struct resource *res;
kernel_code.start = virt_to_phys(_text);
- kernel_code.end = virt_to_phys(_etext - 1);
+ kernel_code.end = virt_to_phys(__init_begin - 1);
kernel_data.start = virt_to_phys(_sdata);
kernel_data.end = virt_to_phys(_end - 1);
*/
cpu_uninstall_idmap();
+ xen_early_init();
efi_init();
arm64_memblock_init();
+ paging_init();
+
+ acpi_table_upgrade();
+
/* Parse the ACPI tables for possible boot-time configuration */
acpi_boot_table_init();
- paging_init();
-
if (acpi_disabled)
unflatten_device_tree();
else
psci_acpi_init();
- xen_early_init();
-
cpu_read_bootcpu_ops();
smp_init_cpus();
smp_build_mpidr_hash();
static inline void prefill_possible_map(void) {}
#define cpu_physical_id(cpu) boot_cpu_physical_apicid
+ #define cpu_acpi_id(cpu) 0
#define safe_smp_processor_id() 0
-#define stack_smp_processor_id() 0
#endif /* CONFIG_SMP */
}
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
int native_cpu_disable(void);
int common_cpu_die(unsigned int cpu);
void native_cpu_die(unsigned int cpu);
+void hlt_play_dead(void);
void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
void smp_store_boot_cpu_info(void);
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
+ #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu)
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
#elif defined(CONFIG_X86_64_SMP)
#define raw_smp_processor_id() (this_cpu_read(cpu_number))
-#define stack_smp_processor_id() \
-({ \
- struct thread_info *ti; \
- __asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \
- ti->cpu; \
-})
#define safe_smp_processor_id() smp_processor_id()
#endif
*/
DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid, BAD_APICID);
+ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
#ifdef CONFIG_X86_32
int thiscpu = max + disabled_cpus - 1;
pr_warning(
- "ACPI: NR_CPUS/possible_cpus limit of %i almost"
+ "APIC: NR_CPUS/possible_cpus limit of %i almost"
" reached. Keeping one slot for boot cpu."
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
int thiscpu = max + disabled_cpus;
pr_warning(
- "ACPI: NR_CPUS/possible_cpus limit of %i reached."
+ "APIC: NR_CPUS/possible_cpus limit of %i reached."
" Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
disabled_cpus++;
if (topology_update_package_map(apicid, cpu) < 0) {
int thiscpu = max + disabled_cpus;
- pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n",
+ pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
disabled_cpus++;
return -ENOSPC;
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
+ #include <asm/xen/cpuid.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/proto.h>
*/
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+ /* Linux <-> Xen vCPU id mapping */
+ DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+ EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);
#endif
}
- static void xen_vcpu_setup(int cpu)
+ void xen_vcpu_setup(int cpu)
{
struct vcpu_register_vcpu_info info;
int err;
if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
return;
}
- if (cpu < MAX_VIRT_CPUS)
- per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
+ per_cpu(xen_vcpu, cpu) =
+ &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
if (!have_vcpu_info_placement) {
if (cpu >= MAX_VIRT_CPUS)
hypervisor has no unregister variant and this hypercall does not
allow to over-write info.mfn and info.offset.
*/
- err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
+ err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+ &info);
if (err) {
printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
for_each_possible_cpu(cpu) {
bool other_cpu = (cpu != smp_processor_id());
- bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL);
+ bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu),
+ NULL);
if (other_cpu && is_up &&
- HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+ HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
BUG();
xen_setup_runstate_info(cpu);
xen_vcpu_setup(cpu);
if (other_cpu && is_up &&
- HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+ HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
BUG();
}
}
preempt_disable();
- pagefault_disable(); /* Avoid warnings due to being atomic. */
- __get_user(dummy, (unsigned char __user __force *)v);
- pagefault_enable();
+ probe_kernel_read(&dummy, v, 1);
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
unsigned long frames[pages];
int f;
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
unsigned long frames[pages];
int f;
{
int cpu;
- for_each_possible_cpu(cpu)
+ for_each_possible_cpu(cpu) {
+ /* Set up direct vCPU id mapping for PV guests. */
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_vcpu_setup(cpu);
+ }
/* xen_vcpu_setup managed to place the vcpu_info within the
* percpu area for all cpus, so make use of it. Note that for
#endif
xen_raw_console_write("about to get started...\n");
+ /* Let's presume PV guests always boot on vCPU with id 0. */
+ per_cpu(xen_vcpu_id, 0) = 0;
+
xen_setup_runstate_info(0);
xen_efi_init();
* in that case multiple vcpus might be online. */
for_each_online_cpu(cpu) {
/* Leave it to be NULL. */
- if (cpu >= MAX_VIRT_CPUS)
+ if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
continue;
- per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ per_cpu(xen_vcpu, cpu) =
+ &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
}
}
xen_setup_features();
+ cpuid(base + 4, &eax, &ebx, &ecx, &edx);
+ if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
+ this_cpu_write(xen_vcpu_id, ebx);
+ else
+ this_cpu_write(xen_vcpu_id, smp_processor_id());
+
pv_info.name = "Xen HVM";
xen_domain_type = XEN_HVM_DOMAIN;
int cpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
+ if (cpu_acpi_id(cpu) != U32_MAX)
+ per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
+ else
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_vcpu_setup(cpu);
if (xen_have_vector_callback) {
if (xen_feature(XENFEAT_hvm_safe_pvclock))
LIST_HEAD(acpi_wakeup_device_list);
static DEFINE_MUTEX(acpi_hp_context_lock);
+ /*
+ * The UART device described by the SPCR table is the only object which needs
+ * special-casing. Everything else is covered by ACPI namespace paths in STAO
+ * table.
