "unable to allocate memory for " - "multicast structure\n"); - ++dev->stats.tx_dropped; - dev_kfree_skb_any(skb); - goto out; - } - - set_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags); - memcpy(mcast->mcmember.mgid.raw, mgid, sizeof (union ib_gid)); - __ipoib_mcast_add(dev, mcast); - list_add_tail(&mcast->list, &priv->multicast_list); - } + /* Let's create a new send only group now */ + ipoib_dbg_mcast(priv, "setting up send only multicast group for %pI6\n", + mgid); + + mcast = ipoib_mcast_alloc(dev, 0); + if (!mcast) { + ipoib_warn(priv, "unable to allocate memory " + "for multicast structure\n"); + ++dev->stats.tx_dropped; + dev_kfree_skb_any(skb); + goto unlock; + } - if (!mcast->ah) { + set_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags); + memcpy(mcast->mcmember.mgid.raw, mgid, + sizeof (union ib_gid)); + __ipoib_mcast_add(dev, mcast); + list_add_tail(&mcast->list, &priv->multicast_list); + } if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) skb_queue_tail(&mcast->pkt_queue, skb); else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } - - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - ipoib_dbg_mcast(priv, "no address vector, " - "but multicast join already started\n"); - else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) - ipoib_mcast_sendonly_join(mcast); - - /* - * If lookup completes between here and out:, don't - * want to send packet twice. - */ - mcast = NULL; - } - -out: - if (mcast && mcast->ah) { + if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) { + __ipoib_mcast_schedule_join_thread(priv, NULL, 0); + } + } else { struct ipoib_neigh *neigh; spin_unlock_irqrestore(&priv->lock, flags); @@ -759,9 +776,12 @@ void ipoib_mcast_dev_flush(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); - /* seperate between the wait to the leave*/ + /* + * make sure the in-flight joins have finished before we attempt + * to leave + */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags)) + if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) wait_for_completion(&mcast->done); list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { @@ -792,9 +812,14 @@ void ipoib_mcast_restart_task(struct work_struct *work) unsigned long flags; struct ib_sa_mcmember_rec rec; - ipoib_dbg_mcast(priv, "restarting multicast task\n"); + if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + /* + * shortcut...on shutdown flush is called next, just + * let it do all the work + */ + return; - ipoib_mcast_stop_thread(dev, 0); + ipoib_dbg_mcast(priv, "restarting multicast task\n"); local_irq_save(flags); netif_addr_lock(dev); @@ -880,14 +905,27 @@ void ipoib_mcast_restart_task(struct work_struct *work) netif_addr_unlock(dev); local_irq_restore(flags); - /* We have to cancel outside of the spinlock */ + /* + * make sure the in-flight joins have finished before we attempt + * to leave + */ + list_for_each_entry_safe(mcast, tmcast, &remove_list, list) + if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) + wait_for_completion(&mcast->done); + list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { ipoib_mcast_leave(mcast->dev, mcast); ipoib_mcast_free(mcast); } - if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) - ipoib_mcast_start_thread(dev); + /* + * Double check that we are still up + */ + if (test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { + spin_lock_irqsave(&priv->lock, flags); + __ipoib_mcast_schedule_join_thread(priv, NULL, 0); + spin_unlock_irqrestore(&priv->lock, flags); + } } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index c56d5d44c53b..e5cc43074196 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -157,6 +157,16 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) goto out_free_pd; } + /* + * the various IPoIB tasks assume they will never race against + * themselves, so always use a single thread workqueue + */ + priv->wq = create_singlethread_workqueue("ipoib_wq"); + if (!priv->wq) { + printk(KERN_WARNING "ipoib: failed to allocate device WQ\n"); + goto out_free_mr; + } + size = ipoib_recvq_size + 1; ret = ipoib_cm_dev_init(dev); if (!ret) { @@ -165,12 +175,13 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) size += ipoib_recvq_size + 1; /* 1 extra for rx_drain_qp */ else size += ipoib_recvq_size * ipoib_max_conn_qp; - } + } else + goto out_free_wq; priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0); if (IS_ERR(priv->recv_cq)) { printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name); - goto out_free_mr; + goto out_cm_dev_cleanup; } priv->send_cq = ib_create_cq(priv->ca, ipoib_send_comp_handler, NULL, @@ -216,15 +227,10 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->tx_wr.send_flags = IB_SEND_SIGNALED; priv->rx_sge[0].lkey = priv->mr->lkey; - if (ipoib_ud_need_sg(priv->max_ib_mtu)) { - priv->rx_sge[0].length = IPOIB_UD_HEAD_SIZE; - priv->rx_sge[1].length = PAGE_SIZE; - priv->rx_sge[1].lkey = priv->mr->lkey; - priv->rx_wr.num_sge = IPOIB_UD_RX_SG; - } else { - priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); - priv->rx_wr.num_sge = 1; - } + + priv->rx_sge[0].length = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); + priv->rx_wr.num_sge = 1; + priv->rx_wr.next = NULL; priv->rx_wr.sg_list = priv->rx_sge; @@ -236,12 +242,19 @@ out_free_send_cq: out_free_recv_cq: ib_destroy_cq(priv->recv_cq); +out_cm_dev_cleanup: + ipoib_cm_dev_cleanup(dev); + +out_free_wq: + destroy_workqueue(priv->wq); + priv->wq = NULL; + out_free_mr: ib_dereg_mr(priv->mr); - ipoib_cm_dev_cleanup(dev); out_free_pd: ib_dealloc_pd(priv->pd); + return -ENODEV; } @@ -265,11 +278,18 @@ void ipoib_transport_dev_cleanup(struct net_device *dev) ipoib_cm_dev_cleanup(dev); + if (priv->wq) { + flush_workqueue(priv->wq); + destroy_workqueue(priv->wq); + priv->wq = NULL; + } + if (ib_dereg_mr(priv->mr)) ipoib_warn(priv, "ib_dereg_mr failed\n"); if (ib_dealloc_pd(priv->pd)) ipoib_warn(priv, "ib_dealloc_pd failed\n"); + } void ipoib_event(struct ib_event_handler *handler, diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index b47aea1094b2..262ba1f8ee50 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -69,7 +69,7 @@ #define DRV_NAME "iser" #define PFX DRV_NAME ": " -#define DRV_VER "1.5" +#define DRV_VER "1.6" #define iser_dbg(fmt, arg...) \ do { \ @@ -218,22 +218,21 @@ enum iser_data_dir { /** * struct iser_data_buf - iSER data buffer * - * @buf: pointer to the sg list + * @sg: pointer to the sg list * @size: num entries of this sg * @data_len: total beffer byte len * @dma_nents: returned by dma_map_sg - * @copy_buf: allocated copy buf for SGs unaligned - * for rdma which are copied - * @sg_single: SG-ified clone of a non SG SC or - * unaligned SG + * @orig_sg: pointer to the original sg list (in case + * we used a copy) + * @orig_size: num entris of orig sg list */ struct iser_data_buf { - void *buf; + struct scatterlist *sg; unsigned int size; unsigned long data_len; unsigned int dma_nents; - char *copy_buf; - struct scatterlist sg_single; + struct scatterlist *orig_sg; + unsigned int orig_size; }; /* fwd declarations */ @@ -244,35 +243,14 @@ struct iscsi_endpoint; /** * struct iser_mem_reg - iSER memory registration info * - * @lkey: MR local key - * @rkey: MR remote key - * @va: MR start address (buffer va) - * @len: MR length + * @sge: memory region sg element + * @rkey: memory region remote key * @mem_h: pointer to registration context (FMR/Fastreg) */ struct iser_mem_reg { - u32 lkey; - u32 rkey; - u64 va; - u64 len; - void *mem_h; -}; - -/** - * struct iser_regd_buf - iSER buffer registration desc - * - * @reg: memory registration info - * @virt_addr: virtual address of buffer - * @device: reference to iser device - * @direction: dma direction (for dma_unmap) - * @data_size: data buffer size in bytes - */ -struct iser_regd_buf { - struct iser_mem_reg reg; - void *virt_addr; - struct iser_device *device; - enum dma_data_direction direction; - unsigned int data_size; + struct ib_sge sge; + u32 rkey; + void *mem_h; }; enum iser_desc_type { @@ -534,11 +512,9 @@ struct iser_conn { * @sc: link to scsi command * @command_sent: indicate if command was sent * @dir: iser data direction - * @rdma_regd: task rdma registration desc + * @rdma_reg: task rdma registration desc * @data: iser data buffer desc - * @data_copy: iser data copy buffer desc (bounce buffer) * @prot: iser protection buffer desc - * @prot_copy: iser protection copy buffer desc (bounce buffer) */ struct iscsi_iser_task { struct iser_tx_desc desc; @@ -547,11 +523,9 @@ struct iscsi_iser_task { struct scsi_cmnd *sc; int command_sent; int dir[ISER_DIRS_NUM]; - struct iser_regd_buf rdma_regd[ISER_DIRS_NUM]; + struct iser_mem_reg rdma_reg[ISER_DIRS_NUM]; struct iser_data_buf data[ISER_DIRS_NUM]; - struct iser_data_buf data_copy[ISER_DIRS_NUM]; struct iser_data_buf prot[ISER_DIRS_NUM]; - struct iser_data_buf prot_copy[ISER_DIRS_NUM]; }; struct iser_page_vec { @@ -621,7 +595,6 @@ void iser_free_rx_descriptors(struct iser_conn *iser_conn); void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_task *iser_task, struct iser_data_buf *mem, - struct iser_data_buf *mem_copy, enum iser_data_dir cmd_dir); int iser_reg_rdma_mem_fmr(struct iscsi_iser_task *task, @@ -634,10 +607,6 @@ int iser_connect(struct iser_conn *iser_conn, struct sockaddr *dst_addr, int non_blocking); -int iser_reg_page_vec(struct ib_conn *ib_conn, - struct iser_page_vec *page_vec, - struct iser_mem_reg *mem_reg); - void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task, enum iser_data_dir cmd_dir); void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task, @@ -667,4 +636,9 @@ int iser_create_fastreg_pool(struct ib_conn *ib_conn, unsigned cmds_max); void iser_free_fastreg_pool(struct ib_conn *ib_conn); u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task, enum iser_data_dir cmd_dir, sector_t *sector); +struct fast_reg_descriptor * +iser_reg_desc_get(struct ib_conn *ib_conn); +void +iser_reg_desc_put(struct ib_conn *ib_conn, + struct fast_reg_descriptor *desc); #endif diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 20e859a6f1a6..3e2118e8ed87 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -50,7 +50,7 @@ static int iser_prepare_read_cmd(struct iscsi_task *task) { struct iscsi_iser_task *iser_task = task->dd_data; struct iser_device *device = iser_task->iser_conn->ib_conn.device; - struct iser_regd_buf *regd_buf; + struct iser_mem_reg *mem_reg; int err; struct iser_hdr *hdr = &iser_task->desc.iser_header; struct iser_data_buf *buf_in = &iser_task->data[ISER_DIR_IN]; @@ -78,15 +78,15 @@ static int iser_prepare_read_cmd(struct iscsi_task *task) iser_err("Failed to set up Data-IN RDMA\n"); return err; } - regd_buf = &iser_task->rdma_regd[ISER_DIR_IN]; + mem_reg = &iser_task->rdma_reg[ISER_DIR_IN]; hdr->flags |= ISER_RSV; - hdr->read_stag = cpu_to_be32(regd_buf->reg.rkey); - hdr->read_va = cpu_to_be64(regd_buf->reg.va); + hdr->read_stag = cpu_to_be32(mem_reg->rkey); + hdr->read_va = cpu_to_be64(mem_reg->sge.addr); iser_dbg("Cmd itt:%d READ tags RKEY:%#.4X VA:%#llX\n", - task->itt, regd_buf->reg.rkey, - (unsigned long long)regd_buf->reg.va); + task->itt, mem_reg->rkey, + (unsigned long long)mem_reg->sge.addr); return 0; } @@ -104,7 +104,7 @@ iser_prepare_write_cmd(struct iscsi_task *task, { struct iscsi_iser_task *iser_task = task->dd_data; struct iser_device *device = iser_task->iser_conn->ib_conn.device; - struct iser_regd_buf *regd_buf; + struct iser_mem_reg *mem_reg; int err; struct iser_hdr *hdr = &iser_task->desc.iser_header; struct iser_data_buf *buf_out = &iser_task->data[ISER_DIR_OUT]; @@ -134,25 +134,25 @@ iser_prepare_write_cmd(struct iscsi_task *task, return err; } - regd_buf = &iser_task->rdma_regd[ISER_DIR_OUT]; + mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT]; if (unsol_sz < edtl) { hdr->flags |= ISER_WSV; - hdr->write_stag = cpu_to_be32(regd_buf->reg.rkey); - hdr->write_va = cpu_to_be64(regd_buf->reg.va + unsol_sz); + hdr->write_stag = cpu_to_be32(mem_reg->rkey); + hdr->write_va = cpu_to_be64(mem_reg->sge.addr + unsol_sz); iser_dbg("Cmd itt:%d, WRITE tags, RKEY:%#.4X " "VA:%#llX + unsol:%d\n", - task->itt, regd_buf->reg.rkey, - (unsigned long long)regd_buf->reg.va, unsol_sz); + task->itt, mem_reg->rkey, + (unsigned long long)mem_reg->sge.addr, unsol_sz); } if (imm_sz > 0) { iser_dbg("Cmd itt:%d, WRITE, adding imm.data sz: %d\n", task->itt, imm_sz); - tx_dsg->addr = regd_buf->reg.va; + tx_dsg->addr = mem_reg->sge.addr; tx_dsg->length = imm_sz; - tx_dsg->lkey = regd_buf->reg.lkey; + tx_dsg->lkey = mem_reg->sge.lkey; iser_task->desc.num_sge = 2; } @@ -401,16 +401,16 @@ int iser_send_command(struct iscsi_conn *conn, } if (scsi_sg_count(sc)) { /* using a scatter list */ - data_buf->buf = scsi_sglist(sc); + data_buf->sg = scsi_sglist(sc); data_buf->size = scsi_sg_count(sc); } data_buf->data_len = scsi_bufflen(sc); if (scsi_prot_sg_count(sc)) { - prot_buf->buf = scsi_prot_sglist(sc); + prot_buf->sg = scsi_prot_sglist(sc); prot_buf->size = scsi_prot_sg_count(sc); - prot_buf->data_len = data_buf->data_len >> - ilog2(sc->device->sector_size) * 8; + prot_buf->data_len = (data_buf->data_len >> + ilog2(sc->device->sector_size)) * 8; } if (hdr->flags & ISCSI_FLAG_CMD_READ) { @@ -450,7 +450,7 @@ int iser_send_data_out(struct iscsi_conn *conn, struct iser_conn *iser_conn = conn->dd_data; struct iscsi_iser_task *iser_task = task->dd_data; struct iser_tx_desc *tx_desc = NULL; - struct iser_regd_buf *regd_buf; + struct iser_mem_reg *mem_reg; unsigned long buf_offset; unsigned long data_seg_len; uint32_t itt; @@ -477,11 +477,11 @@ int iser_send_data_out(struct iscsi_conn *conn, /* build the tx desc */ iser_initialize_task_headers(task, tx_desc); - regd_buf = &iser_task->rdma_regd[ISER_DIR_OUT]; + mem_reg = &iser_task->rdma_reg[ISER_DIR_OUT]; tx_dsg = &tx_desc->tx_sg[1]; - tx_dsg->addr = regd_buf->reg.va + buf_offset; - tx_dsg->length = data_seg_len; - tx_dsg->lkey = regd_buf->reg.lkey; + tx_dsg->addr = mem_reg->sge.addr + buf_offset; + tx_dsg->length = data_seg_len; + tx_dsg->lkey = mem_reg->sge.lkey; tx_desc->num_sge = 2; if (buf_offset + data_seg_len > iser_task->data[ISER_DIR_OUT].data_len) { @@ -658,10 +658,10 @@ void iser_task_rdma_init(struct iscsi_iser_task *iser_task) iser_task->prot[ISER_DIR_IN].data_len = 0; iser_task->prot[ISER_DIR_OUT].data_len = 0; - memset(&iser_task->rdma_regd[ISER_DIR_IN], 0, - sizeof(struct iser_regd_buf)); - memset(&iser_task->rdma_regd[ISER_DIR_OUT], 0, - sizeof(struct iser_regd_buf)); + memset(&iser_task->rdma_reg[ISER_DIR_IN], 0, + sizeof(struct iser_mem_reg)); + memset(&iser_task->rdma_reg[ISER_DIR_OUT], 0, + sizeof(struct iser_mem_reg)); } void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task) @@ -674,35 +674,31 @@ void iser_task_rdma_finalize(struct iscsi_iser_task *iser_task) /* if we were reading, copy back to unaligned sglist, * anyway dma_unmap and free the copy */ - if (iser_task->data_copy[ISER_DIR_IN].copy_buf != NULL) { + if (iser_task->data[ISER_DIR_IN].orig_sg) { is_rdma_data_aligned = 0; iser_finalize_rdma_unaligned_sg(iser_task, &iser_task->data[ISER_DIR_IN], - &iser_task->data_copy[ISER_DIR_IN], ISER_DIR_IN); } - if (iser_task->data_copy[ISER_DIR_OUT].copy_buf != NULL) { + if (iser_task->data[ISER_DIR_OUT].orig_sg) { is_rdma_data_aligned = 0; iser_finalize_rdma_unaligned_sg(iser_task, &iser_task->data[ISER_DIR_OUT], - &iser_task->data_copy[ISER_DIR_OUT], ISER_DIR_OUT); } - if (iser_task->prot_copy[ISER_DIR_IN].copy_buf != NULL) { + if (iser_task->prot[ISER_DIR_IN].orig_sg) { is_rdma_prot_aligned = 0; iser_finalize_rdma_unaligned_sg(iser_task, &iser_task->prot[ISER_DIR_IN], - &iser_task->prot_copy[ISER_DIR_IN], ISER_DIR_IN); } - if (iser_task->prot_copy[ISER_DIR_OUT].copy_buf != NULL) { + if (iser_task->prot[ISER_DIR_OUT].orig_sg) { is_rdma_prot_aligned = 0; iser_finalize_rdma_unaligned_sg(iser_task, &iser_task->prot[ISER_DIR_OUT], - &iser_task->prot_copy[ISER_DIR_OUT], ISER_DIR_OUT); } diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 341040bf0984..f0cdc961eb11 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -39,68 +39,173 @@ #include "iscsi_iser.h" -#define ISER_KMALLOC_THRESHOLD 0x20000 /* 128K - kmalloc limit */ +static void +iser_free_bounce_sg(struct iser_data_buf *data) +{ + struct scatterlist *sg; + int count; -/** - * iser_start_rdma_unaligned_sg - */ -static int iser_start_rdma_unaligned_sg(struct iscsi_iser_task *iser_task, - struct iser_data_buf *data, - struct iser_data_buf *data_copy, - enum iser_data_dir cmd_dir) + for_each_sg(data->sg, sg, data->size, count) + __free_page(sg_page(sg)); + + kfree(data->sg); + + data->sg = data->orig_sg; + data->size = data->orig_size; + data->orig_sg = NULL; + data->orig_size = 0; +} + +static int +iser_alloc_bounce_sg(struct iser_data_buf *data) { - struct ib_device *dev = iser_task->iser_conn->ib_conn.device->ib_device; - struct scatterlist *sgl = (struct scatterlist *)data->buf; struct scatterlist *sg; - char *mem = NULL; - unsigned long cmd_data_len = 0; - int dma_nents, i; + struct page *page; + unsigned long length = data->data_len; + int i = 0, nents = DIV_ROUND_UP(length, PAGE_SIZE); - for_each_sg(sgl, sg, data->size, i) - cmd_data_len += ib_sg_dma_len(dev, sg); + sg = kcalloc(nents, sizeof(*sg), GFP_ATOMIC); + if (!sg) + goto err; - if (cmd_data_len > ISER_KMALLOC_THRESHOLD) - mem = (void *)__get_free_pages(GFP_ATOMIC, - ilog2(roundup_pow_of_two(cmd_data_len)) - PAGE_SHIFT); - else - mem = kmalloc(cmd_data_len, GFP_ATOMIC); + sg_init_table(sg, nents); + while (length) { + u32 page_len = min_t(u32, length, PAGE_SIZE); - if (mem == NULL) { - iser_err("Failed to allocate mem size %d %d for copying sglist\n", - data->size, (int)cmd_data_len); - return -ENOMEM; + page = alloc_page(GFP_ATOMIC); + if (!page) + goto err; + + sg_set_page(&sg[i], page, page_len, 0); + length -= page_len; + i++; } - if (cmd_dir == ISER_DIR_OUT) { - /* copy the unaligned sg the buffer which is used for RDMA */ - char *p, *from; - - sgl = (struct scatterlist *)data->buf; - p = mem; - for_each_sg(sgl, sg, data->size, i) { - from = kmap_atomic(sg_page(sg)); - memcpy(p, - from + sg->offset, - sg->length); - kunmap_atomic(from); - p += sg->length; + data->orig_sg = data->sg; + data->orig_size = data->size; + data->sg = sg; + data->size = nents; + + return 0; + +err: + for (; i > 0; i--) + __free_page(sg_page(&sg[i - 1])); + kfree(sg); + + return -ENOMEM; +} + +static void +iser_copy_bounce(struct iser_data_buf *data, bool to_buffer) +{ + struct scatterlist *osg, *bsg = data->sg; + void *oaddr, *baddr; + unsigned int left = data->data_len; + unsigned int bsg_off = 0; + int i; + + for_each_sg(data->orig_sg, osg, data->orig_size, i) { + unsigned int copy_len, osg_off = 0; + + oaddr = kmap_atomic(sg_page(osg)) + osg->offset; + copy_len = min(left, osg->length); + while (copy_len) { + unsigned int len = min(copy_len, bsg->length - bsg_off); + + baddr = kmap_atomic(sg_page(bsg)) + bsg->offset; + if (to_buffer) + memcpy(baddr + bsg_off, oaddr + osg_off, len); + else + memcpy(oaddr + osg_off, baddr + bsg_off, len); + + kunmap_atomic(baddr - bsg->offset); + osg_off += len; + bsg_off += len; + copy_len -= len; + + if (bsg_off >= bsg->length) { + bsg = sg_next(bsg); + bsg_off = 0; + } } + kunmap_atomic(oaddr - osg->offset); + left -= osg_off; } +} + +static inline void +iser_copy_from_bounce(struct iser_data_buf *data) +{ + iser_copy_bounce(data, false); +} + +static inline void +iser_copy_to_bounce(struct iser_data_buf *data) +{ + iser_copy_bounce(data, true); +} + +struct fast_reg_descriptor * +iser_reg_desc_get(struct ib_conn *ib_conn) +{ + struct fast_reg_descriptor *desc; + unsigned long flags; + + spin_lock_irqsave(&ib_conn->lock, flags); + desc = list_first_entry(&ib_conn->fastreg.pool, + struct fast_reg_descriptor, list); + list_del(&desc->list); + spin_unlock_irqrestore(&ib_conn->lock, flags); + + return desc; +} + +void +iser_reg_desc_put(struct ib_conn *ib_conn, + struct fast_reg_descriptor *desc) +{ + unsigned long flags; - sg_init_one(&data_copy->sg_single, mem, cmd_data_len); - data_copy->buf = &data_copy->sg_single; - data_copy->size = 1; - data_copy->copy_buf = mem; + spin_lock_irqsave(&ib_conn->lock, flags); + list_add(&desc->list, &ib_conn->fastreg.pool); + spin_unlock_irqrestore(&ib_conn->lock, flags); +} - dma_nents = ib_dma_map_sg(dev, &data_copy->sg_single, 1, - (cmd_dir == ISER_DIR_OUT) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE); - BUG_ON(dma_nents == 0); +/** + * iser_start_rdma_unaligned_sg + */ +static int iser_start_rdma_unaligned_sg(struct iscsi_iser_task *iser_task, + struct iser_data_buf *data, + enum iser_data_dir cmd_dir) +{ + struct ib_device *dev = iser_task->iser_conn->ib_conn.device->ib_device; + int rc; + + rc = iser_alloc_bounce_sg(data); + if (rc) { + iser_err("Failed to allocate bounce for data len %lu\n", + data->data_len); + return rc; + } + + if (cmd_dir == ISER_DIR_OUT) + iser_copy_to_bounce(data); - data_copy->dma_nents = dma_nents; - data_copy->data_len = cmd_data_len; + data->dma_nents = ib_dma_map_sg(dev, data->sg, data->size, + (cmd_dir == ISER_DIR_OUT) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); + if (!data->dma_nents) { + iser_err("Got dma_nents %d, something went wrong...\n", + data->dma_nents); + rc = -ENOMEM; + goto err; + } return 0; +err: + iser_free_bounce_sg(data); + return rc; } /** @@ -109,51 +214,18 @@ static int iser_start_rdma_unaligned_sg(struct iscsi_iser_task *iser_task, void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_task *iser_task, struct iser_data_buf *data, - struct iser_data_buf *data_copy, enum iser_data_dir cmd_dir) { - struct ib_device *dev; - unsigned long cmd_data_len; - - dev = iser_task->iser_conn->ib_conn.device->ib_device; + struct ib_device *dev = iser_task->iser_conn->ib_conn.device->ib_device; - ib_dma_unmap_sg(dev, &data_copy->sg_single, 1, + ib_dma_unmap_sg(dev, data->sg, data->size, (cmd_dir == ISER_DIR_OUT) ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - if (cmd_dir == ISER_DIR_IN) { - char *mem; - struct scatterlist *sgl, *sg; - unsigned char *p, *to; - unsigned int sg_size; - int i; - - /* copy back read RDMA to unaligned sg */ - mem = data_copy->copy_buf; - - sgl = (struct scatterlist *)data->buf; - sg_size = data->size; - - p = mem; - for_each_sg(sgl, sg, sg_size, i) { - to = kmap_atomic(sg_page(sg)); - memcpy(to + sg->offset, - p, - sg->length); - kunmap_atomic(to); - p += sg->length; - } - } + if (cmd_dir == ISER_DIR_IN) + iser_copy_from_bounce(data); - cmd_data_len = data->data_len; - - if (cmd_data_len > ISER_KMALLOC_THRESHOLD) - free_pages((unsigned long)data_copy->copy_buf, - ilog2(roundup_pow_of_two(cmd_data_len)) - PAGE_SHIFT); - else - kfree(data_copy->copy_buf); - - data_copy->copy_buf = NULL; + iser_free_bounce_sg(data); } #define IS_4K_ALIGNED(addr) ((((unsigned long)addr) & ~MASK_4K) == 0) @@ -175,7 +247,7 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data, struct ib_device *ibdev, u64 *pages, int *offset, int *data_size) { - struct scatterlist *sg, *sgl = (struct scatterlist *)data->buf; + struct scatterlist *sg, *sgl = data->sg; u64 start_addr, end_addr, page, chunk_start = 0; unsigned long total_sz = 0; unsigned int dma_len; @@ -227,14 +299,14 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data, static int iser_data_buf_aligned_len(struct iser_data_buf *data, struct ib_device *ibdev) { - struct scatterlist *sgl, *sg, *next_sg = NULL; + struct scatterlist *sg, *sgl, *next_sg = NULL; u64 start_addr, end_addr; int i, ret_len, start_check = 0; if (data->dma_nents == 1) return 1; - sgl = (struct scatterlist *)data->buf; + sgl = data->sg; start_addr = ib_sg_dma_address(ibdev, sgl); for_each_sg(sgl, sg, data->dma_nents, i) { @@ -266,11 +338,10 @@ static int iser_data_buf_aligned_len(struct iser_data_buf *data, static void iser_data_buf_dump(struct iser_data_buf *data, struct ib_device *ibdev) { - struct scatterlist *sgl = (struct scatterlist *)data->buf; struct scatterlist *sg; int i; - for_each_sg(sgl, sg, data->dma_nents, i) + for_each_sg(data->sg, sg, data->dma_nents, i) iser_dbg("sg[%d] dma_addr:0x%lX page:0x%p " "off:0x%x sz:0x%x dma_len:0x%x\n", i, (unsigned long)ib_sg_dma_address(ibdev, sg), @@ -288,31 +359,6 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) iser_err("%d %lx\n",i,(unsigned long)page_vec->pages[i]); } -static void iser_page_vec_build(struct iser_data_buf *data, - struct iser_page_vec *page_vec, - struct ib_device *ibdev) -{ - int page_vec_len = 0; - - page_vec->length = 0; - page_vec->offset = 0; - - iser_dbg("Translating sg sz: %d\n", data->dma_nents); - page_vec_len = iser_sg_to_page_vec(data, ibdev, page_vec->pages, - &page_vec->offset, - &page_vec->data_size); - iser_dbg("sg len %d page_vec_len %d\n", data->dma_nents, page_vec_len); - - page_vec->length = page_vec_len; - - if (page_vec_len * SIZE_4K < page_vec->data_size) { - iser_err("page_vec too short to hold this SG\n"); - iser_data_buf_dump(data, ibdev); - iser_dump_page_vec(page_vec); - BUG(); - } -} - int iser_dma_map_task_data(struct iscsi_iser_task *iser_task, struct iser_data_buf *data, enum iser_data_dir iser_dir, @@ -323,7 +369,7 @@ int iser_dma_map_task_data(struct iscsi_iser_task *iser_task, iser_task->dir[iser_dir] = 1; dev = iser_task->iser_conn->ib_conn.device->ib_device; - data->dma_nents = ib_dma_map_sg(dev, data->buf, data->size, dma_dir); + data->dma_nents = ib_dma_map_sg(dev, data->sg, data->size, dma_dir); if (data->dma_nents == 0) { iser_err("dma_map_sg failed!!!\n"); return -EINVAL; @@ -338,24 +384,41 @@ void iser_dma_unmap_task_data(struct iscsi_iser_task *iser_task, struct ib_device *dev; dev = iser_task->iser_conn->ib_conn.device->ib_device; - ib_dma_unmap_sg(dev, data->buf, data->size, dir); + ib_dma_unmap_sg(dev, data->sg, data->size, dir); +} + +static int +iser_reg_dma(struct iser_device *device, struct iser_data_buf *mem, + struct iser_mem_reg *reg) +{ + struct scatterlist *sg = mem->sg; + + reg->sge.lkey = device->mr->lkey; + reg->rkey = device->mr->rkey; + reg->sge.addr = ib_sg_dma_address(device->ib_device, &sg[0]); + reg->sge.length = ib_sg_dma_len(device->ib_device, &sg[0]); + + iser_dbg("Single DMA entry: lkey=0x%x, rkey=0x%x, addr=0x%llx," + " length=0x%x\n", reg->sge.lkey, reg->rkey, + reg->sge.addr, reg->sge.length); + + return 0; } static int fall_to_bounce_buf(struct iscsi_iser_task *iser_task, - struct ib_device *ibdev, struct iser_data_buf *mem, - struct iser_data_buf *mem_copy, enum iser_data_dir cmd_dir, int aligned_len) { - struct iscsi_conn *iscsi_conn = iser_task->iser_conn->iscsi_conn; + struct iscsi_conn *iscsi_conn = iser_task->iser_conn->iscsi_conn; + struct iser_device *device = iser_task->iser_conn->ib_conn.device; iscsi_conn->fmr_unalign_cnt++; iser_warn("rdma alignment violation (%d/%d aligned) or FMR not supported\n", aligned_len, mem->size); if (iser_debug_level > 0) - iser_data_buf_dump(mem, ibdev); + iser_data_buf_dump(mem, device->ib_device); /* unmap the command data before accessing it */ iser_dma_unmap_task_data(iser_task, mem, @@ -364,13 +427,95 @@ static int fall_to_bounce_buf(struct iscsi_iser_task *iser_task, /* allocate copy buf, if we are writing, copy the */ /* unaligned scatterlist, dma map the copy */ - if (iser_start_rdma_unaligned_sg(iser_task, mem, mem_copy, cmd_dir) != 0) + if (iser_start_rdma_unaligned_sg(iser_task, mem, cmd_dir) != 0) return -ENOMEM; return 0; } /** + * iser_reg_page_vec - Register physical memory + * + * returns: 0 on success, errno code on failure + */ +static +int iser_reg_page_vec(struct iscsi_iser_task *iser_task, + struct iser_data_buf *mem, + struct iser_page_vec *page_vec, + struct iser_mem_reg *mem_reg) +{ + struct ib_conn *ib_conn = &iser_task->iser_conn->ib_conn; + struct iser_device *device = ib_conn->device; + struct ib_pool_fmr *fmr; + int ret, plen; + + plen = iser_sg_to_page_vec(mem, device->ib_device, + page_vec->pages, + &page_vec->offset, + &page_vec->data_size); + page_vec->length = plen; + if (plen * SIZE_4K < page_vec->data_size) { + iser_err("page vec too short to hold this SG\n"); + iser_data_buf_dump(mem, device->ib_device); + iser_dump_page_vec(page_vec); + return -EINVAL; + } + + fmr = ib_fmr_pool_map_phys(ib_conn->fmr.pool, + page_vec->pages, + page_vec->length, + page_vec->pages[0]); + if (IS_ERR(fmr)) { + ret = PTR_ERR(fmr); + iser_err("ib_fmr_pool_map_phys failed: %d\n", ret); + return ret; + } + + mem_reg->sge.lkey = fmr->fmr->lkey; + mem_reg->rkey = fmr->fmr->rkey; + mem_reg->sge.addr = page_vec->pages[0] + page_vec->offset; + mem_reg->sge.length = page_vec->data_size; + mem_reg->mem_h = fmr; + + return 0; +} + +/** + * Unregister (previosuly registered using FMR) memory. + * If memory is non-FMR does nothing. + */ +void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task, + enum iser_data_dir cmd_dir) +{ + struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir]; + int ret; + + if (!reg->mem_h) + return; + + iser_dbg("PHYSICAL Mem.Unregister mem_h %p\n", reg->mem_h); + + ret = ib_fmr_pool_unmap((struct ib_pool_fmr *)reg->mem_h); + if (ret) + iser_err("ib_fmr_pool_unmap failed %d\n", ret); + + reg->mem_h = NULL; +} + +void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task, + enum iser_data_dir cmd_dir) +{ + struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir]; + + if (!reg->mem_h) + return; + + iser_reg_desc_put(&iser_task->iser_conn->ib_conn, + reg->mem_h); + reg->mem_h = NULL; +} + +/** * iser_reg_rdma_mem_fmr - Registers memory intended for RDMA, * using FMR (if possible) obtaining rkey and va * @@ -383,45 +528,29 @@ int iser_reg_rdma_mem_fmr(struct iscsi_iser_task *iser_task, struct iser_device *device = ib_conn->device; struct ib_device *ibdev = device->ib_device; struct iser_data_buf *mem = &iser_task->data[cmd_dir]; - struct iser_regd_buf *regd_buf; + struct iser_mem_reg *mem_reg; int aligned_len; int err; int i; - struct scatterlist *sg; - regd_buf = &iser_task->rdma_regd[cmd_dir]; + mem_reg = &iser_task->rdma_reg[cmd_dir]; aligned_len = iser_data_buf_aligned_len(mem, ibdev); if (aligned_len != mem->dma_nents) { - err = fall_to_bounce_buf(iser_task, ibdev, mem, - &iser_task->data_copy[cmd_dir], + err = fall_to_bounce_buf(iser_task, mem, cmd_dir, aligned_len); if (err) { iser_err("failed to allocate bounce buffer\n"); return err; } - mem = &iser_task->data_copy[cmd_dir]; } /* if there a single dma entry, FMR is not needed */ if (mem->dma_nents == 1) { - sg = (struct scatterlist *)mem->buf; - - regd_buf->reg.lkey = device->mr->lkey; - regd_buf->reg.rkey = device->mr->rkey; - regd_buf->reg.len = ib_sg_dma_len(ibdev, &sg[0]); - regd_buf->reg.va = ib_sg_dma_address(ibdev, &sg[0]); - - iser_dbg("PHYSICAL Mem.register: lkey: 0x%08X rkey: 0x%08X " - "va: 0x%08lX sz: %ld]\n", - (unsigned int)regd_buf->reg.lkey, - (unsigned int)regd_buf->reg.rkey, - (unsigned long)regd_buf->reg.va, - (unsigned long)regd_buf->reg.len); + return iser_reg_dma(device, mem, mem_reg); } else { /* use FMR for multiple dma entries */ - iser_page_vec_build(mem, ib_conn->fmr.page_vec, ibdev); - err = iser_reg_page_vec(ib_conn, ib_conn->fmr.page_vec, - ®d_buf->reg); + err = iser_reg_page_vec(iser_task, mem, ib_conn->fmr.page_vec, + mem_reg); if (err && err != -EAGAIN) { iser_data_buf_dump(mem, ibdev); iser_err("mem->dma_nents = %d (dlength = 0x%x)\n", @@ -519,8 +648,10 @@ iser_inv_rkey(struct ib_send_wr *inv_wr, struct ib_mr *mr) static int iser_reg_sig_mr(struct iscsi_iser_task *iser_task, - struct fast_reg_descriptor *desc, struct ib_sge *data_sge, - struct ib_sge *prot_sge, struct ib_sge *sig_sge) + struct fast_reg_descriptor *desc, + struct iser_mem_reg *data_reg, + struct iser_mem_reg *prot_reg, + struct iser_mem_reg *sig_reg) { struct ib_conn *ib_conn = &iser_task->iser_conn->ib_conn; struct iser_pi_context *pi_ctx = desc->pi_ctx; @@ -544,12 +675,12 @@ iser_reg_sig_mr(struct iscsi_iser_task *iser_task, memset(&sig_wr, 0, sizeof(sig_wr)); sig_wr.opcode = IB_WR_REG_SIG_MR; sig_wr.wr_id = ISER_FASTREG_LI_WRID; - sig_wr.sg_list = data_sge; + sig_wr.sg_list = &data_reg->sge; sig_wr.num_sge = 1; sig_wr.wr.sig_handover.sig_attrs = &sig_attrs; sig_wr.wr.sig_handover.sig_mr = pi_ctx->sig_mr; if (scsi_prot_sg_count(iser_task->sc)) - sig_wr.wr.sig_handover.prot = prot_sge; + sig_wr.wr.sig_handover.prot = &prot_reg->sge; sig_wr.wr.sig_handover.access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; @@ -566,27 +697,26 @@ iser_reg_sig_mr(struct iscsi_iser_task *iser_task, } desc->reg_indicators &= ~ISER_SIG_KEY_VALID; - sig_sge->lkey = pi_ctx->sig_mr->lkey; - sig_sge->addr = 0; - sig_sge->length = scsi_transfer_length(iser_task->sc); + sig_reg->sge.lkey = pi_ctx->sig_mr->lkey; + sig_reg->rkey = pi_ctx->sig_mr->rkey; + sig_reg->sge.addr = 0; + sig_reg->sge.length = scsi_transfer_length(iser_task->sc); - iser_dbg("sig_sge: addr: 0x%llx length: %u lkey: 0x%x\n", - sig_sge->addr, sig_sge->length, - sig_sge->lkey); + iser_dbg("sig_sge: lkey: 0x%x, rkey: 0x%x, addr: 0x%llx, length: %u\n", + sig_reg->sge.lkey, sig_reg->rkey, sig_reg->sge.addr, + sig_reg->sge.length); err: return ret; } static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task, - struct iser_regd_buf *regd_buf, struct iser_data_buf *mem, + struct fast_reg_descriptor *desc, enum iser_reg_indicator ind, - struct ib_sge *sge) + struct iser_mem_reg *reg) { - struct fast_reg_descriptor *desc = regd_buf->reg.mem_h; struct ib_conn *ib_conn = &iser_task->iser_conn->ib_conn; struct iser_device *device = ib_conn->device; - struct ib_device *ibdev = device->ib_device; struct ib_mr *mr; struct ib_fast_reg_page_list *frpl; struct ib_send_wr fastreg_wr, inv_wr; @@ -594,17 +724,8 @@ static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task, int ret, offset, size, plen; /* if there a single dma entry, dma mr suffices */ - if (mem->dma_nents == 1) { - struct scatterlist *sg = (struct scatterlist *)mem->buf; - - sge->lkey = device->mr->lkey; - sge->addr = ib_sg_dma_address(ibdev, &sg[0]); - sge->length = ib_sg_dma_len(ibdev, &sg[0]); - - iser_dbg("Single DMA entry: lkey=0x%x, addr=0x%llx, length=0x%x\n", - sge->lkey, sge->addr, sge->length); - return 0; - } + if (mem->dma_nents == 1) + return iser_reg_dma(device, mem, reg); if (ind == ISER_DATA_KEY_VALID) { mr = desc->data_mr; @@ -652,9 +773,10 @@ static int iser_fast_reg_mr(struct iscsi_iser_task *iser_task, } desc->reg_indicators &= ~ind; - sge->lkey = mr->lkey; - sge->addr = frpl->page_list[0] + offset; - sge->length = size; + reg->sge.lkey = mr->lkey; + reg->rkey = mr->rkey; + reg->sge.addr = frpl->page_list[0] + offset; + reg->sge.length = size; return ret; } @@ -672,93 +794,66 @@ int iser_reg_rdma_mem_fastreg(struct iscsi_iser_task *iser_task, struct iser_device *device = ib_conn->device; struct ib_device *ibdev = device->ib_device; struct iser_data_buf *mem = &iser_task->data[cmd_dir]; - struct iser_regd_buf *regd_buf = &iser_task->rdma_regd[cmd_dir]; + struct iser_mem_reg *mem_reg = &iser_task->rdma_reg[cmd_dir]; struct fast_reg_descriptor *desc = NULL; - struct ib_sge data_sge; int err, aligned_len; - unsigned long flags; aligned_len = iser_data_buf_aligned_len(mem, ibdev); if (aligned_len != mem->dma_nents) { - err = fall_to_bounce_buf(iser_task, ibdev, mem, - &iser_task->data_copy[cmd_dir], + err = fall_to_bounce_buf(iser_task, mem, cmd_dir, aligned_len); if (err) { iser_err("failed to allocate bounce buffer\n"); return err; } - mem = &iser_task->data_copy[cmd_dir]; } if (mem->dma_nents != 1 || scsi_get_prot_op(iser_task->sc) != SCSI_PROT_NORMAL) { - spin_lock_irqsave(&ib_conn->lock, flags); - desc = list_first_entry(&ib_conn->fastreg.pool, - struct fast_reg_descriptor, list); - list_del(&desc->list); - spin_unlock_irqrestore(&ib_conn->lock, flags); - regd_buf->reg.mem_h = desc; + desc = iser_reg_desc_get(ib_conn); + mem_reg->mem_h = desc; } - err = iser_fast_reg_mr(iser_task, regd_buf, mem, - ISER_DATA_KEY_VALID, &data_sge); + err = iser_fast_reg_mr(iser_task, mem, desc, + ISER_DATA_KEY_VALID, mem_reg); if (err) goto err_reg; if (scsi_get_prot_op(iser_task->sc) != SCSI_PROT_NORMAL) { - struct ib_sge prot_sge, sig_sge; + struct iser_mem_reg prot_reg; - memset(&prot_sge, 0, sizeof(prot_sge)); + memset(&prot_reg, 0, sizeof(prot_reg)); if (scsi_prot_sg_count(iser_task->sc)) { mem = &iser_task->prot[cmd_dir]; aligned_len = iser_data_buf_aligned_len(mem, ibdev); if (aligned_len != mem->dma_nents) { - err = fall_to_bounce_buf(iser_task, ibdev, mem, - &iser_task->prot_copy[cmd_dir], + err = fall_to_bounce_buf(iser_task, mem, cmd_dir, aligned_len); if (err) { iser_err("failed to allocate bounce buffer\n"); return err; } - mem = &iser_task->prot_copy[cmd_dir]; } - err = iser_fast_reg_mr(iser_task, regd_buf, mem, - ISER_PROT_KEY_VALID, &prot_sge); + err = iser_fast_reg_mr(iser_task, mem, desc, + ISER_PROT_KEY_VALID, &prot_reg); if (err) goto err_reg; } - err = iser_reg_sig_mr(iser_task, desc, &data_sge, - &prot_sge, &sig_sge); + err = iser_reg_sig_mr(iser_task, desc, mem_reg, + &prot_reg, mem_reg); if (err) { iser_err("Failed to register signature mr\n"); return err; } desc->reg_indicators |= ISER_FASTREG_PROTECTED; - - regd_buf->reg.lkey = sig_sge.lkey; - regd_buf->reg.rkey = desc->pi_ctx->sig_mr->rkey; - regd_buf->reg.va = sig_sge.addr; - regd_buf->reg.len = sig_sge.length; - } else { - if (desc) - regd_buf->reg.rkey = desc->data_mr->rkey; - else - regd_buf->reg.rkey = device->mr->rkey; - - regd_buf->reg.lkey = data_sge.lkey; - regd_buf->reg.va = data_sge.addr; - regd_buf->reg.len = data_sge.length; } return 0; err_reg: - if (desc) { - spin_lock_irqsave(&ib_conn->lock, flags); - list_add_tail(&desc->list, &ib_conn->fastreg.pool); - spin_unlock_irqrestore(&ib_conn->lock, flags); - } + if (desc) + iser_reg_desc_put(ib_conn, desc); return err; } diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 4065abe28829..cc2dd35ffbc0 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -274,6 +274,65 @@ void iser_free_fmr_pool(struct ib_conn *ib_conn) } static int +iser_alloc_pi_ctx(struct ib_device *ib_device, struct ib_pd *pd, + struct fast_reg_descriptor *desc) +{ + struct iser_pi_context *pi_ctx = NULL; + struct ib_mr_init_attr mr_init_attr = {.max_reg_descriptors = 2, + .flags = IB_MR_SIGNATURE_EN}; + int ret = 0; + + desc->pi_ctx = kzalloc(sizeof(*desc->pi_ctx), GFP_KERNEL); + if (!desc->pi_ctx) + return -ENOMEM; + + pi_ctx = desc->pi_ctx; + + pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(ib_device, + ISCSI_ISER_SG_TABLESIZE); + if (IS_ERR(pi_ctx->prot_frpl)) { + ret = PTR_ERR(pi_ctx->prot_frpl); + goto prot_frpl_failure; + } + + pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, + ISCSI_ISER_SG_TABLESIZE + 1); + if (IS_ERR(pi_ctx->prot_mr)) { + ret = PTR_ERR(pi_ctx->prot_mr); + goto prot_mr_failure; + } + desc->reg_indicators |= ISER_PROT_KEY_VALID; + + pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr); + if (IS_ERR(pi_ctx->sig_mr)) { + ret = PTR_ERR(pi_ctx->sig_mr); + goto sig_mr_failure; + } + desc->reg_indicators |= ISER_SIG_KEY_VALID; + desc->reg_indicators &= ~ISER_FASTREG_PROTECTED; + + return 0; + +sig_mr_failure: + ib_dereg_mr(desc->pi_ctx->prot_mr); +prot_mr_failure: + ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl); +prot_frpl_failure: + kfree(desc->pi_ctx); + + return ret; +} + +static void +iser_free_pi_ctx(struct iser_pi_context *pi_ctx) +{ + ib_free_fast_reg_page_list(pi_ctx->prot_frpl); + ib_dereg_mr(pi_ctx->prot_mr); + ib_destroy_mr(pi_ctx->sig_mr); + kfree(pi_ctx); +} + +static int iser_create_fastreg_desc(struct ib_device *ib_device, struct ib_pd *pd, bool pi_enable, struct fast_reg_descriptor *desc) { @@ -297,59 +356,12 @@ iser_create_fastreg_desc(struct ib_device *ib_device, struct ib_pd *pd, desc->reg_indicators |= ISER_DATA_KEY_VALID; if (pi_enable) { - struct ib_mr_init_attr mr_init_attr = {0}; - struct iser_pi_context *pi_ctx = NULL; - - desc->pi_ctx = kzalloc(sizeof(*desc->pi_ctx), GFP_KERNEL); - if (!desc->pi_ctx) { - iser_err("Failed to allocate pi context\n"); - ret = -ENOMEM; + ret = iser_alloc_pi_ctx(ib_device, pd, desc); + if (ret) goto pi_ctx_alloc_failure; - } - pi_ctx = desc->pi_ctx; - - pi_ctx->prot_frpl = ib_alloc_fast_reg_page_list(ib_device, - ISCSI_ISER_SG_TABLESIZE); - if (IS_ERR(pi_ctx->prot_frpl)) { - ret = PTR_ERR(pi_ctx->prot_frpl); - iser_err("Failed to allocate prot frpl ret=%d\n", - ret); - goto prot_frpl_failure; - } - - pi_ctx->prot_mr = ib_alloc_fast_reg_mr(pd, - ISCSI_ISER_SG_TABLESIZE + 1); - if (IS_ERR(pi_ctx->prot_mr)) { - ret = PTR_ERR(pi_ctx->prot_mr); - iser_err("Failed to allocate prot frmr ret=%d\n", - ret); - goto prot_mr_failure; - } - desc->reg_indicators |= ISER_PROT_KEY_VALID; - - mr_init_attr.max_reg_descriptors = 2; - mr_init_attr.flags |= IB_MR_SIGNATURE_EN; - pi_ctx->sig_mr = ib_create_mr(pd, &mr_init_attr); - if (IS_ERR(pi_ctx->sig_mr)) { - ret = PTR_ERR(pi_ctx->sig_mr); - iser_err("Failed to allocate signature enabled mr err=%d\n", - ret); - goto sig_mr_failure; - } - desc->reg_indicators |= ISER_SIG_KEY_VALID; } - desc->reg_indicators &= ~ISER_FASTREG_PROTECTED; - - iser_dbg("Create fr_desc %p page_list %p\n", - desc, desc->data_frpl->page_list); return 0; -sig_mr_failure: - ib_dereg_mr(desc->pi_ctx->prot_mr); -prot_mr_failure: - ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl); -prot_frpl_failure: - kfree(desc->pi_ctx); pi_ctx_alloc_failure: ib_dereg_mr(desc->data_mr); fast_reg_mr_failure: @@ -416,12 +428,8 @@ void iser_free_fastreg_pool(struct ib_conn *ib_conn) list_del(&desc->list); ib_free_fast_reg_page_list(desc->data_frpl); ib_dereg_mr(desc->data_mr); - if (desc->pi_ctx) { - ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl); - ib_dereg_mr(desc->pi_ctx->prot_mr); - ib_destroy_mr(desc->pi_ctx->sig_mr); - kfree(desc->pi_ctx); - } + if (desc->pi_ctx) + iser_free_pi_ctx(desc->pi_ctx); kfree(desc); ++i; } @@ -721,7 +729,7 @@ static void iser_connect_error(struct rdma_cm_id *cma_id) struct iser_conn *iser_conn; iser_conn = (struct iser_conn *)cma_id->context; - iser_conn->state = ISER_CONN_DOWN; + iser_conn->state = ISER_CONN_TERMINATING; } /** @@ -992,93 +1000,6 @@ connect_failure: return err; } -/** - * iser_reg_page_vec - Register physical memory - * - * returns: 0 on success, errno code on failure - */ -int iser_reg_page_vec(struct ib_conn *ib_conn, - struct iser_page_vec *page_vec, - struct iser_mem_reg *mem_reg) -{ - struct ib_pool_fmr *mem; - u64 io_addr; - u64 *page_list; - int status; - - page_list = page_vec->pages; - io_addr = page_list[0]; - - mem = ib_fmr_pool_map_phys(ib_conn->fmr.pool, - page_list, - page_vec->length, - io_addr); - - if (IS_ERR(mem)) { - status = (int)PTR_ERR(mem); - iser_err("ib_fmr_pool_map_phys failed: %d\n", status); - return status; - } - - mem_reg->lkey = mem->fmr->lkey; - mem_reg->rkey = mem->fmr->rkey; - mem_reg->len = page_vec->length * SIZE_4K; - mem_reg->va = io_addr; - mem_reg->mem_h = (void *)mem; - - mem_reg->va += page_vec->offset; - mem_reg->len = page_vec->data_size; - - iser_dbg("PHYSICAL Mem.register, [PHYS p_array: 0x%p, sz: %d, " - "entry[0]: (0x%08lx,%ld)] -> " - "[lkey: 0x%08X mem_h: 0x%p va: 0x%08lX sz: %ld]\n", - page_vec, page_vec->length, - (unsigned long)page_vec->pages[0], - (unsigned long)page_vec->data_size, - (unsigned int)mem_reg->lkey, mem_reg->mem_h, - (unsigned long)mem_reg->va, (unsigned long)mem_reg->len); - return 0; -} - -/** - * Unregister (previosuly registered using FMR) memory. - * If memory is non-FMR does nothing. - */ -void iser_unreg_mem_fmr(struct iscsi_iser_task *iser_task, - enum iser_data_dir cmd_dir) -{ - struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg; - int ret; - - if (!reg->mem_h) - return; - - iser_dbg("PHYSICAL Mem.Unregister mem_h %p\n",reg->mem_h); - - ret = ib_fmr_pool_unmap((struct ib_pool_fmr *)reg->mem_h); - if (ret) - iser_err("ib_fmr_pool_unmap failed %d\n", ret); - - reg->mem_h = NULL; -} - -void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task, - enum iser_data_dir cmd_dir) -{ - struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg; - struct iser_conn *iser_conn = iser_task->iser_conn; - struct ib_conn *ib_conn = &iser_conn->ib_conn; - struct fast_reg_descriptor *desc = reg->mem_h; - - if (!desc) - return; - - reg->mem_h = NULL; - spin_lock_bh(&ib_conn->lock); - list_add_tail(&desc->list, &ib_conn->fastreg.pool); - spin_unlock_bh(&ib_conn->lock); -} - int iser_post_recvl(struct iser_conn *iser_conn) { struct ib_recv_wr rx_wr, *rx_wr_failed; @@ -1210,6 +1131,9 @@ iser_handle_comp_error(struct ib_conn *ib_conn, iscsi_conn_failure(iser_conn->iscsi_conn, ISCSI_ERR_CONN_FAILED); + if (wc->wr_id == ISER_FASTREG_LI_WRID) + return; + if (is_iser_tx_desc(iser_conn, wr_id)) { struct iser_tx_desc *desc = wr_id; @@ -1254,13 +1178,11 @@ static void iser_handle_wc(struct ib_wc *wc) else iser_dbg("flush error: wr id %llx\n", wc->wr_id); - if (wc->wr_id != ISER_FASTREG_LI_WRID && - wc->wr_id != ISER_BEACON_WRID) - iser_handle_comp_error(ib_conn, wc); - - /* complete in case all flush errors were consumed */ if (wc->wr_id == ISER_BEACON_WRID) + /* all flush errors were consumed */ complete(&ib_conn->flush_comp); + else + iser_handle_comp_error(ib_conn, wc); } } @@ -1306,7 +1228,7 @@ static void iser_cq_callback(struct ib_cq *cq, void *cq_context) u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task, enum iser_data_dir cmd_dir, sector_t *sector) { - struct iser_mem_reg *reg = &iser_task->rdma_regd[cmd_dir].reg; + struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir]; struct fast_reg_descriptor *desc = reg->mem_h; unsigned long sector_size = iser_task->sc->device->sector_size; struct ib_mr_status mr_status; diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 075b19cc78e8..327529ee85eb 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -76,12 +76,12 @@ isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd) static void isert_qp_event_callback(struct ib_event *e, void *context) { - struct isert_conn *isert_conn = (struct isert_conn *)context; + struct isert_conn *isert_conn = context; isert_err("conn %p event: %d\n", isert_conn, e->event); switch (e->event) { case IB_EVENT_COMM_EST: - rdma_notify(isert_conn->conn_cm_id, IB_EVENT_COMM_EST); + rdma_notify(isert_conn->cm_id, IB_EVENT_COMM_EST); break; case IB_EVENT_QP_LAST_WQE_REACHED: isert_warn("Reached TX IB_EVENT_QP_LAST_WQE_REACHED\n"); @@ -107,13 +107,12 @@ isert_query_device(struct ib_device *ib_dev, struct ib_device_attr *devattr) return 0; } -static int -isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) +static struct isert_comp * +isert_comp_get(struct isert_conn *isert_conn) { - struct isert_device *device = isert_conn->conn_device; - struct ib_qp_init_attr attr; + struct isert_device *device = isert_conn->device; struct isert_comp *comp; - int ret, i, min = 0; + int i, min = 0; mutex_lock(&device_list_mutex); for (i = 0; i < device->comps_used; i++) @@ -122,9 +121,30 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) min = i; comp = &device->comps[min]; comp->active_qps++; + mutex_unlock(&device_list_mutex); + isert_info("conn %p, using comp %p min_index: %d\n", isert_conn, comp, min); + + return comp; +} + +static void +isert_comp_put(struct isert_comp *comp) +{ + mutex_lock(&device_list_mutex); + comp->active_qps--; mutex_unlock(&device_list_mutex); +} + +static struct ib_qp * +isert_create_qp(struct isert_conn *isert_conn, + struct isert_comp *comp, + struct rdma_cm_id *cma_id) +{ + struct isert_device *device = isert_conn->device; + struct ib_qp_init_attr attr; + int ret; memset(&attr, 0, sizeof(struct ib_qp_init_attr)); attr.event_handler = isert_qp_event_callback; @@ -149,19 +169,31 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) if (device->pi_capable) attr.create_flags |= IB_QP_CREATE_SIGNATURE_EN; - ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr); + ret = rdma_create_qp(cma_id, device->pd, &attr); if (ret) { isert_err("rdma_create_qp failed for cma_id %d\n", ret); + return ERR_PTR(ret); + } + + return cma_id->qp; +} + +static int +isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) +{ + struct isert_comp *comp; + int ret; + + comp = isert_comp_get(isert_conn); + isert_conn->qp = isert_create_qp(isert_conn, comp, cma_id); + if (IS_ERR(isert_conn->qp)) { + ret = PTR_ERR(isert_conn->qp); goto err; } - isert_conn->conn_qp = cma_id->qp; return 0; err: - mutex_lock(&device_list_mutex); - comp->active_qps--; - mutex_unlock(&device_list_mutex); - + isert_comp_put(comp); return ret; } @@ -174,18 +206,19 @@ isert_cq_event_callback(struct ib_event *e, void *context) static int isert_alloc_rx_descriptors(struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct iser_rx_desc *rx_desc; struct ib_sge *rx_sg; u64 dma_addr; int i, j; - isert_conn->conn_rx_descs = kzalloc(ISERT_QP_MAX_RECV_DTOS * + isert_conn->rx_descs = kzalloc(ISERT_QP_MAX_RECV_DTOS * sizeof(struct iser_rx_desc), GFP_KERNEL); - if (!isert_conn->conn_rx_descs) + if (!isert_conn->rx_descs) goto fail; - rx_desc = isert_conn->conn_rx_descs; + rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc, @@ -198,21 +231,21 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn) rx_sg = &rx_desc->rx_sg; rx_sg->addr = rx_desc->dma_addr; rx_sg->length = ISER_RX_PAYLOAD_SIZE; - rx_sg->lkey = isert_conn->conn_mr->lkey; + rx_sg->lkey = device->mr->lkey; } - isert_conn->conn_rx_desc_head = 0; + isert_conn->rx_desc_head = 0; return 0; dma_map_fail: - rx_desc = isert_conn->conn_rx_descs; + rx_desc = isert_conn->rx_descs; for (j = 0; j < i; j++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); } - kfree(isert_conn->conn_rx_descs); - isert_conn->conn_rx_descs = NULL; + kfree(isert_conn->rx_descs); + isert_conn->rx_descs = NULL; fail: isert_err("conn %p failed to allocate rx descriptors\n", isert_conn); @@ -222,59 +255,51 @@ fail: static void isert_free_rx_descriptors(struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->device->ib_device; struct iser_rx_desc *rx_desc; int i; - if (!isert_conn->conn_rx_descs) + if (!isert_conn->rx_descs) return; - rx_desc = isert_conn->conn_rx_descs; + rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); } - kfree(isert_conn->conn_rx_descs); - isert_conn->conn_rx_descs = NULL; + kfree(isert_conn->rx_descs); + isert_conn->rx_descs = NULL; } static void isert_cq_work(struct work_struct *); static void isert_cq_callback(struct ib_cq *, void *); -static int -isert_create_device_ib_res(struct isert_device *device) +static void +isert_free_comps(struct isert_device *device) { - struct ib_device *ib_dev = device->ib_device; - struct ib_device_attr *dev_attr; - int ret = 0, i; - int max_cqe; - - dev_attr = &device->dev_attr; - ret = isert_query_device(ib_dev, dev_attr); - if (ret) - return ret; + int i; - max_cqe = min(ISER_MAX_CQ_LEN, dev_attr->max_cqe); + for (i = 0; i < device->comps_used; i++) { + struct isert_comp *comp = &device->comps[i]; - /* asign function handlers */ - if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS && - dev_attr->device_cap_flags & IB_DEVICE_SIGNATURE_HANDOVER) { - device->use_fastreg = 1; - device->reg_rdma_mem = isert_reg_rdma; - device->unreg_rdma_mem = isert_unreg_rdma; - } else { - device->use_fastreg = 0; - device->reg_rdma_mem = isert_map_rdma; - device->unreg_rdma_mem = isert_unmap_cmd; + if (comp->cq) { + cancel_work_sync(&comp->work); + ib_destroy_cq(comp->cq); + } } + kfree(device->comps); +} - /* Check signature cap */ - device->pi_capable = dev_attr->device_cap_flags & - IB_DEVICE_SIGNATURE_HANDOVER ? true : false; +static int +isert_alloc_comps(struct isert_device *device, + struct ib_device_attr *attr) +{ + int i, max_cqe, ret = 0; device->comps_used = min(ISERT_MAX_CQ, min_t(int, num_online_cpus(), - device->ib_device->num_comp_vectors)); + device->ib_device->num_comp_vectors)); + isert_info("Using %d CQs, %s supports %d vectors support " "Fast registration %d pi_capable %d\n", device->comps_used, device->ib_device->name, @@ -288,6 +313,8 @@ isert_create_device_ib_res(struct isert_device *device) return -ENOMEM; } + max_cqe = min(ISER_MAX_CQ_LEN, attr->max_cqe); + for (i = 0; i < device->comps_used; i++) { struct isert_comp *comp = &device->comps[i]; @@ -299,6 +326,7 @@ isert_create_device_ib_res(struct isert_device *device) (void *)comp, max_cqe, i); if (IS_ERR(comp->cq)) { + isert_err("Unable to allocate cq\n"); ret = PTR_ERR(comp->cq); comp->cq = NULL; goto out_cq; @@ -310,40 +338,79 @@ isert_create_device_ib_res(struct isert_device *device) } return 0; - out_cq: - for (i = 0; i < device->comps_used; i++) { - struct isert_comp *comp = &device->comps[i]; + isert_free_comps(device); + return ret; +} - if (comp->cq) { - cancel_work_sync(&comp->work); - ib_destroy_cq(comp->cq); - } +static int +isert_create_device_ib_res(struct isert_device *device) +{ + struct ib_device_attr *dev_attr; + int ret; + + dev_attr = &device->dev_attr; + ret = isert_query_device(device->ib_device, dev_attr); + if (ret) + return ret; + + /* asign function handlers */ + if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS && + dev_attr->device_cap_flags & IB_DEVICE_SIGNATURE_HANDOVER) { + device->use_fastreg = 1; + device->reg_rdma_mem = isert_reg_rdma; + device->unreg_rdma_mem = isert_unreg_rdma; + } else { + device->use_fastreg = 0; + device->reg_rdma_mem = isert_map_rdma; + device->unreg_rdma_mem = isert_unmap_cmd; } - kfree(device->comps); + ret = isert_alloc_comps(device, dev_attr); + if (ret) + return ret; + + device->pd = ib_alloc_pd(device->ib_device); + if (IS_ERR(device->pd)) { + ret = PTR_ERR(device->pd); + isert_err("failed to allocate pd, device %p, ret=%d\n", + device, ret); + goto out_cq; + } + + device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(device->mr)) { + ret = PTR_ERR(device->mr); + isert_err("failed to create dma mr, device %p, ret=%d\n", + device, ret); + goto out_mr; + } + + /* Check signature cap */ + device->pi_capable = dev_attr->device_cap_flags & + IB_DEVICE_SIGNATURE_HANDOVER ? true : false; + + return 0; + +out_mr: + ib_dealloc_pd(device->pd); +out_cq: + isert_free_comps(device); return ret; } static void isert_free_device_ib_res(struct isert_device *device) { - int i; - isert_info("device %p\n", device); - for (i = 0; i < device->comps_used; i++) { - struct isert_comp *comp = &device->comps[i]; - - cancel_work_sync(&comp->work); - ib_destroy_cq(comp->cq); - comp->cq = NULL; - } - kfree(device->comps); + ib_dereg_mr(device->mr); + ib_dealloc_pd(device->pd); + isert_free_comps(device); } static void -isert_device_try_release(struct isert_device *device) +isert_device_put(struct isert_device *device) { mutex_lock(&device_list_mutex); device->refcount--; @@ -357,7 +424,7 @@ isert_device_try_release(struct isert_device *device) } static struct isert_device * -isert_device_find_by_ib_dev(struct rdma_cm_id *cma_id) +isert_device_get(struct rdma_cm_id *cma_id) { struct isert_device *device; int ret; @@ -404,13 +471,13 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn) struct fast_reg_descriptor *fr_desc, *tmp; int i = 0; - if (list_empty(&isert_conn->conn_fr_pool)) + if (list_empty(&isert_conn->fr_pool)) return; isert_info("Freeing conn %p fastreg pool", isert_conn); list_for_each_entry_safe(fr_desc, tmp, - &isert_conn->conn_fr_pool, list) { + &isert_conn->fr_pool, list) { list_del(&fr_desc->list); ib_free_fast_reg_page_list(fr_desc->data_frpl); ib_dereg_mr(fr_desc->data_mr); @@ -424,9 +491,9 @@ isert_conn_free_fastreg_pool(struct isert_conn *isert_conn) ++i; } - if (i < isert_conn->conn_fr_pool_size) + if (i < isert_conn->fr_pool_size) isert_warn("Pool still has %d regions registered\n", - isert_conn->conn_fr_pool_size - i); + isert_conn->fr_pool_size - i); } static int @@ -526,7 +593,7 @@ static int isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) { struct fast_reg_descriptor *fr_desc; - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; struct se_session *se_sess = isert_conn->conn->sess->se_sess; struct se_node_acl *se_nacl = se_sess->se_node_acl; int i, ret, tag_num; @@ -537,7 +604,7 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) tag_num = max_t(u32, ISCSIT_MIN_TAGS, se_nacl->queue_depth); tag_num = (tag_num * 2) + ISCSIT_EXTRA_TAGS; - isert_conn->conn_fr_pool_size = 0; + isert_conn->fr_pool_size = 0; for (i = 0; i < tag_num; i++) { fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL); if (!fr_desc) { @@ -547,7 +614,7 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) } ret = isert_create_fr_desc(device->ib_device, - isert_conn->conn_pd, fr_desc); + device->pd, fr_desc); if (ret) { isert_err("Failed to create fastreg descriptor err=%d\n", ret); @@ -555,12 +622,12 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) goto err; } - list_add_tail(&fr_desc->list, &isert_conn->conn_fr_pool); - isert_conn->conn_fr_pool_size++; + list_add_tail(&fr_desc->list, &isert_conn->fr_pool); + isert_conn->fr_pool_size++; } isert_dbg("Creating conn %p fastreg pool size=%d", - isert_conn, isert_conn->conn_fr_pool_size); + isert_conn, isert_conn->fr_pool_size); return 0; @@ -569,55 +636,50 @@ err: return ret; } -static int -isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) +static void +isert_init_conn(struct isert_conn *isert_conn) { - struct isert_np *isert_np = cma_id->context; - struct iscsi_np *np = isert_np->np; - struct isert_conn *isert_conn; - struct isert_device *device; - struct ib_device *ib_dev = cma_id->device; - int ret = 0; - - spin_lock_bh(&np->np_thread_lock); - if (!np->enabled) { - spin_unlock_bh(&np->np_thread_lock); - isert_dbg("iscsi_np is not enabled, reject connect request\n"); - return rdma_reject(cma_id, NULL, 0); - } - spin_unlock_bh(&np->np_thread_lock); - - isert_dbg("cma_id: %p, portal: %p\n", - cma_id, cma_id->context); - - isert_conn = kzalloc(sizeof(struct isert_conn), GFP_KERNEL); - if (!isert_conn) { - isert_err("Unable to allocate isert_conn\n"); - return -ENOMEM; - } isert_conn->state = ISER_CONN_INIT; - INIT_LIST_HEAD(&isert_conn->conn_accept_node); - init_completion(&isert_conn->conn_login_comp); + INIT_LIST_HEAD(&isert_conn->accept_node); + init_completion(&isert_conn->login_comp); init_completion(&isert_conn->login_req_comp); - init_completion(&isert_conn->conn_wait); - kref_init(&isert_conn->conn_kref); - mutex_init(&isert_conn->conn_mutex); - spin_lock_init(&isert_conn->conn_lock); - INIT_LIST_HEAD(&isert_conn->conn_fr_pool); + init_completion(&isert_conn->wait); + kref_init(&isert_conn->kref); + mutex_init(&isert_conn->mutex); + spin_lock_init(&isert_conn->pool_lock); + INIT_LIST_HEAD(&isert_conn->fr_pool); +} + +static void +isert_free_login_buf(struct isert_conn *isert_conn) +{ + struct ib_device *ib_dev = isert_conn->device->ib_device; - isert_conn->conn_cm_id = cma_id; + ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma, + ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE); + ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, + ISCSI_DEF_MAX_RECV_SEG_LEN, + DMA_FROM_DEVICE); + kfree(isert_conn->login_buf); +} + +static int +isert_alloc_login_buf(struct isert_conn *isert_conn, + struct ib_device *ib_dev) +{ + int ret; isert_conn->login_buf = kzalloc(ISCSI_DEF_MAX_RECV_SEG_LEN + ISER_RX_LOGIN_SIZE, GFP_KERNEL); if (!isert_conn->login_buf) { isert_err("Unable to allocate isert_conn->login_buf\n"); - ret = -ENOMEM; - goto out; + return -ENOMEM; } isert_conn->login_req_buf = isert_conn->login_buf; isert_conn->login_rsp_buf = isert_conn->login_buf + ISCSI_DEF_MAX_RECV_SEG_LEN; + isert_dbg("Set login_buf: %p login_req_buf: %p login_rsp_buf: %p\n", isert_conn->login_buf, isert_conn->login_req_buf, isert_conn->login_rsp_buf); @@ -628,8 +690,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma); if (ret) { - isert_err("ib_dma_mapping_error failed for login_req_dma: %d\n", - ret); + isert_err("login_req_dma mapping error: %d\n", ret); isert_conn->login_req_dma = 0; goto out_login_buf; } @@ -640,17 +701,58 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) ret = ib_dma_mapping_error(ib_dev, isert_conn->login_rsp_dma); if (ret) { - isert_err("ib_dma_mapping_error failed for login_rsp_dma: %d\n", - ret); + isert_err("login_rsp_dma mapping error: %d\n", ret); isert_conn->login_rsp_dma = 0; goto out_req_dma_map; } - device = isert_device_find_by_ib_dev(cma_id); + return 0; + +out_req_dma_map: + ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, + ISCSI_DEF_MAX_RECV_SEG_LEN, DMA_FROM_DEVICE); +out_login_buf: + kfree(isert_conn->login_buf); + return ret; +} + +static int +isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) +{ + struct isert_np *isert_np = cma_id->context; + struct iscsi_np *np = isert_np->np; + struct isert_conn *isert_conn; + struct isert_device *device; + int ret = 0; + + spin_lock_bh(&np->np_thread_lock); + if (!np->enabled) { + spin_unlock_bh(&np->np_thread_lock); + isert_dbg("iscsi_np is not enabled, reject connect request\n"); + return rdma_reject(cma_id, NULL, 0); + } + spin_unlock_bh(&np->np_thread_lock); + + isert_dbg("cma_id: %p, portal: %p\n", + cma_id, cma_id->context); + + isert_conn = kzalloc(sizeof(struct isert_conn), GFP_KERNEL); + if (!isert_conn) + return -ENOMEM; + + isert_init_conn(isert_conn); + isert_conn->cm_id = cma_id; + + ret = isert_alloc_login_buf(isert_conn, cma_id->device); + if (ret) + goto out; + + device = isert_device_get(cma_id); if (IS_ERR(device)) { ret = PTR_ERR(device); goto out_rsp_dma_map; } + isert_conn->device = device; /* Set max inflight RDMA READ requests */ isert_conn->initiator_depth = min_t(u8, @@ -658,24 +760,6 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) device->dev_attr.max_qp_init_rd_atom); isert_dbg("Using initiator_depth: %u\n", isert_conn->initiator_depth); - isert_conn->conn_device = device; - isert_conn->conn_pd = ib_alloc_pd(isert_conn->conn_device->ib_device); - if (IS_ERR(isert_conn->conn_pd)) { - ret = PTR_ERR(isert_conn->conn_pd); - isert_err("ib_alloc_pd failed for conn %p: ret=%d\n", - isert_conn, ret); - goto out_pd; - } - - isert_conn->conn_mr = ib_get_dma_mr(isert_conn->conn_pd, - IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(isert_conn->conn_mr)) { - ret = PTR_ERR(isert_conn->conn_mr); - isert_err("ib_get_dma_mr failed for conn %p: ret=%d\n", - isert_conn, ret); - goto out_mr; - } - ret = isert_conn_setup_qp(isert_conn, cma_id); if (ret) goto out_conn_dev; @@ -689,7 +773,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) goto out_conn_dev; mutex_lock(&isert_np->np_accept_mutex); - list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list); + list_add_tail(&isert_conn->accept_node, &isert_np->np_accept_list); mutex_unlock(&isert_np->np_accept_mutex); isert_info("np %p: Allow accept_np to continue\n", np); @@ -697,19 +781,9 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) return 0; out_conn_dev: - ib_dereg_mr(isert_conn->conn_mr); -out_mr: - ib_dealloc_pd(isert_conn->conn_pd); -out_pd: - isert_device_try_release(device); + isert_device_put(device); out_rsp_dma_map: - ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma, - ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE); -out_req_dma_map: - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISCSI_DEF_MAX_RECV_SEG_LEN, DMA_FROM_DEVICE); -out_login_buf: - kfree(isert_conn->login_buf); + isert_free_login_buf(isert_conn); out: kfree(isert_conn); rdma_reject(cma_id, NULL, 0); @@ -719,43 +793,32 @@ out: static void isert_connect_release(struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; isert_dbg("conn %p\n", isert_conn); - if (device && device->use_fastreg) + BUG_ON(!device); + + if (device->use_fastreg) isert_conn_free_fastreg_pool(isert_conn); isert_free_rx_descriptors(isert_conn); - rdma_destroy_id(isert_conn->conn_cm_id); + if (isert_conn->cm_id) + rdma_destroy_id(isert_conn->cm_id); - if (isert_conn->conn_qp) { - struct isert_comp *comp = isert_conn->conn_qp->recv_cq->cq_context; + if (isert_conn->qp) { + struct isert_comp *comp = isert_conn->qp->recv_cq->cq_context; - isert_dbg("dec completion context %p active_qps\n", comp); - mutex_lock(&device_list_mutex); - comp->active_qps--; - mutex_unlock(&device_list_mutex); - - ib_destroy_qp(isert_conn->conn_qp); + isert_comp_put(comp); + ib_destroy_qp(isert_conn->qp); } - ib_dereg_mr(isert_conn->conn_mr); - ib_dealloc_pd(isert_conn->conn_pd); + if (isert_conn->login_buf) + isert_free_login_buf(isert_conn); - if (isert_conn->login_buf) { - ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma, - ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE); - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISCSI_DEF_MAX_RECV_SEG_LEN, - DMA_FROM_DEVICE); - kfree(isert_conn->login_buf); - } - kfree(isert_conn); + isert_device_put(device); - if (device) - isert_device_try_release(device); + kfree(isert_conn); } static void @@ -765,22 +828,22 @@ isert_connected_handler(struct rdma_cm_id *cma_id) isert_info("conn %p\n", isert_conn); - if (!kref_get_unless_zero(&isert_conn->conn_kref)) { + if (!kref_get_unless_zero(&isert_conn->kref)) { isert_warn("conn %p connect_release is running\n", isert_conn); return; } - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); if (isert_conn->state != ISER_CONN_FULL_FEATURE) isert_conn->state = ISER_CONN_UP; - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); } static void -isert_release_conn_kref(struct kref *kref) +isert_release_kref(struct kref *kref) { struct isert_conn *isert_conn = container_of(kref, - struct isert_conn, conn_kref); + struct isert_conn, kref); isert_info("conn %p final kref %s/%d\n", isert_conn, current->comm, current->pid); @@ -791,7 +854,7 @@ isert_release_conn_kref(struct kref *kref) static void isert_put_conn(struct isert_conn *isert_conn) { - kref_put(&isert_conn->conn_kref, isert_release_conn_kref); + kref_put(&isert_conn->kref, isert_release_kref); } /** @@ -803,7 +866,7 @@ isert_put_conn(struct isert_conn *isert_conn) * to TEMINATING and start teardown sequence (rdma_disconnect). * In case the connection state is UP, complete flush as well. * - * This routine must be called with conn_mutex held. Thus it is + * This routine must be called with mutex held. Thus it is * safe to call multiple times. */ static void @@ -819,7 +882,7 @@ isert_conn_terminate(struct isert_conn *isert_conn) isert_info("Terminating conn %p state %d\n", isert_conn, isert_conn->state); isert_conn->state = ISER_CONN_TERMINATING; - err = rdma_disconnect(isert_conn->conn_cm_id); + err = rdma_disconnect(isert_conn->cm_id); if (err) isert_warn("Failed rdma_disconnect isert_conn %p\n", isert_conn); @@ -868,22 +931,25 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id, isert_conn = cma_id->qp->qp_context; - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); isert_conn_terminate(isert_conn); - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); - isert_info("conn %p completing conn_wait\n", isert_conn); - complete(&isert_conn->conn_wait); + isert_info("conn %p completing wait\n", isert_conn); + complete(&isert_conn->wait); return 0; } -static void +static int isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + isert_conn->cm_id = NULL; isert_put_conn(isert_conn); + + return -1; } static int @@ -912,7 +978,7 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ case RDMA_CM_EVENT_CONNECT_ERROR: - isert_connect_error(cma_id); + ret = isert_connect_error(cma_id); break; default: isert_err("Unhandled RDMA CMA event: %d\n", event->event); @@ -927,11 +993,11 @@ isert_post_recv(struct isert_conn *isert_conn, u32 count) { struct ib_recv_wr *rx_wr, *rx_wr_failed; int i, ret; - unsigned int rx_head = isert_conn->conn_rx_desc_head; + unsigned int rx_head = isert_conn->rx_desc_head; struct iser_rx_desc *rx_desc; - for (rx_wr = isert_conn->conn_rx_wr, i = 0; i < count; i++, rx_wr++) { - rx_desc = &isert_conn->conn_rx_descs[rx_head]; + for (rx_wr = isert_conn->rx_wr, i = 0; i < count; i++, rx_wr++) { + rx_desc = &isert_conn->rx_descs[rx_head]; rx_wr->wr_id = (uintptr_t)rx_desc; rx_wr->sg_list = &rx_desc->rx_sg; rx_wr->num_sge = 1; @@ -943,14 +1009,14 @@ isert_post_recv(struct isert_conn *isert_conn, u32 count) rx_wr->next = NULL; /* mark end of work requests list */ isert_conn->post_recv_buf_count += count; - ret = ib_post_recv(isert_conn->conn_qp, isert_conn->conn_rx_wr, + ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr, &rx_wr_failed); if (ret) { isert_err("ib_post_recv() failed with ret: %d\n", ret); isert_conn->post_recv_buf_count -= count; } else { isert_dbg("Posted %d RX buffers\n", count); - isert_conn->conn_rx_desc_head = rx_head; + isert_conn->rx_desc_head = rx_head; } return ret; } @@ -958,7 +1024,7 @@ isert_post_recv(struct isert_conn *isert_conn, u32 count) static int isert_post_send(struct isert_conn *isert_conn, struct iser_tx_desc *tx_desc) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; struct ib_send_wr send_wr, *send_wr_failed; int ret; @@ -972,7 +1038,7 @@ isert_post_send(struct isert_conn *isert_conn, struct iser_tx_desc *tx_desc) send_wr.opcode = IB_WR_SEND; send_wr.send_flags = IB_SEND_SIGNALED; - ret = ib_post_send(isert_conn->conn_qp, &send_wr, &send_wr_failed); + ret = ib_post_send(isert_conn->qp, &send_wr, &send_wr_failed); if (ret) isert_err("ib_post_send() failed, ret: %d\n", ret); @@ -984,7 +1050,8 @@ isert_create_send_desc(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, struct iser_tx_desc *tx_desc) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; ib_dma_sync_single_for_cpu(ib_dev, tx_desc->dma_addr, ISER_HEADERS_LEN, DMA_TO_DEVICE); @@ -995,8 +1062,8 @@ isert_create_send_desc(struct isert_conn *isert_conn, tx_desc->num_sge = 1; tx_desc->isert_cmd = isert_cmd; - if (tx_desc->tx_sg[0].lkey != isert_conn->conn_mr->lkey) { - tx_desc->tx_sg[0].lkey = isert_conn->conn_mr->lkey; + if (tx_desc->tx_sg[0].lkey != device->mr->lkey) { + tx_desc->tx_sg[0].lkey = device->mr->lkey; isert_dbg("tx_desc %p lkey mismatch, fixing\n", tx_desc); } } @@ -1005,7 +1072,8 @@ static int isert_init_tx_hdrs(struct isert_conn *isert_conn, struct iser_tx_desc *tx_desc) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; u64 dma_addr; dma_addr = ib_dma_map_single(ib_dev, (void *)tx_desc, @@ -1018,7 +1086,7 @@ isert_init_tx_hdrs(struct isert_conn *isert_conn, tx_desc->dma_addr = dma_addr; tx_desc->tx_sg[0].addr = tx_desc->dma_addr; tx_desc->tx_sg[0].length = ISER_HEADERS_LEN; - tx_desc->tx_sg[0].lkey = isert_conn->conn_mr->lkey; + tx_desc->tx_sg[0].lkey = device->mr->lkey; isert_dbg("Setup tx_sg[0].addr: 0x%llx length: %u lkey: 0x%x\n", tx_desc->tx_sg[0].addr, tx_desc->tx_sg[0].length, @@ -1051,7 +1119,7 @@ isert_rdma_post_recvl(struct isert_conn *isert_conn) memset(&sge, 0, sizeof(struct ib_sge)); sge.addr = isert_conn->login_req_dma; sge.length = ISER_RX_LOGIN_SIZE; - sge.lkey = isert_conn->conn_mr->lkey; + sge.lkey = isert_conn->device->mr->lkey; isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n", sge.addr, sge.length, sge.lkey); @@ -1062,7 +1130,7 @@ isert_rdma_post_recvl(struct isert_conn *isert_conn) rx_wr.num_sge = 1; isert_conn->post_recv_buf_count++; - ret = ib_post_recv(isert_conn->conn_qp, &rx_wr, &rx_wr_fail); + ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_fail); if (ret) { isert_err("ib_post_recv() failed: %d\n", ret); isert_conn->post_recv_buf_count--; @@ -1076,8 +1144,9 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, u32 length) { struct isert_conn *isert_conn = conn->context; - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; - struct iser_tx_desc *tx_desc = &isert_conn->conn_login_tx_desc; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; + struct iser_tx_desc *tx_desc = &isert_conn->login_tx_desc; int ret; isert_create_send_desc(isert_conn, NULL, tx_desc); @@ -1100,13 +1169,13 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, tx_dsg->addr = isert_conn->login_rsp_dma; tx_dsg->length = length; - tx_dsg->lkey = isert_conn->conn_mr->lkey; + tx_dsg->lkey = isert_conn->device->mr->lkey; tx_desc->num_sge = 2; } if (!login->login_failed) { if (login->login_complete) { if (!conn->sess->sess_ops->SessionType && - isert_conn->conn_device->use_fastreg) { + isert_conn->device->use_fastreg) { ret = isert_conn_create_fastreg_pool(isert_conn); if (ret) { isert_err("Conn: %p failed to create" @@ -1124,9 +1193,9 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, return ret; /* Now we are in FULL_FEATURE phase */ - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); isert_conn->state = ISER_CONN_FULL_FEATURE; - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); goto post_send; } @@ -1185,7 +1254,7 @@ isert_rx_login_req(struct isert_conn *isert_conn) memcpy(login->req_buf, &rx_desc->data[0], size); if (login->first_request) { - complete(&isert_conn->conn_login_comp); + complete(&isert_conn->login_comp); return; } schedule_delayed_work(&conn->login_work, 0); @@ -1194,7 +1263,7 @@ isert_rx_login_req(struct isert_conn *isert_conn) static struct iscsi_cmd *isert_allocate_cmd(struct iscsi_conn *conn) { - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct isert_cmd *isert_cmd; struct iscsi_cmd *cmd; @@ -1379,13 +1448,12 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc, { struct iscsi_hdr *hdr = &rx_desc->iscsi_header; struct iscsi_conn *conn = isert_conn->conn; - struct iscsi_session *sess = conn->sess; struct iscsi_cmd *cmd; struct isert_cmd *isert_cmd; int ret = -EINVAL; u8 opcode = (hdr->opcode & ISCSI_OPCODE_MASK); - if (sess->sess_ops->SessionType && + if (conn->sess->sess_ops->SessionType && (!(opcode & ISCSI_OP_TEXT) || !(opcode & ISCSI_OP_LOGOUT))) { isert_err("Got illegal opcode: 0x%02x in SessionType=Discovery," " ignoring\n", opcode); @@ -1497,10 +1565,11 @@ isert_rx_do_work(struct iser_rx_desc *rx_desc, struct isert_conn *isert_conn) } static void -isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, - u32 xfer_len) +isert_rcv_completion(struct iser_rx_desc *desc, + struct isert_conn *isert_conn, + u32 xfer_len) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; struct iscsi_hdr *hdr; u64 rx_dma; int rx_buflen, outstanding; @@ -1532,9 +1601,9 @@ isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, if (login && !login->first_request) isert_rx_login_req(isert_conn); } - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); complete(&isert_conn->login_req_comp); - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); } else { isert_rx_do_work(desc, isert_conn); } @@ -1566,7 +1635,7 @@ isert_map_data_buf(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, struct scatterlist *sg, u32 nents, u32 length, u32 offset, enum iser_ib_op_code op, struct isert_data_buf *data) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; data->dma_dir = op == ISER_IB_RDMA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; @@ -1597,7 +1666,7 @@ isert_map_data_buf(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, static void isert_unmap_data_buf(struct isert_conn *isert_conn, struct isert_data_buf *data) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; ib_dma_unmap_sg(ib_dev, data->sg, data->nents, data->dma_dir); memset(data, 0, sizeof(*data)); @@ -1634,7 +1703,6 @@ static void isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn) { struct isert_rdma_wr *wr = &isert_cmd->rdma_wr; - LIST_HEAD(unmap_list); isert_dbg("Cmd %p\n", isert_cmd); @@ -1644,9 +1712,9 @@ isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn) isert_unmap_data_buf(isert_conn, &wr->prot); wr->fr_desc->ind &= ~ISERT_PROTECTED; } - spin_lock_bh(&isert_conn->conn_lock); - list_add_tail(&wr->fr_desc->list, &isert_conn->conn_fr_pool); - spin_unlock_bh(&isert_conn->conn_lock); + spin_lock_bh(&isert_conn->pool_lock); + list_add_tail(&wr->fr_desc->list, &isert_conn->fr_pool); + spin_unlock_bh(&isert_conn->pool_lock); wr->fr_desc = NULL; } @@ -1665,7 +1733,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct isert_conn *isert_conn = isert_cmd->conn; struct iscsi_conn *conn = isert_conn->conn; - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; struct iscsi_text_rsp *hdr; isert_dbg("Cmd %p\n", isert_cmd); @@ -1815,7 +1883,7 @@ isert_completion_rdma_write(struct iser_tx_desc *tx_desc, struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct se_cmd *se_cmd = &cmd->se_cmd; struct isert_conn *isert_conn = isert_cmd->conn; - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; int ret = 0; if (wr->fr_desc && wr->fr_desc->ind & ISERT_PROTECTED) { @@ -1841,7 +1909,7 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc, struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct se_cmd *se_cmd = &cmd->se_cmd; struct isert_conn *isert_conn = isert_cmd->conn; - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; int ret = 0; if (wr->fr_desc && wr->fr_desc->ind & ISERT_PROTECTED) { @@ -1861,11 +1929,13 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc, cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT; spin_unlock_bh(&cmd->istate_lock); - if (ret) + if (ret) { + target_put_sess_cmd(se_cmd->se_sess, se_cmd); transport_send_check_condition_and_sense(se_cmd, se_cmd->pi_err, 0); - else + } else { target_execute_cmd(se_cmd); + } } static void @@ -1874,7 +1944,7 @@ isert_do_control_comp(struct work_struct *work) struct isert_cmd *isert_cmd = container_of(work, struct isert_cmd, comp_work); struct isert_conn *isert_conn = isert_cmd->conn; - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; isert_dbg("Cmd %p i_state %d\n", isert_cmd, cmd->i_state); @@ -1922,10 +1992,10 @@ isert_response_completion(struct iser_tx_desc *tx_desc, } static void -isert_send_completion(struct iser_tx_desc *tx_desc, +isert_snd_completion(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; struct isert_cmd *isert_cmd = tx_desc->isert_cmd; struct isert_rdma_wr *wr; @@ -1938,10 +2008,6 @@ isert_send_completion(struct iser_tx_desc *tx_desc, isert_dbg("Cmd %p iser_ib_op %d\n", isert_cmd, wr->iser_ib_op); switch (wr->iser_ib_op) { - case ISER_IB_RECV: - isert_err("Got ISER_IB_RECV\n"); - dump_stack(); - break; case ISER_IB_SEND: isert_response_completion(tx_desc, isert_cmd, isert_conn, ib_dev); @@ -1973,8 +2039,8 @@ isert_send_completion(struct iser_tx_desc *tx_desc, static inline bool is_isert_tx_desc(struct isert_conn *isert_conn, void *wr_id) { - void *start = isert_conn->conn_rx_descs; - int len = ISERT_QP_MAX_RECV_DTOS * sizeof(*isert_conn->conn_rx_descs); + void *start = isert_conn->rx_descs; + int len = ISERT_QP_MAX_RECV_DTOS * sizeof(*isert_conn->rx_descs); if (wr_id >= start && wr_id < start + len) return false; @@ -1986,11 +2052,11 @@ static void isert_cq_comp_err(struct isert_conn *isert_conn, struct ib_wc *wc) { if (wc->wr_id == ISER_BEACON_WRID) { - isert_info("conn %p completing conn_wait_comp_err\n", + isert_info("conn %p completing wait_comp_err\n", isert_conn); - complete(&isert_conn->conn_wait_comp_err); + complete(&isert_conn->wait_comp_err); } else if (is_isert_tx_desc(isert_conn, (void *)(uintptr_t)wc->wr_id)) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct ib_device *ib_dev = isert_conn->cm_id->device; struct isert_cmd *isert_cmd; struct iser_tx_desc *desc; @@ -2018,10 +2084,10 @@ isert_handle_wc(struct ib_wc *wc) if (likely(wc->status == IB_WC_SUCCESS)) { if (wc->opcode == IB_WC_RECV) { rx_desc = (struct iser_rx_desc *)(uintptr_t)wc->wr_id; - isert_rx_completion(rx_desc, isert_conn, wc->byte_len); + isert_rcv_completion(rx_desc, isert_conn, wc->byte_len); } else { tx_desc = (struct iser_tx_desc *)(uintptr_t)wc->wr_id; - isert_send_completion(tx_desc, isert_conn); + isert_snd_completion(tx_desc, isert_conn); } } else { if (wc->status != IB_WC_WR_FLUSH_ERR) @@ -2070,7 +2136,7 @@ isert_post_response(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd) struct ib_send_wr *wr_failed; int ret; - ret = ib_post_send(isert_conn->conn_qp, &isert_cmd->tx_desc.send_wr, + ret = ib_post_send(isert_conn->qp, &isert_cmd->tx_desc.send_wr, &wr_failed); if (ret) { isert_err("ib_post_send failed with %d\n", ret); @@ -2083,7 +2149,7 @@ static int isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; struct iscsi_scsi_rsp *hdr = (struct iscsi_scsi_rsp *) &isert_cmd->tx_desc.iscsi_header; @@ -2097,7 +2163,8 @@ isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd) if (cmd->se_cmd.sense_buffer && ((cmd->se_cmd.se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) || (cmd->se_cmd.se_cmd_flags & SCF_EMULATED_TASK_SENSE))) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct ib_sge *tx_dsg = &isert_cmd->tx_desc.tx_sg[1]; u32 padding, pdu_len; @@ -2116,7 +2183,7 @@ isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd) isert_cmd->pdu_buf_len = pdu_len; tx_dsg->addr = isert_cmd->pdu_buf_dma; tx_dsg->length = pdu_len; - tx_dsg->lkey = isert_conn->conn_mr->lkey; + tx_dsg->lkey = device->mr->lkey; isert_cmd->tx_desc.num_sge = 2; } @@ -2131,8 +2198,8 @@ static void isert_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; - struct isert_device *device = isert_conn->conn_device; + struct isert_conn *isert_conn = conn->context; + struct isert_device *device = isert_conn->device; spin_lock_bh(&conn->cmd_lock); if (!list_empty(&cmd->i_conn_node)) @@ -2148,8 +2215,8 @@ isert_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) static enum target_prot_op isert_get_sup_prot_ops(struct iscsi_conn *conn) { - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; - struct isert_device *device = isert_conn->conn_device; + struct isert_conn *isert_conn = conn->context; + struct isert_device *device = isert_conn->device; if (conn->tpg->tpg_attrib.t10_pi) { if (device->pi_capable) { @@ -2170,7 +2237,7 @@ isert_put_nopin(struct iscsi_cmd *cmd, struct iscsi_conn *conn, bool nopout_response) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); @@ -2189,7 +2256,7 @@ static int isert_put_logout_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); @@ -2207,7 +2274,7 @@ static int isert_put_tm_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); @@ -2225,9 +2292,10 @@ static int isert_put_reject(struct iscsi_cmd *cmd, struct iscsi_conn *conn) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct ib_sge *tx_dsg = &isert_cmd->tx_desc.tx_sg[1]; struct iscsi_reject *hdr = (struct iscsi_reject *)&isert_cmd->tx_desc.iscsi_header; @@ -2243,7 +2311,7 @@ isert_put_reject(struct iscsi_cmd *cmd, struct iscsi_conn *conn) isert_cmd->pdu_buf_len = ISCSI_HDR_LEN; tx_dsg->addr = isert_cmd->pdu_buf_dma; tx_dsg->length = ISCSI_HDR_LEN; - tx_dsg->lkey = isert_conn->conn_mr->lkey; + tx_dsg->lkey = device->mr->lkey; isert_cmd->tx_desc.num_sge = 2; isert_init_send_wr(isert_conn, isert_cmd, send_wr); @@ -2257,7 +2325,7 @@ static int isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) { struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr; struct iscsi_text_rsp *hdr = (struct iscsi_text_rsp *)&isert_cmd->tx_desc.iscsi_header; @@ -2273,7 +2341,8 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc); if (txt_rsp_len) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct ib_sge *tx_dsg = &isert_cmd->tx_desc.tx_sg[1]; void *txt_rsp_buf = cmd->buf_ptr; @@ -2283,7 +2352,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) isert_cmd->pdu_buf_len = txt_rsp_len; tx_dsg->addr = isert_cmd->pdu_buf_dma; tx_dsg->length = txt_rsp_len; - tx_dsg->lkey = isert_conn->conn_mr->lkey; + tx_dsg->lkey = device->mr->lkey; isert_cmd->tx_desc.num_sge = 2; } isert_init_send_wr(isert_conn, isert_cmd, send_wr); @@ -2300,7 +2369,8 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, { struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct scatterlist *sg_start, *tmp_sg; - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; u32 sg_off, page_off; int i = 0, sg_nents; @@ -2324,7 +2394,7 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, ib_sge->addr = ib_sg_dma_address(ib_dev, tmp_sg) + page_off; ib_sge->length = min_t(u32, data_left, ib_sg_dma_len(ib_dev, tmp_sg) - page_off); - ib_sge->lkey = isert_conn->conn_mr->lkey; + ib_sge->lkey = device->mr->lkey; isert_dbg("RDMA ib_sge: addr: 0x%llx length: %u lkey: %x\n", ib_sge->addr, ib_sge->length, ib_sge->lkey); @@ -2346,7 +2416,7 @@ isert_map_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd, { struct se_cmd *se_cmd = &cmd->se_cmd; struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; struct isert_data_buf *data = &wr->data; struct ib_send_wr *send_wr; struct ib_sge *ib_sge; @@ -2485,7 +2555,8 @@ isert_fast_reg_mr(struct isert_conn *isert_conn, enum isert_indicator ind, struct ib_sge *sge) { - struct ib_device *ib_dev = isert_conn->conn_cm_id->device; + struct isert_device *device = isert_conn->device; + struct ib_device *ib_dev = device->ib_device; struct ib_mr *mr; struct ib_fast_reg_page_list *frpl; struct ib_send_wr fr_wr, inv_wr; @@ -2494,7 +2565,7 @@ isert_fast_reg_mr(struct isert_conn *isert_conn, u32 page_off; if (mem->dma_nents == 1) { - sge->lkey = isert_conn->conn_mr->lkey; + sge->lkey = device->mr->lkey; sge->addr = ib_sg_dma_address(ib_dev, &mem->sg[0]); sge->length = ib_sg_dma_len(ib_dev, &mem->sg[0]); isert_dbg("sge: addr: 0x%llx length: %u lkey: %x\n", @@ -2542,7 +2613,7 @@ isert_fast_reg_mr(struct isert_conn *isert_conn, else wr->next = &fr_wr; - ret = ib_post_send(isert_conn->conn_qp, wr, &bad_wr); + ret = ib_post_send(isert_conn->qp, wr, &bad_wr); if (ret) { isert_err("fast registration failed, ret:%d\n", ret); return ret; @@ -2655,7 +2726,7 @@ isert_reg_sig_mr(struct isert_conn *isert_conn, else wr->next = &sig_wr; - ret = ib_post_send(isert_conn->conn_qp, wr, &bad_wr); + ret = ib_post_send(isert_conn->qp, wr, &bad_wr); if (ret) { isert_err("fast registration failed, ret:%d\n", ret); goto err; @@ -2685,14 +2756,14 @@ isert_handle_prot_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd, struct isert_rdma_wr *wr) { - struct isert_device *device = isert_conn->conn_device; + struct isert_device *device = isert_conn->device; struct se_cmd *se_cmd = &isert_cmd->iscsi_cmd->se_cmd; int ret; if (!wr->fr_desc->pi_ctx) { ret = isert_create_pi_ctx(wr->fr_desc, device->ib_device, - isert_conn->conn_pd); + device->pd); if (ret) { isert_err("conn %p failed to allocate pi_ctx\n", isert_conn); @@ -2763,11 +2834,11 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd, return ret; if (wr->data.dma_nents != 1 || isert_prot_cmd(isert_conn, se_cmd)) { - spin_lock_irqsave(&isert_conn->conn_lock, flags); - fr_desc = list_first_entry(&isert_conn->conn_fr_pool, + spin_lock_irqsave(&isert_conn->pool_lock, flags); + fr_desc = list_first_entry(&isert_conn->fr_pool, struct fast_reg_descriptor, list); list_del(&fr_desc->list); - spin_unlock_irqrestore(&isert_conn->conn_lock, flags); + spin_unlock_irqrestore(&isert_conn->pool_lock, flags); wr->fr_desc = fr_desc; } @@ -2814,9 +2885,9 @@ isert_reg_rdma(struct iscsi_conn *conn, struct iscsi_cmd *cmd, unmap_cmd: if (fr_desc) { - spin_lock_irqsave(&isert_conn->conn_lock, flags); - list_add_tail(&fr_desc->list, &isert_conn->conn_fr_pool); - spin_unlock_irqrestore(&isert_conn->conn_lock, flags); + spin_lock_irqsave(&isert_conn->pool_lock, flags); + list_add_tail(&fr_desc->list, &isert_conn->fr_pool); + spin_unlock_irqrestore(&isert_conn->pool_lock, flags); } isert_unmap_data_buf(isert_conn, &wr->data); @@ -2829,8 +2900,8 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) struct se_cmd *se_cmd = &cmd->se_cmd; struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); struct isert_rdma_wr *wr = &isert_cmd->rdma_wr; - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; - struct isert_device *device = isert_conn->conn_device; + struct isert_conn *isert_conn = conn->context; + struct isert_device *device = isert_conn->device; struct ib_send_wr *wr_failed; int rc; @@ -2859,7 +2930,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd) wr->send_wr_num += 1; } - rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed); + rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed); if (rc) isert_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n"); @@ -2879,8 +2950,8 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery) struct se_cmd *se_cmd = &cmd->se_cmd; struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd); struct isert_rdma_wr *wr = &isert_cmd->rdma_wr; - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; - struct isert_device *device = isert_conn->conn_device; + struct isert_conn *isert_conn = conn->context; + struct isert_device *device = isert_conn->device; struct ib_send_wr *wr_failed; int rc; @@ -2893,7 +2964,7 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery) return rc; } - rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed); + rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed); if (rc) isert_warn("ib_post_send() failed for IB_WR_RDMA_READ\n"); @@ -2987,7 +3058,7 @@ isert_setup_id(struct isert_np *isert_np) goto out_id; } - ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG); + ret = rdma_listen(id, 0); if (ret) { isert_err("rdma_listen() failed: %d\n", ret); goto out_id; @@ -3046,7 +3117,7 @@ out: static int isert_rdma_accept(struct isert_conn *isert_conn) { - struct rdma_cm_id *cm_id = isert_conn->conn_cm_id; + struct rdma_cm_id *cm_id = isert_conn->cm_id; struct rdma_conn_param cp; int ret; @@ -3067,7 +3138,7 @@ isert_rdma_accept(struct isert_conn *isert_conn) static int isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) { - struct isert_conn *isert_conn = (struct isert_conn *)conn->context; + struct isert_conn *isert_conn = conn->context; int ret; isert_info("before login_req comp conn: %p\n", isert_conn); @@ -3090,8 +3161,8 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) isert_rx_login_req(isert_conn); - isert_info("before conn_login_comp conn: %p\n", conn); - ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp); + isert_info("before login_comp conn: %p\n", conn); + ret = wait_for_completion_interruptible(&isert_conn->login_comp); if (ret) return ret; @@ -3104,7 +3175,7 @@ static void isert_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, struct isert_conn *isert_conn) { - struct rdma_cm_id *cm_id = isert_conn->conn_cm_id; + struct rdma_cm_id *cm_id = isert_conn->cm_id; struct rdma_route *cm_route = &cm_id->route; struct sockaddr_in *sock_in; struct sockaddr_in6 *sock_in6; @@ -3137,13 +3208,13 @@ isert_set_conn_info(struct iscsi_np *np, struct iscsi_conn *conn, static int isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) { - struct isert_np *isert_np = (struct isert_np *)np->np_context; + struct isert_np *isert_np = np->np_context; struct isert_conn *isert_conn; - int max_accept = 0, ret; + int ret; accept_wait: ret = down_interruptible(&isert_np->np_sem); - if (ret || max_accept > 5) + if (ret) return -ENODEV; spin_lock_bh(&np->np_thread_lock); @@ -3162,17 +3233,15 @@ accept_wait: mutex_lock(&isert_np->np_accept_mutex); if (list_empty(&isert_np->np_accept_list)) { mutex_unlock(&isert_np->np_accept_mutex); - max_accept++; goto accept_wait; } isert_conn = list_first_entry(&isert_np->np_accept_list, - struct isert_conn, conn_accept_node); - list_del_init(&isert_conn->conn_accept_node); + struct isert_conn, accept_node); + list_del_init(&isert_conn->accept_node); mutex_unlock(&isert_np->np_accept_mutex); conn->context = isert_conn; isert_conn->conn = conn; - max_accept = 0; isert_set_conn_info(np, conn, isert_conn); @@ -3184,7 +3253,7 @@ accept_wait: static void isert_free_np(struct iscsi_np *np) { - struct isert_np *isert_np = (struct isert_np *)np->np_context; + struct isert_np *isert_np = np->np_context; struct isert_conn *isert_conn, *n; if (isert_np->np_cm_id) @@ -3202,7 +3271,7 @@ isert_free_np(struct iscsi_np *np) isert_info("Still have isert connections, cleaning up...