Merge branch 'akpm'
* akpm:
mm: madvise(MADV_DODUMP): allow hugetlbfs pages
ocfs2: fix locking for res->tracking and dlm->tracking_list
mm/vmscan.c: fix int overflow in callers of do_shrink_slab()
mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly
mm/vmstat.c: fix outdated vmstat_text
proc: restrict kernel stack dumps to root
mm/hugetlb: add mmap() encodings for 32MB and 512MB page sizes
mm/migrate.c: split only transparent huge pages when allocation fails
ipc/shm.c: use ERR_CAST() for shm_lock() error return
mm/gup_benchmark: fix unsigned comparison to zero in __gup_benchmark_ioctl
mm, thp: fix mlocking THP page with migration enabled
ocfs2: fix crash in ocfs2_duplicate_clusters_by_page()
hugetlb: take PMD sharing into account when flushing tlb/caches
mm: migration: fix migration of huge PMD shared pages
diff --git a/MAINTAINERS b/MAINTAINERS
index 2206504..48a65c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -324,7 +324,6 @@
F: Documentation/ABI/testing/configfs-acpi
F: drivers/pci/*acpi*
F: drivers/pci/*/*acpi*
-F: drivers/pci/*/*/*acpi*
F: tools/power/acpi/
ACPI APEI
@@ -8599,7 +8598,6 @@
F: arch/*/include/asm/spinlock*.h
F: include/linux/rwlock*.h
F: include/linux/mutex*.h
-F: arch/*/include/asm/mutex*.h
F: include/linux/rwsem*.h
F: arch/*/include/asm/rwsem.h
F: include/linux/seqlock.h
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index fa3f439..141d415 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -68,7 +68,13 @@
CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
$(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
-fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
@@ -138,7 +144,13 @@
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
$(obj)/vdso32.so.dbg: FORCE \
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index f19856d..e48ca3af 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -43,8 +43,9 @@ extern u8 hvclock_page
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
- asm("syscall" : "=a" (ret) :
- "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+ asm ("syscall" : "=a" (ret), "=m" (*ts) :
+ "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+ "memory", "rcx", "r11");
return ret;
}
@@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
{
long ret;
- asm("syscall" : "=a" (ret) :
- "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+ asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
+ "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
+ "memory", "rcx", "r11");
return ret;
}
@@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
- asm(
+ asm (
"mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
+ "mov %[clock], %%ebx \n"
"call __kernel_vsyscall \n"
"mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+ : "=a" (ret), "=m" (*ts)
+ : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
: "memory", "edx");
return ret;
}
@@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
{
long ret;
- asm(
+ asm (
"mov %%ebx, %%edx \n"
- "mov %2, %%ebx \n"
+ "mov %[tv], %%ebx \n"
"call __kernel_vsyscall \n"
"mov %%edx, %%ebx \n"
- : "=a" (ret)
- : "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+ : "=a" (ret), "=m" (*tv), "=m" (*tz)
+ : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
: "memory", "edx");
return ret;
}
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e..8671de1 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
static int num_counters_llc;
static int num_counters_nb;
+static bool l3_mask;
static HLIST_HEAD(uncore_unused_list);
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
hwc->idx = -1;
+ /*
+ * SliceMask and ThreadMask need to be set for certain L3 events in
+ * Family 17h. For other events, the two fields do not affect the count.