+ */
+ static u64 spcr_uart_addr;
+
struct acpi_dep_data {
struct list_head node;
acpi_handle master;
device_del(&device->dev);
}
+static BLOCKING_NOTIFIER_HEAD(acpi_reconfig_chain);
+
static LIST_HEAD(acpi_device_del_list);
static DEFINE_MUTEX(acpi_device_del_lock);
mutex_unlock(&acpi_device_del_lock);
+ blocking_notifier_call_chain(&acpi_reconfig_chain,
+ ACPI_RECONFIG_DEVICE_REMOVE, adev);
+
acpi_device_del(adev);
/*
* Drop references to all power resources that might have been
acpi_bus_get_flags(device);
device->flags.match_driver = false;
device->flags.initialized = true;
- device->flags.visited = false;
+ acpi_device_clear_enumerated(device);
device_initialize(&device->dev);
dev_set_uevent_suppress(&device->dev, true);
acpi_init_coherency(device);
return 0;
}
+ static acpi_status acpi_get_resource_memory(struct acpi_resource *ares,
+ void *context)
+ {
+ struct resource *res = context;
+
+ if (acpi_dev_resource_memory(ares, res))
+ return AE_CTRL_TERMINATE;
+
+ return AE_OK;
+ }
+
+ static bool acpi_device_should_be_hidden(acpi_handle handle)
+ {
+ acpi_status status;
+ struct resource res;
+
+ /* Check if it should ignore the UART device */
+ if (!(spcr_uart_addr && acpi_has_method(handle, METHOD_NAME__CRS)))
+ return false;
+
+ /*
+ * The UART device described in SPCR table is assumed to have only one
+ * memory resource present. So we only look for the first one here.
+ */
+ status = acpi_walk_resources(handle, METHOD_NAME__CRS,
+ acpi_get_resource_memory, &res);
+ if (ACPI_FAILURE(status) || res.start != spcr_uart_addr)
+ return false;
+
+ acpi_handle_info(handle, "The UART device @%pa in SPCR table will be hidden\n",
+ &res.start);
+
+ return true;
+ }
+
static int acpi_bus_type_and_status(acpi_handle handle, int *type,
unsigned long long *sta)
{
switch (acpi_type) {
case ACPI_TYPE_ANY: /* for ACPI_ROOT_OBJECT */
case ACPI_TYPE_DEVICE:
+ if (acpi_device_should_be_hidden(handle))
+ return -ENODEV;
+
*type = ACPI_BUS_TYPE_DEVICE;
status = acpi_bus_get_status_handle(handle, sta);
if (ACPI_FAILURE(status))
bool is_spi_i2c_slave = false;
/*
- * Do not enemerate SPI/I2C slaves as they will be enuerated by their
+ * Do not enumerate SPI/I2C slaves as they will be enumerated by their
* respective parents.
*/
INIT_LIST_HEAD(&resource_list);
acpi_dev_get_resources(device, &resource_list, acpi_check_spi_i2c_slave,
&is_spi_i2c_slave);
acpi_dev_free_resource_list(&resource_list);
- if (!is_spi_i2c_slave)
+ if (!is_spi_i2c_slave) {
acpi_create_platform_device(device);
+ acpi_device_set_enumerated(device);
+ } else {
+ blocking_notifier_call_chain(&acpi_reconfig_chain,
+ ACPI_RECONFIG_DEVICE_ADD, device);
+ }
}
static const struct acpi_device_id generic_device_ids[] = {
acpi_bus_get_status(device);
/* Skip devices that are not present. */
if (!acpi_device_is_present(device)) {
- device->flags.visited = false;
+ acpi_device_clear_enumerated(device);
device->flags.power_manageable = 0;
return;
}
device->flags.initialized = true;
}
- device->flags.visited = false;
+
ret = acpi_scan_attach_handler(device);
if (ret < 0)
return;
if (!ret && device->pnp.type.platform_id)
acpi_default_enumeration(device);
}
- device->flags.visited = true;
ok:
list_for_each_entry(child, &device->children, node)
*/
acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
adev->flags.initialized = false;
- adev->flags.visited = false;
+ acpi_device_clear_enumerated(adev);
}
EXPORT_SYMBOL_GPL(acpi_bus_trim);
return result < 0 ? result : 0;
}
+ static void __init acpi_get_spcr_uart_addr(void)
+ {
+ acpi_status status;
+ struct acpi_table_spcr *spcr_ptr;
+
+ status = acpi_get_table(ACPI_SIG_SPCR, 0,
+ (struct acpi_table_header **)&spcr_ptr);
+ if (ACPI_SUCCESS(status))
+ spcr_uart_addr = spcr_ptr->serial_port.address;
+ else
+ printk(KERN_WARNING PREFIX "STAO table present, but SPCR is missing\n");
+ }
+
+static bool acpi_scan_initialized;
+
int __init acpi_scan_init(void)
{
int result;
+ acpi_status status;
+ struct acpi_table_stao *stao_ptr;
acpi_pci_root_init();
acpi_pci_link_init();
acpi_scan_add_handler(&generic_device_handler);
+ /*
+ * If there is STAO table, check whether it needs to ignore the UART
+ * device in SPCR table.