\n"); list_for_each_entry_safe(isert_conn, n, &isert_np->np_accept_list, - conn_accept_node) { + accept_node) { isert_info("cleaning isert_conn %p state (%d)\n", isert_conn, isert_conn->state); isert_connect_release(isert_conn); @@ -3222,11 +3291,11 @@ static void isert_release_work(struct work_struct *work) isert_info("Starting release conn %p\n", isert_conn); - wait_for_completion(&isert_conn->conn_wait); + wait_for_completion(&isert_conn->wait); - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); isert_conn->state = ISER_CONN_DOWN; - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); isert_info("Destroying conn %p\n", isert_conn); isert_put_conn(isert_conn); @@ -3264,15 +3333,15 @@ isert_wait4flush(struct isert_conn *isert_conn) isert_info("conn %p\n", isert_conn); - init_completion(&isert_conn->conn_wait_comp_err); + init_completion(&isert_conn->wait_comp_err); isert_conn->beacon.wr_id = ISER_BEACON_WRID; /* post an indication that all flush errors were consumed */ - if (ib_post_recv(isert_conn->conn_qp, &isert_conn->beacon, &bad_wr)) { + if (ib_post_recv(isert_conn->qp, &isert_conn->beacon, &bad_wr)) { isert_err("conn %p failed to post beacon", isert_conn); return; } - wait_for_completion(&isert_conn->conn_wait_comp_err); + wait_for_completion(&isert_conn->wait_comp_err); } static void isert_wait_conn(struct iscsi_conn *conn) @@ -3281,17 +3350,17 @@ static void isert_wait_conn(struct iscsi_conn *conn) isert_info("Starting conn %p\n", isert_conn); - mutex_lock(&isert_conn->conn_mutex); + mutex_lock(&isert_conn->mutex); /* - * Only wait for conn_wait_comp_err if the isert_conn made it + * Only wait for wait_comp_err if the isert_conn made it * into full feature phase.. */ if (isert_conn->state == ISER_CONN_INIT) { - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); return; } isert_conn_terminate(isert_conn); - mutex_unlock(&isert_conn->conn_mutex); + mutex_unlock(&isert_conn->mutex); isert_wait4cmds(conn); isert_wait4flush(isert_conn); @@ -3370,7 +3439,7 @@ static void __exit isert_exit(void) } MODULE_DESCRIPTION("iSER-Target for mainline target infrastructure"); -MODULE_VERSION("0.1"); +MODULE_VERSION("1.0"); MODULE_AUTHOR("nab@Linux-iSCSI.org"); MODULE_LICENSE("GPL"); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 8dc8415d152d..9ec23a786c02 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -31,7 +31,6 @@ #define isert_err(fmt, arg...) \ pr_err(PFX "%s: " fmt, __func__ , ## arg) -#define ISERT_RDMA_LISTEN_BACKLOG 10 #define ISCSI_ISER_SG_TABLESIZE 256 #define ISER_FASTREG_LI_WRID 0xffffffffffffffffULL #define ISER_BEACON_WRID 0xfffffffffffffffeULL @@ -160,27 +159,25 @@ struct isert_conn { u64 login_req_dma; int login_req_len; u64 login_rsp_dma; - unsigned int conn_rx_desc_head; - struct iser_rx_desc *conn_rx_descs; - struct ib_recv_wr conn_rx_wr[ISERT_MIN_POSTED_RX]; + unsigned int rx_desc_head; + struct iser_rx_desc *rx_descs; + struct ib_recv_wr rx_wr[ISERT_MIN_POSTED_RX]; struct iscsi_conn *conn; - struct list_head conn_accept_node; - struct completion conn_login_comp; + struct list_head accept_node; + struct completion login_comp; struct completion login_req_comp; - struct iser_tx_desc conn_login_tx_desc; - struct rdma_cm_id *conn_cm_id; - struct ib_pd *conn_pd; - struct ib_mr *conn_mr; - struct ib_qp *conn_qp; - struct isert_device *conn_device; - struct mutex conn_mutex; - struct completion conn_wait; - struct completion conn_wait_comp_err; - struct kref conn_kref; - struct list_head conn_fr_pool; - int conn_fr_pool_size; + struct iser_tx_desc login_tx_desc; + struct rdma_cm_id *cm_id; + struct ib_qp *qp; + struct isert_device *device; + struct mutex mutex; + struct completion wait; + struct completion wait_comp_err; + struct kref kref; + struct list_head fr_pool; + int fr_pool_size; /* lock to protect fastreg pool */ - spinlock_t conn_lock; + spinlock_t pool_lock; struct work_struct release_work; struct ib_recv_wr beacon; bool logout_posted; @@ -211,6 +208,8 @@ struct isert_device { bool pi_capable; int refcount; struct ib_device *ib_device; + struct ib_pd *pd; + struct ib_mr *mr; struct isert_comp *comps; int comps_used; struct list_head dev_node; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 0747c0595a9d..918814cd0f80 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -40,6 +40,7 @@ #include <linux/parser.h> #include <linux/random.h> #include <linux/jiffies.h> +#include <rdma/ib_cache.h> #include <linux/atomic.h> @@ -265,10 +266,10 @@ static int srp_init_qp(struct srp_target_port *target, if (!attr) return -ENOMEM; - ret = ib_find_pkey(target->srp_host->srp_dev->dev, - target->srp_host->port, - be16_to_cpu(target->pkey), - &attr->pkey_index); + ret = ib_find_cached_pkey(target->srp_host->srp_dev->dev, + target->srp_host->port, + be16_to_cpu(target->pkey), + &attr->pkey_index); if (ret) goto out; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 6e0a477681e9..9b84b4c0a000 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -93,7 +93,7 @@ MODULE_PARM_DESC(srpt_service_guid, " instead of using the node_guid of the first HCA."); static struct ib_client srpt_client; -static struct target_fabric_configfs *srpt_target; +static const struct target_core_fabric_ops srpt_template; static void srpt_release_channel(struct srpt_rdma_ch *ch); static int srpt_queue_status(struct se_cmd *cmd); @@ -207,7 +207,7 @@ static void srpt_event_handler(struct ib_event_handler *handler, } break; default: - printk(KERN_ERR "received unrecognized IB event %d\n", + pr_err("received unrecognized IB event %d\n", event->event); break; } @@ -218,7 +218,7 @@ static void srpt_event_handler(struct ib_event_handler *handler, */ static void srpt_srq_event(struct ib_event *event, void *ctx) { - printk(KERN_INFO "SRQ event %d\n", event->event); + pr_info("SRQ event %d\n", event->event); } /** @@ -242,8 +242,7 @@ static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) ch->sess_name, srpt_get_ch_state(ch)); break; default: - printk(KERN_ERR "received unrecognized IB QP event %d\n", - event->event); + pr_err("received unrecognized IB QP event %d\n", event->event); break; } } @@ -602,7 +601,7 @@ static void srpt_unregister_mad_agent(struct srpt_device *sdev) sport = &sdev->port[i - 1]; WARN_ON(sport->port != i); if (ib_modify_port(sdev->device, i, 0, &port_modify) < 0) - printk(KERN_ERR "disabling MAD processing failed.\n"); + pr_err("disabling MAD processing failed.\n"); if (sport->mad_agent) { ib_unregister_mad_agent(sport->mad_agent); sport->mad_agent = NULL; @@ -810,7 +809,7 @@ static int srpt_post_send(struct srpt_rdma_ch *ch, ret = -ENOMEM; if (unlikely(atomic_dec_return(&ch->sq_wr_avail) < 0)) { - printk(KERN_WARNING "IB send queue full (needed 1)\n"); + pr_warn("IB send queue full (needed 1)\n"); goto out; } @@ -912,7 +911,7 @@ static int srpt_get_desc_tbl(struct srpt_send_ioctx *ioctx, if (ioctx->n_rbuf > (srp_cmd->data_out_desc_cnt + srp_cmd->data_in_desc_cnt)) { - printk(KERN_ERR "received unsupported SRP_CMD request" + pr_err("received unsupported SRP_CMD request" " type (%u out + %u in != %u / %zu)\n", srp_cmd->data_out_desc_cnt, srp_cmd->data_in_desc_cnt, @@ -1432,7 +1431,7 @@ static void srpt_handle_send_comp(struct srpt_rdma_ch *ch, srpt_unmap_sg_to_ib_sge(ch, ioctx); transport_generic_free_cmd(&ioctx->cmd, 0); } else { - printk(KERN_ERR "IB completion has been received too late for" + pr_err("IB completion has been received too late for" " wr_id = %u.\n", ioctx->ioctx.index); } } @@ -1457,7 +1456,7 @@ static void srpt_handle_rdma_comp(struct srpt_rdma_ch *ch, SRPT_STATE_DATA_IN)) target_execute_cmd(&ioctx->cmd); else - printk(KERN_ERR "%s[%d]: wrong state = %d\n", __func__, + pr_err("%s[%d]: wrong state = %d\n", __func__, __LINE__, srpt_get_cmd_state(ioctx)); } else if (opcode == SRPT_RDMA_ABORT) { ioctx->rdma_aborted = true; @@ -1481,7 +1480,7 @@ static void srpt_handle_rdma_err_comp(struct srpt_rdma_ch *ch, switch (opcode) { case SRPT_RDMA_READ_LAST: if (ioctx->n_rdma <= 0) { - printk(KERN_ERR "Received invalid RDMA read" + pr_err("Received invalid RDMA read" " error completion with idx %d\n", ioctx->ioctx.index); break; @@ -1490,14 +1489,13 @@ static void srpt_handle_rdma_err_comp(struct srpt_rdma_ch *ch, if (state == SRPT_STATE_NEED_DATA) srpt_abort_cmd(ioctx); else - printk(KERN_ERR "%s[%d]: wrong state = %d\n", + pr_err("%s[%d]: wrong state = %d\n", __func__, __LINE__, state); break; case SRPT_RDMA_WRITE_LAST: break; default: - printk(KERN_ERR "%s[%d]: opcode = %u\n", __func__, - __LINE__, opcode); + pr_err("%s[%d]: opcode = %u\n", __func__, __LINE__, opcode); break; } } @@ -1549,8 +1547,8 @@ static int srpt_build_cmd_rsp(struct srpt_rdma_ch *ch, BUILD_BUG_ON(MIN_MAX_RSP_SIZE <= sizeof(*srp_rsp)); max_sense_len = ch->max_ti_iu_len - sizeof(*srp_rsp); if (sense_data_len > max_sense_len) { - printk(KERN_WARNING "truncated sense data from %d to %d" - " bytes\n", sense_data_len, max_sense_len); + pr_warn("truncated sense data from %d to %d" + " bytes\n", sense_data_len, max_sense_len); sense_data_len = max_sense_len; } @@ -1628,8 +1626,8 @@ static uint64_t srpt_unpack_lun(const uint8_t *lun, int len) int addressing_method; if (unlikely(len < 2)) { - printk(KERN_ERR "Illegal LUN length %d, expected 2 bytes or " - "more", len); + pr_err("Illegal LUN length %d, expected 2 bytes or more\n", + len); goto out; } @@ -1663,7 +1661,7 @@ static uint64_t srpt_unpack_lun(const uint8_t *lun, int len) case SCSI_LUN_ADDR_METHOD_EXTENDED_LUN: default: - printk(KERN_ERR "Unimplemented LUN addressing method %u", + pr_err("Unimplemented LUN addressing method %u\n", addressing_method); break; } @@ -1672,8 +1670,7 @@ out: return res; out_err: - printk(KERN_ERR "Support for multi-level LUNs has not yet been" - " implemented"); + pr_err("Support for multi-level LUNs has not yet been implemented\n"); goto out; } @@ -1723,7 +1720,7 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch, } if (srpt_get_desc_tbl(send_ioctx, srp_cmd, &dir, &data_len)) { - printk(KERN_ERR "0x%llx: parsing SRP descriptor table failed.\n", + pr_err("0x%llx: parsing SRP descriptor table failed.\n", srp_cmd->tag); ret = TCM_INVALID_CDB_FIELD; goto send_sense; @@ -1912,7 +1909,7 @@ static void srpt_handle_new_iu(struct srpt_rdma_ch *ch, srpt_handle_tsk_mgmt(ch, recv_ioctx, send_ioctx); break; case SRP_I_LOGOUT: - printk(KERN_ERR "Not yet implemented: SRP_I_LOGOUT\n"); + pr_err("Not yet implemented: SRP_I_LOGOUT\n"); break; case SRP_CRED_RSP: pr_debug("received SRP_CRED_RSP\n"); @@ -1921,10 +1918,10 @@ static void srpt_handle_new_iu(struct srpt_rdma_ch *ch, pr_debug("received SRP_AER_RSP\n"); break; case SRP_RSP: - printk(KERN_ERR "Received SRP_RSP\n"); + pr_err("Received SRP_RSP\n"); break; default: - printk(KERN_ERR "received IU with unknown opcode 0x%x\n", + pr_err("received IU with unknown opcode 0x%x\n", srp_cmd->opcode); break; } @@ -1948,12 +1945,12 @@ static void srpt_process_rcv_completion(struct ib_cq *cq, req_lim = atomic_dec_return(&ch->req_lim); if (unlikely(req_lim < 0)) - printk(KERN_ERR "req_lim = %d < 0\n", req_lim); + pr_err("req_lim = %d < 0\n", req_lim); ioctx = sdev->ioctx_ring[index]; srpt_handle_new_iu(ch, ioctx, NULL); } else { - printk(KERN_INFO "receiving failed for idx %u with status %d\n", - index, wc->status); + pr_info("receiving failed for idx %u with status %d\n", + index, wc->status); } } @@ -1993,12 +1990,12 @@ static void srpt_process_send_completion(struct ib_cq *cq, } } else { if (opcode == SRPT_SEND) { - printk(KERN_INFO "sending response for idx %u failed" - " with status %d\n", index, wc->status); + pr_info("sending response for idx %u failed" + " with status %d\n", index, wc->status); srpt_handle_send_err_comp(ch, wc->wr_id); } else if (opcode != SRPT_RDMA_MID) { - printk(KERN_INFO "RDMA t %d for idx %u failed with" - " status %d", opcode, index, wc->status); + pr_info("RDMA t %d for idx %u failed with" + " status %d\n", opcode, index, wc->status); srpt_handle_rdma_err_comp(ch, send_ioctx, opcode); } } @@ -2062,15 +2059,15 @@ static int srpt_compl_thread(void *arg) ch = arg; BUG_ON(!ch); - printk(KERN_INFO "Session %s: kernel thread %s (PID %d) started\n", - ch->sess_name, ch->thread->comm, current->pid); + pr_info("Session %s: kernel thread %s (PID %d) started\n", + ch->sess_name, ch->thread->comm, current->pid); while (!kthread_should_stop()) { wait_event_interruptible(ch->wait_queue, (srpt_process_completion(ch->cq, ch), kthread_should_stop())); } - printk(KERN_INFO "Session %s: kernel thread %s (PID %d) stopped\n", - ch->sess_name, ch->thread->comm, current->pid); + pr_info("Session %s: kernel thread %s (PID %d) stopped\n", + ch->sess_name, ch->thread->comm, current->pid); return 0; } @@ -2097,7 +2094,7 @@ retry: ch->rq_size + srp_sq_size, 0); if (IS_ERR(ch->cq)) { ret = PTR_ERR(ch->cq); - printk(KERN_ERR "failed to create CQ cqe= %d ret= %d\n", + pr_err("failed to create CQ cqe= %d ret= %d\n", ch->rq_size + srp_sq_size, ret); goto out; } @@ -2123,7 +2120,7 @@ retry: goto retry; } } - printk(KERN_ERR "failed to create_qp ret= %d\n", ret); + pr_err("failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } @@ -2143,7 +2140,7 @@ retry: ch->thread = kthread_run(srpt_compl_thread, ch, "ib_srpt_compl"); if (IS_ERR(ch->thread)) { - printk(KERN_ERR "failed to create kernel thread %ld\n", + pr_err("failed to create kernel thread %ld\n", PTR_ERR(ch->thread)); ch->thread = NULL; goto err_destroy_qp; @@ -2204,7 +2201,7 @@ static void __srpt_close_ch(struct srpt_rdma_ch *ch) /* fall through */ case CH_LIVE: if (ib_send_cm_dreq(ch->cm_id, NULL, 0) < 0) - printk(KERN_ERR "sending CM DREQ failed.\n"); + pr_err("sending CM DREQ failed.\n"); break; case CH_DISCONNECTING: break; @@ -2291,7 +2288,7 @@ static void srpt_drain_channel(struct ib_cm_id *cm_id) ret = srpt_ch_qp_err(ch); if (ret < 0) - printk(KERN_ERR "Setting queue pair in error state" + pr_err("Setting queue pair in error state" " failed: %d\n", ret); } } @@ -2435,17 +2432,17 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, it_iu_len = be32_to_cpu(req->req_it_iu_len); - printk(KERN_INFO "Received SRP_LOGIN_REQ with i_port_id 0x%llx:0x%llx," - " t_port_id 0x%llx:0x%llx and it_iu_len %d on port %d" - " (guid=0x%llx:0x%llx)\n", - be64_to_cpu(*(__be64 *)&req->initiator_port_id[0]), - be64_to_cpu(*(__be64 *)&req->initiator_port_id[8]), - be64_to_cpu(*(__be64 *)&req->target_port_id[0]), - be64_to_cpu(*(__be64 *)&req->target_port_id[8]), - it_iu_len, - param->port, - be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[0]), - be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[8])); + pr_info("Received SRP_LOGIN_REQ with i_port_id 0x%llx:0x%llx," + " t_port_id 0x%llx:0x%llx and it_iu_len %d on port %d" + " (guid=0x%llx:0x%llx)\n", + be64_to_cpu(*(__be64 *)&req->initiator_port_id[0]), + be64_to_cpu(*(__be64 *)&req->initiator_port_id[8]), + be64_to_cpu(*(__be64 *)&req->target_port_id[0]), + be64_to_cpu(*(__be64 *)&req->target_port_id[8]), + it_iu_len, + param->port, + be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[0]), + be64_to_cpu(*(__be64 *)&sdev->port[param->port - 1].gid.raw[8])); rsp = kzalloc(sizeof *rsp, GFP_KERNEL); rej = kzalloc(sizeof *rej, GFP_KERNEL); @@ -2460,7 +2457,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE); ret = -EINVAL; - printk(KERN_ERR "rejected SRP_LOGIN_REQ because its" + pr_err("rejected SRP_LOGIN_REQ because its" " length (%d bytes) is out of range (%d .. %d)\n", it_iu_len, 64, srp_max_req_size); goto reject; @@ -2470,7 +2467,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); ret = -EINVAL; - printk(KERN_ERR "rejected SRP_LOGIN_REQ because the target port" + pr_err("rejected SRP_LOGIN_REQ because the target port" " has not yet been enabled\n"); goto reject; } @@ -2516,7 +2513,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL); ret = -ENOMEM; - printk(KERN_ERR "rejected SRP_LOGIN_REQ because it" + pr_err("rejected SRP_LOGIN_REQ because it" " has an invalid target port identifier.\n"); goto reject; } @@ -2525,7 +2522,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, if (!ch) { rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - printk(KERN_ERR "rejected SRP_LOGIN_REQ because no memory.\n"); + pr_err("rejected SRP_LOGIN_REQ because no memory.\n"); ret = -ENOMEM; goto reject; } @@ -2562,7 +2559,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, if (ret) { rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - printk(KERN_ERR "rejected SRP_LOGIN_REQ because creating" + pr_err("rejected SRP_LOGIN_REQ because creating" " a new RDMA channel failed.\n"); goto free_ring; } @@ -2571,7 +2568,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, if (ret) { rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES); - printk(KERN_ERR "rejected SRP_LOGIN_REQ because enabling" + pr_err("rejected SRP_LOGIN_REQ because enabling" " RTR failed (error code = %d)\n", ret); goto destroy_ib; } @@ -2586,8 +2583,8 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, nacl = srpt_lookup_acl(sport, ch->i_port_id); if (!nacl) { - printk(KERN_INFO "Rejected login because no ACL has been" - " configured yet for initiator %s.\n", ch->sess_name); + pr_info("Rejected login because no ACL has been" + " configured yet for initiator %s.\n", ch->sess_name); rej->reason = __constant_cpu_to_be32( SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED); goto destroy_ib; @@ -2631,7 +2628,7 @@ static int srpt_cm_req_recv(struct ib_cm_id *cm_id, ret = ib_send_cm_rep(cm_id, rep_param); if (ret) { - printk(KERN_ERR "sending SRP_LOGIN_REQ response failed" + pr_err("sending SRP_LOGIN_REQ response failed" " (error code = %d)\n", ret); goto release_channel; } @@ -2679,7 +2676,7 @@ out: static void srpt_cm_rej_recv(struct ib_cm_id *cm_id) { - printk(KERN_INFO "Received IB REJ for cm_id %p.\n", cm_id); + pr_info("Received IB REJ for cm_id %p.\n", cm_id); srpt_drain_channel(cm_id); } @@ -2714,13 +2711,13 @@ static void srpt_cm_rtu_recv(struct ib_cm_id *cm_id) static void srpt_cm_timewait_exit(struct ib_cm_id *cm_id) { - printk(KERN_INFO "Received IB TimeWait exit for cm_id %p.\n", cm_id); + pr_info("Received IB TimeWait exit for cm_id %p.\n", cm_id); srpt_drain_channel(cm_id); } static void srpt_cm_rep_error(struct ib_cm_id *cm_id) { - printk(KERN_INFO "Received IB REP error for cm_id %p.\n", cm_id); + pr_info("Received IB REP error for cm_id %p.\n", cm_id); srpt_drain_channel(cm_id); } @@ -2755,9 +2752,9 @@ static void srpt_cm_dreq_recv(struct ib_cm_id *cm_id) if (send_drep) { if (ib_send_cm_drep(ch->cm_id, NULL, 0) < 0) - printk(KERN_ERR "Sending IB DREP failed.\n"); - printk(KERN_INFO "Received DREQ and sent DREP for session %s.\n", - ch->sess_name); + pr_err("Sending IB DREP failed.\n"); + pr_info("Received DREQ and sent DREP for session %s.\n", + ch->sess_name); } } @@ -2766,8 +2763,7 @@ static void srpt_cm_dreq_recv(struct ib_cm_id *cm_id) */ static void srpt_cm_drep_recv(struct ib_cm_id *cm_id) { - printk(KERN_INFO "Received InfiniBand DREP message for cm_id %p.\n", - cm_id); + pr_info("Received InfiniBand DREP message for cm_id %p.\n", cm_id); srpt_drain_channel(cm_id); } @@ -2811,14 +2807,13 @@ static int srpt_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) srpt_cm_rep_error(cm_id); break; case IB_CM_DREQ_ERROR: - printk(KERN_INFO "Received IB DREQ ERROR event.\n"); + pr_info("Received IB DREQ ERROR event.\n"); break; case IB_CM_MRA_RECEIVED: - printk(KERN_INFO "Received IB MRA event\n"); + pr_info("Received IB MRA event\n"); break; default: - printk(KERN_ERR "received unrecognized IB CM event %d\n", - event->event); + pr_err("received unrecognized IB CM event %d\n", event->event); break; } @@ -2848,8 +2843,8 @@ static int srpt_perform_rdmas(struct srpt_rdma_ch *ch, ret = -ENOMEM; sq_wr_avail = atomic_sub_return(n_rdma, &ch->sq_wr_avail); if (sq_wr_avail < 0) { - printk(KERN_WARNING "IB send queue full (needed %d)\n", - n_rdma); + pr_warn("IB send queue full (needed %d)\n", + n_rdma); goto out; } } @@ -2889,7 +2884,7 @@ static int srpt_perform_rdmas(struct srpt_rdma_ch *ch, } if (ret) - printk(KERN_ERR "%s[%d]: ib_post_send() returned %d for %d/%d", + pr_err("%s[%d]: ib_post_send() returned %d for %d/%d\n", __func__, __LINE__, ret, i, n_rdma); if (ret && i > 0) { wr.num_sge = 0; @@ -2897,12 +2892,12 @@ static int srpt_perform_rdmas(struct srpt_rdma_ch *ch, wr.send_flags = IB_SEND_SIGNALED; while (ch->state == CH_LIVE && ib_post_send(ch->qp, &wr, &bad_wr) != 0) { - printk(KERN_INFO "Trying to abort failed RDMA transfer [%d]", + pr_info("Trying to abort failed RDMA transfer [%d]\n", ioctx->ioctx.index); msleep(1000); } while (ch->state != CH_RELEASING && !ioctx->rdma_aborted) { - printk(KERN_INFO "Waiting until RDMA abort finished [%d]", + pr_info("Waiting until RDMA abort finished [%d]\n", ioctx->ioctx.index); msleep(1000); } @@ -2923,17 +2918,17 @@ static int srpt_xfer_data(struct srpt_rdma_ch *ch, ret = srpt_map_sg_to_ib_sge(ch, ioctx); if (ret) { - printk(KERN_ERR "%s[%d] ret=%d\n", __func__, __LINE__, ret); + pr_err("%s[%d] ret=%d\n", __func__, __LINE__, ret); goto out; } ret = srpt_perform_rdmas(ch, ioctx); if (ret) { if (ret == -EAGAIN || ret == -ENOMEM) - printk(KERN_INFO "%s[%d] queue full -- ret=%d\n", - __func__, __LINE__, ret); + pr_info("%s[%d] queue full -- ret=%d\n", + __func__, __LINE__, ret); else - printk(KERN_ERR "%s[%d] fatal error -- ret=%d\n", + pr_err("%s[%d] fatal error -- ret=%d\n", __func__, __LINE__, ret); goto out_unmap; } @@ -3058,7 +3053,7 @@ static void srpt_queue_response(struct se_cmd *cmd) !ioctx->queue_status_only) { ret = srpt_xfer_data(ch, ioctx); if (ret) { - printk(KERN_ERR "xfer_data failed for tag %llu\n", + pr_err("xfer_data failed for tag %llu\n", ioctx->tag); return; } @@ -3075,7 +3070,7 @@ static void srpt_queue_response(struct se_cmd *cmd) } ret = srpt_post_send(ch, ioctx, resp_len); if (ret) { - printk(KERN_ERR "sending cmd response failed for tag %llu\n", + pr_err("sending cmd response failed for tag %llu\n", ioctx->tag); srpt_unmap_sg_to_ib_sge(ch, ioctx); srpt_set_cmd_state(ioctx, SRPT_STATE_DONE); @@ -3154,7 +3149,7 @@ static int srpt_release_sdev(struct srpt_device *sdev) res = wait_event_interruptible(sdev->ch_releaseQ, srpt_ch_list_empty(sdev)); if (res) - printk(KERN_ERR "%s: interrupted.\n", __func__); + pr_err("%s: interrupted.\n", __func__); return 0; } @@ -3293,7 +3288,7 @@ static void srpt_add_one(struct ib_device *device) spin_lock_init(&sport->port_acl_lock); if (srpt_refresh_port(sport)) { - printk(KERN_ERR "MAD registration failed for %s-%d.\n", + pr_err("MAD registration failed for %s-%d.\n", srpt_sdev_name(sdev), i); goto err_ring; } @@ -3330,7 +3325,7 @@ free_dev: kfree(sdev); err: sdev = NULL; - printk(KERN_INFO "%s(%s) failed.\n", __func__, device->name); + pr_info("%s(%s) failed.\n", __func__, device->name); goto out; } @@ -3344,8 +3339,7 @@ static void srpt_remove_one(struct ib_device *device) sdev = ib_get_client_data(device, &srpt_client); if (!sdev) { - printk(KERN_INFO "%s(%s): nothing to do.\n", __func__, - device->name); + pr_info("%s(%s): nothing to do.\n", __func__, device->name); return; } @@ -3464,7 +3458,7 @@ static struct se_node_acl *srpt_alloc_fabric_acl(struct se_portal_group *se_tpg) nacl = kzalloc(sizeof(struct srpt_node_acl), GFP_KERNEL); if (!nacl) { - printk(KERN_ERR "Unable to allocate struct srpt_node_acl\n"); + pr_err("Unable to allocate struct srpt_node_acl\n"); return NULL; } @@ -3615,7 +3609,7 @@ static struct se_node_acl *srpt_make_nodeacl(struct se_portal_group *tpg, u8 i_port_id[16]; if (srpt_parse_i_port_id(i_port_id, name) < 0) { - printk(KERN_ERR "invalid initiator port ID %s\n", name); + pr_err("invalid initiator port ID %s\n", name); ret = -EINVAL; goto err; } @@ -3816,12 +3810,12 @@ static ssize_t srpt_tpg_store_enable( ret = kstrtoul(page, 0, &tmp); if (ret < 0) { - printk(KERN_ERR "Unable to extract srpt_tpg_store_enable\n"); + pr_err("Unable to extract srpt_tpg_store_enable\n"); return -EINVAL; } if ((tmp != 0) && (tmp != 1)) { - printk(KERN_ERR "Illegal value for srpt_tpg_store_enable: %lu\n", tmp); + pr_err("Illegal value for srpt_tpg_store_enable: %lu\n", tmp); return -EINVAL; } if (tmp == 1) @@ -3851,7 +3845,7 @@ static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn, int res; /* Initialize sport->port_wwn and sport->port_tpg_1 */ - res = core_tpg_register(&srpt_target->tf_ops, &sport->port_wwn, + res = core_tpg_register(&srpt_template, &sport->port_wwn, &sport->port_tpg_1, sport, TRANSPORT_TPG_TYPE_NORMAL); if (res) return ERR_PTR(res); @@ -3919,7 +3913,9 @@ static struct configfs_attribute *srpt_wwn_attrs[] = { NULL, }; -static struct target_core_fabric_ops srpt_template = { +static const struct target_core_fabric_ops srpt_template = { + .module = THIS_MODULE, + .name = "srpt", .get_fabric_name = srpt_get_fabric_name, .get_fabric_proto_ident = srpt_get_fabric_proto_ident, .tpg_get_wwn = srpt_get_fabric_wwn, @@ -3964,6 +3960,10 @@ static struct target_core_fabric_ops srpt_template = { .fabric_drop_np = NULL, .fabric_make_nodeacl = srpt_make_nodeacl, .fabric_drop_nodeacl = srpt_drop_nodeacl, + + .tfc_wwn_attrs = srpt_wwn_attrs, + .tfc_tpg_base_attrs = srpt_tpg_attrs, + .tfc_tpg_attrib_attrs = srpt_tpg_attrib_attrs, }; /** @@ -3980,7 +3980,7 @@ static int __init srpt_init_module(void) ret = -EINVAL; if (srp_max_req_size < MIN_MAX_REQ_SIZE) { - printk(KERN_ERR "invalid value %d for kernel module parameter" + pr_err("invalid value %d for kernel module parameter" " srp_max_req_size -- must be at least %d.\n", srp_max_req_size, MIN_MAX_REQ_SIZE); goto out; @@ -3988,54 +3988,26 @@ static int __init srpt_init_module(void) if (srpt_srq_size < MIN_SRPT_SRQ_SIZE || srpt_srq_size > MAX_SRPT_SRQ_SIZE) { - printk(KERN_ERR "invalid value %d for kernel module parameter" + pr_err("invalid value %d for kernel module parameter" " srpt_srq_size -- must be in the range [%d..%d].\n", srpt_srq_size, MIN_SRPT_SRQ_SIZE, MAX_SRPT_SRQ_SIZE); goto out; } - srpt_target = target_fabric_configfs_init(THIS_MODULE, "srpt"); - if (IS_ERR(srpt_target)) { - printk(KERN_ERR "couldn't register\n"); - ret = PTR_ERR(srpt_target); + ret = target_register_template(&srpt_template); + if (ret) goto out; - } - - srpt_target->tf_ops = srpt_template; - - /* - * Set up default attribute lists. - */ - srpt_target->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = srpt_wwn_attrs; - srpt_target->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = srpt_tpg_attrs; - srpt_target->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = srpt_tpg_attrib_attrs; - srpt_target->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - srpt_target->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - srpt_target->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - srpt_target->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - srpt_target->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - srpt_target->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - - ret = target_fabric_configfs_register(srpt_target); - if (ret < 0) { - printk(KERN_ERR "couldn't register\n"); - goto out_free_target; - } ret = ib_register_client(&srpt_client); if (ret) { - printk(KERN_ERR "couldn't register IB client\n"); + pr_err("couldn't register IB client\n"); goto out_unregister_target; } return 0; out_unregister_target: - target_fabric_configfs_deregister(srpt_target); - srpt_target = NULL; -out_free_target: - if (srpt_target) - target_fabric_configfs_free(srpt_target); + target_unregister_template(&srpt_template); out: return ret; } @@ -4043,8 +4015,7 @@ out: static void __exit srpt_cleanup_module(void) { ib_unregister_client(&srpt_client); - target_fabric_configfs_deregister(srpt_target); - srpt_target = NULL; + target_unregister_template(&srpt_template); } module_init(srpt_init_module); diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index 64b9b59ad4cb..b50c5b8b8a4d 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -148,16 +148,19 @@ static void cros_ec_keyb_process(struct cros_ec_keyb *ckdev, static int cros_ec_keyb_get_state(struct cros_ec_keyb *ckdev, uint8_t *kb_state) { + int ret; struct cros_ec_command msg = { - .version = 0, .command = EC_CMD_MKBP_STATE, - .outdata = NULL, - .outsize = 0, - .indata = kb_state, .insize = ckdev->cols, }; - return cros_ec_cmd_xfer(ckdev->ec, &msg); + ret = cros_ec_cmd_xfer(ckdev->ec, &msg); + if (ret < 0) + return ret; + + memcpy(kb_state, msg.indata, ckdev->cols); + + return 0; } static irqreturn_t cros_ec_keyb_irq(int irq, void *data) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a35927cd42e5..68d43beccb7e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -50,6 +50,7 @@ #define CONTEXT_SIZE VTD_PAGE_SIZE #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) +#define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB) #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e) @@ -184,32 +185,11 @@ static int force_on = 0; * 64-127: Reserved */ struct root_entry { - u64 val; - u64 rsvd1; + u64 lo; + u64 hi; }; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) -static inline bool root_present(struct root_entry *root) -{ - return (root->val & 1); -} -static inline void set_root_present(struct root_entry *root) -{ - root->val |= 1; -} -static inline void set_root_value(struct root_entry *root, unsigned long value) -{ - root->val &= ~VTD_PAGE_MASK; - root->val |= value & VTD_PAGE_MASK; -} -static inline struct context_entry * -get_context_addr_from_root(struct root_entry *root) -{ - return (struct context_entry *) - (root_present(root)?phys_to_virt( - root->val & VTD_PAGE_MASK) : - NULL); -} /* * low 64 bits: @@ -682,6 +662,40 @@ static void domain_update_iommu_cap(struct dmar_domain *domain) domain->iommu_superpage = domain_update_iommu_superpage(NULL); } +static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu, + u8 bus, u8 devfn, int alloc) +{ + struct root_entry *root = &iommu->root_entry[bus]; + struct context_entry *context; + u64 *entry; + + if (ecap_ecs(iommu->ecap)) { + if (devfn >= 0x80) { + devfn -= 0x80; + entry = &root->hi; + } + devfn *= 2; + } + entry = &root->lo; + if (*entry & 1) + context = phys_to_virt(*entry & VTD_PAGE_MASK); + else { + unsigned long phy_addr; + if (!alloc) + return NULL; + + context = alloc_pgtable_page(iommu->node); + if (!context) + return NULL; + + __iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE); + phy_addr = virt_to_phys((void *)context); + *entry = phy_addr | 1; + __iommu_flush_cache(iommu, entry, sizeof(*entry)); + } + return &context[devfn]; +} + static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn) { struct dmar_drhd_unit *drhd = NULL; @@ -741,75 +755,36 @@ static void domain_flush_cache(struct dmar_domain *domain, clflush_cache_range(addr, size); } -/* Gets context entry for a given bus and devfn */ -static struct context_entry * device_to_context_entry(struct intel_iommu *iommu, - u8 bus, u8 devfn) -{ - struct root_entry *root; - struct context_entry *context; - unsigned long phy_addr; - unsigned long flags; - - spin_lock_irqsave(&iommu->lock, flags); - root = &iommu->root_entry[bus]; - context = get_context_addr_from_root(root); - if (!context) { - context = (struct context_entry *) - alloc_pgtable_page(iommu->node); - if (!context) { - spin_unlock_irqrestore(&iommu->lock, flags); - return NULL; - } - __iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE); - phy_addr = virt_to_phys((void *)context); - set_root_value(root, phy_addr); - set_root_present(root); - __iommu_flush_cache(iommu, root, sizeof(*root)); - } - spin_unlock_irqrestore(&iommu->lock, flags); - return &context[devfn]; -} - static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn) { - struct root_entry *root; struct context_entry *context; - int ret; + int ret = 0; unsigned long flags; spin_lock_irqsave(&iommu->lock, flags); - root = &iommu->root_entry[bus]; - context = get_context_addr_from_root(root); - if (!context) { - ret = 0; - goto out; - } - ret = context_present(&context[devfn]); -out: + context = iommu_context_addr(iommu, bus, devfn, 0); + if (context) + ret = context_present(context); spin_unlock_irqrestore(&iommu->lock, flags); return ret; } static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn) { - struct root_entry *root; struct context_entry *context; unsigned long flags; spin_lock_irqsave(&iommu->lock, flags); - root = &iommu->root_entry[bus]; - context = get_context_addr_from_root(root); + context = iommu_context_addr(iommu, bus, devfn, 0); if (context) { - context_clear_entry(&context[devfn]); - __iommu_flush_cache(iommu, &context[devfn], \ - sizeof(*context)); + context_clear_entry(context); + __iommu_flush_cache(iommu, context, sizeof(*context)); } spin_unlock_irqrestore(&iommu->lock, flags); } static void free_context_table(struct intel_iommu *iommu) { - struct root_entry *root; int i; unsigned long flags; struct context_entry *context; @@ -819,10 +794,17 @@ static void free_context_table(struct intel_iommu *iommu) goto out; } for (i = 0; i < ROOT_ENTRY_NR; i++) { - root = &iommu->root_entry[i]; - context = get_context_addr_from_root(root); + context = iommu_context_addr(iommu, i, 0, 0); + if (context) + free_pgtable_page(context); + + if (!ecap_ecs(iommu->ecap)) + continue; + + context = iommu_context_addr(iommu, i, 0x80, 0); if (context) free_pgtable_page(context); + } free_pgtable_page(iommu->root_entry); iommu->root_entry = NULL; @@ -1146,14 +1128,16 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu) static void iommu_set_root_entry(struct intel_iommu *iommu) { - void *addr; + u64 addr; u32 sts; unsigned long flag; - addr = iommu->root_entry; + addr = virt_to_phys(iommu->root_entry); + if (ecap_ecs(iommu->ecap)) + addr |= DMA_RTADDR_RTT; raw_spin_lock_irqsave(&iommu->register_lock, flag); - dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr)); + dmar_writeq(iommu->reg + DMAR_RTADDR_REG, addr); writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG); @@ -1800,7 +1784,9 @@ static int domain_context_mapping_one(struct dmar_domain *domain, BUG_ON(translation != CONTEXT_TT_PASS_THROUGH && translation != CONTEXT_TT_MULTI_LEVEL); - context = device_to_context_entry(iommu, bus, devfn); + spin_lock_irqsave(&iommu->lock, flags); + context = iommu_context_addr(iommu, bus, devfn, 1); + spin_unlock_irqrestore(&iommu->lock, flags); if (!context) return -ENOMEM; spin_lock_irqsave(&iommu->lock, flags); @@ -2564,6 +2550,10 @@ static bool device_has_rmrr(struct device *dev) * In both cases we assume that PCI USB devices with RMRRs have them largely * for historical reasons and that the RMRR space is not actively used post * boot. This exclusion may change if vendors begin to abuse it. + * + * The same exception is made for graphics devices, with the requirement that + * any use of the RMRR regions will be torn down before assigning the device + * to a guest. */ static bool device_is_rmrr_locked(struct device *dev) { @@ -2573,7 +2563,7 @@ static bool device_is_rmrr_locked(struct device *dev) if (dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(dev); - if ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB) + if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev)) return false; } diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 6c25b3c5b729..5709ae9c3e77 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -637,10 +637,7 @@ static int __init intel_enable_irq_remapping(void) if (x2apic_supported()) { eim = !dmar_x2apic_optout(); if (!eim) - printk(KERN_WARNING - "Your BIOS is broken and requested that x2apic be disabled.\n" - "This will slightly decrease performance.\n" - "Use 'intremap=no_x2apic_optout' to override BIOS request.\n"); + pr_info("x2apic is disabled because BIOS sets x2apic opt out bit. You can use 'intremap=no_x2apic_optout' to override the BIOS setting.\n"); } for_each_iommu(iommu, drhd) { diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index a6ce3476834e..7b315e385ba3 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -33,12 +33,14 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/acpi.h> #include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqchip/arm-gic.h> +#include <linux/irqchip/arm-gic-acpi.h> #include <asm/cputype.h> #include <asm/irq.h> @@ -1107,3 +1109,105 @@ IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init); IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init); #endif + +#ifdef CONFIG_ACPI +static phys_addr_t dist_phy_base, cpu_phy_base __initdata; + +static int __init +gic_acpi_parse_madt_cpu(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_interrupt *processor; + phys_addr_t gic_cpu_base; + static int cpu_base_assigned; + + processor = (struct acpi_madt_generic_interrupt *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + /* + * There is no support for non-banked GICv1/2 register in ACPI spec. + * All CPU interface addresses have to be the same. + */ + gic_cpu_base = processor->base_address; + if (cpu_base_assigned && gic_cpu_base != cpu_phy_base) + return -EINVAL; + + cpu_phy_base = gic_cpu_base; + cpu_base_assigned = 1; + return 0; +} + +static int __init +gic_acpi_parse_madt_distributor(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_distributor *dist; + + dist = (struct acpi_madt_generic_distributor *)header; + + if (BAD_MADT_ENTRY(dist, end)) + return -EINVAL; + + dist_phy_base = dist->base_address; + return 0; +} + +int __init +gic_v2_acpi_init(struct acpi_table_header *table) +{ + void __iomem *cpu_base, *dist_base; + int count; + + /* Collect CPU base addresses */ + count = acpi_parse_entries(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + gic_acpi_parse_madt_cpu, table, + ACPI_MADT_TYPE_GENERIC_INTERRUPT, 0); + if (count <= 0) { + pr_err("No valid GICC entries exist\n"); + return -EINVAL; + } + + /* + * Find distributor base address. We expect one distributor entry since + * ACPI 5.1 spec neither support multi-GIC instances nor GIC cascade. + */ + count = acpi_parse_entries(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + gic_acpi_parse_madt_distributor, table, + ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, 0); + if (count <= 0) { + pr_err("No valid GICD entries exist\n"); + return -EINVAL; + } else if (count > 1) { + pr_err("More than one GICD entry detected\n"); + return -EINVAL; + } + + cpu_base = ioremap(cpu_phy_base, ACPI_GIC_CPU_IF_MEM_SIZE); + if (!cpu_base) { + pr_err("Unable to map GICC registers\n"); + return -ENOMEM; + } + + dist_base = ioremap(dist_phy_base, ACPI_GICV2_DIST_MEM_SIZE); + if (!dist_base) { + pr_err("Unable to map GICD registers\n"); + iounmap(cpu_base); + return -ENOMEM; + } + + /* + * Initialize zero GIC instance (no multi-GIC support). Also, set GIC + * as default IRQ domain to allow for GSI registration and GSI to IRQ + * number translation (see acpi_register_gsi() and acpi_gsi_to_irq()). + */ + gic_init_bases(0, -1, dist_base, cpu_base, 0, NULL); + irq_set_default_host(gic_data[0].domain); + + acpi_irq_model = ACPI_IRQ_MODEL_GIC; + return 0; +} +#endif diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c index 0fe2f718d81c..afd1af3dfe5a 100644 --- a/drivers/irqchip/irqchip.c +++ b/drivers/irqchip/irqchip.c @@ -8,6 +8,7 @@ * warranty of any kind, whether express or implied. */ +#include <linux/acpi_irq.h> #include <linux/init.h> #include <linux/of_irq.h> #include <linux/irqchip.h> @@ -26,4 +27,6 @@ extern struct of_device_id __irqchip_of_table[]; void __init irqchip_init(void) { of_irq_init(__irqchip_of_table); + + acpi_irq_init(); } diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c index 1219af493c0f..19a32280731d 100644 --- a/drivers/lguest/hypercalls.c +++ b/drivers/lguest/hypercalls.c @@ -211,10 +211,9 @@ static void initialize(struct lg_cpu *cpu) /* * The Guest tells us where we're not to deliver interrupts by putting - * the range of addresses into "struct lguest_data". + * the instruction address into "struct lguest_data". */ - if (get_user(cpu->lg->noirq_start, &cpu->lg->lguest_data->noirq_start) - || get_user(cpu->lg->noirq_end, &cpu->lg->lguest_data->noirq_end)) + if (get_user(cpu->lg->noirq_iret, &cpu->lg->lguest_data->noirq_iret)) kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); /* diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 70dfcdc29f1f..5e7559be222a 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -56,21 +56,16 @@ static void push_guest_stack(struct lg_cpu *cpu, unsigned long *gstack, u32 val) } /*H:210 - * The set_guest_interrupt() routine actually delivers the interrupt or - * trap. The mechanics of delivering traps and interrupts to the Guest are the - * same, except some traps have an "error code" which gets pushed onto the - * stack as well: the caller tells us if this is one. - * - * "lo" and "hi" are the two parts of the Interrupt Descriptor Table for this - * interrupt or trap. It's split into two parts for traditional reasons: gcc - * on i386 used to be frightened by 64 bit numbers. + * The push_guest_interrupt_stack() routine saves Guest state on the stack for + * an interrupt or trap. The mechanics of delivering traps and interrupts to + * the Guest are the same, except some traps have an "error code" which gets + * pushed onto the stack as well: the caller tells us if this is one. * * We set up the stack just like the CPU does for a real interrupt, so it's * identical for the Guest (and the standard "iret" instruction will undo * it). */ -static void set_guest_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi, - bool has_err) +static void push_guest_interrupt_stack(struct lg_cpu *cpu, bool has_err) { unsigned long gstack, origstack; u32 eflags, ss, irq_enable; @@ -130,12 +125,28 @@ static void set_guest_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi, if (has_err) push_guest_stack(cpu, &gstack, cpu->regs->errcode); - /* - * Now we've pushed all the old state, we change the stack, the code - * segment and the address to execute. - */ + /* Adjust the stack pointer and stack segment. */ cpu->regs->ss = ss; cpu->regs->esp = virtstack + (gstack - origstack); +} + +/* + * This actually makes the Guest start executing the given interrupt/trap + * handler. + * + * "lo" and "hi" are the two parts of the Interrupt Descriptor Table for this + * interrupt or trap. It's split into two parts for traditional reasons: gcc + * on i386 used to be frightened by 64 bit numbers. + */ +static void guest_run_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi) +{ + /* If we're already in the kernel, we don't change stacks. */ + if ((cpu->regs->ss&0x3) != GUEST_PL) + cpu->regs->ss = cpu->esp1; + + /* + * Set the code segment and the address to execute. + */ cpu->regs->cs = (__KERNEL_CS|GUEST_PL); cpu->regs->eip = idt_address(lo, hi); @@ -158,6 +169,24 @@ static void set_guest_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi, kill_guest(cpu, "Disabling interrupts"); } +/* This restores the eflags word which was pushed on the stack by a trap */ +static void restore_eflags(struct lg_cpu *cpu) +{ + /* This is the physical address of the stack. */ + unsigned long stack_pa = guest_pa(cpu, cpu->regs->esp); + + /* + * Stack looks like this: + * Address Contents + * esp EIP + * esp + 4 CS + * esp + 8 EFLAGS + */ + cpu->regs->eflags = lgread(cpu, stack_pa + 8, u32); + cpu->regs->eflags &= + ~(X86_EFLAGS_TF|X86_EFLAGS_VM|X86_EFLAGS_RF|X86_EFLAGS_NT); +} + /*H:205 * Virtual Interrupts. * @@ -200,14 +229,6 @@ void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more) BUG_ON(irq >= LGUEST_IRQS); - /* - * They may be in the middle of an iret, where they asked us never to - * deliver interrupts. - */ - if (cpu->regs->eip >= cpu->lg->noirq_start && - (cpu->regs->eip < cpu->lg->noirq_end)) - return; - /* If they're halted, interrupts restart them. */ if (cpu->halted) { /* Re-enable interrupts. */ @@ -237,12 +258,34 @@ void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more) if (idt_present(idt->a, idt->b)) { /* OK, mark it no longer pending and deliver it. */ clear_bit(irq, cpu->irqs_pending); + /* - * set_guest_interrupt() takes the interrupt descriptor and a - * flag to say whether this interrupt pushes an error code onto - * the stack as well: virtual interrupts never do. + * They may be about to iret, where they asked us never to + * deliver interrupts. In this case, we can emulate that iret + * then immediately deliver the interrupt. This is basically + * a noop: the iret would pop the interrupt frame and restore + * eflags, and then we'd set it up again. So just restore the + * eflags word and jump straight to the handler in this case. + * + * Denys Vlasenko points out that this isn't quite right: if + * the iret was returning to userspace, then that interrupt + * would reset the stack pointer (which the Guest told us + * about via LHCALL_SET_STACK). But unless the Guest is being + * *really* weird, that will be the same as the current stack + * anyway. */ - set_guest_interrupt(cpu, idt->a, idt->b, false); + if (cpu->regs->eip == cpu->lg->noirq_iret) { + restore_eflags(cpu); + } else { + /* + * set_guest_interrupt() takes a flag to say whether + * this interrupt pushes an error code onto the stack + * as well: virtual interrupts never do. + */ + push_guest_interrupt_stack(cpu, false); + } + /* Actually make Guest cpu jump to handler. */ + guest_run_interrupt(cpu, idt->a, idt->b); } /* @@ -353,8 +396,9 @@ bool deliver_trap(struct lg_cpu *cpu, unsigned int num) */ if (!idt_present(cpu->arch.idt[num].a, cpu->arch.idt[num].b)) return false; - set_guest_interrupt(cpu, cpu->arch.idt[num].a, - cpu->arch.idt[num].b, has_err(num)); + push_guest_interrupt_stack(cpu, has_err(num)); + guest_run_interrupt(cpu, cpu->arch.idt[num].a, + cpu->arch.idt[num].b); return true; } @@ -395,8 +439,9 @@ static bool direct_trap(unsigned int num) * The Guest has the ability to turn its interrupt gates into trap gates, * if it is careful. The Host will let trap gates can go directly to the * Guest, but the Guest needs the interrupts atomically disabled for an - * interrupt gate. It can do this by pointing the trap gate at instructions - * within noirq_start and noirq_end, where it can safely disable interrupts. + * interrupt gate. The Host could provide a mechanism to register more + * "no-interrupt" regions, and the Guest could point the trap gate at + * instructions within that region, where it can safely disable interrupts. */ /*M:006 diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index 307e8b39e7d1..ac8ad0461e80 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -102,7 +102,7 @@ struct lguest { struct pgdir pgdirs[4]; - unsigned long noirq_start, noirq_end; + unsigned long noirq_iret; unsigned int stack_pages; u32 tsc_khz; diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index c4c6113eb9a6..30c60687d277 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -339,6 +339,13 @@ static ssize_t write(struct file *file, const char __user *in, } } +static int open(struct inode *inode, struct file *file) +{ + file->private_data = NULL; + + return 0; +} + /*L:060 * The final piece of interface code is the close() routine. It reverses * everything done in initialize(). This is usually called because the @@ -409,6 +416,7 @@ static int close(struct inode *inode, struct file *file) */ static const struct file_operations lguest_fops = { .owner = THIS_MODULE, + .open = open, .release = close, .write = write, .read = read, diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 6ddc983417d5..edcf4ab66e00 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -175,6 +175,22 @@ config MD_FAULTY In unsure, say N. + +config MD_CLUSTER + tristate "Cluster Support for MD (EXPERIMENTAL)" + depends on BLK_DEV_MD + depends on DLM + default n + ---help--- + Clustering support for MD devices. This enables locking and + synchronization across multiple systems on the cluster, so all + nodes in the cluster can access the MD devices simultaneously. + + This brings the redundancy (and uptime) of RAID levels across the + nodes of the cluster. + + If unsure, say N. + source "drivers/md/bcache/Kconfig" config BLK_DEV_DM_BUILTIN diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 1863feaa5846..dba4db5985fb 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_MD_RAID10) += raid10.o obj-$(CONFIG_MD_RAID456) += raid456.o obj-$(CONFIG_MD_MULTIPATH) += multipath.o obj-$(CONFIG_MD_FAULTY) += faulty.o +obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ obj-$(CONFIG_BLK_DEV_MD) += md-mod.o obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 3a5767968ba0..2bc56e2a3526 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -205,6 +205,10 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; + int node_offset = 0; + + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * store->file_pages; while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { int size = PAGE_SIZE; @@ -433,6 +437,7 @@ void bitmap_update_sb(struct bitmap *bitmap) /* This might have been changed by a reshape */ sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize); + sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes); sb->sectors_reserved = cpu_to_le32(bitmap->mddev-> bitmap_info.space); kunmap_atomic(sb); @@ -544,6 +549,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) bitmap_super_t *sb; unsigned long chunksize, daemon_sleep, write_behind; unsigned long long events; + int nodes = 0; unsigned long sectors_reserved = 0; int err = -EINVAL; struct page *sb_page; @@ -562,6 +568,22 @@ static int bitmap_read_sb(struct bitmap *bitmap) return -ENOMEM; bitmap->storage.sb_page = sb_page; +re_read: + /* If cluster_slot is set, the cluster is setup */ + if (bitmap->cluster_slot >= 0) { + sector_t bm_blocks = bitmap->mddev->resync_max_sectors; + + sector_div(bm_blocks, + bitmap->mddev->bitmap_info.chunksize >> 9); + /* bits to bytes */ + bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t); + /* to 4k blocks */ + bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096); + bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3); + pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__, + bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset); + } + if (bitmap->storage.file) { loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host); int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize; @@ -577,12 +599,15 @@ static int bitmap_read_sb(struct bitmap *bitmap) if (err) return err; + err = -EINVAL; sb = kmap_atomic(sb_page); chunksize = le32_to_cpu(sb->chunksize); daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); sectors_reserved = le32_to_cpu(sb->sectors_reserved); + nodes = le32_to_cpu(sb->nodes); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); /* verify that the bitmap-specific fields are valid */ if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) @@ -619,7 +644,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) goto out; } events = le64_to_cpu(sb->events); - if (events < bitmap->mddev->events) { + if (!nodes && (events < bitmap->mddev->events)) { printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) " "-- forcing full recovery\n", @@ -634,20 +659,40 @@ static int bitmap_read_sb(struct bitmap *bitmap) if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) set_bit(BITMAP_HOSTENDIAN, &bitmap->flags); bitmap->events_cleared = le64_to_cpu(sb->events_cleared); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); err = 0; + out: kunmap_atomic(sb); + /* Assiging chunksize is required for "re_read" */ + bitmap->mddev->bitmap_info.chunksize = chunksize; + if (nodes && (bitmap->cluster_slot < 0)) { + err = md_setup_cluster(bitmap->mddev, nodes); + if (err) { + pr_err("%s: Could not setup cluster service (%d)\n", + bmname(bitmap), err); + goto out_no_sb; + } + bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev); + goto re_read; + } + + out_no_sb: if (test_bit(BITMAP_STALE, &bitmap->flags)) bitmap->events_cleared = bitmap->mddev->events; bitmap->mddev->bitmap_info.chunksize = chunksize; bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->mddev->bitmap_info.nodes = nodes; if (bitmap->mddev->bitmap_info.space == 0 || bitmap->mddev->bitmap_info.space > sectors_reserved) bitmap->mddev->bitmap_info.space = sectors_reserved; - if (err) + if (err) { bitmap_print_sb(bitmap); + if (bitmap->cluster_slot < 0) + md_cluster_stop(bitmap->mddev); + } return err; } @@ -692,9 +737,10 @@ static inline struct page *filemap_get_page(struct bitmap_storage *store, } static int bitmap_storage_alloc(struct bitmap_storage *store, - unsigned long chunks, int with_super) + unsigned long chunks, int with_super, + int slot_number) { - int pnum; + int pnum, offset = 0; unsigned long num_pages; unsigned long bytes; @@ -703,6 +749,7 @@ static int bitmap_storage_alloc(struct bitmap_storage *store, bytes += sizeof(bitmap_super_t); num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); + offset = slot_number * (num_pages - 1); store->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL); @@ -713,20 +760,22 @@ static int bitmap_storage_alloc(struct bitmap_storage *store, store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO); if (store->sb_page == NULL) return -ENOMEM; - store->sb_page->index = 0; } + pnum = 0; if (store->sb_page) { store->filemap[0] = store->sb_page; pnum = 1; + store->sb_page->index = offset; } + for ( ; pnum < num_pages; pnum++) { store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO); if (!store->filemap[pnum]) { store->file_pages = pnum; return -ENOMEM; } - store->filemap[pnum]->index = pnum; + store->filemap[pnum]->index = pnum + offset; } store->file_pages = pnum; @@ -885,6 +934,28 @@ static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) } } +static int bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) +{ + unsigned long bit; + struct page *page; + void *paddr; + unsigned long chunk = block >> bitmap->counts.chunkshift; + int set = 0; + + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) + return -EINVAL; + bit = file_page_offset(&bitmap->storage, chunk); + paddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + set = test_bit(bit, paddr); + else + set = test_bit_le(bit, paddr); + kunmap_atomic(paddr); + return set; +} + + /* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */ @@ -935,7 +1006,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n */ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) { - unsigned long i, chunks, index, oldindex, bit; + unsigned long i, chunks, index, oldindex, bit, node_offset = 0; struct page *page = NULL; unsigned long bit_cnt = 0; struct file *file; @@ -981,6 +1052,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) if (!bitmap->mddev->bitmap_info.external) offset = sizeof(bitmap_super_t); + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE)); + for (i = 0; i < chunks; i++) { int b; index = file_page_index(&bitmap->storage, i); @@ -1001,7 +1075,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) bitmap->mddev, bitmap->mddev->bitmap_info.offset, page, - index, count); + index + node_offset, count); if (ret) goto err; @@ -1207,7 +1281,6 @@ void bitmap_daemon_work(struct mddev *mddev) j < bitmap->storage.file_pages && !test_bit(BITMAP_STALE, &bitmap->flags); j++) { - if (test_page_attr(bitmap, j, BITMAP_PAGE_DIRTY)) /* bitmap_unplug will handle the rest */ @@ -1530,11 +1603,13 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n return; } if (!*bmc) { - *bmc = 2 | (needed ? NEEDED_MASK : 0); + *bmc = 2; bitmap_count_page(&bitmap->counts, offset, 1); bitmap_set_pending(&bitmap->counts, offset); bitmap->allclean = 0; } + if (needed) + *bmc |= NEEDED_MASK; spin_unlock_irq(&bitmap->counts.lock); } @@ -1591,6 +1666,10 @@ static void bitmap_free(struct bitmap *bitmap) if (!bitmap) /* there was no bitmap */ return; + if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info && + bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev)) + md_cluster_stop(bitmap->mddev); + /* Shouldn't be needed - but just in case.... */ wait_event(bitmap->write_wait, atomic_read(&bitmap->pending_writes) == 0); @@ -1636,7 +1715,7 @@ void bitmap_destroy(struct mddev *mddev) * initialize the bitmap structure * if this returns an error, bitmap_destroy must be called to do clean up */ -int bitmap_create(struct mddev *mddev) +struct bitmap *bitmap_create(struct mddev *mddev, int slot) { struct bitmap *bitmap; sector_t blocks = mddev->resync_max_sectors; @@ -1650,7 +1729,7 @@ int bitmap_create(struct mddev *mddev) bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL); if (!bitmap) - return -ENOMEM; + return ERR_PTR(-ENOMEM); spin_lock_init(&bitmap->counts.lock); atomic_set(&bitmap->pending_writes, 0); @@ -1659,6 +1738,7 @@ int bitmap_create(struct mddev *mddev) init_waitqueue_head(&bitmap->behind_wait); bitmap->mddev = mddev; + bitmap->cluster_slot = slot; if (mddev->kobj.sd) bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); @@ -1706,12 +1786,14 @@ int bitmap_create(struct mddev *mddev) printk(KERN_INFO "created bitmap (%lu pages) for device %s\n", bitmap->counts.pages, bmname(bitmap)); - mddev->bitmap = bitmap; - return test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; + err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; + if (err) + goto error; + return bitmap; error: bitmap_free(bitmap); - return err; + return ERR_PTR(err); } int bitmap_load(struct mddev *mddev) @@ -1765,6 +1847,60 @@ out: } EXPORT_SYMBOL_GPL(bitmap_load); +/* Loads the bitmap associated with slot and copies the resync information + * to our bitmap + */ +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *low, sector_t *high, bool clear_bits) +{ + int rv = 0, i, j; + sector_t block, lo = 0, hi = 0; + struct bitmap_counts *counts; + struct bitmap *bitmap = bitmap_create(mddev, slot); + + if (IS_ERR(bitmap)) + return PTR_ERR(bitmap); + + rv = bitmap_read_sb(bitmap); + if (rv) + goto err; + + rv = bitmap_init_from_disk(bitmap, 0); + if (rv) + goto err; + + counts = &bitmap->counts; + for (j = 0; j < counts->chunks; j++) { + block = (sector_t)j << counts->chunkshift; + if (bitmap_file_test_bit(bitmap, block)) { + if (!lo) + lo = block; + hi = block; + bitmap_file_clear_bit(bitmap, block); + bitmap_set_memory_bits(mddev->bitmap, block, 1); + bitmap_file_set_bit(mddev->bitmap, block); + } + } + + if (clear_bits) { + bitmap_update_sb(bitmap); + /* Setting this for the ev_page should be enough. + * And we do not require both write_all and PAGE_DIRT either + */ + for (i = 0; i < bitmap->storage.file_pages; i++) + set_page_attr(bitmap, i, BITMAP_PAGE_DIRTY); + bitmap_write_all(bitmap); + bitmap_unplug(bitmap); + } + *low = lo; + *high = hi; +err: + bitmap_free(bitmap); + return rv; +} +EXPORT_SYMBOL_GPL(bitmap_copy_from_slot); + + void bitmap_status(struct seq_file *seq, struct bitmap *bitmap) { unsigned long chunk_kb; @@ -1849,7 +1985,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, memset(&store, 0, sizeof(store)); if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file) ret = bitmap_storage_alloc(&store, chunks, - !bitmap->mddev->bitmap_info.external); + !bitmap->mddev->bitmap_info.external, + bitmap->cluster_slot); if (ret) goto err; @@ -2021,13 +2158,18 @@ location_store(struct mddev *mddev, const char *buf, size_t len) return -EINVAL; mddev->bitmap_info.offset = offset; if (mddev->pers) { + struct bitmap *bitmap; mddev->pers->quiesce(mddev, 1); - rv = bitmap_create(mddev); - if (!rv) + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) + rv = PTR_ERR(bitmap); + else { + mddev->bitmap = bitmap; rv = bitmap_load(mddev); - if (rv) { - bitmap_destroy(mddev); - mddev->bitmap_info.offset = 0; + if (rv) { + bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + } } mddev->pers->quiesce(mddev, 0); if (rv) @@ -2186,6 +2328,8 @@ __ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store); static ssize_t metadata_show(struct mddev *mddev, char *page) { + if (mddev_is_clustered(mddev)) + return sprintf(page, "clustered\n"); return sprintf(page, "%s\n", (mddev->bitmap_info.external ? "external" : "internal")); } @@ -2198,7 +2342,8 @@ static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len) return -EBUSY; if (strncmp(buf, "external", 8) == 0) mddev->bitmap_info.external = 1; - else if (strncmp(buf, "internal", 8) == 0) + else if ((strncmp(buf, "internal", 8) == 0) || + (strncmp(buf, "clustered", 9) == 0)) mddev->bitmap_info.external = 0; else return -EINVAL; diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index 30210b9c4ef9..f1f4dd01090d 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -130,8 +130,9 @@ typedef struct bitmap_super_s { __le32 write_behind; /* 60 number of outstanding write-behind writes */ __le32 sectors_reserved; /* 64 number of 512-byte sectors that are * reserved for the bitmap. */ - - __u8 pad[256 - 68]; /* set to zero */ + __le32 nodes; /* 68 the maximum number of nodes in cluster. */ + __u8 cluster_name[64]; /* 72 cluster name to which this md belongs */ + __u8 pad[256 - 136]; /* set to zero */ } bitmap_super_t; /* notes: @@ -226,12 +227,13 @@ struct bitmap { wait_queue_head_t behind_wait; struct kernfs_node *sysfs_can_clear; + int cluster_slot; /* Slot offset for clustered env */ }; /* the bitmap API */ /* these are used only by md/bitmap */ -int bitmap_create(struct mddev *mddev); +struct bitmap *bitmap_create(struct mddev *mddev, int slot); int bitmap_load(struct mddev *mddev); void bitmap_flush(struct mddev *mddev); void bitmap_destroy(struct mddev *mddev); @@ -260,6 +262,8 @@ void bitmap_daemon_work(struct mddev *mddev); int bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, int init); +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *lo, sector_t *hi, bool clear_bits); #endif #endif diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c new file mode 100644 index 000000000000..fcfc4b9b2672 --- /dev/null +++ b/drivers/md/md-cluster.c @@ -0,0 +1,965 @@ +/* + * Copyright (C) 2015, SUSE + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + */ + + +#include <linux/module.h> +#include <linux/dlm.h> +#include <linux/sched.h> +#include <linux/raid/md_p.h> +#include "md.h" +#include "bitmap.h" +#include "md-cluster.h" + +#define LVB_SIZE 64 +#define NEW_DEV_TIMEOUT 5000 + +struct dlm_lock_resource { + dlm_lockspace_t *ls; + struct dlm_lksb lksb; + char *name; /* lock name. */ + uint32_t flags; /* flags to pass to dlm_lock() */ + struct completion completion; /* completion for synchronized locking */ + void (*bast)(void *arg, int mode); /* blocking AST function pointer*/ + struct mddev *mddev; /* pointing back to mddev. */ +}; + +struct suspend_info { + int slot; + sector_t lo; + sector_t hi; + struct list_head list; +}; + +struct resync_info { + __le64 lo; + __le64 hi; +}; + +/* md_cluster_info flags */ +#define MD_CLUSTER_WAITING_FOR_NEWDISK 1 + + +struct md_cluster_info { + /* dlm lock space and resources for clustered raid. */ + dlm_lockspace_t *lockspace; + int slot_number; + struct completion completion; + struct dlm_lock_resource *sb_lock; + struct mutex sb_mutex; + struct dlm_lock_resource *bitmap_lockres; + struct list_head suspend_list; + spinlock_t suspend_lock; + struct md_thread *recovery_thread; + unsigned long recovery_map; + /* communication loc resources */ + struct dlm_lock_resource *ack_lockres; + struct dlm_lock_resource *message_lockres; + struct dlm_lock_resource *token_lockres; + struct dlm_lock_resource *no_new_dev_lockres; + struct md_thread *recv_thread; + struct completion newdisk_completion; + unsigned long state; +}; + +enum msg_type { + METADATA_UPDATED = 0, + RESYNCING, + NEWDISK, + REMOVE, + RE_ADD, +}; + +struct cluster_msg { + int type; + int slot; + /* TODO: Unionize this for smaller footprint */ + sector_t low; + sector_t high; + char uuid[16]; + int raid_slot; +}; + +static void sync_ast(void *arg) +{ + struct dlm_lock_resource *res; + + res = (struct dlm_lock_resource *) arg; + complete(&res->completion); +} + +static int dlm_lock_sync(struct dlm_lock_resource *res, int mode) +{ + int ret = 0; + + init_completion(&res->completion); + ret = dlm_lock(res->ls, mode, &res->lksb, + res->flags, res->name, strlen(res->name), + 0, sync_ast, res, res->bast); + if (ret) + return ret; + wait_for_completion(&res->completion); + return res->lksb.sb_status; +} + +static int dlm_unlock_sync(struct dlm_lock_resource *res) +{ + return dlm_lock_sync(res, DLM_LOCK_NL); +} + +static struct dlm_lock_resource *lockres_init(struct mddev *mddev, + char *name, void (*bastfn)(void *arg, int mode), int with_lvb) +{ + struct dlm_lock_resource *res = NULL; + int ret, namelen; + struct md_cluster_info *cinfo = mddev->cluster_info; + + res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL); + if (!res) + return NULL; + res->ls = cinfo->lockspace; + res->mddev = mddev; + namelen = strlen(name); + res->name = kzalloc(namelen + 1, GFP_KERNEL); + if (!res->name) { + pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name); + goto out_err; + } + strlcpy(res->name, name, namelen + 1); + if (with_lvb) { + res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL); + if (!res->lksb.sb_lvbptr) { + pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name); + goto out_err; + } + res->flags = DLM_LKF_VALBLK; + } + + if (bastfn) + res->bast = bastfn; + + res->flags |= DLM_LKF_EXPEDITE; + + ret = dlm_lock_sync(res, DLM_LOCK_NL); + if (ret) { + pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name); + goto out_err; + } + res->flags &= ~DLM_LKF_EXPEDITE; + res->flags |= DLM_LKF_CONVERT; + + return res; +out_err: + kfree(res->lksb.sb_lvbptr); + kfree(res->name); + kfree(res); + return NULL; +} + +static void lockres_free(struct dlm_lock_resource *res) +{ + if (!res) + return; + + init_completion(&res->completion); + dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res); + wait_for_completion(&res->completion); + + kfree(res->name); + kfree(res->lksb.sb_lvbptr); + kfree(res); +} + +static char *pretty_uuid(char *dest, char *src) +{ + int i, len = 0; + + for (i = 0; i < 16; i++) { + if (i == 4 || i == 6 || i == 8 || i == 10) + len += sprintf(dest + len, "-"); + len += sprintf(dest + len, "%02x", (__u8)src[i]); + } + return dest; +} + +static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres, + sector_t lo, sector_t hi) +{ + struct resync_info *ri; + + ri = (struct resync_info *)lockres->lksb.sb_lvbptr; + ri->lo = cpu_to_le64(lo); + ri->hi = cpu_to_le64(hi); +} + +static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres) +{ + struct resync_info ri; + struct suspend_info *s = NULL; + sector_t hi = 0; + + dlm_lock_sync(lockres, DLM_LOCK_CR); + memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info)); + hi = le64_to_cpu(ri.hi); + if (ri.hi > 0) { + s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); + if (!s) + goto out; + s->hi = hi; + s->lo = le64_to_cpu(ri.lo); + } + dlm_unlock_sync(lockres); +out: + return s; +} + +static void recover_bitmaps(struct md_thread *thread) +{ + struct mddev *mddev = thread->mddev; + struct md_cluster_info *cinfo = mddev->cluster_info; + struct dlm_lock_resource *bm_lockres; + char str[64]; + int slot, ret; + struct suspend_info *s, *tmp; + sector_t lo, hi; + + while (cinfo->recovery_map) { + slot = fls64((u64)cinfo->recovery_map) - 1; + + /* Clear suspend_area associated with the bitmap */ + spin_lock_irq(&cinfo->suspend_lock); + list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) + if (slot == s->slot) { + list_del(&s->list); + kfree(s); + } + spin_unlock_irq(&cinfo->suspend_lock); + + snprintf(str, 64, "bitmap%04d", slot); + bm_lockres = lockres_init(mddev, str, NULL, 1); + if (!bm_lockres) { + pr_err("md-cluster: Cannot initialize bitmaps\n"); + goto clear_bit; + } + + ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); + if (ret) { + pr_err("md-cluster: Could not DLM lock %s: %d\n", + str, ret); + goto clear_bit; + } + ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true); + if (ret) { + pr_err("md-cluster: Could not copy data from bitmap %d\n", slot); + goto dlm_unlock; + } + if (hi > 0) { + /* TODO:Wait for current resync to get over */ + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + if (lo < mddev->recovery_cp) + mddev->recovery_cp = lo; + md_check_recovery(mddev); + } +dlm_unlock: + dlm_unlock_sync(bm_lockres); +clear_bit: + clear_bit(slot, &cinfo->recovery_map); + } +} + +static void recover_prep(void *arg) +{ +} + +static void recover_slot(void *arg, struct dlm_slot *slot) +{ + struct mddev *mddev = arg; + struct md_cluster_info *cinfo = mddev->cluster_info; + + pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n", + mddev->bitmap_info.cluster_name, + slot->nodeid, slot->slot, + cinfo->slot_number); + set_bit(slot->slot - 1, &cinfo->recovery_map); + if (!cinfo->recovery_thread) { + cinfo->recovery_thread = md_register_thread(recover_bitmaps, + mddev, "recover"); + if (!cinfo->recovery_thread) { + pr_warn("md-cluster: Could not create recovery thread\n"); + return; + } + } + md_wakeup_thread(cinfo->recovery_thread); +} + +static void recover_done(void *arg, struct dlm_slot *slots, + int num_slots, int our_slot, + uint32_t generation) +{ + struct mddev *mddev = arg; + struct md_cluster_info *cinfo = mddev->cluster_info; + + cinfo->slot_number = our_slot; + complete(&cinfo->completion); +} + +static const struct dlm_lockspace_ops md_ls_ops = { + .recover_prep = recover_prep, + .recover_slot = recover_slot, + .recover_done = recover_done, +}; + +/* + * The BAST function for the ack lock resource + * This function wakes up the receive thread in + * order to receive and process the message. + */ +static void ack_bast(void *arg, int mode) +{ + struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg; + struct md_cluster_info *cinfo = res->mddev->cluster_info; + + if (mode == DLM_LOCK_EX) + md_wakeup_thread(cinfo->recv_thread); +} + +static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot) +{ + struct suspend_info *s, *tmp; + + list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) + if (slot == s->slot) { + pr_info("%s:%d Deleting suspend_info: %d\n", + __func__, __LINE__, slot); + list_del(&s->list); + kfree(s); + break; + } +} + +static void remove_suspend_info(struct md_cluster_info *cinfo, int slot) +{ + spin_lock_irq(&cinfo->suspend_lock); + __remove_suspend_info(cinfo, slot); + spin_unlock_irq(&cinfo->suspend_lock); +} + + +static void process_suspend_info(struct md_cluster_info *cinfo, + int slot, sector_t lo, sector_t hi) +{ + struct suspend_info *s; + + if (!hi) { + remove_suspend_info(cinfo, slot); + return; + } + s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); + if (!s) + return; + s->slot = slot; + s->lo = lo; + s->hi = hi; + spin_lock_irq(&cinfo->suspend_lock); + /* Remove existing entry (if exists) before adding */ + __remove_suspend_info(cinfo, slot); + list_add(&s->list, &cinfo->suspend_list); + spin_unlock_irq(&cinfo->suspend_lock); +} + +static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) +{ + char disk_uuid[64]; + struct md_cluster_info *cinfo = mddev->cluster_info; + char event_name[] = "EVENT=ADD_DEVICE"; + char raid_slot[16]; + char *envp[] = {event_name, disk_uuid, raid_slot, NULL}; + int len; + + len = snprintf(disk_uuid, 64, "DEVICE_UUID="); + pretty_uuid(disk_uuid + len, cmsg->uuid); + snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot); + pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot); + init_completion(&cinfo->newdisk_completion); + set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); + kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp); + wait_for_completion_timeout(&cinfo->newdisk_completion, + NEW_DEV_TIMEOUT); + clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); +} + + +static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + md_reload_sb(mddev); + dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); +} + +static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot); + + if (rdev) + md_kick_rdev_from_array(rdev); + else + pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot); +} + +static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot); + + if (rdev && test_bit(Faulty, &rdev->flags)) + clear_bit(Faulty, &rdev->flags); + else + pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot); +} + +static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) +{ + switch (msg->type) { + case METADATA_UPDATED: + pr_info("%s: %d Received message: METADATA_UPDATE from %d\n", + __func__, __LINE__, msg->slot); + process_metadata_update(mddev, msg); + break; + case RESYNCING: + pr_info("%s: %d Received message: RESYNCING from %d\n", + __func__, __LINE__, msg->slot); + process_suspend_info(mddev->cluster_info, msg->slot, + msg->low, msg->high); + break; + case NEWDISK: + pr_info("%s: %d Received message: NEWDISK from %d\n", + __func__, __LINE__, msg->slot); + process_add_new_disk(mddev, msg); + break; + case REMOVE: + pr_info("%s: %d Received REMOVE from %d\n", + __func__, __LINE__, msg->slot); + process_remove_disk(mddev, msg); + break; + case RE_ADD: + pr_info("%s: %d Received RE_ADD from %d\n", + __func__, __LINE__, msg->slot); + process_readd_disk(mddev, msg); + break; + default: + pr_warn("%s:%d Received unknown message from %d\n", + __func__, __LINE__, msg->slot); + } +} + +/* + * thread for receiving message + */ +static void recv_daemon(struct md_thread *thread) +{ + struct md_cluster_info *cinfo = thread->mddev->cluster_info; + struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres; + struct dlm_lock_resource *message_lockres = cinfo->message_lockres; + struct cluster_msg msg; + + /*get CR on Message*/ + if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) { + pr_err("md/raid1:failed to get CR on MESSAGE\n"); + return; + } + + /* read lvb and wake up thread to process this message_lockres */ + memcpy(&msg, message_lockres->lksb.sb_lvbptr, sizeof(struct cluster_msg)); + process_recvd_msg(thread->mddev, &msg); + + /*release CR on ack_lockres*/ + dlm_unlock_sync(ack_lockres); + /*up-convert to EX on message_lockres*/ + dlm_lock_sync(message_lockres, DLM_LOCK_EX); + /*get CR on ack_lockres again*/ + dlm_lock_sync(ack_lockres, DLM_LOCK_CR); + /*release CR on message_lockres*/ + dlm_unlock_sync(message_lockres); +} + +/* lock_comm() + * Takes the lock on the TOKEN lock resource so no other + * node can communicate while the operation is underway. + */ +static int lock_comm(struct md_cluster_info *cinfo) +{ + int error; + + error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX); + if (error) + pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n", + __func__, __LINE__, error); + return error; +} + +static void unlock_comm(struct md_cluster_info *cinfo) +{ + dlm_unlock_sync(cinfo->token_lockres); +} + +/* __sendmsg() + * This function performs the actual sending of the message. This function is + * usually called after performing the encompassing operation + * The function: + * 1. Grabs the message lockresource in EX mode + * 2. Copies the message to the message LVB + * 3. Downconverts message lockresource to CR + * 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes + * and the other nodes read the message. The thread will wait here until all other + * nodes have released ack lock resource. + * 5. Downconvert ack lockresource to CR + */ +static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) +{ + int error; + int slot = cinfo->slot_number - 1; + + cmsg->slot = cpu_to_le32(slot); + /*get EX on Message*/ + error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX); + if (error) { + pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error); + goto failed_message; + } + + memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg, + sizeof(struct cluster_msg)); + /*down-convert EX to CR on Message*/ + error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CR); + if (error) { + pr_err("md-cluster: failed to convert EX to CR on MESSAGE(%d)\n", + error); + goto failed_message; + } + + /*up-convert CR to EX on Ack*/ + error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_EX); + if (error) { + pr_err("md-cluster: failed to convert CR to EX on ACK(%d)\n", + error); + goto failed_ack; + } + + /*down-convert EX to CR on Ack*/ + error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR); + if (error) { + pr_err("md-cluster: failed to convert EX to CR on ACK(%d)\n", + error); + goto failed_ack; + } + +failed_ack: + dlm_unlock_sync(cinfo->message_lockres); +failed_message: + return error; +} + +static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) +{ + int ret; + + lock_comm(cinfo); + ret = __sendmsg(cinfo, cmsg); + unlock_comm(cinfo); + return ret; +} + +static int gather_all_resync_info(struct mddev *mddev, int total_slots) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + int i, ret = 0; + struct dlm_lock_resource *bm_lockres; + struct suspend_info *s; + char str[64]; + + + for (i = 0; i < total_slots; i++) { + memset(str, '\0', 64); + snprintf(str, 64, "bitmap%04d", i); + bm_lockres = lockres_init(mddev, str, NULL, 1); + if (!bm_lockres) + return -ENOMEM; + if (i == (cinfo->slot_number - 1)) + continue; + + bm_lockres->flags |= DLM_LKF_NOQUEUE; + ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); + if (ret == -EAGAIN) { + memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE); + s = read_resync_info(mddev, bm_lockres); + if (s) { + pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n", + __func__, __LINE__, + (unsigned long long) s->lo, + (unsigned long long) s->hi, i); + spin_lock_irq(&cinfo->suspend_lock); + s->slot = i; + list_add(&s->list, &cinfo->suspend_list); + spin_unlock_irq(&cinfo->suspend_lock); + } + ret = 0; + lockres_free(bm_lockres); + continue; + } + if (ret) + goto out; + /* TODO: Read the disk bitmap sb and check if it needs recovery */ + dlm_unlock_sync(bm_lockres); + lockres_free(bm_lockres); + } +out: + return ret; +} + +static int join(struct mddev *mddev, int nodes) +{ + struct md_cluster_info *cinfo; + int ret, ops_rv; + char str[64]; + + if (!try_module_get(THIS_MODULE)) + return -ENOENT; + + cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL); + if (!cinfo) + return -ENOMEM; + + init_completion(&cinfo->completion); + + mutex_init(&cinfo->sb_mutex); + mddev->cluster_info = cinfo; + + memset(str, 0, 64); + pretty_uuid(str, mddev->uuid); + ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name, + DLM_LSFL_FS, LVB_SIZE, + &md_ls_ops, mddev, &ops_rv, &cinfo->lockspace); + if (ret) + goto err; + wait_for_completion(&cinfo->completion); + if (nodes < cinfo->slot_number) { + pr_err("md-cluster: Slot allotted(%d) is greater than available slots(%d).", + cinfo->slot_number, nodes); + ret = -ERANGE; + goto err; + } + cinfo->sb_lock = lockres_init(mddev, "cmd-super", + NULL, 0); + if (!cinfo->sb_lock) { + ret = -ENOMEM; + goto err; + } + /* Initiate the communication resources */ + ret = -ENOMEM; + cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv"); + if (!cinfo->recv_thread) { + pr_err("md-cluster: cannot allocate memory for recv_thread!