+ */
+ if (l3_mask)
+ hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
if (event->cpu < 0)
return -EINVAL;
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
amd_llc_pmu.name = "amd_l3";
format_attr_event_df.show = &event_show_df;
format_attr_event_l3.show = &event_show_l3;
+ l3_mask = true;
} else {
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
amd_llc_pmu.name = "amd_l2";
format_attr_event_df = format_attr_event;
format_attr_event_l3 = format_attr_event;
+ l3_mask = false;
}
amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 51d7c11..c07bee3 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = {
void bdx_uncore_cpu_init(void)
{
- int pkg = topology_phys_to_logical_pkg(0);
+ int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
@@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = {
.driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3),
},
{ /* M3UPI0 Link 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0),
},
{ /* M3UPI0 Link 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1),
},
{ /* M3UPI1 Link 2 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C),
- .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2),
},
{ /* end: all zeroes */ }
};
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f5408..78241b7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
#define INTEL_ARCH_EVENT_MASK \
(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+#define AMD64_L3_SLICE_SHIFT 48
+#define AMD64_L3_SLICE_MASK \
+ ((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT 56
+#define AMD64_L3_THREAD_MASK \
+ ((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
#define X86_RAW_EVENT_MASK \
(ARCH_PERFMON_EVENTSEL_EVENT | \
ARCH_PERFMON_EVENTSEL_UMASK | \
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index a80c067..e60c45f 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -10,8 +10,13 @@ struct cpumask;
struct mm_struct;
#ifdef CONFIG_X86_UV
+#include <linux/efi.h>
extern enum uv_system_type get_uv_system_type(void);
+static inline bool is_early_uv_system(void)
+{
+ return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab);
+}
extern int is_uv_system(void);
extern int is_uv_hubless(void);
extern void uv_cpu_init(void);
@@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
#else /* X86_UV */
static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline bool is_early_uv_system(void) { return 0; }
static inline int is_uv_system(void) { return 0; }
static inline int is_uv_hubless(void) { return 0; }
static inline void uv_cpu_init(void) { }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 22ab4081..eeea634 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c)
static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
{
/* AMD errata T13 (order #21922) */
- if ((c->x86 == 6)) {
+ if (c->x86 == 6) {
/* Duron Rev A0 */
if (c->x86_model == 3 && c->x86_stepping == 0)
size = 64;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6490f61..b52bd2b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -26,6 +26,7 @@
#include <asm/apic.h>
#include <asm/intel-family.h>
#include <asm/i8259.h>
+#include <asm/uv/uv.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
@@ -1433,6 +1434,9 @@ void __init tsc_early_init(void)
{
if (!boot_cpu_has(X86_FEATURE_TSC))
return;
+ /* Don't change UV TSC multi-chassis synchronization */
+ if (is_early_uv_system())
+ return;
if (!determine_cpu_tsc_frequencies(true))
return;
loops_per_jiffy = get_loops_per_jiffy();
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 3f68e29..a690fd4 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1713,8 +1713,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
dpm_wait_for_subordinate(dev, async);
- if (async_error)
+ if (async_error) {
+ dev->power.direct_complete = false;
goto Complete;
+ }
/*
* If a device configured to wake up the system from sleep states
@@ -1726,6 +1728,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
pm_wakeup_event(dev, 0);
if (pm_wakeup_pending()) {
+ dev->power.direct_complete = false;
async_error = -EBUSY;
goto Complete;
}
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e8f8a19..a57300c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -571,7 +571,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
if (ret)
goto out_free_descs;
lh->descs[i] = desc;
- count = i;
+ count = i + 1;
if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW)
set_bit(FLAG_ACTIVE_LOW, &desc->flags);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 69dddea..5936de7 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -1455,8 +1455,8 @@ static int __load_mappings(struct dm_cache_metadata *cmd,
if (hints_valid) {
r = dm_array_cursor_next(&cmd->hint_cursor);
if (r) {
- DMERR("dm_array_cursor_next for hint failed");
- goto out;
+ dm_array_cursor_end(&cmd->hint_cursor);
+ hints_valid = false;
}
}
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index a534133..e13d991 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -3009,8 +3009,13 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache)
static bool can_resize(struct cache *cache, dm_cblock_t new_size)
{
- if (from_cblock(new_size) > from_cblock(cache->cache_size))
- return true;
+ if (from_cblock(new_size) > from_cblock(cache->cache_size)) {
+ if (cache->sized) {
+ DMERR("%s: unable to extend cache due to missing cache table reload",
+ cache_device_name(cache));
+ return false;
+ }
+ }
/*
* We can't drop a dirty block when shrinking the cache.
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index d94ba6f..419362c 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -806,19 +806,19 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg,
}
static int setup_scsi_dh(struct block_device *bdev, struct multipath *m,
- const char *attached_handler_name, char **error)
+ const char **attached_handler_name, char **error)
{
struct request_queue *q = bdev_get_queue(bdev);
int r;
if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags)) {
retain:
- if (attached_handler_name) {
+ if (*attached_handler_name) {
/*
* Clear any hw_handler_params associated with a
* handler that isn't already attached.
*/
- if (m->hw_handler_name && strcmp(attached_handler_name, m->hw_handler_name)) {
+ if (m->hw_handler_name && strcmp(*attached_handler_name, m->hw_handler_name)) {
kfree(m->hw_handler_params);
m->hw_handler_params = NULL;
}
@@ -830,7 +830,8 @@ static int setup_scsi_dh(struct block_device *bdev, struct multipath *m,
* handler instead of the original table passed in.