+ */
+ status = acpi_get_table(ACPI_SIG_STAO, 0,
+ (struct acpi_table_header **)&stao_ptr);
+ if (ACPI_SUCCESS(status)) {
+ if (stao_ptr->header.length > sizeof(struct acpi_table_stao))
+ printk(KERN_INFO PREFIX "STAO Name List not yet supported.");
+
+ if (stao_ptr->ignore_uart)
+ acpi_get_spcr_uart_addr();
+ }
+
mutex_lock(&acpi_scan_lock);
/*
* Enumerate devices in the ACPI namespace.
acpi_update_all_gpes();
+ acpi_scan_initialized = true;
+
out:
mutex_unlock(&acpi_scan_lock);
return result;
return count;
}
+
+struct acpi_table_events_work {
+ struct work_struct work;
+ void *table;
+ u32 event;
+};
+
+static void acpi_table_events_fn(struct work_struct *work)
+{
+ struct acpi_table_events_work *tew;
+
+ tew = container_of(work, struct acpi_table_events_work, work);
+
+ if (tew->event == ACPI_TABLE_EVENT_LOAD) {
+ acpi_scan_lock_acquire();
+ acpi_bus_scan(ACPI_ROOT_OBJECT);
+ acpi_scan_lock_release();
+ }
+
+ kfree(tew);
+}
+
+void acpi_scan_table_handler(u32 event, void *table, void *context)
+{
+ struct acpi_table_events_work *tew;
+
+ if (!acpi_scan_initialized)
+ return;
+
+ if (event != ACPI_TABLE_EVENT_LOAD)
+ return;
+
+ tew = kmalloc(sizeof(*tew), GFP_KERNEL);
+ if (!tew)
+ return;
+
+ INIT_WORK(&tew->work, acpi_table_events_fn);
+ tew->table = table;
+ tew->event = event;
+
+ schedule_work(&tew->work);
+}
+
+int acpi_reconfig_notifier_register(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&acpi_reconfig_chain, nb);
+}
+EXPORT_SYMBOL(acpi_reconfig_notifier_register);
+
+int acpi_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&acpi_reconfig_chain, nb);
+}
+EXPORT_SYMBOL(acpi_reconfig_notifier_unregister);
NULL
};
- static struct attribute_group xen_vbdstat_group = {
+ static const struct attribute_group xen_vbdstat_group = {
.name = "statistics",
.attrs = xen_vbdstat_attrs,
};
if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags))
vbd->flush_support = true;
- if (q && blk_queue_secdiscard(q))
+ if (q && blk_queue_secure_erase(q))
vbd->discard_secure = true;
pr_debug("Successful creation of handle=%04x (dom=%u)\n",
/* Front end dir is a number, which is used as the handle. */
err = kstrtoul(strrchr(dev->otherend, '/') + 1, 0, &handle);
- if (err)
+ if (err) {
+ kfree(be->mode);
+ be->mode = NULL;
return;
+ }
be->major = major;
be->minor = minor;
pr_debug("%s %s\n", __func__, dev->otherend);
be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT;
- err = xenbus_gather(XBT_NIL, dev->otherend, "protocol",
- "%63s", protocol, NULL);
- if (err)
+ err = xenbus_scanf(XBT_NIL, dev->otherend, "protocol",
+ "%63s", protocol);
+ if (err <= 0)
strcpy(protocol, "unspecified, assuming default");
else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE))
be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE;
xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol);
return -ENOSYS;
}
- err = xenbus_gather(XBT_NIL, dev->otherend,
- "feature-persistent", "%u",
- &pers_grants, NULL);
- if (err)
+ err = xenbus_scanf(XBT_NIL, dev->otherend,
+ "feature-persistent", "%u", &pers_grants);
+ if (err <= 0)
pers_grants = 0;
be->blkif->vbd.feature_gnt_persistent = pers_grants;
unsigned int nr_ring_pages;
struct request_queue *rq;
unsigned int feature_flush;
+ unsigned int feature_fua;
unsigned int feature_discard:1;
unsigned int feature_secdiscard:1;
unsigned int discard_granularity;
struct blk_mq_tag_set tag_set;
struct blkfront_ring_info *rinfo;
unsigned int nr_rings;
+ /* Save uncomplete reqs and bios for migration. */
+ struct list_head requests;
+ struct bio_list bio_list;
};
static unsigned int nr_minors;
ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
ring_req->u.discard.id = id;
ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
- if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+ if (req_op(req) == REQ_OP_SECURE_ERASE && info->feature_secdiscard)
ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
else
ring_req->u.discard.flag = 0;
* The indirect operation can only be a BLKIF_OP_READ or
* BLKIF_OP_WRITE
*/
- BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+ BUG_ON(req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA);
ring_req->operation = BLKIF_OP_INDIRECT;
ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
ring_req->u.rw.handle = info->handle;
ring_req->operation = rq_data_dir(req) ?