\n"); + goto err; + } + cinfo->message_lockres = lockres_init(mddev, "message", NULL, 1); + if (!cinfo->message_lockres) + goto err; + cinfo->token_lockres = lockres_init(mddev, "token", NULL, 0); + if (!cinfo->token_lockres) + goto err; + cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0); + if (!cinfo->ack_lockres) + goto err; + cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0); + if (!cinfo->no_new_dev_lockres) + goto err; + + /* get sync CR lock on ACK. */ + if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR)) + pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n", + ret); + /* get sync CR lock on no-new-dev. */ + if (dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR)) + pr_err("md-cluster: failed to get a sync CR lock on no-new-dev!(%d)\n", ret); + + + pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number); + snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1); + cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1); + if (!cinfo->bitmap_lockres) + goto err; + if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) { + pr_err("Failed to get bitmap lock\n"); + ret = -EINVAL; + goto err; + } + + INIT_LIST_HEAD(&cinfo->suspend_list); + spin_lock_init(&cinfo->suspend_lock); + + ret = gather_all_resync_info(mddev, nodes); + if (ret) + goto err; + + return 0; +err: + lockres_free(cinfo->message_lockres); + lockres_free(cinfo->token_lockres); + lockres_free(cinfo->ack_lockres); + lockres_free(cinfo->no_new_dev_lockres); + lockres_free(cinfo->bitmap_lockres); + lockres_free(cinfo->sb_lock); + if (cinfo->lockspace) + dlm_release_lockspace(cinfo->lockspace, 2); + mddev->cluster_info = NULL; + kfree(cinfo); + module_put(THIS_MODULE); + return ret; +} + +static int leave(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + if (!cinfo) + return 0; + md_unregister_thread(&cinfo->recovery_thread); + md_unregister_thread(&cinfo->recv_thread); + lockres_free(cinfo->message_lockres); + lockres_free(cinfo->token_lockres); + lockres_free(cinfo->ack_lockres); + lockres_free(cinfo->no_new_dev_lockres); + lockres_free(cinfo->sb_lock); + lockres_free(cinfo->bitmap_lockres); + dlm_release_lockspace(cinfo->lockspace, 2); + return 0; +} + +/* slot_number(): Returns the MD slot number to use + * DLM starts the slot numbers from 1, wheras cluster-md + * wants the number to be from zero, so we deduct one + */ +static int slot_number(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + return cinfo->slot_number - 1; +} + +static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi); + /* Re-acquire the lock to refresh LVB */ + dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW); +} + +static int metadata_update_start(struct mddev *mddev) +{ + return lock_comm(mddev->cluster_info); +} + +static int metadata_update_finish(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int ret; + + memset(&cmsg, 0, sizeof(cmsg)); + cmsg.type = cpu_to_le32(METADATA_UPDATED); + ret = __sendmsg(cinfo, &cmsg); + unlock_comm(cinfo); + return ret; +} + +static int metadata_update_cancel(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + return dlm_unlock_sync(cinfo->token_lockres); +} + +static int resync_send(struct mddev *mddev, enum msg_type type, + sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int slot = cinfo->slot_number - 1; + + pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__, + (unsigned long long)lo, + (unsigned long long)hi); + resync_info_update(mddev, lo, hi); + cmsg.type = cpu_to_le32(type); + cmsg.slot = cpu_to_le32(slot); + cmsg.low = cpu_to_le64(lo); + cmsg.high = cpu_to_le64(hi); + return sendmsg(cinfo, &cmsg); +} + +static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi) +{ + pr_info("%s:%d\n", __func__, __LINE__); + return resync_send(mddev, RESYNCING, lo, hi); +} + +static void resync_finish(struct mddev *mddev) +{ + pr_info("%s:%d\n", __func__, __LINE__); + resync_send(mddev, RESYNCING, 0, 0); +} + +static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; + struct suspend_info *s; + + spin_lock_irq(&cinfo->suspend_lock); + if (list_empty(&cinfo->suspend_list)) + goto out; + list_for_each_entry(s, &cinfo->suspend_list, list) + if (hi > s->lo && lo < s->hi) { + ret = 1; + break; + } +out: + spin_unlock_irq(&cinfo->suspend_lock); + return ret; +} + +static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int ret = 0; + struct mdp_superblock_1 *sb = page_address(rdev->sb_page); + char *uuid = sb->device_uuid; + + memset(&cmsg, 0, sizeof(cmsg)); + cmsg.type = cpu_to_le32(NEWDISK); + memcpy(cmsg.uuid, uuid, 16); + cmsg.raid_slot = rdev->desc_nr; + lock_comm(cinfo); + ret = __sendmsg(cinfo, &cmsg); + if (ret) + return ret; + cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE; + ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX); + cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE; + /* Some node does not "see" the device */ + if (ret == -EAGAIN) + ret = -ENOENT; + else + dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); + return ret; +} + +static int add_new_disk_finish(struct mddev *mddev) +{ + struct cluster_msg cmsg; + struct md_cluster_info *cinfo = mddev->cluster_info; + int ret; + /* Write sb and inform others */ + md_update_sb(mddev, 1); + cmsg.type = METADATA_UPDATED; + ret = __sendmsg(cinfo, &cmsg); + unlock_comm(cinfo); + return ret; +} + +static int new_disk_ack(struct mddev *mddev, bool ack) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) { + pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev)); + return -EINVAL; + } + + if (ack) + dlm_unlock_sync(cinfo->no_new_dev_lockres); + complete(&cinfo->newdisk_completion); + return 0; +} + +static int remove_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct cluster_msg cmsg; + struct md_cluster_info *cinfo = mddev->cluster_info; + cmsg.type = REMOVE; + cmsg.raid_slot = rdev->desc_nr; + return __sendmsg(cinfo, &cmsg); +} + +static int gather_bitmaps(struct md_rdev *rdev) +{ + int sn, err; + sector_t lo, hi; + struct cluster_msg cmsg; + struct mddev *mddev = rdev->mddev; + struct md_cluster_info *cinfo = mddev->cluster_info; + + cmsg.type = RE_ADD; + cmsg.raid_slot = rdev->desc_nr; + err = sendmsg(cinfo, &cmsg); + if (err) + goto out; + + for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) { + if (sn == (cinfo->slot_number - 1)) + continue; + err = bitmap_copy_from_slot(mddev, sn, &lo, &hi, false); + if (err) { + pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn); + goto out; + } + if ((hi > 0) && (lo < mddev->recovery_cp)) + mddev->recovery_cp = lo; + } +out: + return err; +} + +static struct md_cluster_operations cluster_ops = { + .join = join, + .leave = leave, + .slot_number = slot_number, + .resync_info_update = resync_info_update, + .resync_start = resync_start, + .resync_finish = resync_finish, + .metadata_update_start = metadata_update_start, + .metadata_update_finish = metadata_update_finish, + .metadata_update_cancel = metadata_update_cancel, + .area_resyncing = area_resyncing, + .add_new_disk_start = add_new_disk_start, + .add_new_disk_finish = add_new_disk_finish, + .new_disk_ack = new_disk_ack, + .remove_disk = remove_disk, + .gather_bitmaps = gather_bitmaps, +}; + +static int __init cluster_init(void) +{ + pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n"); + pr_info("Registering Cluster MD functions\n"); + register_md_cluster_operations(&cluster_ops, THIS_MODULE); + return 0; +} + +static void cluster_exit(void) +{ + unregister_md_cluster_operations(); +} + +module_init(cluster_init); +module_exit(cluster_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Clustering support for MD"); diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h new file mode 100644 index 000000000000..6817ee00e053 --- /dev/null +++ b/drivers/md/md-cluster.h @@ -0,0 +1,29 @@ + + +#ifndef _MD_CLUSTER_H +#define _MD_CLUSTER_H + +#include "md.h" + +struct mddev; +struct md_rdev; + +struct md_cluster_operations { + int (*join)(struct mddev *mddev, int nodes); + int (*leave)(struct mddev *mddev); + int (*slot_number)(struct mddev *mddev); + void (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi); + int (*resync_start)(struct mddev *mddev, sector_t lo, sector_t hi); + void (*resync_finish)(struct mddev *mddev); + int (*metadata_update_start)(struct mddev *mddev); + int (*metadata_update_finish)(struct mddev *mddev); + int (*metadata_update_cancel)(struct mddev *mddev); + int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi); + int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev); + int (*add_new_disk_finish)(struct mddev *mddev); + int (*new_disk_ack)(struct mddev *mddev, bool ack); + int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev); + int (*gather_bitmaps)(struct md_rdev *rdev); +}; + +#endif /* _MD_CLUSTER_H */ diff --git a/drivers/md/md.c b/drivers/md/md.c index e6178787ce3d..d4f31e195e26 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -53,6 +53,7 @@ #include <linux/slab.h> #include "md.h" #include "bitmap.h" +#include "md-cluster.h" #ifndef MODULE static void autostart_arrays(int part); @@ -66,6 +67,11 @@ static void autostart_arrays(int part); static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); +struct md_cluster_operations *md_cluster_ops; +EXPORT_SYMBOL(md_cluster_ops); +struct module *md_cluster_mod; +EXPORT_SYMBOL(md_cluster_mod); + static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; static struct workqueue_struct *md_misc_wq; @@ -640,7 +646,7 @@ void mddev_unlock(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_unlock); -static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) +struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr) { struct md_rdev *rdev; @@ -650,6 +656,7 @@ static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) return NULL; } +EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu); static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev) { @@ -2047,11 +2054,11 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) int choice = 0; if (mddev->pers) choice = mddev->raid_disks; - while (find_rdev_nr_rcu(mddev, choice)) + while (md_find_rdev_nr_rcu(mddev, choice)) choice++; rdev->desc_nr = choice; } else { - if (find_rdev_nr_rcu(mddev, rdev->desc_nr)) { + if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) { rcu_read_unlock(); return -EBUSY; } @@ -2166,11 +2173,12 @@ static void export_rdev(struct md_rdev *rdev) kobject_put(&rdev->kobj); } -static void kick_rdev_from_array(struct md_rdev *rdev) +void md_kick_rdev_from_array(struct md_rdev *rdev) { unbind_rdev_from_array(rdev); export_rdev(rdev); } +EXPORT_SYMBOL_GPL(md_kick_rdev_from_array); static void export_array(struct mddev *mddev) { @@ -2179,7 +2187,7 @@ static void export_array(struct mddev *mddev) while (!list_empty(&mddev->disks)) { rdev = list_first_entry(&mddev->disks, struct md_rdev, same_set); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } mddev->raid_disks = 0; mddev->major_version = 0; @@ -2208,7 +2216,7 @@ static void sync_sbs(struct mddev *mddev, int nospares) } } -static void md_update_sb(struct mddev *mddev, int force_change) +void md_update_sb(struct mddev *mddev, int force_change) { struct md_rdev *rdev; int sync_req; @@ -2369,6 +2377,37 @@ repeat: wake_up(&rdev->blocked_wait); } } +EXPORT_SYMBOL(md_update_sb); + +static int add_bound_rdev(struct md_rdev *rdev) +{ + struct mddev *mddev = rdev->mddev; + int err = 0; + + if (!mddev->pers->hot_remove_disk) { + /* If there is hot_add_disk but no hot_remove_disk + * then added disks for geometry changes, + * and should be added immediately. + */ + super_types[mddev->major_version]. + validate_super(mddev, rdev); + err = mddev->pers->hot_add_disk(mddev, rdev); + if (err) { + unbind_rdev_from_array(rdev); + export_rdev(rdev); + return err; + } + } + sysfs_notify_dirent_safe(rdev->sysfs_state); + + set_bit(MD_CHANGE_DEVS, &mddev->flags); + if (mddev->degraded) + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_new_event(mddev); + md_wakeup_thread(mddev->thread); + return 0; +} /* words written to sysfs files may, or may not, be \n terminated. * We want to accept with case. For this we use cmd_match. @@ -2471,10 +2510,16 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = -EBUSY; else { struct mddev *mddev = rdev->mddev; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + md_kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (mddev->pers) md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); err = 0; } } else if (cmd_match(buf, "writemostly")) { @@ -2553,6 +2598,21 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) clear_bit(Replacement, &rdev->flags); err = 0; } + } else if (cmd_match(buf, "re-add")) { + if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1)) { + /* clear_bit is performed _after_ all the devices + * have their local Faulty bit cleared. If any writes + * happen in the meantime in the local node, they + * will land in the local bitmap, which will be synced + * by this node eventually + */ + if (!mddev_is_clustered(rdev->mddev) || + (err = md_cluster_ops->gather_bitmaps(rdev)) == 0) { + clear_bit(Faulty, &rdev->flags); + err = add_bound_rdev(rdev); + } + } else + err = -EBUSY; } if (!err) sysfs_notify_dirent_safe(rdev->sysfs_state); @@ -3127,7 +3187,7 @@ static void analyze_sbs(struct mddev *mddev) "md: fatal superblock inconsistency in %s" " -- removing from array\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } super_types[mddev->major_version]. @@ -3142,18 +3202,27 @@ static void analyze_sbs(struct mddev *mddev) "md: %s: %s: only %d devices permitted\n", mdname(mddev), bdevname(rdev->bdev, b), mddev->max_disks); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } - if (rdev != freshest) + if (rdev != freshest) { if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { printk(KERN_WARNING "md: kicking non-fresh %s" " from array!\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } + /* No device should have a Candidate flag + * when reading devices + */ + if (test_bit(Candidate, &rdev->flags)) { + pr_info("md: kicking Cluster Candidate %s from array!\n", + bdevname(rdev->bdev, b)); + md_kick_rdev_from_array(rdev); + } + } if (mddev->level == LEVEL_MULTIPATH) { rdev->desc_nr = i++; rdev->raid_disk = rdev->desc_nr; @@ -4008,8 +4077,12 @@ size_store(struct mddev *mddev, const char *buf, size_t len) if (err) return err; if (mddev->pers) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); err = update_size(mddev, sectors); md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } else { if (mddev->dev_sectors == 0 || mddev->dev_sectors > sectors) @@ -4354,7 +4427,6 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long min; int err; - int chunk; if (kstrtoull(buf, 10, &min)) return -EINVAL; @@ -4368,16 +4440,8 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) goto out_unlock; - /* Must be a multiple of chunk_size */ - chunk = mddev->chunk_sectors; - if (chunk) { - sector_t temp = min; - - err = -EINVAL; - if (sector_div(temp, chunk)) - goto out_unlock; - } - mddev->resync_min = min; + /* Round down to multiple of 4K for safety */ + mddev->resync_min = round_down(min, 8); err = 0; out_unlock: @@ -5077,10 +5141,16 @@ int md_run(struct mddev *mddev) } if (err == 0 && pers->sync_request && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { - err = bitmap_create(mddev); - if (err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) { + err = PTR_ERR(bitmap); printk(KERN_ERR "%s: failed to create bitmap (%d)\n", mdname(mddev), err); + } else + mddev->bitmap = bitmap; + } if (err) { mddev_detach(mddev); @@ -5232,6 +5302,8 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); flush_workqueue(md_misc_wq); if (mddev->sync_thread) { @@ -5250,6 +5322,8 @@ static void __md_stop_writes(struct mddev *mddev) mddev->in_sync = 1; md_update_sb(mddev, 1); } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } void md_stop_writes(struct mddev *mddev) @@ -5636,6 +5710,8 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.state = (1<<MD_SB_CLEAN); if (mddev->bitmap && mddev->bitmap_info.offset) info.state |= (1<<MD_SB_BITMAP_PRESENT); + if (mddev_is_clustered(mddev)) + info.state |= (1<<MD_SB_CLUSTERED); info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; @@ -5691,7 +5767,7 @@ static int get_disk_info(struct mddev *mddev, void __user * arg) return -EFAULT; rcu_read_lock(); - rdev = find_rdev_nr_rcu(mddev, info.number); + rdev = md_find_rdev_nr_rcu(mddev, info.number); if (rdev) { info.major = MAJOR(rdev->bdev->bd_dev); info.minor = MINOR(rdev->bdev->bd_dev); @@ -5724,6 +5800,13 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); + if (mddev_is_clustered(mddev) && + !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { + pr_err("%s: Cannot add to clustered mddev.\n", + mdname(mddev)); + return -EINVAL; + } + if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) return -EOVERFLOW; @@ -5810,31 +5893,38 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) else clear_bit(WriteMostly, &rdev->flags); + /* + * check whether the device shows up in other nodes + */ + if (mddev_is_clustered(mddev)) { + if (info->state & (1 << MD_DISK_CANDIDATE)) { + /* Through --cluster-confirm */ + set_bit(Candidate, &rdev->flags); + err = md_cluster_ops->new_disk_ack(mddev, true); + if (err) { + export_rdev(rdev); + return err; + } + } else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { + /* --add initiated by this node */ + err = md_cluster_ops->add_new_disk_start(mddev, rdev); + if (err) { + md_cluster_ops->add_new_disk_finish(mddev); + export_rdev(rdev); + return err; + } + } + } + rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); - if (!err && !mddev->pers->hot_remove_disk) { - /* If there is hot_add_disk but no hot_remove_disk - * then added disks for geometry changes, - * and should be added immediately. - */ - super_types[mddev->major_version]. - validate_super(mddev, rdev); - err = mddev->pers->hot_add_disk(mddev, rdev); - if (err) - unbind_rdev_from_array(rdev); - } if (err) export_rdev(rdev); else - sysfs_notify_dirent_safe(rdev->sysfs_state); - - set_bit(MD_CHANGE_DEVS, &mddev->flags); - if (mddev->degraded) - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (!err) - md_new_event(mddev); - md_wakeup_thread(mddev->thread); + err = add_bound_rdev(rdev); + if (mddev_is_clustered(mddev) && + (info->state & (1 << MD_DISK_CLUSTER_ADD))) + md_cluster_ops->add_new_disk_finish(mddev); return err; } @@ -5895,18 +5985,29 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) if (!rdev) return -ENXIO; + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); + clear_bit(Blocked, &rdev->flags); remove_and_add_spares(mddev, rdev); if (rdev->raid_disk >= 0) goto busy; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + + md_kick_rdev_from_array(rdev); md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return 0; busy: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n", bdevname(rdev->bdev,b), mdname(mddev)); return -EBUSY; @@ -5956,12 +6057,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) err = -EINVAL; goto abort_export; } + + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); clear_bit(In_sync, &rdev->flags); rdev->desc_nr = -1; rdev->saved_raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (err) - goto abort_export; + goto abort_clustered; /* * The rest should better be atomic, we can have disk failures @@ -5972,6 +6076,8 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); /* * Kick recovery, maybe this spare has to be added to the * array immediately. @@ -5981,6 +6087,9 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_new_event(mddev); return 0; +abort_clustered: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); abort_export: export_rdev(rdev); return err; @@ -6038,9 +6147,14 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (mddev->pers) { mddev->pers->quiesce(mddev, 1); if (fd >= 0) { - err = bitmap_create(mddev); - if (!err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; err = bitmap_load(mddev); + } else + err = PTR_ERR(bitmap); } if (fd < 0 || err) { bitmap_destroy(mddev); @@ -6293,6 +6407,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) return rv; } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) rv = update_size(mddev, (sector_t)info->size * 2); @@ -6300,33 +6416,49 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) { - if (mddev->pers->quiesce == NULL || mddev->thread == NULL) - return -EINVAL; - if (mddev->recovery || mddev->sync_thread) - return -EBUSY; + if (mddev->pers->quiesce == NULL || mddev->thread == NULL) { + rv = -EINVAL; + goto err; + } + if (mddev->recovery || mddev->sync_thread) { + rv = -EBUSY; + goto err; + } if (info->state & (1<<MD_SB_BITMAP_PRESENT)) { + struct bitmap *bitmap; /* add the bitmap */ - if (mddev->bitmap) - return -EEXIST; - if (mddev->bitmap_info.default_offset == 0) - return -EINVAL; + if (mddev->bitmap) { + rv = -EEXIST; + goto err; + } + if (mddev->bitmap_info.default_offset == 0) { + rv = -EINVAL; + goto err; + } mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; mddev->pers->quiesce(mddev, 1); - rv = bitmap_create(mddev); - if (!rv) + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; rv = bitmap_load(mddev); + } else + rv = PTR_ERR(bitmap); if (rv) bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); } else { /* remove the bitmap */ - if (!mddev->bitmap) - return -ENOENT; - if (mddev->bitmap->storage.file) - return -EINVAL; + if (!mddev->bitmap) { + rv = -ENOENT; + goto err; + } + if (mddev->bitmap->storage.file) { + rv = -EINVAL; + goto err; + } mddev->pers->quiesce(mddev, 1); bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); @@ -6334,6 +6466,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } } md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return rv; +err: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); return rv; } @@ -6393,6 +6531,7 @@ static inline bool md_ioctl_valid(unsigned int cmd) case SET_DISK_FAULTY: case STOP_ARRAY: case STOP_ARRAY_RO: + case CLUSTERED_DISK_NACK: return true; default: return false; @@ -6665,6 +6804,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } + case CLUSTERED_DISK_NACK: + if (mddev_is_clustered(mddev)) + md_cluster_ops->new_disk_ack(mddev, false); + else + err = -EINVAL; + goto unlock; + case HOT_ADD_DISK: err = hot_add_disk(mddev, new_decode_dev(arg)); goto unlock; @@ -7238,6 +7384,55 @@ int unregister_md_personality(struct md_personality *p) } EXPORT_SYMBOL(unregister_md_personality); +int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module) +{ + if (md_cluster_ops != NULL) + return -EALREADY; + spin_lock(&pers_lock); + md_cluster_ops = ops; + md_cluster_mod = module; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(register_md_cluster_operations); + +int unregister_md_cluster_operations(void) +{ + spin_lock(&pers_lock); + md_cluster_ops = NULL; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(unregister_md_cluster_operations); + +int md_setup_cluster(struct mddev *mddev, int nodes) +{ + int err; + + err = request_module("md-cluster"); + if (err) { + pr_err("md-cluster module not found.\n"); + return err; + } + + spin_lock(&pers_lock); + if (!md_cluster_ops || !try_module_get(md_cluster_mod)) { + spin_unlock(&pers_lock); + return -ENOENT; + } + spin_unlock(&pers_lock); + + return md_cluster_ops->join(mddev, nodes); +} + +void md_cluster_stop(struct mddev *mddev) +{ + if (!md_cluster_ops) + return; + md_cluster_ops->leave(mddev); + module_put(md_cluster_mod); +} + static int is_mddev_idle(struct mddev *mddev, int init) { struct md_rdev *rdev; @@ -7375,7 +7570,11 @@ int md_allow_write(struct mddev *mddev) mddev->safemode == 0) mddev->safemode = 1; spin_unlock(&mddev->lock); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); sysfs_notify_dirent_safe(mddev->sysfs_state); } else spin_unlock(&mddev->lock); @@ -7576,6 +7775,9 @@ void md_do_sync(struct md_thread *thread) md_new_event(mddev); update_time = jiffies; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_start(mddev, j, max_sectors); + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7618,8 +7820,7 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; - sectors = mddev->pers->sync_request(mddev, j, &skipped, - currspeed < speed_min(mddev)); + sectors = mddev->pers->sync_request(mddev, j, &skipped); if (sectors == 0) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); break; @@ -7636,6 +7837,8 @@ void md_do_sync(struct md_thread *thread) j += sectors; if (j > 2) mddev->curr_resync = j; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_info_update(mddev, j, max_sectors); mddev->curr_mark_cnt = io_sectors; if (last_check == 0) /* this is the earliest that rebuild will be @@ -7677,11 +7880,18 @@ void md_do_sync(struct md_thread *thread) /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > speed_min(mddev)) { - if ((currspeed > speed_max(mddev)) || - !is_mddev_idle(mddev, 0)) { + if (currspeed > speed_max(mddev)) { msleep(500); goto repeat; } + if (!is_mddev_idle(mddev, 0)) { + /* + * Give other IO more of a chance. + * The faster the devices, the less we wait. + */ + wait_event(mddev->recovery_wait, + !atomic_read(&mddev->recovery_active)); + } } } printk(KERN_INFO "md: %s: %s %s.\n",mdname(mddev), desc, @@ -7694,7 +7904,10 @@ void md_do_sync(struct md_thread *thread) wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ - mddev->pers->sync_request(mddev, max_sectors, &skipped, 1); + mddev->pers->sync_request(mddev, max_sectors, &skipped); + + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_finish(mddev); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && mddev->curr_resync > 2) { @@ -7925,8 +8138,13 @@ void md_check_recovery(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_state); } - if (mddev->flags & MD_UPDATE_SB_FLAGS) + if (mddev->flags & MD_UPDATE_SB_FLAGS) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { @@ -8024,6 +8242,8 @@ void md_reap_sync_thread(struct mddev *mddev) set_bit(MD_CHANGE_DEVS, &mddev->flags); } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->pers->finish_reshape) mddev->pers->finish_reshape(mddev); @@ -8036,6 +8256,8 @@ void md_reap_sync_thread(struct mddev *mddev) rdev->saved_raid_disk = -1; md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); @@ -8656,6 +8878,28 @@ err_wq: return ret; } +void md_reload_sb(struct mddev *mddev) +{ + struct md_rdev *rdev, *tmp; + + rdev_for_each_safe(rdev, tmp, mddev) { + rdev->sb_loaded = 0; + ClearPageUptodate(rdev->sb_page); + } + mddev->raid_disks = 0; + analyze_sbs(mddev); + rdev_for_each_safe(rdev, tmp, mddev) { + struct mdp_superblock_1 *sb = page_address(rdev->sb_page); + /* since we don't write to faulty devices, we figure out if the + * disk is faulty by comparing events + */ + if (mddev->events > sb->events) + set_bit(Faulty, &rdev->flags); + } + +} +EXPORT_SYMBOL(md_reload_sb); + #ifndef MODULE /* diff --git a/drivers/md/md.h b/drivers/md/md.h index 318ca8fd430f..4046a6c6f223 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -23,6 +23,7 @@ #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> +#include "md-cluster.h" #define MaxSector (~(sector_t)0) @@ -170,6 +171,10 @@ enum flag_bits { * a want_replacement device with same * raid_disk number. */ + Candidate, /* For clustered environments only: + * This device is seen locally but not + * by the whole cluster + */ }; #define BB_LEN_MASK (0x00000000000001FFULL) @@ -202,6 +207,8 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern void md_ack_all_badblocks(struct badblocks *bb); +struct md_cluster_info; + struct mddev { void *private; struct md_personality *pers; @@ -430,6 +437,8 @@ struct mddev { unsigned long daemon_sleep; /* how many jiffies between updates? */ unsigned long max_write_behind; /* write-behind mode */ int external; + int nodes; /* Maximum number of nodes in the cluster */ + char cluster_name[64]; /* Name of the cluster */ } bitmap_info; atomic_t max_corr_read_errors; /* max read retries */ @@ -448,6 +457,7 @@ struct mddev { struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); + struct md_cluster_info *cluster_info; }; static inline int __must_check mddev_lock(struct mddev *mddev) @@ -496,7 +506,7 @@ struct md_personality int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*spare_active) (struct mddev *mddev); - sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster); + sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped); int (*resize) (struct mddev *mddev, sector_t sectors); sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); int (*check_reshape) (struct mddev *mddev); @@ -608,6 +618,11 @@ static inline void safe_put_page(struct page *p) extern int register_md_personality(struct md_personality *p); extern int unregister_md_personality(struct md_personality *p); +extern int register_md_cluster_operations(struct md_cluster_operations *ops, + struct module *module); +extern int unregister_md_cluster_operations(void); +extern int md_setup_cluster(struct mddev *mddev, int nodes); +extern void md_cluster_stop(struct mddev *mddev); extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, @@ -654,6 +669,10 @@ extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev); extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule); +extern void md_reload_sb(struct mddev *mddev); +extern void md_update_sb(struct mddev *mddev, int force); +extern void md_kick_rdev_from_array(struct md_rdev * rdev); +struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr); static inline int mddev_check_plugged(struct mddev *mddev) { return !!blk_check_plugged(md_unplug, mddev, @@ -669,4 +688,9 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) } } +extern struct md_cluster_operations *md_cluster_ops; +static inline int mddev_is_clustered(struct mddev *mddev) +{ + return mddev->cluster_info && mddev->bitmap_info.nodes > 1; +} #endif /* _MD_MD_H */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 3b5d7f704aa3..2cb59a641cd2 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -271,14 +271,16 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) goto abort; } - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - blk_queue_io_opt(mddev->queue, - (mddev->chunk_sectors << 9) * mddev->raid_disks); - - if (!discard_supported) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + if (mddev->queue) { + blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); + blk_queue_io_opt(mddev->queue, + (mddev->chunk_sectors << 9) * mddev->raid_disks); + + if (!discard_supported) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + } pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -429,9 +431,12 @@ static int raid0_run(struct mddev *mddev) } if (md_check_no_bitmap(mddev)) return -EINVAL; - blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + + if (mddev->queue) { + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + } /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { @@ -448,16 +453,17 @@ static int raid0_run(struct mddev *mddev) printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n", mdname(mddev), (unsigned long long)mddev->array_sectors); - /* calculate the max read-ahead size. - * For read-ahead of large files to be effective, we need to - * readahead at least twice a whole stripe. i.e. number of devices - * multiplied by chunk size times 2. - * If an individual device has an ra_pages greater than the - * chunk size, then we will not drive that device as hard as it - * wants. We consider this a configuration error: a larger - * chunksize should be used in that case. - */ - { + + if (mddev->queue) { + /* calculate the max read-ahead size. + * For read-ahead of large files to be effective, we need to + * readahead at least twice a whole stripe. i.e. number of devices + * multiplied by chunk size times 2. + * If an individual device has an ra_pages greater than the + * chunk size, then we will not drive that device as hard as it + * wants. We consider this a configuration error: a larger + * chunksize should be used in that case. + */ int stripe = mddev->raid_disks * (mddev->chunk_sectors << 9) / PAGE_SIZE; if (mddev->queue->backing_dev_info.ra_pages < 2* stripe) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d34e238afa54..9157a29c8dbf 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -539,7 +539,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect has_nonrot_disk = 0; choose_next_idle = 0; - choose_first = (conf->mddev->recovery_cp < this_sector + sectors); + if ((conf->mddev->recovery_cp < this_sector + sectors) || + (mddev_is_clustered(conf->mddev) && + md_cluster_ops->area_resyncing(conf->mddev, this_sector, + this_sector + sectors))) + choose_first = 1; + else + choose_first = 0; for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { sector_t dist; @@ -1102,8 +1108,10 @@ static void make_request(struct mddev *mddev, struct bio * bio) md_write_start(mddev, bio); /* wait on superblock update early */ if (bio_data_dir(bio) == WRITE && - bio_end_sector(bio) > mddev->suspend_lo && - bio->bi_iter.bi_sector < mddev->suspend_hi) { + ((bio_end_sector(bio) > mddev->suspend_lo && + bio->bi_iter.bi_sector < mddev->suspend_hi) || + (mddev_is_clustered(mddev) && + md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) { /* As the suspend_* range is controlled by * userspace, we want an interruptible * wait. @@ -1114,7 +1122,10 @@ static void make_request(struct mddev *mddev, struct bio * bio) prepare_to_wait(&conf->wait_barrier, &w, TASK_INTERRUPTIBLE); if (bio_end_sector(bio) <= mddev->suspend_lo || - bio->bi_iter.bi_sector >= mddev->suspend_hi) + bio->bi_iter.bi_sector >= mddev->suspend_hi || + (mddev_is_clustered(mddev) && + !md_cluster_ops->area_resyncing(mddev, + bio->bi_iter.bi_sector, bio_end_sector(bio)))) break; schedule(); } @@ -1561,6 +1572,7 @@ static int raid1_spare_active(struct mddev *mddev) struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; if (repl + && !test_bit(Candidate, &repl->flags) && repl->recovery_offset == MaxSector && !test_bit(Faulty, &repl->flags) && !test_and_set_bit(In_sync, &repl->flags)) { @@ -2468,7 +2480,7 @@ static int init_resync(struct r1conf *conf) * that can be installed to exclude normal IO requests. */ -static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped) { struct r1conf *conf = mddev->private; struct r1bio *r1_bio; @@ -2521,13 +2533,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp *skipped = 1; return sync_blocks; } - /* - * If there is non-resync activity waiting for a turn, - * and resync is going fast enough, - * then let it though before starting on this new sync request. - */ - if (!go_faster && conf->nr_waiting) - msleep_interruptible(1000); bitmap_cond_end_sync(mddev->bitmap, sector_nr); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a7196c49d15d..e793ab6b3570 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2889,7 +2889,7 @@ static int init_resync(struct r10conf *conf) */ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped, int go_faster) + int *skipped) { struct r10conf *conf = mddev->private; struct r10bio *r10_bio; @@ -2994,12 +2994,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, if (conf->geo.near_copies < conf->geo.raid_disks && max_sector > (sector_nr | chunk_mask)) max_sector = (sector_nr | chunk_mask) + 1; - /* - * If there is non-resync activity waiting for us then - * put in a delay to throttle resync. - */ - if (!go_faster && conf->nr_waiting) - msleep_interruptible(1000); /* Again, very different code for resync and recovery. * Both must result in an r10bio with a list of bios that diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index cd2f96b2c572..77dfd720aaa0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -54,6 +54,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/nodemask.h> +#include <linux/flex_array.h> #include <trace/events/block.h> #include "md.h" @@ -496,7 +497,7 @@ static void shrink_buffers(struct stripe_head *sh) } } -static int grow_buffers(struct stripe_head *sh) +static int grow_buffers(struct stripe_head *sh, gfp_t gfp) { int i; int num = sh->raid_conf->pool_size; @@ -504,7 +505,7 @@ static int grow_buffers(struct stripe_head *sh) for (i = 0; i < num; i++) { struct page *page; - if (!(page = alloc_page(GFP_KERNEL))) { + if (!(page = alloc_page(gfp))) { return 1; } sh->dev[i].page = page; @@ -525,6 +526,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); BUG_ON(stripe_operations_active(sh)); + BUG_ON(sh->batch_head); pr_debug("init_stripe called, stripe %llu\n", (unsigned long long)sector); @@ -552,8 +554,10 @@ retry: } if (read_seqcount_retry(&conf->gen_lock, seq)) goto retry; + sh->overwrite_disks = 0; insert_hash(conf, sh); sh->cpu = smp_processor_id(); + set_bit(STRIPE_BATCH_READY, &sh->state); } static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, @@ -668,20 +672,28 @@ get_active_stripe(struct r5conf *conf, sector_t sector, *(conf->hash_locks + hash)); sh = __find_stripe(conf, sector, conf->generation - previous); if (!sh) { - if (!conf->inactive_blocked) + if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) { sh = get_free_stripe(conf, hash); + if (!sh && llist_empty(&conf->released_stripes) && + !test_bit(R5_DID_ALLOC, &conf->cache_state)) + set_bit(R5_ALLOC_MORE, + &conf->cache_state); + } if (noblock && sh == NULL) break; if (!sh) { - conf->inactive_blocked = 1; + set_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state); wait_event_lock_irq( conf->wait_for_stripe, !list_empty(conf->inactive_list + hash) && (atomic_read(&conf->active_stripes) < (conf->max_nr_stripes * 3 / 4) - || !conf->inactive_blocked), + || !test_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state)), *(conf->hash_locks + hash)); - conf->inactive_blocked = 0; + clear_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state); } else { init_stripe(sh, sector, previous); atomic_inc(&sh->count); @@ -708,6 +720,130 @@ get_active_stripe(struct r5conf *conf, sector_t sector, return sh; } +static bool is_full_stripe_write(struct stripe_head *sh) +{ + BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded)); + return sh->overwrite_disks == (sh->disks - sh->raid_conf->max_degraded); +} + +static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) +{ + local_irq_disable(); + if (sh1 > sh2) { + spin_lock(&sh2->stripe_lock); + spin_lock_nested(&sh1->stripe_lock, 1); + } else { + spin_lock(&sh1->stripe_lock); + spin_lock_nested(&sh2->stripe_lock, 1); + } +} + +static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) +{ + spin_unlock(&sh1->stripe_lock); + spin_unlock(&sh2->stripe_lock); + local_irq_enable(); +} + +/* Only freshly new full stripe normal write stripe can be added to a batch list */ +static bool stripe_can_batch(struct stripe_head *sh) +{ + return test_bit(STRIPE_BATCH_READY, &sh->state) && + is_full_stripe_write(sh); +} + +/* we only do back search */ +static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh) +{ + struct stripe_head *head; + sector_t head_sector, tmp_sec; + int hash; + int dd_idx; + + if (!stripe_can_batch(sh)) + return; + /* Don't cross chunks, so stripe pd_idx/qd_idx is the same */ + tmp_sec = sh->sector; + if (!sector_div(tmp_sec, conf->chunk_sectors)) + return; + head_sector = sh->sector - STRIPE_SECTORS; + + hash = stripe_hash_locks_hash(head_sector); + spin_lock_irq(conf->hash_locks + hash); + head = __find_stripe(conf, head_sector, conf->generation); + if (head && !atomic_inc_not_zero(&head->count)) { + spin_lock(&conf->device_lock); + if (!atomic_read(&head->count)) { + if (!test_bit(STRIPE_HANDLE, &head->state)) + atomic_inc(&conf->active_stripes); + BUG_ON(list_empty(&head->lru) && + !test_bit(STRIPE_EXPANDING, &head->state)); + list_del_init(&head->lru); + if (head->group) { + head->group->stripes_cnt--; + head->group = NULL; + } + } + atomic_inc(&head->count); + spin_unlock(&conf->device_lock); + } + spin_unlock_irq(conf->hash_locks + hash); + + if (!head) + return; + if (!stripe_can_batch(head)) + goto out; + + lock_two_stripes(head, sh); + /* clear_batch_ready clear the flag */ + if (!stripe_can_batch(head) || !stripe_can_batch(sh)) + goto unlock_out; + + if (sh->batch_head) + goto unlock_out; + + dd_idx = 0; + while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) + dd_idx++; + if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw) + goto unlock_out; + + if (head->batch_head) { + spin_lock(&head->batch_head->batch_lock); + /* This batch list is already running */ + if (!stripe_can_batch(head)) { + spin_unlock(&head->batch_head->batch_lock); + goto unlock_out; + } + + /* + * at this point, head's BATCH_READY could be cleared, but we + * can still add the stripe to batch list + */ + list_add(&sh->batch_list, &head->batch_list); + spin_unlock(&head->batch_head->batch_lock); + + sh->batch_head = head->batch_head; + } else { + head->batch_head = head; + sh->batch_head = head->batch_head; + spin_lock(&head->batch_lock); + list_add_tail(&sh->batch_list, &head->batch_list); + spin_unlock(&head->batch_lock); + } + + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + if (atomic_dec_return(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + + atomic_inc(&sh->count); +unlock_out: + unlock_two_stripes(head, sh); +out: + release_stripe(head); +} + /* Determine if 'data_offset' or 'new_data_offset' should be used * in this stripe_head. */ @@ -738,6 +874,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) { struct r5conf *conf = sh->raid_conf; int i, disks = sh->disks; + struct stripe_head *head_sh = sh; might_sleep(); @@ -746,6 +883,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) int replace_only = 0; struct bio *bi, *rbi; struct md_rdev *rdev, *rrdev = NULL; + + sh = head_sh; if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) { if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags)) rw = WRITE_FUA; @@ -764,6 +903,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags)) rw |= REQ_SYNC; +again: bi = &sh->dev[i].req; rbi = &sh->dev[i].rreq; /* For writing to replacement */ @@ -782,7 +922,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) /* We raced and saw duplicates */ rrdev = NULL; } else { - if (test_bit(R5_ReadRepl, &sh->dev[i].flags) && rrdev) + if (test_bit(R5_ReadRepl, &head_sh->dev[i].flags) && rrdev) rdev = rrdev; rrdev = NULL; } @@ -853,13 +993,15 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) __func__, (unsigned long long)sh->sector, bi->bi_rw, i); atomic_inc(&sh->count); + if (sh != head_sh) + atomic_inc(&head_sh->count); if (use_new_offset(conf, sh)) bi->bi_iter.bi_sector = (sh->sector + rdev->new_data_offset); else bi->bi_iter.bi_sector = (sh->sector + rdev->data_offset); - if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags)) bi->bi_rw |= REQ_NOMERGE; if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) @@ -903,6 +1045,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) __func__, (unsigned long long)sh->sector, rbi->bi_rw, i); atomic_inc(&sh->count); + if (sh != head_sh) + atomic_inc(&head_sh->count); if (use_new_offset(conf, sh)) rbi->bi_iter.bi_sector = (sh->sector + rrdev->new_data_offset); @@ -934,8 +1078,18 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) pr_debug("skip op %ld on disc %d for sector %llu\n", bi->bi_rw, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); + if (sh->batch_head) + set_bit(STRIPE_BATCH_ERR, + &sh->batch_head->state); set_bit(STRIPE_HANDLE, &sh->state); } + + if (!head_sh->batch_head) + continue; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + if (sh != head_sh) + goto again; } } @@ -1051,6 +1205,7 @@ static void ops_run_biofill(struct stripe_head *sh) struct async_submit_ctl submit; int i; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1109,16 +1264,28 @@ static void ops_complete_compute(void *stripe_head_ref) /* return a pointer to the address conversion region of the scribble buffer */ static addr_conv_t *to_addr_conv(struct stripe_head *sh, - struct raid5_percpu *percpu) + struct raid5_percpu *percpu, int i) { - return percpu->scribble + sizeof(struct page *) * (sh->disks + 2); + void *addr; + + addr = flex_array_get(percpu->scribble, i); + return addr + sizeof(struct page *) * (sh->disks + 2); +} + +/* return a pointer to the address conversion region of the scribble buffer */ +static struct page **to_addr_page(struct raid5_percpu *percpu, int i) +{ + void *addr; + + addr = flex_array_get(percpu->scribble, i); + return addr; } static struct dma_async_tx_descriptor * ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); int target = sh->ops.target; struct r5dev *tgt = &sh->dev[target]; struct page *xor_dest = tgt->page; @@ -1127,6 +1294,8 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) struct async_submit_ctl submit; int i; + BUG_ON(sh->batch_head); + pr_debug("%s: stripe %llu block: %d\n", __func__, (unsigned long long)sh->sector, target); BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); @@ -1138,7 +1307,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) atomic_inc(&sh->count); init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, - ops_complete_compute, sh, to_addr_conv(sh, percpu)); + ops_complete_compute, sh, to_addr_conv(sh, percpu, 0)); if (unlikely(count == 1)) tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); else @@ -1156,7 +1325,9 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) * destination buffer is recorded in srcs[count] and the Q destination * is recorded in srcs[count+1]]. */ -static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh) +static int set_syndrome_sources(struct page **srcs, + struct stripe_head *sh, + int srctype) { int disks = sh->disks; int syndrome_disks = sh->ddf_layout ? disks : (disks - 2); @@ -1171,8 +1342,15 @@ static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh) i = d0_idx; do { int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + struct r5dev *dev = &sh->dev[i]; - srcs[slot] = sh->dev[i].page; + if (i == sh->qd_idx || i == sh->pd_idx || + (srctype == SYNDROME_SRC_ALL) || + (srctype == SYNDROME_SRC_WANT_DRAIN && + test_bit(R5_Wantdrain, &dev->flags)) || + (srctype == SYNDROME_SRC_WRITTEN && + dev->written)) + srcs[slot] = sh->dev[i].page; i = raid6_next_disk(i, disks); } while (i != d0_idx); @@ -1183,7 +1361,7 @@ static struct dma_async_tx_descriptor * ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) { int disks = sh->disks; - struct page **blocks = percpu->scribble; + struct page **blocks = to_addr_page(percpu, 0); int target; int qd_idx = sh->qd_idx; struct dma_async_tx_descriptor *tx; @@ -1193,6 +1371,7 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) int i; int count; + BUG_ON(sh->batch_head); if (sh->ops.target < 0) target = sh->ops.target2; else if (sh->ops.target2 < 0) @@ -1211,12 +1390,12 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) atomic_inc(&sh->count); if (target == qd_idx) { - count = set_syndrome_sources(blocks, sh); + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL); blocks[count] = NULL; /* regenerating p is not necessary */ BUG_ON(blocks[count+1] != dest); /* q should already be set */ init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } else { /* Compute any data- or p-drive using XOR */ @@ -1229,7 +1408,7 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); } @@ -1248,9 +1427,10 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) struct r5dev *tgt = &sh->dev[target]; struct r5dev *tgt2 = &sh->dev[target2]; struct dma_async_tx_descriptor *tx; - struct page **blocks = percpu->scribble; + struct page **blocks = to_addr_page(percpu, 0); struct async_submit_ctl submit; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu block1: %d block2: %d\n", __func__, (unsigned long long)sh->sector, target, target2); BUG_ON(target < 0 || target2 < 0); @@ -1290,7 +1470,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) /* Missing P+Q, just recompute */ init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); return async_gen_syndrome(blocks, 0, syndrome_disks+2, STRIPE_SIZE, &submit); } else { @@ -1314,21 +1494,21 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, NULL, NULL, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); - count = set_syndrome_sources(blocks, sh); + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL); init_async_submit(&submit, ASYNC_TX_FENCE, tx, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); return async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } } else { init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); if (failb == syndrome_disks) { /* We're missing D+P. */ return async_raid6_datap_recov(syndrome_disks+2, @@ -1352,17 +1532,18 @@ static void ops_complete_prexor(void *stripe_head_ref) } static struct dma_async_tx_descriptor * -ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, - struct dma_async_tx_descriptor *tx) +ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); int count = 0, pd_idx = sh->pd_idx, i; struct async_submit_ctl submit; /* existing parity data subtracted */ struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1374,31 +1555,56 @@ ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, } init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, - ops_complete_prexor, sh, to_addr_conv(sh, percpu)); + ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0)); tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); return tx; } static struct dma_async_tx_descriptor * +ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) +{ + struct page **blocks = to_addr_page(percpu, 0); + int count; + struct async_submit_ctl submit; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN); + + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx, + ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0)); + tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); + + return tx; +} + +static struct dma_async_tx_descriptor * ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) { int disks = sh->disks; int i; + struct stripe_head *head_sh = sh; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); for (i = disks; i--; ) { - struct r5dev *dev = &sh->dev[i]; + struct r5dev *dev; struct bio *chosen; - if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { + sh = head_sh; + if (test_and_clear_bit(R5_Wantdrain, &head_sh->dev[i].flags)) { struct bio *wbi; +again: + dev = &sh->dev[i]; spin_lock_irq(&sh->stripe_lock); chosen = dev->towrite; dev->towrite = NULL; + sh->overwrite_disks = 0; BUG_ON(dev->written); wbi = dev->written = chosen; spin_unlock_irq(&sh->stripe_lock); @@ -1423,6 +1629,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) } wbi = r5_next_bio(wbi, dev->sector); } + + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, + batch_list); + if (sh == head_sh) + continue; + goto again; + } } } @@ -1478,12 +1693,15 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, struct dma_async_tx_descriptor *tx) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs; struct async_submit_ctl submit; - int count = 0, pd_idx = sh->pd_idx, i; + int count, pd_idx = sh->pd_idx, i; struct page *xor_dest; int prexor = 0; unsigned long flags; + int j = 0; + struct stripe_head *head_sh = sh; + int last_stripe; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1500,15 +1718,18 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, ops_complete_reconstruct(sh); return; } +again: + count = 0; + xor_srcs = to_addr_page(percpu, j); /* check if prexor is active which means only process blocks * that are part of a read-modify-write (written) */ - if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) { prexor = 1; xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (dev->written) + if (head_sh->dev[i].written) xor_srcs[count++] = dev->page; } } else { @@ -1525,17 +1746,32 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST * for the synchronous xor case */ - flags = ASYNC_TX_ACK | - (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); - - atomic_inc(&sh->count); + last_stripe = !head_sh->batch_head || + list_first_entry(&sh->batch_list, + struct stripe_head, batch_list) == head_sh; + if (last_stripe) { + flags = ASYNC_TX_ACK | + (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); + + atomic_inc(&head_sh->count); + init_async_submit(&submit, flags, tx, ops_complete_reconstruct, head_sh, + to_addr_conv(sh, percpu, j)); + } else { + flags = prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST; + init_async_submit(&submit, flags, tx, NULL, NULL, + to_addr_conv(sh, percpu, j)); + } - init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh, - to_addr_conv(sh, percpu)); if (unlikely(count == 1)) tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); else tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); + if (!last_stripe) { + j++; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + goto again; + } } static void @@ -1543,8 +1779,12 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, struct dma_async_tx_descriptor *tx) { struct async_submit_ctl submit; - struct page **blocks = percpu->scribble; - int count, i; + struct page **blocks; + int count, i, j = 0; + struct stripe_head *head_sh = sh; + int last_stripe; + int synflags; + unsigned long txflags; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1562,13 +1802,36 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, return; } - count = set_syndrome_sources(blocks, sh); +again: + blocks = to_addr_page(percpu, j); - atomic_inc(&sh->count); + if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + synflags = SYNDROME_SRC_WRITTEN; + txflags = ASYNC_TX_ACK | ASYNC_TX_PQ_XOR_DST; + } else { + synflags = SYNDROME_SRC_ALL; + txflags = ASYNC_TX_ACK; + } + + count = set_syndrome_sources(blocks, sh, synflags); + last_stripe = !head_sh->batch_head || + list_first_entry(&sh->batch_list, + struct stripe_head, batch_list) == head_sh; - init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct, - sh, to_addr_conv(sh, percpu)); + if (last_stripe) { + atomic_inc(&head_sh->count); + init_async_submit(&submit, txflags, tx, ops_complete_reconstruct, + head_sh, to_addr_conv(sh, percpu, j)); + } else + init_async_submit(&submit, 0, tx, NULL, NULL, + to_addr_conv(sh, percpu, j)); async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); + if (!last_stripe) { + j++; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + goto again; + } } static void ops_complete_check(void *stripe_head_ref) @@ -1589,7 +1852,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) int pd_idx = sh->pd_idx; int qd_idx = sh->qd_idx; struct page *xor_dest; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); struct dma_async_tx_descriptor *tx; struct async_submit_ctl submit; int count; @@ -1598,6 +1861,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); + BUG_ON(sh->batch_head); count = 0; xor_dest = sh->dev[pd_idx].page; xor_srcs[count++] = xor_dest; @@ -1608,7 +1872,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) } init_async_submit(&submit, 0, NULL, NULL, NULL, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &sh->ops.zero_sum_result, &submit); @@ -1619,20 +1883,21 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp) { - struct page **srcs = percpu->scribble; + struct page **srcs = to_addr_page(percpu, 0); struct async_submit_ctl submit; int count; pr_debug("%s: stripe %llu checkp: %d\n", __func__, (unsigned long long)sh->sector, checkp); - count = set_syndrome_sources(srcs, sh); + BUG_ON(sh->batch_head); + count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL); if (!checkp) srcs[count] = NULL; atomic_inc(&sh->count); init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check, - sh, to_addr_conv(sh, percpu)); + sh, to_addr_conv(sh, percpu, 0)); async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE, &sh->ops.zero_sum_result, percpu->spare_page, &submit); } @@ -1667,8 +1932,12 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) async_tx_ack(tx); } - if (test_bit(STRIPE_OP_PREXOR, &ops_request)) - tx = ops_run_prexor(sh, percpu, tx); + if (test_bit(STRIPE_OP_PREXOR, &ops_request)) { + if (level < 6) + tx = ops_run_prexor5(sh, percpu, tx); + else + tx = ops_run_prexor6(sh, percpu, tx); + } if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) { tx = ops_run_biodrain(sh, tx); @@ -1693,7 +1962,7 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) BUG(); } - if (overlap_clear) + if (overlap_clear && !sh->batch_head) for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_Overlap, &dev->flags)) @@ -1702,10 +1971,10 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) put_cpu(); } -static int grow_one_stripe(struct r5conf *conf, int hash) +static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) { struct stripe_head *sh; - sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL); + sh = kmem_cache_zalloc(conf->slab_cache, gfp); if (!sh) return 0; @@ -1713,17 +1982,23 @@ static int grow_one_stripe(struct r5conf *conf, int hash) spin_lock_init(&sh->stripe_lock); - if (grow_buffers(sh)) { + if (grow_buffers(sh, gfp)) { shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); return 0; } - sh->hash_lock_index = hash; + sh->hash_lock_index = + conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; /* we just created an active stripe so... */ atomic_set(&sh->count, 1); atomic_inc(&conf->active_stripes); INIT_LIST_HEAD(&sh->lru); + + spin_lock_init(&sh->batch_lock); + INIT_LIST_HEAD(&sh->batch_list); + sh->batch_head = NULL; release_stripe(sh); + conf->max_nr_stripes++; return 1; } @@ -1731,7 +2006,6 @@ static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; int devs = max(conf->raid_disks, conf->previous_raid_disks); - int hash; if (conf->mddev->gendisk) sprintf(conf->cache_name[0], @@ -1749,13 +2023,10 @@ static int grow_stripes(struct r5conf *conf, int num) return 1; conf->slab_cache = sc; conf->pool_size = devs; - hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; - while (num--) { - if (!grow_one_stripe(conf, hash)) + while (num--) + if (!grow_one_stripe(conf, GFP_KERNEL)) return 1; - conf->max_nr_stripes++; - hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; - } + return 0; } @@ -1772,13 +2043,21 @@ static int grow_stripes(struct r5conf *conf, int num) * calculate over all devices (not just the data blocks), using zeros in place * of the P and Q blocks. */ -static size_t scribble_len(int num) +static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags) { + struct flex_array *ret; size_t len; len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2); - - return len; + ret = flex_array_alloc(len, cnt, flags); + if (!ret) + return NULL; + /* always prealloc all elements, so no locking is required */ + if (flex_array_prealloc(ret, 0, cnt, flags)) { + flex_array_free(ret); + return NULL; + } + return ret; } static int resize_stripes(struct r5conf *conf, int newsize) @@ -1896,16 +2175,16 @@ static int resize_stripes(struct r5conf *conf, int newsize) err = -ENOMEM; get_online_cpus(); - conf->scribble_len = scribble_len(newsize); for_each_present_cpu(cpu) { struct raid5_percpu *percpu; - void *scribble; + struct flex_array *scribble; percpu = per_cpu_ptr(conf->percpu, cpu); - scribble = kmalloc(conf->scribble_len, GFP_NOIO); + scribble = scribble_alloc(newsize, conf->chunk_sectors / + STRIPE_SECTORS, GFP_NOIO); if (scribble) { - kfree(percpu->scribble); + flex_array_free(percpu->scribble); percpu->scribble = scribble; } else { err = -ENOMEM; @@ -1937,9 +2216,10 @@ static int resize_stripes(struct r5conf *conf, int newsize) return err; } -static int drop_one_stripe(struct r5conf *conf, int hash) +static int drop_one_stripe(struct r5conf *conf) { struct stripe_head *sh; + int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; spin_lock_irq(conf->hash_locks + hash); sh = get_free_stripe(conf, hash); @@ -1950,15 +2230,15 @@ static int drop_one_stripe(struct r5conf *conf, int hash) shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); + conf->max_nr_stripes--; return 1; } static void shrink_stripes(struct r5conf *conf) { - int hash; - for (hash = 0; hash < NR_STRIPE_HASH_LOCKS; hash++) - while (drop_one_stripe(conf, hash)) - ; + while (conf->max_nr_stripes && + drop_one_stripe(conf)) + ; if (conf->slab_cache) kmem_cache_destroy(conf->slab_cache); @@ -2154,10 +2434,16 @@ static void raid5_end_write_request(struct bio *bi, int error) } rdev_dec_pending(rdev, conf->mddev); + if (sh->batch_head && !uptodate) + set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state); + if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags)) clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); + + if (sh->batch_head && sh != sh->batch_head) + release_stripe(sh->batch_head); } static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); @@ -2535,7 +2821,7 @@ static void schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int rcw, int expand) { - int i, pd_idx = sh->pd_idx, disks = sh->disks; + int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx, disks = sh->disks; struct r5conf *conf = sh->raid_conf; int level = conf->level; @@ -2571,13 +2857,15 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) atomic_inc(&conf->pending_full_writes); } else { - BUG_ON(level == 6); BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); + BUG_ON(level == 6 && + (!(test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags) || + test_bit(R5_Wantcompute, &sh->dev[qd_idx].flags)))); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (i == pd_idx) + if (i == pd_idx || i == qd_idx) continue; if (dev->towrite && @@ -2624,7 +2912,8 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, * toread/towrite point to the first in a chain. * The bi_next chain must be in order. */ -static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite) +static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, + int forwrite, int previous) { struct bio **bip; struct r5conf *conf = sh->raid_conf; @@ -2643,6 +2932,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in * protect it. */ spin_lock_irq(&sh->stripe_lock); + /* Don't allow new IO added to stripes in batch list */ + if (sh->batch_head) + goto overlap; if (forwrite) { bip = &sh->dev[dd_idx].towrite; if (*bip == NULL) @@ -2657,6 +2949,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi)) goto overlap; + if (!forwrite || previous) + clear_bit(STRIPE_BATCH_READY, &sh->state); + BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next); if (*bip) bi->bi_next = *bip; @@ -2674,7 +2969,8 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in sector = bio_end_sector(bi); } if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) - set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); + if (!test_and_set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags)) + sh->overwrite_disks++; } pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", @@ -2688,6 +2984,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in sh->bm_seq = conf->seq_flush+1; set_bit(STRIPE_BIT_DELAY, &sh->state); } + + if (stripe_can_batch(sh)) + stripe_add_to_batch_list(conf, sh); return 1; overlap: @@ -2720,6 +3019,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, struct bio **return_bi) { int i; + BUG_ON(sh->batch_head); for (i = disks; i--; ) { struct bio *bi; int bitmap_end = 0; @@ -2746,6 +3046,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, /* fail all writes first */ bi = sh->dev[i].towrite; sh->dev[i].towrite = NULL; + sh->overwrite_disks = 0; spin_unlock_irq(&sh->stripe_lock); if (bi) bitmap_end = 1; @@ -2834,6 +3135,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, int abort = 0; int i; + BUG_ON(sh->batch_head); clear_bit(STRIPE_SYNCING, &sh->state); if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) wake_up(&conf->wait_for_overlap); @@ -3064,6 +3366,7 @@ static void handle_stripe_fill(struct stripe_head *sh, { int i; + BUG_ON(sh->batch_head); /* look for blocks to read/compute, skip this if a compute * is already in flight, or if the stripe contents are in the * midst of changing due to a write @@ -3087,6 +3390,9 @@ static void handle_stripe_clean_event(struct r5conf *conf, int i; struct r5dev *dev; int discard_pending = 0; + struct stripe_head *head_sh = sh; + bool do_endio = false; + int wakeup_nr = 0; for (i = disks; i--; ) if (sh->dev[i].written) { @@ -3102,8 +3408,11 @@ static void handle_stripe_clean_event(struct r5conf *conf, clear_bit(R5_UPTODATE, &dev->flags); if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) { WARN_ON(test_bit(R5_UPTODATE, &dev->flags)); - dev->page = dev->orig_page; } + do_endio = true; + +returnbi: + dev->page = dev->orig_page; wbi = dev->written; dev->written = NULL; while (wbi && wbi->bi_iter.bi_sector < @@ -3120,6 +3429,17 @@ static void handle_stripe_clean_event(struct r5conf *conf, STRIPE_SECTORS, !test_bit(STRIPE_DEGRADED, &sh->state), 0); + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, + batch_list); + if (sh != head_sh) { + dev = &sh->dev[i]; + goto returnbi; + } + } + sh = head_sh; + dev = &sh->dev[i]; } else if (test_bit(R5_Discard, &dev->flags)) discard_pending = 1; WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); @@ -3141,8 +3461,17 @@ static void handle_stripe_clean_event(struct r5conf *conf, * will be reinitialized */ spin_lock_irq(&conf->device_lock); +unhash: remove_hash(sh); + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + if (sh != head_sh) + goto unhash; + } spin_unlock_irq(&conf->device_lock); + sh = head_sh; + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) set_bit(STRIPE_HANDLE, &sh->state); @@ -3151,6 +3480,45 @@ static void handle_stripe_clean_event(struct r5conf *conf, if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) if (atomic_dec_and_test(&conf->pending_full_writes)) md_wakeup_thread(conf->mddev->thread); + + if (!head_sh->batch_head || !do_endio) + return; + for (i = 0; i < head_sh->disks; i++) { + if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags)) + wakeup_nr++; + } + while (!list_empty(&head_sh->batch_list)) { + int i; + sh = list_first_entry(&head_sh->batch_list, + struct stripe_head, batch_list); + list_del_init(&sh->batch_list); + + set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, + head_sh->state & ~((1 << STRIPE_ACTIVE) | + (1 << STRIPE_PREREAD_ACTIVE) | + STRIPE_EXPAND_SYNC_FLAG)); + sh->check_state = head_sh->check_state; + sh->reconstruct_state = head_sh->reconstruct_state; + for (i = 0; i < sh->disks; i++) { + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wakeup_nr++; + sh->dev[i].flags = head_sh->dev[i].flags; + } + + spin_lock_irq(&sh->stripe_lock); + sh->batch_head = NULL; + spin_unlock_irq(&sh->stripe_lock); + if (sh->state & STRIPE_EXPAND_SYNC_FLAG) + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + } + + spin_lock_irq(&head_sh->stripe_lock); + head_sh->batch_head = NULL; + spin_unlock_irq(&head_sh->stripe_lock); + wake_up_nr(&conf->wait_for_overlap, wakeup_nr); + if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG) + set_bit(STRIPE_HANDLE, &head_sh->state); } static void handle_stripe_dirtying(struct r5conf *conf, @@ -3161,28 +3529,27 @@ static void handle_stripe_dirtying(struct r5conf *conf, int rmw = 0, rcw = 0, i; sector_t recovery_cp = conf->mddev->recovery_cp; - /* RAID6 requires 'rcw' in current implementation. - * Otherwise, check whether resync is now happening or should start. + /* Check whether resync is now happening or should start. * If yes, then the array is dirty (after unclean shutdown or * initial creation), so parity in some stripes might be inconsistent. * In this case, we need to always do reconstruct-write, to ensure * that in case of drive failure or read-error correction, we * generate correct data from the parity. */ - if (conf->max_degraded == 2 || + if (conf->rmw_level == PARITY_DISABLE_RMW || (recovery_cp < MaxSector && sh->sector >= recovery_cp && s->failed == 0)) { /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ rcw = 1; rmw = 2; - pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n", - conf->max_degraded, (unsigned long long)recovery_cp, + pr_debug("force RCW rmw_level=%u, recovery_cp=%llu sh->sector=%llu\n", + conf->rmw_level, (unsigned long long)recovery_cp, (unsigned long long)sh->sector); } else for (i = disks; i--; ) { /* would I have to read this buffer for read_modify_write */ struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && + if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { @@ -3192,7 +3559,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, rmw += 2*disks; /* cannot read it */ } /* Would I have to read this buffer for reconstruct_write */ - if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && + if (!test_bit(R5_OVERWRITE, &dev->flags) && + i != sh->pd_idx && i != sh->qd_idx && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { @@ -3205,7 +3573,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, pr_debug("for sector %llu, rmw=%d rcw=%d\n", (unsigned long long)sh->sector, rmw, rcw); set_bit(STRIPE_HANDLE, &sh->state); - if (rmw < rcw && rmw > 0) { + if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) { /* prefer read-modify-write, but need to get some data */ if (conf->mddev->queue) blk_add_trace_msg(conf->mddev->queue, @@ -3213,7 +3581,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, (unsigned long long)sh->sector, rmw); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && + if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags)) && @@ -3232,7 +3600,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, } } } - if (rcw <= rmw && rcw > 0) { + if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) { /* want reconstruct write, but need to get some data */ int qread =0; rcw = 0; @@ -3290,6 +3658,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, { struct r5dev *dev = NULL; + BUG_ON(sh->batch_head); set_bit(STRIPE_HANDLE, &sh->state); switch (sh->check_state) { @@ -3380,6 +3749,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, int qd_idx = sh->qd_idx; struct r5dev *dev; + BUG_ON(sh->batch_head); set_bit(STRIPE_HANDLE, &sh->state); BUG_ON(s->failed > 2); @@ -3543,6 +3913,7 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) * copy some of them into a target stripe for expand. */ struct dma_async_tx_descriptor *tx = NULL; + BUG_ON(sh->batch_head); clear_bit(STRIPE_EXPAND_SOURCE, &sh->state); for (i = 0; i < sh->disks; i++) if (i != sh->pd_idx && i != sh->qd_idx) { @@ -3615,8 +3986,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) memset(s, 0, sizeof(*s)); - s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); - s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); + s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state) && !sh->batch_head; + s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state) && !sh->batch_head; s->failed_num[0] = -1; s->failed_num[1] = -1; @@ -3786,6 +4157,80 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) rcu_read_unlock(); } +static int clear_batch_ready(struct stripe_head *sh) +{ + struct stripe_head *tmp; + if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state)) + return 0; + spin_lock(&sh->stripe_lock); + if (!sh->batch_head) { + spin_unlock(&sh->stripe_lock); + return 0; + } + + /* + * this stripe could be added to a batch list before we check + * BATCH_READY, skips it + */ + if (sh->batch_head != sh) { + spin_unlock(&sh->stripe_lock); + return 1; + } + spin_lock(&sh->batch_lock); + list_for_each_entry(tmp, &sh->batch_list, batch_list) + clear_bit(STRIPE_BATCH_READY, &tmp->state); + spin_unlock(&sh->batch_lock); + spin_unlock(&sh->stripe_lock); + + /* + * BATCH_READY is cleared, no new stripes can be added. + * batch_list can be accessed without lock + */ + return 0; +} + +static void check_break_stripe_batch_list(struct stripe_head *sh) +{ + struct stripe_head *head_sh, *next; + int i; + + if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state)) + return; + + head_sh = sh; + do { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + BUG_ON(sh == head_sh); + } while (!test_bit(STRIPE_DEGRADED, &sh->state)); + + while (sh != head_sh) { + next = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + list_del_init(&sh->batch_list); + + set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, + head_sh->state & ~((1 << STRIPE_ACTIVE) | + (1 << STRIPE_PREREAD_ACTIVE) | + (1 << STRIPE_DEGRADED) | + STRIPE_EXPAND_SYNC_FLAG)); + sh->check_state = head_sh->check_state; + sh->reconstruct_state = head_sh->reconstruct_state; + for (i = 0; i < sh->disks; i++) + sh->dev[i].flags = head_sh->dev[i].flags & + (~((1 << R5_WriteError) | (1 << R5_Overlap))); + + spin_lock_irq(&sh->stripe_lock); + sh->batch_head = NULL; + spin_unlock_irq(&sh->stripe_lock); + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + + sh = next; + } +} + static void handle_stripe(struct stripe_head *sh) { struct stripe_head_state s; @@ -3803,7 +4248,14 @@ static void handle_stripe(struct stripe_head *sh) return; } - if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + if (clear_batch_ready(sh) ) { + clear_bit_unlock(STRIPE_ACTIVE, &sh->state); + return; + } + + check_break_stripe_batch_list(sh); + + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) { spin_lock(&sh->stripe_lock); /* Cannot process 'sync' concurrently with 'discard' */ if (!test_bit(STRIPE_DISCARD, &sh->state) && @@ -4158,7 +4610,7 @@ static int raid5_congested(struct mddev *mddev, int bits) * how busy the stripe_cache is */ - if (conf->inactive_blocked) + if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) return 1; if (conf->quiesce) return 1; @@ -4180,8 +4632,12 @@ static int raid5_mergeable_bvec(struct mddev *mddev, unsigned int chunk_sectors = mddev->chunk_sectors; unsigned int bio_sectors = bvm->bi_size >> 9; - if ((bvm->bi_rw & 1) == WRITE) - return biovec->bv_len; /* always allow writes to be mergeable */ + /* + * always allow writes to be mergeable, read as well if array + * is degraded as we'll go through stripe cache anyway. + */ + if ((bvm->bi_rw & 1) == WRITE || mddev->degraded) + return biovec->bv_len; if (mddev->new_chunk_sectors < mddev->chunk_sectors) chunk_sectors = mddev->new_chunk_sectors; @@ -4603,12 +5059,14 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } set_bit(STRIPE_DISCARD, &sh->state); finish_wait(&conf->wait_for_overlap, &w); + sh->overwrite_disks = 0; for (d = 0; d < conf->raid_disks; d++) { if (d == sh->pd_idx || d == sh->qd_idx) continue; sh->dev[d].towrite = bi; set_bit(R5_OVERWRITE, &sh->dev[d].flags); raid5_inc_bi_active_stripes(bi); + sh->overwrite_disks++; } spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap) { @@ -4656,7 +5114,12 @@ static void make_request(struct mddev *mddev, struct bio * bi) md_write_start(mddev, bi); - if (rw == READ && + /* + * If array is degraded, better not do chunk aligned read because + * later we might have to read it again in order to reconstruct + * data on failed drives. + */ + if (rw == READ && mddev->degraded == 0 && mddev->reshape_position == MaxSector && chunk_aligned_read(mddev,bi)) return; @@ -4772,7 +5235,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) } if (test_bit(STRIPE_EXPANDING, &sh->state) || - !add_stripe_bio(sh, bi, dd_idx, rw)) { + !add_stripe_bio(sh, bi, dd_idx, rw, previous)) { /* Stripe is busy expanding or * add failed due to overlap. Flush everything * and wait a while @@ -4785,7 +5248,8 @@ static void make_request(struct mddev *mddev, struct bio * bi) } set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); - if ((bi->bi_rw & REQ_SYNC) && + if ((!sh->batch_head || sh == sh->batch_head) && + (bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); release_stripe_plug(mddev, sh); @@ -5050,8 +5514,7 @@ ret: return reshape_sectors; } -/* FIXME go_faster isn't used */ -static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped) { struct r5conf *conf = mddev->private; struct stripe_head *sh; @@ -5186,7 +5649,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) return handled; } - if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) { + if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) { release_stripe(sh); raid5_set_bi_processed_stripes(raid_bio, scnt); conf->retry_read_aligned = raid_bio; @@ -5312,6 +5775,8 @@ static void raid5d(struct md_thread *thread) int batch_size, released; released = release_stripe_list(conf, conf->temp_inactive_list); + if (released) + clear_bit(R5_DID_ALLOC, &conf->cache_state); if ( !list_empty(&conf->bitmap_list)) { @@ -5350,6 +5815,13 @@ static void raid5d(struct md_thread *thread) pr_debug("%d stripes handled\n", handled); spin_unlock_irq(&conf->device_lock); + if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) { + grow_one_stripe(conf, __GFP_NOWARN); + /* Set flag even if allocation failed. This helps + * slow down allocation requests when mem is short + */ + set_bit(R5_DID_ALLOC, &conf->cache_state); + } async_tx_issue_pending_all(); blk_finish_plug(&plug); @@ -5365,7 +5837,7 @@ raid5_show_stripe_cache_size(struct mddev *mddev, char *page) spin_lock(&mddev->lock); conf = mddev->private; if (conf) - ret = sprintf(page, "%d\n", conf->max_nr_stripes); + ret = sprintf(page, "%d\n", conf->min_nr_stripes); spin_unlock(&mddev->lock); return ret; } @@ -5375,30 +5847,24 @@ raid5_set_cache_size(struct mddev *mddev, int size) { struct r5conf *conf = mddev->private; int err; - int hash; if (size <= 16 || size > 32768) return -EINVAL; - hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; - while (size < conf->max_nr_stripes) { - if (drop_one_stripe(conf, hash)) - conf->max_nr_stripes--; - else - break; - hash--; - if (hash < 0) - hash = NR_STRIPE_HASH_LOCKS - 1; - } + + conf->min_nr_stripes = size; + while (size < conf->max_nr_stripes && + drop_one_stripe(conf)) + ; + + err = md_allow_write(mddev); if (err) return err; - hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; - while (size > conf->max_nr_stripes) { - if (grow_one_stripe(conf, hash)) - conf->max_nr_stripes++; - else break; - hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; - } + + while (size > conf->max_nr_stripes) + if (!grow_one_stripe(conf, GFP_KERNEL)) + break; + return 0; } EXPORT_SYMBOL(raid5_set_cache_size); @@ -5433,6 +5899,49 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR, raid5_store_stripe_cache_size); static ssize_t +raid5_show_rmw_level(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->rmw_level); + else + return 0; +} + +static ssize_t +raid5_store_rmw_level(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + + if (!conf) + return -ENODEV; + + if (len >= PAGE_SIZE) + return -EINVAL; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + + if (new != PARITY_DISABLE_RMW && !raid6_call.xor_syndrome) + return -EINVAL; + + if (new != PARITY_DISABLE_RMW && + new != PARITY_ENABLE_RMW && + new != PARITY_PREFER_RMW) + return -EINVAL; + + conf->rmw_level = new; + return len; +} + +static struct md_sysfs_entry +raid5_rmw_level = __ATTR(rmw_level, S_IRUGO | S_IWUSR, + raid5_show_rmw_level, + raid5_store_rmw_level); + + +static ssize_t raid5_show_preread_threshold(struct mddev *mddev, char *page) { struct r5conf *conf; @@ -5463,7 +5972,7 @@ raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len) conf = mddev->private; if (!conf) err = -ENODEV; - else if (new > conf->max_nr_stripes) + else if (new > conf->min_nr_stripes) err = -EINVAL; else conf->bypass_threshold = new; @@ -5618,6 +6127,7 @@ static struct attribute *raid5_attrs[] = { &raid5_preread_bypass_threshold.attr, &raid5_group_thread_cnt.attr, &raid5_skip_copy.attr, + &raid5_rmw_level.attr, NULL, }; static struct attribute_group raid5_attrs_group = { @@ -5699,7 +6209,8 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) { safe_put_page(percpu->spare_page); - kfree(percpu->scribble); + if (percpu->scribble) + flex_array_free(percpu->scribble); percpu->spare_page = NULL; percpu->scribble = NULL; } @@ -5709,7 +6220,9 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu if (conf->level == 6 && !percpu->spare_page) percpu->spare_page = alloc_page(GFP_KERNEL); if (!percpu->scribble) - percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + percpu->scribble = scribble_alloc(max(conf->raid_disks, + conf->previous_raid_disks), conf->chunk_sectors / + STRIPE_SECTORS, GFP_KERNEL); if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { free_scratch_buffer(conf, percpu); @@ -5740,6 +6253,8 @@ static void raid5_free_percpu(struct r5conf *conf) static void free_conf(struct r5conf *conf) { + if (conf->shrinker.seeks) + unregister_shrinker(&conf->shrinker); free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -5807,6 +6322,30 @@ static int raid5_alloc_percpu(struct r5conf *conf) return err; } +static unsigned long raid5_cache_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + int ret = 0; + while (ret < sc->nr_to_scan) { + if (drop_one_stripe(conf) == 0) + return SHRINK_STOP; + ret++; + } + return ret; +} + +static unsigned long raid5_cache_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + + if (conf->max_nr_stripes < conf->min_nr_stripes) + /* unlikely, but not impossible */ + return 0; + return conf->max_nr_stripes - conf->min_nr_stripes; +} + static struct r5conf *setup_conf(struct mddev *mddev) { struct r5conf *conf; @@ -5879,7 +6418,6 @@ static struct r5conf *setup_conf(struct mddev *mddev) else conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks; max_disks = max(conf->raid_disks, conf->previous_raid_disks); - conf->scribble_len = scribble_len(max_disks); conf->disks = kzalloc(max_disks * sizeof(struct disk_info), GFP_KERNEL); @@ -5907,6 +6445,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) INIT_LIST_HEAD(conf->temp_inactive_list + i); conf->level = mddev->new_level; + conf->chunk_sectors = mddev->new_chunk_sectors; if (raid5_alloc_percpu(conf) != 0) goto abort; @@ -5939,12 +6478,17 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->fullsync = 1; } - conf->chunk_sectors = mddev->new_chunk_sectors; conf->level = mddev->new_level; - if (conf->level == 6) + if (conf->level == 6) { conf->max_degraded = 2; - else + if (raid6_call.xor_syndrome) + conf->rmw_level = PARITY_ENABLE_RMW; + else + conf->rmw_level = PARITY_DISABLE_RMW; + } else { conf->max_degraded = 1; + conf->rmw_level = PARITY_ENABLE_RMW; + } conf->algorithm = mddev->new_layout; conf->reshape_progress = mddev->reshape_position; if (conf->reshape_progress != MaxSector) { @@ -5952,10 +6496,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->prev_algo = mddev->layout; } - memory = conf->max_nr_stripes * (sizeof(struct stripe_head) + + conf->min_nr_stripes = NR_STRIPES; + memory = conf->min_nr_stripes * (sizeof(struct stripe_head) + max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024; atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS); - if (grow_stripes(conf, NR_STRIPES)) { + if (grow_stripes(conf, conf->min_nr_stripes)) { printk(KERN_ERR "md/raid:%s: couldn't allocate %dkB for buffers\n", mdname(mddev), memory); @@ -5963,6 +6508,17 @@ static struct r5conf *setup_conf(struct mddev *mddev) } else printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); + /* + * Losing a stripe head costs more than the time to refill it, + * it reduces the queue depth and so can hurt throughput. + * So set it rather large, scaled by number of devices. + */ + conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4; + conf->shrinker.scan_objects = raid5_cache_scan; + conf->shrinker.count_objects = raid5_cache_count; + conf->shrinker.batch = 128; + conf->shrinker.flags = 0; + register_shrinker(&conf->shrinker); sprintf(pers_name, "raid%d", mddev->new_level); conf->thread = md_register_thread(raid5d, mddev, pers_name); @@ -6604,9 +7160,9 @@ static int check_stripe_cache(struct mddev *mddev) */ struct r5conf *conf = mddev->private; if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4 - > conf->max_nr_stripes || + > conf->min_nr_stripes || ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4 - > conf->max_nr_stripes) { + > conf->min_nr_stripes) { printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n", mdname(mddev), ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 983e18a83db1..7dc0dd86074b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -210,11 +210,19 @@ struct stripe_head { atomic_t count; /* nr of active thread/requests */ int bm_seq; /* sequence number for bitmap flushes */ int disks; /* disks in stripe */ + int overwrite_disks; /* total overwrite disks in stripe, + * this is only checked when stripe + * has STRIPE_BATCH_READY + */ enum check_states check_state; enum reconstruct_states reconstruct_state; spinlock_t stripe_lock; int cpu; struct r5worker_group *group; + + struct stripe_head *batch_head; /* protected by stripe lock */ + spinlock_t batch_lock; /* only header's lock is useful */ + struct list_head batch_list; /* protected by head's batch lock*/ /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -327,8 +335,15 @@ enum { STRIPE_ON_UNPLUG_LIST, STRIPE_DISCARD, STRIPE_ON_RELEASE_LIST, + STRIPE_BATCH_READY, + STRIPE_BATCH_ERR, }; +#define STRIPE_EXPAND_SYNC_FLAG \ + ((1 << STRIPE_EXPAND_SOURCE) |\ + (1 << STRIPE_EXPAND_READY) |\ + (1 << STRIPE_EXPANDING) |\ + (1 << STRIPE_SYNC_REQUESTED)) /* * Operation request flags */ @@ -340,6 +355,24 @@ enum { STRIPE_OP_RECONSTRUCT, STRIPE_OP_CHECK, }; + +/* + * RAID parity calculation preferences + */ +enum { + PARITY_DISABLE_RMW = 0, + PARITY_ENABLE_RMW, + PARITY_PREFER_RMW, +}; + +/* + * Pages requested from set_syndrome_sources() + */ +enum { + SYNDROME_SRC_ALL, + SYNDROME_SRC_WANT_DRAIN, + SYNDROME_SRC_WRITTEN, +}; /* * Plugging: * @@ -396,10 +429,11 @@ struct r5conf { spinlock_t hash_locks[NR_STRIPE_HASH_LOCKS]; struct mddev *mddev; int chunk_sectors; - int level, algorithm; + int level, algorithm, rmw_level; int max_degraded; int raid_disks; int max_nr_stripes; + int min_nr_stripes; /* reshape_progress is the leading edge of a 'reshape' * It has value MaxSector when no reshape is happening @@ -458,15 +492,11 @@ struct r5conf { /* per cpu variables */ struct raid5_percpu { struct page *spare_page; /* Used when checking P/Q in raid6 */ - void *scribble; /* space for constructing buffer + struct flex_array *scribble; /* space for constructing buffer * lists and performing address * conversions */ } __percpu *percpu; - size_t scribble_len; /* size of scribble region must be - * associated with conf to handle - * cpu hotplug while reshaping - */ #ifdef CONFIG_HOTPLUG_CPU struct notifier_block cpu_notify; #endif @@ -480,9 +510,19 @@ struct r5conf { struct llist_head released_stripes; wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; - int inactive_blocked; /* release of inactive stripes blocked, - * waiting for 25% to be free - */ + unsigned long cache_state; +#define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked, + * waiting for 25% to be free + */ +#define R5_ALLOC_MORE 2 /* It might help to allocate another + * stripe. + */ +#define R5_DID_ALLOC 4 /* A stripe was allocated, don't allocate + * more until at least one has been + * released. This avoids flooding + * the cache. + */ + struct shrinker shrinker; int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; @@ -497,6 +537,7 @@ struct r5conf { int worker_cnt_per_group; }; + /* * Our supported algorithms */ diff --git a/drivers/media/platform/xilinx/xilinx-dma.c b/drivers/media/platform/xilinx/xilinx-dma.c index 10209c294168..efde88adf624 100644 --- a/drivers/media/platform/xilinx/xilinx-dma.c +++ b/drivers/media/platform/xilinx/xilinx-dma.c @@ -12,7 +12,7 @@ * published by the Free Software Foundation. */ -#include <linux/amba/xilinx_dma.h> +#include <linux/dma/xilinx_dma.h> #include <linux/lcm.h> #include <linux/list.h> #include <linux/module.h> diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c index 69e0483adfee..644dec73d220 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c @@ -402,6 +402,12 @@ static struct dma_buf *vb2_dc_get_dmabuf(void *buf_priv, unsigned long flags) { struct vb2_dc_buf *buf = buf_priv; struct dma_buf *dbuf; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &vb2_dc_dmabuf_ops; + exp_info.size = buf->size; + exp_info.flags = flags; + exp_info.priv = buf; if (!buf->sgt_base) buf->sgt_base = vb2_dc_get_base_sgt(buf); @@ -409,7 +415,7 @@ static struct dma_buf *vb2_dc_get_dmabuf(void *buf_priv, unsigned long flags) if (WARN_ON(!buf->sgt_base)) return NULL; - dbuf = dma_buf_export(buf, &vb2_dc_dmabuf_ops, buf->size, flags, NULL); + dbuf = dma_buf_export(&exp_info); if (IS_ERR(dbuf)) return NULL; diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c index b1838abb6d00..45c708e463b9 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c @@ -583,11 +583,17 @@ static struct dma_buf *vb2_dma_sg_get_dmabuf(void *buf_priv, unsigned long flags { struct vb2_dma_sg_buf *buf = buf_priv; struct dma_buf *dbuf; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &vb2_dma_sg_dmabuf_ops; + exp_info.size = buf->size; + exp_info.flags = flags; + exp_info.priv = buf; if (WARN_ON(!buf->dma_sgt)) return NULL; - dbuf = dma_buf_export(buf, &vb2_dma_sg_dmabuf_ops, buf->size, flags, NULL); + dbuf = dma_buf_export(&exp_info); if (IS_ERR(dbuf)) return NULL; diff --git a/drivers/media/v4l2-core/videobuf2-vmalloc.c b/drivers/media/v4l2-core/videobuf2-vmalloc.c index bcde88572429..657ab302a5cf 100644 --- a/drivers/media/v4l2-core/videobuf2-vmalloc.c +++ b/drivers/media/v4l2-core/videobuf2-vmalloc.c @@ -368,11 +368,17 @@ static struct dma_buf *vb2_vmalloc_get_dmabuf(void *buf_priv, unsigned long flag { struct vb2_vmalloc_buf *buf = buf_priv; struct dma_buf *dbuf; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + + exp_info.ops = &vb2_vmalloc_dmabuf_ops; + exp_info.size = buf->size; + exp_info.flags = flags; + exp_info.priv = buf; if (WARN_ON(!buf->vaddr)) return NULL; - dbuf = dma_buf_export(buf, &vb2_vmalloc_dmabuf_ops, buf->size, flags, NULL); + dbuf = dma_buf_export(&exp_info); if (IS_ERR(dbuf)) return NULL; diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c index fc0c81ef04ff..c4aecc6f8373 100644 --- a/drivers/mfd/cros_ec.c +++ b/drivers/mfd/cros_ec.c @@ -74,15 +74,11 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, ret = ec_dev->cmd_xfer(ec_dev, msg); if (msg->result == EC_RES_IN_PROGRESS) { int i; - struct cros_ec_command status_msg; - struct ec_response_get_comms_status status; + struct cros_ec_command status_msg = { }; + struct ec_response_get_comms_status *status; - status_msg.version = 0; status_msg.command = EC_CMD_GET_COMMS_STATUS; - status_msg.outdata = NULL; - status_msg.outsize = 0; - status_msg.indata = (uint8_t *)&status; - status_msg.insize = sizeof(status); + status_msg.insize = sizeof(*status); /* * Query the EC's status until it's no longer busy or @@ -98,7 +94,10 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, msg->result = status_msg.result; if (status_msg.result != EC_RES_SUCCESS) break; - if (!