*/
kfree(m->hw_handler_name);
- m->hw_handler_name = attached_handler_name;
+ m->hw_handler_name = *attached_handler_name;
+ *attached_handler_name = NULL;
}
}
@@ -867,7 +868,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
struct pgpath *p;
struct multipath *m = ti->private;
struct request_queue *q;
- const char *attached_handler_name;
+ const char *attached_handler_name = NULL;
/* we need at least a path arg */
if (as->argc < 1) {
@@ -890,7 +891,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL);
if (attached_handler_name || m->hw_handler_name) {
INIT_DELAYED_WORK(&p->activate_path, activate_path_work);
- r = setup_scsi_dh(p->path.dev->bdev, m, attached_handler_name, &ti->error);
+ r = setup_scsi_dh(p->path.dev->bdev, m, &attached_handler_name, &ti->error);
if (r) {
dm_put_device(ti, p->path.dev);
goto bad;
@@ -905,6 +906,7 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps
return p;
bad:
+ kfree(attached_handler_name);
free_pgpath(p);
return ERR_PTR(r);
}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5ba067f..c44925e 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3353,7 +3353,7 @@ static const char *sync_str(enum sync_state state)
};
/* Return enum sync_state for @mddev derived from @recovery flags */
-static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery)
+static enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery)
{
if (test_bit(MD_RECOVERY_FROZEN, &recovery))
return st_frozen;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 74f6770..20b0776 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -832,10 +832,8 @@ static void __set_metadata_reserve(struct dm_pool_metadata *pmd)
if (r) {
DMERR("could not get size of metadata device");
pmd->metadata_reserve = max_blocks;
- } else {
- sector_div(total, 10);
- pmd->metadata_reserve = min(max_blocks, total);
- }
+ } else
+ pmd->metadata_reserve = min(max_blocks, div_u64(total, 10));
}
struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 50eb072..a41d79b 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1145,7 +1145,6 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
{
struct device *dev = &pcie->pdev->dev;
struct device_node *np = dev->of_node;
- unsigned int i;
int ret;
INIT_LIST_HEAD(&pcie->resources);
@@ -1179,15 +1178,60 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
resource_size(&pcie->io) - 1);
pcie->realio.name = "PCI I/O";
- for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
- pci_ioremap_io(i, pcie->io.start + i);
-
pci_add_resource(&pcie->resources, &pcie->realio);
}
return devm_request_pci_bus_resources(dev, &pcie->resources);
}
+/*
+ * This is a copy of pci_host_probe(), except that it does the I/O
+ * remap as the last step, once we are sure we won't fail.
+ *
+ * It should be removed once the I/O remap error handling issue has
+ * been sorted out.
+ */
+static int mvebu_pci_host_probe(struct pci_host_bridge *bridge)
+{
+ struct mvebu_pcie *pcie;
+ struct pci_bus *bus, *child;
+ int ret;
+
+ ret = pci_scan_root_bus_bridge(bridge);
+ if (ret < 0) {
+ dev_err(bridge->dev.parent, "Scanning root bridge failed");
+ return ret;
+ }
+
+ pcie = pci_host_bridge_priv(bridge);
+ if (resource_size(&pcie->io) != 0) {
+ unsigned int i;
+
+ for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
+ pci_ioremap_io(i, pcie->io.start + i);
+ }
+
+ bus = bridge->bus;
+
+ /*
+ * We insert PCI resources into the iomem_resource and
+ * ioport_resource trees in either pci_bus_claim_resources()
+ * or pci_bus_assign_resources().