BLKIF_OP_WRITE : BLKIF_OP_READ;
- if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+ if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) {
/*
* Ideally we can do an unordered flush-to-disk.
* In case the backend onlysupports barriers, use that.
* implement it the same way. (It's also a FLUSH+FUA,
* since it is guaranteed ordered WRT previous writes.)
*/
- switch (info->feature_flush &
- ((REQ_FLUSH|REQ_FUA))) {
- case REQ_FLUSH|REQ_FUA:
+ if (info->feature_flush && info->feature_fua)
ring_req->operation =
BLKIF_OP_WRITE_BARRIER;
- break;
- case REQ_FLUSH:
+ else if (info->feature_flush)
ring_req->operation =
BLKIF_OP_FLUSH_DISKCACHE;
- break;
- default:
+ else
ring_req->operation = 0;
- }
}
ring_req->u.rw.nr_segments = num_grant;
if (unlikely(require_extra_req)) {
if (unlikely(rinfo->dev_info->connected != BLKIF_STATE_CONNECTED))
return 1;
- if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE)))
+ if (unlikely(req_op(req) == REQ_OP_DISCARD ||
+ req_op(req) == REQ_OP_SECURE_ERASE))
return blkif_queue_discard_req(req, rinfo);
else
return blkif_queue_rw_req(req, rinfo);
struct blkfront_info *info)
{
return ((req->cmd_type != REQ_TYPE_FS) ||
- ((req->cmd_flags & REQ_FLUSH) &&
- !(info->feature_flush & REQ_FLUSH)) ||
+ ((req_op(req) == REQ_OP_FLUSH) &&
+ !info->feature_flush) ||
((req->cmd_flags & REQ_FUA) &&
- !(info->feature_flush & REQ_FUA)));
+ !info->feature_fua));
}
static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
rq->limits.discard_granularity = info->discard_granularity;
rq->limits.discard_alignment = info->discard_alignment;
if (info->feature_secdiscard)
- queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
+ queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
}
/* Hard sector size and max sectors impersonate the equiv. hardware. */
return 0;
}
-static const char *flush_info(unsigned int feature_flush)
+static const char *flush_info(struct blkfront_info *info)
{
- switch (feature_flush & ((REQ_FLUSH | REQ_FUA))) {
- case REQ_FLUSH|REQ_FUA:
+ if (info->feature_flush && info->feature_fua)
return "barrier: enabled;";
- case REQ_FLUSH:
+ else if (info->feature_flush)
return "flush diskcache: enabled;";
- default:
+ else
return "barrier or flush: disabled;";
- }
}
static void xlvbd_flush(struct blkfront_info *info)
{
- blk_queue_write_cache(info->rq, info->feature_flush & REQ_FLUSH,
- info->feature_flush & REQ_FUA);
+ blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
+ info->feature_fua ? true : false);
pr_info("blkfront: %s: %s %s %s %s %s\n",
- info->gd->disk_name, flush_info(info->feature_flush),
+ info->gd->disk_name, flush_info(info),
"persistent grants:", info->feature_persistent ?
"enabled;" : "disabled;", "indirect descriptors:",
info->max_indirect_segments ? "enabled;" : "disabled;");
gd->first_minor = minor;
gd->fops = &xlvbd_block_fops;
gd->private_data = info;
- gd->driverfs_dev = &(info->xbdev->dev);
set_capacity(gd, capacity);
if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
- queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
+ queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
}
blk_mq_complete_request(req, error);
break;
if (unlikely(error)) {
if (error == -EOPNOTSUPP)
error = 0;
+ info->feature_fua = 0;
info->feature_flush = 0;
xlvbd_flush(info);
}
{
unsigned int i, r_index;
struct request *req, *n;
- struct blk_shadow *copy;
int rc;
struct bio *bio, *cloned_bio;
- struct bio_list bio_list, merge_bio;
unsigned int segs, offset;
int pending, size;
struct split_bio *split_bio;
- struct list_head requests;
blkfront_gather_backend_features(info);
segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
blk_queue_max_segments(info->rq, segs);
- bio_list_init(&bio_list);
- INIT_LIST_HEAD(&requests);
for (r_index = 0; r_index < info->nr_rings; r_index++) {
- struct blkfront_ring_info *rinfo;
-
- rinfo = &info->rinfo[r_index];
- /* Stage 1: Make a safe copy of the shadow state. */
- copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow),
- GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
- if (!copy)
- return -ENOMEM;
-
- /* Stage 2: Set up free list. */
- memset(&rinfo->shadow, 0, sizeof(rinfo->shadow));
- for (i = 0; i < BLK_RING_SIZE(info); i++)
- rinfo->shadow[i].req.u.rw.id = i+1;
- rinfo->shadow_free = rinfo->ring.req_prod_pvt;
- rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
+ struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
rc = blkfront_setup_indirect(rinfo);
- if (rc) {
- kfree(copy);
+ if (rc)
return rc;
- }
-
- for (i = 0; i < BLK_RING_SIZE(info); i++) {
- /* Not in use? */
- if (!copy[i].request)
- continue;
-
- /*
- * Get the bios in the request so we can re-queue them.