(status.flags & EC_COMMS_STATUS_PROCESSING)) + + status = (struct ec_response_get_comms_status *) + status_msg.indata; + if (!(status->flags & EC_COMMS_STATUS_PROCESSING)) break; } } @@ -119,6 +118,10 @@ static const struct mfd_cell cros_devs[] = { .id = 2, .of_compatible = "google,cros-ec-i2c-tunnel", }, + { + .name = "cros-ec-ctl", + .id = 3, + }, }; int cros_ec_register(struct cros_ec_device *ec_dev) diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 072f67066df3..2b6ef6bd5d5f 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -388,7 +388,7 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host, { struct dma_slave_config cfg = { 0, }; struct dma_chan *chan; - unsigned int slave_id; + void *slave_data = NULL; struct resource *res; dma_cap_mask_t mask; int ret; @@ -397,13 +397,12 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host, dma_cap_set(DMA_SLAVE, mask); if (pdata) - slave_id = direction == DMA_MEM_TO_DEV - ? pdata->slave_id_tx : pdata->slave_id_rx; - else - slave_id = 0; + slave_data = direction == DMA_MEM_TO_DEV ? + (void *)pdata->slave_id_tx : + (void *)pdata->slave_id_rx; chan = dma_request_slave_channel_compat(mask, shdma_chan_filter, - (void *)(unsigned long)slave_id, &host->pd->dev, + slave_data, &host->pd->dev, direction == DMA_MEM_TO_DEV ? "tx" : "rx"); dev_dbg(&host->pd->dev, "%s: %s: got channel %p\n", __func__, @@ -414,8 +413,6 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host, res = platform_get_resource(host->pd, IORESOURCE_MEM, 0); - /* In the OF case the driver will get the slave ID from the DT */ - cfg.slave_id = slave_id; cfg.direction = direction; if (direction == DMA_DEV_TO_MEM) { diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 6906a905cd54..354f4f335ed5 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -201,7 +201,7 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) of_match_device(sh_mobile_sdhi_of_match, &pdev->dev); struct sh_mobile_sdhi *priv; struct tmio_mmc_data *mmc_data; - struct sh_mobile_sdhi_info *p = pdev->dev.platform_data; + struct tmio_mmc_data *mmd = pdev->dev.platform_data; struct tmio_mmc_host *host; struct resource *res; int irq, ret, i = 0; @@ -245,30 +245,14 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev) else host->bus_shift = 0; - mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; - if (p) { - mmc_data->flags = p->tmio_flags; - mmc_data->ocr_mask = p->tmio_ocr_mask; - mmc_data->capabilities |= p->tmio_caps; - mmc_data->capabilities2 |= p->tmio_caps2; - mmc_data->cd_gpio = p->cd_gpio; - - if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) { - /* - * Yes, we have to provide slave IDs twice to TMIO: - * once as a filter parameter and once for channel - * configuration as an explicit slave ID - */ - dma_priv->chan_priv_tx = (void *)p->dma_slave_tx; - dma_priv->chan_priv_rx = (void *)p->dma_slave_rx; - dma_priv->slave_id_tx = p->dma_slave_tx; - dma_priv->slave_id_rx = p->dma_slave_rx; - } - } + if (mmd) + *mmc_data = *mmd; + dma_priv->filter = shdma_chan_filter; dma_priv->enable = sh_mobile_sdhi_enable_dma; mmc_data->alignment_shift = 1; /* 2-byte alignment */ + mmc_data->capabilities |= MMC_CAP_MMC_HIGHSPEED; /* * All SDHI blocks support 2-byte and larger block sizes in 4-bit diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index fc3805ed69d1..4a597f5a53e2 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -43,10 +43,6 @@ struct tmio_mmc_data; struct tmio_mmc_host; struct tmio_mmc_dma { - void *chan_priv_tx; - void *chan_priv_rx; - int slave_id_tx; - int slave_id_rx; enum dma_slave_buswidth dma_buswidth; bool (*filter)(struct dma_chan *chan, void *arg); void (*enable)(struct tmio_mmc_host *host, bool enable); diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index 331bb618e398..e4b05dbb9ca8 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -261,7 +261,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat { /* We can only either use DMA for both Tx and Rx or not use it at all */ if (!host->dma || (!host->pdev->dev.of_node && - (!host->dma->chan_priv_tx || !host->dma->chan_priv_rx))) + (!pdata->chan_priv_tx || !pdata->chan_priv_rx))) return; if (!host->chan_tx && !host->chan_rx) { @@ -278,7 +278,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat dma_cap_set(DMA_SLAVE, mask); host->chan_tx = dma_request_slave_channel_compat(mask, - host->dma->filter, host->dma->chan_priv_tx, + host->dma->filter, pdata->chan_priv_tx, &host->pdev->dev, "tx"); dev_dbg(&host->pdev->dev, "%s: TX: got channel %p\n", __func__, host->chan_tx); @@ -286,8 +286,6 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (!host->chan_tx) return; - if (host->dma->chan_priv_tx) - cfg.slave_id = host->dma->slave_id_tx; cfg.direction = DMA_MEM_TO_DEV; cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->bus_shift); cfg.dst_addr_width = host->dma->dma_buswidth; @@ -299,7 +297,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat goto ecfgtx; host->chan_rx = dma_request_slave_channel_compat(mask, - host->dma->filter, host->dma->chan_priv_rx, + host->dma->filter, pdata->chan_priv_rx, &host->pdev->dev, "rx"); dev_dbg(&host->pdev->dev, "%s: RX: got channel %p\n", __func__, host->chan_rx); @@ -307,8 +305,6 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat if (!host->chan_rx) goto ereqrx; - if (host->dma->chan_priv_rx) - cfg.slave_id = host->dma->slave_id_rx; cfg.direction = DMA_DEV_TO_MEM; cfg.src_addr = cfg.dst_addr + host->pdata->dma_rx_offset; cfg.src_addr_width = host->dma->dma_buswidth; diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index 71fea895ce38..a03ad2951c7b 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -309,6 +309,19 @@ config MTD_SWAP The driver provides wear leveling by storing erase counter into the OOB. +config MTD_PARTITIONED_MASTER + bool "Retain master device when partitioned" + default n + depends on MTD + help + For historical reasons, by default, either a master is present or + several partitions are present, but not both. The concern was that + data listed in multiple partitions was dangerous; however, SCSI does + this and it is frequently useful for applications. This config option + leaves the master in even if the device is partitioned. It also makes + the parent of the partition device be the master device, rather than + what lies behind the master. + source "drivers/mtd/chips/Kconfig" source "drivers/mtd/maps/Kconfig" diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c index 423666b51efb..9a1a6ffd16b8 100644 --- a/drivers/mtd/chips/cfi_cmdset_0020.c +++ b/drivers/mtd/chips/cfi_cmdset_0020.c @@ -206,23 +206,23 @@ static struct mtd_info *cfi_staa_setup(struct map_info *map) mtd->eraseregions[(j*cfi->cfiq->NumEraseRegions)+i].numblocks = ernum; } offset += (ersize * ernum); - } + } - if (offset != devsize) { - /* Argh */ - printk(KERN_WARNING "Sum of regions (%lx) != total size of set of interleaved chips (%lx)\n", offset, devsize); - kfree(mtd->eraseregions); - kfree(cfi->cmdset_priv); - kfree(mtd); - return NULL; - } + if (offset != devsize) { + /* Argh */ + printk(KERN_WARNING "Sum of regions (%lx) != total size of set of interleaved chips (%lx)\n", offset, devsize); + kfree(mtd->eraseregions); + kfree(cfi->cmdset_priv); + kfree(mtd); + return NULL; + } - for (i=0; i<mtd->numeraseregions;i++){ - printk(KERN_DEBUG "%d: offset=0x%llx,size=0x%x,blocks=%d\n", - i, (unsigned long long)mtd->eraseregions[i].offset, - mtd->eraseregions[i].erasesize, - mtd->eraseregions[i].numblocks); - } + for (i=0; i<mtd->numeraseregions;i++){ + printk(KERN_DEBUG "%d: offset=0x%llx,size=0x%x,blocks=%d\n", + i, (unsigned long long)mtd->eraseregions[i].offset, + mtd->eraseregions[i].erasesize, + mtd->eraseregions[i].numblocks); + } /* Also select the correct geometry setup too */ mtd->_erase = cfi_staa_erase_varsize; diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 66f0405f7e53..b16f3cda97ff 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -9,7 +9,15 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +/* + * When the first attempt at device initialization fails, we may need to + * wait a little bit and retry. This timeout, by default 3 seconds, gives + * device time to start up. Required on BCM2708 and a few other chipsets. + */ +#define MTD_DEFAULT_TIMEOUT 3 + #include <linux/module.h> +#include <linux/delay.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/bio.h> @@ -209,10 +217,14 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) } -static struct block2mtd_dev *add_device(char *devname, int erase_size) +static struct block2mtd_dev *add_device(char *devname, int erase_size, + int timeout) { +#ifndef MODULE + int i; +#endif const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL; - struct block_device *bdev; + struct block_device *bdev = ERR_PTR(-ENODEV); struct block2mtd_dev *dev; char *name; @@ -225,15 +237,28 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size) /* Get a handle on the device */ bdev = blkdev_get_by_path(devname, mode, dev); -#ifndef MODULE - if (IS_ERR(bdev)) { - - /* We might not have rootfs mounted at this point. Try - to resolve the device name by other means. */ - dev_t devt = name_to_dev_t(devname); - if (devt) - bdev = blkdev_get_by_dev(devt, mode, dev); +#ifndef MODULE + /* + * We might not have the root device mounted at this point. + * Try to resolve the device name by other means. + */ + for (i = 0; IS_ERR(bdev) && i <= timeout; i++) { + dev_t devt; + + if (i) + /* + * Calling wait_for_device_probe in the first loop + * was not enough, sleep for a bit in subsequent + * go-arounds. + */ + msleep(1000); + wait_for_device_probe(); + + devt = name_to_dev_t(devname); + if (!devt) + continue; + bdev = blkdev_get_by_dev(devt, mode, dev); } #endif @@ -280,6 +305,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size) /* Device didn't get added, so free the entry */ goto err_destroy_mutex; } + list_add(&dev->list, &blkmtd_device_list); pr_info("mtd%d: [%s] erase_size = %dKiB [%d]\n", dev->mtd.index, @@ -348,16 +374,19 @@ static inline void kill_final_newline(char *str) #ifndef MODULE static int block2mtd_init_called = 0; -static char block2mtd_paramline[80 + 12]; /* 80 for device, 12 for erase size */ +/* 80 for device, 12 for erase size */ +static char block2mtd_paramline[80 + 12]; #endif static int block2mtd_setup2(const char *val) { - char buf[80 + 12]; /* 80 for device, 12 for erase size */ + /* 80 for device, 12 for erase size, 80 for name, 8 for timeout */ + char buf[80 + 12 + 80 + 8]; char *str = buf; char *token[2]; char *name; size_t erase_size = PAGE_SIZE; + unsigned long timeout = MTD_DEFAULT_TIMEOUT; int i, ret; if (strnlen(val, sizeof(buf)) >= sizeof(buf)) { @@ -395,7 +424,7 @@ static int block2mtd_setup2(const char *val) } } - add_device(name, erase_size); + add_device(name, erase_size, timeout); return 0; } @@ -463,8 +492,7 @@ static void block2mtd_exit(void) } } - -module_init(block2mtd_init); +late_initcall(block2mtd_init); module_exit(block2mtd_exit); MODULE_LICENSE("GPL"); diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c index 448ce42f951e..866d31904475 100644 --- a/drivers/mtd/devices/docg3.c +++ b/drivers/mtd/devices/docg3.c @@ -1805,7 +1805,7 @@ static int __init doc_dbg_register(struct docg3 *docg3) } } -static void __exit doc_dbg_unregister(struct docg3 *docg3) +static void doc_dbg_unregister(struct docg3 *docg3) { debugfs_remove_recursive(docg3->debugfs_root); } @@ -2033,7 +2033,7 @@ static int __init docg3_probe(struct platform_device *pdev) struct mtd_info *mtd; struct resource *ress; void __iomem *base; - int ret, floor, found = 0; + int ret, floor; struct docg3_cascade *cascade; ret = -ENXIO; @@ -2073,14 +2073,11 @@ static int __init docg3_probe(struct platform_device *pdev) 0); if (ret) goto err_probe; - found++; } ret = doc_register_sysfs(pdev, cascade); if (ret) goto err_probe; - if (!found) - goto notfound; platform_set_drvdata(pdev, cascade); doc_dbg_register(cascade->floors[0]->priv); @@ -2103,7 +2100,7 @@ err_probe: * * Returns 0 */ -static int __exit docg3_release(struct platform_device *pdev) +static int docg3_release(struct platform_device *pdev) { struct docg3_cascade *cascade = platform_get_drvdata(pdev); struct docg3 *docg3 = cascade->floors[0]->priv; @@ -2134,7 +2131,7 @@ static struct platform_driver g3_driver = { }, .suspend = docg3_suspend, .resume = docg3_resume, - .remove = __exit_p(docg3_release), + .remove = docg3_release, }; module_platform_driver_probe(g3_driver, docg3_probe); diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 85e35467fba6..7c8b1694a134 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -223,6 +223,8 @@ static int m25p_probe(struct spi_device *spi) */ if (data && data->type) flash_name = data->type; + else if (!strcmp(spi->modalias, "nor-jedec")) + flash_name = NULL; /* auto-detect */ else flash_name = spi->modalias; @@ -247,9 +249,16 @@ static int m25p_remove(struct spi_device *spi) } /* - * XXX This needs to be kept in sync with spi_nor_ids. We can't share - * it with spi-nor, because if this is built as a module then modpost - * won't be able to read it and add appropriate aliases. + * Do NOT add to this array without reading the following: + * + * Historically, many flash devices are bound to this driver by their name. But + * since most of these flash are compatible to some extent, and their + * differences can often be differentiated by the JEDEC read-ID command, we + * encourage new users to add support to the spi-nor library, and simply bind + * against a generic string here (e.g., "nor-jedec"). + * + * Many flash names are kept here in this list (as well as in spi-nor.c) to + * keep them available as module aliases for existing platforms. */ static const struct spi_device_id m25p_ids[] = { {"at25fs010"}, {"at25fs040"}, {"at25df041a"}, {"at25df321a"}, @@ -291,6 +300,12 @@ static const struct spi_device_id m25p_ids[] = { {"w25x64"}, {"w25q64"}, {"w25q80"}, {"w25q80bl"}, {"w25q128"}, {"w25q256"}, {"cat25c11"}, {"cat25c03"}, {"cat25c09"}, {"cat25c17"}, {"cat25128"}, + + /* + * Generic support for SPI NOR that can be identified by the JEDEC READ + * ID opcode (0x9F). Use this, if possible. + */ + {"nor-jedec"}, { }, }; MODULE_DEVICE_TABLE(spi, m25p_ids); diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index ba801d2c6dcc..e715ae90632f 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -242,7 +242,7 @@ config MTD_L440GX config MTD_CFI_FLAGADM tristate "CFI Flash device mapping on FlagaDM" - depends on 8xx && MTD_CFI + depends on PPC_8xx && MTD_CFI help Mapping for the Flaga digital module. If you don't have one, ignore this setting. diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c index ea697202935a..892ad6ac63f2 100644 --- a/drivers/mtd/maps/sa1100-flash.c +++ b/drivers/mtd/maps/sa1100-flash.c @@ -274,7 +274,7 @@ static int sa1100_mtd_probe(struct platform_device *pdev) return err; } -static int __exit sa1100_mtd_remove(struct platform_device *pdev) +static int sa1100_mtd_remove(struct platform_device *pdev) { struct sa_info *info = platform_get_drvdata(pdev); struct flash_platform_data *plat = dev_get_platdata(&pdev->dev); @@ -286,7 +286,7 @@ static int __exit sa1100_mtd_remove(struct platform_device *pdev) static struct platform_driver sa1100_mtd_driver = { .probe = sa1100_mtd_probe, - .remove = __exit_p(sa1100_mtd_remove), + .remove = sa1100_mtd_remove, .driver = { .name = "sa1100-mtd", }, diff --git a/drivers/mtd/maps/ts5500_flash.c b/drivers/mtd/maps/ts5500_flash.c index d1d671daf235..9969fedb1f13 100644 --- a/drivers/mtd/maps/ts5500_flash.c +++ b/drivers/mtd/maps/ts5500_flash.c @@ -117,5 +117,5 @@ module_exit(cleanup_ts5500_map); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Sean Young <sean@mess.org>"); -MODULE_DESCRIPTION("MTD map driver for Techology Systems TS-5500 board"); +MODULE_DESCRIPTION("MTD map driver for Technology Systems TS-5500 board"); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index d08229eb44d8..2b0c52870999 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -171,9 +171,6 @@ static void mtd_blktrans_work(struct work_struct *work) background_done = 0; } - if (req) - __blk_end_request_all(req, -EIO); - spin_unlock_irq(rq->queue_lock); } diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 11883bd26d9d..d172195fbd15 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -38,6 +38,7 @@ #include <linux/gfp.h> #include <linux/slab.h> #include <linux/reboot.h> +#include <linux/kconfig.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> @@ -501,6 +502,29 @@ out_error: return ret; } +static int mtd_add_device_partitions(struct mtd_info *mtd, + struct mtd_partition *real_parts, + int nbparts) +{ + int ret; + + if (nbparts == 0 || IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) { + ret = add_mtd_device(mtd); + if (ret == 1) + return -ENODEV; + } + + if (nbparts > 0) { + ret = add_mtd_partitions(mtd, real_parts, nbparts); + if (ret && IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) + del_mtd_device(mtd); + return ret; + } + + return 0; +} + + /** * mtd_device_parse_register - parse partitions and register an MTD device. * @@ -523,7 +547,8 @@ out_error: * found this functions tries to fallback to information specified in * @parts/@nr_parts. * * If any partitioning info was found, this function registers the found - * partitions. + * partitions. If the MTD_PARTITIONED_MASTER option is set, then the device + * as a whole is registered first. * * If no partitions were found this function just registers the MTD device * @mtd and exits. * @@ -534,27 +559,21 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, const struct mtd_partition *parts, int nr_parts) { - int err; - struct mtd_partition *real_parts; + int ret; + struct mtd_partition *real_parts = NULL; - err = parse_mtd_partitions(mtd, types, &real_parts, parser_data); - if (err <= 0 && nr_parts && parts) { + ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data); + if (ret <= 0 && nr_parts && parts) { real_parts = kmemdup(parts, sizeof(*parts) * nr_parts, GFP_KERNEL); if (!real_parts) - err = -ENOMEM; + ret = -ENOMEM; else - err = nr_parts; + ret = nr_parts; } - if (err > 0) { - err = add_mtd_partitions(mtd, real_parts, err); - kfree(real_parts); - } else if (err == 0) { - err = add_mtd_device(mtd); - if (err == 1) - err = -ENODEV; - } + if (ret >= 0) + ret = mtd_add_device_partitions(mtd, real_parts, ret); /* * FIXME: some drivers unfortunately call this function more than once. @@ -569,7 +588,8 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, register_reboot_notifier(&mtd->reboot_notifier); } - return err; + kfree(real_parts); + return ret; } EXPORT_SYMBOL_GPL(mtd_device_parse_register); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index e779de315ade..cafdb8855a79 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -30,6 +30,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/err.h> +#include <linux/kconfig.h> #include "mtdcore.h" @@ -379,10 +380,17 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, slave->mtd.name = name; slave->mtd.owner = master->owner; - /* NOTE: we don't arrange MTDs as a tree; it'd be error-prone - * to have the same data be in two different partitions. + /* NOTE: Historically, we didn't arrange MTDs as a tree out of + * concern for showing the same data in multiple partitions. + * However, it is very useful to have the master node present, + * so the MTD_PARTITIONED_MASTER option allows that. The master + * will have device nodes etc only if this is set, so make the + * parent conditional on that option. Note, this is a way to + * distinguish between the master and the partition in sysfs. */ - slave->mtd.dev.parent = master->dev.parent; + slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ? + &master->dev : + master->dev.parent; slave->mtd._read = part_read; slave->mtd._write = part_write; @@ -546,12 +554,35 @@ out_register: return slave; } +static ssize_t mtd_partition_offset_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mtd_info *mtd = dev_get_drvdata(dev); + struct mtd_part *part = PART(mtd); + return snprintf(buf, PAGE_SIZE, "%lld\n", part->offset); +} + +static DEVICE_ATTR(offset, S_IRUGO, mtd_partition_offset_show, NULL); + +static const struct attribute *mtd_partition_attrs[] = { + &dev_attr_offset.attr, + NULL +}; + +static int mtd_add_partition_attrs(struct mtd_part *new) +{ + int ret = sysfs_create_files(&new->mtd.dev.kobj, mtd_partition_attrs); + if (ret) + printk(KERN_WARNING + "mtd: failed to create partition attrs, err=%d\n", ret); + return ret; +} + int mtd_add_partition(struct mtd_info *master, const char *name, long long offset, long long length) { struct mtd_partition part; - struct mtd_part *p, *new; - uint64_t start, end; + struct mtd_part *new; int ret = 0; /* the direct offset is expected */ @@ -575,31 +606,15 @@ int mtd_add_partition(struct mtd_info *master, const char *name, if (IS_ERR(new)) return PTR_ERR(new); - start = offset; - end = offset + length; - mutex_lock(&mtd_partitions_mutex); - list_for_each_entry(p, &mtd_partitions, list) - if (p->master == master) { - if ((start >= p->offset) && - (start < (p->offset + p->mtd.size))) - goto err_inv; - - if ((end >= p->offset) && - (end < (p->offset + p->mtd.size))) - goto err_inv; - } - list_add(&new->list, &mtd_partitions); mutex_unlock(&mtd_partitions_mutex); add_mtd_device(&new->mtd); + mtd_add_partition_attrs(new); + return ret; -err_inv: - mutex_unlock(&mtd_partitions_mutex); - free_partition(new); - return -EINVAL; } EXPORT_SYMBOL_GPL(mtd_add_partition); @@ -612,6 +627,8 @@ int mtd_del_partition(struct mtd_info *master, int partno) list_for_each_entry_safe(slave, next, &mtd_partitions, list) if ((slave->master == master) && (slave->mtd.index == partno)) { + sysfs_remove_files(&slave->mtd.dev.kobj, + mtd_partition_attrs); ret = del_mtd_device(&slave->mtd); if (ret < 0) break; @@ -631,8 +648,8 @@ EXPORT_SYMBOL_GPL(mtd_del_partition); * and registers slave MTD objects which are bound to the master according to * the partition definitions. * - * We don't register the master, or expect the caller to have done so, - * for reasons of data integrity. + * For historical reasons, this function's caller only registers the master + * if the MTD_PARTITIONED_MASTER config option is set. */ int add_mtd_partitions(struct mtd_info *master, @@ -655,6 +672,7 @@ int add_mtd_partitions(struct mtd_info *master, mutex_unlock(&mtd_partitions_mutex); add_mtd_device(&slave->mtd); + mtd_add_partition_attrs(slave); cur_offset = slave->offset + slave->mtd.size; } diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c index d93c849b70b5..46010bd895b1 100644 --- a/drivers/mtd/nand/atmel_nand.c +++ b/drivers/mtd/nand/atmel_nand.c @@ -485,7 +485,7 @@ static void pmecc_config_ecc_layout(struct nand_ecclayout *layout, for (i = 0; i < ecc_len; i++) layout->eccpos[i] = oobsize - ecc_len + i; - layout->oobfree[0].offset = 2; + layout->oobfree[0].offset = PMECC_OOB_RESERVED_BYTES; layout->oobfree[0].length = oobsize - ecc_len - layout->oobfree[0].offset; } @@ -1204,14 +1204,14 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev, goto err; } - regs_rom = platform_get_resource(pdev, IORESOURCE_MEM, 3); - host->pmecc_rom_base = devm_ioremap_resource(&pdev->dev, regs_rom); - if (IS_ERR(host->pmecc_rom_base)) { - if (!host->has_no_lookup_table) - /* Don't display the information again */ + if (!host->has_no_lookup_table) { + regs_rom = platform_get_resource(pdev, IORESOURCE_MEM, 3); + host->pmecc_rom_base = devm_ioremap_resource(&pdev->dev, + regs_rom); + if (IS_ERR(host->pmecc_rom_base)) { dev_err(host->dev, "Can not get I/O resource for ROM, will build a lookup table in runtime!\n"); - - host->has_no_lookup_table = true; + host->has_no_lookup_table = true; + } } if (host->has_no_lookup_table) { @@ -1254,7 +1254,8 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev, nand_chip->ecc.steps = mtd->writesize / sector_size; nand_chip->ecc.total = nand_chip->ecc.bytes * nand_chip->ecc.steps; - if (nand_chip->ecc.total > mtd->oobsize - 2) { + if (nand_chip->ecc.total > + mtd->oobsize - PMECC_OOB_RESERVED_BYTES) { dev_err(host->dev, "No room for ECC bytes\n"); err_no = -EINVAL; goto err; @@ -1719,7 +1720,7 @@ static int nfc_wait_interrupt(struct atmel_nand_host *host, u32 flag) comp[index++] = &host->nfc->comp_cmd_done; if (index == 0) { - dev_err(host->dev, "Unkown interrupt flag: 0x%08x\n", flag); + dev_err(host->dev, "Unknown interrupt flag: 0x%08x\n", flag); return -EINVAL; } @@ -1752,11 +1753,10 @@ static int nfc_send_command(struct atmel_nand_host *host, cmd, addr, cycle0); timeout = jiffies + msecs_to_jiffies(NFC_TIME_OUT_MS); - while (nfc_cmd_readl(NFCADDR_CMD_NFCBUSY, host->nfc->base_cmd_regs) - & NFCADDR_CMD_NFCBUSY) { + while (nfc_readl(host->nfc->hsmc_regs, SR) & NFC_SR_BUSY) { if (time_after(jiffies, timeout)) { dev_err(host->dev, - "Time out to wait CMD_NFCBUSY ready!\n"); + "Time out to wait for NFC ready!\n"); return -ETIMEDOUT; } } diff --git a/drivers/mtd/nand/atmel_nand_ecc.h b/drivers/mtd/nand/atmel_nand_ecc.h index d4035e335ad8..668e7358f19b 100644 --- a/drivers/mtd/nand/atmel_nand_ecc.h +++ b/drivers/mtd/nand/atmel_nand_ecc.h @@ -152,4 +152,7 @@ /* Time out value for reading PMECC status register */ #define PMECC_MAX_TIMEOUT_MS 100 +/* Reserved bytes in oob area */ +#define PMECC_OOB_RESERVED_BYTES 2 + #endif diff --git a/drivers/mtd/nand/atmel_nand_nfc.h b/drivers/mtd/nand/atmel_nand_nfc.h index 85b8ca6af7d2..4d5d26221a7e 100644 --- a/drivers/mtd/nand/atmel_nand_nfc.h +++ b/drivers/mtd/nand/atmel_nand_nfc.h @@ -35,6 +35,7 @@ #define NFC_CTRL_DISABLE (1 << 1) #define ATMEL_HSMC_NFC_SR 0x08 /* NFC Status Register */ +#define NFC_SR_BUSY (1 << 8) #define NFC_SR_XFR_DONE (1 << 16) #define NFC_SR_CMD_DONE (1 << 17) #define NFC_SR_DTOE (1 << 20) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index f44c6061536a..870c7fc0f759 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -225,7 +225,6 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali, uint16_t Twhr[6] = {120, 80, 80, 60, 60, 60}; uint16_t Tcs[6] = {70, 35, 25, 25, 20, 15}; - uint16_t TclsRising = 1; uint16_t data_invalid_rhoh, data_invalid_rloh, data_invalid; uint16_t dv_window = 0; uint16_t en_lo, en_hi; @@ -276,8 +275,6 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali, re_2_re = CEIL_DIV(Trhz[mode], CLK_X); we_2_re = CEIL_DIV(Twhr[mode], CLK_X); cs_cnt = CEIL_DIV((Tcs[mode] - Trp[mode]), CLK_X); - if (!TclsRising) - cs_cnt = CEIL_DIV(Tcs[mode], CLK_X); if (cs_cnt == 0) cs_cnt = 1; @@ -1536,6 +1533,9 @@ int denali_init(struct denali_nand_info *denali) denali->nand.options |= NAND_SKIP_BBTSCAN; denali->nand.ecc.mode = NAND_ECC_HW_SYNDROME; + /* no subpage writes on denali */ + denali->nand.options |= NAND_NO_SUBPAGE_WRITE; + /* * Denali Controller only support 15bit and 8bit ECC in MRST, * so just let controller do 15bit ECC for MLC and 8bit ECC for diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index 4c05f4f6a5c6..51394e59901b 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -317,7 +317,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd) /* wait for command complete flag or timeout */ wait_event_timeout(ctrl->nand_wait, ctrl->nand_stat, - IFC_TIMEOUT_MSECS * HZ/1000); + msecs_to_jiffies(IFC_TIMEOUT_MSECS)); /* ctrl->nand_stat will be updated from IRQ context */ if (!ctrl->nand_stat) @@ -860,7 +860,7 @@ static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv) /* wait for command complete flag or timeout */ wait_event_timeout(ctrl->nand_wait, ctrl->nand_stat, - IFC_TIMEOUT_MSECS * HZ/1000); + msecs_to_jiffies(IFC_TIMEOUT_MSECS)); if (ctrl->nand_stat != IFC_NAND_EVTER_STAT_OPC) printk(KERN_ERR "fsl-ifc: Failed to Initialise SRAM\n"); diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index edfaa21b1817..e58af4bfa8c8 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -873,6 +873,7 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, { struct fsmc_nand_platform_data *pdata = dev_get_platdata(&pdev->dev); u32 val; + int ret; /* Set default NAND width to 8 bits */ pdata->width = 8; @@ -891,8 +892,12 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, sizeof(*pdata->nand_timings), GFP_KERNEL); if (!pdata->nand_timings) return -ENOMEM; - of_property_read_u8_array(np, "timings", (u8 *)pdata->nand_timings, + ret = of_property_read_u8_array(np, "timings", (u8 *)pdata->nand_timings, sizeof(*pdata->nand_timings)); + if (ret) { + dev_info(&pdev->dev, "No timings in dts specified, using default timings!\n"); + pdata->nand_timings = NULL; + } /* Set default NAND bank to 0 */ pdata->bank = 0; diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 33f3c3c54dbc..1b8f3500e6d2 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -446,7 +446,7 @@ int start_dma_without_bch_irq(struct gpmi_nand_data *this, struct dma_async_tx_descriptor *desc) { struct completion *dma_c = &this->dma_done; - int err; + unsigned long timeout; init_completion(dma_c); @@ -456,8 +456,8 @@ int start_dma_without_bch_irq(struct gpmi_nand_data *this, dma_async_issue_pending(get_dma_chan(this)); /* Wait for the interrupt from the DMA block. */ - err = wait_for_completion_timeout(dma_c, msecs_to_jiffies(1000)); - if (!err) { + timeout = wait_for_completion_timeout(dma_c, msecs_to_jiffies(1000)); + if (!timeout) { dev_err(this->dev, "DMA timeout, last DMA :%d\n", this->last_dma_type); gpmi_dump_info(this); @@ -477,7 +477,7 @@ int start_dma_with_bch_irq(struct gpmi_nand_data *this, struct dma_async_tx_descriptor *desc) { struct completion *bch_c = &this->bch_done; - int err; + unsigned long timeout; /* Prepare to receive an interrupt from the BCH block. */ init_completion(bch_c); @@ -486,8 +486,8 @@ int start_dma_with_bch_irq(struct gpmi_nand_data *this, start_dma_without_bch_irq(this, desc); /* Wait for the interrupt from the BCH block. */ - err = wait_for_completion_timeout(bch_c, msecs_to_jiffies(1000)); - if (!err) { + timeout = wait_for_completion_timeout(bch_c, msecs_to_jiffies(1000)); + if (!timeout) { dev_err(this->dev, "BCH timeout, last DMA :%d\n", this->last_dma_type); gpmi_dump_info(this); @@ -1950,7 +1950,9 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) ret = nand_boot_init(this); if (ret) goto err_out; - chip->scan_bbt(mtd); + ret = chip->scan_bbt(mtd); + if (ret) + goto err_out; ppdata.of_node = this->pdev->dev.of_node; ret = mtd_device_parse_register(mtd, NULL, &ppdata, NULL, 0); diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index a8f550fec35e..372e0e38f59b 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -386,26 +386,51 @@ static irqreturn_t mxc_nfc_irq(int irq, void *dev_id) /* This function polls the NANDFC to wait for the basic operation to * complete by checking the INT bit of config2 register. */ -static void wait_op_done(struct mxc_nand_host *host, int useirq) +static int wait_op_done(struct mxc_nand_host *host, int useirq) { - int max_retries = 8000; + int ret = 0; + + /* + * If operation is already complete, don't bother to setup an irq or a + * loop. + */ + if (host->devtype_data->check_int(host)) + return 0; if (useirq) { - if (!host->devtype_data->check_int(host)) { - reinit_completion(&host->op_completion); - irq_control(host, 1); - wait_for_completion(&host->op_completion); + unsigned long timeout; + + reinit_completion(&host->op_completion); + + irq_control(host, 1); + + timeout = wait_for_completion_timeout(&host->op_completion, HZ); + if (!timeout && !host->devtype_data->check_int(host)) { + dev_dbg(host->dev, "timeout waiting for irq\n"); + ret = -ETIMEDOUT; } } else { - while (max_retries-- > 0) { - if (host->devtype_data->check_int(host)) - break; + int max_retries = 8000; + int done; + do { udelay(1); + + done = host->devtype_data->check_int(host); + if (done) + break; + + } while (--max_retries); + + if (!done) { + dev_dbg(host->dev, "timeout polling for completion\n"); + ret = -ETIMEDOUT; } - if (max_retries < 0) - pr_debug("%s: INT not set\n", __func__); } + + WARN_ONCE(ret < 0, "timeout! useirq=%d\n", useirq); + + return ret; } static void send_cmd_v3(struct mxc_nand_host *host, uint16_t cmd, int useirq) @@ -527,30 +552,17 @@ static void send_page_v1(struct mtd_info *mtd, unsigned int ops) static void send_read_id_v3(struct mxc_nand_host *host) { - struct nand_chip *this = &host->nand; - /* Read ID into main buffer */ writel(NFC_ID, NFC_V3_LAUNCH); wait_op_done(host, true); memcpy32_fromio(host->data_buf, host->main_area0, 16); - - if (this->options & NAND_BUSWIDTH_16) { - /* compress the ID info */ - host->data_buf[1] = host->data_buf[2]; - host->data_buf[2] = host->data_buf[4]; - host->data_buf[3] = host->data_buf[6]; - host->data_buf[4] = host->data_buf[8]; - host->data_buf[5] = host->data_buf[10]; - } } /* Request the NANDFC to perform a read of the NAND device ID. */ static void send_read_id_v1_v2(struct mxc_nand_host *host) { - struct nand_chip *this = &host->nand; - /* NANDFC buffer 0 is used for device ID output */ writew(host->active_cs << 4, NFC_V1_V2_BUF_ADDR); @@ -560,15 +572,6 @@ static void send_read_id_v1_v2(struct mxc_nand_host *host) wait_op_done(host, true); memcpy32_fromio(host->data_buf, host->main_area0, 16); - - if (this->options & NAND_BUSWIDTH_16) { - /* compress the ID info */ - host->data_buf[1] = host->data_buf[2]; - host->data_buf[2] = host->data_buf[4]; - host->data_buf[3] = host->data_buf[6]; - host->data_buf[4] = host->data_buf[8]; - host->data_buf[5] = host->data_buf[10]; - } } static uint16_t get_dev_status_v3(struct mxc_nand_host *host) @@ -694,9 +697,17 @@ static u_char mxc_nand_read_byte(struct mtd_info *mtd) if (host->status_request) return host->devtype_data->get_dev_status(host) & 0xFF; - ret = *(uint8_t *)(host->data_buf + host->buf_start); - host->buf_start++; + if (nand_chip->options & NAND_BUSWIDTH_16) { + /* only take the lower byte of each word */ + ret = *(uint16_t *)(host->data_buf + host->buf_start); + + host->buf_start += 2; + } else { + ret = *(uint8_t *)(host->data_buf + host->buf_start); + host->buf_start++; + } + pr_debug("%s: ret=0x%hhx (start=%u)\n", __func__, ret, host->buf_start); return ret; } @@ -825,6 +836,12 @@ static void copy_spare(struct mtd_info *mtd, bool bfrom) } } +/* + * MXC NANDFC can only perform full page+spare or spare-only read/write. When + * the upper layers perform a read/write buf operation, the saved column address + * is used to index into the full page. So usually this function is called with + * column == 0 (unless no column cycle is needed indicated by column == -1) + */ static void mxc_do_addr_cycle(struct mtd_info *mtd, int column, int page_addr) { struct nand_chip *nand_chip = mtd->priv; @@ -832,16 +849,13 @@ static void mxc_do_addr_cycle(struct mtd_info *mtd, int column, int page_addr) /* Write out column address, if necessary */ if (column != -1) { - /* - * MXC NANDFC can only perform full page+spare or - * spare-only read/write. When the upper layers - * perform a read/write buf operation, the saved column - * address is used to index into the full page. - */ - host->devtype_data->send_addr(host, 0, page_addr == -1); + host->devtype_data->send_addr(host, column & 0xff, + page_addr == -1); if (mtd->writesize > 512) /* another col addr cycle for 2k page */ - host->devtype_data->send_addr(host, 0, false); + host->devtype_data->send_addr(host, + (column >> 8) & 0xff, + false); } /* Write out page address, if necessary */ @@ -903,7 +917,7 @@ static void preset_v1(struct mtd_info *mtd) struct mxc_nand_host *host = nand_chip->priv; uint16_t config1 = 0; - if (nand_chip->ecc.mode == NAND_ECC_HW) + if (nand_chip->ecc.mode == NAND_ECC_HW && mtd->writesize) config1 |= NFC_V1_V2_CONFIG1_ECC_EN; if (!host->devtype_data->irqpending_quirk) @@ -931,9 +945,6 @@ static void preset_v2(struct mtd_info *mtd) struct mxc_nand_host *host = nand_chip->priv; uint16_t config1 = 0; - if (nand_chip->ecc.mode == NAND_ECC_HW) - config1 |= NFC_V1_V2_CONFIG1_ECC_EN; - config1 |= NFC_V2_CONFIG1_FP_INT; if (!host->devtype_data->irqpending_quirk) @@ -942,6 +953,9 @@ static void preset_v2(struct mtd_info *mtd) if (mtd->writesize) { uint16_t pages_per_block = mtd->erasesize / mtd->writesize; + if (nand_chip->ecc.mode == NAND_ECC_HW) + config1 |= NFC_V1_V2_CONFIG1_ECC_EN; + host->eccsize = get_eccsize(mtd); if (host->eccsize == 4) config1 |= NFC_V2_CONFIG1_ECC_MODE_4; @@ -999,9 +1013,6 @@ static void preset_v3(struct mtd_info *mtd) NFC_V3_CONFIG2_INT_MSK | NFC_V3_CONFIG2_NUM_ADDR_PHASE0; - if (chip->ecc.mode == NAND_ECC_HW) - config2 |= NFC_V3_CONFIG2_ECC_EN; - addr_phases = fls(chip->pagemask) >> 3; if (mtd->writesize == 2048) { @@ -1016,6 +1027,9 @@ static void preset_v3(struct mtd_info *mtd) } if (mtd->writesize) { + if (chip->ecc.mode == NAND_ECC_HW) + config2 |= NFC_V3_CONFIG2_ECC_EN; + config2 |= NFC_V3_CONFIG2_PPB( ffs(mtd->erasesize / mtd->writesize) - 6, host->devtype_data->ppb_shift); @@ -1066,6 +1080,9 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, host->status_request = true; host->devtype_data->send_cmd(host, command, true); + WARN_ONCE(column != -1 || page_addr != -1, + "Unexpected column/row value (cmd=%u, col=%d, row=%d)\n", + command, column, page_addr); mxc_do_addr_cycle(mtd, column, page_addr); break; @@ -1079,7 +1096,10 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, command = NAND_CMD_READ0; /* only READ0 is valid */ host->devtype_data->send_cmd(host, command, false); - mxc_do_addr_cycle(mtd, column, page_addr); + WARN_ONCE(column < 0, + "Unexpected column/row value (cmd=%u, col=%d, row=%d)\n", + command, column, page_addr); + mxc_do_addr_cycle(mtd, 0, page_addr); if (mtd->writesize > 512) host->devtype_data->send_cmd(host, @@ -1100,7 +1120,10 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, host->buf_start = column; host->devtype_data->send_cmd(host, command, false); - mxc_do_addr_cycle(mtd, column, page_addr); + WARN_ONCE(column < -1, + "Unexpected column/row value (cmd=%u, col=%d, row=%d)\n", + command, column, page_addr); + mxc_do_addr_cycle(mtd, 0, page_addr); break; case NAND_CMD_PAGEPROG: @@ -1108,6 +1131,9 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, copy_spare(mtd, false); host->devtype_data->send_page(mtd, NFC_INPUT); host->devtype_data->send_cmd(host, command, true); + WARN_ONCE(column != -1 || page_addr != -1, + "Unexpected column/row value (cmd=%u, col=%d, row=%d)\n", + command, column, page_addr); mxc_do_addr_cycle(mtd, column, page_addr); break; @@ -1115,15 +1141,29 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, host->devtype_data->send_cmd(host, command, true); mxc_do_addr_cycle(mtd, column, page_addr); host->devtype_data->send_read_id(host); - host->buf_start = column; + host->buf_start = 0; break; case NAND_CMD_ERASE1: case NAND_CMD_ERASE2: host->devtype_data->send_cmd(host, command, false); + WARN_ONCE(column != -1, + "Unexpected column value (cmd=%u, col=%d)\n", + command, column); mxc_do_addr_cycle(mtd, column, page_addr); break; + case NAND_CMD_PARAM: + host->devtype_data->send_cmd(host, command, false); + mxc_do_addr_cycle(mtd, column, page_addr); + host->devtype_data->send_page(mtd, NFC_OUTPUT); + memcpy32_fromio(host->data_buf, host->main_area0, 512); + host->buf_start = 0; + break; + default: + WARN_ONCE(1, "Unimplemented command (cmd=%u)\n", + command); + break; } } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index df7eb4ff07d1..c2e1232cd45c 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -386,7 +386,7 @@ static int nand_default_block_markbad(struct mtd_info *mtd, loff_t ofs) uint8_t buf[2] = { 0, 0 }; int ret = 0, res, i = 0; - ops.datbuf = NULL; + memset(&ops, 0, sizeof(ops)); ops.oobbuf = buf; ops.ooboffs = chip->badblockpos; if (chip->options & NAND_BUSWIDTH_16) { @@ -566,6 +566,25 @@ void nand_wait_ready(struct mtd_info *mtd) EXPORT_SYMBOL_GPL(nand_wait_ready); /** + * nand_wait_status_ready - [GENERIC] Wait for the ready status after commands. + * @mtd: MTD device structure + * @timeo: Timeout in ms + * + * Wait for status ready (i.e. command done) or timeout. + */ +static void nand_wait_status_ready(struct mtd_info *mtd, unsigned long timeo) +{ + register struct nand_chip *chip = mtd->priv; + + timeo = jiffies + msecs_to_jiffies(timeo); + do { + if ((chip->read_byte(mtd) & NAND_STATUS_READY)) + break; + touch_softlockup_watchdog(); + } while (time_before(jiffies, timeo)); +}; + +/** * nand_command - [DEFAULT] Send command to NAND device * @mtd: MTD device structure * @command: the command to be sent @@ -643,8 +662,8 @@ static void nand_command(struct mtd_info *mtd, unsigned int command, NAND_CTRL_CLE | NAND_CTRL_CHANGE); chip->cmd_ctrl(mtd, NAND_CMD_NONE, NAND_NCE | NAND_CTRL_CHANGE); - while (!(chip->read_byte(mtd) & NAND_STATUS_READY)) - ; + /* EZ-NAND can take upto 250ms as per ONFi v4.0 */ + nand_wait_status_ready(mtd, 250); return; /* This applies to read commands */ @@ -740,8 +759,8 @@ static void nand_command_lp(struct mtd_info *mtd, unsigned int command, NAND_NCE | NAND_CLE | NAND_CTRL_CHANGE); chip->cmd_ctrl(mtd, NAND_CMD_NONE, NAND_NCE | NAND_CTRL_CHANGE); - while (!(chip->read_byte(mtd) & NAND_STATUS_READY)) - ; + /* EZ-NAND can take upto 250ms as per ONFi v4.0 */ + nand_wait_status_ready(mtd, 250); return; case NAND_CMD_RNDOUT: @@ -968,7 +987,7 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) __func__, (unsigned long long)ofs, len); if (check_offs_len(mtd, ofs, len)) - ret = -EINVAL; + return -EINVAL; /* Align to last block address if size addresses end of the device */ if (ofs + len == mtd->size) @@ -1031,7 +1050,7 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) __func__, (unsigned long long)ofs, len); if (check_offs_len(mtd, ofs, len)) - ret = -EINVAL; + return -EINVAL; nand_get_device(mtd, FL_LOCKING); @@ -1716,9 +1735,9 @@ static int nand_read(struct mtd_info *mtd, loff_t from, size_t len, int ret; nand_get_device(mtd, FL_READING); + memset(&ops, 0, sizeof(ops)); ops.len = len; ops.datbuf = buf; - ops.oobbuf = NULL; ops.mode = MTD_OPS_PLACE_OOB; ret = nand_do_read_ops(mtd, from, &ops); *retlen = ops.retlen; @@ -2124,7 +2143,7 @@ static int nand_write_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip, /** - * nand_write_subpage_hwecc - [REPLACABLE] hardware ECC based subpage write + * nand_write_subpage_hwecc - [REPLACEABLE] hardware ECC based subpage write * @mtd: mtd info structure * @chip: nand chip info structure * @offset: column address of subpage within the page @@ -2508,9 +2527,9 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, /* Grab the device */ panic_nand_get_device(chip, mtd, FL_WRITING); + memset(&ops, 0, sizeof(ops)); ops.len = len; ops.datbuf = (uint8_t *)buf; - ops.oobbuf = NULL; ops.mode = MTD_OPS_PLACE_OOB; ret = nand_do_write_ops(mtd, to, &ops); @@ -2536,9 +2555,9 @@ static int nand_write(struct mtd_info *mtd, loff_t to, size_t len, int ret; nand_get_device(mtd, FL_WRITING); + memset(&ops, 0, sizeof(ops)); ops.len = len; ops.datbuf = (uint8_t *)buf; - ops.oobbuf = NULL; ops.mode = MTD_OPS_PLACE_OOB; ret = nand_do_write_ops(mtd, to, &ops); *retlen = ops.retlen; diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 10b1f7a4fe50..a4615fcc3d00 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -38,8 +38,8 @@ #include <linux/platform_data/mtd-nand-pxa3xx.h> -#define CHIP_DELAY_TIMEOUT (2 * HZ/10) -#define NAND_STOP_DELAY (2 * HZ/50) +#define CHIP_DELAY_TIMEOUT msecs_to_jiffies(200) +#define NAND_STOP_DELAY msecs_to_jiffies(40) #define PAGE_CHUNK_SIZE (2048) /* @@ -605,11 +605,24 @@ static void start_data_dma(struct pxa3xx_nand_info *info) {} #endif +static irqreturn_t pxa3xx_nand_irq_thread(int irq, void *data) +{ + struct pxa3xx_nand_info *info = data; + + handle_data_pio(info); + + info->state = STATE_CMD_DONE; + nand_writel(info, NDSR, NDSR_WRDREQ | NDSR_RDDREQ); + + return IRQ_HANDLED; +} + static irqreturn_t pxa3xx_nand_irq(int irq, void *devid) { struct pxa3xx_nand_info *info = devid; unsigned int status, is_completed = 0, is_ready = 0; unsigned int ready, cmd_done; + irqreturn_t ret = IRQ_HANDLED; if (info->cs == 0) { ready = NDSR_FLASH_RDY; @@ -651,7 +664,8 @@ static irqreturn_t pxa3xx_nand_irq(int irq, void *devid) } else { info->state = (status & NDSR_RDDREQ) ? STATE_PIO_READING : STATE_PIO_WRITING; - handle_data_pio(info); + ret = IRQ_WAKE_THREAD; + goto NORMAL_IRQ_EXIT; } } if (status & cmd_done) { @@ -692,7 +706,7 @@ static irqreturn_t pxa3xx_nand_irq(int irq, void *devid) if (is_ready) complete(&info->dev_ready); NORMAL_IRQ_EXIT: - return IRQ_HANDLED; + return ret; } static inline int is_buf_blank(uint8_t *buf, size_t len) @@ -951,7 +965,7 @@ static void nand_cmdfunc(struct mtd_info *mtd, unsigned command, { struct pxa3xx_nand_host *host = mtd->priv; struct pxa3xx_nand_info *info = host->info_data; - int ret, exec_cmd; + int exec_cmd; /* * if this is a x16 device ,then convert the input @@ -983,9 +997,8 @@ static void nand_cmdfunc(struct mtd_info *mtd, unsigned command, info->need_wait = 1; pxa3xx_nand_start(info); - ret = wait_for_completion_timeout(&info->cmd_complete, - CHIP_DELAY_TIMEOUT); - if (!ret) { + if (!wait_for_completion_timeout(&info->cmd_complete, + CHIP_DELAY_TIMEOUT)) { dev_err(&info->pdev->dev, "Wait time out!!!\n"); /* Stop State Machine for next command cycle */ pxa3xx_nand_stop(info); @@ -1000,7 +1013,7 @@ static void nand_cmdfunc_extended(struct mtd_info *mtd, { struct pxa3xx_nand_host *host = mtd->priv; struct pxa3xx_nand_info *info = host->info_data; - int ret, exec_cmd, ext_cmd_type; + int exec_cmd, ext_cmd_type; /* * if this is a x16 device then convert the input @@ -1063,9 +1076,8 @@ static void nand_cmdfunc_extended(struct mtd_info *mtd, init_completion(&info->cmd_complete); pxa3xx_nand_start(info); - ret = wait_for_completion_timeout(&info->cmd_complete, - CHIP_DELAY_TIMEOUT); - if (!ret) { + if (!wait_for_completion_timeout(&info->cmd_complete, + CHIP_DELAY_TIMEOUT)) { dev_err(&info->pdev->dev, "Wait time out!!!\n"); /* Stop State Machine for next command cycle */ pxa3xx_nand_stop(info); @@ -1198,13 +1210,11 @@ static int pxa3xx_nand_waitfunc(struct mtd_info *mtd, struct nand_chip *this) { struct pxa3xx_nand_host *host = mtd->priv; struct pxa3xx_nand_info *info = host->info_data; - int ret; if (info->need_wait) { - ret = wait_for_completion_timeout(&info->dev_ready, - CHIP_DELAY_TIMEOUT); info->need_wait = 0; - if (!ret) { + if (!wait_for_completion_timeout(&info->dev_ready, + CHIP_DELAY_TIMEOUT)) { dev_err(&info->pdev->dev, "Ready time out!!!\n"); return NAND_STATUS_FAIL; } @@ -1508,6 +1518,8 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd) return ret; } + memset(pxa3xx_flash_ids, 0, sizeof(pxa3xx_flash_ids)); + pxa3xx_flash_ids[0].name = f->name; pxa3xx_flash_ids[0].dev_id = (f->chip_id >> 8) & 0xffff; pxa3xx_flash_ids[0].pagesize = f->page_size; @@ -1710,7 +1722,9 @@ static int alloc_nand_resource(struct platform_device *pdev) /* initialize all interrupts to be disabled */ disable_int(info, NDSR_MASK); - ret = request_irq(irq, pxa3xx_nand_irq, 0, pdev->name, info); + ret = request_threaded_irq(irq, pxa3xx_nand_irq, + pxa3xx_nand_irq_thread, IRQF_ONESHOT, + pdev->name, info); if (ret < 0) { dev_err(&pdev->dev, "failed to request IRQ\n"); goto fail_free_buf; diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c index 35aef5edb588..0e02be47ce1d 100644 --- a/drivers/mtd/nand/s3c2410.c +++ b/drivers/mtd/nand/s3c2410.c @@ -948,8 +948,6 @@ static int s3c24xx_nand_probe(struct platform_device *pdev) cpu_type = platform_get_device_id(pdev)->driver_data; - pr_debug("s3c2410_nand_probe(%p)\n", pdev); - info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); if (info == NULL) { err = -ENOMEM; @@ -1045,7 +1043,6 @@ static int s3c24xx_nand_probe(struct platform_device *pdev) s3c2410_nand_clk_set_state(info, CLOCK_SUSPEND); } - pr_debug("initialised ok\n"); return 0; exit_error: diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c index a21c378f096a..c3ce81c1a716 100644 --- a/drivers/mtd/nand/sh_flctl.c +++ b/drivers/mtd/nand/sh_flctl.c @@ -159,7 +159,6 @@ static void flctl_setup_dma(struct sh_flctl *flctl) return; memset(&cfg, 0, sizeof(cfg)); - cfg.slave_id = pdata->slave_id_fifo0_tx; cfg.direction = DMA_MEM_TO_DEV; cfg.dst_addr = (dma_addr_t)FLDTFIFO(flctl); cfg.src_addr = 0; @@ -175,7 +174,6 @@ static void flctl_setup_dma(struct sh_flctl *flctl) if (!flctl->chan_fifo0_rx) goto err; - cfg.slave_id = pdata->slave_id_fifo0_rx; cfg.direction = DMA_DEV_TO_MEM; cfg.dst_addr = 0; cfg.src_addr = (dma_addr_t)FLDTFIFO(flctl); diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c index 635ee0027691..43b3392ffee7 100644 --- a/drivers/mtd/onenand/onenand_base.c +++ b/drivers/mtd/onenand/onenand_base.c @@ -1743,7 +1743,6 @@ static int onenand_panic_write(struct mtd_info *mtd, loff_t to, size_t len, struct onenand_chip *this = mtd->priv; int column, subpage; int written = 0; - int ret = 0; if (this->state == FL_PM_SUSPENDED) return -EBUSY; @@ -1786,15 +1785,10 @@ static int onenand_panic_write(struct mtd_info *mtd, loff_t to, size_t len, onenand_panic_wait(mtd); /* In partial page write we don't update bufferram */ - onenand_update_bufferram(mtd, to, !ret && !subpage); + onenand_update_bufferram(mtd, to, !subpage); if (ONENAND_IS_2PLANE(this)) { ONENAND_SET_BUFFERRAM1(this); - onenand_update_bufferram(mtd, to + this->writesize, !ret && !subpage); - } - - if (ret) { - printk(KERN_ERR "%s: write failed %d\n", __func__, ret); - break; + onenand_update_bufferram(mtd, to + this->writesize, !subpage); } written += thislen; @@ -1808,7 +1802,7 @@ static int onenand_panic_write(struct mtd_info *mtd, loff_t to, size_t len, } *retlen = written; - return ret; + return 0; } /** diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c index 1c7308c2c77d..5d5d36272bb5 100644 --- a/drivers/mtd/spi-nor/fsl-quadspi.c +++ b/drivers/mtd/spi-nor/fsl-quadspi.c @@ -460,8 +460,7 @@ fsl_qspi_runcmd(struct fsl_qspi *q, u8 cmd, unsigned int addr, int len) writel((seqid << QUADSPI_IPCR_SEQID_SHIFT) | len, base + QUADSPI_IPCR); /* Wait for the interrupt. */ - err = wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000)); - if (!err) { + if (!wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000))) { dev_err(q->dev, "cmd 0x%.2x timeout, addr@%.8x, FR:0x%.8x, SR:0x%.8x\n", cmd, addr, readl(base + QUADSPI_FR), @@ -830,27 +829,27 @@ static int fsl_qspi_probe(struct platform_device *pdev) ret = clk_prepare_enable(q->clk_en); if (ret) { - dev_err(dev, "can not enable the qspi_en clock\n"); + dev_err(dev, "cannot enable the qspi_en clock: %d\n", ret); return ret; } ret = clk_prepare_enable(q->clk); if (ret) { - dev_err(dev, "can not enable the qspi clock\n"); + dev_err(dev, "cannot enable the qspi clock: %d\n", ret); goto clk_failed; } /* find the irq */ ret = platform_get_irq(pdev, 0); if (ret < 0) { - dev_err(dev, "failed to get the irq\n"); + dev_err(dev, "failed to get the irq: %d\n", ret); goto irq_failed; } ret = devm_request_irq(dev, ret, fsl_qspi_irq_handler, 0, pdev->name, q); if (ret) { - dev_err(dev, "failed to request irq.\n"); + dev_err(dev, "failed to request irq: %d\n", ret); goto irq_failed; } diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index b6a5a0c269e1..14a5d2325dac 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -369,17 +369,13 @@ erase_err: return ret; } -static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) +static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len) { - struct spi_nor *nor = mtd_to_spi_nor(mtd); + struct mtd_info *mtd = nor->mtd; uint32_t offset = ofs; uint8_t status_old, status_new; int ret = 0; - ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_LOCK); - if (ret) - return ret; - status_old = read_sr(nor); if (offset < mtd->size - (mtd->size / 2)) @@ -402,26 +398,18 @@ static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) (status_old & (SR_BP2 | SR_BP1 | SR_BP0))) { write_enable(nor); ret = write_sr(nor, status_new); - if (ret) - goto err; } -err: - spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK); return ret; } -static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) +static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) { - struct spi_nor *nor = mtd_to_spi_nor(mtd); + struct mtd_info *mtd = nor->mtd; uint32_t offset = ofs; uint8_t status_old, status_new; int ret = 0; - ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_UNLOCK); - if (ret) - return ret; - status_old = read_sr(nor); if (offset+len > mtd->size - (mtd->size / 64)) @@ -444,15 +432,41 @@ static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) (status_old & (SR_BP2 | SR_BP1 | SR_BP0))) { write_enable(nor); ret = write_sr(nor, status_new); - if (ret) - goto err; } -err: + return ret; +} + +static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) +{ + struct spi_nor *nor = mtd_to_spi_nor(mtd); + int ret; + + ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_LOCK); + if (ret) + return ret; + + ret = nor->flash_lock(nor, ofs, len); + spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_UNLOCK); return ret; } +static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) +{ + struct spi_nor *nor = mtd_to_spi_nor(mtd); + int ret; + + ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_UNLOCK); + if (ret) + return ret; + + ret = nor->flash_unlock(nor, ofs, len); + + spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK); + return ret; +} + /* Used when the "_ext_id" is two bytes at most */ #define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags) \ ((kernel_ulong_t)&(struct flash_info) { \ @@ -524,6 +538,7 @@ static const struct spi_device_id spi_nor_ids[] = { { "en25q64", INFO(0x1c3017, 0, 64 * 1024, 128, SECT_4K) }, { "en25qh128", INFO(0x1c7018, 0, 64 * 1024, 256, 0) }, { "en25qh256", INFO(0x1c7019, 0, 64 * 1024, 512, 0) }, + { "en25s64", INFO(0x1c3817, 0, 64 * 1024, 128, 0) }, /* ESMT */ { "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) }, @@ -553,6 +568,7 @@ static const struct spi_device_id spi_nor_ids[] = { { "mx25l3205d", INFO(0xc22016, 0, 64 * 1024, 64, 0) }, { "mx25l3255e", INFO(0xc29e16, 0, 64 * 1024, 64, SECT_4K) }, { "mx25l6405d", INFO(0xc22017, 0, 64 * 1024, 128, 0) }, + { "mx25u6435f", INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) }, { "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) }, { "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) }, { "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) }, @@ -648,6 +664,7 @@ static const struct spi_device_id spi_nor_ids[] = { { "m25px80", INFO(0x207114, 0, 64 * 1024, 16, 0) }, /* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */ + { "w25x05", INFO(0xef3010, 0, 64 * 1024, 1, SECT_4K) }, { "w25x10", INFO(0xef3011, 0, 64 * 1024, 2, SECT_4K) }, { "w25x20", INFO(0xef3012, 0, 64 * 1024, 4, SECT_4K) }, { "w25x40", INFO(0xef3013, 0, 64 * 1024, 8, SECT_4K) }, @@ -658,6 +675,7 @@ static const struct spi_device_id spi_nor_ids[] = { { "w25q32dw", INFO(0xef6016, 0, 64 * 1024, 64, SECT_4K) }, { "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) }, { "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) }, + { "w25q64dw", INFO(0xef6017, 0, 64 * 1024, 128, SECT_4K) }, { "w25q80", INFO(0xef5014, 0, 64 * 1024, 16, SECT_4K) }, { "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16, SECT_4K) }, { "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) }, @@ -1045,6 +1063,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) /* nor protection support for STmicro chips */ if (JEDEC_MFR(info) == CFI_MFR_ST) { + nor->flash_lock = stm_lock; + nor->flash_unlock = stm_unlock; + } + + if (nor->flash_lock && nor->flash_unlock) { mtd->_lock = spi_nor_lock; mtd->_unlock = spi_nor_unlock; } diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index e579f9027c47..79316159eec6 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -9,6 +9,8 @@ #include <linux/slab.h> #include <linux/mtd/nand_ecc.h> +#include "mtd_test.h" + /* * Test the implementation for software ECC * @@ -274,6 +276,10 @@ static int nand_ecc_test_run(const size_t size) } pr_info("ok - %s-%zd\n", nand_ecc_test[i].name, size); + + err = mtdtest_relax(); + if (err) + break; } error: kfree(error_data); diff --git a/drivers/mtd/tests/mtd_test.h b/drivers/mtd/tests/mtd_test.h index f437c776c54f..4b7bee17c924 100644 --- a/drivers/mtd/tests/mtd_test.h +++ b/drivers/mtd/tests/mtd_test.h @@ -1,4 +1,16 @@ #include <linux/mtd/mtd.h> +#include <linux/sched.h> + +static inline int mtdtest_relax(void) +{ + cond_resched(); + if (signal_pending(current)) { + pr_info("aborting test due to pending signal!\n"); + return -EINTR; + } + + return 0; +} int mtdtest_erase_eraseblock(struct mtd_info *mtd, unsigned int ebnum); int mtdtest_scan_for_bad_eraseblocks(struct mtd_info *mtd, unsigned char *bbt, diff --git a/drivers/mtd/tests/nandbiterrs.c b/drivers/mtd/tests/nandbiterrs.c index 273f7e553954..09a4ccac53a2 100644 --- a/drivers/mtd/tests/nandbiterrs.c +++ b/drivers/mtd/tests/nandbiterrs.c @@ -320,6 +320,10 @@ static int overwrite_test(void) break; } + err = mtdtest_relax(); + if (err) + break; + opno++; } diff --git a/drivers/mtd/tests/oobtest.c b/drivers/mtd/tests/oobtest.c index 5e061186eab1..8e8525f0202f 100644 --- a/drivers/mtd/tests/oobtest.c +++ b/drivers/mtd/tests/oobtest.c @@ -70,7 +70,7 @@ static int write_eraseblock(int ebnum) int i; struct mtd_oob_ops ops; int err = 0; - loff_t addr = ebnum * mtd->erasesize; + loff_t addr = (loff_t)ebnum * mtd->erasesize; prandom_bytes_state(&rnd_state, writebuf, use_len_max * pgcnt); for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) { @@ -112,7 +112,10 @@ static int write_whole_device(void) return err; if (i % 256 == 0) pr_info("written up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + return err; } pr_info("written %u eraseblocks\n", i); return 0; @@ -141,6 +144,31 @@ static size_t memcmpshow(loff_t addr, const void *cs, const void *ct, size_t cou return bitflips; } +/* + * Compare with 0xff and show the address, offset and data bytes at + * comparison failure. Return number of bitflips encountered. + */ +static size_t memffshow(loff_t addr, loff_t offset, const void *cs, + size_t count) +{ + const unsigned char *su1; + int res; + size_t i = 0; + size_t bitflips = 0; + + for (su1 = cs; 0 < count; ++su1, count--, i++) { + res = *su1 ^ 0xff; + if (res) { + pr_info("error @addr[0x%lx:0x%lx] 0x%x -> 0xff diff 0x%x\n", + (unsigned long)addr, (unsigned long)offset + i, + *su1, res); + bitflips += hweight8(res); + } + } + + return bitflips; +} + static int verify_eraseblock(int ebnum) { int i; @@ -203,6 +231,15 @@ static int verify_eraseblock(int ebnum) bitflips = memcmpshow(addr, readbuf + use_offset, writebuf + (use_len_max * i) + use_offset, use_len); + + /* verify pre-offset area for 0xff */ + bitflips += memffshow(addr, 0, readbuf, use_offset); + + /* verify post-(use_offset + use_len) area for 0xff */ + k = use_offset + use_len; + bitflips += memffshow(addr, k, readbuf + k, + mtd->ecclayout->oobavail - k); + if (bitflips > bitflip_limit) { pr_err("error: verify failed at %#llx\n", (long long)addr); @@ -212,34 +249,8 @@ static int verify_eraseblock(int ebnum) return -1; } } else if (bitflips) { - pr_info("ignoring error as within bitflip_limit\n"); + pr_info("ignoring errors as within bitflip limit\n"); } - - for (k = 0; k < use_offset; ++k) - if (readbuf[k] != 0xff) { - pr_err("error: verify 0xff " - "failed at %#llx\n", - (long long)addr); - errcnt += 1; - if (errcnt > 1000) { - pr_err("error: too " - "many errors\n"); - return -1; - } - } - for (k = use_offset + use_len; - k < mtd->ecclayout->oobavail; ++k) - if (readbuf[k] != 0xff) { - pr_err("error: verify 0xff " - "failed at %#llx\n", - (long long)addr); - errcnt += 1; - if (errcnt > 1000) { - pr_err("error: too " - "many errors\n"); - return -1; - } - } } if (vary_offset) do_vary_offset(); @@ -310,7 +321,10 @@ static int verify_all_eraseblocks(void) return err; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + return err; } pr_info("verified %u eraseblocks\n", i); return 0; @@ -421,7 +435,10 @@ static int __init mtd_oobtest_init(void) goto out; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("verified %u eraseblocks\n", i); @@ -634,7 +651,11 @@ static int __init mtd_oobtest_init(void) goto out; if (i % 256 == 0) pr_info("written up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; + addr += mtd->writesize; } } @@ -672,7 +693,10 @@ static int __init mtd_oobtest_init(void) } if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("verified %u eraseblocks\n", i); diff --git a/drivers/mtd/tests/pagetest.c b/drivers/mtd/tests/pagetest.c index 88296e888e9d..ba1890d5632c 100644 --- a/drivers/mtd/tests/pagetest.c +++ b/drivers/mtd/tests/pagetest.c @@ -407,7 +407,10 @@ static int __init mtd_pagetest_init(void) goto out; if (i % 256 == 0) pr_info("written up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("written %u eraseblocks\n", i); @@ -422,7 +425,10 @@ static int __init mtd_pagetest_init(void) goto out; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("verified %u eraseblocks\n", i); diff --git a/drivers/mtd/tests/readtest.c b/drivers/mtd/tests/readtest.c index a54cf1511114..a3196b750a22 100644 --- a/drivers/mtd/tests/readtest.c +++ b/drivers/mtd/tests/readtest.c @@ -190,7 +190,10 @@ static int __init mtd_readtest_init(void) if (!err) err = ret; } - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } if (err) diff --git a/drivers/mtd/tests/speedtest.c b/drivers/mtd/tests/speedtest.c index 5ee9f7021020..5a6f31af06f9 100644 --- a/drivers/mtd/tests/speedtest.c +++ b/drivers/mtd/tests/speedtest.c @@ -185,7 +185,7 @@ static long calc_speed(void) (finish.tv_usec - start.tv_usec) / 1000; if (ms == 0) return 0; - k = goodebcnt * (mtd->erasesize / 1024) * 1000; + k = (uint64_t)goodebcnt * (mtd->erasesize / 1024) * 1000; do_div(k, ms); return k; } @@ -269,7 +269,10 @@ static int __init mtd_speedtest_init(void) err = write_eraseblock(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -284,7 +287,10 @@ static int __init mtd_speedtest_init(void) err = read_eraseblock(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -303,7 +309,10 @@ static int __init mtd_speedtest_init(void) err = write_eraseblock_by_page(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -318,7 +327,10 @@ static int __init mtd_speedtest_init(void) err = read_eraseblock_by_page(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -337,7 +349,10 @@ static int __init mtd_speedtest_init(void) err = write_eraseblock_by_2pages(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -352,7 +367,10 @@ static int __init mtd_speedtest_init(void) err = read_eraseblock_by_2pages(i); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } stop_timing(); speed = calc_speed(); @@ -385,7 +403,11 @@ static int __init mtd_speedtest_init(void) err = multiblock_erase(i, j); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; + i += j; } stop_timing(); diff --git a/drivers/mtd/tests/stresstest.c b/drivers/mtd/tests/stresstest.c index c9d42cc2df1b..e509f8aa9a7e 100644 --- a/drivers/mtd/tests/stresstest.c +++ b/drivers/mtd/tests/stresstest.c @@ -96,7 +96,7 @@ static int do_read(void) if (offs + len > mtd->erasesize) len = mtd->erasesize - offs; } - addr = eb * mtd->erasesize + offs; + addr = (loff_t)eb * mtd->erasesize + offs; return mtdtest_read(mtd, addr, len, readbuf); } @@ -124,7 +124,7 @@ static int do_write(void) offsets[eb + 1] = 0; } } - addr = eb * mtd->erasesize + offs; + addr = (loff_t)eb * mtd->erasesize + offs; err = mtdtest_write(mtd, addr, len, writebuf); if (unlikely(err)) return err; @@ -221,7 +221,10 @@ static int __init mtd_stresstest_init(void) err = do_operation(); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("finished, %d operations done\n", op); diff --git a/drivers/mtd/tests/subpagetest.c b/drivers/mtd/tests/subpagetest.c index 7b59ef522d5e..aecc6ce5a9e1 100644 --- a/drivers/mtd/tests/subpagetest.c +++ b/drivers/mtd/tests/subpagetest.c @@ -95,7 +95,7 @@ static int write_eraseblock2(int ebnum) loff_t addr = (loff_t)ebnum * mtd->erasesize; for (k = 1; k < 33; ++k) { - if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize) + if (addr + (subpgsize * k) > (loff_t)(ebnum + 1) * mtd->erasesize) break; prandom_bytes_state(&rnd_state, writebuf, subpgsize * k); err = mtd_write(mtd, addr, subpgsize * k, &written, writebuf); @@ -195,7 +195,7 @@ static int verify_eraseblock2(int ebnum) loff_t addr = (loff_t)ebnum * mtd->erasesize; for (k = 1; k < 33; ++k) { - if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize) + if (addr + (subpgsize * k) > (loff_t)(ebnum + 1) * mtd->erasesize) break; prandom_bytes_state(&rnd_state, writebuf, subpgsize * k); clear_data(readbuf, subpgsize * k); @@ -269,7 +269,10 @@ static int verify_all_eraseblocks_ff(void) return err; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + return err; } pr_info("verified %u eraseblocks\n", i); return 0; @@ -346,7 +349,10 @@ static int __init mtd_subpagetest_init(void) goto out; if (i % 256 == 0) pr_info("written up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("written %u eraseblocks\n", i); @@ -360,7 +366,10 @@ static int __init mtd_subpagetest_init(void) goto out; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("verified %u eraseblocks\n", i); @@ -383,7 +392,10 @@ static int __init mtd_subpagetest_init(void) goto out; if (i % 256 == 0) pr_info("written up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("written %u eraseblocks\n", i); @@ -398,7 +410,10 @@ static int __init mtd_subpagetest_init(void) goto out; if (i % 256 == 0) pr_info("verified up to eraseblock %u\n", i); - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } pr_info("verified %u eraseblocks\n", i); diff --git a/drivers/mtd/tests/torturetest.c b/drivers/mtd/tests/torturetest.c index b55bc52a1340..e5d6e6d9532f 100644 --- a/drivers/mtd/tests/torturetest.c +++ b/drivers/mtd/tests/torturetest.c @@ -101,11 +101,11 @@ static inline int check_eraseblock(int ebnum, unsigned char *buf) { int err, retries = 0; size_t read; - loff_t addr = ebnum * mtd->erasesize; + loff_t addr = (loff_t)ebnum * mtd->erasesize; size_t len = mtd->erasesize; if (pgcnt) { - addr = (ebnum + 1) * mtd->erasesize - pgcnt * pgsize; + addr = (loff_t)(ebnum + 1) * mtd->erasesize - pgcnt * pgsize; len = pgcnt * pgsize; } @@ -155,11 +155,11 @@ static inline int write_pattern(int ebnum, void *buf) { int err; size_t written; - loff_t addr = ebnum * mtd->erasesize; + loff_t addr = (loff_t)ebnum * mtd->erasesize; size_t len = mtd->erasesize; if (pgcnt) { - addr = (ebnum + 1) * mtd->erasesize - pgcnt * pgsize; + addr = (loff_t)(ebnum + 1) * mtd->erasesize - pgcnt * pgsize; len = pgcnt * pgsize; } err = mtd_write(mtd, addr, len, &written, buf); @@ -279,7 +279,10 @@ static int __init tort_init(void) " for 0xFF... pattern\n"); goto out; } - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } } @@ -294,7 +297,10 @@ static int __init tort_init(void) err = write_pattern(i, patt); if (err) goto out; - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } /* Verify what we wrote */ @@ -314,7 +320,10 @@ static int __init tort_init(void) "0x55AA55..." : "0xAA55AA..."); goto out; } - cond_resched(); + + err = mtdtest_relax(); + if (err) + goto out; } } diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 9690cf9aaef5..b7f824d5ee88 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1169,9 +1169,9 @@ static struct mtd_info * __init open_mtd_by_chdev(const char *mtd_dev) return ERR_PTR(err); /* MTD device number is defined by the major / minor numbers */ - major = imajor(path.dentry->d_inode); - minor = iminor(path.dentry->d_inode); - mode = path.dentry->d_inode->i_mode; + major = imajor(d_backing_inode(path.dentry)); + minor = iminor(d_backing_inode(path.dentry)); + mode = d_backing_inode(path.dentry)->i_mode; path_put(&path); if (major != MTD_CHAR_MAJOR || !S_ISCHR(mode)) return ERR_PTR(-EINVAL); diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c index 478e00cf2d9e..e844887732fb 100644 --- a/drivers/mtd/ubi/kapi.c +++ b/drivers/mtd/ubi/kapi.c @@ -314,7 +314,7 @@ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode) if (error) return ERR_PTR(error); - inode = path.dentry->d_inode; + inode = d_backing_inode(path.dentry); mod = inode->i_mode; ubi_num = ubi_major2num(imajor(inode)); vol_id = iminor(inode) - 1; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78dde56ae6e6..3a10551d64cf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -82,6 +82,8 @@ #include <net/bond_3ad.h> #include <net/bond_alb.h> +#include "bonding_priv.h" + /*---------------------------- Module parameters ----------------------------*/ /* monitor all links that often (in milliseconds). <=0 disables monitoring */ diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 62694cfc05b6..b20b35acb47d 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -4,6 +4,7 @@ #include <net/netns/generic.h> #include <net/bonding.h> +#include "bonding_priv.h" static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h new file mode 100644 index 000000000000..5a4d81a9437c --- /dev/null +++ b/drivers/net/bonding/bonding_priv.h @@ -0,0 +1,25 @@ +/* + * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. + * + * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes + * NCM: Network and Communications Management, Inc. + * + * BUT, I'm the one who modified it for ethernet, so: + * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov + * + * This software may be used and distributed according to the terms + * of the GNU Public License, incorporated herein by reference. + * + */ + +#ifndef _BONDING_PRIV_H +#define _BONDING_PRIV_H + +#define DRV_VERSION "3.7.1" +#define DRV_RELDATE "April 27, 2011" +#define DRV_NAME "bonding" +#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" + +#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" + +#endif diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 4643914859b2..8b17a9065b0b 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1102,7 +1102,7 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv, if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME | MSG_FLAG_NERR)) { - netdev_err(priv->netdev, "Unknow error (flags: 0x%02x)\n", + netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n", msg->u.rx_can_header.flag); stats->rx_errors++; diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index b36ee9e0d220..d686b9cac29f 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -523,7 +523,7 @@ static int etherh_addr(char *addr, struct expansion_card *ec) char *s; if (!ecard_readchunk(&cd, ec, 0xf5, 0)) { - printk(KERN_ERR "%s: unable to read podule description string\n", + printk(KERN_ERR "%s: unable to read module description string\n", dev_name(&ec->dev)); goto no_addr; } diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h index eba070f16782..89cd11d86642 100644 --- a/drivers/net/ethernet/altera/altera_msgdmahw.h +++ b/drivers/net/ethernet/altera/altera_msgdmahw.h @@ -58,15 +58,12 @@ struct msgdma_extended_desc { /* Tx buffer control flags */ #define MSGDMA_DESC_CTL_TX_FIRST (MSGDMA_DESC_CTL_GEN_SOP | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) -#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_TR_ERR_IRQ | \ - MSGDMA_DESC_CTL_GO) +#define MSGDMA_DESC_CTL_TX_MIDDLE (MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_LAST (MSGDMA_DESC_CTL_GEN_EOP | \ MSGDMA_DESC_CTL_TR_COMP_IRQ | \ - MSGDMA_DESC_CTL_TR_ERR_IRQ | \ MSGDMA_DESC_CTL_GO) #define MSGDMA_DESC_CTL_TX_SINGLE (MSGDMA_DESC_CTL_GEN_SOP | \ diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 90a76306ad0f..0533c051a3e5 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -777,6 +777,8 @@ static int init_phy(struct net_device *dev) struct altera_tse_private *priv = netdev_priv(dev); struct phy_device *phydev; struct device_node *phynode; + bool fixed_link = false; + int rc = 0; /* Avoid init phy in case of no phy present */ if (!priv->phy_iface) @@ -789,13 +791,32 @@ static int init_phy(struct net_device *dev) phynode = of_parse_phandle(priv->device->of_node, "phy-handle", 0); if (!phynode) { - netdev_dbg(dev, "no phy-handle found\n"); - if (!priv->mdio) { - netdev_err(dev, - "No phy-handle nor local mdio specified\n"); - return -ENODEV; + /* check if a fixed-link is defined in device-tree */ + if (of_phy_is_fixed_link(priv->device->of_node)) { + rc = of_phy_register_fixed_link(priv->device->of_node); + if (rc < 0) { + netdev_err(dev, "cannot register fixed PHY\n"); + return rc; + } + + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ + phynode = of_node_get(priv->device->of_node); + fixed_link = true; + + netdev_dbg(dev, "fixed-link detected\n"); + phydev = of_phy_connect(dev, phynode, + &altera_tse_adjust_link, + 0, priv->phy_iface); + } else { + netdev_dbg(dev, "no phy-handle found\n"); + if (!priv->mdio) { + netdev_err(dev, "No phy-handle nor local mdio specified\n"); + return -ENODEV; + } + phydev = connect_local_phy(dev); } - phydev = connect_local_phy(dev); } else { netdev_dbg(dev, "phy-handle found\n"); phydev = of_phy_connect(dev, phynode, @@ -819,10 +840,10 @@ static int init_phy(struct net_device *dev) /* Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent - * device as well. + * device as well. If a fixed-link is used the phy_id is always 0. * Note: phydev->phy_id is the result of reading the UID PHY registers. */ - if (phydev->phy_id == 0) { + if ((phydev->phy_id == 0) && !fixed_link) { netdev_err(dev, "Bad PHY UID 0x%08x\n", phydev->phy_id); phy_disconnect(phydev); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 6f7dc81581ff..3558a36b1c2d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2485,8 +2485,10 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index) else if (bp->flags & GRO_ENABLE_FLAG) fp->mode = TPA_MODE_GRO; - /* We don't want TPA on an FCoE L2 ring */ - if (IS_FCOE_FP(fp)) + /* We don't want TPA if it's disabled in bp + * or if this is an FCoE L2 ring. + */ + if (bp->disable_tpa || IS_FCOE_FP(fp)) fp->disable_tpa = 1; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 1270b189a9a2..069952fa5d64 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18129,7 +18129,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, rtnl_lock(); - tp->pcierr_recovery = true; + /* We needn't recover from permanent error */ + if (state == pci_channel_io_frozen) + tp->pcierr_recovery = true; /* We probably don't have netdev yet */ if (!netdev || !netif_running(netdev)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index f0285bcbe598..371f75e782e5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -538,7 +538,7 @@ static ssize_t tp_la_write(struct file *file, const char __user *buf, char s[32]; unsigned long val; size_t size = min(sizeof(s) - 1, count); - struct adapter *adap = FILE_DATA(file)->i_private; + struct adapter *adap = file_inode(file)->i_private; if (copy_from_user(s, buf, size)) return -EFAULT; @@ -647,7 +647,7 @@ static int pm_stats_open(struct inode *inode, struct file *file) static ssize_t pm_stats_clear(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct adapter *adap = FILE_DATA(file)->i_private; + struct adapter *adap = file_inode(file)->i_private; t4_write_reg(adap, PM_RX_STAT_CONFIG_A, 0); t4_write_reg(adap, PM_TX_STAT_CONFIG_A, 0); @@ -1005,7 +1005,7 @@ static ssize_t mbox_write(struct file *file, const char __user *buf, &data[7], &c) < 8 || c != '\n') return -EINVAL; - ino = FILE_DATA(file); + ino = file_inode(file); mbox = (uintptr_t)ino->i_private & 7; adap = ino->i_private - mbox; addr = adap->regs + PF_REG(mbox, CIM_PF_MAILBOX_DATA_A); @@ -1034,7 +1034,7 @@ static ssize_t flash_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { loff_t pos = *ppos; - loff_t avail = FILE_DATA(file)->i_size; + loff_t avail = file_inode(file)->i_size; struct adapter *adap = file->private_data; if (pos < 0) @@ -1479,7 +1479,7 @@ static ssize_t rss_key_write(struct file *file, const char __user *buf, int i, j; u32 key[10]; char s[100], *p; - struct adapter *adap = FILE_DATA(file)->i_private; + struct adapter *adap = file_inode(file)->i_private; if (count > sizeof(s) - 1) return -EINVAL; @@ -1951,12 +1951,6 @@ static const struct file_operations mem_debugfs_fops = { .llseek = default_llseek, }; -static void set_debugfs_file_size(struct dentry *de, loff_t size) -{ - if (!IS_ERR(de) && de->d_inode) - de->d_inode->i_size = size; -} - static void add_debugfs_mem(struct adapter *adap, const char *name, unsigned int idx, unsigned int size_mb) { @@ -2072,9 +2066,8 @@ int t4_setup_debugfs(struct adapter *adap) } } - de = debugfs_create_file("flash", S_IRUSR, adap->debugfs_root, adap, - &flash_debugfs_fops); - set_debugfs_file_size(de, adap->params.sf_size); + de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap, + &flash_debugfs_fops, adap->params.sf_size); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h index 8f418ba868bd..23f43a0f8950 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h @@ -37,8 +37,6 @@ #include <linux/export.h> -#define FILE_DATA(_file) ((_file)->f_path.dentry->d_inode) - #define DEFINE_SIMPLE_DEBUGFS_FILE(name) \ static int name##_open(struct inode *inode, struct file *file) \ { \ diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 291c87036e17..2a0dc127df3f 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3347,7 +3347,7 @@ static int ehea_register_memory_hooks(void) { int ret = 0; - if (atomic_inc_and_test(&ehea_memory_hooks_registered)) + if (atomic_inc_return(&ehea_memory_hooks_registered) > 1) return 0; ret = ehea_create_busmap(); @@ -3381,12 +3381,14 @@ out3: out2: unregister_reboot_notifier(&ehea_reboot_nb); out: + atomic_dec(&ehea_memory_hooks_registered); return ret; } static void ehea_unregister_memory_hooks(void) { - if (atomic_read(&ehea_memory_hooks_registered)) + /* Only remove the hooks if we've registered them */ + if (atomic_read(&ehea_memory_hooks_registered) == 0) return; unregister_reboot_notifier(&ehea_reboot_nb); diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index af829c578400..7ace07dad6a3 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev) np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); if (!np) { dev_err(&pdev->dev, "missing phy-handle\n"); - return -EINVAL; + err = -EINVAL; + goto err_netdev; } of_property_read_u32(np, "reg", &pep->phy_addr); pep->phy_intf = of_get_phy_mode(pdev->dev.of_node); @@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) pep->smi_bus = mdiobus_alloc(); if (pep->smi_bus == NULL) { err = -ENOMEM; - goto err_base; + goto err_netdev; } pep->smi_bus->priv = pep; pep->smi_bus->name = "pxa168_eth smi"; @@ -1551,13 +1552,10 @@ err_mdiobus: mdiobus_unregister(pep->smi_bus); err_free_mdio: mdiobus_free(pep->smi_bus); -err_base: - iounmap(pep->base); err_netdev: free_netdev(dev); err_clk: - clk_disable(clk); - clk_put(clk); + clk_disable_unprepare(clk); return err; } @@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev) if (pep->phy) phy_disconnect(pep->phy); if (pep->clk) { - clk_disable(pep->clk); - clk_put(pep->clk); - pep->clk = NULL; + clk_disable_unprepare(pep->clk); } - iounmap(pep->base); - pep->base = NULL; mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); unregister_netdev(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index f0fbb4ade85d..4f7dc044601e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -939,21 +939,34 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, return err; } if (smp->attr_id == IB_SMP_ATTR_GUID_INFO) { - /* compute slave's gid block */ - smp->attr_mod = cpu_to_be32(slave / 8); - /* execute cmd */ - err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, - vhcr->in_modifier, opcode_modifier, - vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); - if (!err) { - /* if needed, move slave gid to index 0 */ - if (slave % 8) - memcpy(outsmp->data, - outsmp->data + (slave % 8) * 8, 8); - /* delete all other gids */ - memset(outsmp->data + 8, 0, 56); + __be64 guid = mlx4_get_admin_guid(dev, slave, + port); + + /* set the PF admin guid to the FW/HW burned + * GUID, if it wasn't yet set + */ + if (slave == 0 && guid == 0) { + smp->attr_mod = 0; + err = mlx4_cmd_box(dev, + inbox->dma, + outbox->dma, + vhcr->in_modifier, + opcode_modifier, + vhcr->op, + MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (err) + return err; + mlx4_set_admin_guid(dev, + *(__be64 *)outsmp-> + data, slave, port); + } else { + memcpy(outsmp->data, &guid, 8); } - return err; + + /* clean all other gids */ + memset(outsmp->data + 8, 0, 56); + return 0; } if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) { err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, @@ -2350,6 +2363,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) oper_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT; vf_oper->vport[port].vlan_idx = NO_INDX; vf_oper->vport[port].mac_idx = NO_INDX; + mlx4_set_random_admin_guid(dev, i, port); } spin_lock_init(&s_state->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3f44e2bbb982..a2ddf3d75ff8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1102,20 +1102,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc) struct mlx4_en_priv *priv = netdev_priv(dev); /* check if requested function is supported by the device */ - if ((hfunc == ETH_RSS_HASH_TOP && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) || - (hfunc == ETH_RSS_HASH_XOR && - !