+ */
+ if (pci_has_flag(PCI_PROBE_ONLY)) {
+ pci_bus_claim_resources(bus);
+ } else {
+ pci_bus_size_bridges(bus);
+ pci_bus_assign_resources(bus);
+
+ list_for_each_entry(child, &bus->children, node)
+ pcie_bus_configure_settings(child);
+ }
+
+ pci_bus_add_devices(bus);
+ return 0;
+}
+
static int mvebu_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -1268,7 +1312,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
bridge->align_resource = mvebu_pcie_align_resource;
bridge->msi = pcie->msi;
- return pci_host_probe(bridge);
+ return mvebu_pci_host_probe(bridge);
}
static const struct of_device_id mvebu_pcie_of_match_table[] = {
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1835f3a..51b6c81 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1289,12 +1289,12 @@ int pci_save_state(struct pci_dev *dev)
EXPORT_SYMBOL(pci_save_state);
static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
- u32 saved_val, int retry)
+ u32 saved_val, int retry, bool force)
{
u32 val;
pci_read_config_dword(pdev, offset, &val);
- if (val == saved_val)
+ if (!force && val == saved_val)
return;
for (;;) {
@@ -1313,25 +1313,36 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
}
static void pci_restore_config_space_range(struct pci_dev *pdev,
- int start, int end, int retry)
+ int start, int end, int retry,
+ bool force)
{
int index;
for (index = end; index >= start; index--)
pci_restore_config_dword(pdev, 4 * index,
pdev->saved_config_space[index],
- retry);
+ retry, force);
}
static void pci_restore_config_space(struct pci_dev *pdev)
{
if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
- pci_restore_config_space_range(pdev, 10, 15, 0);
+ pci_restore_config_space_range(pdev, 10, 15, 0, false);
/* Restore BARs before the command register. */
- pci_restore_config_space_range(pdev, 4, 9, 10);
- pci_restore_config_space_range(pdev, 0, 3, 0);
+ pci_restore_config_space_range(pdev, 4, 9, 10, false);
+ pci_restore_config_space_range(pdev, 0, 3, 0, false);
+ } else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+ pci_restore_config_space_range(pdev, 12, 15, 0, false);
+
+ /*
+ * Force rewriting of prefetch registers to avoid S3 resume
+ * issues on Intel PCI bridges that occur when these
+ * registers are not explicitly written.
+ */
+ pci_restore_config_space_range(pdev, 9, 11, 0, true);
+ pci_restore_config_space_range(pdev, 0, 8, 0, false);
} else {
- pci_restore_config_space_range(pdev, 0, 15, 0);
+ pci_restore_config_space_range(pdev, 0, 15, 0, false);
}
}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1e22d96..3f4c0b1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -671,12 +671,6 @@ typedef struct pglist_data {
#ifdef CONFIG_NUMA_BALANCING
/* Lock serializing the migrate rate limiting window */
spinlock_t numabalancing_migrate_lock;
-
- /* Rate limiting time interval */
- unsigned long numabalancing_migrate_next_window;
-
- /* Number of pages migrated during the rate limiting time interval */
- unsigned long numabalancing_migrate_nr_pages;
#endif
/*
* This is a per-node reserve of pages that are not available
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 7113728..705b33d 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages,
__print_symbolic(__entry->mode, MIGRATE_MODE),
__print_symbolic(__entry->reason, MIGRATE_REASON))
);
-
-TRACE_EVENT(mm_numa_migrate_ratelimit,
-
- TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages),
-
- TP_ARGS(p, dst_nid, nr_pages),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN)
- __field( pid_t, pid)
- __field( int, dst_nid)
- __field( unsigned long, nr_pages)
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->dst_nid = dst_nid;
- __entry->nr_pages = nr_pages;
- ),
-
- TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu",
- __entry->comm,
- __entry->pid,
- __entry->dst_nid,
- __entry->nr_pages)
-);
#endif /* _TRACE_MIGRATE_H */
/* This part must be outside protection */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index dcb093e..5a97f34 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8314,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
goto unlock;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+ if (event->cpu != smp_processor_id())
+ continue;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
continue;
if (event->attr.config != entry->type)
@@ -9431,9 +9433,7 @@ static void free_pmu_context(struct pmu *pmu)
if (pmu->task_ctx_nr > perf_invalid_context)
return;
- mutex_lock(&pmus_lock);
free_percpu(pmu->pmu_cpu_context);
- mutex_unlock(&pmus_lock);
}
/*
@@ -9689,12 +9689,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
void perf_pmu_unregister(struct pmu *pmu)
{
- int remove_device;
-
mutex_lock(&pmus_lock);
- remove_device = pmu_bus_running;
list_del_rcu(&pmu->entry);
- mutex_unlock(&pmus_lock);
/*
* We dereference the pmu list under both SRCU and regular RCU, so