- */
- if (copy[i].request->cmd_flags &
- (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) {
- /*
- * Flush operations don't contain bios, so
- * we need to requeue the whole request
- */
- list_add(©[i].request->queuelist, &requests);
- continue;
- }
- merge_bio.head = copy[i].request->bio;
- merge_bio.tail = copy[i].request->biotail;
- bio_list_merge(&bio_list, &merge_bio);
- copy[i].request->bio = NULL;
- blk_end_request_all(copy[i].request, 0);
- }
-
- kfree(copy);
}
xenbus_switch_state(info->xbdev, XenbusStateConnected);
kick_pending_request_queues(rinfo);
}
- list_for_each_entry_safe(req, n, &requests, queuelist) {
+ list_for_each_entry_safe(req, n, &info->requests, queuelist) {
/* Requeue pending requests (flush or discard) */
list_del_init(&req->queuelist);
BUG_ON(req->nr_phys_segments > segs);
}
blk_mq_kick_requeue_list(info->rq);
- while ((bio = bio_list_pop(&bio_list)) != NULL) {
+ while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
/* Traverse the list of pending bios and re-queue them */
if (bio_segments(bio) > segs) {
/*
bio_trim(cloned_bio, offset, size);
cloned_bio->bi_private = split_bio;
cloned_bio->bi_end_io = split_bio_end;
- submit_bio(cloned_bio->bi_rw, cloned_bio);
+ submit_bio(cloned_bio);
}
/*
* Now we have to wait for all those smaller bios to
continue;
}
/* We don't need to split this bio */
- submit_bio(bio->bi_rw, bio);
+ submit_bio(bio);
}
return 0;
{
struct blkfront_info *info = dev_get_drvdata(&dev->dev);
int err = 0;
+ unsigned int i, j;
dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
+ bio_list_init(&info->bio_list);
+ INIT_LIST_HEAD(&info->requests);
+ for (i = 0; i < info->nr_rings; i++) {
+ struct blkfront_ring_info *rinfo = &info->rinfo[i];
+ struct bio_list merge_bio;
+ struct blk_shadow *shadow = rinfo->shadow;
+
+ for (j = 0; j < BLK_RING_SIZE(info); j++) {
+ /* Not in use? */
+ if (!shadow[j].request)
+ continue;
+
+ /*
+ * Get the bios in the request so we can re-queue them.
+ */
+ if (req_op(shadow[i].request) == REQ_OP_FLUSH ||
+ req_op(shadow[i].request) == REQ_OP_DISCARD ||
+ req_op(shadow[i].request) == REQ_OP_SECURE_ERASE ||
+ shadow[j].request->cmd_flags & REQ_FUA) {
+ /*
+ * Flush operations don't contain bios, so
+ * we need to requeue the whole request
+ *
+ * XXX: but this doesn't make any sense for a
+ * write with the FUA flag set..
+ */
+ list_add(&shadow[j].request->queuelist, &info->requests);
+ continue;
+ }
+ merge_bio.head = shadow[j].request->bio;
+ merge_bio.tail = shadow[j].request->biotail;
+ bio_list_merge(&info->bio_list, &merge_bio);
+ shadow[j].request->bio = NULL;
+ blk_mq_end_request(shadow[j].request, 0);
+ }
+ }
+
blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
err = negotiate_mq(info);
info->discard_granularity = discard_granularity;
info->discard_alignment = discard_alignment;
}
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "discard-secure", "%d", &discard_secure,
- NULL);
- if (!err)
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "discard-secure", "%u", &discard_secure);
+ if (err > 0)
info->feature_secdiscard = !!discard_secure;
}
unsigned int indirect_segments;
info->feature_flush = 0;
+ info->feature_fua = 0;
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-barrier", "%d", &barrier,
- NULL);
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "feature-barrier", "%d", &barrier);
/*
* If there's no "feature-barrier" defined, then it means
*
* If there are barriers, then we use flush.
*/
- if (!err && barrier) {
- if (err > 0 && barrier)
- info->feature_flush = REQ_FLUSH | REQ_FUA;
++ if (err > 0 && barrier) {
+ info->feature_flush = 1;
+ info->feature_fua = 1;
+ }
+
/*
* And if there is "feature-flush-cache" use that above
* barriers.