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))) - return -EINVAL; + if (hfunc == ETH_RSS_HASH_TOP) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) + return -EINVAL; + if (!(dev->features & NETIF_F_RXHASH)) + en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); + return 0; + } else if (hfunc == ETH_RSS_HASH_XOR) { + if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)) + return -EINVAL; + if (dev->features & NETIF_F_RXHASH) + en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); + return 0; + } - priv->rss_hash_fn = hfunc; - if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n"); - if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH)) - en_warn(priv, - "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n"); - return 0; + return -EINVAL; } static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key, @@ -1189,6 +1190,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index, priv->prof->rss_rings = rss_rings; if (key) memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE); + if (hfunc != ETH_RSS_HASH_NO_CHANGE) + priv->rss_hash_fn = hfunc; if (port_up) { err = mlx4_en_start_port(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 190fd624bdfe..2619c9fbf42d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -702,6 +702,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) priv->mfunc.master.slave_state[flr_slave].is_slave_going_down = 1; } spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags); + mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN, + flr_slave); queue_work(priv->mfunc.master.comm_wq, &priv->mfunc.master.slave_flr_event_work); break; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index acceb75e8c44..ced5ecab5aa7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2260,6 +2260,37 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx) } EXPORT_SYMBOL_GPL(mlx4_counter_free); +void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + priv->mfunc.master.vf_admin[entry].vport[port].guid = guid; +} +EXPORT_SYMBOL_GPL(mlx4_set_admin_guid); + +__be64 mlx4_get_admin_guid(struct mlx4_dev *dev, int entry, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + return priv->mfunc.master.vf_admin[entry].vport[port].guid; +} +EXPORT_SYMBOL_GPL(mlx4_get_admin_guid); + +void mlx4_set_random_admin_guid(struct mlx4_dev *dev, int entry, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + __be64 guid; + + /* hw GUID */ + if (entry == 0) + return; + + get_random_bytes((char *)&guid, sizeof(guid)); + guid &= ~(cpu_to_be64(1ULL << 56)); + guid |= cpu_to_be64(1ULL << 57); + priv->mfunc.master.vf_admin[entry].vport[port].guid = guid; +} + static int mlx4_setup_hca(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index f30eeb730a86..502d3dd2c888 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -499,6 +499,7 @@ struct mlx4_vport_state { bool spoofchk; u32 link_state; u8 qos_vport; + __be64 guid; }; struct mlx4_vf_admin_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index df2238372ea7..8a64542abc16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -211,26 +211,28 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr) return 0; } +#define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT) + static void free_4k(struct mlx5_core_dev *dev, u64 addr) { struct fw_page *fwp; int n; - fwp = find_fw_page(dev, addr & PAGE_MASK); + fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK); if (!fwp) { mlx5_core_warn(dev, "page not found\n"); return; } - n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT; + n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT; fwp->free_count++; set_bit(n, &fwp->bitmask); if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) { rb_erase(&fwp->rb_node, &dev->priv.page_root); if (fwp->free_count != 1) list_del(&fwp->list); - dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE, - DMA_BIDIRECTIONAL); + dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK, + PAGE_SIZE, DMA_BIDIRECTIONAL); __free_page(fwp->page); kfree(fwp); } else if (fwp->free_count == 1) { diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 2bef655279f3..9b7e0a34c98b 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -1765,7 +1765,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, ALE_PORT_STATE, ALE_PORT_STATE_FORWARD); - if (ndev && slave->open) + if (ndev && slave->open && + slave->link_interface != SGMII_LINK_MAC_PHY && + slave->link_interface != XGMII_LINK_MAC_PHY) netif_carrier_on(ndev); } else { writel(mac_control, GBE_REG_ADDR(slave, emac_regs, @@ -1773,7 +1775,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, cpsw_ale_control_set(gbe_dev->ale, slave->port_num, ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); - if (ndev) + if (ndev && + slave->link_interface != SGMII_LINK_MAC_PHY && + slave->link_interface != XGMII_LINK_MAC_PHY) netif_carrier_off(ndev); } diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 49ce7ece5af3..c9cb486c753d 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -80,7 +80,8 @@ static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir) * assume the pin serves as pull-up. If direction is * output, the default value is high. */ - gpio_set_value(bitbang->mdo, 1 ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + 1 ^ bitbang->mdo_active_low); return; } @@ -96,7 +97,8 @@ static int mdio_get(struct mdiobb_ctrl *ctrl) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - return gpio_get_value(bitbang->mdio) ^ bitbang->mdio_active_low; + return gpio_get_value_cansleep(bitbang->mdio) ^ + bitbang->mdio_active_low; } static void mdio_set(struct mdiobb_ctrl *ctrl, int what) @@ -105,9 +107,11 @@ static void mdio_set(struct mdiobb_ctrl *ctrl, int what) container_of(ctrl, struct mdio_gpio_info, ctrl); if (bitbang->mdo) - gpio_set_value(bitbang->mdo, what ^ bitbang->mdo_active_low); + gpio_set_value_cansleep(bitbang->mdo, + what ^ bitbang->mdo_active_low); else - gpio_set_value(bitbang->mdio, what ^ bitbang->mdio_active_low); + gpio_set_value_cansleep(bitbang->mdio, + what ^ bitbang->mdio_active_low); } static void mdc_set(struct mdiobb_ctrl *ctrl, int what) @@ -115,7 +119,7 @@ static void mdc_set(struct mdiobb_ctrl *ctrl, int what) struct mdio_gpio_info *bitbang = container_of(ctrl, struct mdio_gpio_info, ctrl); - gpio_set_value(bitbang->mdc, what ^ bitbang->mdc_active_low); + gpio_set_value_cansleep(bitbang->mdc, what ^ bitbang->mdc_active_low); } static struct mdiobb_ops mdio_gpio_ops = { diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c index 1a87a585e74d..66edd99bc302 100644 --- a/drivers/net/phy/mdio-mux-gpio.c +++ b/drivers/net/phy/mdio-mux-gpio.c @@ -12,33 +12,30 @@ #include <linux/module.h> #include <linux/phy.h> #include <linux/mdio-mux.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> #define DRV_VERSION "1.1" #define DRV_DESCRIPTION "GPIO controlled MDIO bus multiplexer driver" -#define MDIO_MUX_GPIO_MAX_BITS 8 - struct mdio_mux_gpio_state { - struct gpio_desc *gpio[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int num_gpios; + struct gpio_descs *gpios; void *mux_handle; }; static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, void *data) { - int values[MDIO_MUX_GPIO_MAX_BITS]; - unsigned int n; struct mdio_mux_gpio_state *s = data; + int values[s->gpios->ndescs]; + unsigned int n; if (current_child == desired_child) return 0; - for (n = 0; n < s->num_gpios; n++) { + for (n = 0; n < s->gpios->ndescs; n++) values[n] = (desired_child >> n) & 1; - } - gpiod_set_array_cansleep(s->num_gpios, s->gpio, values); + + gpiod_set_array_cansleep(s->gpios->ndescs, s->gpios->desc, values); return 0; } @@ -46,56 +43,33 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child, static int mdio_mux_gpio_probe(struct platform_device *pdev) { struct mdio_mux_gpio_state *s; - int num_gpios; - unsigned int n; int r; - if (!pdev->dev.of_node) - return -ENODEV; - - num_gpios = of_gpio_count(pdev->dev.of_node); - if (num_gpios <= 0 || num_gpios > MDIO_MUX_GPIO_MAX_BITS) - return -ENODEV; - s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; - s->num_gpios = num_gpios; - - for (n = 0; n < num_gpios; ) { - struct gpio_desc *gpio = gpiod_get_index(&pdev->dev, NULL, n, - GPIOD_OUT_LOW); - if (IS_ERR(gpio)) { - r = PTR_ERR(gpio); - goto err; - } - s->gpio[n] = gpio; - n++; - } + s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW); + if (IS_ERR(s->gpios)) + return PTR_ERR(s->gpios); r = mdio_mux_init(&pdev->dev, mdio_mux_gpio_switch_fn, &s->mux_handle, s); - if (r == 0) { - pdev->dev.platform_data = s; - return 0; - } -err: - while (n) { - n--; - gpiod_put(s->gpio[n]); + if (r != 0) { + gpiod_put_array(s->gpios); + return r; } - return r; + + pdev->dev.platform_data = s; + return 0; } static int mdio_mux_gpio_remove(struct platform_device *pdev) { - unsigned int n; struct mdio_mux_gpio_state *s = dev_get_platdata(&pdev->dev); mdio_mux_uninit(s->mux_handle); - for (n = 0; n < s->num_gpios; n++) - gpiod_put(s->gpio[n]); + gpiod_put_array(s->gpios); return 0; } diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index 911b21602ff2..05005c660d4d 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -478,7 +478,6 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, struct blkcipher_desc desc = { .tfm = state->arc4 }; unsigned ccount; int flushed = MPPE_BITS(ibuf) & MPPE_BIT_FLUSHED; - int sanity = 0; struct scatterlist sg_in[1], sg_out[1]; if (isize <= PPP_HDRLEN + MPPE_OVHD) { @@ -514,31 +513,19 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, "mppe_decompress[%d]: ENCRYPTED bit not set!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (!state->stateful && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set in " "stateless mode!\n", state->unit); state->sanity_errors += 100; - sanity = 1; + goto sanity_error; } if (state->stateful && ((ccount & 0xff) == 0xff) && !flushed) { printk(KERN_DEBUG "mppe_decompress[%d]: FLUSHED bit not set on " "flag packet!\n", state->unit); state->sanity_errors += 100; - sanity = 1; - } - - if (sanity) { - if (state->sanity_errors < SANITY_MAX) - return DECOMP_ERROR; - else - /* - * Take LCP down if the peer is sending too many bogons. - * We don't want to do this for a single or just a few - * instances since it could just be due to packet corruption. - */ - return DECOMP_FATALERROR; + goto sanity_error; } /* @@ -546,6 +533,13 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, */ if (!state->stateful) { + /* Discard late packet */ + if ((ccount - state->ccount) % MPPE_CCOUNT_SPACE + > MPPE_CCOUNT_SPACE / 2) { + state->sanity_errors++; + goto sanity_error; + } + /* RFC 3078, sec 8.1. Rekey for every packet. */ while (state->ccount != ccount) { mppe_rekey(state, 0); @@ -649,6 +643,16 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, state->sanity_errors >>= 1; return osize; + +sanity_error: + if (state->sanity_errors < SANITY_MAX) + return DECOMP_ERROR; + else + /* Take LCP down if the peer is sending too many bogons. + * We don't want to do this for a single or just a few + * instances since it could just be due to packet corruption. + */ + return DECOMP_FATALERROR; } /* diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 1470b5227834..07bb3c8f191b 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -50,7 +50,7 @@ config OF_ADDRESS_PCI config OF_IRQ def_bool y - depends on !SPARC + depends on !SPARC && IRQ_DOMAIN config OF_NET depends on NETDEVICES diff --git a/drivers/of/base.c b/drivers/of/base.c index a1aa0c7dee50..99764db0875a 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -568,6 +568,29 @@ bool of_device_is_available(const struct device_node *device) EXPORT_SYMBOL(of_device_is_available); /** + * of_device_is_big_endian - check if a device has BE registers + * + * @device: Node to check for endianness + * + * Returns true if the device has a "big-endian" property, or if the kernel + * was compiled for BE *and* the device has a "native-endian" property. + * Returns false otherwise. + * + * Callers would nominally use ioread32be/iowrite32be if + * of_device_is_big_endian() == true, or readl/writel otherwise. + */ +bool of_device_is_big_endian(const struct device_node *device) +{ + if (of_property_read_bool(device, "big-endian")) + return true; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) && + of_property_read_bool(device, "native-endian")) + return true; + return false; +} +EXPORT_SYMBOL(of_device_is_big_endian); + +/** * of_get_parent - Get a node's parent if any * @node: Node to get parent * @@ -640,8 +663,9 @@ static struct device_node *__of_get_next_child(const struct device_node *node, * @node: parent node * @prev: previous child of the parent node, or NULL to get first * - * Returns a node pointer with refcount incremented, use - * of_node_put() on it when done. + * Returns a node pointer with refcount incremented, use of_node_put() on + * it when done. Returns NULL when prev is the last child. Decrements the + * refcount of prev. */ struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 3a896c9aeb74..cde35c5d0191 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -109,6 +109,25 @@ int of_fdt_is_compatible(const void *blob, } /** + * of_fdt_is_big_endian - Return true if given node needs BE MMIO accesses + * @blob: A device tree blob + * @node: node to test + * + * Returns true if the node has a "big-endian" property, or if the kernel + * was compiled for BE *and* the node has a "native-endian" property. + * Returns false otherwise. + */ +bool of_fdt_is_big_endian(const void *blob, unsigned long node) +{ + if (fdt_getprop(blob, node, "big-endian", NULL)) + return true; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) && + fdt_getprop(blob, node, "native-endian", NULL)) + return true; + return false; +} + +/** * of_fdt_match - Return true if node matches a list of compatible values */ int of_fdt_match(const void *blob, unsigned long node, @@ -172,7 +191,7 @@ static void * unflatten_dt_node(void *blob, if (!pathp) return mem; - allocl = l++; + allocl = ++l; /* version 0x10 has a more compact unit name here instead of the full * path. we accumulate the full path size using "fpsize", we'll rebuild @@ -879,8 +898,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname, endp = reg + (l / sizeof(__be32)); - pr_debug("memory scan node %s, reg size %d, data: %x %x %x %x,\n", - uname, l, reg[0], reg[1], reg[2], reg[3]); + pr_debug("memory scan node %s, reg size %d,\n", uname, l); while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { u64 base, size; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index e844907c9efa..18016341d5a9 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -23,6 +23,8 @@ #include <linux/i2c.h> #include <linux/i2c-mux.h> +#include <linux/bitops.h> + #include "of_private.h" static struct unittest_results { @@ -1109,6 +1111,59 @@ static const char *overlay_path(int nr) static const char *bus_path = "/testcase-data/overlay-node/test-bus"; +/* it is guaranteed that overlay ids are assigned in sequence */ +#define MAX_UNITTEST_OVERLAYS 256 +static unsigned long overlay_id_bits[BITS_TO_LONGS(MAX_UNITTEST_OVERLAYS)]; +static int overlay_first_id = -1; + +static void of_unittest_track_overlay(int id) +{ + if (overlay_first_id < 0) + overlay_first_id = id; + id -= overlay_first_id; + + /* we shouldn't need that many */ + BUG_ON(id >= MAX_UNITTEST_OVERLAYS); + overlay_id_bits[BIT_WORD(id)] |= BIT_MASK(id); +} + +static void of_unittest_untrack_overlay(int id) +{ + if (overlay_first_id < 0) + return; + id -= overlay_first_id; + BUG_ON(id >= MAX_UNITTEST_OVERLAYS); + overlay_id_bits[BIT_WORD(id)] &= ~BIT_MASK(id); +} + +static void of_unittest_destroy_tracked_overlays(void) +{ + int id, ret, defers; + + if (overlay_first_id < 0) + return; + + /* try until no defers */ + do { + defers = 0; + /* remove in reverse order */ + for (id = MAX_UNITTEST_OVERLAYS - 1; id >= 0; id--) { + if (!(overlay_id_bits[BIT_WORD(id)] & BIT_MASK(id))) + continue; + + ret = of_overlay_destroy(id + overlay_first_id); + if (ret != 0) { + defers++; + pr_warn("%s: overlay destroy failed for #%d\n", + __func__, id + overlay_first_id); + continue; + } + + overlay_id_bits[BIT_WORD(id)] &= ~BIT_MASK(id); + } + } while (defers > 0); +} + static int of_unittest_apply_overlay(int unittest_nr, int overlay_nr, int *overlay_id) { @@ -1130,6 +1185,7 @@ static int of_unittest_apply_overlay(int unittest_nr, int overlay_nr, goto out; } id = ret; + of_unittest_track_overlay(id); ret = 0; @@ -1343,6 +1399,7 @@ static void of_unittest_overlay_6(void) return; } ov_id[i] = ret; + of_unittest_track_overlay(ov_id[i]); } for (i = 0; i < 2; i++) { @@ -1367,6 +1424,7 @@ static void of_unittest_overlay_6(void) PDEV_OVERLAY)); return; } + of_unittest_untrack_overlay(ov_id[i]); } for (i = 0; i < 2; i++) { @@ -1411,6 +1469,7 @@ static void of_unittest_overlay_8(void) return; } ov_id[i] = ret; + of_unittest_track_overlay(ov_id[i]); } /* now try to remove first overlay (it should fail) */ @@ -1433,6 +1492,7 @@ static void of_unittest_overlay_8(void) PDEV_OVERLAY)); return; } + of_unittest_untrack_overlay(ov_id[i]); } unittest(1, "overlay test %d passed\n", 8); @@ -1855,6 +1915,8 @@ static void __init of_unittest_overlay(void) of_unittest_overlay_i2c_cleanup(); #endif + of_unittest_destroy_tracked_overlays(); + out: of_node_put(bus_np); } diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index 3f493459378f..dd92c5edf219 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -138,22 +138,22 @@ static int __oprofilefs_create_file(struct dentry *root, char const *name, struct dentry *dentry; struct inode *inode; - mutex_lock(&root->d_inode->i_mutex); + mutex_lock(&d_inode(root)->i_mutex); dentry = d_alloc_name(root, name); if (!dentry) { - mutex_unlock(&root->d_inode->i_mutex); + mutex_unlock(&d_inode(root)->i_mutex); return -ENOMEM; } inode = oprofilefs_get_inode(root->d_sb, S_IFREG | perm); if (!inode) { dput(dentry); - mutex_unlock(&root->d_inode->i_mutex); + mutex_unlock(&d_inode(root)->i_mutex); return -ENOMEM; } inode->i_fop = fops; inode->i_private = priv; d_add(dentry, inode); - mutex_unlock(&root->d_inode->i_mutex); + mutex_unlock(&d_inode(root)->i_mutex); return 0; } @@ -215,22 +215,22 @@ struct dentry *oprofilefs_mkdir(struct dentry *parent, char const *name) struct dentry *dentry; struct inode *inode; - mutex_lock(&parent->d_inode->i_mutex); + mutex_lock(&d_inode(parent)->i_mutex); dentry = d_alloc_name(parent, name); if (!dentry) { - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); return NULL; } inode = oprofilefs_get_inode(parent->d_sb, S_IFDIR | 0755); if (!inode) { dput(dentry); - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); return NULL; } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; d_add(dentry, inode); - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&d_inode(parent)->i_mutex); return dentry; } diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index 440ed776efd4..2a6531a5fde8 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -4,7 +4,7 @@ menuconfig CHROME_PLATFORMS bool "Platform support for Chrome hardware" - depends on X86 + depends on X86 || ARM ---help--- Say Y here to get to see options for platform support for various Chromebooks and Chromeboxes. This option alone does @@ -16,8 +16,7 @@ if CHROME_PLATFORMS config CHROMEOS_LAPTOP tristate "Chrome OS Laptop" - depends on I2C - depends on DMI + depends on I2C && DMI && X86 ---help--- This driver instantiates i2c and smbus devices such as light sensors and touchpads. @@ -27,6 +26,7 @@ config CHROMEOS_LAPTOP config CHROMEOS_PSTORE tristate "Chrome OS pstore support" + depends on X86 ---help--- This module instantiates the persistent storage on x86 ChromeOS devices. It can be used to store away console logs and crash @@ -38,5 +38,25 @@ config CHROMEOS_PSTORE If you have a supported Chromebook, choose Y or M here. The module will be called chromeos_pstore. +config CROS_EC_CHARDEV + tristate "Chrome OS Embedded Controller userspace device interface" + depends on MFD_CROS_EC + ---help--- + This driver adds support to talk with the ChromeOS EC from userspace. + + If you have a supported Chromebook, choose Y or M here. + The module will be called cros_ec_dev. + +config CROS_EC_LPC + tristate "ChromeOS Embedded Controller (LPC)" + depends on MFD_CROS_EC && (X86 || COMPILE_TEST) + help + If you say Y here, you get support for talking to the ChromeOS EC + over an LPC bus. This uses a simple byte-level protocol with a + checksum. This is used for userspace access only. The kernel + typically has its own communication methods. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_lpc. endif # CHROMEOS_PLATFORMS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 2b860ca7450f..bd8d8601e875 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -1,3 +1,6 @@ obj-$(CONFIG_CHROMEOS_LAPTOP) += chromeos_laptop.o obj-$(CONFIG_CHROMEOS_PSTORE) += chromeos_pstore.o +cros_ec_devs-objs := cros_ec_dev.o cros_ec_sysfs.o cros_ec_lightbar.o +obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_devs.o +obj-$(CONFIG_CROS_EC_LPC) += cros_ec_lpc.o diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index b84fdd6b629b..a04019ab9feb 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -133,12 +133,13 @@ static struct i2c_client *__add_probed_i2c_device( const char *name, int bus, struct i2c_board_info *info, - const unsigned short *addrs) + const unsigned short *alt_addr_list) { const struct dmi_device *dmi_dev; const struct dmi_dev_onboard *dev_data; struct i2c_adapter *adapter; - struct i2c_client *client; + struct i2c_client *client = NULL; + const unsigned short addr_list[] = { info->addr, I2C_CLIENT_END }; if (bus < 0) return NULL; @@ -169,8 +170,28 @@ static struct i2c_client *__add_probed_i2c_device( return NULL; } - /* add the i2c device */ - client = i2c_new_probed_device(adapter, info, addrs, NULL); + /* + * Add the i2c device. If we can't detect it at the primary + * address we scan secondary addresses. In any case the client + * structure gets assigned primary address. + */ + client = i2c_new_probed_device(adapter, info, addr_list, NULL); + if (!client && alt_addr_list) { + struct i2c_board_info dummy_info = { + I2C_BOARD_INFO("dummy", info->addr), + }; + struct i2c_client *dummy; + + dummy = i2c_new_probed_device(adapter, &dummy_info, + alt_addr_list, NULL); + if (dummy) { + pr_debug("%s %d-%02x is probed at %02x\n", + __func__, bus, info->addr, dummy->addr); + i2c_unregister_device(dummy); + client = i2c_new_device(adapter, info); + } + } + if (!client) pr_notice("%s failed to register device %d-%02x\n", __func__, bus, info->addr); @@ -254,12 +275,10 @@ static struct i2c_client *add_i2c_device(const char *name, enum i2c_adapter_type type, struct i2c_board_info *info) { - const unsigned short addr_list[] = { info->addr, I2C_CLIENT_END }; - return __add_probed_i2c_device(name, find_i2c_adapter_num(type), info, - addr_list); + NULL); } static int setup_cyapa_tp(enum i2c_adapter_type type) @@ -275,7 +294,6 @@ static int setup_cyapa_tp(enum i2c_adapter_type type) static int setup_atmel_224s_tp(enum i2c_adapter_type type) { const unsigned short addr_list[] = { ATMEL_TP_I2C_BL_ADDR, - ATMEL_TP_I2C_ADDR, I2C_CLIENT_END }; if (tp) return 0; @@ -289,7 +307,6 @@ static int setup_atmel_224s_tp(enum i2c_adapter_type type) static int setup_atmel_1664s_ts(enum i2c_adapter_type type) { const unsigned short addr_list[] = { ATMEL_TS_I2C_BL_ADDR, - ATMEL_TS_I2C_ADDR, I2C_CLIENT_END }; if (ts) return 0; diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c new file mode 100644 index 000000000000..6090d0b2826f --- /dev/null +++ b/drivers/platform/chrome/cros_ec_dev.c @@ -0,0 +1,274 @@ +/* + * cros_ec_dev - expose the Chrome OS Embedded Controller to user-space + * + * Copyright (C) 2014 Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/uaccess.h> + +#include "cros_ec_dev.h" + +/* Device variables */ +#define CROS_MAX_DEV 128 +static struct class *cros_class; +static int ec_major; + +/* Basic communication */ +static int ec_get_version(struct cros_ec_device *ec, char *str, int maxlen) +{ + struct ec_response_get_version *resp; + static const char * const current_image_name[] = { + "unknown", "read-only", "read-write", "invalid", + }; + struct cros_ec_command msg = { + .version = 0, + .command = EC_CMD_GET_VERSION, + .outdata = { 0 }, + .outsize = 0, + .indata = { 0 }, + .insize = sizeof(*resp), + }; + int ret; + + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + + if (msg.result != EC_RES_SUCCESS) { + snprintf(str, maxlen, + "%s\nUnknown EC version: EC returned %d\n", + CROS_EC_DEV_VERSION, msg.result); + return 0; + } + + resp = (struct ec_response_get_version *)msg.indata; + if (resp->current_image >= ARRAY_SIZE(current_image_name)) + resp->current_image = 3; /* invalid */ + + snprintf(str, maxlen, "%s\n%s\n%s\n%s\n", CROS_EC_DEV_VERSION, + resp->version_string_ro, resp->version_string_rw, + current_image_name[resp->current_image]); + + return 0; +} + +/* Device file ops */ +static int ec_device_open(struct inode *inode, struct file *filp) +{ + filp->private_data = container_of(inode->i_cdev, + struct cros_ec_device, cdev); + return 0; +} + +static int ec_device_release(struct inode *inode, struct file *filp) +{ + return 0; +} + +static ssize_t ec_device_read(struct file *filp, char __user *buffer, + size_t length, loff_t *offset) +{ + struct cros_ec_device *ec = filp->private_data; + char msg[sizeof(struct ec_response_get_version) + + sizeof(CROS_EC_DEV_VERSION)]; + size_t count; + int ret; + + if (*offset != 0) + return 0; + + ret = ec_get_version(ec, msg, sizeof(msg)); + if (ret) + return ret; + + count = min(length, strlen(msg)); + + if (copy_to_user(buffer, msg, count)) + return -EFAULT; + + *offset = count; + return count; +} + +/* Ioctls */ +static long ec_device_ioctl_xcmd(struct cros_ec_device *ec, void __user *arg) +{ + long ret; + struct cros_ec_command s_cmd = { }; + + if (copy_from_user(&s_cmd, arg, sizeof(s_cmd))) + return -EFAULT; + + ret = cros_ec_cmd_xfer(ec, &s_cmd); + /* Only copy data to userland if data was received. */ + if (ret < 0) + return ret; + + if (copy_to_user(arg, &s_cmd, sizeof(s_cmd))) + return -EFAULT; + + return 0; +} + +static long ec_device_ioctl_readmem(struct cros_ec_device *ec, void __user *arg) +{ + struct cros_ec_readmem s_mem = { }; + long num; + + /* Not every platform supports direct reads */ + if (!ec->cmd_readmem) + return -ENOTTY; + + if (copy_from_user(&s_mem, arg, sizeof(s_mem))) + return -EFAULT; + + num = ec->cmd_readmem(ec, s_mem.offset, s_mem.bytes, s_mem.buffer); + if (num <= 0) + return num; + + if (copy_to_user((void __user *)arg, &s_mem, sizeof(s_mem))) + return -EFAULT; + + return 0; +} + +static long ec_device_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct cros_ec_device *ec = filp->private_data; + + if (_IOC_TYPE(cmd) != CROS_EC_DEV_IOC) + return -ENOTTY; + + switch (cmd) { + case CROS_EC_DEV_IOCXCMD: + return ec_device_ioctl_xcmd(ec, (void __user *)arg); + case CROS_EC_DEV_IOCRDMEM: + return ec_device_ioctl_readmem(ec, (void __user *)arg); + } + + return -ENOTTY; +} + +/* Module initialization */ +static const struct file_operations fops = { + .open = ec_device_open, + .release = ec_device_release, + .read = ec_device_read, + .unlocked_ioctl = ec_device_ioctl, +}; + +static int ec_device_probe(struct platform_device *pdev) +{ + struct cros_ec_device *ec = dev_get_drvdata(pdev->dev.parent); + int retval = -ENOTTY; + dev_t devno = MKDEV(ec_major, 0); + + /* Instantiate it (and remember the EC) */ + cdev_init(&ec->cdev, &fops); + + retval = cdev_add(&ec->cdev, devno, 1); + if (retval) { + dev_err(&pdev->dev, ": failed to add character device\n"); + return retval; + } + + ec->vdev = device_create(cros_class, NULL, devno, ec, + CROS_EC_DEV_NAME); + if (IS_ERR(ec->vdev)) { + retval = PTR_ERR(ec->vdev); + dev_err(&pdev->dev, ": failed to create device\n"); + cdev_del(&ec->cdev); + return retval; + } + + /* Initialize extra interfaces */ + ec_dev_sysfs_init(ec); + ec_dev_lightbar_init(ec); + + return 0; +} + +static int ec_device_remove(struct platform_device *pdev) +{ + struct cros_ec_device *ec = dev_get_drvdata(pdev->dev.parent); + + ec_dev_lightbar_remove(ec); + ec_dev_sysfs_remove(ec); + device_destroy(cros_class, MKDEV(ec_major, 0)); + cdev_del(&ec->cdev); + return 0; +} + +static struct platform_driver cros_ec_dev_driver = { + .driver = { + .name = "cros-ec-ctl", + }, + .probe = ec_device_probe, + .remove = ec_device_remove, +}; + +static int __init cros_ec_dev_init(void) +{ + int ret; + dev_t dev = 0; + + cros_class = class_create(THIS_MODULE, "chromeos"); + if (IS_ERR(cros_class)) { + pr_err(CROS_EC_DEV_NAME ": failed to register device class\n"); + return PTR_ERR(cros_class); + } + + /* Get a range of minor numbers (starting with 0) to work with */ + ret = alloc_chrdev_region(&dev, 0, CROS_MAX_DEV, CROS_EC_DEV_NAME); + if (ret < 0) { + pr_err(CROS_EC_DEV_NAME ": alloc_chrdev_region() failed\n"); + goto failed_chrdevreg; + } + ec_major = MAJOR(dev); + + /* Register the driver */ + ret = platform_driver_register(&cros_ec_dev_driver); + if (ret < 0) { + pr_warn(CROS_EC_DEV_NAME ": can't register driver: %d\n", ret); + goto failed_devreg; + } + return 0; + +failed_devreg: + unregister_chrdev_region(MKDEV(ec_major, 0), CROS_MAX_DEV); +failed_chrdevreg: + class_destroy(cros_class); + return ret; +} + +static void __exit cros_ec_dev_exit(void) +{ + platform_driver_unregister(&cros_ec_dev_driver); + unregister_chrdev(ec_major, CROS_EC_DEV_NAME); + class_destroy(cros_class); +} + +module_init(cros_ec_dev_init); +module_exit(cros_ec_dev_exit); + +MODULE_AUTHOR("Bill Richardson <wfrichar@chromium.org>"); +MODULE_DESCRIPTION("Userspace interface to the Chrome OS Embedded Controller"); +MODULE_VERSION("1.0"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/chrome/cros_ec_dev.h b/drivers/platform/chrome/cros_ec_dev.h new file mode 100644 index 000000000000..45d67f7e518c --- /dev/null +++ b/drivers/platform/chrome/cros_ec_dev.h @@ -0,0 +1,53 @@ +/* + * cros_ec_dev - expose the Chrome OS Embedded Controller to userspace + * + * Copyright (C) 2014 Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _CROS_EC_DEV_H_ +#define _CROS_EC_DEV_H_ + +#include <linux/ioctl.h> +#include <linux/types.h> +#include <linux/mfd/cros_ec.h> + +#define CROS_EC_DEV_NAME "cros_ec" +#define CROS_EC_DEV_VERSION "1.0.0" + +/* + * @offset: within EC_LPC_ADDR_MEMMAP region + * @bytes: number of bytes to read. zero means "read a string" (including '\0') + * (at most only EC_MEMMAP_SIZE bytes can be read) + * @buffer: where to store the result + * ioctl returns the number of bytes read, negative on error + */ +struct cros_ec_readmem { + uint32_t offset; + uint32_t bytes; + uint8_t buffer[EC_MEMMAP_SIZE]; +}; + +#define CROS_EC_DEV_IOC 0xEC +#define CROS_EC_DEV_IOCXCMD _IOWR(CROS_EC_DEV_IOC, 0, struct cros_ec_command) +#define CROS_EC_DEV_IOCRDMEM _IOWR(CROS_EC_DEV_IOC, 1, struct cros_ec_readmem) + +void ec_dev_sysfs_init(struct cros_ec_device *); +void ec_dev_sysfs_remove(struct cros_ec_device *); + +void ec_dev_lightbar_init(struct cros_ec_device *); +void ec_dev_lightbar_remove(struct cros_ec_device *); + +#endif /* _CROS_EC_DEV_H_ */ diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c new file mode 100644 index 000000000000..b4ff47a9069a --- /dev/null +++ b/drivers/platform/chrome/cros_ec_lightbar.c @@ -0,0 +1,367 @@ +/* + * cros_ec_lightbar - expose the Chromebook Pixel lightbar to userspace + * + * Copyright (C) 2014 Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "cros_ec_lightbar: " fmt + +#include <linux/ctype.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/kobject.h> +#include <linux/mfd/cros_ec.h> +#include <linux/mfd/cros_ec_commands.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/uaccess.h> + +#include "cros_ec_dev.h" + +/* Rate-limit the lightbar interface to prevent DoS. */ +static unsigned long lb_interval_jiffies = 50 * HZ / 1000; + +static ssize_t interval_msec_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long msec = lb_interval_jiffies * 1000 / HZ; + + return scnprintf(buf, PAGE_SIZE, "%lu\n", msec); +} + +static ssize_t interval_msec_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long msec; + + if (kstrtoul(buf, 0, &msec)) + return -EINVAL; + + lb_interval_jiffies = msec * HZ / 1000; + + return count; +} + +static DEFINE_MUTEX(lb_mutex); +/* Return 0 if able to throttle correctly, error otherwise */ +static int lb_throttle(void) +{ + static unsigned long last_access; + unsigned long now, next_timeslot; + long delay; + int ret = 0; + + mutex_lock(&lb_mutex); + + now = jiffies; + next_timeslot = last_access + lb_interval_jiffies; + + if (time_before(now, next_timeslot)) { + delay = (long)(next_timeslot) - (long)now; + set_current_state(TASK_INTERRUPTIBLE); + if (schedule_timeout(delay) > 0) { + /* interrupted - just abort */ + ret = -EINTR; + goto out; + } + now = jiffies; + } + + last_access = now; +out: + mutex_unlock(&lb_mutex); + + return ret; +} + +#define INIT_MSG(P, R) { \ + .command = EC_CMD_LIGHTBAR_CMD, \ + .outsize = sizeof(*P), \ + .insize = sizeof(*R), \ + } + +static int get_lightbar_version(struct cros_ec_device *ec, + uint32_t *ver_ptr, uint32_t *flg_ptr) +{ + struct ec_params_lightbar *param; + struct ec_response_lightbar *resp; + struct cros_ec_command msg = INIT_MSG(param, resp); + int ret; + + param = (struct ec_params_lightbar *)msg.outdata; + param->cmd = LIGHTBAR_CMD_VERSION; + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return 0; + + switch (msg.result) { + case EC_RES_INVALID_PARAM: + /* Pixel had no version command. */ + if (ver_ptr) + *ver_ptr = 0; + if (flg_ptr) + *flg_ptr = 0; + return 1; + + case EC_RES_SUCCESS: + resp = (struct ec_response_lightbar *)msg.indata; + + /* Future devices w/lightbars should implement this command */ + if (ver_ptr) + *ver_ptr = resp->version.num; + if (flg_ptr) + *flg_ptr = resp->version.flags; + return 1; + } + + /* Anything else (ie, EC_RES_INVALID_COMMAND) - no lightbar */ + return 0; +} + +static ssize_t version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + uint32_t version, flags; + struct cros_ec_device *ec = dev_get_drvdata(dev); + int ret; + + ret = lb_throttle(); + if (ret) + return ret; + + /* This should always succeed, because we check during init. */ + if (!get_lightbar_version(ec, &version, &flags)) + return -EIO; + + return scnprintf(buf, PAGE_SIZE, "%d %d\n", version, flags); +} + +static ssize_t brightness_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ec_params_lightbar *param; + struct ec_response_lightbar *resp; + struct cros_ec_command msg = INIT_MSG(param, resp); + int ret; + unsigned int val; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + if (kstrtouint(buf, 0, &val)) + return -EINVAL; + + param = (struct ec_params_lightbar *)msg.outdata; + param->cmd = LIGHTBAR_CMD_BRIGHTNESS; + param->brightness.num = val; + ret = lb_throttle(); + if (ret) + return ret; + + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + + if (msg.result != EC_RES_SUCCESS) + return -EINVAL; + + return count; +} + + +/* + * We expect numbers, and we'll keep reading until we find them, skipping over + * any whitespace (sysfs guarantees that the input is null-terminated). Every + * four numbers are sent to the lightbar as <LED,R,G,B>. We fail at the first + * parsing error, if we don't parse any numbers, or if we have numbers left + * over. + */ +static ssize_t led_rgb_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ec_params_lightbar *param; + struct ec_response_lightbar *resp; + struct cros_ec_command msg = INIT_MSG(param, resp); + struct cros_ec_device *ec = dev_get_drvdata(dev); + unsigned int val[4]; + int ret, i = 0, j = 0, ok = 0; + + do { + /* Skip any whitespace */ + while (*buf && isspace(*buf)) + buf++; + + if (!*buf) + break; + + ret = sscanf(buf, "%i", &val[i++]); + if (ret == 0) + return -EINVAL; + + if (i == 4) { + param = (struct ec_params_lightbar *)msg.outdata; + param->cmd = LIGHTBAR_CMD_RGB; + param->rgb.led = val[0]; + param->rgb.red = val[1]; + param->rgb.green = val[2]; + param->rgb.blue = val[3]; + /* + * Throttle only the first of every four transactions, + * so that the user can update all four LEDs at once. + */ + if ((j++ % 4) == 0) { + ret = lb_throttle(); + if (ret) + return ret; + } + + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + + if (msg.result != EC_RES_SUCCESS) + return -EINVAL; + + i = 0; + ok = 1; + } + + /* Skip over the number we just read */ + while (*buf && !isspace(*buf)) + buf++; + + } while (*buf); + + return (ok && i == 0) ? count : -EINVAL; +} + +static char const *seqname[] = { + "ERROR", "S5", "S3", "S0", "S5S3", "S3S0", + "S0S3", "S3S5", "STOP", "RUN", "PULSE", "TEST", "KONAMI", +}; + +static ssize_t sequence_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ec_params_lightbar *param; + struct ec_response_lightbar *resp; + struct cros_ec_command msg = INIT_MSG(param, resp); + int ret; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + param = (struct ec_params_lightbar *)msg.outdata; + param->cmd = LIGHTBAR_CMD_GET_SEQ; + ret = lb_throttle(); + if (ret) + return ret; + + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + + if (msg.result != EC_RES_SUCCESS) + return scnprintf(buf, PAGE_SIZE, + "ERROR: EC returned %d\n", msg.result); + + resp = (struct ec_response_lightbar *)msg.indata; + if (resp->get_seq.num >= ARRAY_SIZE(seqname)) + return scnprintf(buf, PAGE_SIZE, "%d\n", resp->get_seq.num); + else + return scnprintf(buf, PAGE_SIZE, "%s\n", + seqname[resp->get_seq.num]); +} + +static ssize_t sequence_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ec_params_lightbar *param; + struct ec_response_lightbar *resp; + struct cros_ec_command msg = INIT_MSG(param, resp); + unsigned int num; + int ret, len; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + for (len = 0; len < count; len++) + if (!isalnum(buf[len])) + break; + + for (num = 0; num < ARRAY_SIZE(seqname); num++) + if (!strncasecmp(seqname[num], buf, len)) + break; + + if (num >= ARRAY_SIZE(seqname)) { + ret = kstrtouint(buf, 0, &num); + if (ret) + return ret; + } + + param = (struct ec_params_lightbar *)msg.outdata; + param->cmd = LIGHTBAR_CMD_SEQ; + param->seq.num = num; + ret = lb_throttle(); + if (ret) + return ret; + + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + + if (msg.result != EC_RES_SUCCESS) + return -EINVAL; + + return count; +} + +/* Module initialization */ + +static DEVICE_ATTR_RW(interval_msec); +static DEVICE_ATTR_RO(version); +static DEVICE_ATTR_WO(brightness); +static DEVICE_ATTR_WO(led_rgb); +static DEVICE_ATTR_RW(sequence); +static struct attribute *__lb_cmds_attrs[] = { + &dev_attr_interval_msec.attr, + &dev_attr_version.attr, + &dev_attr_brightness.attr, + &dev_attr_led_rgb.attr, + &dev_attr_sequence.attr, + NULL, +}; +static struct attribute_group lb_cmds_attr_group = { + .name = "lightbar", + .attrs = __lb_cmds_attrs, +}; + +void ec_dev_lightbar_init(struct cros_ec_device *ec) +{ + int ret = 0; + + /* Only instantiate this stuff if the EC has a lightbar */ + if (!get_lightbar_version(ec, NULL, NULL)) + return; + + ret = sysfs_create_group(&ec->vdev->kobj, &lb_cmds_attr_group); + if (ret) + pr_warn("sysfs_create_group() failed: %d\n", ret); +} + +void ec_dev_lightbar_remove(struct cros_ec_device *ec) +{ + sysfs_remove_group(&ec->vdev->kobj, &lb_cmds_attr_group); +} diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c new file mode 100644 index 000000000000..8f9ac4d7bbd0 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -0,0 +1,319 @@ +/* + * cros_ec_lpc - LPC access to the Chrome OS Embedded Controller + * + * Copyright (C) 2012-2015 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#include <linux/dmi.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/mfd/cros_ec.h> +#include <linux/mfd/cros_ec_commands.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/printk.h> + +#define DRV_NAME "cros_ec_lpc" + +static int ec_response_timed_out(void) +{ + unsigned long one_second = jiffies + HZ; + + usleep_range(200, 300); + do { + if (!(inb(EC_LPC_ADDR_HOST_CMD) & EC_LPC_STATUS_BUSY_MASK)) + return 0; + usleep_range(100, 200); + } while (time_before(jiffies, one_second)); + + return 1; +} + +static int cros_ec_cmd_xfer_lpc(struct cros_ec_device *ec, + struct cros_ec_command *msg) +{ + struct ec_lpc_host_args args; + int csum; + int i; + int ret = 0; + + if (msg->outsize > EC_PROTO2_MAX_PARAM_SIZE || + msg->insize > EC_PROTO2_MAX_PARAM_SIZE) { + dev_err(ec->dev, + "invalid buffer sizes (out %d, in %d)\n", + msg->outsize, msg->insize); + return -EINVAL; + } + + /* Now actually send the command to the EC and get the result */ + args.flags = EC_HOST_ARGS_FLAG_FROM_HOST; + args.command_version = msg->version; + args.data_size = msg->outsize; + + /* Initialize checksum */ + csum = msg->command + args.flags + + args.command_version + args.data_size; + + /* Copy data and update checksum */ + for (i = 0; i < msg->outsize; i++) { + outb(msg->outdata[i], EC_LPC_ADDR_HOST_PARAM + i); + csum += msg->outdata[i]; + } + + /* Finalize checksum and write args */ + args.checksum = csum & 0xFF; + outb(args.flags, EC_LPC_ADDR_HOST_ARGS); + outb(args.command_version, EC_LPC_ADDR_HOST_ARGS + 1); + outb(args.data_size, EC_LPC_ADDR_HOST_ARGS + 2); + outb(args.checksum, EC_LPC_ADDR_HOST_ARGS + 3); + + /* Here we go */ + outb(msg->command, EC_LPC_ADDR_HOST_CMD); + + if (ec_response_timed_out()) { + dev_warn(ec->dev, "EC responsed timed out\n"); + ret = -EIO; + goto done; + } + + /* Check result */ + msg->result = inb(EC_LPC_ADDR_HOST_DATA); + + switch (msg->result) { + case EC_RES_SUCCESS: + break; + case EC_RES_IN_PROGRESS: + ret = -EAGAIN; + dev_dbg(ec->dev, "command 0x%02x in progress\n", + msg->command); + goto done; + default: + dev_dbg(ec->dev, "command 0x%02x returned %d\n", + msg->command, msg->result); + } + + /* Read back args */ + args.flags = inb(EC_LPC_ADDR_HOST_ARGS); + args.command_version = inb(EC_LPC_ADDR_HOST_ARGS + 1); + args.data_size = inb(EC_LPC_ADDR_HOST_ARGS + 2); + args.checksum = inb(EC_LPC_ADDR_HOST_ARGS + 3); + + if (args.data_size > msg->insize) { + dev_err(ec->dev, + "packet too long (%d bytes, expected %d)", + args.data_size, msg->insize); + ret = -ENOSPC; + goto done; + } + + /* Start calculating response checksum */ + csum = msg->command + args.flags + + args.command_version + args.data_size; + + /* Read response and update checksum */ + for (i = 0; i < args.data_size; i++) { + msg->indata[i] = inb(EC_LPC_ADDR_HOST_PARAM + i); + csum += msg->indata[i]; + } + + /* Verify checksum */ + if (args.checksum != (csum & 0xFF)) { + dev_err(ec->dev, + "bad packet checksum, expected %02x, got %02x\n", + args.checksum, csum & 0xFF); + ret = -EBADMSG; + goto done; + } + + /* Return actual amount of data received */ + ret = args.data_size; +done: + return ret; +} + +/* Returns num bytes read, or negative on error. Doesn't need locking. */ +static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset, + unsigned int bytes, void *dest) +{ + int i = offset; + char *s = dest; + int cnt = 0; + + if (offset >= EC_MEMMAP_SIZE - bytes) + return -EINVAL; + + /* fixed length */ + if (bytes) { + for (; cnt < bytes; i++, s++, cnt++) + *s = inb(EC_LPC_ADDR_MEMMAP + i); + return cnt; + } + + /* string */ + for (; i < EC_MEMMAP_SIZE; i++, s++) { + *s = inb(EC_LPC_ADDR_MEMMAP + i); + cnt++; + if (!*s) + break; + } + + return cnt; +} + +static int cros_ec_lpc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_device *ec_dev; + int ret; + + if (!devm_request_region(dev, EC_LPC_ADDR_MEMMAP, EC_MEMMAP_SIZE, + dev_name(dev))) { + dev_err(dev, "couldn't reserve memmap region\n"); + return -EBUSY; + } + + if ((inb(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID) != 'E') || + (inb(EC_LPC_ADDR_MEMMAP + EC_MEMMAP_ID + 1) != 'C')) { + dev_err(dev, "EC ID not detected\n"); + return -ENODEV; + } + + if (!devm_request_region(dev, EC_HOST_CMD_REGION0, + EC_HOST_CMD_REGION_SIZE, dev_name(dev))) { + dev_err(dev, "couldn't reserve region0\n"); + return -EBUSY; + } + if (!devm_request_region(dev, EC_HOST_CMD_REGION1, + EC_HOST_CMD_REGION_SIZE, dev_name(dev))) { + dev_err(dev, "couldn't reserve region1\n"); + return -EBUSY; + } + + ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL); + if (!ec_dev) + return -ENOMEM; + + platform_set_drvdata(pdev, ec_dev); + ec_dev->dev = dev; + ec_dev->ec_name = pdev->name; + ec_dev->phys_name = dev_name(dev); + ec_dev->parent = dev; + ec_dev->cmd_xfer = cros_ec_cmd_xfer_lpc; + ec_dev->cmd_readmem = cros_ec_lpc_readmem; + + ret = cros_ec_register(ec_dev); + if (ret) { + dev_err(dev, "couldn't register ec_dev (%d)\n", ret); + return ret; + } + + return 0; +} + +static int cros_ec_lpc_remove(struct platform_device *pdev) +{ + struct cros_ec_device *ec_dev; + + ec_dev = platform_get_drvdata(pdev); + cros_ec_remove(ec_dev); + + return 0; +} + +static struct dmi_system_id cros_ec_lpc_dmi_table[] __initdata = { + { + /* + * Today all Chromebooks/boxes ship with Google_* as version and + * coreboot as bios vendor. No other systems with this + * combination are known to date. + */ + .matches = { + DMI_MATCH(DMI_BIOS_VENDOR, "coreboot"), + DMI_MATCH(DMI_BIOS_VERSION, "Google_"), + }, + }, + { + /* x86-link, the Chromebook Pixel. */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Link"), + }, + }, + { + /* x86-peppy, the Acer C720 Chromebook. */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Peppy"), + }, + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(dmi, cros_ec_lpc_dmi_table); + +static struct platform_driver cros_ec_lpc_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_ec_lpc_probe, + .remove = cros_ec_lpc_remove, +}; + +static struct platform_device cros_ec_lpc_device = { + .name = DRV_NAME +}; + +static int __init cros_ec_lpc_init(void) +{ + int ret; + + if (!dmi_check_system(cros_ec_lpc_dmi_table)) { + pr_err(DRV_NAME ": unsupported system.\n"); + return -ENODEV; + } + + /* Register the driver */ + ret = platform_driver_register(&cros_ec_lpc_driver); + if (ret) { + pr_err(DRV_NAME ": can't register driver: %d\n", ret); + return ret; + } + + /* Register the device, and it'll get hooked up automatically */ + ret = platform_device_register(&cros_ec_lpc_device); + if (ret) { + pr_err(DRV_NAME ": can't register device: %d\n", ret); + platform_driver_unregister(&cros_ec_lpc_driver); + return ret; + } + + return 0; +} + +static void __exit cros_ec_lpc_exit(void) +{ + platform_device_unregister(&cros_ec_lpc_device); + platform_driver_unregister(&cros_ec_lpc_driver); +} + +module_init(cros_ec_lpc_init); +module_exit(cros_ec_lpc_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("ChromeOS EC LPC driver"); diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c new file mode 100644 index 000000000000..fb62ab6cc659 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_sysfs.c @@ -0,0 +1,271 @@ +/* + * cros_ec_sysfs - expose the Chrome OS EC through sysfs + * + * Copyright (C) 2014 Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#define pr_fmt(fmt) "cros_ec_sysfs: " fmt + +#include <linux/ctype.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/kobject.h> +#include <linux/mfd/cros_ec.h> +#include <linux/mfd/cros_ec_commands.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/printk.h> +#include <linux/stat.h> +#include <linux/types.h> +#include <linux/uaccess.h> + +#include "cros_ec_dev.h" + +/* Accessor functions */ + +static ssize_t show_ec_reboot(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int count = 0; + + count += scnprintf(buf + count, PAGE_SIZE - count, + "ro|rw|cancel|cold|disable-jump|hibernate"); + count += scnprintf(buf + count, PAGE_SIZE - count, + " [at-shutdown]\n"); + return count; +} + +static ssize_t store_ec_reboot(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + static const struct { + const char * const str; + uint8_t cmd; + uint8_t flags; + } words[] = { + {"cancel", EC_REBOOT_CANCEL, 0}, + {"ro", EC_REBOOT_JUMP_RO, 0}, + {"rw", EC_REBOOT_JUMP_RW, 0}, + {"cold", EC_REBOOT_COLD, 0}, + {"disable-jump", EC_REBOOT_DISABLE_JUMP, 0}, + {"hibernate", EC_REBOOT_HIBERNATE, 0}, + {"at-shutdown", -1, EC_REBOOT_FLAG_ON_AP_SHUTDOWN}, + }; + struct cros_ec_command msg = { 0 }; + struct ec_params_reboot_ec *param = + (struct ec_params_reboot_ec *)msg.outdata; + int got_cmd = 0, offset = 0; + int i; + int ret; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + param->flags = 0; + while (1) { + /* Find word to start scanning */ + while (buf[offset] && isspace(buf[offset])) + offset++; + if (!buf[offset]) + break; + + for (i = 0; i < ARRAY_SIZE(words); i++) { + if (!strncasecmp(words[i].str, buf+offset, + strlen(words[i].str))) { + if (words[i].flags) { + param->flags |= words[i].flags; + } else { + param->cmd = words[i].cmd; + got_cmd = 1; + } + break; + } + } + + /* On to the next word, if any */ + while (buf[offset] && !isspace(buf[offset])) + offset++; + } + + if (!got_cmd) + return -EINVAL; + + msg.command = EC_CMD_REBOOT_EC; + msg.outsize = sizeof(param); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + if (msg.result != EC_RES_SUCCESS) { + dev_dbg(ec->dev, "EC result %d\n", msg.result); + return -EINVAL; + } + + return count; +} + +static ssize_t show_ec_version(struct device *dev, + struct device_attribute *attr, char *buf) +{ + static const char * const image_names[] = {"unknown", "RO", "RW"}; + struct ec_response_get_version *r_ver; + struct ec_response_get_chip_info *r_chip; + struct ec_response_board_version *r_board; + struct cros_ec_command msg = { 0 }; + int ret; + int count = 0; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + /* Get versions. RW may change. */ + msg.command = EC_CMD_GET_VERSION; + msg.insize = sizeof(*r_ver); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + if (msg.result != EC_RES_SUCCESS) + return scnprintf(buf, PAGE_SIZE, + "ERROR: EC returned %d\n", msg.result); + + r_ver = (struct ec_response_get_version *)msg.indata; + /* Strings should be null-terminated, but let's be sure. */ + r_ver->version_string_ro[sizeof(r_ver->version_string_ro) - 1] = '\0'; + r_ver->version_string_rw[sizeof(r_ver->version_string_rw) - 1] = '\0'; + count += scnprintf(buf + count, PAGE_SIZE - count, + "RO version: %s\n", r_ver->version_string_ro); + count += scnprintf(buf + count, PAGE_SIZE - count, + "RW version: %s\n", r_ver->version_string_rw); + count += scnprintf(buf + count, PAGE_SIZE - count, + "Firmware copy: %s\n", + (r_ver->current_image < ARRAY_SIZE(image_names) ? + image_names[r_ver->current_image] : "?")); + + /* Get build info. */ + msg.command = EC_CMD_GET_BUILD_INFO; + msg.insize = sizeof(msg.indata); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Build info: XFER ERROR %d\n", ret); + else if (msg.result != EC_RES_SUCCESS) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Build info: EC error %d\n", msg.result); + else { + msg.indata[sizeof(msg.indata) - 1] = '\0'; + count += scnprintf(buf + count, PAGE_SIZE - count, + "Build info: %s\n", msg.indata); + } + + /* Get chip info. */ + msg.command = EC_CMD_GET_CHIP_INFO; + msg.insize = sizeof(*r_chip); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip info: XFER ERROR %d\n", ret); + else if (msg.result != EC_RES_SUCCESS) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip info: EC error %d\n", msg.result); + else { + r_chip = (struct ec_response_get_chip_info *)msg.indata; + + r_chip->vendor[sizeof(r_chip->vendor) - 1] = '\0'; + r_chip->name[sizeof(r_chip->name) - 1] = '\0'; + r_chip->revision[sizeof(r_chip->revision) - 1] = '\0'; + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip vendor: %s\n", r_chip->vendor); + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip name: %s\n", r_chip->name); + count += scnprintf(buf + count, PAGE_SIZE - count, + "Chip revision: %s\n", r_chip->revision); + } + + /* Get board version */ + msg.command = EC_CMD_GET_BOARD_VERSION; + msg.insize = sizeof(*r_board); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Board version: XFER ERROR %d\n", ret); + else if (msg.result != EC_RES_SUCCESS) + count += scnprintf(buf + count, PAGE_SIZE - count, + "Board version: EC error %d\n", msg.result); + else { + r_board = (struct ec_response_board_version *)msg.indata; + + count += scnprintf(buf + count, PAGE_SIZE - count, + "Board version: %d\n", + r_board->board_version); + } + + return count; +} + +static ssize_t show_ec_flashinfo(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ec_response_flash_info *resp; + struct cros_ec_command msg = { 0 }; + int ret; + struct cros_ec_device *ec = dev_get_drvdata(dev); + + /* The flash info shouldn't ever change, but ask each time anyway. */ + msg.command = EC_CMD_FLASH_INFO; + msg.insize = sizeof(*resp); + ret = cros_ec_cmd_xfer(ec, &msg); + if (ret < 0) + return ret; + if (msg.result != EC_RES_SUCCESS) + return scnprintf(buf, PAGE_SIZE, + "ERROR: EC returned %d\n", msg.result); + + resp = (struct ec_response_flash_info *)msg.indata; + + return scnprintf(buf, PAGE_SIZE, + "FlashSize %d\nWriteSize %d\n" + "EraseSize %d\nProtectSize %d\n", + resp->flash_size, resp->write_block_size, + resp->erase_block_size, resp->protect_block_size); +} + +/* Module initialization */ + +static DEVICE_ATTR(reboot, S_IWUSR | S_IRUGO, show_ec_reboot, store_ec_reboot); +static DEVICE_ATTR(version, S_IRUGO, show_ec_version, NULL); +static DEVICE_ATTR(flashinfo, S_IRUGO, show_ec_flashinfo, NULL); + +static struct attribute *__ec_attrs[] = { + &dev_attr_reboot.attr, + &dev_attr_version.attr, + &dev_attr_flashinfo.attr, + NULL, +}; + +static struct attribute_group ec_attr_group = { + .attrs = __ec_attrs, +}; + +void ec_dev_sysfs_init(struct cros_ec_device *ec) +{ + int error; + + error = sysfs_create_group(&ec->vdev->kobj, &ec_attr_group); + if (error) + pr_warn("failed to create group: %d\n", error); +} + +void ec_dev_sysfs_remove(struct cros_ec_device *ec) +{ + sysfs_remove_group(&ec->vdev->kobj, &ec_attr_group); +} diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 97527614141b..f9f205cb1f11 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -614,6 +614,7 @@ config ACPI_TOSHIBA depends on INPUT depends on RFKILL || RFKILL = n depends on SERIO_I8042 || SERIO_I8042 = n + depends on ACPI_VIDEO || ACPI_VIDEO = n select INPUT_POLLDEV select INPUT_SPARSEKMAP ---help--- diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c index 66d6d22c239c..6808715003f6 100644 --- a/drivers/platform/x86/apple-gmux.c +++ b/drivers/platform/x86/apple-gmux.c @@ -22,6 +22,7 @@ #include <linux/delay.h> #include <linux/pci.h> #include <linux/vga_switcheroo.h> +#include <linux/vgaarb.h> #include <acpi/video.h> #include <asm/io.h> @@ -31,6 +32,7 @@ struct apple_gmux_data { bool indexed; struct mutex index_lock; + struct pci_dev *pdev; struct backlight_device *bdev; /* switcheroo data */ @@ -415,6 +417,23 @@ static int gmux_resume(struct device *dev) return 0; } +static struct pci_dev *gmux_get_io_pdev(void) +{ + struct pci_dev *pdev = NULL; + + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev))) { + u16 cmd; + + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if (!(cmd & PCI_COMMAND_IO)) + continue; + + return pdev; + } + + return NULL; +} + static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { struct apple_gmux_data *gmux_data; @@ -425,6 +444,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) int ret = -ENXIO; acpi_status status; unsigned long long gpe; + struct pci_dev *pdev = NULL; if (apple_gmux_data) return -EBUSY; @@ -475,7 +495,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) ver_minor = (version >> 16) & 0xff; ver_release = (version >> 8) & 0xff; } else { - pr_info("gmux device not present\n"); + pr_info("gmux device not present or IO disabled\n"); ret = -ENODEV; goto err_release; } @@ -483,6 +503,23 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor, ver_release, (gmux_data->indexed ? "indexed" : "classic")); + /* + * Apple systems with gmux are EFI based and normally don't use + * VGA. In addition changing IO+MEM ownership between IGP and dGPU + * disables IO/MEM used for backlight control on some systems. + * Lock IO+MEM to GPU with active IO to prevent switch. + */ + pdev = gmux_get_io_pdev(); + if (pdev && vga_tryget(pdev, + VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM)) { + pr_err("IO+MEM vgaarb-locking for PCI:%s failed\n", + pci_name(pdev)); + ret = -EBUSY; + goto err_release; + } else if (pdev) + pr_info("locked IO for PCI:%s\n", pci_name(pdev)); + gmux_data->pdev = pdev; + memset(&props, 0, sizeof(props)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = gmux_read32(gmux_data, GMUX_PORT_MAX_BRIGHTNESS); @@ -574,6 +611,10 @@ err_enable_gpe: err_notify: backlight_device_unregister(bdev); err_release: + if (gmux_data->pdev) + vga_put(gmux_data->pdev, + VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM); + pci_dev_put(pdev); release_region(gmux_data->iostart, gmux_data->iolen); err_free: kfree(gmux_data); @@ -593,6 +634,11 @@ static void gmux_remove(struct pnp_dev *pnp) &gmux_notify_handler); } + if (gmux_data->pdev) { + vga_put(gmux_data->pdev, + VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM); + pci_dev_put(gmux_data->pdev); + } backlight_device_unregister(gmux_data->bdev); release_region(gmux_data->iostart, gmux_data->iolen); diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 3d21efe11d7b..d688d806a8a5 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -2,9 +2,11 @@ * Driver for Dell laptop extras * * Copyright (c) Red Hat <mjg@redhat.com> + * Copyright (c) 2014 Gabriele Mazzotta <gabriele.mzt@gmail.com> + * Copyright (c) 2014 Pali Rohár <pali.rohar@gmail.com> * - * Based on documentation in the libsmbios package, Copyright (C) 2005 Dell - * Inc. + * Based on documentation in the libsmbios package: + * Copyright (C) 2005-2014 Dell Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -32,6 +34,13 @@ #include "../../firmware/dcdbas.h" #define BRIGHTNESS_TOKEN 0x7d +#define KBD_LED_OFF_TOKEN 0x01E1 +#define KBD_LED_ON_TOKEN 0x01E2 +#define KBD_LED_AUTO_TOKEN 0x01E3 +#define KBD_LED_AUTO_25_TOKEN 0x02EA +#define KBD_LED_AUTO_50_TOKEN 0x02EB +#define KBD_LED_AUTO_75_TOKEN 0x02EC +#define KBD_LED_AUTO_100_TOKEN 0x02F6 /* This structure will be modified by the firmware when we enter * system management mode, hence the volatiles */ @@ -62,6 +71,13 @@ struct calling_interface_structure { struct quirk_entry { u8 touchpad_led; + + int needs_kbd_timeouts; + /* + * Ordered list of timeouts expressed in seconds. + * The list must end with -1 + */ + int kbd_timeouts[]; }; static struct quirk_entry *quirks; @@ -76,6 +92,15 @@ static int __init dmi_matched(const struct dmi_system_id *dmi) return 1; } +/* + * These values come from Windows utility provided by Dell. If any other value + * is used then BIOS silently set timeout to 0 without any error message. + */ +static struct quirk_entry quirk_dell_xps13_9333 = { + .needs_kbd_timeouts = 1, + .kbd_timeouts = { 0, 5, 15, 60, 5 * 60, 15 * 60, -1 }, +}; + static int da_command_address; static int da_command_code; static int da_num_tokens; @@ -267,6 +292,15 @@ static const struct dmi_system_id dell_quirks[] __initconst = { }, .driver_data = &quirk_dell_vostro_v130, }, + { + .callback = dmi_matched, + .ident = "Dell XPS13 9333", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS13 9333"), + }, + .driver_data = &quirk_dell_xps13_9333, + }, { } }; @@ -331,17 +365,29 @@ static void __init find_tokens(const struct dmi_header *dm, void *dummy) } } -static int find_token_location(int tokenid) +static int find_token_id(int tokenid) { int i; + for (i = 0; i < da_num_tokens; i++) { if (da_tokens[i].tokenID == tokenid) - return da_tokens[i].location; + return i; } return -1; } +static int find_token_location(int tokenid) +{ + int id; + + id = find_token_id(tokenid); + if (id == -1) + return -1; + + return da_tokens[id].location; +} + static struct calling_interface_buffer * dell_send_request(struct calling_interface_buffer *buffer, int class, int select) @@ -362,6 +408,20 @@ dell_send_request(struct calling_interface_buffer *buffer, int class, return buffer; } +static inline int dell_smi_error(int value) +{ + switch (value) { + case 0: /* Completed successfully */ + return 0; + case -1: /* Completed with error */ + return -EIO; + case -2: /* Function not supported */ + return -ENXIO; + default: /* Unknown error */ + return -EINVAL; + } +} + /* Derived from information in DellWirelessCtl.cpp: Class 17, select 11 is radio control. It returns an array of 32-bit values. @@ -716,7 +776,7 @@ static int dell_send_intensity(struct backlight_device *bd) else dell_send_request(buffer, 1, 1); -out: + out: release_buffer(); return ret; } @@ -740,7 +800,7 @@ static int dell_get_intensity(struct backlight_device *bd) ret = buffer->output[1]; -out: + out: release_buffer(); return ret; } @@ -789,6 +849,1018 @@ static void touchpad_led_exit(void) led_classdev_unregister(&touchpad_led); } +/* + * Derived from information in smbios-keyboard-ctl: + * + * cbClass 4 + * cbSelect 11 + * Keyboard illumination + * cbArg1 determines the function to be performed + * + * cbArg1 0x0 = Get Feature Information + * cbRES1 Standard return codes (0, -1, -2) + * cbRES2, word0 Bitmap of user-selectable modes + * bit 0 Always off (All systems) + * bit 1 Always on (Travis ATG, Siberia) + * bit 2 Auto: ALS-based On; ALS-based Off (Travis ATG) + * bit 3 Auto: ALS- and input-activity-based On; input-activity based Off + * bit 4 Auto: Input-activity-based On; input-activity based Off + * bit 5 Auto: Input-activity-based On (illumination level 25%); input-activity based Off + * bit 6 Auto: Input-activity-based On (illumination level 50%); input-activity based Off + * bit 7 Auto: Input-activity-based On (illumination level 75%); input-activity based Off + * bit 8 Auto: Input-activity-based On (illumination level 100%); input-activity based Off + * bits 9-15 Reserved for future use + * cbRES2, byte2 Reserved for future use + * cbRES2, byte3 Keyboard illumination type + * 0 Reserved + * 1 Tasklight + * 2 Backlight + * 3-255 Reserved for future use + * cbRES3, byte0 Supported auto keyboard illumination trigger bitmap. + * bit 0 Any keystroke + * bit 1 Touchpad activity + * bit 2 Pointing stick + * bit 3 Any mouse + * bits 4-7 Reserved for future use + * cbRES3, byte1 Supported timeout unit bitmap + * bit 0 Seconds + * bit 1 Minutes + * bit 2 Hours + * bit 3 Days + * bits 4-7 Reserved for future use + * cbRES3, byte2 Number of keyboard light brightness levels + * cbRES4, byte0 Maximum acceptable seconds value (0 if seconds not supported). + * cbRES4, byte1 Maximum acceptable minutes value (0 if minutes not supported). + * cbRES4, byte2 Maximum acceptable hours value (0 if hours not supported). + * cbRES4, byte3 Maximum acceptable days value (0 if days not supported) + * + * cbArg1 0x1 = Get Current State + * cbRES1 Standard return codes (0, -1, -2) + * cbRES2, word0 Bitmap of current mode state + * bit 0 Always off (All systems) + * bit 1 Always on (Travis ATG, Siberia) + * bit 2 Auto: ALS-based On; ALS-based Off (Travis ATG) + * bit 3 Auto: ALS- and input-activity-based On; input-activity based Off + * bit 4 Auto: Input-activity-based On; input-activity based Off + * bit 5 Auto: Input-activity-based On (illumination level 25%); input-activity based Off + * bit 6 Auto: Input-activity-based On (illumination level 50%); input-activity based Off + * bit 7 Auto: Input-activity-based On (illumination level 75%); input-activity based Off + * bit 8 Auto: Input-activity-based On (illumination level 100%); input-activity based Off + * bits 9-15 Reserved for future use + * Note: Only One bit can be set + * cbRES2, byte2 Currently active auto keyboard illumination triggers. + * bit 0 Any keystroke + * bit 1 Touchpad activity + * bit 2 Pointing stick + * bit 3 Any mouse + * bits 4-7 Reserved for future use + * cbRES2, byte3 Current Timeout + * bits 7:6 Timeout units indicator: + * 00b Seconds + * 01b Minutes + * 10b Hours + * 11b Days + * bits 5:0 Timeout value (0-63) in sec/min/hr/day + * NOTE: A value of 0 means always on (no timeout) if any bits of RES3 byte + * are set upon return from the [Get feature information] call. + * cbRES3, byte0 Current setting of ALS value that turns the light on or off. + * cbRES3, byte1 Current ALS reading + * cbRES3, byte2 Current keyboard light level. + * + * cbArg1 0x2 = Set New State + * cbRES1 Standard return codes (0, -1, -2) + * cbArg2, word0 Bitmap of current mode state + * bit 0 Always off (All systems) + * bit 1 Always on (Travis ATG, Siberia) + * bit 2 Auto: ALS-based On; ALS-based Off (Travis ATG) + * bit 3 Auto: ALS- and input-activity-based On; input-activity based Off + * bit 4 Auto: Input-activity-based On; input-activity based Off + * bit 5 Auto: Input-activity-based On (illumination level 25%); input-activity based Off + * bit 6 Auto: Input-activity-based On (illumination level 50%); input-activity based Off + * bit 7 Auto: Input-activity-based On (illumination level 75%); input-activity based Off + * bit 8 Auto: Input-activity-based On (illumination level 100%); input-activity based Off + * bits 9-15 Reserved for future use + * Note: Only One bit can be set + * cbArg2, byte2 Desired auto keyboard illumination triggers. Must remain inactive to allow + * keyboard to turn off automatically. + * bit 0 Any keystroke + * bit 1 Touchpad activity + * bit 2 Pointing stick + * bit 3 Any mouse + * bits 4-7 Reserved for future use + * cbArg2, byte3 Desired Timeout + * bits 7:6 Timeout units indicator: + * 00b Seconds + * 01b Minutes + * 10b Hours + * 11b Days + * bits 5:0 Timeout value (0-63) in sec/min/hr/day + * cbArg3, byte0 Desired setting of ALS value that turns the light on or off. + * cbArg3, byte2 Desired keyboard light level. + */ + + +enum kbd_timeout_unit { + KBD_TIMEOUT_SECONDS = 0, + KBD_TIMEOUT_MINUTES, + KBD_TIMEOUT_HOURS, + KBD_TIMEOUT_DAYS, +}; + +enum kbd_mode_bit { + KBD_MODE_BIT_OFF = 0, + KBD_MODE_BIT_ON, + KBD_MODE_BIT_ALS, + KBD_MODE_BIT_TRIGGER_ALS, + KBD_MODE_BIT_TRIGGER, + KBD_MODE_BIT_TRIGGER_25, + KBD_MODE_BIT_TRIGGER_50, + KBD_MODE_BIT_TRIGGER_75, + KBD_MODE_BIT_TRIGGER_100, +}; + +#define kbd_is_als_mode_bit(bit) \ + ((bit) == KBD_MODE_BIT_ALS || (bit) == KBD_MODE_BIT_TRIGGER_ALS) +#define kbd_is_trigger_mode_bit(bit) \ + ((bit) >= KBD_MODE_BIT_TRIGGER_ALS && (bit) <= KBD_MODE_BIT_TRIGGER_100) +#define kbd_is_level_mode_bit(bit) \ + ((bit) >= KBD_MODE_BIT_TRIGGER_25 && (bit) <= KBD_MODE_BIT_TRIGGER_100) + +struct kbd_info { + u16 modes; + u8 type; + u8 triggers; + u8 levels; + u8 seconds; + u8 minutes; + u8 hours; + u8 days; +}; + +struct kbd_state { + u8 mode_bit; + u8 triggers; + u8 timeout_value; + u8 timeout_unit; + u8 als_setting; + u8 als_value; + u8 level; +}; + +static const int kbd_tokens[] = { + KBD_LED_OFF_TOKEN, + KBD_LED_AUTO_25_TOKEN, + KBD_LED_AUTO_50_TOKEN, + KBD_LED_AUTO_75_TOKEN, + KBD_LED_AUTO_100_TOKEN, + KBD_LED_ON_TOKEN, +}; + +static u16 kbd_token_bits; + +static struct kbd_info kbd_info; +static bool kbd_als_supported; +static bool kbd_triggers_supported; + +static u8 kbd_mode_levels[16]; +static int kbd_mode_levels_count; + +static u8 kbd_previous_level; +static u8 kbd_previous_mode_bit; + +static bool kbd_led_present; + +/* + * NOTE: there are three ways to set the keyboard backlight level. + * First, via kbd_state.mode_bit (assigning KBD_MODE_BIT_TRIGGER_* value). + * Second, via kbd_state.level (assigning numerical value <= kbd_info.levels). + * Third, via SMBIOS tokens (KBD_LED_* in kbd_tokens) + * + * There are laptops which support only one of these methods. If we want to + * support as many machines as possible we need to implement all three methods. + * The first two methods use the kbd_state structure. The third uses SMBIOS + * tokens. If kbd_info.levels == 0, the machine does not support setting the + * keyboard backlight level via kbd_state.level. + */ + +static int kbd_get_info(struct kbd_info *info) +{ + u8 units; + int ret; + + get_buffer(); + + buffer->input[0] = 0x0; + dell_send_request(buffer, 4, 11); + ret = buffer->output[0]; + + if (ret) { + ret = dell_smi_error(ret); + goto out; + } + + info->modes = buffer->output[1] & 0xFFFF; + info->type = (buffer->output[1] >> 24) & 0xFF; + info->triggers = buffer->output[2] & 0xFF; + units = (buffer->output[2] >> 8) & 0xFF; + info->levels = (buffer->output[2] >> 16) & 0xFF; + + if (units & BIT(0)) + info->seconds = (buffer->output[3] >> 0) & 0xFF; + if (units & BIT(1)) + info->minutes = (buffer->output[3] >> 8) & 0xFF; + if (units & BIT(2)) + info->hours = (buffer->output[3] >> 16) & 0xFF; + if (units & BIT(3)) + info->days = (buffer->output[3] >> 24) & 0xFF; + + out: + release_buffer(); + return ret; +} + +static unsigned int kbd_get_max_level(void) +{ + if (kbd_info.levels != 0) + return kbd_info.levels; + if (kbd_mode_levels_count > 0) + return kbd_mode_levels_count - 1; + return 0; +} + +static int kbd_get_level(struct kbd_state *state) +{ + int i; + + if (kbd_info.levels != 0) + return state->level; + + if (kbd_mode_levels_count > 0) { + for (i = 0; i < kbd_mode_levels_count; ++i) + if (kbd_mode_levels[i] == state->mode_bit) + return i; + return 0; + } + + return -EINVAL; +} + +static int kbd_set_level(struct kbd_state *state, u8 level) +{ + if (kbd_info.levels != 0) { + if (level != 0) + kbd_previous_level = level; + if (state->level == level) + return 0; + state->level = level; + if (level != 0 && state->mode_bit == KBD_MODE_BIT_OFF) + state->mode_bit = kbd_previous_mode_bit; + else if (level == 0 && state->mode_bit != KBD_MODE_BIT_OFF) { + kbd_previous_mode_bit = state->mode_bit; + state->mode_bit = KBD_MODE_BIT_OFF; + } + return 0; + } + + if (kbd_mode_levels_count > 0 && level < kbd_mode_levels_count) { + if (level != 0) + kbd_previous_level = level; + state->mode_bit = kbd_mode_levels[level]; + return 0; + } + + return -EINVAL; +} + +static int kbd_get_state(struct kbd_state *state) +{ + int ret; + + get_buffer(); + + buffer->input[0] = 0x1; + dell_send_request(buffer, 4, 11); + ret = buffer->output[0]; + + if (ret) { + ret = dell_smi_error(ret); + goto out; + } + + state->mode_bit = ffs(buffer->output[1] & 0xFFFF); + if (state->mode_bit != 0) + state->mode_bit--; + + state->triggers = (buffer->output[1] >> 16) & 0xFF; + state->timeout_value = (buffer->output[1] >> 24) & 0x3F; + state->timeout_unit = (buffer->output[1] >> 30) & 0x3; + state->als_setting = buffer->output[2] & 0xFF; + state->als_value = (buffer->output[2] >> 8) & 0xFF; + state->level = (buffer->output[2] >> 16) & 0xFF; + + out: + release_buffer(); + return ret; +} + +static int kbd_set_state(struct kbd_state *state) +{ + int ret; + + get_buffer(); + buffer->input[0] = 0x2; + buffer->input[1] = BIT(state->mode_bit) & 0xFFFF; + buffer->input[1] |= (state->triggers & 0xFF) << 16; + buffer->input[1] |= (state->timeout_value & 0x3F) << 24; + buffer->input[1] |= (state->timeout_unit & 0x3) << 30; + buffer->input[2] = state->als_setting & 0xFF; + buffer->input[2] |= (state->level & 0xFF) << 16; + dell_send_request(buffer, 4, 11); + ret = buffer->output[0]; + release_buffer(); + + return dell_smi_error(ret); +} + +static int kbd_set_state_safe(struct kbd_state *state, struct kbd_state *old) +{ + int ret; + + ret = kbd_set_state(state); + if (ret == 0) + return 0; + + /* + * When setting the new state fails,try to restore the previous one. + * This is needed on some machines where BIOS sets a default state when + * setting a new state fails. This default state could be all off. + */ + + if (kbd_set_state(old)) + pr_err("Setting old previous keyboard state failed\n"); + + return ret; +} + +static int kbd_set_token_bit(u8 bit) +{ + int id; + int ret; + + if (bit >= ARRAY_SIZE(kbd_tokens)) + return -EINVAL; + + id = find_token_id(kbd_tokens[bit]); + if (id == -1) + return -EINVAL; + + get_buffer(); + buffer->input[0] = da_tokens[id].location; + buffer->input[1] = da_tokens[id].value; + dell_send_request(buffer, 1, 0); + ret = buffer->output[0]; + release_buffer(); + + return dell_smi_error(ret); +} + +static int kbd_get_token_bit(u8 bit) +{ + int id; + int ret; + int val; + + if (bit >= ARRAY_SIZE(kbd_tokens)) + return -EINVAL; + + id = find_token_id(kbd_tokens[bit]); + if (id == -1) + return -EINVAL; + + get_buffer(); + buffer->input[0] = da_tokens[id].location; + dell_send_request(buffer, 0, 0); + ret = buffer->output[0]; + val = buffer->output[1]; + release_buffer(); + + if (ret) + return dell_smi_error(ret); + + return (val == da_tokens[id].value); +} + +static int kbd_get_first_active_token_bit(void) +{ + int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(kbd_tokens); ++i) { + ret = kbd_get_token_bit(i); + if (ret == 1) + return i; + } + + return ret; +} + +static int kbd_get_valid_token_counts(void) +{ + return hweight16(kbd_token_bits); +} + +static inline int kbd_init_info(void) +{ + struct kbd_state state; + int ret; + int i; + + ret = kbd_get_info(&kbd_info); + if (ret) + return ret; + + kbd_get_state(&state); + + /* NOTE: timeout value is stored in 6 bits so max value is 63 */ + if (kbd_info.seconds > 63) + kbd_info.seconds = 63; + if (kbd_info.minutes > 63) + kbd_info.minutes = 63; + if (kbd_info.hours > 63) + kbd_info.hours = 63; + if (kbd_info.days > 63) + kbd_info.days = 63; + + /* NOTE: On tested machines ON mode did not work and caused + * problems (turned backlight off) so do not use it + */ + kbd_info.modes &= ~BIT(KBD_MODE_BIT_ON); + + kbd_previous_level = kbd_get_level(&state); + kbd_previous_mode_bit = state.mode_bit; + + if (kbd_previous_level == 0 && kbd_get_max_level() != 0) + kbd_previous_level = 1; + + if (kbd_previous_mode_bit == KBD_MODE_BIT_OFF) { + kbd_previous_mode_bit = + ffs(kbd_info.modes & ~BIT(KBD_MODE_BIT_OFF)); + if (kbd_previous_mode_bit != 0) + kbd_previous_mode_bit--; + } + + if (kbd_info.modes & (BIT(KBD_MODE_BIT_ALS) | + BIT(KBD_MODE_BIT_TRIGGER_ALS))) + kbd_als_supported = true; + + if (kbd_info.modes & ( + BIT(KBD_MODE_BIT_TRIGGER_ALS) | BIT(KBD_MODE_BIT_TRIGGER) | + BIT(KBD_MODE_BIT_TRIGGER_25) | BIT(KBD_MODE_BIT_TRIGGER_50) | + BIT(KBD_MODE_BIT_TRIGGER_75) | BIT(KBD_MODE_BIT_TRIGGER_100) + )) + kbd_triggers_supported = true; + + /* kbd_mode_levels[0] is reserved, see below */ + for (i = 0; i < 16; ++i) + if (kbd_is_level_mode_bit(i) && (BIT(i) & kbd_info.modes)) + kbd_mode_levels[1 + kbd_mode_levels_count++] = i; + + /* + * Find the first supported mode and assign to kbd_mode_levels[0]. + * This should be 0 (off), but we cannot depend on the BIOS to + * support 0. + */ + if (kbd_mode_levels_count > 0) { + for (i = 0; i < 16; ++i) { + if (BIT(i) & kbd_info.modes) { + kbd_mode_levels[0] = i; + break; + } + } + kbd_mode_levels_count++; + } + + return 0; + +} + +static inline void kbd_init_tokens(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kbd_tokens); ++i) + if (find_token_id(kbd_tokens[i]) != -1) + kbd_token_bits |= BIT(i); +} + +static void kbd_init(void) +{ + int ret; + + ret = kbd_init_info(); + kbd_init_tokens(); + + if (kbd_token_bits != 0 || ret == 0) + kbd_led_present = true; +} + +static ssize_t kbd_led_timeout_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kbd_state new_state; + struct kbd_state state; + bool convert; + int value; + int ret; + char ch; + u8 unit; + int i; + + ret = sscanf(buf, "%d %c", &value, &ch); + if (ret < 1) + return -EINVAL; + else if (ret == 1) + ch = 's'; + + if (value < 0) + return -EINVAL; + + convert = false; + + switch (ch) { + case 's': + if (value > kbd_info.seconds) + convert = true; + unit = KBD_TIMEOUT_SECONDS; + break; + case 'm': + if (value > kbd_info.minutes) + convert = true; + unit = KBD_TIMEOUT_MINUTES; + break; + case 'h': + if (value > kbd_info.hours) + convert = true; + unit = KBD_TIMEOUT_HOURS; + break; + case 'd': + if (value > kbd_info.days) + convert = true; + unit = KBD_TIMEOUT_DAYS; + break; + default: + return -EINVAL; + } + + if (quirks && quirks->needs_kbd_timeouts) + convert = true; + + if (convert) { + /* Convert value from current units to seconds */ + switch (unit) { + case KBD_TIMEOUT_DAYS: + value *= 24; + case KBD_TIMEOUT_HOURS: + value *= 60; + case KBD_TIMEOUT_MINUTES: + value *= 60; + unit = KBD_TIMEOUT_SECONDS; + } + + if (quirks && quirks->needs_kbd_timeouts) { + for (i = 0; quirks->kbd_timeouts[i] != -1; i++) { + if (value <= quirks->kbd_timeouts[i]) { + value = quirks->kbd_timeouts[i]; + break; + } + } + } + + if (value <= kbd_info.seconds && kbd_info.seconds) { + unit = KBD_TIMEOUT_SECONDS; + } else if (value / 60 <= kbd_info.minutes && kbd_info.minutes) { + value /= 60; + unit = KBD_TIMEOUT_MINUTES; + } else if (value / (60 * 60) <= kbd_info.hours && kbd_info.hours) { + value /= (60 * 60); + unit = KBD_TIMEOUT_HOURS; + } else if (value / (60 * 60 * 24) <= kbd_info.days && kbd_info.days) { + value /= (60 * 60 * 24); + unit = KBD_TIMEOUT_DAYS; + } else { + return -EINVAL; + } + } + + ret = kbd_get_state(&state); + if (ret) + return ret; + + new_state = state; + new_state.timeout_value = value; + new_state.timeout_unit = unit; + + ret = kbd_set_state_safe(&new_state, &state); + if (ret) + return ret; + + return count; +} + +static ssize_t kbd_led_timeout_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct kbd_state state; + int ret; + int len; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + len = sprintf(buf, "%d", state.timeout_value); + + switch (state.timeout_unit) { + case KBD_TIMEOUT_SECONDS: + return len + sprintf(buf+len, "s\n"); + case KBD_TIMEOUT_MINUTES: + return len + sprintf(buf+len, "m\n"); + case KBD_TIMEOUT_HOURS: + return len + sprintf(buf+len, "h\n"); + case KBD_TIMEOUT_DAYS: + return len + sprintf(buf+len, "d\n"); + default: + return -EINVAL; + } + + return len; +} + +static DEVICE_ATTR(stop_timeout, S_IRUGO | S_IWUSR, + kbd_led_timeout_show, kbd_led_timeout_store); + +static const char * const kbd_led_triggers[] = { + "keyboard", + "touchpad", + /*"trackstick"*/ NULL, /* NOTE: trackstick is just alias for touchpad */ + "mouse", +}; + +static ssize_t kbd_led_triggers_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kbd_state new_state; + struct kbd_state state; + bool triggers_enabled = false; + int trigger_bit = -1; + char trigger[21]; + int i, ret; + + ret = sscanf(buf, "%20s", trigger); + if (ret != 1) + return -EINVAL; + + if (trigger[0] != '+' && trigger[0] != '-') + return -EINVAL; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + if (kbd_triggers_supported) + triggers_enabled = kbd_is_trigger_mode_bit(state.mode_bit); + + if (kbd_triggers_supported) { + for (i = 0; i < ARRAY_SIZE(kbd_led_triggers); ++i) { + if (!(kbd_info.triggers & BIT(i))) + continue; + if (!kbd_led_triggers[i]) + continue; + if (strcmp(trigger+1, kbd_led_triggers[i]) != 0) + continue; + if (trigger[0] == '+' && + triggers_enabled && (state.triggers & BIT(i))) + return count; + if (trigger[0] == '-' && + (!triggers_enabled || !(state.triggers & BIT(i)))) + return count; + trigger_bit = i; + break; + } + } + + if (trigger_bit != -1) { + new_state = state; + if (trigger[0] == '+') + new_state.triggers |= BIT(trigger_bit); + else { + new_state.triggers &= ~BIT(trigger_bit); + /* NOTE: trackstick bit (2) must be disabled when + * disabling touchpad bit (1), otherwise touchpad + * bit (1) will not be disabled */ + if (trigger_bit == 1) + new_state.triggers &= ~BIT(2); + } + if ((kbd_info.triggers & new_state.triggers) != + new_state.triggers) + return -EINVAL; + if (new_state.triggers && !triggers_enabled) { + new_state.mode_bit = KBD_MODE_BIT_TRIGGER; + kbd_set_level(&new_state, kbd_previous_level); + } else if (new_state.triggers == 0) { + kbd_set_level(&new_state, 0); + } + if (!(kbd_info.modes & BIT(new_state.mode_bit))) + return -EINVAL; + ret = kbd_set_state_safe(&new_state, &state); + if (ret) + return ret; + if (new_state.mode_bit != KBD_MODE_BIT_OFF) + kbd_previous_mode_bit = new_state.mode_bit; + return count; + } + + return -EINVAL; +} + +static ssize_t kbd_led_triggers_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct kbd_state state; + bool triggers_enabled; + int level, i, ret; + int len = 0; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + len = 0; + + if (kbd_triggers_supported) { + triggers_enabled = kbd_is_trigger_mode_bit(state.mode_bit); + level = kbd_get_level(&state); + for (i = 0; i < ARRAY_SIZE(kbd_led_triggers); ++i) { + if (!(kbd_info.triggers & BIT(i))) + continue; + if (!kbd_led_triggers[i]) + continue; + if ((triggers_enabled || level <= 0) && + (state.triggers & BIT(i))) + buf[len++] = '+'; + else + buf[len++] = '-'; + len += sprintf(buf+len, "%s ", kbd_led_triggers[i]); + } + } + + if (len) + buf[len - 1] = '\n'; + + return len; +} + +static DEVICE_ATTR(start_triggers, S_IRUGO | S_IWUSR, + kbd_led_triggers_show, kbd_led_triggers_store); + +static ssize_t kbd_led_als_enabled_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kbd_state new_state; + struct kbd_state state; + bool triggers_enabled = false; + int enable; + int ret; + + ret = kstrtoint(buf, 0, &enable); + if (ret) + return ret; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + if (enable == kbd_is_als_mode_bit(state.mode_bit)) + return count; + + new_state = state; + + if (kbd_triggers_supported) + triggers_enabled = kbd_is_trigger_mode_bit(state.mode_bit); + + if (enable) { + if (triggers_enabled) + new_state.mode_bit = KBD_MODE_BIT_TRIGGER_ALS; + else + new_state.mode_bit = KBD_MODE_BIT_ALS; + } else { + if (triggers_enabled) { + new_state.mode_bit = KBD_MODE_BIT_TRIGGER; + kbd_set_level(&new_state, kbd_previous_level); + } else { + new_state.mode_bit = KBD_MODE_BIT_ON; + } + } + if (!(kbd_info.modes & BIT(new_state.mode_bit))) + return -EINVAL; + + ret = kbd_set_state_safe(&new_state, &state); + if (ret) + return ret; + kbd_previous_mode_bit = new_state.mode_bit; + + return count; +} + +static ssize_t kbd_led_als_enabled_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kbd_state state; + bool enabled = false; + int ret; + + ret = kbd_get_state(&state); + if (ret) + return ret; + enabled = kbd_is_als_mode_bit(state.mode_bit); + + return sprintf(buf, "%d\n", enabled ? 1 : 0); +} + +static DEVICE_ATTR(als_enabled, S_IRUGO | S_IWUSR, + kbd_led_als_enabled_show, kbd_led_als_enabled_store); + +static ssize_t kbd_led_als_setting_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct kbd_state state; + struct kbd_state new_state; + u8 setting; + int ret; + + ret = kstrtou8(buf, 10, &setting); + if (ret) + return ret; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + new_state = state; + new_state.als_setting = setting; + + ret = kbd_set_state_safe(&new_state, &state); + if (ret) + return ret; + + return count; +} + +static ssize_t kbd_led_als_setting_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct kbd_state state; + int ret; + + ret = kbd_get_state(&state); + if (ret) + return ret; + + return sprintf(buf, "%d\n", state.als_setting); +} + +static DEVICE_ATTR(als_setting, S_IRUGO | S_IWUSR, + kbd_led_als_setting_show, kbd_led_als_setting_store); + +static struct attribute *kbd_led_attrs[] = { + &dev_attr_stop_timeout.attr, + &dev_attr_start_triggers.attr, + NULL, +}; + +static const struct attribute_group kbd_led_group = { + .attrs = kbd_led_attrs, +}; + +static struct attribute *kbd_led_als_attrs[] = { + &dev_attr_als_enabled.attr, + &dev_attr_als_setting.attr, + NULL, +}; + +static const struct attribute_group kbd_led_als_group = { + .attrs = kbd_led_als_attrs, +}; + +static const struct attribute_group *kbd_led_groups[] = { + &kbd_led_group, + &kbd_led_als_group, + NULL, +}; + +static enum led_brightness kbd_led_level_get(struct led_classdev *led_cdev) +{ + int ret; + u16 num; + struct kbd_state state; + + if (kbd_get_max_level()) { + ret = kbd_get_state(&state); + if (ret) + return 0; + ret = kbd_get_level(&state); + if (ret < 0) + return 0; + return ret; + } + + if (kbd_get_valid_token_counts()) { + ret = kbd_get_first_active_token_bit(); + if (ret < 0) + return 0; + for (num = kbd_token_bits; num != 0 && ret > 0; --ret) + num &= num - 1; /* clear the first bit set */ + if (num == 0) + return 0; + return ffs(num) - 1; + } + + pr_warn("Keyboard brightness level control not supported\n"); + return 0; +} + +static void kbd_led_level_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct kbd_state state; + struct kbd_state new_state; + u16 num; + + if (kbd_get_max_level()) { + if (kbd_get_state(&state)) + return; + new_state = state; + if (kbd_set_level(&new_state, value)) + return; + kbd_set_state_safe(&new_state, &state); + return; + } + + if (kbd_get_valid_token_counts()) { + for (num = kbd_token_bits; num != 0 && value > 0; --value) + num &= num - 1; /* clear the first bit set */ + if (num == 0) + return; + kbd_set_token_bit(ffs(num) - 1); + return; + } + + pr_warn("Keyboard brightness level control not supported\n"); +} + +static struct led_classdev kbd_led = { + .name = "dell::kbd_backlight", + .brightness_set = kbd_led_level_set, + .brightness_get = kbd_led_level_get, + .groups = kbd_led_groups, +}; + +static int __init kbd_led_init(struct device *dev) +{ + kbd_init(); + if (!kbd_led_present) + return -ENODEV; + if (!kbd_als_supported) + kbd_led_groups[1] = NULL; + kbd_led.max_brightness = kbd_get_max_level(); + if (!kbd_led.max_brightness) { + kbd_led.max_brightness = kbd_get_valid_token_counts(); + if (kbd_led.max_brightness) + kbd_led.max_brightness--; + } + return led_classdev_register(dev, &kbd_led); +} + +static void brightness_set_exit(struct led_classdev *led_cdev, + enum led_brightness value) +{ + /* Don't change backlight level on exit */ +}; + +static void kbd_led_exit(void) +{ + if (!kbd_led_present) + return; + kbd_led.brightness_set = brightness_set_exit; + led_classdev_unregister(&kbd_led); +} + static int __init dell_init(void) { int max_intensity = 0; @@ -841,6 +1913,8 @@ static int __init dell_init(void) if (quirks && quirks->touchpad_led) touchpad_led_init(&platform_device->dev); + kbd_led_init(&platform_device->dev); + dell_laptop_dir = debugfs_create_dir("dell_laptop", NULL); if (dell_laptop_dir != NULL) debugfs_create_file("rfkill", 0444, dell_laptop_dir, NULL, @@ -908,6 +1982,7 @@ static void __exit dell_exit(void) debugfs_remove_recursive(dell_laptop_dir); if (quirks && quirks->touchpad_led) touchpad_led_exit(); + kbd_led_exit(); i8042_remove_filter(dell_laptop_i8042_filter); cancel_delayed_work_sync(&dell_rfkill_work); backlight_device_unregister(dell_backlight_device); @@ -924,5 +1999,7 @@ module_init(dell_init); module_exit(dell_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); +MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); +MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); MODULE_DESCRIPTION("Dell laptop driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c index a4a4258f6134..8037c8b46241 100644 --- a/drivers/platform/x86/intel_oaktrail.c +++ b/drivers/platform/x86/intel_oaktrail.c @@ -62,7 +62,7 @@ * (1 << 1): Bluetooth enable/disable, RW. * (1 << 2): GPS enable/disable, RW. * (1 << 3): WiFi enable/disable, RW. - * (1 << 4): WWAN (3G) enable/disalbe, RW. + * (1 << 4): WWAN (3G) enable/disable, RW. * (1 << 5): Touchscreen enable/disable, Read Only. */ #define OT_EC_DEVICE_STATE_ADDRESS 0xD6 diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 3b8ceee7c5cb..7769575345d8 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -319,6 +319,7 @@ static struct { u32 sensors_pdrv_attrs_registered:1; u32 sensors_pdev_attrs_registered:1; u32 hotkey_poll_active:1; + u32 has_adaptive_kbd:1; } tp_features; static struct { @@ -1911,6 +1912,27 @@ enum { /* hot key scan codes (derived from ACPI DSDT) */ TP_ACPI_HOTKEYSCAN_UNK7, TP_ACPI_HOTKEYSCAN_UNK8, + TP_ACPI_HOTKEYSCAN_MUTE2, + TP_ACPI_HOTKEYSCAN_BRIGHTNESS_ZERO, + TP_ACPI_HOTKEYSCAN_CLIPPING_TOOL, + TP_ACPI_HOTKEYSCAN_CLOUD, + TP_ACPI_HOTKEYSCAN_UNK9, + TP_ACPI_HOTKEYSCAN_VOICE, + TP_ACPI_HOTKEYSCAN_UNK10, + TP_ACPI_HOTKEYSCAN_GESTURES, + TP_ACPI_HOTKEYSCAN_UNK11, + TP_ACPI_HOTKEYSCAN_UNK12, + TP_ACPI_HOTKEYSCAN_UNK13, + TP_ACPI_HOTKEYSCAN_CONFIG, + TP_ACPI_HOTKEYSCAN_NEW_TAB, + TP_ACPI_HOTKEYSCAN_RELOAD, + TP_ACPI_HOTKEYSCAN_BACK, + TP_ACPI_HOTKEYSCAN_MIC_DOWN, + TP_ACPI_HOTKEYSCAN_MIC_UP, + TP_ACPI_HOTKEYSCAN_MIC_CANCELLATION, + TP_ACPI_HOTKEYSCAN_CAMERA_MODE, + TP_ACPI_HOTKEYSCAN_ROTATE_DISPLAY, + /* Hotkey keymap size */ TPACPI_HOTKEY_MAP_LEN }; @@ -2647,9 +2669,7 @@ static ssize_t hotkey_enable_store(struct device *dev, return count; } -static struct device_attribute dev_attr_hotkey_enable = - __ATTR(hotkey_enable, S_IWUSR | S_IRUGO, - hotkey_enable_show, hotkey_enable_store); +static DEVICE_ATTR_RW(hotkey_enable); /* sysfs hotkey mask --------------------------------------------------- */ static ssize_t hotkey_mask_show(struct device *dev, @@ -2685,9 +2705,7 @@ static ssize_t hotkey_mask_store(struct device *dev, return (res) ? res : count; } -static struct device_attribute dev_attr_hotkey_mask = - __ATTR(hotkey_mask, S_IWUSR | S_IRUGO, - hotkey_mask_show, hotkey_mask_store); +static DEVICE_ATTR_RW(hotkey_mask); /* sysfs hotkey bios_enabled ------------------------------------------- */ static ssize_t hotkey_bios_enabled_show(struct device *dev, @@ -2697,8 +2715,7 @@ static ssize_t hotkey_bios_enabled_show(struct device *dev, return sprintf(buf, "0\n"); } -static struct device_attribute dev_attr_hotkey_bios_enabled = - __ATTR(hotkey_bios_enabled, S_IRUGO, hotkey_bios_enabled_show, NULL); +static DEVICE_ATTR_RO(hotkey_bios_enabled); /* sysfs hotkey bios_mask ---------------------------------------------- */ static ssize_t hotkey_bios_mask_show(struct device *dev, @@ -2710,8 +2727,7 @@ static ssize_t hotkey_bios_mask_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "0x%08x\n", hotkey_orig_mask); } -static struct device_attribute dev_attr_hotkey_bios_mask = - __ATTR(hotkey_bios_mask, S_IRUGO, hotkey_bios_mask_show, NULL); +static DEVICE_ATTR_RO(hotkey_bios_mask); /* sysfs hotkey all_mask ----------------------------------------------- */ static ssize_t hotkey_all_mask_show(struct device *dev, @@ -2722,8 +2738,7 @@ static ssize_t hotkey_all_mask_show(struct device *dev, hotkey_all_mask | hotkey_source_mask); } -static struct device_attribute dev_attr_hotkey_all_mask = - __ATTR(hotkey_all_mask, S_IRUGO, hotkey_all_mask_show, NULL); +static DEVICE_ATTR_RO(hotkey_all_mask); /* sysfs hotkey recommended_mask --------------------------------------- */ static ssize_t hotkey_recommended_mask_show(struct device *dev, @@ -2735,9 +2750,7 @@ static ssize_t hotkey_recommended_mask_show(struct device *dev, & ~hotkey_reserved_mask); } -static struct device_attribute dev_attr_hotkey_recommended_mask = - __ATTR(hotkey_recommended_mask, S_IRUGO, - hotkey_recommended_mask_show, NULL); +static DEVICE_ATTR_RO(hotkey_recommended_mask); #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL @@ -2792,9 +2805,7 @@ static ssize_t hotkey_source_mask_store(struct device *dev, return (rc < 0) ? rc : count; } -static struct device_attribute dev_attr_hotkey_source_mask = - __ATTR(hotkey_source_mask, S_IWUSR | S_IRUGO, - hotkey_source_mask_show, hotkey_source_mask_store); +static DEVICE_ATTR_RW(hotkey_source_mask); /* sysfs hotkey hotkey_poll_freq --------------------------------------- */ static ssize_t hotkey_poll_freq_show(struct device *dev, @@ -2826,9 +2837,7 @@ static ssize_t hotkey_poll_freq_store(struct device *dev, return count; } -static struct device_attribute dev_attr_hotkey_poll_freq = - __ATTR(hotkey_poll_freq, S_IWUSR | S_IRUGO, - hotkey_poll_freq_show, hotkey_poll_freq_store); +static DEVICE_ATTR_RW(hotkey_poll_freq); #endif /* CONFIG_THINKPAD_ACPI_HOTKEY_POLL */ @@ -2849,8 +2858,7 @@ static ssize_t hotkey_radio_sw_show(struct device *dev, (res == TPACPI_RFK_RADIO_OFF) ? 0 : 1); } -static struct device_attribute dev_attr_hotkey_radio_sw = - __ATTR(hotkey_radio_sw, S_IRUGO, hotkey_radio_sw_show, NULL); +static DEVICE_ATTR_RO(hotkey_radio_sw); static void hotkey_radio_sw_notify_change(void) { @@ -2872,8 +2880,7 @@ static ssize_t hotkey_tablet_mode_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", !!s); } -static struct device_attribute dev_attr_hotkey_tablet_mode = - __ATTR(hotkey_tablet_mode, S_IRUGO, hotkey_tablet_mode_show, NULL); +static DEVICE_ATTR_RO(hotkey_tablet_mode); static void hotkey_tablet_mode_notify_change(void) { @@ -2890,8 +2897,7 @@ static ssize_t hotkey_wakeup_reason_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_wakeup_reason); } -static struct device_attribute dev_attr_hotkey_wakeup_reason = - __ATTR(wakeup_reason, S_IRUGO, hotkey_wakeup_reason_show, NULL); +static DEVICE_ATTR_RO(hotkey_wakeup_reason); static void hotkey_wakeup_reason_notify_change(void) { @@ -2907,9 +2913,7 @@ static ssize_t hotkey_wakeup_hotunplug_complete_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_autosleep_ack); } -static struct device_attribute dev_attr_hotkey_wakeup_hotunplug_complete = - __ATTR(wakeup_hotunplug_complete, S_IRUGO, - hotkey_wakeup_hotunplug_complete_show, NULL); +static DEVICE_ATTR_RO(hotkey_wakeup_hotunplug_complete); static void hotkey_wakeup_hotunplug_complete_notify_change(void) { @@ -2917,6 +2921,57 @@ static void hotkey_wakeup_hotunplug_complete_notify_change(void) "wakeup_hotunplug_complete"); } +/* sysfs adaptive kbd mode --------------------------------------------- */ + +static int adaptive_keyboard_get_mode(void); +static int adaptive_keyboard_set_mode(int new_mode); + +enum ADAPTIVE_KEY_MODE { + HOME_MODE, + WEB_BROWSER_MODE, + WEB_CONFERENCE_MODE, + FUNCTION_MODE, + LAYFLAT_MODE +}; + +static ssize_t adaptive_kbd_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int current_mode; + + current_mode = adaptive_keyboard_get_mode(); + if (current_mode < 0) + return current_mode; + + return snprintf(buf, PAGE_SIZE, "%d\n", current_mode); +} + +static ssize_t adaptive_kbd_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long t; + int res; + + if (parse_strtoul(buf, LAYFLAT_MODE, &t)) + return -EINVAL; + + res = adaptive_keyboard_set_mode(t); + return (res < 0) ? res : count; +} + +static DEVICE_ATTR_RW(adaptive_kbd_mode); + +static struct attribute *adaptive_kbd_attributes[] = { + &dev_attr_adaptive_kbd_mode.attr, + NULL +}; + +static const struct attribute_group adaptive_kbd_attr_group = { + .attrs = adaptive_kbd_attributes, +}; + /* --------------------------------------------------------------------- */ static struct attribute *hotkey_attributes[] __initdata = { @@ -3118,6 +3173,13 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) /* (assignments unknown, please report if found) */ KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + + /* No assignments, only used for Adaptive keyboards. */ + KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, + KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, }, /* Generic keymap for Lenovo ThinkPads */ @@ -3174,6 +3236,35 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) /* Extra keys in use since the X240 / T440 / T540 */ KEY_CONFIG, KEY_SEARCH, KEY_SCALE, KEY_FILE, + + /* + * These are the adaptive keyboard keycodes for Carbon X1 2014. + * The first item in this list is the Mute button which is + * emitted with 0x103 through + * adaptive_keyboard_hotkey_notify_hotkey() when the sound + * symbol is held. + * We'll need to offset those by 0x20. + */ + KEY_RESERVED, /* Mute held, 0x103 */ + KEY_BRIGHTNESS_MIN, /* Backlight off */ + KEY_RESERVED, /* Clipping tool */ + KEY_RESERVED, /* Cloud */ + KEY_RESERVED, + KEY_VOICECOMMAND, /* Voice */ + KEY_RESERVED, + KEY_RESERVED, /* Gestures */ + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + KEY_CONFIG, /* Settings */ + KEY_RESERVED, /* New tab */ + KEY_REFRESH, /* Reload */ + KEY_BACK, /* Back */ + KEY_RESERVED, /* Microphone down */ + KEY_RESERVED, /* Microphone up */ + KEY_RESERVED, /* Microphone cancellation */ + KEY_RESERVED, /* Camera mode */ + KEY_RESERVED, /* Rotate display, 0x116 */ }, }; @@ -3227,6 +3318,20 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) if (!tp_features.hotkey) return 1; + /* + * Check if we have an adaptive keyboard, like on the + * Lenovo Carbon X1 2014 (2nd Gen). + */ + if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) { + if ((hkeyv >> 8) == 2) { + tp_features.has_adaptive_kbd = true; + res = sysfs_create_group(&tpacpi_pdev->dev.kobj, + &adaptive_kbd_attr_group); + if (res) + goto err_exit; + } + } + quirks = tpacpi_check_quirks(tpacpi_hotkey_qtable, ARRAY_SIZE(tpacpi_hotkey_qtable)); @@ -3437,6 +3542,9 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) err_exit: delete_attr_set(hotkey_dev_attributes, &tpacpi_pdev->dev.kobj); + sysfs_remove_group(&tpacpi_pdev->dev.kobj, + &adaptive_kbd_attr_group); + hotkey_dev_attributes = NULL; return (res < 0) ? res : 1; @@ -3449,14 +3557,6 @@ err_exit: * Will consider support rest of modes in future. * */ -enum ADAPTIVE_KEY_MODE { - HOME_MODE, - WEB_BROWSER_MODE, - WEB_CONFERENCE_MODE, - FUNCTION_MODE, - LAYFLAT_MODE -}; - static const int adaptive_keyboard_modes[] = { HOME_MODE, /* WEB_BROWSER_MODE = 2, @@ -3466,6 +3566,8 @@ static const int adaptive_keyboard_modes[] = { #define DFR_CHANGE_ROW 0x101 #define DFR_SHOW_QUICKVIEW_ROW 0x102 +#define FIRST_ADAPTIVE_KEY 0x103 +#define ADAPTIVE_KEY_OFFSET 0x020 /* press Fn key a while second, it will switch to Function Mode. Then * release Fn key, previous mode be restored. @@ -3473,6 +3575,32 @@ static const int adaptive_keyboard_modes[] = { static bool adaptive_keyboard_mode_is_saved; static int adaptive_keyboard_prev_mode; +static int adaptive_keyboard_get_mode(void) +{ + int mode = 0; + + if (!acpi_evalf(hkey_handle, &mode, "GTRW", "dd", 0)) { + pr_err("Cannot read adaptive keyboard mode\n"); + return -EIO; + } + + return mode; +} + +static int adaptive_keyboard_set_mode(int new_mode) +{ + if (new_mode < 0 || + new_mode > LAYFLAT_MODE) + return -EINVAL; + + if (!acpi_evalf(hkey_handle, NULL, "STRW", "vd", new_mode)) { + pr_err("Cannot set adaptive keyboard mode\n"); + return -EIO; + } + + return 0; +} + static int adaptive_keyboard_get_next_mode(int mode) { size_t i; @@ -3493,8 +3621,9 @@ static int adaptive_keyboard_get_next_mode(int mode) static bool adaptive_keyboard_hotkey_notify_hotkey(unsigned int scancode) { - u32 current_mode = 0; + int current_mode = 0; int new_mode = 0; + int keycode; switch (scancode) { case DFR_CHANGE_ROW: @@ -3502,43 +3631,51 @@ static bool adaptive_keyboard_hotkey_notify_hotkey(unsigned int scancode) new_mode = adaptive_keyboard_prev_mode; adaptive_keyboard_mode_is_saved = false; } else { - if (!acpi_evalf( - hkey_handle, ¤t_mode, - "GTRW", "dd", 0)) { - pr_err("Cannot read adaptive keyboard mode\n"); + current_mode = adaptive_keyboard_get_mode(); + if (current_mode < 0) return false; - } else { - new_mode = adaptive_keyboard_get_next_mode( - current_mode); - } + new_mode = adaptive_keyboard_get_next_mode( + current_mode); } - if (!acpi_evalf(hkey_handle, NULL, "STRW", "vd", new_mode)) { - pr_err("Cannot set adaptive keyboard mode\n"); + if (adaptive_keyboard_set_mode(new_mode) < 0) return false; - } return true; case DFR_SHOW_QUICKVIEW_ROW: - if (!acpi_evalf(hkey_handle, - &adaptive_keyboard_prev_mode, - "GTRW", "dd", 0)) { - pr_err("Cannot read adaptive keyboard mode\n"); + current_mode = adaptive_keyboard_get_mode(); + if (current_mode < 0) return false; - } else { - adaptive_keyboard_mode_is_saved = true; - if (!acpi_evalf(hkey_handle, - NULL, "STRW", "vd", FUNCTION_MODE)) { - pr_err("Cannot set adaptive keyboard mode\n"); - return false; - } - } + adaptive_keyboard_prev_mode = current_mode; + adaptive_keyboard_mode_is_saved = true; + + if (adaptive_keyboard_set_mode (FUNCTION_MODE) < 0) + return false; return true; default: - return false; + if (scancode < FIRST_ADAPTIVE_KEY || + scancode >= FIRST_ADAPTIVE_KEY + TPACPI_HOTKEY_MAP_LEN - + ADAPTIVE_KEY_OFFSET) { + pr_info("Unhandled adaptive keyboard key: 0x%x\n", + scancode); + return false; + } + keycode = hotkey_keycode_map[scancode - FIRST_ADAPTIVE_KEY + ADAPTIVE_KEY_OFFSET]; + if (keycode != KEY_RESERVED) { + mutex_lock(&tpacpi_inputdev_send_mutex); + + input_report_key(tpacpi_inputdev, keycode, 1); + input_sync(tpacpi_inputdev); + + input_report_key(tpacpi_inputdev, keycode, 0); + input_sync(tpacpi_inputdev); + + mutex_unlock(&tpacpi_inputdev_send_mutex); + } + return true; } } @@ -3836,28 +3973,21 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event) static void hotkey_suspend(void) { - int hkeyv; - /* Do these on suspend, we get the events on early resume! */ hotkey_wakeup_reason = TP_ACPI_WAKEUP_NONE; hotkey_autosleep_ack = 0; /* save previous mode of adaptive keyboard of X1 Carbon */ - if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) { - if ((hkeyv >> 8) == 2) { - if (!acpi_evalf(hkey_handle, - &adaptive_keyboard_prev_mode, - "GTRW", "dd", 0)) { - pr_err("Cannot read adaptive keyboard mode.\n"); - } + if (tp_features.has_adaptive_kbd) { + if (!acpi_evalf(hkey_handle, &adaptive_keyboard_prev_mode, + "GTRW", "dd", 0)) { + pr_err("Cannot read adaptive keyboard mode.\n"); } } } static void hotkey_resume(void) { - int hkeyv; - tpacpi_disable_brightness_delay(); if (hotkey_status_set(true) < 0 || @@ -3872,14 +4002,10 @@ static void hotkey_resume(void) hotkey_poll_setup_safe(false); /* restore previous mode of adapive keyboard of X1 Carbon */ - if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) { - if ((hkeyv >> 8) == 2) { - if (!acpi_evalf(hkey_handle, - NULL, - "STRW", "vd", - adaptive_keyboard_prev_mode)) { - pr_err("Cannot set adaptive keyboard mode.\n"); - } + if (tp_features.has_adaptive_kbd) { + if (!acpi_evalf(hkey_handle, NULL, "STRW", "vd", + adaptive_keyboard_prev_mode)) { + pr_err("Cannot set adaptive keyboard mode.\n"); } } } @@ -4079,9 +4205,7 @@ static ssize_t bluetooth_enable_store(struct device *dev, attr, buf, count); } -static struct device_attribute dev_attr_bluetooth_enable = - __ATTR(bluetooth_enable, S_IWUSR | S_IRUGO, - bluetooth_enable_show, bluetooth_enable_store); +static DEVICE_ATTR_RW(bluetooth_enable); /* --------------------------------------------------------------------- */ @@ -4269,9 +4393,7 @@ static ssize_t wan_enable_store(struct device *dev, attr, buf, count); } -static struct device_attribute dev_attr_wan_enable = - __ATTR(wwan_enable, S_IWUSR | S_IRUGO, - wan_enable_show, wan_enable_store); +static DEVICE_ATTR_RW(wan_enable); /* --------------------------------------------------------------------- */ @@ -5048,8 +5170,7 @@ static ssize_t cmos_command_store(struct device *dev, return (res) ? res : count; } -static struct device_attribute dev_attr_cmos_command = - __ATTR(cmos_command, S_IWUSR, NULL, cmos_command_store); +static DEVICE_ATTR_WO(cmos_command); /* --------------------------------------------------------------------- */ @@ -8017,9 +8138,7 @@ static ssize_t fan_pwm1_enable_store(struct device *dev, return count; } -static struct device_attribute dev_attr_fan_pwm1_enable = - __ATTR(pwm1_enable, S_IWUSR | S_IRUGO, - fan_pwm1_enable_show, fan_pwm1_enable_store); +static DEVICE_ATTR_RW(fan_pwm1_enable); /* sysfs fan pwm1 ------------------------------------------------------ */ static ssize_t fan_pwm1_show(struct device *dev, @@ -8079,9 +8198,7 @@ static ssize_t fan_pwm1_store(struct device *dev, return (rc) ? rc : count; } -static struct device_attribute dev_attr_fan_pwm1 = - __ATTR(pwm1, S_IWUSR | S_IRUGO, - fan_pwm1_show, fan_pwm1_store); +static DEVICE_ATTR_RW(fan_pwm1); /* sysfs fan fan1_input ------------------------------------------------ */ static ssize_t fan_fan1_input_show(struct device *dev, @@ -8098,9 +8215,7 @@ static ssize_t fan_fan1_input_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%u\n", speed); } -static struct device_attribute dev_attr_fan_fan1_input = - __ATTR(fan1_input, S_IRUGO, - fan_fan1_input_show, NULL); +static DEVICE_ATTR_RO(fan_fan1_input); /* sysfs fan fan2_input ------------------------------------------------ */ static ssize_t fan_fan2_input_show(struct device *dev, @@ -8117,9 +8232,7 @@ static ssize_t fan_fan2_input_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%u\n", speed); } -static struct device_attribute dev_attr_fan_fan2_input = - __ATTR(fan2_input, S_IRUGO, - fan_fan2_input_show, NULL); +static DEVICE_ATTR_RO(fan_fan2_input); /* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */ static ssize_t fan_fan_watchdog_show(struct device_driver *drv, @@ -8735,8 +8848,7 @@ static ssize_t thinkpad_acpi_pdev_name_show(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", TPACPI_NAME); } -static struct device_attribute dev_attr_thinkpad_acpi_pdev_name = - __ATTR(name, S_IRUGO, thinkpad_acpi_pdev_name_show, NULL); +static DEVICE_ATTR_RO(thinkpad_acpi_pdev_name); /* --------------------------------------------------------------------- */ diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index dbcb7a8915b8..9956b9902bb4 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -51,6 +51,7 @@ #include <linux/acpi.h> #include <linux/dmi.h> #include <linux/uaccess.h> +#include <acpi/video.h> MODULE_AUTHOR("John Belmonte"); MODULE_DESCRIPTION("Toshiba Laptop ACPI Extras Driver"); @@ -116,6 +117,7 @@ MODULE_LICENSE("GPL"); #define HCI_KBD_ILLUMINATION 0x0095 #define HCI_ECO_MODE 0x0097 #define HCI_ACCELEROMETER2 0x00a6 +#define HCI_SYSTEM_INFO 0xc000 #define SCI_PANEL_POWER_ON 0x010d #define SCI_ILLUMINATION 0x014e #define SCI_USB_SLEEP_CHARGE 0x0150 @@ -129,10 +131,13 @@ MODULE_LICENSE("GPL"); #define HCI_ACCEL_MASK 0x7fff #define HCI_HOTKEY_DISABLE 0x0b #define HCI_HOTKEY_ENABLE 0x09 +#define HCI_HOTKEY_SPECIAL_FUNCTIONS 0x10 #define HCI_LCD_BRIGHTNESS_BITS 3 #define HCI_LCD_BRIGHTNESS_SHIFT (16-HCI_LCD_BRIGHTNESS_BITS) #define HCI_LCD_BRIGHTNESS_LEVELS (1 << HCI_LCD_BRIGHTNESS_BITS) #define HCI_MISC_SHIFT 0x10 +#define HCI_SYSTEM_TYPE1 0x10 +#define HCI_SYSTEM_TYPE2 0x11 #define HCI_VIDEO_OUT_LCD 0x1 #define HCI_VIDEO_OUT_CRT 0x2 #define HCI_VIDEO_OUT_TV 0x4 @@ -147,9 +152,10 @@ MODULE_LICENSE("GPL"); #define SCI_KBD_MODE_OFF 0x10 #define SCI_KBD_TIME_MAX 0x3c001a #define SCI_USB_CHARGE_MODE_MASK 0xff -#define SCI_USB_CHARGE_DISABLED 0x30000 -#define SCI_USB_CHARGE_ALTERNATE 0x30009 -#define SCI_USB_CHARGE_AUTO 0x30021 +#define SCI_USB_CHARGE_DISABLED 0x00 +#define SCI_USB_CHARGE_ALTERNATE 0x09 +#define SCI_USB_CHARGE_TYPICAL 0x11 +#define SCI_USB_CHARGE_AUTO 0x21 #define SCI_USB_CHARGE_BAT_MASK 0x7 #define SCI_USB_CHARGE_BAT_LVL_OFF 0x1 #define SCI_USB_CHARGE_BAT_LVL_ON 0x4 @@ -174,6 +180,8 @@ struct toshiba_acpi_dev { int kbd_mode; int kbd_time; int usbsc_bat_level; + int usbsc_mode_base; + int hotkey_event_type; unsigned int illumination_supported:1; unsigned int video_supported:1; @@ -243,29 +251,6 @@ static const struct key_entry toshiba_acpi_keymap[] = { { KE_END, 0 }, }; -/* alternative keymap */ -static const struct dmi_system_id toshiba_alt_keymap_dmi[] = { - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "Satellite M840"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "Qosmio X75-A"), - }, - }, - { - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), - DMI_MATCH(DMI_PRODUCT_NAME, "TECRA A50-A"), - }, - }, - {} -}; - static const struct key_entry toshiba_acpi_alt_keymap[] = { { KE_KEY, 0x157, { KEY_MUTE } }, { KE_KEY, 0x102, { KEY_ZOOMOUT } }, @@ -281,6 +266,14 @@ static const struct key_entry toshiba_acpi_alt_keymap[] = { }; /* + * List of models which have a broken acpi-video backlight interface and thus + * need to use the toshiba (vendor) interface instead. + */ +static const struct dmi_system_id toshiba_vendor_backlight_dmi[] = { + {} +}; + +/* * Utility */ @@ -819,6 +812,54 @@ static int toshiba_accelerometer_get(struct toshiba_acpi_dev *dev, } /* Sleep (Charge and Music) utilities support */ +static void toshiba_usb_sleep_charge_available(struct toshiba_acpi_dev *dev) +{ + u32 in[TCI_WORDS] = { SCI_GET, SCI_USB_SLEEP_CHARGE, 0, 0, 0, 0 }; + u32 out[TCI_WORDS]; + acpi_status status; + + /* Set the feature to "not supported" in case of error */ + dev->usb_sleep_charge_supported = 0; + + if (!sci_open(dev)) + return; + + status = tci_raw(dev, in, out); + if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) { + pr_err("ACPI call to get USB Sleep and Charge mode failed\n"); + sci_close(dev); + return; + } else if (out[0] == TOS_NOT_SUPPORTED) { + pr_info("USB Sleep and Charge not supported\n"); + sci_close(dev); + return; + } else if (out[0] == TOS_SUCCESS) { + dev->usbsc_mode_base = out[4]; + } + + in[5] = SCI_USB_CHARGE_BAT_LVL; + status = tci_raw(dev, in, out); + if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) { + pr_err("ACPI call to get USB Sleep and Charge mode failed\n"); + sci_close(dev); + return; + } else if (out[0] == TOS_NOT_SUPPORTED) { + pr_info("USB Sleep and Charge not supported\n"); + sci_close(dev); + return; + } else if (out[0] == TOS_SUCCESS) { + dev->usbsc_bat_level = out[2]; + /* + * If we reach this point, it means that the laptop has support + * for this feature and all values are initialized. + * Set it as supported. + */ + dev->usb_sleep_charge_supported = 1; + } + + sci_close(dev); +} + static int toshiba_usb_sleep_charge_get(struct toshiba_acpi_dev *dev, u32 *mode) { @@ -934,11 +975,11 @@ static int toshiba_usb_rapid_charge_get(struct toshiba_acpi_dev *dev, status = tci_raw(dev, in, out); sci_close(dev); if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) { - pr_err("ACPI call to get USB S&C battery level failed\n"); + pr_err("ACPI call to get USB Rapid Charge failed\n"); return -EIO; } else if (out[0] == TOS_NOT_SUPPORTED || out[0] == TOS_INPUT_DATA_ERROR) { - pr_info("USB Sleep and Charge not supported\n"); + pr_info("USB Rapid Charge not supported\n"); return -ENODEV; } @@ -962,10 +1003,10 @@ static int toshiba_usb_rapid_charge_set(struct toshiba_acpi_dev *dev, status = tci_raw(dev, in, out); sci_close(dev); if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) { - pr_err("ACPI call to set USB S&C battery level failed\n"); + pr_err("ACPI call to set USB Rapid Charge failed\n"); return -EIO; } else if (out[0] == TOS_NOT_SUPPORTED) { - pr_info("USB Sleep and Charge not supported\n"); + pr_info("USB Rapid Charge not supported\n"); return -ENODEV; } else if (out[0] == TOS_INPUT_DATA_ERROR) { return -EIO; @@ -984,10 +1025,10 @@ static int toshiba_usb_sleep_music_get(struct toshiba_acpi_dev *dev, u32 *state) result = sci_read(dev, SCI_USB_SLEEP_MUSIC, state); sci_close(dev); if (result == TOS_FAILURE) { - pr_err("ACPI call to set USB S&C mode failed\n"); + pr_err("ACPI call to get Sleep and Music failed\n"); return -EIO; } else if (result == TOS_NOT_SUPPORTED) { - pr_info("USB Sleep and Charge not supported\n"); + pr_info("Sleep and Music not supported\n"); return -ENODEV; } else if (result == TOS_INPUT_DATA_ERROR) { return -EIO; @@ -1006,10 +1047,10 @@ static int toshiba_usb_sleep_music_set(struct toshiba_acpi_dev *dev, u32 state) result = sci_write(dev, SCI_USB_SLEEP_MUSIC, state); sci_close(dev); if (result == TOS_FAILURE) { - pr_err("ACPI call to set USB S&C mode failed\n"); + pr_err("ACPI call to set Sleep and Music failed\n"); return -EIO; } else if (result == TOS_NOT_SUPPORTED) { - pr_info("USB Sleep and Charge not supported\n"); + pr_info("Sleep and Music not supported\n"); return -ENODEV; } else if (result == TOS_INPUT_DATA_ERROR) { return -EIO; @@ -1149,6 +1190,28 @@ static int toshiba_usb_three_set(struct toshiba_acpi_dev *dev, u32 state) return 0; } +/* Hotkey Event type */ +static int toshiba_hotkey_event_type_get(struct toshiba_acpi_dev *dev, + u32 *type) +{ + u32 val1 = 0x03; + u32 val2 = 0; + u32 result; + + result = hci_read2(dev, HCI_SYSTEM_INFO, &val1, &val2); + if (result == TOS_FAILURE) { + pr_err("ACPI call to get System type failed\n"); + return -EIO; + } else if (result == TOS_NOT_SUPPORTED) { + pr_info("System type not supported\n"); + return -ENODEV; + } + + *type = val2; + + return 0; +} + /* Bluetooth rfkill handlers */ static u32 hci_get_bt_present(struct toshiba_acpi_dev *dev, bool *present) @@ -1973,17 +2036,21 @@ static ssize_t usb_sleep_charge_store(struct device *dev, * 0 - Disabled * 1 - Alternate (Non USB conformant devices that require more power) * 2 - Auto (USB conformant devices) + * 3 - Typical */ - if (state != 0 && state != 1 && state != 2) + if (state != 0 && state != 1 && state != 2 && state != 3) return -EINVAL; /* Set the USB charging mode to internal value */ + mode = toshiba->usbsc_mode_base; if (state == 0) - mode = SCI_USB_CHARGE_DISABLED; + mode |= SCI_USB_CHARGE_DISABLED; else if (state == 1) - mode = SCI_USB_CHARGE_ALTERNATE; + mode |= SCI_USB_CHARGE_ALTERNATE; else if (state == 2) - mode = SCI_USB_CHARGE_AUTO; + mode |= SCI_USB_CHARGE_AUTO; + else if (state == 3) + mode |= SCI_USB_CHARGE_TYPICAL; ret = toshiba_usb_sleep_charge_set(toshiba, mode); if (ret) @@ -2333,6 +2400,20 @@ static int toshiba_acpi_enable_hotkeys(struct toshiba_acpi_dev *dev) return 0; } +static void toshiba_acpi_enable_special_functions(struct toshiba_acpi_dev *dev) +{ + u32 result; + + /* + * Re-activate the hotkeys, but this time, we are using the + * "Special Functions" mode. + */ + result = hci_write1(dev, HCI_HOTKEY_EVENT, + HCI_HOTKEY_SPECIAL_FUNCTIONS); + if (result != TOS_SUCCESS) + pr_err("Could not enable the Special Function mode\n"); +} + static bool toshiba_acpi_i8042_filter(unsigned char data, unsigned char str, struct serio *port) { @@ -2434,10 +2515,22 @@ static void toshiba_acpi_process_hotkeys(struct toshiba_acpi_dev *dev) static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev) { + const struct key_entry *keymap = toshiba_acpi_keymap; acpi_handle ec_handle; - int error; + u32 events_type; u32 hci_result; - const struct key_entry *keymap = toshiba_acpi_keymap; + int error; + + error = toshiba_acpi_enable_hotkeys(dev); + if (error) + return error; + + error = toshiba_hotkey_event_type_get(dev, &events_type); + if (error) { + pr_err("Unable to query Hotkey Event Type\n"); + return error; + } + dev->hotkey_event_type = events_type; dev->hotkey_dev = input_allocate_device(); if (!dev->hotkey_dev) @@ -2447,8 +2540,14 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev) dev->hotkey_dev->phys = "toshiba_acpi/input0"; dev->hotkey_dev->id.bustype = BUS_HOST; - if (dmi_check_system(toshiba_alt_keymap_dmi)) + if (events_type == HCI_SYSTEM_TYPE1 || + !dev->kbd_function_keys_supported) + keymap = toshiba_acpi_keymap; + else if (events_type == HCI_SYSTEM_TYPE2 || + dev->kbd_function_keys_supported) keymap = toshiba_acpi_alt_keymap; + else + pr_info("Unknown event type received %x\n", events_type); error = sparse_keymap_setup(dev->hotkey_dev, keymap, NULL); if (error) goto err_free_dev; @@ -2490,12 +2589,6 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev) goto err_remove_filter; } - error = toshiba_acpi_enable_hotkeys(dev); - if (error) { - pr_info("Unable to enable hotkeys\n"); - goto err_remove_filter; - } - error = input_register_device(dev->hotkey_dev); if (error) { pr_info("Unable to register input device\n"); @@ -2541,6 +2634,20 @@ static int toshiba_acpi_setup_backlight(struct toshiba_acpi_dev *dev) ret = get_tr_backlight_status(dev, &enabled); dev->tr_backlight_supported = !ret; + /* + * Tell acpi-video-detect code to prefer vendor backlight on all + * systems with transflective backlight and on dmi matched systems. + */ + if (dev->tr_backlight_supported || + dmi_check_system(toshiba_vendor_backlight_dmi)) + acpi_video_dmi_promote_vendor(); + + if (acpi_video_backlight_support()) + return 0; + + /* acpi-video may have loaded before we called dmi_promote_vendor() */ + acpi_video_unregister_backlight(); + memset(&props, 0, sizeof(props)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = HCI_LCD_BRIGHTNESS_LEVELS - 1; @@ -2624,6 +2731,7 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) { struct toshiba_acpi_dev *dev; const char *hci_method; + u32 special_functions; u32 dummy; bool bt_present; int ret = 0; @@ -2648,6 +2756,16 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) acpi_dev->driver_data = dev; dev_set_drvdata(&acpi_dev->dev, dev); + /* Query the BIOS for supported features */ + + /* + * The "Special Functions" are always supported by the laptops + * with the new keyboard layout, query for its presence to help + * determine the keymap layout to use. + */ + ret = toshiba_function_keys_get(dev, &special_functions); + dev->kbd_function_keys_supported = !ret; + if (toshiba_acpi_setup_keyboard(dev)) pr_info("Unable to activate hotkeys\n"); @@ -2716,8 +2834,7 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) ret = toshiba_accelerometer_supported(dev); dev->accelerometer_supported = !ret; - ret = toshiba_usb_sleep_charge_get(dev, &dummy); - dev->usb_sleep_charge_supported = !ret; + toshiba_usb_sleep_charge_available(dev); ret = toshiba_usb_rapid_charge_get(dev, &dummy); dev->usb_rapid_charge_supported = !ret; @@ -2725,23 +2842,25 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) ret = toshiba_usb_sleep_music_get(dev, &dummy); dev->usb_sleep_music_supported = !ret; - ret = toshiba_function_keys_get(dev, &dummy); - dev->kbd_function_keys_supported = !ret; - ret = toshiba_panel_power_on_get(dev, &dummy); dev->panel_power_on_supported = !ret; ret = toshiba_usb_three_get(dev, &dummy); dev->usb_three_supported = !ret; - /* Determine whether or not BIOS supports fan and video interfaces */ - ret = get_video_status(dev, &dummy); dev->video_supported = !ret; ret = get_fan_status(dev, &dummy); dev->fan_supported = !ret; + /* + * Enable the "Special Functions" mode only if they are + * supported and if they are activated. + */ + if (dev->kbd_function_keys_supported && special_functions) + toshiba_acpi_enable_special_functions(dev); + ret = sysfs_create_group(&dev->acpi_dev->dev.kobj, &toshiba_attr_group); if (ret) { @@ -2770,6 +2889,21 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event) case 0x80: /* Hotkeys and some system events */ toshiba_acpi_process_hotkeys(dev); break; + case 0x81: /* Dock events */ + case 0x82: + case 0x83: + pr_info("Dock event received %x\n", event); + break; + case 0x88: /* Thermal events */ + pr_info("Thermal event received\n"); + break; + case 0x8f: /* LID closed */ + case 0x90: /* LID is closed and Dock has been ejected */ + break; + case 0x8c: /* SATA power events */ + case 0x8b: + pr_info("SATA power event received %x\n", event); + break; case 0x92: /* Keyboard backlight mode changed */ /* Update sysfs entries */ ret = sysfs_update_group(&acpi_dev->dev.kobj, @@ -2777,17 +2911,19 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event) if (ret) pr_err("Unable to update sysfs entries\n"); break; - case 0x81: /* Unknown */ - case 0x82: /* Unknown */ - case 0x83: /* Unknown */ - case 0x8c: /* Unknown */ + case 0x85: /* Unknown */ + case 0x8d: /* Unknown */ case 0x8e: /* Unknown */ - case 0x8f: /* Unknown */ - case 0x90: /* Unknown */ + case 0x94: /* Unknown */ + case 0x95: /* Unknown */ default: pr_info("Unknown event received %x\n", event); break; } + + acpi_bus_generate_netlink_event(acpi_dev->pnp.device_class, + dev_name(&acpi_dev->dev), + event, 0); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/platform/x86/toshiba_bluetooth.c b/drivers/platform/x86/toshiba_bluetooth.c index 2cb1ea62b4a7..249800763362 100644 --- a/drivers/platform/x86/toshiba_bluetooth.c +++ b/drivers/platform/x86/toshiba_bluetooth.c @@ -2,6 +2,7 @@ * Toshiba Bluetooth Enable Driver * * Copyright (C) 2009 Jes Sorensen <Jes.Sorensen@gmail.com> + * Copyright (C) 2015 Azael Avalos <coproscefalo@gmail.com> * * Thanks to Matthew Garrett for background info on ACPI innards which * normal people aren't meant to understand :-) @@ -25,6 +26,10 @@ #include <linux/types.h> #include <linux/acpi.h> +#define BT_KILLSWITCH_MASK 0x01 +#define BT_PLUGGED_MASK 0x40 +#define BT_POWER_MASK 0x80 + MODULE_AUTHOR("Jes Sorensen <Jes.Sorensen@gmail.com>"); MODULE_DESCRIPTION("Toshiba Laptop ACPI Bluetooth Enable Driver"); MODULE_LICENSE("GPL"); @@ -57,32 +62,107 @@ static struct acpi_driver toshiba_bt_rfkill_driver = { .drv.pm = &toshiba_bt_pm, }; +static int toshiba_bluetooth_present(acpi_handle handle) +{ + acpi_status result; + u64 bt_present; + + /* + * Some Toshiba laptops may have a fake TOS6205 device in + * their ACPI BIOS, so query the _STA method to see if there + * is really anything there. + */ + result = acpi_evaluate_integer(handle, "_STA", NULL, &bt_present); + if (ACPI_FAILURE(result)) { + pr_err("ACPI call to query Bluetooth presence failed"); + return -ENXIO; + } else if (!bt_present) { + pr_info("Bluetooth device not present\n"); + return -ENODEV; + } + + return 0; +} + +static int toshiba_bluetooth_status(acpi_handle handle) +{ + acpi_status result; + u64 status; + + result = acpi_evaluate_integer(handle, "BTST", NULL, &status); + if (ACPI_FAILURE(result)) { + pr_err("Could not get Bluetooth device status\n"); + return -ENXIO; + } + + pr_info("Bluetooth status %llu\n", status); + + return status; +} static int toshiba_bluetooth_enable(acpi_handle handle) { - acpi_status res1, res2; - u64 result; + acpi_status result; + bool killswitch; + bool powered; + bool plugged; + int status; /* * Query ACPI to verify RFKill switch is set to 'on'. * If not, we return silently, no need to report it as * an error. */ - res1 = acpi_evaluate_integer(handle, "BTST", NULL, &result); - if (ACPI_FAILURE(res1)) - return res1; - if (!(result & 0x01)) - return 0; + status = toshiba_bluetooth_status(handle); + if (status < 0) + return status; + + killswitch = (status & BT_KILLSWITCH_MASK) ? true : false; + powered = (status & BT_POWER_MASK) ? true : false; + plugged = (status & BT_PLUGGED_MASK) ? true : false; - pr_info("Re-enabling Toshiba Bluetooth\n"); - res1 = acpi_evaluate_object(handle, "AUSB", NULL, NULL); - res2 = acpi_evaluate_object(handle, "BTPO", NULL, NULL); - if (!ACPI_FAILURE(res1) || !ACPI_FAILURE(res2)) + if (!killswitch) return 0; + /* + * This check ensures to only enable the device if it is powered + * off or detached, as some recent devices somehow pass the killswitch + * test, causing a loop enabling/disabling the device, see bug 93911. + */ + if (powered || plugged) + return 0; + + result = acpi_evaluate_object(handle, "AUSB", NULL, NULL); + if (ACPI_FAILURE(result)) { + pr_err("Could not attach USB Bluetooth device\n"); + return -ENXIO; + } + + result = acpi_evaluate_object(handle, "BTPO", NULL, NULL); + if (ACPI_FAILURE(result)) { + pr_err("Could not power ON Bluetooth device\n"); + return -ENXIO; + } + + return 0; +} + +static int toshiba_bluetooth_disable(acpi_handle handle) +{ + acpi_status result; + + result = acpi_evaluate_object(handle, "BTPF", NULL, NULL); + if (ACPI_FAILURE(result)) { + pr_err("Could not power OFF Bluetooth device\n"); + return -ENXIO; + } - pr_warn("Failed to re-enable Toshiba Bluetooth\n"); + result = acpi_evaluate_object(handle, "DUSB", NULL, NULL); + if (ACPI_FAILURE(result)) { + pr_err("Could not detach USB Bluetooth device\n"); + return -ENXIO; + } - return -ENODEV; + return 0; } static void toshiba_bt_rfkill_notify(struct acpi_device *device, u32 event) @@ -99,23 +179,18 @@ static int toshiba_bt_resume(struct device *dev) static int toshiba_bt_rfkill_add(struct acpi_device *device) { - acpi_status status; - u64 bt_present; - int result = -ENODEV; + int result; - /* - * Some Toshiba laptops may have a fake TOS6205 device in - * their ACPI BIOS, so query the _STA method to see if there - * is really anything there, before trying to enable it. - */ - status = acpi_evaluate_integer(device->handle, "_STA", NULL, - &bt_present); + result = toshiba_bluetooth_present(device->handle); + if (result) + return result; - if (!ACPI_FAILURE(status) && bt_present) { - pr_info("Detected Toshiba ACPI Bluetooth device - " - "installing RFKill handler\n"); - result = toshiba_bluetooth_enable(device->handle); - } + pr_info("Toshiba ACPI Bluetooth device driver\n"); + + /* Enable the BT device */ + result = toshiba_bluetooth_enable(device->handle); + if (result) + return result; return result; } @@ -123,7 +198,7 @@ static int toshiba_bt_rfkill_add(struct acpi_device *device) static int toshiba_bt_rfkill_remove(struct acpi_device *device) { /* clean up */ - return 0; + return toshiba_bluetooth_disable(device->handle); } module_acpi_driver(toshiba_bt_rfkill_driver); diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 737e56d46f61..aac47573f9ed 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -45,7 +45,6 @@ MODULE_LICENSE("GPL"); #define ACPI_WMI_CLASS "wmi" -static DEFINE_MUTEX(wmi_data_lock); static LIST_HEAD(wmi_block_list); struct guid_block { @@ -240,10 +239,10 @@ static bool find_guid(const char *guid_string, struct wmi_block **out) if (memcmp(block->guid, guid_input, 16) == 0) { if (out) *out = wblock; - return 1; + return true; } } - return 0; + return false; } static acpi_status wmi_method_enable(struct wmi_block *wblock, int enable) diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index e03877c4b195..fd243231620a 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -1064,6 +1064,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { RAPL_CPU(0x3f, rapl_defaults_hsw_server),/* Haswell servers */ RAPL_CPU(0x4f, rapl_defaults_hsw_server),/* Broadwell servers */ RAPL_CPU(0x45, rapl_defaults_core),/* Haswell ULT */ + RAPL_CPU(0x4E, rapl_defaults_core),/* Skylake */ RAPL_CPU(0x4C, rapl_defaults_atom),/* Braswell */ RAPL_CPU(0x4A, rapl_defaults_atom),/* Tangier */ RAPL_CPU(0x56, rapl_defaults_core),/* Future Xeon */ diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 810aef3f4c3e..ba34c7d89042 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -573,7 +573,7 @@ EXPORT_SYMBOL_GPL(of_pwm_get); * @table: array of consumers to register * @num: number of consumers in table */ -void __init pwm_add_table(struct pwm_lookup *table, size_t num) +void pwm_add_table(struct pwm_lookup *table, size_t num) { mutex_lock(&pwm_lookup_lock); diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c index 522f7075bb1a..fa5feaba25a5 100644 --- a/drivers/pwm/pwm-atmel-hlcdc.c +++ b/drivers/pwm/pwm-atmel-hlcdc.c @@ -225,6 +225,10 @@ static const struct of_device_id atmel_hlcdc_dt_ids[] = { .compatible = "atmel,sama5d3-hlcdc", .data = &atmel_hlcdc_pwm_sama5d3_errata, }, + { + .compatible = "atmel,sama5d4-hlcdc", + .data = &atmel_hlcdc_pwm_sama5d3_errata, + }, { /* sentinel */ }, }; diff --git a/drivers/pwm/pwm-mxs.c b/drivers/pwm/pwm-mxs.c index f75ecb09d97d..b430811e14f5 100644 --- a/drivers/pwm/pwm-mxs.c +++ b/drivers/pwm/pwm-mxs.c @@ -35,6 +35,10 @@ #define PERIOD_CDIV(div) (((div) & 0x7) << 20) #define PERIOD_CDIV_MAX 8 +static const unsigned int cdiv[PERIOD_CDIV_MAX] = { + 1, 2, 4, 8, 16, 64, 256, 1024 +}; + struct mxs_pwm_chip { struct pwm_chip chip; struct clk *clk; @@ -54,13 +58,13 @@ static int mxs_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, rate = clk_get_rate(mxs->clk); while (1) { - c = rate / (1 << div); + c = rate / cdiv[div]; c = c * period_ns; do_div(c, 1000000000); if (c < PERIOD_PERIOD_MAX) break; div++; - if (div > PERIOD_CDIV_MAX) + if (div >= PERIOD_CDIV_MAX) return -EINVAL; } diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index 3fb775ded0df..34b5c275a92a 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -202,7 +202,7 @@ static const struct pwm_ops pca9685_pwm_ops = { .owner = THIS_MODULE, }; -static struct regmap_config pca9685_regmap_i2c_config = { +static const struct regmap_config pca9685_regmap_i2c_config = { .reg_bits = 8, .val_bits = 8, .max_register = PCA9685_NUMREGS, diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c index 3e9b5835a4af..ff201e1b9219 100644 --- a/drivers/pwm/pwm-samsung.c +++ b/drivers/pwm/pwm-samsung.c @@ -269,12 +269,31 @@ static void pwm_samsung_disable(struct pwm_chip *chip, struct pwm_device *pwm) spin_unlock_irqrestore(&samsung_pwm_lock, flags); } +static void pwm_samsung_manual_update(struct samsung_pwm_chip *chip, + struct pwm_device *pwm) +{ + unsigned int tcon_chan = to_tcon_channel(pwm->hwpwm); + u32 tcon; + unsigned long flags; + + spin_lock_irqsave(&samsung_pwm_lock, flags); + + tcon = readl(chip->base + REG_TCON); + tcon |= TCON_MANUALUPDATE(tcon_chan); + writel(tcon, chip->base + REG_TCON); + + tcon &= ~TCON_MANUALUPDATE(tcon_chan); + writel(tcon, chip->base + REG_TCON); + + spin_unlock_irqrestore(&samsung_pwm_lock, flags); +} + static int pwm_samsung_config(struct pwm_chip *chip, struct pwm_device *pwm, int duty_ns, int period_ns) { struct samsung_pwm_chip *our_chip = to_samsung_pwm_chip(chip); struct samsung_pwm_channel *chan = pwm_get_chip_data(pwm); - u32 tin_ns = chan->tin_ns, tcnt, tcmp; + u32 tin_ns = chan->tin_ns, tcnt, tcmp, oldtcmp; /* * We currently avoid using 64bit arithmetic by using the @@ -288,6 +307,7 @@ static int pwm_samsung_config(struct pwm_chip *chip, struct pwm_device *pwm, return 0; tcnt = readl(our_chip->base + REG_TCNTB(pwm->hwpwm)); + oldtcmp = readl(our_chip->base + REG_TCMPB(pwm->hwpwm)); /* We need tick count for calculation, not last tick. */ ++tcnt; @@ -335,6 +355,16 @@ static int pwm_samsung_config(struct pwm_chip *chip, struct pwm_device *pwm, writel(tcnt, our_chip->base + REG_TCNTB(pwm->hwpwm)); writel(tcmp, our_chip->base + REG_TCMPB(pwm->hwpwm)); + /* + * In case the PWM is currently at 100% duty cycle, force a manual + * update to prevent the signal staying high if the PWM is disabled + * shortly afer this update (before it autoreloaded the new values). + */ + if (oldtcmp == (u32) -1) { + dev_dbg(our_chip->chip.dev, "Forcing manual update"); + pwm_samsung_manual_update(our_chip, pwm); + } + chan->period_ns = period_ns; chan->tin_ns = tin_ns; chan->duty_ns = duty_ns; diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c index 71d7802aa8b4..6f1fa1773e76 100644 --- a/drivers/s390/kvm/virtio_ccw.c +++ b/drivers/s390/kvm/virtio_ccw.c @@ -1201,13 +1201,9 @@ static int virtio_ccw_online(struct ccw_device *cdev) vcdev->vdev.id.vendor = cdev->id.cu_type; vcdev->vdev.id.device = cdev->id.cu_model; - if (virtio_device_is_legacy_only(vcdev->vdev.id)) { - vcdev->revision = 0; - } else { - ret = virtio_ccw_set_transport_rev(vcdev); - if (ret) - goto out_free; - } + ret = virtio_ccw_set_transport_rev(vcdev); + if (ret) + goto out_free; ret = register_virtio_device(&vcdev->vdev); if (ret) { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 57418258c101..fe8a8d157e22 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3065,7 +3065,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle, { struct qla_hw_data *ha = vha->hw; struct se_cmd *se_cmd; - struct target_core_fabric_ops *tfo; + const struct target_core_fabric_ops *tfo; struct qla_tgt_cmd *cmd; if (handle & CTIO_INTERMEDIATE_HANDLE_MARK) { diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index ab4879e12ea7..68c2002e78bf 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -53,9 +53,8 @@ static struct workqueue_struct *tcm_qla2xxx_free_wq; static struct workqueue_struct *tcm_qla2xxx_cmd_wq; -/* Local pointer to allocated TCM configfs fabric module */ -static struct target_fabric_configfs *tcm_qla2xxx_fabric_configfs; -static struct target_fabric_configfs *tcm_qla2xxx_npiv_fabric_configfs; +static const struct target_core_fabric_ops tcm_qla2xxx_ops; +static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops; /* * Parse WWN. @@ -336,6 +335,14 @@ static int tcm_qla2xxx_check_demo_mode_login_only(struct se_portal_group *se_tpg return tpg->tpg_attrib.demo_mode_login_only; } +static int tcm_qla2xxx_check_prot_fabric_only(struct se_portal_group *se_tpg) +{ + struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, + struct tcm_qla2xxx_tpg, se_tpg); + + return tpg->tpg_attrib.fabric_prot_type; +} + static struct se_node_acl *tcm_qla2xxx_alloc_fabric_acl( struct se_portal_group *se_tpg) { @@ -1082,8 +1089,53 @@ static ssize_t tcm_qla2xxx_tpg_store_enable( TF_TPG_BASE_ATTR(tcm_qla2xxx, enable, S_IRUGO | S_IWUSR); +static ssize_t tcm_qla2xxx_tpg_show_dynamic_sessions( + struct se_portal_group *se_tpg, + char *page) +{ + return target_show_dynamic_sessions(se_tpg, page); +} + +TF_TPG_BASE_ATTR_RO(tcm_qla2xxx, dynamic_sessions); + +static ssize_t tcm_qla2xxx_tpg_store_fabric_prot_type( + struct se_portal_group *se_tpg, + const char *page, + size_t count) +{ + struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, + struct tcm_qla2xxx_tpg, se_tpg); + unsigned long val; + int ret = kstrtoul(page, 0, &val); + + if (ret) { + pr_err("kstrtoul() returned %d for fabric_prot_type\n", ret); + return ret; + } + if (val != 0 && val != 1 && val != 3) { + pr_err("Invalid qla2xxx fabric_prot_type: %lu\n", val); + return -EINVAL; + } + tpg->tpg_attrib.fabric_prot_type = val; + + return count; +} + +static ssize_t tcm_qla2xxx_tpg_show_fabric_prot_type( + struct se_portal_group *se_tpg, + char *page) +{ + struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, + struct tcm_qla2xxx_tpg, se_tpg); + + return sprintf(page, "%d\n", tpg->tpg_attrib.fabric_prot_type); +} +TF_TPG_BASE_ATTR(tcm_qla2xxx, fabric_prot_type, S_IRUGO | S_IWUSR); + static struct configfs_attribute *tcm_qla2xxx_tpg_attrs[] = { &tcm_qla2xxx_tpg_enable.attr, + &tcm_qla2xxx_tpg_dynamic_sessions.attr, + &tcm_qla2xxx_tpg_fabric_prot_type.attr, NULL, }; @@ -1124,7 +1176,7 @@ static struct se_portal_group *tcm_qla2xxx_make_tpg( tpg->tpg_attrib.cache_dynamic_acls = 1; tpg->tpg_attrib.demo_mode_login_only = 1; - ret = core_tpg_register(&tcm_qla2xxx_fabric_configfs->tf_ops, wwn, + ret = core_tpg_register(&tcm_qla2xxx_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { kfree(tpg); @@ -1244,7 +1296,7 @@ static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg( tpg->tpg_attrib.cache_dynamic_acls = 1; tpg->tpg_attrib.demo_mode_login_only = 1; - ret = core_tpg_register(&tcm_qla2xxx_npiv_fabric_configfs->tf_ops, wwn, + ret = core_tpg_register(&tcm_qla2xxx_npiv_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { kfree(tpg); @@ -1560,7 +1612,7 @@ static int tcm_qla2xxx_check_initiator_node_acl( se_sess = transport_init_session_tags(num_tags, sizeof(struct qla_tgt_cmd), - TARGET_PROT_NORMAL); + TARGET_PROT_ALL); if (IS_ERR(se_sess)) { pr_err("Unable to initialize struct se_session\n"); return PTR_ERR(se_sess); @@ -1934,7 +1986,9 @@ static struct configfs_attribute *tcm_qla2xxx_wwn_attrs[] = { NULL, }; -static struct target_core_fabric_ops tcm_qla2xxx_ops = { +static const struct target_core_fabric_ops tcm_qla2xxx_ops = { + .module = THIS_MODULE, + .name = "qla2xxx", .get_fabric_name = tcm_qla2xxx_get_fabric_name, .get_fabric_proto_ident = tcm_qla2xxx_get_fabric_proto_ident, .tpg_get_wwn = tcm_qla2xxx_get_fabric_wwn, @@ -1949,6 +2003,7 @@ static struct target_core_fabric_ops tcm_qla2xxx_ops = { tcm_qla2xxx_check_demo_write_protect, .tpg_check_prod_mode_write_protect = tcm_qla2xxx_check_prod_write_protect, + .tpg_check_prot_fabric_only = tcm_qla2xxx_check_prot_fabric_only, .tpg_check_demo_mode_login_only = tcm_qla2xxx_check_demo_mode_login_only, .tpg_alloc_fabric_acl = tcm_qla2xxx_alloc_fabric_acl, .tpg_release_fabric_acl = tcm_qla2xxx_release_fabric_acl, @@ -1983,9 +2038,15 @@ static struct target_core_fabric_ops tcm_qla2xxx_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = tcm_qla2xxx_make_nodeacl, .fabric_drop_nodeacl = tcm_qla2xxx_drop_nodeacl, + + .tfc_wwn_attrs = tcm_qla2xxx_wwn_attrs, + .tfc_tpg_base_attrs = tcm_qla2xxx_tpg_attrs, + .tfc_tpg_attrib_attrs = tcm_qla2xxx_tpg_attrib_attrs, }; -static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = { +static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = { + .module = THIS_MODULE, + .name = "qla2xxx_npiv", .get_fabric_name = tcm_qla2xxx_npiv_get_fabric_name, .get_fabric_proto_ident = tcm_qla2xxx_get_fabric_proto_ident, .tpg_get_wwn = tcm_qla2xxx_get_fabric_wwn, @@ -2033,94 +2094,26 @@ static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = tcm_qla2xxx_make_nodeacl, .fabric_drop_nodeacl = tcm_qla2xxx_drop_nodeacl, + + .tfc_wwn_attrs = tcm_qla2xxx_wwn_attrs, + .tfc_tpg_base_attrs = tcm_qla2xxx_npiv_tpg_attrs, }; static int tcm_qla2xxx_register_configfs(void) { - struct target_fabric_configfs *fabric, *npiv_fabric; int ret; pr_debug("TCM QLOGIC QLA2XXX fabric module %s on %s/%s on " UTS_RELEASE"\n", TCM_QLA2XXX_VERSION, utsname()->sysname, utsname()->machine); - /* - * Register the top level struct config_item_type with TCM core - */ - fabric = target_fabric_configfs_init(THIS_MODULE, "qla2xxx"); - if (IS_ERR(fabric)) { - pr_err("target_fabric_configfs_init() failed\n"); - return PTR_ERR(fabric); - } - /* - * Setup fabric->tf_ops from our local tcm_qla2xxx_ops - */ - fabric->tf_ops = tcm_qla2xxx_ops; - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_qla2xxx_tpg_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = - tcm_qla2xxx_tpg_attrib_attrs; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - /* - * Register the fabric for use within TCM - */ - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() failed for TCM_QLA2XXX\n"); + + ret = target_register_template(&tcm_qla2xxx_ops); + if (ret) return ret; - } - /* - * Setup our local pointer to *fabric - */ - tcm_qla2xxx_fabric_configfs = fabric; - pr_debug("TCM_QLA2XXX[0] - Set fabric -> tcm_qla2xxx_fabric_configfs\n"); - /* - * Register the top level struct config_item_type for NPIV with TCM core - */ - npiv_fabric = target_fabric_configfs_init(THIS_MODULE, "qla2xxx_npiv"); - if (IS_ERR(npiv_fabric)) { - pr_err("target_fabric_configfs_init() failed\n"); - ret = PTR_ERR(npiv_fabric); - goto out_fabric; - } - /* - * Setup fabric->tf_ops from our local tcm_qla2xxx_npiv_ops - */ - npiv_fabric->tf_ops = tcm_qla2xxx_npiv_ops; - /* - * Setup default attribute lists for various npiv_fabric->tf_cit_tmpl - */ - npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs; - npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = - tcm_qla2xxx_npiv_tpg_attrs; - npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - /* - * Register the npiv_fabric for use within TCM - */ - ret = target_fabric_configfs_register(npiv_fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() failed for TCM_QLA2XXX\n"); + ret = target_register_template(&tcm_qla2xxx_npiv_ops); + if (ret) goto out_fabric; - } - /* - * Setup our local pointer to *npiv_fabric - */ - tcm_qla2xxx_npiv_fabric_configfs = npiv_fabric; - pr_debug("TCM_QLA2XXX[0] - Set fabric -> tcm_qla2xxx_npiv_fabric_configfs\n"); tcm_qla2xxx_free_wq = alloc_workqueue("tcm_qla2xxx_free", WQ_MEM_RECLAIM, 0); @@ -2140,9 +2133,9 @@ static int tcm_qla2xxx_register_configfs(void) out_free_wq: destroy_workqueue(tcm_qla2xxx_free_wq); out_fabric_npiv: - target_fabric_configfs_deregister(tcm_qla2xxx_npiv_fabric_configfs); + target_unregister_template(&tcm_qla2xxx_npiv_ops); out_fabric: - target_fabric_configfs_deregister(tcm_qla2xxx_fabric_configfs); + target_unregister_template(&tcm_qla2xxx_ops); return ret; } @@ -2151,13 +2144,8 @@ static void tcm_qla2xxx_deregister_configfs(void) destroy_workqueue(tcm_qla2xxx_cmd_wq); destroy_workqueue(tcm_qla2xxx_free_wq); - target_fabric_configfs_deregister(tcm_qla2xxx_fabric_configfs); - tcm_qla2xxx_fabric_configfs = NULL; - pr_debug("TCM_QLA2XXX[0] - Cleared tcm_qla2xxx_fabric_configfs\n"); - - target_fabric_configfs_deregister(tcm_qla2xxx_npiv_fabric_configfs); - tcm_qla2xxx_npiv_fabric_configfs = NULL; - pr_debug("TCM_QLA2XXX[0] - Cleared tcm_qla2xxx_npiv_fabric_configfs\n"); + target_unregister_template(&tcm_qla2xxx_ops); + target_unregister_template(&tcm_qla2xxx_npiv_ops); } static int __init tcm_qla2xxx_init(void) diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h index 10c002145648..23295115c9fc 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h @@ -33,6 +33,7 @@ struct tcm_qla2xxx_tpg_attrib { int demo_mode_write_protect; int prod_mode_write_protect; int demo_mode_login_only; + int fabric_prot_type; }; struct tcm_qla2xxx_tpg { diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 186924aa4740..f6bac9e77d06 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -1023,7 +1023,6 @@ static struct dma_chan *rspi_request_dma_chan(struct device *dev, } memset(&cfg, 0, sizeof(cfg)); - cfg.slave_id = id; cfg.direction = dir; if (dir == DMA_MEM_TO_DEV) { cfg.dst_addr = port_addr; diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index e57eec0b2f46..bcc7c635d8e7 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -1030,7 +1030,6 @@ static struct dma_chan *sh_msiof_request_dma_chan(struct device *dev, } memset(&cfg, 0, sizeof(cfg)); - cfg.slave_id = id; cfg.direction = dir; if (dir == DMA_MEM_TO_DEV) { cfg.dst_addr = port_addr; diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index 0e3d8c7add24..b0b96ab31954 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -1106,6 +1106,7 @@ struct dma_buf *ion_share_dma_buf(struct ion_client *client, struct ion_buffer *buffer; struct dma_buf *dmabuf; bool valid_handle; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); mutex_lock(&client->lock); valid_handle = ion_handle_validate(client, handle); @@ -1118,8 +1119,12 @@ struct dma_buf *ion_share_dma_buf(struct ion_client *client, ion_buffer_get(buffer); mutex_unlock(&client->lock); - dmabuf = dma_buf_export(buffer, &dma_buf_ops, buffer->size, O_RDWR, - NULL); + exp_info.ops = &dma_buf_ops; + exp_info.size = buffer->size; + exp_info.flags = O_RDWR; + exp_info.priv = buffer; + + dmabuf = dma_buf_export(&exp_info); if (IS_ERR(dmabuf)) { ion_buffer_put(buffer); return dmabuf; diff --git a/drivers/staging/lustre/lustre/llite/dcache.c b/drivers/staging/lustre/lustre/llite/dcache.c index fe1fd05423e9..5af01351306d 100644 --- a/drivers/staging/lustre/lustre/llite/dcache.c +++ b/drivers/staging/lustre/lustre/llite/dcache.c @@ -153,7 +153,7 @@ static int ll_ddelete(const struct dentry *de) CDEBUG(D_DENTRY, "%s dentry %pd (%p, parent %p, inode %p) %s%s\n", d_lustre_invalid((struct dentry *)de) ? "deleting" : "keeping", - de, de, de->d_parent, de->d_inode, + de, de, de->d_parent, d_inode(de), d_unhashed(de) ? "" : "hashed,", list_empty(&de->d_subdirs) ? "" : "subdirs"); @@ -167,8 +167,8 @@ static int ll_ddelete(const struct dentry *de) #if 0 /* if not ldlm lock for this inode, set i_nlink to 0 so that * this inode can be recycled later b=20433 */ - if (de->d_inode && !find_cbdata(de->d_inode)) - clear_nlink(de->d_inode); + if (d_really_is_positive(de) && !find_cbdata(d_inode(de))) + clear_nlink(d_inode(de)); #endif if (d_lustre_invalid((struct dentry *)de)) @@ -181,7 +181,7 @@ int ll_d_init(struct dentry *de) LASSERT(de != NULL); CDEBUG(D_DENTRY, "ldd on dentry %pd (%p) parent %p inode %p refc %d\n", - de, de, de->d_parent, de->d_inode, + de, de, de->d_parent, d_inode(de), d_count(de)); if (de->d_fsdata == NULL) { @@ -261,7 +261,7 @@ void ll_invalidate_aliases(struct inode *inode) ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) { CDEBUG(D_DENTRY, "dentry in drop %pd (%p) parent %p inode %p flags %d\n", dentry, dentry, dentry->d_parent, - dentry->d_inode, dentry->d_flags); + d_inode(dentry), dentry->d_flags); d_lustre_invalidate(dentry, 0); } @@ -309,7 +309,7 @@ void ll_lookup_finish_locks(struct lookup_intent *it, struct inode *inode) static int ll_revalidate_dentry(struct dentry *dentry, unsigned int lookup_flags) { - struct inode *dir = dentry->d_parent->d_inode; + struct inode *dir = d_inode(dentry->d_parent); /* * if open&create is set, talk to MDS to make sure file is created if @@ -329,7 +329,7 @@ static int ll_revalidate_dentry(struct dentry *dentry, if (lookup_flags & LOOKUP_RCU) return -ECHILD; - do_statahead_enter(dir, &dentry, dentry->d_inode == NULL); + do_statahead_enter(dir, &dentry, d_inode(dentry) == NULL); ll_statahead_mark(dir, dentry); return 1; } diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c index 529062ea112b..4b44c634fcc3 100644 --- a/drivers/staging/lustre/lustre/llite/file.c +++ b/drivers/staging/lustre/lustre/llite/file.c @@ -388,7 +388,7 @@ int ll_file_release(struct inode *inode, struct file *file) static int ll_intent_file_open(struct dentry *dentry, void *lmm, int lmmsize, struct lookup_intent *itp) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct ll_sb_info *sbi = ll_i2sbi(inode); struct dentry *parent = dentry->d_parent; const char *name = dentry->d_name.name; @@ -413,7 +413,7 @@ static int ll_intent_file_open(struct dentry *dentry, void *lmm, opc = LUSTRE_OPC_CREATE; } - op_data = ll_prep_md_op_data(NULL, parent->d_inode, + op_data = ll_prep_md_op_data(NULL, d_inode(parent), inode, name, len, O_RDWR, opc, NULL); if (IS_ERR(op_data)) @@ -2896,7 +2896,7 @@ static int ll_inode_revalidate_fini(struct inode *inode, int rc) static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct ptlrpc_request *req = NULL; struct obd_export *exp; int rc = 0; @@ -2948,12 +2948,12 @@ static int __ll_inode_revalidate(struct dentry *dentry, __u64 ibits) do_lookup() -> ll_revalidate_it(). We cannot use d_drop here to preserve get_cwd functionality on 2.6. Bug 10503 */ - if (!dentry->d_inode->i_nlink) + if (!d_inode(dentry)->i_nlink) d_lustre_invalidate(dentry, 0); ll_lookup_finish_locks(&oit, inode); - } else if (!ll_have_md_lock(dentry->d_inode, &ibits, LCK_MINMODE)) { - struct ll_sb_info *sbi = ll_i2sbi(dentry->d_inode); + } else if (!ll_have_md_lock(d_inode(dentry), &ibits, LCK_MINMODE)) { + struct ll_sb_info *sbi = ll_i2sbi(d_inode(dentry)); u64 valid = OBD_MD_FLGETATTR; struct md_op_data *op_data; int ealen = 0; @@ -2991,7 +2991,7 @@ out: static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); int rc; rc = __ll_inode_revalidate(dentry, ibits); @@ -3019,7 +3019,7 @@ static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits) int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat) { - struct inode *inode = de->d_inode; + struct inode *inode = d_inode(de); struct ll_sb_info *sbi = ll_i2sbi(inode); struct ll_inode_info *lli = ll_i2info(inode); int res = 0; diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h index e7422f5c9c6f..5f918e3c4683 100644 --- a/drivers/staging/lustre/lustre/llite/llite_internal.h +++ b/drivers/staging/lustre/lustre/llite/llite_internal.h @@ -1488,7 +1488,7 @@ static inline void d_lustre_invalidate(struct dentry *dentry, int nested) { CDEBUG(D_DENTRY, "invalidate dentry %pd (%p) parent %p inode %p refc %d\n", dentry, dentry, - dentry->d_parent, dentry->d_inode, d_count(dentry)); + dentry->d_parent, d_inode(dentry), d_count(dentry)); spin_lock_nested(&dentry->d_lock, nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL); diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index bf1ec277a1dc..a27af7882170 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -1166,7 +1166,7 @@ static int ll_md_setattr(struct dentry *dentry, struct md_op_data *op_data, struct md_open_data **mod) { struct lustre_md md; - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct ll_sb_info *sbi = ll_i2sbi(inode); struct ptlrpc_request *request = NULL; int rc, ia_valid; @@ -1290,7 +1290,7 @@ static int ll_setattr_ost(struct inode *inode, struct iattr *attr) */ int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct ll_inode_info *lli = ll_i2info(inode); struct md_op_data *op_data = NULL; struct md_open_data *mod = NULL; @@ -1465,7 +1465,7 @@ out: int ll_setattr(struct dentry *de, struct iattr *attr) { - int mode = de->d_inode->i_mode; + int mode = d_inode(de)->i_mode; if ((attr->ia_valid & (ATTR_CTIME|ATTR_SIZE|ATTR_MODE)) == (ATTR_CTIME|ATTR_SIZE|ATTR_MODE)) diff --git a/drivers/staging/lustre/lustre/llite/llite_nfs.c b/drivers/staging/lustre/lustre/llite/llite_nfs.c index 243a7840457f..db43b81386f7 100644 --- a/drivers/staging/lustre/lustre/llite/llite_nfs.c +++ b/drivers/staging/lustre/lustre/llite/llite_nfs.c @@ -230,11 +230,11 @@ static int ll_nfs_get_name_filldir(struct dir_context *ctx, const char *name, static int ll_get_name(struct dentry *dentry, char *name, struct dentry *child) { - struct inode *dir = dentry->d_inode; + struct inode *dir = d_inode(dentry); int rc; struct ll_getname_data lgd = { .lgd_name = name, - .lgd_fid = ll_i2info(child->d_inode)->lli_fid, + .lgd_fid = ll_i2info(d_inode(child))->lli_fid, .ctx.actor = ll_nfs_get_name_filldir, }; @@ -282,7 +282,7 @@ static struct dentry *ll_fh_to_parent(struct super_block *sb, struct fid *fid, static struct dentry *ll_get_parent(struct dentry *dchild) { struct ptlrpc_request *req = NULL; - struct inode *dir = dchild->d_inode; + struct inode *dir = d_inode(dchild); struct ll_sb_info *sbi; struct dentry *result = NULL; struct mdt_body *body; diff --git a/drivers/staging/lustre/lustre/llite/namei.c b/drivers/staging/lustre/lustre/llite/namei.c index 49f1cb067ea2..5a25dcd10126 100644 --- a/drivers/staging/lustre/lustre/llite/namei.c +++ b/drivers/staging/lustre/lustre/llite/namei.c @@ -155,7 +155,7 @@ static void ll_invalidate_negative_children(struct inode *dir) list_for_each_entry_safe(child, tmp_subdir, &dentry->d_subdirs, d_child) { - if (child->d_inode == NULL) + if (d_really_is_negative(child)) d_lustre_invalidate(child, 1); } } @@ -392,7 +392,7 @@ struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de) iput(inode); CDEBUG(D_DENTRY, "Reuse dentry %p inode %p refc %d flags %#x\n", - new, new->d_inode, d_count(new), new->d_flags); + new, d_inode(new), d_count(new), new->d_flags); return new; } } @@ -401,7 +401,7 @@ struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de) return ERR_PTR(rc); d_add(de, inode); CDEBUG(D_DENTRY, "Add dentry %p inode %p refc %d flags %#x\n", - de, de->d_inode, d_count(de), de->d_flags); + de, d_inode(de), d_count(de), de->d_flags); return de; } @@ -448,7 +448,7 @@ static int ll_lookup_it_finish(struct ptlrpc_request *request, !it_disposition(it, DISP_OPEN_CREATE)) { /* With DISP_OPEN_CREATE dentry will instantiated in ll_create_it. */ - LASSERT((*de)->d_inode == NULL); + LASSERT(d_inode(*de) == NULL); d_instantiate(*de, inode); } @@ -541,7 +541,7 @@ static struct dentry *ll_lookup_it(struct inode *parent, struct dentry *dentry, goto out; } - inode = dentry->d_inode; + inode = d_inode(dentry); if ((it->it_op & IT_OPEN) && inode && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) { @@ -638,9 +638,9 @@ static int ll_atomic_open(struct inode *dir, struct dentry *dentry, *opened |= FILE_CREATED; } - if (dentry->d_inode && it_disposition(it, DISP_OPEN_OPEN)) { + if (d_really_is_positive(dentry) && it_disposition(it, DISP_OPEN_OPEN)) { /* Open dentry. */ - if (S_ISFIFO(dentry->d_inode->i_mode)) { + if (S_ISFIFO(d_inode(dentry)->i_mode)) { /* We cannot call open here as it would * deadlock. */ @@ -862,8 +862,8 @@ static int ll_create_nd(struct inode *dir, struct dentry *dentry, static inline void ll_get_child_fid(struct dentry *child, struct lu_fid *fid) { - if (child->d_inode) - *fid = *ll_inode2fid(child->d_inode); + if (d_really_is_positive(child)) + *fid = *ll_inode2fid(d_inode(child)); } /** @@ -1076,7 +1076,7 @@ static int ll_symlink(struct inode *dir, struct dentry *dentry, static int ll_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { - struct inode *src = old_dentry->d_inode; + struct inode *src = d_inode(old_dentry); struct ll_sb_info *sbi = ll_i2sbi(dir); struct ptlrpc_request *request = NULL; struct md_op_data *op_data; diff --git a/drivers/staging/lustre/lustre/llite/statahead.c b/drivers/staging/lustre/lustre/llite/statahead.c index b75562c6b5de..7f8071242f23 100644 --- a/drivers/staging/lustre/lustre/llite/statahead.c +++ b/drivers/staging/lustre/lustre/llite/statahead.c @@ -880,7 +880,7 @@ static int do_sa_lookup(struct inode *dir, struct ll_sa_entry *entry) static int do_sa_revalidate(struct inode *dir, struct ll_sa_entry *entry, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct lookup_intent it = { .it_op = IT_GETATTR, .d.lustre.it_lock_handle = 0 }; struct md_enqueue_info *minfo; @@ -926,7 +926,7 @@ static int do_sa_revalidate(struct inode *dir, struct ll_sa_entry *entry, static void ll_statahead_one(struct dentry *parent, const char *entry_name, int entry_name_len) { - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); struct ll_inode_info *lli = ll_i2info(dir); struct ll_statahead_info *sai = lli->lli_sai; struct dentry *dentry = NULL; @@ -944,8 +944,8 @@ static void ll_statahead_one(struct dentry *parent, const char *entry_name, rc = do_sa_lookup(dir, entry); } else { rc = do_sa_revalidate(dir, entry, dentry); - if (rc == 1 && agl_should_run(sai, dentry->d_inode)) - ll_agl_add(sai, dentry->d_inode, entry->se_index); + if (rc == 1 && agl_should_run(sai, d_inode(dentry))) + ll_agl_add(sai, d_inode(dentry), entry->se_index); } if (dentry != NULL) @@ -968,7 +968,7 @@ static void ll_statahead_one(struct dentry *parent, const char *entry_name, static int ll_agl_thread(void *arg) { struct dentry *parent = (struct dentry *)arg; - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); struct ll_inode_info *plli = ll_i2info(dir); struct ll_inode_info *clli; struct ll_sb_info *sbi = ll_i2sbi(dir); @@ -1042,7 +1042,7 @@ static void ll_start_agl(struct dentry *parent, struct ll_statahead_info *sai) CDEBUG(D_READA, "start agl thread: sai %p, parent %pd\n", sai, parent); - plli = ll_i2info(parent->d_inode); + plli = ll_i2info(d_inode(parent)); task = kthread_run(ll_agl_thread, parent, "ll_agl_%u", plli->lli_opendir_pid); if (IS_ERR(task)) { @@ -1059,7 +1059,7 @@ static void ll_start_agl(struct dentry *parent, struct ll_statahead_info *sai) static int ll_statahead_thread(void *arg) { struct dentry *parent = (struct dentry *)arg; - struct inode *dir = parent->d_inode; + struct inode *dir = d_inode(parent); struct ll_inode_info *plli = ll_i2info(dir); struct ll_inode_info *clli; struct ll_sb_info *sbi = ll_i2sbi(dir); @@ -1604,7 +1604,7 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, rc = md_revalidate_lock(ll_i2mdexp(dir), &it, ll_inode2fid(inode), &bits); if (rc == 1) { - if ((*dentryp)->d_inode == NULL) { + if (d_inode(*dentryp) == NULL) { struct dentry *alias; alias = ll_splice_alias(inode, @@ -1614,13 +1614,13 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, return PTR_ERR(alias); } *dentryp = alias; - } else if ((*dentryp)->d_inode != inode) { + } else if (d_inode(*dentryp) != inode) { /* revalidate, but inode is recreated */ CDEBUG(D_READA, "stale dentry %pd inode %lu/%u, statahead inode %lu/%u\n", *dentryp, - (*dentryp)->d_inode->i_ino, - (*dentryp)->d_inode->i_generation, + d_inode(*dentryp)->i_ino, + d_inode(*dentryp)->i_generation, inode->i_ino, inode->i_generation); ll_sai_unplug(sai, entry); @@ -1666,8 +1666,8 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, /* get parent reference count here, and put it in ll_statahead_thread */ parent = dget((*dentryp)->d_parent); - if (unlikely(sai->sai_inode != parent->d_inode)) { - struct ll_inode_info *nlli = ll_i2info(parent->d_inode); + if (unlikely(sai->sai_inode != d_inode(parent))) { + struct ll_inode_info *nlli = ll_i2info(d_inode(parent)); CWARN("Race condition, someone changed %pd just now: old parent "DFID", new parent "DFID"\n", *dentryp, @@ -1689,7 +1689,7 @@ int do_statahead_enter(struct inode *dir, struct dentry **dentryp, ll_sai_get(sai); lli->lli_sai = sai; - plli = ll_i2info(parent->d_inode); + plli = ll_i2info(d_inode(parent)); rc = PTR_ERR(kthread_run(ll_statahead_thread, parent, "ll_sa_%u", plli->lli_opendir_pid)); thread = &sai->sai_thread; diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c index 686b6a574cc5..3711e671a4df 100644 --- a/drivers/staging/lustre/lustre/llite/symlink.c +++ b/drivers/staging/lustre/lustre/llite/symlink.c @@ -120,7 +120,7 @@ failed: static void *ll_follow_link(struct dentry *dentry, struct nameidata *nd) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct ptlrpc_request *request = NULL; int rc; char *symname = NULL; diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c index b439936b4524..e0fcbe1395fd 100644 --- a/drivers/staging/lustre/lustre/llite/xattr.c +++ b/drivers/staging/lustre/lustre/llite/xattr.c @@ -214,7 +214,7 @@ int ll_setxattr_common(struct inode *inode, const char *name, int ll_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); LASSERT(inode); LASSERT(name); @@ -267,7 +267,7 @@ int ll_setxattr(struct dentry *dentry, const char *name, int ll_removexattr(struct dentry *dentry, const char *name) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); LASSERT(inode); LASSERT(name); @@ -457,7 +457,7 @@ out: ssize_t ll_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); LASSERT(inode); LASSERT(name); @@ -545,7 +545,7 @@ out: ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); int rc = 0, rc2 = 0; struct lov_mds_md *lmm = NULL; struct ptlrpc_request *request = NULL; diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig index 81d44c477a5b..257361280510 100644 --- a/drivers/target/Kconfig +++ b/drivers/target/Kconfig @@ -31,12 +31,13 @@ config TCM_PSCSI Say Y here to enable the TCM/pSCSI subsystem plugin for non-buffered passthrough access to Linux/SCSI device -config TCM_USER +config TCM_USER2 tristate "TCM/USER Subsystem Plugin for Linux" depends on UIO && NET help Say Y here to enable the TCM/USER subsystem plugin for a userspace - process to handle requests + process to handle requests. This is version 2 of the ABI; version 1 + is obsolete. source "drivers/target/loopback/Kconfig" source "drivers/target/tcm_fc/Kconfig" diff --git a/drivers/target/Makefile b/drivers/target/Makefile index bbb4a7d638ef..e619c0266a79 100644 --- a/drivers/target/Makefile +++ b/drivers/target/Makefile @@ -22,7 +22,7 @@ obj-$(CONFIG_TARGET_CORE) += target_core_mod.o obj-$(CONFIG_TCM_IBLOCK) += target_core_iblock.o obj-$(CONFIG_TCM_FILEIO) += target_core_file.o obj-$(CONFIG_TCM_PSCSI) += target_core_pscsi.o -obj-$(CONFIG_TCM_USER) += target_core_user.o +obj-$(CONFIG_TCM_USER2) += target_core_user.o # Fabric modules obj-$(CONFIG_LOOPBACK_TARGET) += loopback/ diff --git a/drivers/target/iscsi/Makefile b/drivers/target/iscsi/Makefile index 13a92403fe3e..0f43be9c3453 100644 --- a/drivers/target/iscsi/Makefile +++ b/drivers/target/iscsi/Makefile @@ -1,6 +1,5 @@ iscsi_target_mod-y += iscsi_target_parameters.o \ iscsi_target_seq_pdu_list.o \ - iscsi_target_tq.o \ iscsi_target_auth.o \ iscsi_target_datain_values.o \ iscsi_target_device.o \ diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 77d64251af40..34871a628b11 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -33,8 +33,6 @@ #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_parameters.h" #include "iscsi_target_seq_pdu_list.h" -#include "iscsi_target_tq.h" -#include "iscsi_target_configfs.h" #include "iscsi_target_datain_values.h" #include "iscsi_target_erl0.h" #include "iscsi_target_erl1.h" @@ -537,7 +535,7 @@ static struct iscsit_transport iscsi_target_transport = { static int __init iscsi_target_init_module(void) { - int ret = 0; + int ret = 0, size; pr_debug("iSCSI-Target "ISCSIT_VERSION"\n"); @@ -546,24 +544,21 @@ static int __init iscsi_target_init_module(void) pr_err("Unable to allocate memory for iscsit_global\n"); return -1; } + spin_lock_init(&iscsit_global->ts_bitmap_lock); mutex_init(&auth_id_lock); spin_lock_init(&sess_idr_lock); idr_init(&tiqn_idr); idr_init(&sess_idr); - ret = iscsi_target_register_configfs(); - if (ret < 0) + ret = target_register_template(&iscsi_ops); + if (ret) goto out; - ret = iscsi_thread_set_init(); - if (ret < 0) + size = BITS_TO_LONGS(ISCSIT_BITMAP_BITS) * sizeof(long); + iscsit_global->ts_bitmap = vzalloc(size); + if (!iscsit_global->ts_bitmap) { + pr_err("Unable to allocate iscsit_global->ts_bitmap\n"); goto configfs_out; - - if (iscsi_allocate_thread_sets(TARGET_THREAD_SET_COUNT) != - TARGET_THREAD_SET_COUNT) { - pr_err("iscsi_allocate_thread_sets() returned" - " unexpected value!\n"); - goto ts_out1; } lio_qr_cache = kmem_cache_create("lio_qr_cache", @@ -572,7 +567,7 @@ static int __init iscsi_target_init_module(void) if (!lio_qr_cache) { pr_err("nable to kmem_cache_create() for" " lio_qr_cache\n"); - goto ts_out2; + goto bitmap_out; } lio_dr_cache = kmem_cache_create("lio_dr_cache", @@ -617,12 +612,13 @@ dr_out: kmem_cache_destroy(lio_dr_cache); qr_out: kmem_cache_destroy(lio_qr_cache); -ts_out2: - iscsi_deallocate_thread_sets(); -ts_out1: - iscsi_thread_set_free(); +bitmap_out: + vfree(iscsit_global->ts_bitmap); configfs_out: - iscsi_target_deregister_configfs(); + /* XXX: this probably wants it to be it's own unwind step.. */ + if (iscsit_global->discovery_tpg) + iscsit_tpg_disable_portal_group(iscsit_global->discovery_tpg, 1); + target_unregister_template(&iscsi_ops); out: kfree(iscsit_global); return -ENOMEM; @@ -630,8 +626,6 @@ out: static void __exit iscsi_target_cleanup_module(void) { - iscsi_deallocate_thread_sets(); - iscsi_thread_set_free(); iscsit_release_discovery_tpg(); iscsit_unregister_transport(&iscsi_target_transport); kmem_cache_destroy(lio_qr_cache); @@ -639,8 +633,15 @@ static void __exit iscsi_target_cleanup_module(void) kmem_cache_destroy(lio_ooo_cache); kmem_cache_destroy(lio_r2t_cache); - iscsi_target_deregister_configfs(); + /* + * Shutdown discovery sessions and disable discovery TPG + */ + if (iscsit_global->discovery_tpg) + iscsit_tpg_disable_portal_group(iscsit_global->discovery_tpg, 1); + target_unregister_template(&iscsi_ops); + + vfree(iscsit_global->ts_bitmap); kfree(iscsit_global); } @@ -990,7 +991,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, /* * Initialize struct se_cmd descriptor from target_core_mod infrastructure */ - transport_init_se_cmd(&cmd->se_cmd, &lio_target_fabric_configfs->tf_ops, + transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops, conn->sess->se_sess, be32_to_cpu(hdr->data_length), cmd->data_direction, sam_task_attr, cmd->sense_buffer + 2); @@ -1805,8 +1806,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, u8 tcm_function; int ret; - transport_init_se_cmd(&cmd->se_cmd, - &lio_target_fabric_configfs->tf_ops, + transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); @@ -2155,7 +2155,6 @@ reject: cmd->text_in_ptr = NULL; return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf); } -EXPORT_SYMBOL(iscsit_handle_text_cmd); int iscsit_logout_closesession(struct iscsi_cmd *cmd, struct iscsi_conn *conn) { @@ -3715,17 +3714,16 @@ static int iscsit_send_reject( void iscsit_thread_get_cpumask(struct iscsi_conn *conn) { - struct iscsi_thread_set *ts = conn->thread_set; int ord, cpu; /* - * thread_id is assigned from iscsit_global->ts_bitmap from - * within iscsi_thread_set.c:iscsi_allocate_thread_sets() + * bitmap_id is assigned from iscsit_global->ts_bitmap from + * within iscsit_start_kthreads() * - * Here we use thread_id to determine which CPU that this - * iSCSI connection's iscsi_thread_set will be scheduled to + * Here we use bitmap_id to determine which CPU that this + * iSCSI connection's RX/TX threads will be scheduled to * execute upon. */ - ord = ts->thread_id % cpumask_weight(cpu_online_mask); + ord = conn->bitmap_id % cpumask_weight(cpu_online_mask); for_each_online_cpu(cpu) { if (ord-- == 0) { cpumask_set_cpu(cpu, conn->conn_cpumask); @@ -3914,7 +3912,7 @@ check_rsp_state: switch (state) { case ISTATE_SEND_LOGOUTRSP: if (!iscsit_logout_post_handler(cmd, conn)) - goto restart; + return -ECONNRESET; /* fall through */ case ISTATE_SEND_STATUS: case ISTATE_SEND_ASYNCMSG: @@ -3942,8 +3940,6 @@ check_rsp_state: err: return -1; -restart: - return -EAGAIN; } static int iscsit_handle_response_queue(struct iscsi_conn *conn) @@ -3970,21 +3966,13 @@ static int iscsit_handle_response_queue(struct iscsi_conn *conn) int iscsi_target_tx_thread(void *arg) { int ret = 0; - struct iscsi_conn *conn; - struct iscsi_thread_set *ts = arg; + struct iscsi_conn *conn = arg; /* * Allow ourselves to be interrupted by SIGINT so that a * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); -restart: - conn = iscsi_tx_thread_pre_handler(ts); - if (!conn) - goto out; - - ret = 0; - while (!kthread_should_stop()) { /* * Ensure that both TX and RX per connection kthreads @@ -3993,11 +3981,9 @@ restart: iscsit_thread_check_cpumask(conn, current, 1); wait_event_interruptible(conn->queues_wq, - !iscsit_conn_all_queues_empty(conn) || - ts->status == ISCSI_THREAD_SET_RESET); + !iscsit_conn_all_queues_empty(conn)); - if ((ts->status == ISCSI_THREAD_SET_RESET) || - signal_pending(current)) + if (signal_pending(current)) goto transport_err; get_immediate: @@ -4008,15 +3994,14 @@ get_immediate: ret = iscsit_handle_response_queue(conn); if (ret == 1) goto get_immediate; - else if (ret == -EAGAIN) - goto restart; + else if (ret == -ECONNRESET) + goto out; else if (ret < 0) goto transport_err; } transport_err: iscsit_take_action_for_connection_exit(conn); - goto restart; out: return 0; } @@ -4111,8 +4096,7 @@ int iscsi_target_rx_thread(void *arg) int ret; u8 buffer[ISCSI_HDR_LEN], opcode; u32 checksum = 0, digest = 0; - struct iscsi_conn *conn = NULL; - struct iscsi_thread_set *ts = arg; + struct iscsi_conn *conn = arg; struct kvec iov; /* * Allow ourselves to be interrupted by SIGINT so that a @@ -4120,11 +4104,6 @@ int iscsi_target_rx_thread(void *arg) */ allow_signal(SIGINT); -restart: - conn = iscsi_rx_thread_pre_handler(ts); - if (!conn) - goto out; - if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) { struct completion comp; int rc; @@ -4134,7 +4113,7 @@ restart: if (rc < 0) goto transport_err; - goto out; + goto transport_err; } while (!kthread_should_stop()) { @@ -4210,8 +4189,6 @@ transport_err: if (!signal_pending(current)) atomic_set(&conn->transport_failed, 1); iscsit_take_action_for_connection_exit(conn); - goto restart; -out: return 0; } @@ -4273,7 +4250,24 @@ int iscsit_close_connection( if (conn->conn_transport->transport_type == ISCSI_TCP) complete(&conn->conn_logout_comp); - iscsi_release_thread_set(conn); + if (!strcmp(current->comm, ISCSI_RX_THREAD_NAME)) { + if (conn->tx_thread && + cmpxchg(&conn->tx_thread_active, true, false)) { + send_sig(SIGINT, conn->tx_thread, 1); + kthread_stop(conn->tx_thread); + } + } else if (!strcmp(current->comm, ISCSI_TX_THREAD_NAME)) { + if (conn->rx_thread && + cmpxchg(&conn->rx_thread_active, true, false)) { + send_sig(SIGINT, conn->rx_thread, 1); + kthread_stop(conn->rx_thread); + } + } + + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); iscsit_stop_timers_for_cmds(conn); iscsit_stop_nopin_response_timer(conn); @@ -4383,8 +4377,6 @@ int iscsit_close_connection( iscsit_put_transport(conn->conn_transport); - conn->thread_set = NULL; - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); conn->conn_state = TARG_CONN_STATE_FREE; kfree(conn); @@ -4551,15 +4543,13 @@ static void iscsit_logout_post_handler_closesession( struct iscsi_conn *conn) { struct iscsi_session *sess = conn->sess; - - iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); - iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); + int sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); iscsit_dec_conn_usage_count(conn); - iscsit_stop_session(sess, 1, 1); + iscsit_stop_session(sess, sleep, sleep); iscsit_dec_session_usage_count(sess); target_put_session(sess->se_sess); } @@ -4567,13 +4557,12 @@ static void iscsit_logout_post_handler_closesession( static void iscsit_logout_post_handler_samecid( struct iscsi_conn *conn) { - iscsi_set_thread_clear(conn, ISCSI_CLEAR_TX_THREAD); - iscsi_set_thread_set_signal(conn, ISCSI_SIGNAL_TX_THREAD); + int sleep = cmpxchg(&conn->tx_thread_active, true, false); atomic_set(&conn->conn_logout_remove, 0); complete(&conn->conn_logout_comp); - iscsit_cause_connection_reinstatement(conn, 1); + iscsit_cause_connection_reinstatement(conn, sleep); iscsit_dec_conn_usage_count(conn); } diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h index e936d56fb523..7d0f9c00d9c2 100644 --- a/drivers/target/iscsi/iscsi_target.h +++ b/drivers/target/iscsi/iscsi_target.h @@ -35,7 +35,7 @@ extern void iscsit_stop_session(struct iscsi_session *, int, int); extern int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *, int); extern struct iscsit_global *iscsit_global; -extern struct target_fabric_configfs *lio_target_fabric_configfs; +extern const struct target_core_fabric_ops iscsi_ops; extern struct kmem_cache *lio_dr_cache; extern struct kmem_cache *lio_ooo_cache; diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 48384b675e62..469fce44ebad 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -37,9 +37,6 @@ #include "iscsi_target_util.h" #include "iscsi_target.h" #include <target/iscsi/iscsi_target_stat.h> -#include "iscsi_target_configfs.h" - -struct target_fabric_configfs *lio_target_fabric_configfs; struct lio_target_configfs_attribute { struct configfs_attribute attr; @@ -1052,6 +1049,11 @@ TPG_ATTR(default_erl, S_IRUGO | S_IWUSR); */ DEF_TPG_ATTRIB(t10_pi); TPG_ATTR(t10_pi, S_IRUGO | S_IWUSR); +/* + * Define iscsi_tpg_attrib_s_fabric_prot_type + */ +DEF_TPG_ATTRIB(fabric_prot_type); +TPG_ATTR(fabric_prot_type, S_IRUGO | S_IWUSR); static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_authentication.attr, @@ -1065,6 +1067,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_demo_mode_discovery.attr, &iscsi_tpg_attrib_default_erl.attr, &iscsi_tpg_attrib_t10_pi.attr, + &iscsi_tpg_attrib_fabric_prot_type.attr, NULL, }; @@ -1410,8 +1413,18 @@ out: TF_TPG_BASE_ATTR(lio_target, enable, S_IRUGO | S_IWUSR); +static ssize_t lio_target_tpg_show_dynamic_sessions( + struct se_portal_group *se_tpg, + char *page) +{ + return target_show_dynamic_sessions(se_tpg, page); +} + +TF_TPG_BASE_ATTR_RO(lio_target, dynamic_sessions); + static struct configfs_attribute *lio_target_tpg_attrs[] = { &lio_target_tpg_enable.attr, + &lio_target_tpg_dynamic_sessions.attr, NULL, }; @@ -1450,10 +1463,8 @@ static struct se_portal_group *lio_target_tiqn_addtpg( if (!tpg) return NULL; - ret = core_tpg_register( - &lio_target_fabric_configfs->tf_ops, - wwn, &tpg->tpg_se_tpg, tpg, - TRANSPORT_TPG_TYPE_NORMAL); + ret = core_tpg_register(&iscsi_ops, wwn, &tpg->tpg_se_tpg, + tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) return NULL; @@ -1872,6 +1883,20 @@ static int lio_tpg_check_prod_mode_write_protect( return tpg->tpg_attrib.prod_mode_write_protect; } +static int lio_tpg_check_prot_fabric_only( + struct se_portal_group *se_tpg) +{ + struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr; + /* + * Only report fabric_prot_type if t10_pi has also been enabled + * for incoming ib_isert sessions. + */ + if (!tpg->tpg_attrib.t10_pi) + return 0; + + return tpg->tpg_attrib.fabric_prot_type; +} + static void lio_tpg_release_fabric_acl( struct se_portal_group *se_tpg, struct se_node_acl *se_acl) @@ -1953,115 +1978,60 @@ static void lio_release_cmd(struct se_cmd *se_cmd) iscsit_release_cmd(cmd); } -/* End functions for target_core_fabric_ops */ - -int iscsi_target_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - - lio_target_fabric_configfs = NULL; - fabric = target_fabric_configfs_init(THIS_MODULE, "iscsi"); - if (IS_ERR(fabric)) { - pr_err("target_fabric_configfs_init() for" - " LIO-Target failed!