*/
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-flush-cache", "%d", &flush,
- NULL);
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "feature-flush-cache", "%d", &flush);
- if (!err && flush) {
- if (err > 0 && flush)
- info->feature_flush = REQ_FLUSH;
++ if (err > 0 && flush) {
+ info->feature_flush = 1;
+ info->feature_fua = 0;
+ }
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-discard", "%d", &discard,
- NULL);
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "feature-discard", "%d", &discard);
- if (!err && discard)
+ if (err > 0 && discard)
blkfront_setup_discard(info);
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-persistent", "%u", &persistent,
- NULL);
- if (err)
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "feature-persistent", "%d", &persistent);
+ if (err <= 0)
info->feature_persistent = 0;
else
info->feature_persistent = persistent;
- err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
- "feature-max-indirect-segments", "%u", &indirect_segments,
- NULL);
- if (err)
+ err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+ "feature-max-indirect-segments", "%u",
+ &indirect_segments);
+ if (err <= 0)
info->max_indirect_segments = 0;
else
info->max_indirect_segments = min(indirect_segments,
for (i = 0; i < info->nr_rings; i++)
kick_pending_request_queues(&info->rinfo[i]);
- add_disk(info->gd);
+ device_add_disk(&info->xbdev->dev, info->gd);
info->is_ready = 1;
}
#include <linux/of_fdt.h>
#include <linux/io.h>
#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/acpi.h>
+#include <linux/ucs2_string.h>
#include <asm/early_ioremap.h>
efivars_unregister(&generic_efivars);
}
+#if IS_ENABLED(CONFIG_ACPI)
+#define EFIVAR_SSDT_NAME_MAX 16
+static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
+static int __init efivar_ssdt_setup(char *str)
+{
+ if (strlen(str) < sizeof(efivar_ssdt))
+ memcpy(efivar_ssdt, str, strlen(str));
+ else
+ pr_warn("efivar_ssdt: name too long: %s\n", str);
+ return 0;
+}
+__setup("efivar_ssdt=", efivar_ssdt_setup);
+
+static __init int efivar_ssdt_iter(efi_char16_t *name, efi_guid_t vendor,
+ unsigned long name_size, void *data)
+{
+ struct efivar_entry *entry;
+ struct list_head *list = data;
+ char utf8_name[EFIVAR_SSDT_NAME_MAX];
+ int limit = min_t(unsigned long, EFIVAR_SSDT_NAME_MAX, name_size);
+
+ ucs2_as_utf8(utf8_name, name, limit - 1);
+ if (strncmp(utf8_name, efivar_ssdt, limit) != 0)
+ return 0;
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return 0;
+
+ memcpy(entry->var.VariableName, name, name_size);
+ memcpy(&entry->var.VendorGuid, &vendor, sizeof(efi_guid_t));
+
+ efivar_entry_add(entry, list);
+
+ return 0;
+}
+
+static __init int efivar_ssdt_load(void)
+{
+ LIST_HEAD(entries);
+ struct efivar_entry *entry, *aux;
+ unsigned long size;
+ void *data;
+ int ret;
+
+ ret = efivar_init(efivar_ssdt_iter, &entries, true, &entries);
+
+ list_for_each_entry_safe(entry, aux, &entries, list) {
+ pr_info("loading SSDT from variable %s-%pUl\n", efivar_ssdt,
+ &entry->var.VendorGuid);
+
+ list_del(&entry->list);
+
+ ret = efivar_entry_size(entry, &size);
+ if (ret) {
+ pr_err("failed to get var size\n");
+ goto free_entry;
+ }
+
+ data = kmalloc(size, GFP_KERNEL);
+ if (!data)
+ goto free_entry;
+
+ ret = efivar_entry_get(entry, NULL, &size, data);
+ if (ret) {
+ pr_err("failed to get var data\n");
+ goto free_data;
+ }
+
+ ret = acpi_load_table(data);
+ if (ret) {
+ pr_err("failed to load table: %d\n", ret);
+ goto free_data;
+ }
+
+ goto free_entry;
+
+free_data:
+ kfree(data);
+
+free_entry:
+ kfree(entry);
+ }
+
+ return ret;
+}
+#else
+static inline int efivar_ssdt_load(void) { return 0; }
+#endif
+
/*
* We register the efi subsystem with the firmware subsystem and the
* efivars subsystem with the efi subsystem, if the system was booted with
if (error)
goto err_put;
+ if (efi_enabled(EFI_RUNTIME_SERVICES))
+ efivar_ssdt_load();
+
error = sysfs_create_group(efi_kobj, &efi_subsys_attr_group);
if (error) {
pr_err("efi: Sysfs attribute export failed with error %d.\n",
FIELD_SIZEOF(struct efi_fdt_params, field) \
}
- static __initdata struct {
+ struct params {
const char name[32];
const char propname[32];
int offset;
int size;
- } dt_params[] = {
+ };
+
+ static __initdata struct params fdt_params[] = {
UEFI_PARAM("System Table", "linux,uefi-system-table", system_table),
UEFI_PARAM("MemMap Address", "linux,uefi-mmap-start", mmap),
UEFI_PARAM("MemMap Size", "linux,uefi-mmap-size", mmap_size),
UEFI_PARAM("MemMap Desc. Version", "linux,uefi-mmap-desc-ver", desc_ver)
};
+ static __initdata struct params xen_fdt_params[] = {
+ UEFI_PARAM("System Table", "xen,uefi-system-table", system_table),
+ UEFI_PARAM("MemMap Address", "xen,uefi-mmap-start", mmap),
+ UEFI_PARAM("MemMap Size", "xen,uefi-mmap-size", mmap_size),
+ UEFI_PARAM("MemMap Desc. Size", "xen,uefi-mmap-desc-size", desc_size),