\n"); - return PTR_ERR(fabric); - } - /* - * Setup the fabric API of function pointers used by target_core_mod.. - */ - fabric->tf_ops.get_fabric_name = &iscsi_get_fabric_name; - fabric->tf_ops.get_fabric_proto_ident = &iscsi_get_fabric_proto_ident; - fabric->tf_ops.tpg_get_wwn = &lio_tpg_get_endpoint_wwn; - fabric->tf_ops.tpg_get_tag = &lio_tpg_get_tag; - fabric->tf_ops.tpg_get_default_depth = &lio_tpg_get_default_depth; - fabric->tf_ops.tpg_get_pr_transport_id = &iscsi_get_pr_transport_id; - fabric->tf_ops.tpg_get_pr_transport_id_len = - &iscsi_get_pr_transport_id_len; - fabric->tf_ops.tpg_parse_pr_out_transport_id = - &iscsi_parse_pr_out_transport_id; - fabric->tf_ops.tpg_check_demo_mode = &lio_tpg_check_demo_mode; - fabric->tf_ops.tpg_check_demo_mode_cache = - &lio_tpg_check_demo_mode_cache; - fabric->tf_ops.tpg_check_demo_mode_write_protect = - &lio_tpg_check_demo_mode_write_protect; - fabric->tf_ops.tpg_check_prod_mode_write_protect = - &lio_tpg_check_prod_mode_write_protect; - fabric->tf_ops.tpg_alloc_fabric_acl = &lio_tpg_alloc_fabric_acl; - fabric->tf_ops.tpg_release_fabric_acl = &lio_tpg_release_fabric_acl; - fabric->tf_ops.tpg_get_inst_index = &lio_tpg_get_inst_index; - fabric->tf_ops.check_stop_free = &lio_check_stop_free, - fabric->tf_ops.release_cmd = &lio_release_cmd; - fabric->tf_ops.shutdown_session = &lio_tpg_shutdown_session; - fabric->tf_ops.close_session = &lio_tpg_close_session; - fabric->tf_ops.sess_get_index = &lio_sess_get_index; - fabric->tf_ops.sess_get_initiator_sid = &lio_sess_get_initiator_sid; - fabric->tf_ops.write_pending = &lio_write_pending; - fabric->tf_ops.write_pending_status = &lio_write_pending_status; - fabric->tf_ops.set_default_node_attributes = - &lio_set_default_node_attributes; - fabric->tf_ops.get_task_tag = &iscsi_get_task_tag; - fabric->tf_ops.get_cmd_state = &iscsi_get_cmd_state; - fabric->tf_ops.queue_data_in = &lio_queue_data_in; - fabric->tf_ops.queue_status = &lio_queue_status; - fabric->tf_ops.queue_tm_rsp = &lio_queue_tm_rsp; - fabric->tf_ops.aborted_task = &lio_aborted_task; - /* - * Setup function pointers for generic logic in target_core_fabric_configfs.c - */ - fabric->tf_ops.fabric_make_wwn = &lio_target_call_coreaddtiqn; - fabric->tf_ops.fabric_drop_wwn = &lio_target_call_coredeltiqn; - fabric->tf_ops.fabric_make_tpg = &lio_target_tiqn_addtpg; - fabric->tf_ops.fabric_drop_tpg = &lio_target_tiqn_deltpg; - fabric->tf_ops.fabric_post_link = NULL; - fabric->tf_ops.fabric_pre_unlink = NULL; - fabric->tf_ops.fabric_make_np = &lio_target_call_addnptotpg; - fabric->tf_ops.fabric_drop_np = &lio_target_call_delnpfromtpg; - fabric->tf_ops.fabric_make_nodeacl = &lio_target_make_nodeacl; - fabric->tf_ops.fabric_drop_nodeacl = &lio_target_drop_nodeacl; - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - * sturct config_item_type's - */ - fabric->tf_cit_tmpl.tfc_discovery_cit.ct_attrs = lio_target_discovery_auth_attrs; - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = lio_target_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = lio_target_tpg_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = lio_target_tpg_attrib_attrs; - fabric->tf_cit_tmpl.tfc_tpg_auth_cit.ct_attrs = lio_target_tpg_auth_attrs; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = lio_target_tpg_param_attrs; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = lio_target_portal_attrs; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = lio_target_initiator_attrs; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = lio_target_nacl_attrib_attrs; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = lio_target_nacl_auth_attrs; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = lio_target_nacl_param_attrs; - - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() for" - " LIO-Target failed!\n"); - target_fabric_configfs_free(fabric); - return ret; - } - - lio_target_fabric_configfs = fabric; - pr_debug("LIO_TARGET[0] - Set fabric ->" - " lio_target_fabric_configfs\n"); - return 0; -} - - -void iscsi_target_deregister_configfs(void) -{ - if (!lio_target_fabric_configfs) - return; - /* - * Shutdown discovery sessions and disable discovery TPG - */ - if (iscsit_global->discovery_tpg) - iscsit_tpg_disable_portal_group(iscsit_global->discovery_tpg, 1); - - target_fabric_configfs_deregister(lio_target_fabric_configfs); - lio_target_fabric_configfs = NULL; - pr_debug("LIO_TARGET[0] - Cleared" - " lio_target_fabric_configfs\n"); -} +const struct target_core_fabric_ops iscsi_ops = { + .module = THIS_MODULE, + .name = "iscsi", + .get_fabric_name = iscsi_get_fabric_name, + .get_fabric_proto_ident = iscsi_get_fabric_proto_ident, + .tpg_get_wwn = lio_tpg_get_endpoint_wwn, + .tpg_get_tag = lio_tpg_get_tag, + .tpg_get_default_depth = lio_tpg_get_default_depth, + .tpg_get_pr_transport_id = iscsi_get_pr_transport_id, + .tpg_get_pr_transport_id_len = iscsi_get_pr_transport_id_len, + .tpg_parse_pr_out_transport_id = iscsi_parse_pr_out_transport_id, + .tpg_check_demo_mode = lio_tpg_check_demo_mode, + .tpg_check_demo_mode_cache = lio_tpg_check_demo_mode_cache, + .tpg_check_demo_mode_write_protect = + lio_tpg_check_demo_mode_write_protect, + .tpg_check_prod_mode_write_protect = + lio_tpg_check_prod_mode_write_protect, + .tpg_check_prot_fabric_only = &lio_tpg_check_prot_fabric_only, + .tpg_alloc_fabric_acl = lio_tpg_alloc_fabric_acl, + .tpg_release_fabric_acl = lio_tpg_release_fabric_acl, + .tpg_get_inst_index = lio_tpg_get_inst_index, + .check_stop_free = lio_check_stop_free, + .release_cmd = lio_release_cmd, + .shutdown_session = lio_tpg_shutdown_session, + .close_session = lio_tpg_close_session, + .sess_get_index = lio_sess_get_index, + .sess_get_initiator_sid = lio_sess_get_initiator_sid, + .write_pending = lio_write_pending, + .write_pending_status = lio_write_pending_status, + .set_default_node_attributes = lio_set_default_node_attributes, + .get_task_tag = iscsi_get_task_tag, + .get_cmd_state = iscsi_get_cmd_state, + .queue_data_in = lio_queue_data_in, + .queue_status = lio_queue_status, + .queue_tm_rsp = lio_queue_tm_rsp, + .aborted_task = lio_aborted_task, + .fabric_make_wwn = lio_target_call_coreaddtiqn, + .fabric_drop_wwn = lio_target_call_coredeltiqn, + .fabric_make_tpg = lio_target_tiqn_addtpg, + .fabric_drop_tpg = lio_target_tiqn_deltpg, + .fabric_make_np = lio_target_call_addnptotpg, + .fabric_drop_np = lio_target_call_delnpfromtpg, + .fabric_make_nodeacl = lio_target_make_nodeacl, + .fabric_drop_nodeacl = lio_target_drop_nodeacl, + + .tfc_discovery_attrs = lio_target_discovery_auth_attrs, + .tfc_wwn_attrs = lio_target_wwn_attrs, + .tfc_tpg_base_attrs = lio_target_tpg_attrs, + .tfc_tpg_attrib_attrs = lio_target_tpg_attrib_attrs, + .tfc_tpg_auth_attrs = lio_target_tpg_auth_attrs, + .tfc_tpg_param_attrs = lio_target_tpg_param_attrs, + .tfc_tpg_np_base_attrs = lio_target_portal_attrs, + .tfc_tpg_nacl_base_attrs = lio_target_initiator_attrs, + .tfc_tpg_nacl_attrib_attrs = lio_target_nacl_attrib_attrs, + .tfc_tpg_nacl_auth_attrs = lio_target_nacl_auth_attrs, + .tfc_tpg_nacl_param_attrs = lio_target_nacl_param_attrs, +}; diff --git a/drivers/target/iscsi/iscsi_target_configfs.h b/drivers/target/iscsi/iscsi_target_configfs.h deleted file mode 100644 index 8cd5a63c4edc..000000000000 --- a/drivers/target/iscsi/iscsi_target_configfs.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef ISCSI_TARGET_CONFIGFS_H -#define ISCSI_TARGET_CONFIGFS_H - -extern int iscsi_target_register_configfs(void); -extern void iscsi_target_deregister_configfs(void); - -#endif /* ISCSI_TARGET_CONFIGFS_H */ diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c index bdd8731a4daa..959a14c9dd5d 100644 --- a/drivers/target/iscsi/iscsi_target_erl0.c +++ b/drivers/target/iscsi/iscsi_target_erl0.c @@ -23,7 +23,6 @@ #include <target/iscsi/iscsi_target_core.h> #include "iscsi_target_seq_pdu_list.h" -#include "iscsi_target_tq.h" #include "iscsi_target_erl0.h" #include "iscsi_target_erl1.h" #include "iscsi_target_erl2.h" @@ -860,7 +859,10 @@ void iscsit_connection_reinstatement_rcfr(struct iscsi_conn *conn) } spin_unlock_bh(&conn->state_lock); - iscsi_thread_set_force_reinstatement(conn); + if (conn->tx_thread && conn->tx_thread_active) + send_sig(SIGINT, conn->tx_thread, 1); + if (conn->rx_thread && conn->rx_thread_active) + send_sig(SIGINT, conn->rx_thread, 1); sleep: wait_for_completion(&conn->conn_wait_rcfr_comp); @@ -885,10 +887,10 @@ void iscsit_cause_connection_reinstatement(struct iscsi_conn *conn, int sleep) return; } - if (iscsi_thread_set_force_reinstatement(conn) < 0) { - spin_unlock_bh(&conn->state_lock); - return; - } + if (conn->tx_thread && conn->tx_thread_active) + send_sig(SIGINT, conn->tx_thread, 1); + if (conn->rx_thread && conn->rx_thread_active) + send_sig(SIGINT, conn->rx_thread, 1); atomic_set(&conn->connection_reinstatement, 1); if (!sleep) { diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 153fb66ac1b8..8ce94ff744e6 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -26,7 +26,6 @@ #include <target/iscsi/iscsi_target_core.h> #include <target/iscsi/iscsi_target_stat.h> -#include "iscsi_target_tq.h" #include "iscsi_target_device.h" #include "iscsi_target_nego.h" #include "iscsi_target_erl0.h" @@ -699,6 +698,51 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn) iscsit_start_nopin_timer(conn); } +static int iscsit_start_kthreads(struct iscsi_conn *conn) +{ + int ret = 0; + + spin_lock(&iscsit_global->ts_bitmap_lock); + conn->bitmap_id = bitmap_find_free_region(iscsit_global->ts_bitmap, + ISCSIT_BITMAP_BITS, get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + + if (conn->bitmap_id < 0) { + pr_err("bitmap_find_free_region() failed for" + " iscsit_start_kthreads()\n"); + return -ENOMEM; + } + + conn->tx_thread = kthread_run(iscsi_target_tx_thread, conn, + "%s", ISCSI_TX_THREAD_NAME); + if (IS_ERR(conn->tx_thread)) { + pr_err("Unable to start iscsi_target_tx_thread\n"); + ret = PTR_ERR(conn->tx_thread); + goto out_bitmap; + } + conn->tx_thread_active = true; + + conn->rx_thread = kthread_run(iscsi_target_rx_thread, conn, + "%s", ISCSI_RX_THREAD_NAME); + if (IS_ERR(conn->rx_thread)) { + pr_err("Unable to start iscsi_target_rx_thread\n"); + ret = PTR_ERR(conn->rx_thread); + goto out_tx; + } + conn->rx_thread_active = true; + + return 0; +out_tx: + kthread_stop(conn->tx_thread); + conn->tx_thread_active = false; +out_bitmap: + spin_lock(&iscsit_global->ts_bitmap_lock); + bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id, + get_order(1)); + spin_unlock(&iscsit_global->ts_bitmap_lock); + return ret; +} + int iscsi_post_login_handler( struct iscsi_np *np, struct iscsi_conn *conn, @@ -709,7 +753,7 @@ int iscsi_post_login_handler( struct se_session *se_sess = sess->se_sess; struct iscsi_portal_group *tpg = sess->tpg; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; - struct iscsi_thread_set *ts; + int rc; iscsit_inc_conn_usage_count(conn); @@ -724,7 +768,6 @@ int iscsi_post_login_handler( /* * SCSI Initiator -> SCSI Target Port Mapping */ - ts = iscsi_get_thread_set(); if (!zero_tsih) { iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 0); @@ -751,9 +794,11 @@ int iscsi_post_login_handler( sess->sess_ops->InitiatorName); spin_unlock_bh(&sess->conn_lock); - iscsi_post_login_start_timers(conn); + rc = iscsit_start_kthreads(conn); + if (rc) + return rc; - iscsi_activate_thread_set(conn, ts); + iscsi_post_login_start_timers(conn); /* * Determine CPU mask to ensure connection's RX and TX kthreads * are scheduled on the same CPU. @@ -810,8 +855,11 @@ int iscsi_post_login_handler( " iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt); spin_unlock_bh(&se_tpg->session_lock); + rc = iscsit_start_kthreads(conn); + if (rc) + return rc; + iscsi_post_login_start_timers(conn); - iscsi_activate_thread_set(conn, ts); /* * Determine CPU mask to ensure connection's RX and TX kthreads * are scheduled on the same CPU. diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index bdd127c0e3ae..e8a240818353 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -68,10 +68,8 @@ int iscsit_load_discovery_tpg(void) return -1; } - ret = core_tpg_register( - &lio_target_fabric_configfs->tf_ops, - NULL, &tpg->tpg_se_tpg, tpg, - TRANSPORT_TPG_TYPE_DISCOVERY); + ret = core_tpg_register(&iscsi_ops, NULL, &tpg->tpg_se_tpg, + tpg, TRANSPORT_TPG_TYPE_DISCOVERY); if (ret < 0) { kfree(tpg); return -1; @@ -228,6 +226,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg) a->demo_mode_discovery = TA_DEMO_MODE_DISCOVERY; a->default_erl = TA_DEFAULT_ERL; a->t10_pi = TA_DEFAULT_T10_PI; + a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE; } int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg) @@ -878,3 +877,21 @@ int iscsit_ta_t10_pi( return 0; } + +int iscsit_ta_fabric_prot_type( + struct iscsi_portal_group *tpg, + u32 prot_type) +{ + struct iscsi_tpg_attrib *a = &tpg->tpg_attrib; + + if ((prot_type != 0) && (prot_type != 1) && (prot_type != 3)) { + pr_err("Illegal value for fabric_prot_type: %u\n", prot_type); + return -EINVAL; + } + + a->fabric_prot_type = prot_type; + pr_debug("iSCSI_TPG[%hu] - T10 Fabric Protection Type: %u\n", + tpg->tpgt, prot_type); + + return 0; +} diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index e7265337bc43..95ff5bdecd71 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -39,5 +39,6 @@ extern int iscsit_ta_prod_mode_write_protect(struct iscsi_portal_group *, u32); extern int iscsit_ta_demo_mode_discovery(struct iscsi_portal_group *, u32); extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32); extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32); +extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32); #endif /* ISCSI_TARGET_TPG_H */ diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c deleted file mode 100644 index 26aa50996473..000000000000 --- a/drivers/target/iscsi/iscsi_target_tq.c +++ /dev/null @@ -1,495 +0,0 @@ -/******************************************************************************* - * This file contains the iSCSI Login Thread and Thread Queue functions. - * - * (c) Copyright 2007-2013 Datera, Inc. - * - * Author: Nicholas A. Bellinger <nab@linux-iscsi.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - ******************************************************************************/ - -#include <linux/kthread.h> -#include <linux/list.h> -#include <linux/bitmap.h> - -#include <target/iscsi/iscsi_target_core.h> -#include "iscsi_target_tq.h" -#include "iscsi_target.h" - -static LIST_HEAD(inactive_ts_list); -static DEFINE_SPINLOCK(inactive_ts_lock); -static DEFINE_SPINLOCK(ts_bitmap_lock); - -static void iscsi_add_ts_to_inactive_list(struct iscsi_thread_set *ts) -{ - if (!list_empty(&ts->ts_list)) { - WARN_ON(1); - return; - } - spin_lock(&inactive_ts_lock); - list_add_tail(&ts->ts_list, &inactive_ts_list); - iscsit_global->inactive_ts++; - spin_unlock(&inactive_ts_lock); -} - -static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void) -{ - struct iscsi_thread_set *ts; - - spin_lock(&inactive_ts_lock); - if (list_empty(&inactive_ts_list)) { - spin_unlock(&inactive_ts_lock); - return NULL; - } - - ts = list_first_entry(&inactive_ts_list, struct iscsi_thread_set, ts_list); - - list_del_init(&ts->ts_list); - iscsit_global->inactive_ts--; - spin_unlock(&inactive_ts_lock); - - return ts; -} - -int iscsi_allocate_thread_sets(u32 thread_pair_count) -{ - int allocated_thread_pair_count = 0, i, thread_id; - struct iscsi_thread_set *ts = NULL; - - for (i = 0; i < thread_pair_count; i++) { - ts = kzalloc(sizeof(struct iscsi_thread_set), GFP_KERNEL); - if (!ts) { - pr_err("Unable to allocate memory for" - " thread set.\n"); - return allocated_thread_pair_count; - } - /* - * Locate the next available regision in the thread_set_bitmap - */ - spin_lock(&ts_bitmap_lock); - thread_id = bitmap_find_free_region(iscsit_global->ts_bitmap, - iscsit_global->ts_bitmap_count, get_order(1)); - spin_unlock(&ts_bitmap_lock); - if (thread_id < 0) { - pr_err("bitmap_find_free_region() failed for" - " thread_set_bitmap\n"); - kfree(ts); - return allocated_thread_pair_count; - } - - ts->thread_id = thread_id; - ts->status = ISCSI_THREAD_SET_FREE; - INIT_LIST_HEAD(&ts->ts_list); - spin_lock_init(&ts->ts_state_lock); - init_completion(&ts->rx_restart_comp); - init_completion(&ts->tx_restart_comp); - init_completion(&ts->rx_start_comp); - init_completion(&ts->tx_start_comp); - sema_init(&ts->ts_activate_sem, 0); - - ts->create_threads = 1; - ts->tx_thread = kthread_run(iscsi_target_tx_thread, ts, "%s", - ISCSI_TX_THREAD_NAME); - if (IS_ERR(ts->tx_thread)) { - dump_stack(); - pr_err("Unable to start iscsi_target_tx_thread\n"); - break; - } - - ts->rx_thread = kthread_run(iscsi_target_rx_thread, ts, "%s", - ISCSI_RX_THREAD_NAME); - if (IS_ERR(ts->rx_thread)) { - kthread_stop(ts->tx_thread); - pr_err("Unable to start iscsi_target_rx_thread\n"); - break; - } - ts->create_threads = 0; - - iscsi_add_ts_to_inactive_list(ts); - allocated_thread_pair_count++; - } - - pr_debug("Spawned %d thread set(s) (%d total threads).\n", - allocated_thread_pair_count, allocated_thread_pair_count * 2); - return allocated_thread_pair_count; -} - -static void iscsi_deallocate_thread_one(struct iscsi_thread_set *ts) -{ - spin_lock_bh(&ts->ts_state_lock); - ts->status = ISCSI_THREAD_SET_DIE; - - if (ts->rx_thread) { - complete(&ts->rx_start_comp); - spin_unlock_bh(&ts->ts_state_lock); - kthread_stop(ts->rx_thread); - spin_lock_bh(&ts->ts_state_lock); - } - if (ts->tx_thread) { - complete(&ts->tx_start_comp); - spin_unlock_bh(&ts->ts_state_lock); - kthread_stop(ts->tx_thread); - spin_lock_bh(&ts->ts_state_lock); - } - spin_unlock_bh(&ts->ts_state_lock); - /* - * Release this thread_id in the thread_set_bitmap - */ - spin_lock(&ts_bitmap_lock); - bitmap_release_region(iscsit_global->ts_bitmap, - ts->thread_id, get_order(1)); - spin_unlock(&ts_bitmap_lock); - - kfree(ts); -} - -void iscsi_deallocate_thread_sets(void) -{ - struct iscsi_thread_set *ts = NULL; - u32 released_count = 0; - - while ((ts = iscsi_get_ts_from_inactive_list())) { - - iscsi_deallocate_thread_one(ts); - released_count++; - } - - if (released_count) - pr_debug("Stopped %d thread set(s) (%d total threads)." - "\n", released_count, released_count * 2); -} - -static void iscsi_deallocate_extra_thread_sets(void) -{ - u32 orig_count, released_count = 0; - struct iscsi_thread_set *ts = NULL; - - orig_count = TARGET_THREAD_SET_COUNT; - - while ((iscsit_global->inactive_ts + 1) > orig_count) { - ts = iscsi_get_ts_from_inactive_list(); - if (!ts) - break; - - iscsi_deallocate_thread_one(ts); - released_count++; - } - - if (released_count) - pr_debug("Stopped %d thread set(s) (%d total threads)." - "\n", released_count, released_count * 2); -} - -void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts) -{ - spin_lock_bh(&ts->ts_state_lock); - conn->thread_set = ts; - ts->conn = conn; - ts->status = ISCSI_THREAD_SET_ACTIVE; - spin_unlock_bh(&ts->ts_state_lock); - - complete(&ts->rx_start_comp); - complete(&ts->tx_start_comp); - - down(&ts->ts_activate_sem); -} - -struct iscsi_thread_set *iscsi_get_thread_set(void) -{ - struct iscsi_thread_set *ts; - -get_set: - ts = iscsi_get_ts_from_inactive_list(); - if (!ts) { - iscsi_allocate_thread_sets(1); - goto get_set; - } - - ts->delay_inactive = 1; - ts->signal_sent = 0; - ts->thread_count = 2; - init_completion(&ts->rx_restart_comp); - init_completion(&ts->tx_restart_comp); - sema_init(&ts->ts_activate_sem, 0); - - return ts; -} - -void iscsi_set_thread_clear(struct iscsi_conn *conn, u8 thread_clear) -{ - struct iscsi_thread_set *ts = NULL; - - if (!conn->thread_set) { - pr_err("struct iscsi_conn->thread_set is NULL\n"); - return; - } - ts = conn->thread_set; - - spin_lock_bh(&ts->ts_state_lock); - ts->thread_clear &= ~thread_clear; - - if ((thread_clear & ISCSI_CLEAR_RX_THREAD) && - (ts->blocked_threads & ISCSI_BLOCK_RX_THREAD)) - complete(&ts->rx_restart_comp); - else if ((thread_clear & ISCSI_CLEAR_TX_THREAD) && - (ts->blocked_threads & ISCSI_BLOCK_TX_THREAD)) - complete(&ts->tx_restart_comp); - spin_unlock_bh(&ts->ts_state_lock); -} - -void iscsi_set_thread_set_signal(struct iscsi_conn *conn, u8 signal_sent) -{ - struct iscsi_thread_set *ts = NULL; - - if (!conn->thread_set) { - pr_err("struct iscsi_conn->thread_set is NULL\n"); - return; - } - ts = conn->thread_set; - - spin_lock_bh(&ts->ts_state_lock); - ts->signal_sent |= signal_sent; - spin_unlock_bh(&ts->ts_state_lock); -} - -int iscsi_release_thread_set(struct iscsi_conn *conn) -{ - int thread_called = 0; - struct iscsi_thread_set *ts = NULL; - - if (!conn || !conn->thread_set) { - pr_err("connection or thread set pointer is NULL\n"); - BUG(); - } - ts = conn->thread_set; - - spin_lock_bh(&ts->ts_state_lock); - ts->status = ISCSI_THREAD_SET_RESET; - - if (!strncmp(current->comm, ISCSI_RX_THREAD_NAME, - strlen(ISCSI_RX_THREAD_NAME))) - thread_called = ISCSI_RX_THREAD; - else if (!strncmp(current->comm, ISCSI_TX_THREAD_NAME, - strlen(ISCSI_TX_THREAD_NAME))) - thread_called = ISCSI_TX_THREAD; - - if (ts->rx_thread && (thread_called == ISCSI_TX_THREAD) && - (ts->thread_clear & ISCSI_CLEAR_RX_THREAD)) { - - if (!(ts->signal_sent & ISCSI_SIGNAL_RX_THREAD)) { - send_sig(SIGINT, ts->rx_thread, 1); - ts->signal_sent |= ISCSI_SIGNAL_RX_THREAD; - } - ts->blocked_threads |= ISCSI_BLOCK_RX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); - wait_for_completion(&ts->rx_restart_comp); - spin_lock_bh(&ts->ts_state_lock); - ts->blocked_threads &= ~ISCSI_BLOCK_RX_THREAD; - } - if (ts->tx_thread && (thread_called == ISCSI_RX_THREAD) && - (ts->thread_clear & ISCSI_CLEAR_TX_THREAD)) { - - if (!(ts->signal_sent & ISCSI_SIGNAL_TX_THREAD)) { - send_sig(SIGINT, ts->tx_thread, 1); - ts->signal_sent |= ISCSI_SIGNAL_TX_THREAD; - } - ts->blocked_threads |= ISCSI_BLOCK_TX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); - wait_for_completion(&ts->tx_restart_comp); - spin_lock_bh(&ts->ts_state_lock); - ts->blocked_threads &= ~ISCSI_BLOCK_TX_THREAD; - } - - ts->conn = NULL; - ts->status = ISCSI_THREAD_SET_FREE; - spin_unlock_bh(&ts->ts_state_lock); - - return 0; -} - -int iscsi_thread_set_force_reinstatement(struct iscsi_conn *conn) -{ - struct iscsi_thread_set *ts; - - if (!conn->thread_set) - return -1; - ts = conn->thread_set; - - spin_lock_bh(&ts->ts_state_lock); - if (ts->status != ISCSI_THREAD_SET_ACTIVE) { - spin_unlock_bh(&ts->ts_state_lock); - return -1; - } - - if (ts->tx_thread && (!(ts->signal_sent & ISCSI_SIGNAL_TX_THREAD))) { - send_sig(SIGINT, ts->tx_thread, 1); - ts->signal_sent |= ISCSI_SIGNAL_TX_THREAD; - } - if (ts->rx_thread && (!(ts->signal_sent & ISCSI_SIGNAL_RX_THREAD))) { - send_sig(SIGINT, ts->rx_thread, 1); - ts->signal_sent |= ISCSI_SIGNAL_RX_THREAD; - } - spin_unlock_bh(&ts->ts_state_lock); - - return 0; -} - -static void iscsi_check_to_add_additional_sets(void) -{ - int thread_sets_add; - - spin_lock(&inactive_ts_lock); - thread_sets_add = iscsit_global->inactive_ts; - spin_unlock(&inactive_ts_lock); - if (thread_sets_add == 1) - iscsi_allocate_thread_sets(1); -} - -static int iscsi_signal_thread_pre_handler(struct iscsi_thread_set *ts) -{ - spin_lock_bh(&ts->ts_state_lock); - if (ts->status == ISCSI_THREAD_SET_DIE || kthread_should_stop() || - signal_pending(current)) { - spin_unlock_bh(&ts->ts_state_lock); - return -1; - } - spin_unlock_bh(&ts->ts_state_lock); - - return 0; -} - -struct iscsi_conn *iscsi_rx_thread_pre_handler(struct iscsi_thread_set *ts) -{ - int ret; - - spin_lock_bh(&ts->ts_state_lock); - if (ts->create_threads) { - spin_unlock_bh(&ts->ts_state_lock); - goto sleep; - } - - if (ts->status != ISCSI_THREAD_SET_DIE) - flush_signals(current); - - if (ts->delay_inactive && (--ts->thread_count == 0)) { - spin_unlock_bh(&ts->ts_state_lock); - - if (!iscsit_global->in_shutdown) - iscsi_deallocate_extra_thread_sets(); - - iscsi_add_ts_to_inactive_list(ts); - spin_lock_bh(&ts->ts_state_lock); - } - - if ((ts->status == ISCSI_THREAD_SET_RESET) && - (ts->thread_clear & ISCSI_CLEAR_RX_THREAD)) - complete(&ts->rx_restart_comp); - - ts->thread_clear &= ~ISCSI_CLEAR_RX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); -sleep: - ret = wait_for_completion_interruptible(&ts->rx_start_comp); - if (ret != 0) - return NULL; - - if (iscsi_signal_thread_pre_handler(ts) < 0) - return NULL; - - iscsi_check_to_add_additional_sets(); - - spin_lock_bh(&ts->ts_state_lock); - if (!ts->conn) { - pr_err("struct iscsi_thread_set->conn is NULL for" - " RX thread_id: %s/%d\n", current->comm, current->pid); - spin_unlock_bh(&ts->ts_state_lock); - return NULL; - } - ts->thread_clear |= ISCSI_CLEAR_RX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); - - up(&ts->ts_activate_sem); - - return ts->conn; -} - -struct iscsi_conn *iscsi_tx_thread_pre_handler(struct iscsi_thread_set *ts) -{ - int ret; - - spin_lock_bh(&ts->ts_state_lock); - if (ts->create_threads) { - spin_unlock_bh(&ts->ts_state_lock); - goto sleep; - } - - if (ts->status != ISCSI_THREAD_SET_DIE) - flush_signals(current); - - if (ts->delay_inactive && (--ts->thread_count == 0)) { - spin_unlock_bh(&ts->ts_state_lock); - - if (!iscsit_global->in_shutdown) - iscsi_deallocate_extra_thread_sets(); - - iscsi_add_ts_to_inactive_list(ts); - spin_lock_bh(&ts->ts_state_lock); - } - if ((ts->status == ISCSI_THREAD_SET_RESET) && - (ts->thread_clear & ISCSI_CLEAR_TX_THREAD)) - complete(&ts->tx_restart_comp); - - ts->thread_clear &= ~ISCSI_CLEAR_TX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); -sleep: - ret = wait_for_completion_interruptible(&ts->tx_start_comp); - if (ret != 0) - return NULL; - - if (iscsi_signal_thread_pre_handler(ts) < 0) - return NULL; - - iscsi_check_to_add_additional_sets(); - - spin_lock_bh(&ts->ts_state_lock); - if (!ts->conn) { - pr_err("struct iscsi_thread_set->conn is NULL for" - " TX thread_id: %s/%d\n", current->comm, current->pid); - spin_unlock_bh(&ts->ts_state_lock); - return NULL; - } - ts->thread_clear |= ISCSI_CLEAR_TX_THREAD; - spin_unlock_bh(&ts->ts_state_lock); - - up(&ts->ts_activate_sem); - - return ts->conn; -} - -int iscsi_thread_set_init(void) -{ - int size; - - iscsit_global->ts_bitmap_count = ISCSI_TS_BITMAP_BITS; - - size = BITS_TO_LONGS(iscsit_global->ts_bitmap_count) * sizeof(long); - iscsit_global->ts_bitmap = kzalloc(size, GFP_KERNEL); - if (!iscsit_global->ts_bitmap) { - pr_err("Unable to allocate iscsit_global->ts_bitmap\n"); - return -ENOMEM; - } - - return 0; -} - -void iscsi_thread_set_free(void) -{ - kfree(iscsit_global->ts_bitmap); -} diff --git a/drivers/target/iscsi/iscsi_target_tq.h b/drivers/target/iscsi/iscsi_target_tq.h deleted file mode 100644 index cc1eede5ab3a..000000000000 --- a/drivers/target/iscsi/iscsi_target_tq.h +++ /dev/null @@ -1,84 +0,0 @@ -#ifndef ISCSI_THREAD_QUEUE_H -#define ISCSI_THREAD_QUEUE_H - -/* - * Defines for thread sets. - */ -extern int iscsi_thread_set_force_reinstatement(struct iscsi_conn *); -extern int iscsi_allocate_thread_sets(u32); -extern void iscsi_deallocate_thread_sets(void); -extern void iscsi_activate_thread_set(struct iscsi_conn *, struct iscsi_thread_set *); -extern struct iscsi_thread_set *iscsi_get_thread_set(void); -extern void iscsi_set_thread_clear(struct iscsi_conn *, u8); -extern void iscsi_set_thread_set_signal(struct iscsi_conn *, u8); -extern int iscsi_release_thread_set(struct iscsi_conn *); -extern struct iscsi_conn *iscsi_rx_thread_pre_handler(struct iscsi_thread_set *); -extern struct iscsi_conn *iscsi_tx_thread_pre_handler(struct iscsi_thread_set *); -extern int iscsi_thread_set_init(void); -extern void iscsi_thread_set_free(void); - -extern int iscsi_target_tx_thread(void *); -extern int iscsi_target_rx_thread(void *); - -#define TARGET_THREAD_SET_COUNT 4 - -#define ISCSI_RX_THREAD 1 -#define ISCSI_TX_THREAD 2 -#define ISCSI_RX_THREAD_NAME "iscsi_trx" -#define ISCSI_TX_THREAD_NAME "iscsi_ttx" -#define ISCSI_BLOCK_RX_THREAD 0x1 -#define ISCSI_BLOCK_TX_THREAD 0x2 -#define ISCSI_CLEAR_RX_THREAD 0x1 -#define ISCSI_CLEAR_TX_THREAD 0x2 -#define ISCSI_SIGNAL_RX_THREAD 0x1 -#define ISCSI_SIGNAL_TX_THREAD 0x2 - -/* struct iscsi_thread_set->status */ -#define ISCSI_THREAD_SET_FREE 1 -#define ISCSI_THREAD_SET_ACTIVE 2 -#define ISCSI_THREAD_SET_DIE 3 -#define ISCSI_THREAD_SET_RESET 4 -#define ISCSI_THREAD_SET_DEALLOCATE_THREADS 5 - -/* By default allow a maximum of 32K iSCSI connections */ -#define ISCSI_TS_BITMAP_BITS 32768 - -struct iscsi_thread_set { - /* flags used for blocking and restarting sets */ - int blocked_threads; - /* flag for creating threads */ - int create_threads; - /* flag for delaying readding to inactive list */ - int delay_inactive; - /* status for thread set */ - int status; - /* which threads have had signals sent */ - int signal_sent; - /* flag for which threads exited first */ - int thread_clear; - /* Active threads in the thread set */ - int thread_count; - /* Unique thread ID */ - u32 thread_id; - /* pointer to connection if set is active */ - struct iscsi_conn *conn; - /* used for controlling ts state accesses */ - spinlock_t ts_state_lock; - /* used for restarting thread queue */ - struct completion rx_restart_comp; - /* used for restarting thread queue */ - struct completion tx_restart_comp; - /* used for normal unused blocking */ - struct completion rx_start_comp; - /* used for normal unused blocking */ - struct completion tx_start_comp; - /* OS descriptor for rx thread */ - struct task_struct *rx_thread; - /* OS descriptor for tx thread */ - struct task_struct *tx_thread; - /* struct iscsi_thread_set in list list head*/ - struct list_head ts_list; - struct semaphore ts_activate_sem; -}; - -#endif /*** ISCSI_THREAD_QUEUE_H ***/ diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 390df8ed72b2..b18edda3e8af 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -33,7 +33,6 @@ #include "iscsi_target_erl1.h" #include "iscsi_target_erl2.h" #include "iscsi_target_tpg.h" -#include "iscsi_target_tq.h" #include "iscsi_target_util.h" #include "iscsi_target.h" diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index c36bd7c29136..51f0c895c6a5 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -41,8 +41,7 @@ #define to_tcm_loop_hba(hba) container_of(hba, struct tcm_loop_hba, dev) -/* Local pointer to allocated TCM configfs fabric module */ -static struct target_fabric_configfs *tcm_loop_fabric_configfs; +static const struct target_core_fabric_ops loop_ops; static struct workqueue_struct *tcm_loop_workqueue; static struct kmem_cache *tcm_loop_cmd_cache; @@ -108,7 +107,7 @@ static struct device_driver tcm_loop_driverfs = { /* * Used with root_device_register() in tcm_loop_alloc_core_bus() below */ -struct device *tcm_loop_primary; +static struct device *tcm_loop_primary; static void tcm_loop_submission_work(struct work_struct *work) { @@ -697,6 +696,13 @@ static int tcm_loop_check_prod_mode_write_protect(struct se_portal_group *se_tpg return 0; } +static int tcm_loop_check_prot_fabric_only(struct se_portal_group *se_tpg) +{ + struct tcm_loop_tpg *tl_tpg = container_of(se_tpg, struct tcm_loop_tpg, + tl_se_tpg); + return tl_tpg->tl_fabric_prot_type; +} + static struct se_node_acl *tcm_loop_tpg_alloc_fabric_acl( struct se_portal_group *se_tpg) { @@ -912,6 +918,46 @@ static void tcm_loop_port_unlink( /* End items for tcm_loop_port_cit */ +static ssize_t tcm_loop_tpg_attrib_show_fabric_prot_type( + struct se_portal_group *se_tpg, + char *page) +{ + struct tcm_loop_tpg *tl_tpg = container_of(se_tpg, struct tcm_loop_tpg, + tl_se_tpg); + + return sprintf(page, "%d\n", tl_tpg->tl_fabric_prot_type); +} + +static ssize_t tcm_loop_tpg_attrib_store_fabric_prot_type( + struct se_portal_group *se_tpg, + const char *page, + size_t count) +{ + struct tcm_loop_tpg *tl_tpg = container_of(se_tpg, struct tcm_loop_tpg, + tl_se_tpg); + unsigned long val; + int ret = kstrtoul(page, 0, &val); + + if (ret) { + pr_err("kstrtoul() returned %d for fabric_prot_type\n", ret); + return ret; + } + if (val != 0 && val != 1 && val != 3) { + pr_err("Invalid qla2xxx fabric_prot_type: %lu\n", val); + return -EINVAL; + } + tl_tpg->tl_fabric_prot_type = val; + + return count; +} + +TF_TPG_ATTRIB_ATTR(tcm_loop, fabric_prot_type, S_IRUGO | S_IWUSR); + +static struct configfs_attribute *tcm_loop_tpg_attrib_attrs[] = { + &tcm_loop_tpg_attrib_fabric_prot_type.attr, + NULL, +}; + /* Start items for tcm_loop_nexus_cit */ static int tcm_loop_make_nexus( @@ -937,7 +983,8 @@ static int tcm_loop_make_nexus( /* * Initialize the struct se_session pointer */ - tl_nexus->se_sess = transport_init_session(TARGET_PROT_ALL); + tl_nexus->se_sess = transport_init_session( + TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS); if (IS_ERR(tl_nexus->se_sess)) { ret = PTR_ERR(tl_nexus->se_sess); goto out; @@ -1165,21 +1212,19 @@ static struct se_portal_group *tcm_loop_make_naa_tpg( struct tcm_loop_hba *tl_hba = container_of(wwn, struct tcm_loop_hba, tl_hba_wwn); struct tcm_loop_tpg *tl_tpg; - char *tpgt_str, *end_ptr; int ret; - unsigned short int tpgt; + unsigned long tpgt; - tpgt_str = strstr(name, "tpgt_"); - if (!tpgt_str) { + if (strstr(name, "tpgt_") != name) { pr_err("Unable to locate \"tpgt_#\" directory" " group\n"); return ERR_PTR(-EINVAL); } - tpgt_str += 5; /* Skip ahead of "tpgt_" */ - tpgt = (unsigned short int) simple_strtoul(tpgt_str, &end_ptr, 0); + if (kstrtoul(name+5, 10, &tpgt)) + return ERR_PTR(-EINVAL); if (tpgt >= TL_TPGS_PER_HBA) { - pr_err("Passed tpgt: %hu exceeds TL_TPGS_PER_HBA:" + pr_err("Passed tpgt: %lu exceeds TL_TPGS_PER_HBA:" " %u\n", tpgt, TL_TPGS_PER_HBA); return ERR_PTR(-EINVAL); } @@ -1189,14 +1234,13 @@ static struct se_portal_group *tcm_loop_make_naa_tpg( /* * Register the tl_tpg as a emulated SAS TCM Target Endpoint */ - ret = core_tpg_register(&tcm_loop_fabric_configfs->tf_ops, - wwn, &tl_tpg->tl_se_tpg, tl_tpg, + ret = core_tpg_register(&loop_ops, wwn, &tl_tpg->tl_se_tpg, tl_tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) return ERR_PTR(-ENOMEM); pr_debug("TCM_Loop_ConfigFS: Allocated Emulated %s" - " Target Port %s,t,0x%04x\n", tcm_loop_dump_proto_id(tl_hba), + " Target Port %s,t,0x%04lx\n", tcm_loop_dump_proto_id(tl_hba), config_item_name(&wwn->wwn_group.cg_item), tpgt); return &tl_tpg->tl_se_tpg; @@ -1338,127 +1382,51 @@ static struct configfs_attribute *tcm_loop_wwn_attrs[] = { /* End items for tcm_loop_cit */ -static int tcm_loop_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - /* - * Set the TCM Loop HBA counter to zero - */ - tcm_loop_hba_no_cnt = 0; - /* - * Register the top level struct config_item_type with TCM core - */ - fabric = target_fabric_configfs_init(THIS_MODULE, "loopback"); - if (IS_ERR(fabric)) { - pr_err("tcm_loop_register_configfs() failed!\n"); - return PTR_ERR(fabric); - } - /* - * Setup the fabric API of function pointers used by target_core_mod - */ - fabric->tf_ops.get_fabric_name = &tcm_loop_get_fabric_name; - fabric->tf_ops.get_fabric_proto_ident = &tcm_loop_get_fabric_proto_ident; - fabric->tf_ops.tpg_get_wwn = &tcm_loop_get_endpoint_wwn; - fabric->tf_ops.tpg_get_tag = &tcm_loop_get_tag; - fabric->tf_ops.tpg_get_default_depth = &tcm_loop_get_default_depth; - fabric->tf_ops.tpg_get_pr_transport_id = &tcm_loop_get_pr_transport_id; - fabric->tf_ops.tpg_get_pr_transport_id_len = - &tcm_loop_get_pr_transport_id_len; - fabric->tf_ops.tpg_parse_pr_out_transport_id = - &tcm_loop_parse_pr_out_transport_id; - fabric->tf_ops.tpg_check_demo_mode = &tcm_loop_check_demo_mode; - fabric->tf_ops.tpg_check_demo_mode_cache = - &tcm_loop_check_demo_mode_cache; - fabric->tf_ops.tpg_check_demo_mode_write_protect = - &tcm_loop_check_demo_mode_write_protect; - fabric->tf_ops.tpg_check_prod_mode_write_protect = - &tcm_loop_check_prod_mode_write_protect; - /* - * The TCM loopback fabric module runs in demo-mode to a local - * virtual SCSI device, so fabric dependent initator ACLs are - * not required. - */ - fabric->tf_ops.tpg_alloc_fabric_acl = &tcm_loop_tpg_alloc_fabric_acl; - fabric->tf_ops.tpg_release_fabric_acl = - &tcm_loop_tpg_release_fabric_acl; - fabric->tf_ops.tpg_get_inst_index = &tcm_loop_get_inst_index; - /* - * Used for setting up remaining TCM resources in process context - */ - fabric->tf_ops.check_stop_free = &tcm_loop_check_stop_free; - fabric->tf_ops.release_cmd = &tcm_loop_release_cmd; - fabric->tf_ops.shutdown_session = &tcm_loop_shutdown_session; - fabric->tf_ops.close_session = &tcm_loop_close_session; - fabric->tf_ops.sess_get_index = &tcm_loop_sess_get_index; - fabric->tf_ops.sess_get_initiator_sid = NULL; - fabric->tf_ops.write_pending = &tcm_loop_write_pending; - fabric->tf_ops.write_pending_status = &tcm_loop_write_pending_status; - /* - * Not used for TCM loopback - */ - fabric->tf_ops.set_default_node_attributes = - &tcm_loop_set_default_node_attributes; - fabric->tf_ops.get_task_tag = &tcm_loop_get_task_tag; - fabric->tf_ops.get_cmd_state = &tcm_loop_get_cmd_state; - fabric->tf_ops.queue_data_in = &tcm_loop_queue_data_in; - fabric->tf_ops.queue_status = &tcm_loop_queue_status; - fabric->tf_ops.queue_tm_rsp = &tcm_loop_queue_tm_rsp; - fabric->tf_ops.aborted_task = &tcm_loop_aborted_task; - - /* - * Setup function pointers for generic logic in target_core_fabric_configfs.c - */ - fabric->tf_ops.fabric_make_wwn = &tcm_loop_make_scsi_hba; - fabric->tf_ops.fabric_drop_wwn = &tcm_loop_drop_scsi_hba; - fabric->tf_ops.fabric_make_tpg = &tcm_loop_make_naa_tpg; - fabric->tf_ops.fabric_drop_tpg = &tcm_loop_drop_naa_tpg; - /* - * fabric_post_link() and fabric_pre_unlink() are used for - * registration and release of TCM Loop Virtual SCSI LUNs. - */ - fabric->tf_ops.fabric_post_link = &tcm_loop_port_link; - fabric->tf_ops.fabric_pre_unlink = &tcm_loop_port_unlink; - fabric->tf_ops.fabric_make_np = NULL; - fabric->tf_ops.fabric_drop_np = NULL; - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_loop_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_loop_tpg_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - /* - * Once fabric->tf_ops has been setup, now register the fabric for - * use within TCM - */ - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() for" - " TCM_Loop failed!\n"); - target_fabric_configfs_free(fabric); - return -1; - } - /* - * Setup our local pointer to *fabric. - */ - tcm_loop_fabric_configfs = fabric; - pr_debug("TCM_LOOP[0] - Set fabric ->" - " tcm_loop_fabric_configfs\n"); - return 0; -} - -static void tcm_loop_deregister_configfs(void) -{ - if (!tcm_loop_fabric_configfs) - return; - - target_fabric_configfs_deregister(tcm_loop_fabric_configfs); - tcm_loop_fabric_configfs = NULL; - pr_debug("TCM_LOOP[0] - Cleared" - " tcm_loop_fabric_configfs\n"); -} +static const struct target_core_fabric_ops loop_ops = { + .module = THIS_MODULE, + .name = "loopback", + .get_fabric_name = tcm_loop_get_fabric_name, + .get_fabric_proto_ident = tcm_loop_get_fabric_proto_ident, + .tpg_get_wwn = tcm_loop_get_endpoint_wwn, + .tpg_get_tag = tcm_loop_get_tag, + .tpg_get_default_depth = tcm_loop_get_default_depth, + .tpg_get_pr_transport_id = tcm_loop_get_pr_transport_id, + .tpg_get_pr_transport_id_len = tcm_loop_get_pr_transport_id_len, + .tpg_parse_pr_out_transport_id = tcm_loop_parse_pr_out_transport_id, + .tpg_check_demo_mode = tcm_loop_check_demo_mode, + .tpg_check_demo_mode_cache = tcm_loop_check_demo_mode_cache, + .tpg_check_demo_mode_write_protect = + tcm_loop_check_demo_mode_write_protect, + .tpg_check_prod_mode_write_protect = + tcm_loop_check_prod_mode_write_protect, + .tpg_check_prot_fabric_only = tcm_loop_check_prot_fabric_only, + .tpg_alloc_fabric_acl = tcm_loop_tpg_alloc_fabric_acl, + .tpg_release_fabric_acl = tcm_loop_tpg_release_fabric_acl, + .tpg_get_inst_index = tcm_loop_get_inst_index, + .check_stop_free = tcm_loop_check_stop_free, + .release_cmd = tcm_loop_release_cmd, + .shutdown_session = tcm_loop_shutdown_session, + .close_session = tcm_loop_close_session, + .sess_get_index = tcm_loop_sess_get_index, + .write_pending = tcm_loop_write_pending, + .write_pending_status = tcm_loop_write_pending_status, + .set_default_node_attributes = tcm_loop_set_default_node_attributes, + .get_task_tag = tcm_loop_get_task_tag, + .get_cmd_state = tcm_loop_get_cmd_state, + .queue_data_in = tcm_loop_queue_data_in, + .queue_status = tcm_loop_queue_status, + .queue_tm_rsp = tcm_loop_queue_tm_rsp, + .aborted_task = tcm_loop_aborted_task, + .fabric_make_wwn = tcm_loop_make_scsi_hba, + .fabric_drop_wwn = tcm_loop_drop_scsi_hba, + .fabric_make_tpg = tcm_loop_make_naa_tpg, + .fabric_drop_tpg = tcm_loop_drop_naa_tpg, + .fabric_post_link = tcm_loop_port_link, + .fabric_pre_unlink = tcm_loop_port_unlink, + .tfc_wwn_attrs = tcm_loop_wwn_attrs, + .tfc_tpg_base_attrs = tcm_loop_tpg_attrs, + .tfc_tpg_attrib_attrs = tcm_loop_tpg_attrib_attrs, +}; static int __init tcm_loop_fabric_init(void) { @@ -1482,7 +1450,7 @@ static int __init tcm_loop_fabric_init(void) if (ret) goto out_destroy_cache; - ret = tcm_loop_register_configfs(); + ret = target_register_template(&loop_ops); if (ret) goto out_release_core_bus; @@ -1500,7 +1468,7 @@ out: static void __exit tcm_loop_fabric_exit(void) { - tcm_loop_deregister_configfs(); + target_unregister_template(&loop_ops); tcm_loop_release_core_bus(); kmem_cache_destroy(tcm_loop_cmd_cache); destroy_workqueue(tcm_loop_workqueue); diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index 6ae49f272ba6..1e72ff77cac9 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -43,6 +43,7 @@ struct tcm_loop_nacl { struct tcm_loop_tpg { unsigned short tl_tpgt; unsigned short tl_transport_status; + enum target_prot_type tl_fabric_prot_type; atomic_t tl_tpg_port_count; struct se_portal_group tl_se_tpg; struct tcm_loop_hba *tl_hba; diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 9512af6a8114..18b0f9703ff2 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -42,8 +42,7 @@ #include "sbp_target.h" -/* Local pointer to allocated TCM configfs fabric module */ -static struct target_fabric_configfs *sbp_fabric_configfs; +static const struct target_core_fabric_ops sbp_ops; /* FireWire address region for management and command block address handlers */ static const struct fw_address_region sbp_register_region = { @@ -2215,8 +2214,7 @@ static struct se_portal_group *sbp_make_tpg( goto out_free_tpg; } - ret = core_tpg_register(&sbp_fabric_configfs->tf_ops, wwn, - &tpg->se_tpg, (void *)tpg, + ret = core_tpg_register(&sbp_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) goto out_unreg_mgt_agt; @@ -2503,7 +2501,9 @@ static struct configfs_attribute *sbp_tpg_attrib_attrs[] = { NULL, }; -static struct target_core_fabric_ops sbp_ops = { +static const struct target_core_fabric_ops sbp_ops = { + .module = THIS_MODULE, + .name = "sbp", .get_fabric_name = sbp_get_fabric_name, .get_fabric_proto_ident = sbp_get_fabric_proto_ident, .tpg_get_wwn = sbp_get_fabric_wwn, @@ -2544,68 +2544,20 @@ static struct target_core_fabric_ops sbp_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = sbp_make_nodeacl, .fabric_drop_nodeacl = sbp_drop_nodeacl, -}; - -static int sbp_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - - fabric = target_fabric_configfs_init(THIS_MODULE, "sbp"); - if (IS_ERR(fabric)) { - pr_err("target_fabric_configfs_init() failed\n"); - return PTR_ERR(fabric); - } - - fabric->tf_ops = sbp_ops; - - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = sbp_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = sbp_tpg_base_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = sbp_tpg_attrib_attrs; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() failed for SBP\n"); - return ret; - } - sbp_fabric_configfs = fabric; - - return 0; -}; - -static void sbp_deregister_configfs(void) -{ - if (!sbp_fabric_configfs) - return; - - target_fabric_configfs_deregister(sbp_fabric_configfs); - sbp_fabric_configfs = NULL; + .tfc_wwn_attrs = sbp_wwn_attrs, + .tfc_tpg_base_attrs = sbp_tpg_base_attrs, + .tfc_tpg_attrib_attrs = sbp_tpg_attrib_attrs, }; static int __init sbp_init(void) { - int ret; - - ret = sbp_register_configfs(); - if (ret < 0) - return ret; - - return 0; + return target_register_template(&sbp_ops); }; static void __exit sbp_exit(void) { - sbp_deregister_configfs(); + target_unregister_template(&sbp_ops); }; MODULE_DESCRIPTION("FireWire SBP fabric driver"); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 75d89adfccc0..ddaf76a4ac2a 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -142,8 +142,8 @@ static struct config_group *target_core_register_fabric( tf = target_core_get_fabric(name); if (!tf) { - pr_err("target_core_register_fabric() trying autoload for %s\n", - name); + pr_debug("target_core_register_fabric() trying autoload for %s\n", + name); /* * Below are some hardcoded request_module() calls to automatically @@ -165,8 +165,8 @@ static struct config_group *target_core_register_fabric( */ ret = request_module("iscsi_target_mod"); if (ret < 0) { - pr_err("request_module() failed for" - " iscsi_target_mod.ko: %d\n", ret); + pr_debug("request_module() failed for" + " iscsi_target_mod.ko: %d\n", ret); return ERR_PTR(-EINVAL); } } else if (!strncmp(name, "loopback", 8)) { @@ -178,8 +178,8 @@ static struct config_group *target_core_register_fabric( */ ret = request_module("tcm_loop"); if (ret < 0) { - pr_err("request_module() failed for" - " tcm_loop.ko: %d\n", ret); + pr_debug("request_module() failed for" + " tcm_loop.ko: %d\n", ret); return ERR_PTR(-EINVAL); } } @@ -188,8 +188,8 @@ static struct config_group *target_core_register_fabric( } if (!tf) { - pr_err("target_core_get_fabric() failed for %s\n", - name); + pr_debug("target_core_get_fabric() failed for %s\n", + name); return ERR_PTR(-EINVAL); } pr_debug("Target_Core_ConfigFS: REGISTER -> Located fabric:" @@ -300,81 +300,17 @@ struct configfs_subsystem *target_core_subsystem[] = { // Start functions called by external Target Fabrics Modules //############################################################################*/ -/* - * First function called by fabric modules to: - * - * 1) Allocate a struct target_fabric_configfs and save the *fabric_cit pointer. - * 2) Add struct target_fabric_configfs to g_tf_list - * 3) Return struct target_fabric_configfs to fabric module to be passed - * into target_fabric_configfs_register(). - */ -struct target_fabric_configfs *target_fabric_configfs_init( - struct module *fabric_mod, - const char *name) +static int target_fabric_tf_ops_check(const struct target_core_fabric_ops *tfo) { - struct target_fabric_configfs *tf; - - if (!(name)) { - pr_err("Unable to locate passed fabric name\n"); - return ERR_PTR(-EINVAL); + if (!tfo->name) { + pr_err("Missing tfo->name\n"); + return -EINVAL; } - if (strlen(name) >= TARGET_FABRIC_NAME_SIZE) { + if (strlen(tfo->name) >= TARGET_FABRIC_NAME_SIZE) { pr_err("Passed name: %s exceeds TARGET_FABRIC" - "_NAME_SIZE\n", name); - return ERR_PTR(-EINVAL); + "_NAME_SIZE\n", tfo->name); + return -EINVAL; } - - tf = kzalloc(sizeof(struct target_fabric_configfs), GFP_KERNEL); - if (!tf) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(&tf->tf_list); - atomic_set(&tf->tf_access_cnt, 0); - /* - * Setup the default generic struct config_item_type's (cits) in - * struct target_fabric_configfs->tf_cit_tmpl - */ - tf->tf_module = fabric_mod; - target_fabric_setup_cits(tf); - - tf->tf_subsys = target_core_subsystem[0]; - snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", name); - - mutex_lock(&g_tf_lock); - list_add_tail(&tf->tf_list, &g_tf_list); - mutex_unlock(&g_tf_lock); - - pr_debug("<<<<<<<<<<<<<<<<<<<<<< BEGIN FABRIC API >>>>>>>>" - ">>>>>>>>>>>>>>\n"); - pr_debug("Initialized struct target_fabric_configfs: %p for" - " %s\n", tf, tf->tf_name); - return tf; -} -EXPORT_SYMBOL(target_fabric_configfs_init); - -/* - * Called by fabric plugins after FAILED target_fabric_configfs_register() call. - */ -void target_fabric_configfs_free( - struct target_fabric_configfs *tf) -{ - mutex_lock(&g_tf_lock); - list_del(&tf->tf_list); - mutex_unlock(&g_tf_lock); - - kfree(tf); -} -EXPORT_SYMBOL(target_fabric_configfs_free); - -/* - * Perform a sanity check of the passed tf->tf_ops before completing - * TCM fabric module registration. - */ -static int target_fabric_tf_ops_check( - struct target_fabric_configfs *tf) -{ - struct target_core_fabric_ops *tfo = &tf->tf_ops; - if (!tfo->get_fabric_name) { pr_err("Missing tfo->get_fabric_name()\n"); return -EINVAL; @@ -508,77 +444,59 @@ static int target_fabric_tf_ops_check( return 0; } -/* - * Called 2nd from fabric module with returned parameter of - * struct target_fabric_configfs * from target_fabric_configfs_init(). - * - * Upon a successful registration, the new fabric's struct config_item is - * return. Also, a pointer to this struct is set in the passed - * struct target_fabric_configfs. - */ -int target_fabric_configfs_register( - struct target_fabric_configfs *tf) +int target_register_template(const struct target_core_fabric_ops *fo) { + struct target_fabric_configfs *tf; int ret; + ret = target_fabric_tf_ops_check(fo); + if (ret) + return ret; + + tf = kzalloc(sizeof(struct target_fabric_configfs), GFP_KERNEL); if (!tf) { - pr_err("Unable to locate target_fabric_configfs" - " pointer\n"); - return -EINVAL; - } - if (!tf->tf_subsys) { - pr_err("Unable to target struct config_subsystem" - " pointer\n"); - return -EINVAL; + pr_err("%s: could not allocate memory!\n", __func__); + return -ENOMEM; } - ret = target_fabric_tf_ops_check(tf); - if (ret < 0) - return ret; - pr_debug("<<<<<<<<<<<<<<<<<<<<<< END FABRIC API >>>>>>>>>>>>" - ">>>>>>>>>>\n"); + INIT_LIST_HEAD(&tf->tf_list); + atomic_set(&tf->tf_access_cnt, 0); + + /* + * Setup the default generic struct config_item_type's (cits) in + * struct target_fabric_configfs->tf_cit_tmpl + */ + tf->tf_module = fo->module; + tf->tf_subsys = target_core_subsystem[0]; + snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name); + + tf->tf_ops = *fo; + target_fabric_setup_cits(tf); + + mutex_lock(&g_tf_lock); + list_add_tail(&tf->tf_list, &g_tf_list); + mutex_unlock(&g_tf_lock); + return 0; } -EXPORT_SYMBOL(target_fabric_configfs_register); +EXPORT_SYMBOL(target_register_template); -void target_fabric_configfs_deregister( - struct target_fabric_configfs *tf) +void target_unregister_template(const struct target_core_fabric_ops *fo) { - struct configfs_subsystem *su; + struct target_fabric_configfs *t; - if (!tf) { - pr_err("Unable to locate passed target_fabric_" - "configfs\n"); - return; - } - su = tf->tf_subsys; - if (!su) { - pr_err("Unable to locate passed tf->tf_subsys" - " pointer\n"); - return; - } - pr_debug("<<<<<<<<<<<<<<<<<<<<<< BEGIN FABRIC API >>>>>>>>>>" - ">>>>>>>>>>>>\n"); mutex_lock(&g_tf_lock); - if (atomic_read(&tf->tf_access_cnt)) { - mutex_unlock(&g_tf_lock); - pr_err("Non zero tf->tf_access_cnt for fabric %s\n", - tf->tf_name); - BUG(); + list_for_each_entry(t, &g_tf_list, tf_list) { + if (!strcmp(t->tf_name, fo->name)) { + BUG_ON(atomic_read(&t->tf_access_cnt)); + list_del(&t->tf_list); + kfree(t); + break; + } } - list_del(&tf->tf_list); mutex_unlock(&g_tf_lock); - - pr_debug("Target_Core_ConfigFS: DEREGISTER -> Releasing tf:" - " %s\n", tf->tf_name); - tf->tf_module = NULL; - tf->tf_subsys = NULL; - kfree(tf); - - pr_debug("<<<<<<<<<<<<<<<<<<<<<< END FABRIC API >>>>>>>>>>>>>>>>>" - ">>>>>\n"); } -EXPORT_SYMBOL(target_fabric_configfs_deregister); +EXPORT_SYMBOL(target_unregister_template); /*############################################################################## // Stop functions called by external Target Fabrics Modules @@ -945,7 +863,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_holder_tg_port( struct se_lun *lun; struct se_portal_group *se_tpg; struct t10_pr_registration *pr_reg; - struct target_core_fabric_ops *tfo; + const struct target_core_fabric_ops *tfo; ssize_t len = 0; spin_lock(&dev->dev_reservation_lock); @@ -979,7 +897,7 @@ SE_DEV_PR_ATTR_RO(res_pr_holder_tg_port); static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts( struct se_device *dev, char *page) { - struct target_core_fabric_ops *tfo; + const struct target_core_fabric_ops *tfo; struct t10_pr_registration *pr_reg; unsigned char buf[384]; char i_buf[PR_REG_ISID_ID_LEN]; diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 0c3f90130b7d..1f7886bb16bf 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -56,6 +56,20 @@ static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf) pr_debug("Setup generic %s\n", __stringify(_name)); \ } +#define TF_CIT_SETUP_DRV(_name, _item_ops, _group_ops) \ +static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf) \ +{ \ + struct target_fabric_configfs_template *tfc = &tf->tf_cit_tmpl; \ + struct config_item_type *cit = &tfc->tfc_##_name##_cit; \ + struct configfs_attribute **attrs = tf->tf_ops.tfc_##_name##_attrs; \ + \ + cit->ct_item_ops = _item_ops; \ + cit->ct_group_ops = _group_ops; \ + cit->ct_attrs = attrs; \ + cit->ct_owner = tf->tf_module; \ + pr_debug("Setup generic %s\n", __stringify(_name)); \ +} + /* Start of tfc_tpg_mappedlun_cit */ static int target_fabric_mappedlun_link( @@ -278,7 +292,7 @@ static struct configfs_item_operations target_fabric_nacl_attrib_item_ops = { .store_attribute = target_fabric_nacl_attrib_attr_store, }; -TF_CIT_SETUP(tpg_nacl_attrib, &target_fabric_nacl_attrib_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_nacl_attrib, &target_fabric_nacl_attrib_item_ops, NULL); /* End of tfc_tpg_nacl_attrib_cit */ @@ -291,7 +305,7 @@ static struct configfs_item_operations target_fabric_nacl_auth_item_ops = { .store_attribute = target_fabric_nacl_auth_attr_store, }; -TF_CIT_SETUP(tpg_nacl_auth, &target_fabric_nacl_auth_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_nacl_auth, &target_fabric_nacl_auth_item_ops, NULL); /* End of tfc_tpg_nacl_auth_cit */ @@ -304,7 +318,7 @@ static struct configfs_item_operations target_fabric_nacl_param_item_ops = { .store_attribute = target_fabric_nacl_param_attr_store, }; -TF_CIT_SETUP(tpg_nacl_param, &target_fabric_nacl_param_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_nacl_param, &target_fabric_nacl_param_item_ops, NULL); /* End of tfc_tpg_nacl_param_cit */ @@ -461,8 +475,8 @@ static struct configfs_group_operations target_fabric_nacl_base_group_ops = { .drop_item = target_fabric_drop_mappedlun, }; -TF_CIT_SETUP(tpg_nacl_base, &target_fabric_nacl_base_item_ops, - &target_fabric_nacl_base_group_ops, NULL); +TF_CIT_SETUP_DRV(tpg_nacl_base, &target_fabric_nacl_base_item_ops, + &target_fabric_nacl_base_group_ops); /* End of tfc_tpg_nacl_base_cit */ @@ -570,7 +584,7 @@ static struct configfs_item_operations target_fabric_np_base_item_ops = { .store_attribute = target_fabric_np_base_attr_store, }; -TF_CIT_SETUP(tpg_np_base, &target_fabric_np_base_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_np_base, &target_fabric_np_base_item_ops, NULL); /* End of tfc_tpg_np_base_cit */ @@ -966,7 +980,7 @@ static struct configfs_item_operations target_fabric_tpg_attrib_item_ops = { .store_attribute = target_fabric_tpg_attrib_attr_store, }; -TF_CIT_SETUP(tpg_attrib, &target_fabric_tpg_attrib_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_attrib, &target_fabric_tpg_attrib_item_ops, NULL); /* End of tfc_tpg_attrib_cit */ @@ -979,7 +993,7 @@ static struct configfs_item_operations target_fabric_tpg_auth_item_ops = { .store_attribute = target_fabric_tpg_auth_attr_store, }; -TF_CIT_SETUP(tpg_auth, &target_fabric_tpg_auth_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_auth, &target_fabric_tpg_auth_item_ops, NULL); /* End of tfc_tpg_attrib_cit */ @@ -992,7 +1006,7 @@ static struct configfs_item_operations target_fabric_tpg_param_item_ops = { .store_attribute = target_fabric_tpg_param_attr_store, }; -TF_CIT_SETUP(tpg_param, &target_fabric_tpg_param_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_param, &target_fabric_tpg_param_item_ops, NULL); /* End of tfc_tpg_param_cit */ @@ -1018,7 +1032,7 @@ static struct configfs_item_operations target_fabric_tpg_base_item_ops = { .store_attribute = target_fabric_tpg_attr_store, }; -TF_CIT_SETUP(tpg_base, &target_fabric_tpg_base_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(tpg_base, &target_fabric_tpg_base_item_ops, NULL); /* End of tfc_tpg_base_cit */ @@ -1192,7 +1206,7 @@ static struct configfs_item_operations target_fabric_wwn_item_ops = { .store_attribute = target_fabric_wwn_attr_store, }; -TF_CIT_SETUP(wwn, &target_fabric_wwn_item_ops, &target_fabric_wwn_group_ops, NULL); +TF_CIT_SETUP_DRV(wwn, &target_fabric_wwn_item_ops, &target_fabric_wwn_group_ops); /* End of tfc_wwn_cit */ @@ -1206,7 +1220,7 @@ static struct configfs_item_operations target_fabric_discovery_item_ops = { .store_attribute = target_fabric_discovery_attr_store, }; -TF_CIT_SETUP(discovery, &target_fabric_discovery_item_ops, NULL, NULL); +TF_CIT_SETUP_DRV(discovery, &target_fabric_discovery_item_ops, NULL); /* End of tfc_discovery_cit */ diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 44620fb6bd45..f7e6e51aed36 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -264,40 +264,32 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, struct se_device *se_dev = cmd->se_dev; struct fd_dev *dev = FD_DEV(se_dev); struct file *prot_fd = dev->fd_prot_file; - struct scatterlist *sg; loff_t pos = (cmd->t_task_lba * se_dev->prot_length); unsigned char *buf; - u32 prot_size, len, size; - int rc, ret = 1, i; + u32 prot_size; + int rc, ret = 1; prot_size = (cmd->data_length / se_dev->dev_attrib.block_size) * se_dev->prot_length; if (!is_write) { - fd_prot->prot_buf = vzalloc(prot_size); + fd_prot->prot_buf = kzalloc(prot_size, GFP_KERNEL); if (!fd_prot->prot_buf) { pr_err("Unable to allocate fd_prot->prot_buf\n"); return -ENOMEM; } buf = fd_prot->prot_buf; - fd_prot->prot_sg_nents = cmd->t_prot_nents; - fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist) * - fd_prot->prot_sg_nents, GFP_KERNEL); + fd_prot->prot_sg_nents = 1; + fd_prot->prot_sg = kzalloc(sizeof(struct scatterlist), + GFP_KERNEL); if (!fd_prot->prot_sg) { pr_err("Unable to allocate fd_prot->prot_sg\n"); - vfree(fd_prot->prot_buf); + kfree(fd_prot->prot_buf); return -ENOMEM; } - size = prot_size; - - for_each_sg(fd_prot->prot_sg, sg, fd_prot->prot_sg_nents, i) { - - len = min_t(u32, PAGE_SIZE, size); - sg_set_buf(sg, buf, len); - size -= len; - buf += len; - } + sg_init_table(fd_prot->prot_sg, fd_prot->prot_sg_nents); + sg_set_buf(fd_prot->prot_sg, buf, prot_size); } if (is_write) { @@ -318,7 +310,7 @@ static int fd_do_prot_rw(struct se_cmd *cmd, struct fd_prot *fd_prot, if (is_write || ret < 0) { kfree(fd_prot->prot_sg); - vfree(fd_prot->prot_buf); + kfree(fd_prot->prot_buf); } return ret; @@ -331,36 +323,33 @@ static int fd_do_rw(struct se_cmd *cmd, struct scatterlist *sgl, struct fd_dev *dev = FD_DEV(se_dev); struct file *fd = dev->fd_file; struct scatterlist *sg; - struct iovec *iov; - mm_segment_t old_fs; + struct iov_iter iter; + struct bio_vec *bvec; + ssize_t len = 0; loff_t pos = (cmd->t_task_lba * se_dev->dev_attrib.block_size); int ret = 0, i; - iov = kzalloc(sizeof(struct iovec) * sgl_nents, GFP_KERNEL); - if (!iov) { + bvec = kcalloc(sgl_nents, sizeof(struct bio_vec), GFP_KERNEL); + if (!bvec) { pr_err("Unable to allocate fd_do_readv iov[]\n"); return -ENOMEM; } for_each_sg(sgl, sg, sgl_nents, i) { - iov[i].iov_len = sg->length; - iov[i].iov_base = kmap(sg_page(sg)) + sg->offset; - } + bvec[i].bv_page = sg_page(sg); + bvec[i].bv_len = sg->length; + bvec[i].bv_offset = sg->offset; - old_fs = get_fs(); - set_fs(get_ds()); + len += sg->length; + } + iov_iter_bvec(&iter, ITER_BVEC, bvec, sgl_nents, len); if (is_write) - ret = vfs_writev(fd, &iov[0], sgl_nents, &pos); + ret = vfs_iter_write(fd, &iter, &pos); else - ret = vfs_readv(fd, &iov[0], sgl_nents, &pos); - - set_fs(old_fs); - - for_each_sg(sgl, sg, sgl_nents, i) - kunmap(sg_page(sg)); + ret = vfs_iter_read(fd, &iter, &pos); - kfree(iov); + kfree(bvec); if (is_write) { if (ret < 0 || ret != cmd->data_length) { @@ -436,59 +425,17 @@ fd_execute_sync_cache(struct se_cmd *cmd) return 0; } -static unsigned char * -fd_setup_write_same_buf(struct se_cmd *cmd, struct scatterlist *sg, - unsigned int len) -{ - struct se_device *se_dev = cmd->se_dev; - unsigned int block_size = se_dev->dev_attrib.block_size; - unsigned int i = 0, end; - unsigned char *buf, *p, *kmap_buf; - - buf = kzalloc(min_t(unsigned int, len, PAGE_SIZE), GFP_KERNEL); - if (!buf) { - pr_err("Unable to allocate fd_execute_write_same buf\n"); - return NULL; - } - - kmap_buf = kmap(sg_page(sg)) + sg->offset; - if (!kmap_buf) { - pr_err("kmap() failed in fd_setup_write_same\n"); - kfree(buf); - return NULL; - } - /* - * Fill local *buf to contain multiple WRITE_SAME blocks up to - * min(len, PAGE_SIZE) - */ - p = buf; - end = min_t(unsigned int, len, PAGE_SIZE); - - while (i < end) { - memcpy(p, kmap_buf, block_size); - - i += block_size; - p += block_size; - } - kunmap(sg_page(sg)); - - return buf; -} - static sense_reason_t fd_execute_write_same(struct se_cmd *cmd) { struct se_device *se_dev = cmd->se_dev; struct fd_dev *fd_dev = FD_DEV(se_dev); - struct file *f = fd_dev->fd_file; - struct scatterlist *sg; - struct iovec *iov; - mm_segment_t old_fs; - sector_t nolb = sbc_get_write_same_sectors(cmd); loff_t pos = cmd->t_task_lba * se_dev->dev_attrib.block_size; - unsigned int len, len_tmp, iov_num; - int i, rc; - unsigned char *buf; + sector_t nolb = sbc_get_write_same_sectors(cmd); + struct iov_iter iter; + struct bio_vec *bvec; + unsigned int len = 0, i; + ssize_t ret; if (!nolb) { target_complete_cmd(cmd, SAM_STAT_GOOD); @@ -499,56 +446,92 @@ fd_execute_write_same(struct se_cmd *cmd) " backends not supported\n"); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } - sg = &cmd->t_data_sg[0]; if (cmd->t_data_nents > 1 || - sg->length != cmd->se_dev->dev_attrib.block_size) { + cmd->t_data_sg[0].length != cmd->se_dev->dev_attrib.block_size) { pr_err("WRITE_SAME: Illegal SGL t_data_nents: %u length: %u" - " block_size: %u\n", cmd->t_data_nents, sg->length, + " block_size: %u\n", + cmd->t_data_nents, + cmd->t_data_sg[0].length, cmd->se_dev->dev_attrib.block_size); return TCM_INVALID_CDB_FIELD; } - len = len_tmp = nolb * se_dev->dev_attrib.block_size; - iov_num = DIV_ROUND_UP(len, PAGE_SIZE); - - buf = fd_setup_write_same_buf(cmd, sg, len); - if (!buf) + bvec = kcalloc(nolb, sizeof(struct bio_vec), GFP_KERNEL); + if (!bvec) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - iov = vzalloc(sizeof(struct iovec) * iov_num); - if (!iov) { - pr_err("Unable to allocate fd_execute_write_same iovecs\n"); - kfree(buf); + for (i = 0; i < nolb; i++) { + bvec[i].bv_page = sg_page(&cmd->t_data_sg[0]); + bvec[i].bv_len = cmd->t_data_sg[0].length; + bvec[i].bv_offset = cmd->t_data_sg[0].offset; + + len += se_dev->dev_attrib.block_size; + } + + iov_iter_bvec(&iter, ITER_BVEC, bvec, nolb, len); + ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos); + + kfree(bvec); + if (ret < 0 || ret != len) { + pr_err("vfs_iter_write() returned %zd for write same\n", ret); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } - /* - * Map the single fabric received scatterlist block now populated - * in *buf into each iovec for I/O submission. - */ - for (i = 0; i < iov_num; i++) { - iov[i].iov_base = buf; - iov[i].iov_len = min_t(unsigned int, len_tmp, PAGE_SIZE); - len_tmp -= iov[i].iov_len; + + target_complete_cmd(cmd, SAM_STAT_GOOD); + return 0; +} + +static int +fd_do_prot_fill(struct se_device *se_dev, sector_t lba, sector_t nolb, + void *buf, size_t bufsize) +{ + struct fd_dev *fd_dev = FD_DEV(se_dev); + struct file *prot_fd = fd_dev->fd_prot_file; + sector_t prot_length, prot; + loff_t pos = lba * se_dev->prot_length; + + if (!prot_fd) { + pr_err("Unable to locate fd_dev->fd_prot_file\n"); + return -ENODEV; } - old_fs = get_fs(); - set_fs(get_ds()); - rc = vfs_writev(f, &iov[0], iov_num, &pos); - set_fs(old_fs); + prot_length = nolb * se_dev->prot_length; - vfree(iov); - kfree(buf); + for (prot = 0; prot < prot_length;) { + sector_t len = min_t(sector_t, bufsize, prot_length - prot); + ssize_t ret = kernel_write(prot_fd, buf, len, pos + prot); - if (rc < 0 || rc != len) { - pr_err("vfs_writev() returned %d for write same\n", rc); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + if (ret != len) { + pr_err("vfs_write to prot file failed: %zd\n", ret); + return ret < 0 ? ret : -ENODEV; + } + prot += ret; } - target_complete_cmd(cmd, SAM_STAT_GOOD); return 0; } +static int +fd_do_prot_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) +{ + void *buf; + int rc; + + buf = (void *)__get_free_page(GFP_KERNEL); + if (!buf) { + pr_err("Unable to allocate FILEIO prot buf\n"); + return -ENOMEM; + } + memset(buf, 0xff, PAGE_SIZE); + + rc = fd_do_prot_fill(cmd->se_dev, lba, nolb, buf, PAGE_SIZE); + + free_page((unsigned long)buf); + + return rc; +} + static sense_reason_t fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb) { @@ -556,6 +539,12 @@ fd_do_unmap(struct se_cmd *cmd, void *priv, sector_t lba, sector_t nolb) struct inode *inode = file->f_mapping->host; int ret; + if (cmd->se_dev->dev_attrib.pi_prot_type) { + ret = fd_do_prot_unmap(cmd, lba, nolb); + if (ret) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } + if (S_ISBLK(inode->i_mode)) { /* The backend is block device, use discard */ struct block_device *bdev = inode->i_bdev; @@ -595,7 +584,7 @@ fd_execute_write_same_unmap(struct se_cmd *cmd) struct file *file = fd_dev->fd_file; sector_t lba = cmd->t_task_lba; sector_t nolb = sbc_get_write_same_sectors(cmd); - int ret; + sense_reason_t ret; if (!nolb) { target_complete_cmd(cmd, SAM_STAT_GOOD); @@ -643,7 +632,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (data_direction == DMA_FROM_DEVICE) { memset(&fd_prot, 0, sizeof(struct fd_prot)); - if (cmd->prot_type) { + if (cmd->prot_type && dev->dev_attrib.pi_prot_type) { ret = fd_do_prot_rw(cmd, &fd_prot, false); if (ret < 0) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -651,23 +640,23 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, ret = fd_do_rw(cmd, sgl, sgl_nents, 0); - if (ret > 0 && cmd->prot_type) { + if (ret > 0 && cmd->prot_type && dev->dev_attrib.pi_prot_type) { u32 sectors = cmd->data_length / dev->dev_attrib.block_size; rc = sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors, 0, fd_prot.prot_sg, 0); if (rc) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return rc; } kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); } } else { memset(&fd_prot, 0, sizeof(struct fd_prot)); - if (cmd->prot_type) { + if (cmd->prot_type && dev->dev_attrib.pi_prot_type) { u32 sectors = cmd->data_length / dev->dev_attrib.block_size; ret = fd_do_prot_rw(cmd, &fd_prot, false); @@ -678,7 +667,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, 0, fd_prot.prot_sg, 0); if (rc) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return rc; } } @@ -705,7 +694,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, vfs_fsync_range(fd_dev->fd_file, start, end, 1); } - if (ret > 0 && cmd->prot_type) { + if (ret > 0 && cmd->prot_type && dev->dev_attrib.pi_prot_type) { ret = fd_do_prot_rw(cmd, &fd_prot, true); if (ret < 0) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -714,7 +703,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (ret < 0) { kfree(fd_prot.prot_sg); - vfree(fd_prot.prot_buf); + kfree(fd_prot.prot_buf); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } @@ -878,48 +867,28 @@ static int fd_init_prot(struct se_device *dev) static int fd_format_prot(struct se_device *dev) { - struct fd_dev *fd_dev = FD_DEV(dev); - struct file *prot_fd = fd_dev->fd_prot_file; - sector_t prot_length, prot; unsigned char *buf; - loff_t pos = 0; int unit_size = FDBD_FORMAT_UNIT_SIZE * dev->dev_attrib.block_size; - int rc, ret = 0, size, len; + int ret; if (!dev->dev_attrib.pi_prot_type) { pr_err("Unable to format_prot while pi_prot_type == 0\n"); return -ENODEV; } - if (!prot_fd) { - pr_err("Unable to locate fd_dev->fd_prot_file\n"); - return -ENODEV; - } buf = vzalloc(unit_size); if (!buf) { pr_err("Unable to allocate FILEIO prot buf\n"); return -ENOMEM; } - prot_length = (dev->transport->get_blocks(dev) + 1) * dev->prot_length; - size = prot_length; pr_debug("Using FILEIO prot_length: %llu\n", - (unsigned long long)prot_length); + (unsigned long long)(dev->transport->get_blocks(dev) + 1) * + dev->prot_length); memset(buf, 0xff, unit_size); - for (prot = 0; prot < prot_length; prot += unit_size) { - len = min(unit_size, size); - rc = kernel_write(prot_fd, buf, len, pos); - if (rc != len) { - pr_err("vfs_write to prot file failed: %d\n", rc); - ret = -ENODEV; - goto out; - } - pos += len; - size -= len; - } - -out: + ret = fd_do_prot_fill(dev, 0, dev->transport->get_blocks(dev) + 1, + buf, unit_size); vfree(buf); return ret; } diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index d4a4b0fb444a..1b7947c2510f 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -444,7 +444,7 @@ iblock_execute_write_same_unmap(struct se_cmd *cmd) struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd; sector_t lba = cmd->t_task_lba; sector_t nolb = sbc_get_write_same_sectors(cmd); - int ret; + sense_reason_t ret; ret = iblock_do_unmap(cmd, bdev, lba, nolb); if (ret) @@ -774,7 +774,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, sg_num--; } - if (cmd->prot_type) { + if (cmd->prot_type && dev->dev_attrib.pi_prot_type) { int rc = iblock_alloc_bip(cmd, bio_start); if (rc) goto fail_put_bios; diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 60381db90026..874a9bc988d8 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -4,7 +4,13 @@ /* target_core_alua.c */ extern struct t10_alua_lu_gp *default_lu_gp; +/* target_core_configfs.c */ +extern struct configfs_subsystem *target_core_subsystem[]; + /* target_core_device.c */ +extern struct mutex g_device_mutex; +extern struct list_head g_device_list; + struct se_dev_entry *core_get_se_deve_from_rtpi(struct se_node_acl *, u16); int core_free_device_list_for_node(struct se_node_acl *, struct se_portal_group *); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 2de6fb8cee8d..c1aa9655e96e 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -78,6 +78,22 @@ enum preempt_type { static void __core_scsi3_complete_pro_release(struct se_device *, struct se_node_acl *, struct t10_pr_registration *, int, int); +static int is_reservation_holder( + struct t10_pr_registration *pr_res_holder, + struct t10_pr_registration *pr_reg) +{ + int pr_res_type; + + if (pr_res_holder) { + pr_res_type = pr_res_holder->pr_res_type; + + return pr_res_holder == pr_reg || + pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG || + pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG; + } + return 0; +} + static sense_reason_t target_scsi2_reservation_check(struct se_cmd *cmd) { @@ -664,7 +680,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration( struct se_dev_entry *deve_tmp; struct se_node_acl *nacl_tmp; struct se_port *port, *port_tmp; - struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; + const struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; struct t10_pr_registration *pr_reg, *pr_reg_atp, *pr_reg_tmp, *pr_reg_tmp_safe; int ret; /* @@ -963,7 +979,7 @@ int core_scsi3_check_aptpl_registration( } static void __core_scsi3_dump_registration( - struct target_core_fabric_ops *tfo, + const struct target_core_fabric_ops *tfo, struct se_device *dev, struct se_node_acl *nacl, struct t10_pr_registration *pr_reg, @@ -1004,7 +1020,7 @@ static void __core_scsi3_add_registration( enum register_type register_type, int register_move) { - struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; + const struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; struct t10_pr_registration *pr_reg_tmp, *pr_reg_tmp_safe; struct t10_reservation *pr_tmpl = &dev->t10_pr; @@ -1220,8 +1236,10 @@ static void __core_scsi3_free_registration( struct t10_pr_registration *pr_reg, struct list_head *preempt_and_abort_list, int dec_holders) + __releases(&pr_tmpl->registration_lock) + __acquires(&pr_tmpl->registration_lock) { - struct target_core_fabric_ops *tfo = + const struct target_core_fabric_ops *tfo = pr_reg->pr_reg_nacl->se_tpg->se_tpg_tfo; struct t10_reservation *pr_tmpl = &dev->t10_pr; char i_buf[PR_REG_ISID_ID_LEN]; @@ -1445,7 +1463,7 @@ core_scsi3_decode_spec_i_port( struct t10_pr_registration *pr_reg_tmp, *pr_reg_tmp_safe; LIST_HEAD(tid_dest_list); struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp; - struct target_core_fabric_ops *tmp_tf_ops; + const struct target_core_fabric_ops *tmp_tf_ops; unsigned char *buf; unsigned char *ptr, *i_str = NULL, proto_ident, tmp_proto_ident; char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN]; @@ -2287,7 +2305,6 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; if (pr_res_holder) { - int pr_res_type = pr_res_holder->pr_res_type; /* * From spc4r17 Section 5.7.9: Reserving: * @@ -2298,9 +2315,7 @@ core_scsi3_pro_reserve(struct se_cmd *cmd, int type, int scope, u64 res_key) * the logical unit, then the command shall be completed with * RESERVATION CONFLICT status. */ - if ((pr_res_holder != pr_reg) && - (pr_res_type != PR_TYPE_WRITE_EXCLUSIVE_ALLREG) && - (pr_res_type != PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) { + if (!is_reservation_holder(pr_res_holder, pr_reg)) { struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl; pr_err("SPC-3 PR: Attempted RESERVE from" " [%s]: %s while reservation already held by" @@ -2409,7 +2424,7 @@ static void __core_scsi3_complete_pro_release( int explicit, int unreg) { - struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo; + const struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo; char i_buf[PR_REG_ISID_ID_LEN]; int pr_res_type = 0, pr_res_scope = 0; @@ -2477,7 +2492,6 @@ core_scsi3_emulate_pro_release(struct se_cmd *cmd, int type, int scope, struct se_lun *se_lun = cmd->se_lun; struct t10_pr_registration *pr_reg, *pr_reg_p, *pr_res_holder; struct t10_reservation *pr_tmpl = &dev->t10_pr; - int all_reg = 0; sense_reason_t ret = 0; if (!se_sess || !se_lun) { @@ -2514,13 +2528,9 @@ core_scsi3_emulate_pro_release(struct se_cmd *cmd, int type, int scope, spin_unlock(&dev->dev_reservation_lock); goto out_put_pr_reg; } - if ((pr_res_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) || - (pr_res_holder->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) - all_reg = 1; - if ((all_reg == 0) && (pr_res_holder != pr_reg)) { + if (!is_reservation_holder(pr_res_holder, pr_reg)) { /* - * Non 'All Registrants' PR Type cases.. * Release request from a registered I_T nexus that is not a * persistent reservation holder. return GOOD status. */ @@ -2726,7 +2736,7 @@ static void __core_scsi3_complete_pro_preempt( enum preempt_type preempt_type) { struct se_node_acl *nacl = pr_reg->pr_reg_nacl; - struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; + const struct target_core_fabric_ops *tfo = nacl->se_tpg->se_tpg_tfo; char i_buf[PR_REG_ISID_ID_LEN]; memset(i_buf, 0, PR_REG_ISID_ID_LEN); @@ -3111,7 +3121,7 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key, struct se_node_acl *pr_res_nacl, *pr_reg_nacl, *dest_node_acl = NULL; struct se_port *se_port; struct se_portal_group *se_tpg, *dest_se_tpg = NULL; - struct target_core_fabric_ops *dest_tf_ops = NULL, *tf_ops; + const struct target_core_fabric_ops *dest_tf_ops = NULL, *tf_ops; struct t10_pr_registration *pr_reg, *pr_res_holder, *dest_pr_reg; struct t10_reservation *pr_tmpl = &dev->t10_pr; unsigned char *buf; @@ -3375,7 +3385,7 @@ after_iport_check: * From spc4r17 section 5.7.8 Table 50 -- * Register behaviors for a REGISTER AND MOVE service action */ - if (pr_res_holder != pr_reg) { + if (!is_reservation_holder(pr_res_holder, pr_reg)) { pr_warn("SPC-3 PR REGISTER_AND_MOVE: Calling I_T" " Nexus is not reservation holder\n"); spin_unlock(&dev->dev_reservation_lock); diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 98e83ac5661b..a263bf5fab8d 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -139,10 +139,22 @@ static int rd_allocate_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table * unsigned char *p; while (total_sg_needed) { + unsigned int chain_entry = 0; + sg_per_table = (total_sg_needed > max_sg_per_table) ? max_sg_per_table : total_sg_needed; - sg = kzalloc(sg_per_table * sizeof(struct scatterlist), +#ifdef CONFIG_ARCH_HAS_SG_CHAIN + + /* + * Reserve extra element for chain entry + */ + if (sg_per_table < total_sg_needed) + chain_entry = 1; + +#endif /* CONFIG_ARCH_HAS_SG_CHAIN */ + + sg = kcalloc(sg_per_table + chain_entry, sizeof(*sg), GFP_KERNEL); if (!sg) { pr_err("Unable to allocate scatterlist array" @@ -150,7 +162,16 @@ static int rd_allocate_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table * return -ENOMEM; } - sg_init_table(sg, sg_per_table); + sg_init_table(sg, sg_per_table + chain_entry); + +#ifdef CONFIG_ARCH_HAS_SG_CHAIN + + if (i > 0) { + sg_chain(sg_table[i - 1].sg_table, + max_sg_per_table + 1, sg); + } + +#endif /* CONFIG_ARCH_HAS_SG_CHAIN */ sg_table[i].sg_table = sg; sg_table[i].rd_sg_count = sg_per_table; @@ -382,6 +403,76 @@ static struct rd_dev_sg_table *rd_get_prot_table(struct rd_dev *rd_dev, u32 page return NULL; } +typedef sense_reason_t (*dif_verify)(struct se_cmd *, sector_t, unsigned int, + unsigned int, struct scatterlist *, int); + +static sense_reason_t rd_do_prot_rw(struct se_cmd *cmd, dif_verify dif_verify) +{ + struct se_device *se_dev = cmd->se_dev; + struct rd_dev *dev = RD_DEV(se_dev); + struct rd_dev_sg_table *prot_table; + bool need_to_release = false; + struct scatterlist *prot_sg; + u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size; + u32 prot_offset, prot_page; + u32 prot_npages __maybe_unused; + u64 tmp; + sense_reason_t rc = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + + tmp = cmd->t_task_lba * se_dev->prot_length; + prot_offset = do_div(tmp, PAGE_SIZE); + prot_page = tmp; + + prot_table = rd_get_prot_table(dev, prot_page); + if (!prot_table) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + + prot_sg = &prot_table->sg_table[prot_page - + prot_table->page_start_offset]; + +#ifndef CONFIG_ARCH_HAS_SG_CHAIN + + prot_npages = DIV_ROUND_UP(prot_offset + sectors * se_dev->prot_length, + PAGE_SIZE); + + /* + * Allocate temporaly contiguous scatterlist entries if prot pages + * straddles multiple scatterlist tables. + */ + if (prot_table->page_end_offset < prot_page + prot_npages - 1) { + int i; + + prot_sg = kcalloc(prot_npages, sizeof(*prot_sg), GFP_KERNEL); + if (!prot_sg) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + + need_to_release = true; + sg_init_table(prot_sg, prot_npages); + + for (i = 0; i < prot_npages; i++) { + if (prot_page + i > prot_table->page_end_offset) { + prot_table = rd_get_prot_table(dev, + prot_page + i); + if (!prot_table) { + kfree(prot_sg); + return rc; + } + sg_unmark_end(&prot_sg[i - 1]); + } + prot_sg[i] = prot_table->sg_table[prot_page + i - + prot_table->page_start_offset]; + } + } + +#endif /* !CONFIG_ARCH_HAS_SG_CHAIN */ + + rc = dif_verify(cmd, cmd->t_task_lba, sectors, 0, prot_sg, prot_offset); + if (need_to_release) + kfree(prot_sg); + + return rc; +} + static sense_reason_t rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, enum dma_data_direction data_direction) @@ -419,24 +510,9 @@ rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, data_direction == DMA_FROM_DEVICE ? "Read" : "Write", cmd->t_task_lba, rd_size, rd_page, rd_offset); - if (cmd->prot_type && data_direction == DMA_TO_DEVICE) { - struct rd_dev_sg_table *prot_table; - struct scatterlist *prot_sg; - u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size; - u32 prot_offset, prot_page; - - tmp = cmd->t_task_lba * se_dev->prot_length; - prot_offset = do_div(tmp, PAGE_SIZE); - prot_page = tmp; - - prot_table = rd_get_prot_table(dev, prot_page); - if (!prot_table) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - - prot_sg = &prot_table->sg_table[prot_page - prot_table->page_start_offset]; - - rc = sbc_dif_verify_write(cmd, cmd->t_task_lba, sectors, 0, - prot_sg, prot_offset); + if (cmd->prot_type && se_dev->dev_attrib.pi_prot_type && + data_direction == DMA_TO_DEVICE) { + rc = rd_do_prot_rw(cmd, sbc_dif_verify_write); if (rc) return rc; } @@ -502,24 +578,9 @@ rd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, } sg_miter_stop(&m); - if (cmd->prot_type && data_direction == DMA_FROM_DEVICE) { - struct rd_dev_sg_table *prot_table; - struct scatterlist *prot_sg; - u32 sectors = cmd->data_length / se_dev->dev_attrib.block_size; - u32 prot_offset, prot_page; - - tmp = cmd->t_task_lba * se_dev->prot_length; - prot_offset = do_div(tmp, PAGE_SIZE); - prot_page = tmp; - - prot_table = rd_get_prot_table(dev, prot_page); - if (!prot_table) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - - prot_sg = &prot_table->sg_table[prot_page - prot_table->page_start_offset]; - - rc = sbc_dif_verify_read(cmd, cmd->t_task_lba, sectors, 0, - prot_sg, prot_offset); + if (cmd->prot_type && se_dev->dev_attrib.pi_prot_type && + data_direction == DMA_FROM_DEVICE) { + rc = rd_do_prot_rw(cmd, sbc_dif_verify_read); if (rc) return rc; } diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 3e7297411110..8855781ac653 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -93,6 +93,8 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct se_session *sess = cmd->se_sess; + int pi_prot_type = dev->dev_attrib.pi_prot_type; + unsigned char *rbuf; unsigned char buf[32]; unsigned long long blocks = dev->transport->get_blocks(dev); @@ -114,8 +116,15 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) * Set P_TYPE and PROT_EN bits for DIF support */ if (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) { - if (dev->dev_attrib.pi_prot_type) - buf[12] = (dev->dev_attrib.pi_prot_type - 1) << 1 | 0x1; + /* + * Only override a device's pi_prot_type if no T10-PI is + * available, and sess_prot_type has been explicitly enabled. + */ + if (!pi_prot_type) + pi_prot_type = sess->sess_prot_type; + + if (pi_prot_type) + buf[12] = (pi_prot_type - 1) << 1 | 0x1; } if (dev->transport->get_lbppbe) @@ -312,7 +321,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o return 0; } -static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd) +static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success) { unsigned char *buf, *addr; struct scatterlist *sg; @@ -376,7 +385,7 @@ sbc_execute_rw(struct se_cmd *cmd) cmd->data_direction); } -static sense_reason_t compare_and_write_post(struct se_cmd *cmd) +static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success) { struct se_device *dev = cmd->se_dev; @@ -399,7 +408,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd) return TCM_NO_SENSE; } -static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) +static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success) { struct se_device *dev = cmd->se_dev; struct scatterlist *write_sg = NULL, *sg; @@ -414,11 +423,16 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd) /* * Handle early failure in transport_generic_request_failure(), - * which will not have taken ->caw_mutex yet.. + * which will not have taken ->caw_sem yet.. */ - if (!cmd->t_data_sg || !cmd->t_bidi_data_sg) + if (!success && (!cmd->t_data_sg || !cmd->t_bidi_data_sg)) return TCM_NO_SENSE; /* + * Handle special case for zero-length COMPARE_AND_WRITE + */ + if (!cmd->data_length) + goto out; + /* * Immediately exit + release dev->caw_sem if command has already * been failed with a non-zero SCSI status. */ @@ -581,12 +595,13 @@ sbc_compare_and_write(struct se_cmd *cmd) } static int -sbc_set_prot_op_checks(u8 protect, enum target_prot_type prot_type, +sbc_set_prot_op_checks(u8 protect, bool fabric_prot, enum target_prot_type prot_type, bool is_write, struct se_cmd *cmd) { if (is_write) { - cmd->prot_op = protect ? TARGET_PROT_DOUT_PASS : - TARGET_PROT_DOUT_INSERT; + cmd->prot_op = fabric_prot ? TARGET_PROT_DOUT_STRIP : + protect ? TARGET_PROT_DOUT_PASS : + TARGET_PROT_DOUT_INSERT; switch (protect) { case 0x0: case 0x3: @@ -610,8 +625,9 @@ sbc_set_prot_op_checks(u8 protect, enum target_prot_type prot_type, return -EINVAL; } } else { - cmd->prot_op = protect ? TARGET_PROT_DIN_PASS : - TARGET_PROT_DIN_STRIP; + cmd->prot_op = fabric_prot ? TARGET_PROT_DIN_INSERT : + protect ? TARGET_PROT_DIN_PASS : + TARGET_PROT_DIN_STRIP; switch (protect) { case 0x0: case 0x1: @@ -644,11 +660,15 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, u32 sectors, bool is_write) { u8 protect = cdb[1] >> 5; + int sp_ops = cmd->se_sess->sup_prot_ops; + int pi_prot_type = dev->dev_attrib.pi_prot_type; + bool fabric_prot = false; if (!cmd->t_prot_sg || !cmd->t_prot_nents) { - if (protect && !dev->dev_attrib.pi_prot_type) { - pr_err("CDB contains protect bit, but device does not" - " advertise PROTECT=1 feature bit\n"); + if (unlikely(protect && + !dev->dev_attrib.pi_prot_type && !cmd->se_sess->sess_prot_type)) { + pr_err("CDB contains protect bit, but device + fabric does" + " not advertise PROTECT=1 feature bit\n"); return TCM_INVALID_CDB_FIELD; } if (cmd->prot_pto) @@ -669,15 +689,32 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb, cmd->reftag_seed = cmd->t_task_lba; break; case TARGET_DIF_TYPE0_PROT: + /* + * See if the fabric supports T10-PI, and the session has been + * configured to allow export PROTECT=1 feature bit with backend + * devices that don't support T10-PI. + */ + fabric_prot = is_write ? + !!