+ UEFI_PARAM("MemMap Desc. Version", "xen,uefi-mmap-desc-ver", desc_ver)
+ };
+
+ #define EFI_FDT_PARAMS_SIZE ARRAY_SIZE(fdt_params)
+
+ static __initdata struct {
+ const char *uname;
+ const char *subnode;
+ struct params *params;
+ } dt_params[] = {
+ { "hypervisor", "uefi", xen_fdt_params },
+ { "chosen", NULL, fdt_params },
+ };
+
struct param_info {
int found;
void *params;
+ const char *missing;
};
- static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
- int depth, void *data)
+ static int __init __find_uefi_params(unsigned long node,
+ struct param_info *info,
+ struct params *params)
{
- struct param_info *info = data;
const void *prop;
void *dest;
u64 val;
int i, len;
- if (depth != 1 || strcmp(uname, "chosen") != 0)
- return 0;
-
- for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
- prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len);
- if (!prop)
+ for (i = 0; i < EFI_FDT_PARAMS_SIZE; i++) {
+ prop = of_get_flat_dt_prop(node, params[i].propname, &len);
+ if (!prop) {
+ info->missing = params[i].name;
return 0;
- dest = info->params + dt_params[i].offset;
+ }
+
+ dest = info->params + params[i].offset;
info->found++;
val = of_read_number(prop, len / sizeof(u32));
- if (dt_params[i].size == sizeof(u32))
+ if (params[i].size == sizeof(u32))
*(u32 *)dest = val;
else
*(u64 *)dest = val;
if (efi_enabled(EFI_DBG))
- pr_info(" %s: 0x%0*llx\n", dt_params[i].name,
- dt_params[i].size * 2, val);
+ pr_info(" %s: 0x%0*llx\n", params[i].name,
+ params[i].size * 2, val);
}
+
return 1;
}
+ static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
+ int depth, void *data)
+ {
+ struct param_info *info = data;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
+ const char *subnode = dt_params[i].subnode;
+
+ if (depth != 1 || strcmp(uname, dt_params[i].uname) != 0) {
+ info->missing = dt_params[i].params[0].name;
+ continue;
+ }
+
+ if (subnode) {
+ node = of_get_flat_dt_subnode_by_name(node, subnode);
+ if (node < 0)
+ return 0;
+ }
+
+ return __find_uefi_params(node, info, dt_params[i].params);
+ }
+
+ return 0;
+ }
+
int __init efi_get_fdt_params(struct efi_fdt_params *params)
{
struct param_info info;
pr_info("UEFI not found.\n");
else if (!ret)
pr_err("Can't find '%s' in device tree!\n",
- dt_params[info.found].name);
+ info.missing);
return ret;
}
*/
void irqtime_account_irq(struct task_struct *curr)
{
- unsigned long flags;
s64 delta;
int cpu;
if (!sched_clock_irqtime)
return;
- local_irq_save(flags);
-
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
__this_cpu_add(irq_start_time, delta);
__this_cpu_add(cpu_softirq_time, delta);
irq_time_write_end();
- local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
-static int irqtime_account_hi_update(void)
+static cputime_t irqtime_account_hi_update(cputime_t maxtime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
unsigned long flags;
- u64 latest_ns;
- int ret = 0;
+ cputime_t irq_cputime;
local_irq_save(flags);
- latest_ns = this_cpu_read(cpu_hardirq_time);
- if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
- ret = 1;
+ irq_cputime = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time)) -
+ cpustat[CPUTIME_IRQ];
+ irq_cputime = min(irq_cputime, maxtime);
+ cpustat[CPUTIME_IRQ] += irq_cputime;
local_irq_restore(flags);
- return ret;
+ return irq_cputime;
}
-static int irqtime_account_si_update(void)
+static cputime_t irqtime_account_si_update(cputime_t maxtime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
unsigned long flags;
- u64 latest_ns;
- int ret = 0;
+ cputime_t softirq_cputime;
local_irq_save(flags);
- latest_ns = this_cpu_read(cpu_softirq_time);
- if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
- ret = 1;
+ softirq_cputime = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time)) -
+ cpustat[CPUTIME_SOFTIRQ];
+ softirq_cputime = min(softirq_cputime, maxtime);
+ cpustat[CPUTIME_SOFTIRQ] += softirq_cputime;
local_irq_restore(flags);
- return ret;
+ return softirq_cputime;
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
#define sched_clock_irqtime (0)
+static cputime_t irqtime_account_hi_update(cputime_t dummy)
+{
+ return 0;
+}
+
+static cputime_t irqtime_account_si_update(cputime_t dummy)
+{
+ return 0;
+}
+
#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
static inline void task_group_account_field(struct task_struct *p, int index,
cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}
-static __always_inline bool steal_account_process_tick(void)
+static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
+ cputime_t steal_cputime;
u64 steal;
- unsigned long steal_jiffies;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
- /*
- * steal is in nsecs but our caller is expecting steal
- * time in jiffies. Lets cast the result to jiffies
- * granularity and account the rest on the next rounds.
- */
- steal_jiffies = nsecs_to_jiffies(steal);
- this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
+ steal_cputime = min(nsecs_to_cputime(steal), maxtime);
+ account_steal_time(steal_cputime);
+ this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime);
- account_steal_time(jiffies_to_cputime(steal_jiffies));
- return steal_jiffies;
+ return steal_cputime;
}
#endif
- return false;
+ return 0;
+}
+
+/*
+ * Account how much elapsed time was spent in steal, irq, or softirq time.
+ */
+static inline cputime_t account_other_time(cputime_t max)
+{
+ cputime_t accounted;
+
+ accounted = steal_account_process_time(max);
+
+ if (accounted < max)
+ accounted += irqtime_account_hi_update(max - accounted);
+
+ if (accounted < max)
+ accounted += irqtime_account_si_update(max - accounted);
+
+ return accounted;
}
/*
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
struct rq *rq, int ticks)
{
- cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
- u64 cputime = (__force u64) cputime_one_jiffy;
- u64 *cpustat = kcpustat_this_cpu->cpustat;
+ u64 cputime = (__force u64) cputime_one_jiffy * ticks;
+ cputime_t scaled, other;
- if (steal_account_process_tick())
+ /*
+ * When returning from idle, many ticks can get accounted at
+ * once, including some ticks of steal, irq, and softirq time.
+ * Subtract those ticks from the amount of time accounted to
+ * idle, or potentially user or system time. Due to rounding,
+ * other time can exceed ticks occasionally.
+ */
+ other = account_other_time(cputime);
+ if (other >= cputime)
return;
+ cputime -= other;
+ scaled = cputime_to_scaled(cputime);
- cputime *= ticks;
- scaled *= ticks;
-
- if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += cputime;
- } else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += cputime;
- } else if (this_cpu_ksoftirqd() == p) {
+ if (this_cpu_ksoftirqd() == p) {
/*
* ksoftirqd time do not get accounted in cpu_softirq_time.
* So, we have to handle it separately here.
}
#endif
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
/*
* Archs that account the whole time spent in the idle task
* (outside irq) as idle time can rely on this and just implement
* vtime_account().
*/
#ifndef __ARCH_HAS_VTIME_ACCOUNT
-void vtime_common_account_irq_enter(struct task_struct *tsk)
+void vtime_account_irq_enter(struct task_struct *tsk)
{
- if (!in_interrupt()) {
- /*
- * If we interrupted user, context_tracking_in_user()
- * is 1 because the context tracking don't hook
- * on irq entry/exit. This way we know if
- * we need to flush user time on kernel entry.
- */
- if (context_tracking_in_user()) {
- vtime_account_user(tsk);
- return;
- }
-
- if (is_idle_task(tsk)) {
- vtime_account_idle(tsk);
- return;
- }
- }
- vtime_account_system(tsk);
+ if (!in_interrupt() && is_idle_task(tsk))
+ vtime_account_idle(tsk);
+ else
+ vtime_account_system(tsk);
}
-EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter);
+EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
#endif /* __ARCH_HAS_VTIME_ACCOUNT */
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
*ut = p->utime;
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
- cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime_t cputime, scaled, steal;
struct rq *rq = this_rq();
if (vtime_accounting_cpu_enabled())
return;
}
- if (steal_account_process_tick())
+ cputime = cputime_one_jiffy;
+ steal = steal_account_process_time(cputime);
+
+ if (steal >= cputime)
return;
+ cputime -= steal;
+ scaled = cputime_to_scaled(cputime);
+
if (user_tick)
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ account_user_time(p, cputime, scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
- account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
- one_jiffy_scaled);
+ account_system_time(p, HARDIRQ_OFFSET, cputime, scaled);
else
- account_idle_time(cputime_one_jiffy);
+ account_idle_time(cputime);
}
- /*
- * Account multiple ticks of steal time.
- * @p: the process from which the cpu time has been stolen
- * @ticks: number of stolen ticks
- */
- void account_steal_ticks(unsigned long ticks)
- {
- account_steal_time(jiffies_to_cputime(ticks));
- }
-
/*
* Account multiple ticks of idle time.
* @ticks: number of stolen ticks
static cputime_t get_vtime_delta(struct task_struct *tsk)
{
unsigned long now = READ_ONCE(jiffies);
- unsigned long delta = now - tsk->vtime_snap;
+ cputime_t delta, other;
+ delta = jiffies_to_cputime(now - tsk->vtime_snap);
+ other = account_other_time(delta);
WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
tsk->vtime_snap = now;
- return jiffies_to_cputime(delta);
+ return delta - other;
}
static void __vtime_account_system(struct task_struct *tsk)
write_seqcount_end(&tsk->vtime_seqcount);
}
-void vtime_gen_account_irq_exit(struct task_struct *tsk)
-{
- write_seqcount_begin(&tsk->vtime_seqcount);
- if (vtime_delta(tsk))
- __vtime_account_system(tsk);
- if (context_tracking_in_user())
- tsk->vtime_snap_whence = VTIME_USER;
- write_seqcount_end(&tsk->vtime_seqcount);
-}
-
void vtime_account_user(struct task_struct *tsk)
{
cputime_t delta_cpu;