(sp_ops & (TARGET_PROT_DOUT_PASS | TARGET_PROT_DOUT_STRIP)) : + !!(sp_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DIN_INSERT)); + + if (fabric_prot && cmd->se_sess->sess_prot_type) { + pi_prot_type = cmd->se_sess->sess_prot_type; + break; + } + if (!protect) + return TCM_NO_SENSE; + /* Fallthrough */ default: - return TCM_NO_SENSE; + pr_err("Unable to determine pi_prot_type for CDB: 0x%02x " + "PROTECT: 0x%02x\n", cdb[0], protect); + return TCM_INVALID_CDB_FIELD; } - if (sbc_set_prot_op_checks(protect, dev->dev_attrib.pi_prot_type, - is_write, cmd)) + if (sbc_set_prot_op_checks(protect, fabric_prot, pi_prot_type, is_write, cmd)) return TCM_INVALID_CDB_FIELD; - cmd->prot_type = dev->dev_attrib.pi_prot_type; + cmd->prot_type = pi_prot_type; cmd->prot_length = dev->prot_length * sectors; /** @@ -1166,14 +1203,16 @@ sbc_dif_generate(struct se_cmd *cmd) sdt = paddr + offset; sdt->guard_tag = cpu_to_be16(crc_t10dif(daddr + j, dev->dev_attrib.block_size)); - if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT) + if (cmd->prot_type == TARGET_DIF_TYPE1_PROT) sdt->ref_tag = cpu_to_be32(sector & 0xffffffff); sdt->app_tag = 0; - pr_debug("DIF WRITE INSERT sector: %llu guard_tag: 0x%04x" + pr_debug("DIF %s INSERT sector: %llu guard_tag: 0x%04x" " app_tag: 0x%04x ref_tag: %u\n", - (unsigned long long)sector, sdt->guard_tag, - sdt->app_tag, be32_to_cpu(sdt->ref_tag)); + (cmd->data_direction == DMA_TO_DEVICE) ? + "WRITE" : "READ", (unsigned long long)sector, + sdt->guard_tag, sdt->app_tag, + be32_to_cpu(sdt->ref_tag)); sector++; offset += sizeof(struct se_dif_v1_tuple); @@ -1185,12 +1224,16 @@ sbc_dif_generate(struct se_cmd *cmd) } static sense_reason_t -sbc_dif_v1_verify(struct se_device *dev, struct se_dif_v1_tuple *sdt, +sbc_dif_v1_verify(struct se_cmd *cmd, struct se_dif_v1_tuple *sdt, const void *p, sector_t sector, unsigned int ei_lba) { + struct se_device *dev = cmd->se_dev; int block_size = dev->dev_attrib.block_size; __be16 csum; + if (!(cmd->prot_checks & TARGET_DIF_CHECK_GUARD)) + goto check_ref; + csum = cpu_to_be16(crc_t10dif(p, block_size)); if (sdt->guard_tag != csum) { @@ -1200,7 +1243,11 @@ sbc_dif_v1_verify(struct se_device *dev, struct se_dif_v1_tuple *sdt, return TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED; } - if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT && +check_ref: + if (!(cmd->prot_checks & TARGET_DIF_CHECK_REFTAG)) + return 0; + + if (cmd->prot_type == TARGET_DIF_TYPE1_PROT && be32_to_cpu(sdt->ref_tag) != (sector & 0xffffffff)) { pr_err("DIFv1 Type 1 reference failed on sector: %llu tag: 0x%08x" " sector MSB: 0x%08x\n", (unsigned long long)sector, @@ -1208,7 +1255,7 @@ sbc_dif_v1_verify(struct se_device *dev, struct se_dif_v1_tuple *sdt, return TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED; } - if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE2_PROT && + if (cmd->prot_type == TARGET_DIF_TYPE2_PROT && be32_to_cpu(sdt->ref_tag) != ei_lba) { pr_err("DIFv1 Type 2 reference failed on sector: %llu tag: 0x%08x" " ei_lba: 0x%08x\n", (unsigned long long)sector, @@ -1229,6 +1276,9 @@ sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read, unsigned int i, len, left; unsigned int offset = sg_off; + if (!sg) + return; + left = sectors * dev->prot_length; for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) { @@ -1292,7 +1342,7 @@ sbc_dif_verify_write(struct se_cmd *cmd, sector_t start, unsigned int sectors, (unsigned long long)sector, sdt->guard_tag, sdt->app_tag, be32_to_cpu(sdt->ref_tag)); - rc = sbc_dif_v1_verify(dev, sdt, daddr + j, sector, + rc = sbc_dif_v1_verify(cmd, sdt, daddr + j, sector, ei_lba); if (rc) { kunmap_atomic(paddr); @@ -1309,6 +1359,9 @@ sbc_dif_verify_write(struct se_cmd *cmd, sector_t start, unsigned int sectors, kunmap_atomic(paddr); kunmap_atomic(daddr); } + if (!sg) + return 0; + sbc_dif_copy_prot(cmd, sectors, false, sg, sg_off); return 0; @@ -1353,7 +1406,7 @@ __sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors, continue; } - rc = sbc_dif_v1_verify(dev, sdt, daddr + j, sector, + rc = sbc_dif_v1_verify(cmd, sdt, daddr + j, sector, ei_lba); if (rc) { kunmap_atomic(paddr); diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 6c8bd6bc175c..7912aa124385 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -103,10 +103,12 @@ spc_emulate_inquiry_std(struct se_cmd *cmd, unsigned char *buf) buf[5] |= 0x8; /* * Set Protection (PROTECT) bit when DIF has been enabled on the - * device, and the transport supports VERIFY + PASS. + * device, and the fabric supports VERIFY + PASS. Also report + * PROTECT=1 if sess_prot_type has been configured to allow T10-PI + * to unprotected devices. */ if (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) { - if (dev->dev_attrib.pi_prot_type) + if (dev->dev_attrib.pi_prot_type || cmd->se_sess->sess_prot_type) buf[5] |= 0x1; } @@ -467,9 +469,11 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) * only for TYPE3 protection. */ if (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) { - if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT) + if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE1_PROT || + cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE1_PROT) buf[4] = 0x5; - else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT) + else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT || + cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT) buf[4] = 0x4; } @@ -861,7 +865,7 @@ static int spc_modesense_control(struct se_cmd *cmd, u8 pc, u8 *p) * TAG field. */ if (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) { - if (dev->dev_attrib.pi_prot_type) + if (dev->dev_attrib.pi_prot_type || sess->sess_prot_type) p[5] |= 0x80; } @@ -1099,7 +1103,7 @@ static sense_reason_t spc_emulate_modeselect(struct se_cmd *cmd) unsigned char *buf; unsigned char tbuf[SE_MODE_PAGE_BUF]; int length; - int ret = 0; + sense_reason_t ret = 0; int i; if (!cmd->data_length) { diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index fa5e157db47b..315ec3458eeb 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -125,8 +125,8 @@ void core_tmr_abort_task( if (dev != se_cmd->se_dev) continue; - /* skip se_cmd associated with tmr */ - if (tmr->task_cmd == se_cmd) + /* skip task management functions, including tmr->task_cmd */ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) continue; ref_tag = se_cmd->se_tfo->get_task_tag(se_cmd); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 0696de9553d3..47f064415bf6 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -672,7 +672,7 @@ static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg) } int core_tpg_register( - struct target_core_fabric_ops *tfo, + const struct target_core_fabric_ops *tfo, struct se_wwn *se_wwn, struct se_portal_group *se_tpg, void *tpg_fabric_ptr, diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ac3cbabdbdf0..3fe5cb240b6f 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -322,6 +322,7 @@ void __transport_register_session( struct se_session *se_sess, void *fabric_sess_ptr) { + const struct target_core_fabric_ops *tfo = se_tpg->se_tpg_tfo; unsigned char buf[PR_REG_ISID_LEN]; se_sess->se_tpg = se_tpg; @@ -334,6 +335,21 @@ void __transport_register_session( */ if (se_nacl) { /* + * + * Determine if fabric allows for T10-PI feature bits exposed to + * initiators for device backends with !dev->dev_attrib.pi_prot_type. + * + * If so, then always save prot_type on a per se_node_acl node + * basis and re-instate the previous sess_prot_type to avoid + * disabling PI from below any previously initiator side + * registered LUNs. + */ + if (se_nacl->saved_prot_type) + se_sess->sess_prot_type = se_nacl->saved_prot_type; + else if (tfo->tpg_check_prot_fabric_only) + se_sess->sess_prot_type = se_nacl->saved_prot_type = + tfo->tpg_check_prot_fabric_only(se_tpg); + /* * If the fabric module supports an ISID based TransportID, * save this value in binary from the fabric I_T Nexus now. */ @@ -404,6 +420,30 @@ void target_put_session(struct se_session *se_sess) } EXPORT_SYMBOL(target_put_session); +ssize_t target_show_dynamic_sessions(struct se_portal_group *se_tpg, char *page) +{ + struct se_session *se_sess; + ssize_t len = 0; + + spin_lock_bh(&se_tpg->session_lock); + list_for_each_entry(se_sess, &se_tpg->tpg_sess_list, sess_list) { + if (!se_sess->se_node_acl) + continue; + if (!se_sess->se_node_acl->dynamic_node_acl) + continue; + if (strlen(se_sess->se_node_acl->initiatorname) + 1 + len > PAGE_SIZE) + break; + + len += snprintf(page + len, PAGE_SIZE - len, "%s\n", + se_sess->se_node_acl->initiatorname); + len += 1; /* Include NULL terminator */ + } + spin_unlock_bh(&se_tpg->session_lock); + + return len; +} +EXPORT_SYMBOL(target_show_dynamic_sessions); + static void target_complete_nacl(struct kref *kref) { struct se_node_acl *nacl = container_of(kref, @@ -462,7 +502,7 @@ EXPORT_SYMBOL(transport_free_session); void transport_deregister_session(struct se_session *se_sess) { struct se_portal_group *se_tpg = se_sess->se_tpg; - struct target_core_fabric_ops *se_tfo; + const struct target_core_fabric_ops *se_tfo; struct se_node_acl *se_nacl; unsigned long flags; bool comp_nacl = true; @@ -1118,7 +1158,7 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size) */ void transport_init_se_cmd( struct se_cmd *cmd, - struct target_core_fabric_ops *tfo, + const struct target_core_fabric_ops *tfo, struct se_session *se_sess, u32 data_length, int data_direction, @@ -1570,6 +1610,8 @@ EXPORT_SYMBOL(target_submit_tmr); * has completed. */ bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags) + __releases(&cmd->t_state_lock) + __acquires(&cmd->t_state_lock) { bool was_active = false; @@ -1615,11 +1657,11 @@ void transport_generic_request_failure(struct se_cmd *cmd, transport_complete_task_attr(cmd); /* * Handle special case for COMPARE_AND_WRITE failure, where the - * callback is expected to drop the per device ->caw_mutex. + * callback is expected to drop the per device ->caw_sem. */ if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && cmd->transport_complete_callback) - cmd->transport_complete_callback(cmd); + cmd->transport_complete_callback(cmd, false); switch (sense_reason) { case TCM_NON_EXISTENT_LUN: @@ -1706,6 +1748,41 @@ void __target_execute_cmd(struct se_cmd *cmd) } } +static int target_write_prot_action(struct se_cmd *cmd) +{ + u32 sectors; + /* + * Perform WRITE_INSERT of PI using software emulation when backend + * device has PI enabled, if the transport has not already generated + * PI using hardware WRITE_INSERT offload. + */ + switch (cmd->prot_op) { + case TARGET_PROT_DOUT_INSERT: + if (!(cmd->se_sess->sup_prot_ops & TARGET_PROT_DOUT_INSERT)) + sbc_dif_generate(cmd); + break; + case TARGET_PROT_DOUT_STRIP: + if (cmd->se_sess->sup_prot_ops & TARGET_PROT_DOUT_STRIP) + break; + + sectors = cmd->data_length >> ilog2(cmd->se_dev->dev_attrib.block_size); + cmd->pi_err = sbc_dif_verify_write(cmd, cmd->t_task_lba, + sectors, 0, NULL, 0); + if (unlikely(cmd->pi_err)) { + spin_lock_irq(&cmd->t_state_lock); + cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT; + spin_unlock_irq(&cmd->t_state_lock); + transport_generic_request_failure(cmd, cmd->pi_err); + return -1; + } + break; + default: + break; + } + + return 0; +} + static bool target_handle_task_attr(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1785,15 +1862,9 @@ 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; spin_unlock_irq(&cmd->t_state_lock); - /* - * Perform WRITE_INSERT of PI using software emulation when backend - * device has PI enabled, if the transport has not already generated - * PI using hardware WRITE_INSERT offload. - */ - if (cmd->prot_op == TARGET_PROT_DOUT_INSERT) { - if (!(cmd->se_sess->sup_prot_ops & TARGET_PROT_DOUT_INSERT)) - sbc_dif_generate(cmd); - } + + if (target_write_prot_action(cmd)) + return; if (target_handle_task_attr(cmd)) { spin_lock_irq(&cmd->t_state_lock); @@ -1919,16 +1990,28 @@ static void transport_handle_queue_full( schedule_work(&cmd->se_dev->qf_work_queue); } -static bool target_check_read_strip(struct se_cmd *cmd) +static bool target_read_prot_action(struct se_cmd *cmd) { sense_reason_t rc; - if (!(cmd->se_sess->sup_prot_ops & TARGET_PROT_DIN_STRIP)) { - rc = sbc_dif_read_strip(cmd); - if (rc) { - cmd->pi_err = rc; - return true; + switch (cmd->prot_op) { + case TARGET_PROT_DIN_STRIP: + if (!(cmd->se_sess->sup_prot_ops & TARGET_PROT_DIN_STRIP)) { + rc = sbc_dif_read_strip(cmd); + if (rc) { + cmd->pi_err = rc; + return true; + } } + break; + case TARGET_PROT_DIN_INSERT: + if (cmd->se_sess->sup_prot_ops & TARGET_PROT_DIN_INSERT) + break; + + sbc_dif_generate(cmd); + break; + default: + break; } return false; @@ -1975,8 +2058,12 @@ static void target_complete_ok_work(struct work_struct *work) if (cmd->transport_complete_callback) { sense_reason_t rc; - rc = cmd->transport_complete_callback(cmd); + rc = cmd->transport_complete_callback(cmd, true); if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) { + if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && + !cmd->data_length) + goto queue_rsp; + return; } else if (rc) { ret = transport_send_check_condition_and_sense(cmd, @@ -1990,6 +2077,7 @@ static void target_complete_ok_work(struct work_struct *work) } } +queue_rsp: switch (cmd->data_direction) { case DMA_FROM_DEVICE: spin_lock(&cmd->se_lun->lun_sep_lock); @@ -2003,8 +2091,7 @@ static void target_complete_ok_work(struct work_struct *work) * backend had PI enabled, if the transport will not be * performing hardware READ_STRIP offload. */ - if (cmd->prot_op == TARGET_PROT_DIN_STRIP && - target_check_read_strip(cmd)) { + if (target_read_prot_action(cmd)) { ret = transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0); if (ret == -EAGAIN || ret == -ENOMEM) @@ -2094,6 +2181,16 @@ static inline void transport_reset_sgl_orig(struct se_cmd *cmd) static inline void transport_free_pages(struct se_cmd *cmd) { if (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) { + /* + * Release special case READ buffer payload required for + * SG_TO_MEM_NOALLOC to function with COMPARE_AND_WRITE + */ + if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) { + transport_free_sgl(cmd->t_bidi_data_sg, + cmd->t_bidi_data_nents); + cmd->t_bidi_data_sg = NULL; + cmd->t_bidi_data_nents = 0; + } transport_reset_sgl_orig(cmd); return; } @@ -2246,6 +2343,7 @@ sense_reason_t transport_generic_new_cmd(struct se_cmd *cmd) { int ret = 0; + bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); /* * Determine is the TCM fabric module has already allocated physical @@ -2254,7 +2352,6 @@ transport_generic_new_cmd(struct se_cmd *cmd) */ if (!(cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC) && cmd->data_length) { - bool zero_flag = !(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB); if ((cmd->se_cmd_flags & SCF_BIDI) || (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE)) { @@ -2285,6 +2382,20 @@ transport_generic_new_cmd(struct se_cmd *cmd) cmd->data_length, zero_flag); if (ret < 0) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + } else if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) && + cmd->data_length) { + /* + * Special case for COMPARE_AND_WRITE with fabrics + * using SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC. + */ + u32 caw_length = cmd->t_task_nolb * + cmd->se_dev->dev_attrib.block_size; + + ret = target_alloc_sgl(&cmd->t_bidi_data_sg, + &cmd->t_bidi_data_nents, + caw_length, zero_flag); + if (ret < 0) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } /* * If this command is not a write we can execute it right here, @@ -2376,10 +2487,8 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, * fabric acknowledgement that requires two target_put_sess_cmd() * invocations before se_cmd descriptor release. */ - if (ack_kref) { + if (ack_kref) kref_get(&se_cmd->cmd_kref); - se_cmd->se_cmd_flags |= SCF_ACK_KREF; - } spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); if (se_sess->sess_tearing_down) { @@ -2398,6 +2507,7 @@ out: EXPORT_SYMBOL(target_get_sess_cmd); static void target_release_cmd_kref(struct kref *kref) + __releases(&se_cmd->se_sess->sess_cmd_lock) { struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref); struct se_session *se_sess = se_cmd->se_sess; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 1a1bcf71ec9d..dbc872a6c981 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -344,8 +344,11 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) entry = (void *) mb + CMDR_OFF + cmd_head; tcmu_flush_dcache_range(entry, sizeof(*entry)); - tcmu_hdr_set_op(&entry->hdr, TCMU_OP_PAD); - tcmu_hdr_set_len(&entry->hdr, pad_size); + tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_PAD); + tcmu_hdr_set_len(&entry->hdr.len_op, pad_size); + entry->hdr.cmd_id = 0; /* not used for PAD */ + entry->hdr.kflags = 0; + entry->hdr.uflags = 0; UPDATE_HEAD(mb->cmd_head, pad_size, udev->cmdr_size); @@ -355,9 +358,11 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) entry = (void *) mb + CMDR_OFF + cmd_head; tcmu_flush_dcache_range(entry, sizeof(*entry)); - tcmu_hdr_set_op(&entry->hdr, TCMU_OP_CMD); - tcmu_hdr_set_len(&entry->hdr, command_size); - entry->cmd_id = tcmu_cmd->cmd_id; + tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_CMD); + tcmu_hdr_set_len(&entry->hdr.len_op, command_size); + entry->hdr.cmd_id = tcmu_cmd->cmd_id; + entry->hdr.kflags = 0; + entry->hdr.uflags = 0; /* * Fix up iovecs, and handle if allocation in data ring wrapped. @@ -376,7 +381,8 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) /* Even iov_base is relative to mb_addr */ iov->iov_len = copy_bytes; - iov->iov_base = (void *) udev->data_off + udev->data_head; + iov->iov_base = (void __user *) udev->data_off + + udev->data_head; iov_cnt++; iov++; @@ -388,7 +394,8 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) copy_bytes = sg->length - copy_bytes; iov->iov_len = copy_bytes; - iov->iov_base = (void *) udev->data_off + udev->data_head; + iov->iov_base = (void __user *) udev->data_off + + udev->data_head; if (se_cmd->data_direction == DMA_TO_DEVICE) { to = (void *) mb + udev->data_off + udev->data_head; @@ -405,6 +412,8 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) kunmap_atomic(from); } entry->req.iov_cnt = iov_cnt; + entry->req.iov_bidi_cnt = 0; + entry->req.iov_dif_cnt = 0; /* All offsets relative to mb_addr, not start of entry! */ cdb_off = CMDR_OFF + cmd_head + base_command_size; @@ -462,6 +471,17 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * return; } + if (entry->hdr.uflags & TCMU_UFLAG_UNKNOWN_OP) { + UPDATE_HEAD(udev->data_tail, cmd->data_length, udev->data_size); + pr_warn("TCMU: Userspace set UNKNOWN_OP flag on se_cmd %p\n", + cmd->se_cmd); + transport_generic_request_failure(cmd->se_cmd, + TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE); + cmd->se_cmd = NULL; + kmem_cache_free(tcmu_cmd_cache, cmd); + return; + } + if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) { memcpy(se_cmd->sense_buffer, entry->rsp.sense_buffer, se_cmd->scsi_sense_length); @@ -540,14 +560,16 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) tcmu_flush_dcache_range(entry, sizeof(*entry)); - if (tcmu_hdr_get_op(&entry->hdr) == TCMU_OP_PAD) { - UPDATE_HEAD(udev->cmdr_last_cleaned, tcmu_hdr_get_len(&entry->hdr), udev->cmdr_size); + if (tcmu_hdr_get_op(entry->hdr.len_op) == TCMU_OP_PAD) { + UPDATE_HEAD(udev->cmdr_last_cleaned, + tcmu_hdr_get_len(entry->hdr.len_op), + udev->cmdr_size); continue; } - WARN_ON(tcmu_hdr_get_op(&entry->hdr) != TCMU_OP_CMD); + WARN_ON(tcmu_hdr_get_op(entry->hdr.len_op) != TCMU_OP_CMD); spin_lock(&udev->commands_lock); - cmd = idr_find(&udev->commands, entry->cmd_id); + cmd = idr_find(&udev->commands, entry->hdr.cmd_id); if (cmd) idr_remove(&udev->commands, cmd->cmd_id); spin_unlock(&udev->commands_lock); @@ -560,7 +582,9 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) tcmu_handle_completion(cmd, entry); - UPDATE_HEAD(udev->cmdr_last_cleaned, tcmu_hdr_get_len(&entry->hdr), udev->cmdr_size); + UPDATE_HEAD(udev->cmdr_last_cleaned, + tcmu_hdr_get_len(entry->hdr.len_op), + udev->cmdr_size); handled++; } @@ -838,14 +862,14 @@ static int tcmu_configure_device(struct se_device *dev) udev->data_size = TCMU_RING_SIZE - CMDR_SIZE; mb = udev->mb_addr; - mb->version = 1; + mb->version = TCMU_MAILBOX_VERSION; mb->cmdr_off = CMDR_OFF; mb->cmdr_size = udev->cmdr_size; WARN_ON(!PAGE_ALIGNED(udev->data_off)); WARN_ON(udev->data_size % PAGE_SIZE); - info->version = "1"; + info->version = xstr(TCMU_MAILBOX_VERSION); info->mem[0].name = "tcm-user command & data buffer"; info->mem[0].addr = (phys_addr_t) udev->mb_addr; diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 33ac39bf75e5..a600ff15dcfd 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -34,20 +34,12 @@ #include <target/target_core_fabric.h> #include <target/target_core_configfs.h> +#include "target_core_internal.h" #include "target_core_pr.h" #include "target_core_ua.h" #include "target_core_xcopy.h" static struct workqueue_struct *xcopy_wq = NULL; -/* - * From target_core_device.c - */ -extern struct mutex g_device_mutex; -extern struct list_head g_device_list; -/* - * From target_core_configfs.c - */ -extern struct configfs_subsystem *target_core_subsystem[]; static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf) { @@ -433,7 +425,7 @@ static int xcopy_pt_queue_status(struct se_cmd *se_cmd) return 0; } -static struct target_core_fabric_ops xcopy_pt_tfo = { +static const struct target_core_fabric_ops xcopy_pt_tfo = { .get_fabric_name = xcopy_pt_get_fabric_name, .get_task_tag = xcopy_pt_get_tag, .get_cmd_state = xcopy_pt_get_cmd_state, @@ -548,33 +540,22 @@ static void target_xcopy_setup_pt_port( } } -static int target_xcopy_init_pt_lun( - struct xcopy_pt_cmd *xpt_cmd, - struct xcopy_op *xop, - struct se_device *se_dev, - struct se_cmd *pt_cmd, - bool remote_port) +static void target_xcopy_init_pt_lun(struct se_device *se_dev, + struct se_cmd *pt_cmd, bool remote_port) { /* * Don't allocate + init an pt_cmd->se_lun if honoring local port for * reservations. The pt_cmd->se_lun pointer will be setup from within * target_xcopy_setup_pt_port() */ - if (!remote_port) { - pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH; - return 0; + if (remote_port) { + pr_debug("Setup emulated se_dev: %p from se_dev\n", + pt_cmd->se_dev); + pt_cmd->se_lun = &se_dev->xcopy_lun; + pt_cmd->se_dev = se_dev; } - pt_cmd->se_lun = &se_dev->xcopy_lun; - pt_cmd->se_dev = se_dev; - - pr_debug("Setup emulated se_dev: %p from se_dev\n", pt_cmd->se_dev); - pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH; - - pr_debug("Setup emulated se_dev: %p to pt_cmd->se_lun->lun_se_dev\n", - pt_cmd->se_lun->lun_se_dev); - - return 0; + pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD; } static int target_xcopy_setup_pt_cmd( @@ -592,11 +573,8 @@ static int target_xcopy_setup_pt_cmd( * Setup LUN+port to honor reservations based upon xop->op_origin for * X-COPY PUSH or X-COPY PULL based upon where the CDB was received. */ - rc = target_xcopy_init_pt_lun(xpt_cmd, xop, se_dev, cmd, remote_port); - if (rc < 0) { - ret = rc; - goto out; - } + target_xcopy_init_pt_lun(se_dev, cmd, remote_port); + xpt_cmd->xcopy_op = xop; target_xcopy_setup_pt_port(xpt_cmd, xop, remote_port); diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h index a0bcfd3e7e7d..881deb3d499a 100644 --- a/drivers/target/tcm_fc/tcm_fc.h +++ b/drivers/target/tcm_fc/tcm_fc.h @@ -129,7 +129,6 @@ struct ft_cmd { extern struct mutex ft_lport_lock; extern struct fc4_prov ft_prov; -extern struct target_fabric_configfs *ft_configfs; extern unsigned int ft_debug_logging; /* diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c index efdcb9663a1a..65dce1345966 100644 --- a/drivers/target/tcm_fc/tfc_conf.c +++ b/drivers/target/tcm_fc/tfc_conf.c @@ -48,7 +48,7 @@ #include "tcm_fc.h" -struct target_fabric_configfs *ft_configfs; +static const struct target_core_fabric_ops ft_fabric_ops; static LIST_HEAD(ft_wwn_list); DEFINE_MUTEX(ft_lport_lock); @@ -337,7 +337,7 @@ static struct se_portal_group *ft_add_tpg( return NULL; } - ret = core_tpg_register(&ft_configfs->tf_ops, wwn, &tpg->se_tpg, + ret = core_tpg_register(&ft_fabric_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { destroy_workqueue(wq); @@ -507,7 +507,9 @@ static u32 ft_tpg_get_inst_index(struct se_portal_group *se_tpg) return tpg->index; } -static struct target_core_fabric_ops ft_fabric_ops = { +static const struct target_core_fabric_ops ft_fabric_ops = { + .module = THIS_MODULE, + .name = "fc", .get_fabric_name = ft_get_fabric_name, .get_fabric_proto_ident = fc_get_fabric_proto_ident, .tpg_get_wwn = ft_get_fabric_wwn, @@ -552,62 +554,10 @@ static struct target_core_fabric_ops ft_fabric_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = &ft_add_acl, .fabric_drop_nodeacl = &ft_del_acl, -}; - -static int ft_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - - /* - * Register the top level struct config_item_type with TCM core - */ - fabric = target_fabric_configfs_init(THIS_MODULE, "fc"); - if (IS_ERR(fabric)) { - pr_err("%s: target_fabric_configfs_init() failed!\n", - __func__); - return PTR_ERR(fabric); - } - fabric->tf_ops = ft_fabric_ops; - - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = ft_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = - ft_nacl_base_attrs; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - /* - * register the fabric for use within TCM - */ - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_debug("target_fabric_configfs_register() for" - " FC Target failed!\n"); - target_fabric_configfs_free(fabric); - return -1; - } - - /* - * Setup our local pointer to *fabric. - */ - ft_configfs = fabric; - return 0; -} -static void ft_deregister_configfs(void) -{ - if (!ft_configfs) - return; - target_fabric_configfs_deregister(ft_configfs); - ft_configfs = NULL; -} + .tfc_wwn_attrs = ft_wwn_attrs, + .tfc_tpg_nacl_base_attrs = ft_nacl_base_attrs, +}; static struct notifier_block ft_notifier = { .notifier_call = ft_lport_notify @@ -615,15 +565,24 @@ static struct notifier_block ft_notifier = { static int __init ft_init(void) { - if (ft_register_configfs()) - return -1; - if (fc_fc4_register_provider(FC_TYPE_FCP, &ft_prov)) { - ft_deregister_configfs(); - return -1; - } + int ret; + + ret = target_register_template(&ft_fabric_ops); + if (ret) + goto out; + + ret = fc_fc4_register_provider(FC_TYPE_FCP, &ft_prov); + if (ret) + goto out_unregister_template; + blocking_notifier_chain_register(&fc_lport_notifier_head, &ft_notifier); fc_lport_iterate(ft_lport_add, NULL); return 0; + +out_unregister_template: + target_unregister_template(&ft_fabric_ops); +out: + return ret; } static void __exit ft_exit(void) @@ -632,7 +591,7 @@ static void __exit ft_exit(void) &ft_notifier); fc_fc4_deregister_provider(FC_TYPE_FCP, &ft_prov); fc_lport_iterate(ft_lport_del, NULL); - ft_deregister_configfs(); + target_unregister_template(&ft_fabric_ops); synchronize_rcu(); } diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 422ebea96a64..4506e405c8f3 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -450,6 +450,18 @@ static unsigned int mem32_serial_in(struct uart_port *p, int offset) return readl(p->membase + offset); } +static void mem32be_serial_out(struct uart_port *p, int offset, int value) +{ + offset = offset << p->regshift; + iowrite32be(value, p->membase + offset); +} + +static unsigned int mem32be_serial_in(struct uart_port *p, int offset) +{ + offset = offset << p->regshift; + return ioread32be(p->membase + offset); +} + static unsigned int io_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; @@ -488,6 +500,11 @@ static void set_io_from_upio(struct uart_port *p) p->serial_out = mem32_serial_out; break; + case UPIO_MEM32BE: + p->serial_in = mem32be_serial_in; + p->serial_out = mem32be_serial_out; + break; + #if defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_SERIAL_8250_RT288X) case UPIO_AU: p->serial_in = au_serial_in; @@ -513,6 +530,7 @@ serial_port_out_sync(struct uart_port *p, int offset, int value) switch (p->iotype) { case UPIO_MEM: case UPIO_MEM32: + case UPIO_MEM32BE: case UPIO_AU: p->serial_out(p, offset, value); p->serial_in(p, UART_LCR); /* safe, no side-effects */ @@ -2748,6 +2766,7 @@ static int serial8250_request_std_resource(struct uart_8250_port *up) case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: + case UPIO_MEM32BE: case UPIO_MEM: if (!port->mapbase) break; @@ -2784,6 +2803,7 @@ static void serial8250_release_std_resource(struct uart_8250_port *up) case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: + case UPIO_MEM32BE: case UPIO_MEM: if (!port->mapbase) break; diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c index 8e119682266a..6c0fd8b9d1c3 100644 --- a/drivers/tty/serial/8250/8250_early.c +++ b/drivers/tty/serial/8250/8250_early.c @@ -42,6 +42,8 @@ unsigned int __weak __init serial8250_early_in(struct uart_port *port, int offse return readb(port->membase + offset); case UPIO_MEM32: return readl(port->membase + (offset << 2)); + case UPIO_MEM32BE: + return ioread32be(port->membase + (offset << 2)); case UPIO_PORT: return inb(port->iobase + offset); default: @@ -58,6 +60,9 @@ void __weak __init serial8250_early_out(struct uart_port *port, int offset, int case UPIO_MEM32: writel(value, port->membase + (offset << 2)); break; + case UPIO_MEM32BE: + iowrite32be(value, port->membase + (offset << 2)); + break; case UPIO_PORT: outb(value, port->iobase + offset); break; diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index aa00154c4a6d..5b73afb9f9f3 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -116,7 +116,8 @@ static int of_platform_serial_setup(struct platform_device *ofdev, port->iotype = UPIO_MEM; break; case 4: - port->iotype = UPIO_MEM32; + port->iotype = of_device_is_big_endian(np) ? + UPIO_MEM32BE : UPIO_MEM32; break; default: dev_warn(&ofdev->dev, "unsupported reg-io-width (%d)\n", diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 6af58c6dba5e..2030565c6789 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1505,7 +1505,7 @@ static void destroy_ep_files (struct dev_data *dev) list_del_init (&ep->epfiles); dentry = ep->dentry; ep->dentry = NULL; - parent = dentry->d_parent->d_inode; + parent = d_inode(dentry->d_parent); /* break link to controller */ if (ep->state == STATE_EP_ENABLED) diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c index 6e0a019aad54..8b80addc4ce6 100644 --- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c +++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c @@ -29,7 +29,7 @@ USB_GADGET_COMPOSITE_OPTIONS(); -static struct target_fabric_configfs *usbg_fabric_configfs; +static const struct target_core_fabric_ops usbg_ops; static inline struct f_uas *to_f_uas(struct usb_function *f) { @@ -1572,8 +1572,7 @@ static struct se_portal_group *usbg_make_tpg( tpg->tport = tport; tpg->tport_tpgt = tpgt; - ret = core_tpg_register(&usbg_fabric_configfs->tf_ops, wwn, - &tpg->se_tpg, tpg, + ret = core_tpg_register(&usbg_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { destroy_workqueue(tpg->workqueue); @@ -1864,7 +1863,9 @@ static int usbg_check_stop_free(struct se_cmd *se_cmd) return 1; } -static struct target_core_fabric_ops usbg_ops = { +static const struct target_core_fabric_ops usbg_ops = { + .module = THIS_MODULE, + .name = "usb_gadget", .get_fabric_name = usbg_get_fabric_name, .get_fabric_proto_ident = usbg_get_fabric_proto_ident, .tpg_get_wwn = usbg_get_fabric_wwn, @@ -1906,46 +1907,9 @@ static struct target_core_fabric_ops usbg_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = usbg_make_nodeacl, .fabric_drop_nodeacl = usbg_drop_nodeacl, -}; - -static int usbg_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - - fabric = target_fabric_configfs_init(THIS_MODULE, "usb_gadget"); - if (IS_ERR(fabric)) { - printk(KERN_ERR "target_fabric_configfs_init() failed\n"); - return PTR_ERR(fabric); - } - - fabric->tf_ops = usbg_ops; - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = usbg_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = usbg_base_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - printk(KERN_ERR "target_fabric_configfs_register() failed" - " for usb-gadget\n"); - return ret; - } - usbg_fabric_configfs = fabric; - return 0; -}; -static void usbg_deregister_configfs(void) -{ - if (!(usbg_fabric_configfs)) - return; - - target_fabric_configfs_deregister(usbg_fabric_configfs); - usbg_fabric_configfs = NULL; + .tfc_wwn_attrs = usbg_wwn_attrs, + .tfc_tpg_base_attrs = usbg_base_attrs, }; /* Start gadget.c code */ @@ -2454,16 +2418,13 @@ static void usbg_detach(struct usbg_tpg *tpg) static int __init usb_target_gadget_init(void) { - int ret; - - ret = usbg_register_configfs(); - return ret; + return target_register_template(&usbg_ops); } module_init(usb_target_gadget_init); static void __exit usb_target_gadget_exit(void) { - usbg_deregister_configfs(); + target_unregister_template(&usbg_ops); } module_exit(usb_target_gadget_exit); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 71df240a467a..5e19bb53b3a9 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -131,6 +131,8 @@ struct vhost_scsi_tpg { int tv_tpg_port_count; /* Used for vhost_scsi device reference to tpg_nexus, protected by tv_tpg_mutex */ int tv_tpg_vhost_count; + /* Used for enabling T10-PI with legacy devices */ + int tv_fabric_prot_type; /* list for vhost_scsi_list */ struct list_head tv_tpg_list; /* Used to protect access for tpg_nexus */ @@ -214,9 +216,7 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; -/* Local pointer to allocated TCM configfs fabric module */ -static struct target_fabric_configfs *vhost_scsi_fabric_configfs; - +static struct target_core_fabric_ops vhost_scsi_ops; static struct workqueue_struct *vhost_scsi_workqueue; /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ @@ -431,6 +431,14 @@ vhost_scsi_parse_pr_out_transport_id(struct se_portal_group *se_tpg, port_nexus_ptr); } +static int vhost_scsi_check_prot_fabric_only(struct se_portal_group *se_tpg) +{ + struct vhost_scsi_tpg *tpg = container_of(se_tpg, + struct vhost_scsi_tpg, se_tpg); + + return tpg->tv_fabric_prot_type; +} + static struct se_node_acl * vhost_scsi_alloc_fabric_acl(struct se_portal_group *se_tpg) { @@ -1878,6 +1886,45 @@ static void vhost_scsi_free_cmd_map_res(struct vhost_scsi_nexus *nexus, } } +static ssize_t vhost_scsi_tpg_attrib_store_fabric_prot_type( + struct se_portal_group *se_tpg, + const char *page, + size_t count) +{ + struct vhost_scsi_tpg *tpg = container_of(se_tpg, + struct vhost_scsi_tpg, se_tpg); + unsigned long val; + int ret = kstrtoul(page, 0, &val); + + if (ret) { + pr_err("kstrtoul() returned %d for fabric_prot_type\n", ret); + return ret; + } + if (val != 0 && val != 1 && val != 3) { + pr_err("Invalid vhost_scsi fabric_prot_type: %lu\n", val); + return -EINVAL; + } + tpg->tv_fabric_prot_type = val; + + return count; +} + +static ssize_t vhost_scsi_tpg_attrib_show_fabric_prot_type( + struct se_portal_group *se_tpg, + char *page) +{ + struct vhost_scsi_tpg *tpg = container_of(se_tpg, + struct vhost_scsi_tpg, se_tpg); + + return sprintf(page, "%d\n", tpg->tv_fabric_prot_type); +} +TF_TPG_ATTRIB_ATTR(vhost_scsi, fabric_prot_type, S_IRUGO | S_IWUSR); + +static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { + &vhost_scsi_tpg_attrib_fabric_prot_type.attr, + NULL, +}; + static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, const char *name) { @@ -2155,7 +2202,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, tpg->tport = tport; tpg->tport_tpgt = tpgt; - ret = core_tpg_register(&vhost_scsi_fabric_configfs->tf_ops, wwn, + ret = core_tpg_register(&vhost_scsi_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { kfree(tpg); @@ -2277,6 +2324,8 @@ static struct configfs_attribute *vhost_scsi_wwn_attrs[] = { }; static struct target_core_fabric_ops vhost_scsi_ops = { + .module = THIS_MODULE, + .name = "vhost", .get_fabric_name = vhost_scsi_get_fabric_name, .get_fabric_proto_ident = vhost_scsi_get_fabric_proto_ident, .tpg_get_wwn = vhost_scsi_get_fabric_wwn, @@ -2289,6 +2338,7 @@ static struct target_core_fabric_ops vhost_scsi_ops = { .tpg_check_demo_mode_cache = vhost_scsi_check_true, .tpg_check_demo_mode_write_protect = vhost_scsi_check_false, .tpg_check_prod_mode_write_protect = vhost_scsi_check_false, + .tpg_check_prot_fabric_only = vhost_scsi_check_prot_fabric_only, .tpg_alloc_fabric_acl = vhost_scsi_alloc_fabric_acl, .tpg_release_fabric_acl = vhost_scsi_release_fabric_acl, .tpg_get_inst_index = vhost_scsi_tpg_get_inst_index, @@ -2320,70 +2370,20 @@ static struct target_core_fabric_ops vhost_scsi_ops = { .fabric_drop_np = NULL, .fabric_make_nodeacl = vhost_scsi_make_nodeacl, .fabric_drop_nodeacl = vhost_scsi_drop_nodeacl, + + .tfc_wwn_attrs = vhost_scsi_wwn_attrs, + .tfc_tpg_base_attrs = vhost_scsi_tpg_attrs, + .tfc_tpg_attrib_attrs = vhost_scsi_tpg_attrib_attrs, }; -static int vhost_scsi_register_configfs(void) +static int __init vhost_scsi_init(void) { - struct target_fabric_configfs *fabric; - int ret; + int ret = -ENOMEM; - pr_debug("vhost-scsi fabric module %s on %s/%s" + pr_debug("TCM_VHOST fabric module %s on %s/%s" " on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname, utsname()->machine); - /* - * Register the top level struct config_item_type with TCM core - */ - fabric = target_fabric_configfs_init(THIS_MODULE, "vhost"); - if (IS_ERR(fabric)) { - pr_err("target_fabric_configfs_init() failed\n"); - return PTR_ERR(fabric); - } - /* - * Setup fabric->tf_ops from our local vhost_scsi_ops - */ - fabric->tf_ops = vhost_scsi_ops; - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = vhost_scsi_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = vhost_scsi_tpg_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - /* - * Register the fabric for use within TCM - */ - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - pr_err("target_fabric_configfs_register() failed" - " for TCM_VHOST\n"); - return ret; - } - /* - * Setup our local pointer to *fabric - */ - vhost_scsi_fabric_configfs = fabric; - pr_debug("TCM_VHOST[0] - Set fabric -> vhost_scsi_fabric_configfs\n"); - return 0; -}; - -static void vhost_scsi_deregister_configfs(void) -{ - if (!vhost_scsi_fabric_configfs) - return; - - target_fabric_configfs_deregister(vhost_scsi_fabric_configfs); - vhost_scsi_fabric_configfs = NULL; - pr_debug("TCM_VHOST[0] - Cleared vhost_scsi_fabric_configfs\n"); -}; -static int __init vhost_scsi_init(void) -{ - int ret = -ENOMEM; /* * Use our own dedicated workqueue for submitting I/O into * target core to avoid contention within system_wq. @@ -2396,7 +2396,7 @@ static int __init vhost_scsi_init(void) if (ret < 0) goto out_destroy_workqueue; - ret = vhost_scsi_register_configfs(); + ret = target_register_template(&vhost_scsi_ops); if (ret < 0) goto out_vhost_scsi_deregister; @@ -2412,7 +2412,7 @@ out: static void vhost_scsi_exit(void) { - vhost_scsi_deregister_configfs(); + target_unregister_template(&vhost_scsi_ops); vhost_scsi_deregister(); destroy_workqueue(vhost_scsi_workqueue); }; diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index b546da5d8ea3..cab9f3f63a38 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -48,6 +48,16 @@ config VIRTIO_BALLOON If unsure, say M. +config VIRTIO_INPUT + tristate "Virtio input driver" + depends on VIRTIO + depends on INPUT + ---help--- + This driver supports virtio input devices such as + keyboards, mice and tablets. + + If unsure, say M. + config VIRTIO_MMIO tristate "Platform bus driver for memory mapped virtio devices" depends on HAS_IOMEM diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index d85565b8ea46..41e30e3dc842 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o +obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 5ce2aa48fc6e..b1877d73fa56 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -278,12 +278,6 @@ static struct bus_type virtio_bus = { .remove = virtio_dev_remove, }; -bool virtio_device_is_legacy_only(struct virtio_device_id id) -{ - return id.device == VIRTIO_ID_BALLOON; -} -EXPORT_SYMBOL_GPL(virtio_device_is_legacy_only); - int register_virtio_driver(struct virtio_driver *driver) { /* Catch this early. */ diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 6a356e344f82..82e80e034f25 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -214,8 +214,8 @@ static inline void update_stat(struct virtio_balloon *vb, int idx, u16 tag, u64 val) { BUG_ON(idx >= VIRTIO_BALLOON_S_NR); - vb->stats[idx].tag = tag; - vb->stats[idx].val = val; + vb->stats[idx].tag = cpu_to_virtio16(vb->vdev, tag); + vb->stats[idx].val = cpu_to_virtio64(vb->vdev, val); } #define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT) @@ -283,18 +283,27 @@ static void virtballoon_changed(struct virtio_device *vdev) static inline s64 towards_target(struct virtio_balloon *vb) { - __le32 v; s64 target; + u32 num_pages; - virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages, &v); + virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages, + &num_pages); - target = le32_to_cpu(v); + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + num_pages = le32_to_cpu((__force __le32)num_pages); + + target = num_pages; return target - vb->num_pages; } static void update_balloon_size(struct virtio_balloon *vb) { - __le32 actual = cpu_to_le32(vb->num_pages); + u32 actual = vb->num_pages; + + /* Legacy balloon config space is LE, unlike all other devices. */ + if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1)) + actual = (__force u32)cpu_to_le32(actual); virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual, &actual); diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c new file mode 100644 index 000000000000..60e2a1677563 --- /dev/null +++ b/drivers/virtio/virtio_input.c @@ -0,0 +1,384 @@ +#include <linux/module.h> +#include <linux/virtio.h> +#include <linux/virtio_config.h> +#include <linux/input.h> + +#include <uapi/linux/virtio_ids.h> +#include <uapi/linux/virtio_input.h> + +struct virtio_input { + struct virtio_device *vdev; + struct input_dev *idev; + char name[64]; + char serial[64]; + char phys[64]; + struct virtqueue *evt, *sts; + struct virtio_input_event evts[64]; + spinlock_t lock; + bool ready; +}; + +static void virtinput_queue_evtbuf(struct virtio_input *vi, + struct virtio_input_event *evtbuf) +{ + struct scatterlist sg[1]; + + sg_init_one(sg, evtbuf, sizeof(*evtbuf)); + virtqueue_add_inbuf(vi->evt, sg, 1, evtbuf, GFP_ATOMIC); +} + +static void virtinput_recv_events(struct virtqueue *vq) +{ + struct virtio_input *vi = vq->vdev->priv; + struct virtio_input_event *event; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&vi->lock, flags); + if (vi->ready) { + while ((event = virtqueue_get_buf(vi->evt, &len)) != NULL) { + spin_unlock_irqrestore(&vi->lock, flags); + input_event(vi->idev, + le16_to_cpu(event->type), + le16_to_cpu(event->code), + le32_to_cpu(event->value)); + spin_lock_irqsave(&vi->lock, flags); + virtinput_queue_evtbuf(vi, event); + } + virtqueue_kick(vq); + } + spin_unlock_irqrestore(&vi->lock, flags); +} + +/* + * On error we are losing the status update, which isn't critical as + * this is typically used for stuff like keyboard leds. + */ +static int virtinput_send_status(struct virtio_input *vi, + u16 type, u16 code, s32 value) +{ + struct virtio_input_event *stsbuf; + struct scatterlist sg[1]; + unsigned long flags; + int rc; + + stsbuf = kzalloc(sizeof(*stsbuf), GFP_ATOMIC); + if (!stsbuf) + return -ENOMEM; + + stsbuf->type = cpu_to_le16(type); + stsbuf->code = cpu_to_le16(code); + stsbuf->value = cpu_to_le32(value); + sg_init_one(sg, stsbuf, sizeof(*stsbuf)); + + spin_lock_irqsave(&vi->lock, flags); + if (vi->ready) { + rc = virtqueue_add_outbuf(vi->sts, sg, 1, stsbuf, GFP_ATOMIC); + virtqueue_kick(vi->sts); + } else { + rc = -ENODEV; + } + spin_unlock_irqrestore(&vi->lock, flags); + + if (rc != 0) + kfree(stsbuf); + return rc; +} + +static void virtinput_recv_status(struct virtqueue *vq) +{ + struct virtio_input *vi = vq->vdev->priv; + struct virtio_input_event *stsbuf; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&vi->lock, flags); + while ((stsbuf = virtqueue_get_buf(vi->sts, &len)) != NULL) + kfree(stsbuf); + spin_unlock_irqrestore(&vi->lock, flags); +} + +static int virtinput_status(struct input_dev *idev, unsigned int type, + unsigned int code, int value) +{ + struct virtio_input *vi = input_get_drvdata(idev); + + return virtinput_send_status(vi, type, code, value); +} + +static u8 virtinput_cfg_select(struct virtio_input *vi, + u8 select, u8 subsel) +{ + u8 size; + + virtio_cwrite(vi->vdev, struct virtio_input_config, select, &select); + virtio_cwrite(vi->vdev, struct virtio_input_config, subsel, &subsel); + virtio_cread(vi->vdev, struct virtio_input_config, size, &size); + return size; +} + +static void virtinput_cfg_bits(struct virtio_input *vi, int select, int subsel, + unsigned long *bits, unsigned int bitcount) +{ + unsigned int bit; + u8 *virtio_bits; + u8 bytes; + + bytes = virtinput_cfg_select(vi, select, subsel); + if (!bytes) + return; + if (bitcount > bytes * 8) + bitcount = bytes * 8; + + /* + * Bitmap in virtio config space is a simple stream of bytes, + * with the first byte carrying bits 0-7, second bits 8-15 and + * so on. + */ + virtio_bits = kzalloc(bytes, GFP_KERNEL); + if (!virtio_bits) + return; + virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config, + u.bitmap), + virtio_bits, bytes); + for (bit = 0; bit < bitcount; bit++) { + if (virtio_bits[bit / 8] & (1 << (bit % 8))) + __set_bit(bit, bits); + } + kfree(virtio_bits); + + if (select == VIRTIO_INPUT_CFG_EV_BITS) + __set_bit(subsel, vi->idev->evbit); +} + +static void virtinput_cfg_abs(struct virtio_input *vi, int abs) +{ + u32 mi, ma, re, fu, fl; + + virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs); + virtio_cread(vi->vdev, struct virtio_input_config, u.abs.min, &mi); + virtio_cread(vi->vdev, struct virtio_input_config, u.abs.max, &ma); + virtio_cread(vi->vdev, struct virtio_input_config, u.abs.res, &re); + virtio_cread(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu); + virtio_cread(vi->vdev, struct virtio_input_config, u.abs.flat, &fl); + input_set_abs_params(vi->idev, abs, mi, ma, fu, fl); + input_abs_set_res(vi->idev, abs, re); +} + +static int virtinput_init_vqs(struct virtio_input *vi) +{ + struct virtqueue *vqs[2]; + vq_callback_t *cbs[] = { virtinput_recv_events, + virtinput_recv_status }; + static const char *names[] = { "events", "status" }; + int err; + + err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names); + if (err) + return err; + vi->evt = vqs[0]; + vi->sts = vqs[1]; + + return 0; +} + +static void virtinput_fill_evt(struct virtio_input *vi) +{ + unsigned long flags; + int i, size; + + spin_lock_irqsave(&vi->lock, flags); + size = virtqueue_get_vring_size(vi->evt); + if (size > ARRAY_SIZE(vi->evts)) + size = ARRAY_SIZE(vi->evts); + for (i = 0; i < size; i++) + virtinput_queue_evtbuf(vi, &vi->evts[i]); + virtqueue_kick(vi->evt); + spin_unlock_irqrestore(&vi->lock, flags); +} + +static int virtinput_probe(struct virtio_device *vdev) +{ + struct virtio_input *vi; + unsigned long flags; + size_t size; + int abs, err; + + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + return -ENODEV; + + vi = kzalloc(sizeof(*vi), GFP_KERNEL); + if (!vi) + return -ENOMEM; + + vdev->priv = vi; + vi->vdev = vdev; + spin_lock_init(&vi->lock); + + err = virtinput_init_vqs(vi); + if (err) + goto err_init_vq; + + vi->idev = input_allocate_device(); + if (!vi->idev) { + err = -ENOMEM; + goto err_input_alloc; + } + input_set_drvdata(vi->idev, vi); + + size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_NAME, 0); + virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config, + u.string), + vi->name, min(size, sizeof(vi->name))); + size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_SERIAL, 0); + virtio_cread_bytes(vi->vdev, offsetof(struct virtio_input_config, + u.string), + vi->serial, min(size, sizeof(vi->serial))); + snprintf(vi->phys, sizeof(vi->phys), + "virtio%d/input0", vdev->index); + vi->idev->name = vi->name; + vi->idev->phys = vi->phys; + vi->idev->uniq = vi->serial; + + size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0); + if (size >= sizeof(struct virtio_input_devids)) { + virtio_cread(vi->vdev, struct virtio_input_config, + u.ids.bustype, &vi->idev->id.bustype); + virtio_cread(vi->vdev, struct virtio_input_config, + u.ids.vendor, &vi->idev->id.vendor); + virtio_cread(vi->vdev, struct virtio_input_config, + u.ids.product, &vi->idev->id.product); + virtio_cread(vi->vdev, struct virtio_input_config, + u.ids.version, &vi->idev->id.version); + } else { + vi->idev->id.bustype = BUS_VIRTUAL; + } + + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_PROP_BITS, 0, + vi->idev->propbit, INPUT_PROP_CNT); + size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_REP); + if (size) + __set_bit(EV_REP, vi->idev->evbit); + + vi->idev->dev.parent = &vdev->dev; + vi->idev->event = virtinput_status; + + /* device -> kernel */ + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_KEY, + vi->idev->keybit, KEY_CNT); + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_REL, + vi->idev->relbit, REL_CNT); + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_ABS, + vi->idev->absbit, ABS_CNT); + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_MSC, + vi->idev->mscbit, MSC_CNT); + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_SW, + vi->idev->swbit, SW_CNT); + + /* kernel -> device */ + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_LED, + vi->idev->ledbit, LED_CNT); + virtinput_cfg_bits(vi, VIRTIO_INPUT_CFG_EV_BITS, EV_SND, + vi->idev->sndbit, SND_CNT); + + if (test_bit(EV_ABS, vi->idev->evbit)) { + for (abs = 0; abs < ABS_CNT; abs++) { + if (!test_bit(abs, vi->idev->absbit)) + continue; + virtinput_cfg_abs(vi, abs); + } + } + + virtio_device_ready(vdev); + vi->ready = true; + err = input_register_device(vi->idev); + if (err) + goto err_input_register; + + virtinput_fill_evt(vi); + return 0; + +err_input_register: + spin_lock_irqsave(&vi->lock, flags); + vi->ready = false; + spin_unlock_irqrestore(&vi->lock, flags); + input_free_device(vi->idev); +err_input_alloc: + vdev->config->del_vqs(vdev); +err_init_vq: + kfree(vi); + return err; +} + +static void virtinput_remove(struct virtio_device *vdev) +{ + struct virtio_input *vi = vdev->priv; + unsigned long flags; + + spin_lock_irqsave(&vi->lock, flags); + vi->ready = false; + spin_unlock_irqrestore(&vi->lock, flags); + + input_unregister_device(vi->idev); + vdev->config->del_vqs(vdev); + kfree(vi); +} + +#ifdef CONFIG_PM_SLEEP +static int virtinput_freeze(struct virtio_device *vdev) +{ + struct virtio_input *vi = vdev->priv; + unsigned long flags; + + spin_lock_irqsave(&vi->lock, flags); + vi->ready = false; + spin_unlock_irqrestore(&vi->lock, flags); + + vdev->config->del_vqs(vdev); + return 0; +} + +static int virtinput_restore(struct virtio_device *vdev) +{ + struct virtio_input *vi = vdev->priv; + int err; + + err = virtinput_init_vqs(vi); + if (err) + return err; + + virtio_device_ready(vdev); + vi->ready = true; + virtinput_fill_evt(vi); + return 0; +} +#endif + +static unsigned int features[] = { + /* none */ +}; +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_INPUT, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct virtio_driver virtio_input_driver = { + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .id_table = id_table, + .probe = virtinput_probe, + .remove = virtinput_remove, +#ifdef CONFIG_PM_SLEEP + .freeze = virtinput_freeze, + .restore = virtinput_restore, +#endif +}; + +module_virtio_driver(virtio_input_driver); +MODULE_DEVICE_TABLE(virtio, id_table); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Virtio input device driver"); +MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 6010d7ec0a0f..7a5e60dea6c5 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -581,14 +581,6 @@ static int virtio_mmio_probe(struct platform_device *pdev) } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); - /* Reject legacy-only IDs for version 2 devices */ - if (vm_dev->version == 2 && - virtio_device_is_legacy_only(vm_dev->vdev.id)) { - dev_err(&pdev->dev, "Version 2 not supported for devices %u!\n", - vm_dev->vdev.id.device); - return -ENODEV; - } - if (vm_dev->version == 1) writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 2aa38e59db2e..e88e0997a889 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -20,6 +20,50 @@ #define VIRTIO_PCI_NO_LEGACY #include "virtio_pci_common.h" +/* + * Type-safe wrappers for io accesses. + * Use these to enforce at compile time the following spec requirement: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses + * for 16-bit fields and 8-bit accesses for 8-bit fields. + */ +static inline u8 vp_ioread8(u8 __iomem *addr) +{ + return ioread8(addr); +} +static inline u16 vp_ioread16 (u16 __iomem *addr) +{ + return ioread16(addr); +} + +static inline u32 vp_ioread32(u32 __iomem *addr) +{ + return ioread32(addr); +} + +static inline void vp_iowrite8(u8 value, u8 __iomem *addr) +{ + iowrite8(value, addr); +} + +static inline void vp_iowrite16(u16 value, u16 __iomem *addr) +{ + iowrite16(value, addr); +} + +static inline void vp_iowrite32(u32 value, u32 __iomem *addr) +{ + iowrite32(value, addr); +} + +static void vp_iowrite64_twopart(u64 val, + __le32 __iomem *lo, __le32 __iomem *hi) +{ + vp_iowrite32((u32)val, lo); + vp_iowrite32(val >> 32, hi); +} + static void __iomem *map_capability(struct pci_dev *dev, int off, size_t minlen, u32 align, @@ -94,22 +138,16 @@ static void __iomem *map_capability(struct pci_dev *dev, int off, return p; } -static void iowrite64_twopart(u64 val, __le32 __iomem *lo, __le32 __iomem *hi) -{ - iowrite32((u32)val, lo); - iowrite32(val >> 32, hi); -} - /* virtio config->get_features() implementation */ static u64 vp_get_features(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); u64 features; - iowrite32(0, &vp_dev->common->device_feature_select); - features = ioread32(&vp_dev->common->device_feature); - iowrite32(1, &vp_dev->common->device_feature_select); - features |= ((u64)ioread32(&vp_dev->common->device_feature) << 32); + vp_iowrite32(0, &vp_dev->common->device_feature_select); + features = vp_ioread32(&vp_dev->common->device_feature); + vp_iowrite32(1, &vp_dev->common->device_feature_select); + features |= ((u64)vp_ioread32(&vp_dev->common->device_feature) << 32); return features; } @@ -128,10 +166,10 @@ static int vp_finalize_features(struct virtio_device *vdev) return -EINVAL; } - iowrite32(0, &vp_dev->common->guest_feature_select); - iowrite32((u32)vdev->features, &vp_dev->common->guest_feature); - iowrite32(1, &vp_dev->common->guest_feature_select); - iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature); + vp_iowrite32(0, &vp_dev->common->guest_feature_select); + vp_iowrite32((u32)vdev->features, &vp_dev->common->guest_feature); + vp_iowrite32(1, &vp_dev->common->guest_feature_select); + vp_iowrite32(vdev->features >> 32, &vp_dev->common->guest_feature); return 0; } @@ -210,14 +248,14 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, static u32 vp_generation(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - return ioread8(&vp_dev->common->config_generation); + return vp_ioread8(&vp_dev->common->config_generation); } /* config->{get,set}_status() implementations */ static u8 vp_get_status(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - return ioread8(&vp_dev->common->device_status); + return vp_ioread8(&vp_dev->common->device_status); } static void vp_set_status(struct virtio_device *vdev, u8 status) @@ -225,17 +263,17 @@ static void vp_set_status(struct virtio_device *vdev, u8 status) struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* We should never be setting status to 0. */ BUG_ON(status == 0); - iowrite8(status, &vp_dev->common->device_status); + vp_iowrite8(status, &vp_dev->common->device_status); } static void vp_reset(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* 0 status means a reset. */ - iowrite8(0, &vp_dev->common->device_status); + vp_iowrite8(0, &vp_dev->common->device_status); /* Flush out the status write, and flush in device writes, * including MSI-X interrupts, if any. */ - ioread8(&vp_dev->common->device_status); + vp_ioread8(&vp_dev->common->device_status); /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -243,10 +281,10 @@ static void vp_reset(struct virtio_device *vdev) static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) { /* Setup the vector used for configuration events */ - iowrite16(vector, &vp_dev->common->msix_config); + vp_iowrite16(vector, &vp_dev->common->msix_config); /* Verify we had enough resources to assign the vector */ /* Will also flush the write out to device */ - return ioread16(&vp_dev->common->msix_config); + return vp_ioread16(&vp_dev->common->msix_config); } static size_t vring_pci_size(u16 num) @@ -286,15 +324,15 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, u16 num, off; int err; - if (index >= ioread16(&cfg->num_queues)) + if (index >= vp_ioread16(&cfg->num_queues)) return ERR_PTR(-ENOENT); /* Select the queue we're interested in */ - iowrite16(index, &cfg->queue_select); + vp_iowrite16(index, &cfg->queue_select); /* Check if queue is either not available or already active. */ - num = ioread16(&cfg->queue_size); - if (!num || ioread16(&cfg->queue_enable)) + num = vp_ioread16(&cfg->queue_size); + if (!num || vp_ioread16(&cfg->queue_enable)) return ERR_PTR(-ENOENT); if (num & (num - 1)) { @@ -303,7 +341,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } /* get offset of notification word for this vq */ - off = ioread16(&cfg->queue_notify_off); + off = vp_ioread16(&cfg->queue_notify_off); info->num = num; info->msix_vector = msix_vec; @@ -322,13 +360,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } /* activate the queue */ - iowrite16(num, &cfg->queue_size); - iowrite64_twopart(virt_to_phys(info->queue), - &cfg->queue_desc_lo, &cfg->queue_desc_hi); - iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)), - &cfg->queue_avail_lo, &cfg->queue_avail_hi); - iowrite64_twopart(virt_to_phys(virtqueue_get_used(vq)), - &cfg->queue_used_lo, &cfg->queue_used_hi); + vp_iowrite16(num, &cfg->queue_size); + vp_iowrite64_twopart(virt_to_phys(info->queue), + &cfg->queue_desc_lo, &cfg->queue_desc_hi); + vp_iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)), + &cfg->queue_avail_lo, &cfg->queue_avail_hi); + vp_iowrite64_twopart(virt_to_phys(virtqueue_get_used(vq)), + &cfg->queue_used_lo, &cfg->queue_used_hi); if (vp_dev->notify_base) { /* offset should not wrap */ @@ -357,8 +395,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } if (msix_vec != VIRTIO_MSI_NO_VECTOR) { - iowrite16(msix_vec, &cfg->queue_msix_vector); - msix_vec = ioread16(&cfg->queue_msix_vector); + vp_iowrite16(msix_vec, &cfg->queue_msix_vector); + msix_vec = vp_ioread16(&cfg->queue_msix_vector); if (msix_vec == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto err_assign_vector; @@ -393,8 +431,8 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, * this, there's no way to go back except reset. */ list_for_each_entry(vq, &vdev->vqs, list) { - iowrite16(vq->index, &vp_dev->common->queue_select); - iowrite16(1, &vp_dev->common->queue_enable); + vp_iowrite16(vq->index, &vp_dev->common->queue_select); + vp_iowrite16(1, &vp_dev->common->queue_enable); } return 0; @@ -405,13 +443,13 @@ static void del_vq(struct virtio_pci_vq_info *info) struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); - iowrite16(vq->index, &vp_dev->common->queue_select); + vp_iowrite16(vq->index, &vp_dev->common->queue_select); if (vp_dev->msix_enabled) { - iowrite16(VIRTIO_MSI_NO_VECTOR, - &vp_dev->common->queue_msix_vector); + vp_iowrite16(VIRTIO_MSI_NO_VECTOR, + &vp_dev->common->queue_msix_vector); /* Flush the write out to device */ - ioread16(&vp_dev->common->queue_msix_vector); + vp_ioread16(&vp_dev->common->queue_msix_vector); } if (!vp_dev->notify_base) @@ -577,9 +615,6 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) } vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor; - if (virtio_device_is_legacy_only(vp_dev->vdev.id)) - return -ENODEV; - /* check for a common config: if not, use legacy mode (bar 0). */ common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, IORESOURCE_IO | IORESOURCE_MEM); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index ce4f3a7f95fd..e5e7c5505de7 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -169,7 +169,6 @@ config AT91SAM9X_WATCHDOG config CADENCE_WATCHDOG tristate "Cadence Watchdog Timer" - depends on ARM select WATCHDOG_CORE help Say Y here if you want to include support for the watchdog @@ -1190,6 +1189,7 @@ config OCTEON_WDT tristate "Cavium OCTEON SOC family Watchdog Timer" depends on CAVIUM_OCTEON_SOC default y + select WATCHDOG_CORE select EXPORT_UASM if OCTEON_WDT = m help Hardware driver for OCTEON's on chip watchdog timer. diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c index 4e37db3539a4..22d8ae65772a 100644 --- a/drivers/watchdog/bcm_kona_wdt.c +++ b/drivers/watchdog/bcm_kona_wdt.c @@ -99,12 +99,14 @@ static int secure_register_read(struct bcm_kona_wdt *wdt, uint32_t offset) static int bcm_kona_wdt_dbg_show(struct seq_file *s, void *data) { - int ctl_val, cur_val, ret; + int ctl_val, cur_val; unsigned long flags; struct bcm_kona_wdt *wdt = s->private; - if (!wdt) - return seq_puts(s, "No device pointer\n"); + if (!wdt) { + seq_puts(s, "No device pointer\n"); + return 0; + } spin_lock_irqsave(&wdt->lock, flags); ctl_val = secure_register_read(wdt, SECWDOG_CTRL_REG); @@ -112,7 +114,7 @@ static int bcm_kona_wdt_dbg_show(struct seq_file *s, void *data) spin_unlock_irqrestore(&wdt->lock, flags); if (ctl_val < 0 || cur_val < 0) { - ret = seq_puts(s, "Error accessing hardware\n"); + seq_puts(s, "Error accessing hardware\n"); } else { int ctl, cur, ctl_sec, cur_sec, res; @@ -121,15 +123,18 @@ static int bcm_kona_wdt_dbg_show(struct seq_file *s, void *data) cur = cur_val & SECWDOG_COUNT_MASK; ctl_sec = TICKS_TO_SECS(ctl, wdt); cur_sec = TICKS_TO_SECS(cur, wdt); - ret = seq_printf(s, "Resolution: %d / %d\n" - "Control: %d s / %d (%#x) ticks\n" - "Current: %d s / %d (%#x) ticks\n" - "Busy count: %lu\n", res, - wdt->resolution, ctl_sec, ctl, ctl, cur_sec, - cur, cur, wdt->busy_count); + seq_printf(s, + "Resolution: %d / %d\n" + "Control: %d s / %d (%#x) ticks\n" + "Current: %d s / %d (%#x) ticks\n" + "Busy count: %lu\n", + res, wdt->resolution, + ctl_sec, ctl, ctl, + cur_sec, cur, cur, + wdt->busy_count); } - return ret; + return 0; } static int bcm_kona_dbg_open(struct inode *inode, struct file *file) diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c index 8453531545df..14521c8b3d5a 100644 --- a/drivers/watchdog/octeon-wdt-main.c +++ b/drivers/watchdog/octeon-wdt-main.c @@ -3,6 +3,8 @@ * * Copyright (C) 2007, 2008, 2009, 2010 Cavium Networks * + * Converted to use WATCHDOG_CORE by Aaro Koskinen <aaro.koskinen@iki.fi>. + * * Some parts derived from wdt.c * * (c) Copyright 1996-1997 Alan Cox <alan@lxorguk.ukuu.org.uk>, @@ -103,13 +105,10 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static unsigned long octeon_wdt_is_open; -static char expect_close; - -static u32 __initdata nmi_stage1_insns[64]; +static u32 nmi_stage1_insns[64] __initdata; /* We need one branch and therefore one relocation per target label. */ -static struct uasm_label __initdata labels[5]; -static struct uasm_reloc __initdata relocs[5]; +static struct uasm_label labels[5] __initdata; +static struct uasm_reloc relocs[5] __initdata; enum lable_id { label_enter_bootloader = 1 @@ -218,7 +217,8 @@ static void __init octeon_wdt_build_stage1(void) pr_debug("\t.set pop\n"); if (len > 32) - panic("NMI stage 1 handler exceeds 32 instructions, was %d\n", len); + panic("NMI stage 1 handler exceeds 32 instructions, was %d\n", + len); } static int cpu2core(int cpu) @@ -294,6 +294,7 @@ static void octeon_wdt_write_hex(u64 value, int digits) { int d; int v; + for (d = 0; d < digits; d++) { v = (value >> ((digits - d - 1) * 4)) & 0xf; if (v >= 10) @@ -303,7 +304,7 @@ static void octeon_wdt_write_hex(u64 value, int digits) } } -const char *reg_name[] = { +static const char reg_name[][3] = { "$0", "at", "v0", "v1", "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", "s0", "s1", "s2", "s3", "s4", "s5", "s6", "s7", @@ -444,7 +445,7 @@ static int octeon_wdt_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static void octeon_wdt_ping(void) +static int octeon_wdt_ping(struct watchdog_device __always_unused *wdog) { int cpu; int coreid; @@ -457,10 +458,12 @@ static void octeon_wdt_ping(void) !cpumask_test_cpu(cpu, &irq_enabled_cpus)) { /* We have to enable the irq */ int irq = OCTEON_IRQ_WDOG0 + coreid; + enable_irq(irq); cpumask_set_cpu(cpu, &irq_enabled_cpus); } } + return 0; } static void octeon_wdt_calc_parameters(int t) @@ -489,7 +492,8 @@ static void octeon_wdt_calc_parameters(int t) timeout_cnt = ((octeon_get_io_clock_rate() >> 8) * timeout_sec) >> 8; } -static int octeon_wdt_set_heartbeat(int t) +static int octeon_wdt_set_timeout(struct watchdog_device *wdog, + unsigned int t) { int cpu; int coreid; @@ -509,158 +513,45 @@ static int octeon_wdt_set_heartbeat(int t) cvmx_write_csr(CVMX_CIU_WDOGX(coreid), ciu_wdog.u64); cvmx_write_csr(CVMX_CIU_PP_POKEX(coreid), 1); } - octeon_wdt_ping(); /* Get the irqs back on. */ + octeon_wdt_ping(wdog); /* Get the irqs back on. */ return 0; } -/** - * octeon_wdt_write: - * @file: file handle to the watchdog - * @buf: buffer to write (unused as data does not matter here - * @count: count of bytes - * @ppos: pointer to the position to write. No seeks allowed - * - * A write to a watchdog device is defined as a keepalive signal. Any - * write of data will do, as we we don't define content meaning. - */ - -static ssize_t octeon_wdt_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - if (count) { - if (!nowayout) { - size_t i; - - /* In case it was set long ago */ - expect_close = 0; - - for (i = 0; i != count; i++) { - char c; - if (get_user(c, buf + i)) - return -EFAULT; - if (c == 'V') - expect_close = 1; - } - } - octeon_wdt_ping(); - } - return count; -} - -/** - * octeon_wdt_ioctl: - * @file: file handle to the device - * @cmd: watchdog command - * @arg: argument pointer - * - * The watchdog API defines a common set of functions for all - * watchdogs according to their available features. We only - * actually usefully support querying capabilities and setting - * the timeout. - */ - -static long octeon_wdt_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - void __user *argp = (void __user *)arg; - int __user *p = argp; - int new_heartbeat; - - static struct watchdog_info ident = { - .options = WDIOF_SETTIMEOUT| - WDIOF_MAGICCLOSE| - WDIOF_KEEPALIVEPING, - .firmware_version = 1, - .identity = "OCTEON", - }; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0; - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, p); - case WDIOC_KEEPALIVE: - octeon_wdt_ping(); - return 0; - case WDIOC_SETTIMEOUT: - if (get_user(new_heartbeat, p)) - return -EFAULT; - if (octeon_wdt_set_heartbeat(new_heartbeat)) - return -EINVAL; - /* Fall through. */ - case WDIOC_GETTIMEOUT: - return put_user(heartbeat, p); - default: - return -ENOTTY; - } -} - -/** - * octeon_wdt_open: - * @inode: inode of device - * @file: file handle to device - * - * The watchdog device has been opened. The watchdog device is single - * open and on opening we do a ping to reset the counters. - */ - -static int octeon_wdt_open(struct inode *inode, struct file *file) +static int octeon_wdt_start(struct watchdog_device *wdog) { - if (test_and_set_bit(0, &octeon_wdt_is_open)) - return -EBUSY; - /* - * Activate - */ - octeon_wdt_ping(); + octeon_wdt_ping(wdog); do_coundown = 1; - return nonseekable_open(inode, file); + return 0; } -/** - * octeon_wdt_release: - * @inode: inode to board - * @file: file handle to board - * - * The watchdog has a configurable API. There is a religious dispute - * between people who want their watchdog to be able to shut down and - * those who want to be sure if the watchdog manager dies the machine - * reboots. In the former case we disable the counters, in the latter - * case you have to open it again very soon. - */ - -static int octeon_wdt_release(struct inode *inode, struct file *file) +static int octeon_wdt_stop(struct watchdog_device *wdog) { - if (expect_close) { - do_coundown = 0; - octeon_wdt_ping(); - } else { - pr_crit("WDT device closed unexpectedly. WDT will not stop!\n"); - } - clear_bit(0, &octeon_wdt_is_open); - expect_close = 0; + do_coundown = 0; + octeon_wdt_ping(wdog); return 0; } -static const struct file_operations octeon_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = octeon_wdt_write, - .unlocked_ioctl = octeon_wdt_ioctl, - .open = octeon_wdt_open, - .release = octeon_wdt_release, +static struct notifier_block octeon_wdt_cpu_notifier = { + .notifier_call = octeon_wdt_cpu_callback, }; -static struct miscdevice octeon_wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &octeon_wdt_fops, +static const struct watchdog_info octeon_wdt_info = { + .options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING, + .identity = "OCTEON", }; -static struct notifier_block octeon_wdt_cpu_notifier = { - .notifier_call = octeon_wdt_cpu_callback, +static const struct watchdog_ops octeon_wdt_ops = { + .owner = THIS_MODULE, + .start = octeon_wdt_start, + .stop = octeon_wdt_stop, + .ping = octeon_wdt_ping, + .set_timeout = octeon_wdt_set_timeout, }; +static struct watchdog_device octeon_wdt = { + .info = &octeon_wdt_info, + .ops = &octeon_wdt_ops, +}; /** * Module/ driver initialization. @@ -685,7 +576,8 @@ static int __init octeon_wdt_init(void) max_timeout_sec = 6; do { max_timeout_sec--; - timeout_cnt = ((octeon_get_io_clock_rate() >> 8) * max_timeout_sec) >> 8; + timeout_cnt = ((octeon_get_io_clock_rate() >> 8) * + max_timeout_sec) >> 8; } while (timeout_cnt > 65535); BUG_ON(timeout_cnt == 0); @@ -694,11 +586,15 @@ static int __init octeon_wdt_init(void) pr_info("Initial granularity %d Sec\n", timeout_sec); - ret = misc_register(&octeon_wdt_miscdev); + octeon_wdt.timeout = timeout_sec; + octeon_wdt.max_timeout = UINT_MAX; + + watchdog_set_nowayout(&octeon_wdt, nowayout); + + ret = watchdog_register_device(&octeon_wdt); if (ret) { - pr_err("cannot register miscdev on minor=%d (err=%d)\n", - WATCHDOG_MINOR, ret); - goto out; + pr_err("watchdog_register_device() failed: %d\n", ret); + return ret; } /* Build the NMI handler ... */ @@ -721,8 +617,7 @@ static int __init octeon_wdt_init(void) __register_hotcpu_notifier(&octeon_wdt_cpu_notifier); cpu_notifier_register_done(); -out: - return ret; + return 0; } /** @@ -732,7 +627,7 @@ static void __exit octeon_wdt_cleanup(void) { int cpu; - misc_deregister(&octeon_wdt_miscdev); + watchdog_unregister_device(&octeon_wdt); cpu_notifier_register_begin(); __unregister_hotcpu_notifier(&octeon_wdt_cpu_notifier); diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c index 55e220150103..b9c6049c3e78 100644 --- a/drivers/watchdog/pnx4008_wdt.c +++ b/drivers/watchdog/pnx4008_wdt.c @@ -216,7 +216,7 @@ static struct platform_driver platform_wdt_driver = { module_platform_driver(platform_wdt_driver); MODULE_AUTHOR("MontaVista Software, Inc. <source@mvista.com>"); -MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>"); +MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>"); MODULE_DESCRIPTION("PNX4008 Watchdog Driver"); module_param(heartbeat, uint, 0); diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c index aa85618c4d03..aa03ca8f2d9b 100644 --- a/drivers/watchdog/qcom-wdt.c +++ b/drivers/watchdog/qcom-wdt.c @@ -20,9 +20,9 @@ #include <linux/reboot.h> #include <linux/watchdog.h> -#define WDT_RST 0x0 -#define WDT_EN 0x8 -#define WDT_BITE_TIME 0x24 +#define WDT_RST 0x38 +#define WDT_EN 0x40 +#define WDT_BITE_TIME 0x5C struct qcom_wdt { struct watchdog_device wdd; @@ -117,6 +117,8 @@ static int qcom_wdt_probe(struct platform_device *pdev) { struct qcom_wdt *wdt; struct resource *res; + struct device_node *np = pdev->dev.of_node; + u32 percpu_offset; int ret; wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL); @@ -124,6 +126,14 @@ static int qcom_wdt_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + /* We use CPU0's DGT for the watchdog */ + if (of_property_read_u32(np, "cpu-offset", &percpu_offset)) + percpu_offset = 0; + + res->start += percpu_offset; + res->end += percpu_offset; + wdt->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(wdt->base)) return PTR_ERR(wdt->base); @@ -203,9 +213,8 @@ static int qcom_wdt_remove(struct platform_device *pdev) } static const struct of_device_id qcom_wdt_of_table[] = { - { .compatible = "qcom,kpss-wdt-msm8960", }, - { .compatible = "qcom,kpss-wdt-apq8064", }, - { .compatible = "qcom,kpss-wdt-ipq8064", }, + { .compatible = "qcom,kpss-timer" }, + { .compatible = "qcom,scss-timer" }, { }, }; MODULE_DEVICE_TABLE(of, qcom_wdt_of_table); diff --git a/drivers/watchdog/stmp3xxx_rtc_wdt.c b/drivers/watchdog/stmp3xxx_rtc_wdt.c index a62b1b6decf4..e7f0d5b60d3d 100644 --- a/drivers/watchdog/stmp3xxx_rtc_wdt.c +++ b/drivers/watchdog/stmp3xxx_rtc_wdt.c @@ -1,7 +1,7 @@ /* * Watchdog driver for the RTC based watchdog in STMP3xxx and i.MX23/28 * - * Author: Wolfram Sang <w.sang@pengutronix.de> + * Author: Wolfram Sang <kernel@pengutronix.de> * * Copyright (C) 2011-12 Wolfram Sang, Pengutronix * @@ -129,4 +129,4 @@ module_platform_driver(stmp3xxx_wdt_driver); MODULE_DESCRIPTION("STMP3XXX RTC Watchdog Driver"); MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>"); +MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>"); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index a270004c9605..7cd226da15fe 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -276,4 +276,8 @@ config XEN_AUTO_XLATE help Support for auto-translated physmap guests. +config XEN_ACPI + def_bool y + depends on X86 && ACPI + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 40edd1cbb60d..e293bc507cbc 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -13,7 +13,7 @@ CFLAGS_efi.o += -fshort-wchar dom0-$(CONFIG_PCI) += pci.o dom0-$(CONFIG_USB_SUPPORT) += dbgp.o -dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y) +dom0-$(CONFIG_XEN_ACPI) += acpi.o $(xen-pad-y) xen-pad-$(CONFIG_X86) += xen-acpi-pad.o dom0-$(CONFIG_X86) += pcpu.o obj-$(CONFIG_XEN_DOM0) += $(dom0-y) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 07ef38325223..b7f51504f85a 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -204,8 +204,7 @@ static LIST_HEAD(scsiback_free_pages); static DEFINE_MUTEX(scsiback_mutex); static LIST_HEAD(scsiback_list); -/* Local pointer to allocated TCM configfs fabric module */ -static struct target_fabric_configfs *scsiback_fabric_configfs; +static const struct target_core_fabric_ops scsiback_ops; static void scsiback_get(struct vscsibk_info *info) { @@ -1902,7 +1901,7 @@ scsiback_make_tpg(struct se_wwn *wwn, tpg->tport = tport; tpg->tport_tpgt = tpgt; - ret = core_tpg_register(&scsiback_fabric_configfs->tf_ops, wwn, + ret = core_tpg_register(&scsiback_ops, wwn, &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); if (ret < 0) { kfree(tpg); @@ -1944,7 +1943,9 @@ static int scsiback_check_false(struct se_portal_group *se_tpg) return 0; } -static struct target_core_fabric_ops scsiback_ops = { +static const struct target_core_fabric_ops scsiback_ops = { + .module = THIS_MODULE, + .name = "xen-pvscsi", .get_fabric_name = scsiback_get_fabric_name, .get_fabric_proto_ident = scsiback_get_fabric_proto_ident, .tpg_get_wwn = scsiback_get_fabric_wwn, @@ -1991,62 +1992,10 @@ static struct target_core_fabric_ops scsiback_ops = { .fabric_make_nodeacl = scsiback_make_nodeacl, .fabric_drop_nodeacl = scsiback_drop_nodeacl, #endif -}; - -static int scsiback_register_configfs(void) -{ - struct target_fabric_configfs *fabric; - int ret; - - pr_debug("fabric module %s on %s/%s on "UTS_RELEASE"\n", - VSCSI_VERSION, utsname()->sysname, utsname()->machine); - /* - * Register the top level struct config_item_type with TCM core - */ - fabric = target_fabric_configfs_init(THIS_MODULE, "xen-pvscsi"); - if (IS_ERR(fabric)) - return PTR_ERR(fabric); - /* - * Setup fabric->tf_ops from our local scsiback_ops - */ - fabric->tf_ops = scsiback_ops; - /* - * Setup default attribute lists for various fabric->tf_cit_tmpl - */ - fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = scsiback_wwn_attrs; - fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = scsiback_tpg_attrs; - fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = scsiback_param_attrs; - fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL; - fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL; - /* - * Register the fabric for use within TCM - */ - ret = target_fabric_configfs_register(fabric); - if (ret < 0) { - target_fabric_configfs_free(fabric); - return ret; - } - /* - * Setup our local pointer to *fabric - */ - scsiback_fabric_configfs = fabric; - pr_debug("Set fabric -> scsiback_fabric_configfs\n"); - return 0; -}; - -static void scsiback_deregister_configfs(void) -{ - if (!scsiback_fabric_configfs) - return; - - target_fabric_configfs_deregister(scsiback_fabric_configfs); - scsiback_fabric_configfs = NULL; - pr_debug("Cleared scsiback_fabric_configfs\n"); + .tfc_wwn_attrs = scsiback_wwn_attrs, + .tfc_tpg_base_attrs = scsiback_tpg_attrs, + .tfc_tpg_param_attrs = scsiback_param_attrs, }; static const struct xenbus_device_id scsiback_ids[] = { @@ -2078,6 +2027,9 @@ static int __init scsiback_init(void) if (!xen_domain()) return -ENODEV; + pr_debug("xen-pvscsi: fabric module %s on %s/%s on "UTS_RELEASE"\n", + VSCSI_VERSION, utsname()->sysname, utsname()->machine); + scsiback_cachep = kmem_cache_create("vscsiif_cache", sizeof(struct vscsibk_pend), 0, 0, scsiback_init_pend); if (!scsiback_cachep) @@ -2087,7 +2039,7 @@ static int __init scsiback_init(void) if (ret) goto out_cache_destroy; - ret = scsiback_register_configfs(); + ret = target_register_template(&scsiback_ops); if (ret) goto out_unregister_xenbus; @@ -2110,7 +2062,7 @@ static void __exit scsiback_exit(void) BUG(); gnttab_free_pages(1, &page); } - scsiback_deregister_configfs(); + target_unregister_template(&scsiback_ops); xenbus_unregister_driver(&scsiback_driver); kmem_cache_destroy(scsiback_cachep); } |