@@ -9706,13 +9702,14 @@ void perf_pmu_unregister(struct pmu *pmu)
free_percpu(pmu->pmu_disable_count);
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
- if (remove_device) {
+ if (pmu_bus_running) {
if (pmu->nr_addr_filters)
device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
device_del(pmu->dev);
put_device(pmu->dev);
}
free_pmu_context(pmu);
+ mutex_unlock(&pmus_lock);
}
EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0be047d..65a3b7e 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work)
{
struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
struct ww_acquire_ctx ctx;
- int err;
+ int err, erra = 0;
ww_acquire_init(&ctx, &ww_class);
ww_mutex_lock(&cycle->a_mutex, &ctx);
@@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work)
err = ww_mutex_lock(cycle->b_mutex, &ctx);
if (err == -EDEADLK) {
+ err = 0;
ww_mutex_unlock(&cycle->a_mutex);
ww_mutex_lock_slow(cycle->b_mutex, &ctx);
- err = ww_mutex_lock(&cycle->a_mutex, &ctx);
+ erra = ww_mutex_lock(&cycle->a_mutex, &ctx);
}
if (!err)
ww_mutex_unlock(cycle->b_mutex);
- ww_mutex_unlock(&cycle->a_mutex);
+ if (!erra)
+ ww_mutex_unlock(&cycle->a_mutex);
ww_acquire_fini(&ctx);
- cycle->result = err;
+ cycle->result = err ?: erra;
}
static int __test_cycle(unsigned int nthreads)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 625bc98..ad97f3b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1167,7 +1167,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
if (task_cpu(p) != new_cpu) {
if (p->sched_class->migrate_task_rq)
- p->sched_class->migrate_task_rq(p);
+ p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
rseq_migrate(p);
perf_event_task_migrate(p);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 997ea7b..91e4202 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1607,7 +1607,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
return cpu;
}
-static void migrate_task_rq_dl(struct task_struct *p)
+static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
{
struct rq *rq;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f808ddf..7fc4a37 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1392,6 +1392,17 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int last_cpupid, this_cpupid;
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+ last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+
+ /*
+ * Allow first faults or private faults to migrate immediately early in
+ * the lifetime of a task. The magic number 4 is based on waiting for
+ * two full passes of the "multi-stage node selection" test that is
+ * executed below.
+ */
+ if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) &&
+ (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid)))
+ return true;
/*
* Multi-stage node selection is used in conjunction with a periodic
@@ -1410,7 +1421,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
* This quadric squishes small probabilities, making it less likely we
* act on an unlikely task<->page relation.
*/
- last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
if (!cpupid_pid_unset(last_cpupid) &&
cpupid_to_nid(last_cpupid) != dst_nid)
return false;
@@ -1514,6 +1524,21 @@ struct task_numa_env {
static void task_numa_assign(struct task_numa_env *env,
struct task_struct *p, long imp)
{
+ struct rq *rq = cpu_rq(env->dst_cpu);
+
+ /* Bail out if run-queue part of active NUMA balance. */
+ if (xchg(&rq->numa_migrate_on, 1))
+ return;
+
+ /*
+ * Clear previous best_cpu/rq numa-migrate flag, since task now
+ * found a better CPU to move/swap.
+ */
+ if (env->best_cpu != -1) {
+ rq = cpu_rq(env->best_cpu);
+ WRITE_ONCE(rq->numa_migrate_on, 0);
+ }
+
if (env->best_task)
put_task_struct(env->best_task);
if (p)
@@ -1553,6 +1578,13 @@ static bool load_too_imbalanced(long src_load, long dst_load,
}
/*
+ * Maximum NUMA importance can be 1998 (2*999);
+ * SMALLIMP @ 30 would be close to 1998/64.
+ * Used to deter task migration.
+ */
+#define SMALLIMP 30
+
+/*
* This checks if the overall compute and NUMA accesses of the system would
* be improved if the source tasks was migrated to the target dst_cpu taking
* into account that it might be best if task running on the dst_cpu should
@@ -1569,6 +1601,9 @@ static void task_numa_compare(struct task_numa_env *env,
long moveimp = imp;
int dist = env->dist;
+ if (READ_ONCE(dst_rq->numa_migrate_on))
+ return;
+
rcu_read_lock();
cur = task_rcu_dereference(&dst_rq->curr);
if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
@@ -1582,7 +1617,7 @@ static void task_numa_compare(struct task_numa_env *env,
goto unlock;
if (!cur) {
- if (maymove || imp > env->best_imp)
+ if (maymove && moveimp >= env->best_imp)
goto assign;
else
goto unlock;
@@ -1625,16 +1660,22 @@ static void task_numa_compare(struct task_numa_env *env,
task_weight(cur, env->dst_nid, dist);
}
- if (imp <= env->best_imp)
- goto unlock;
-
if (maymove && moveimp > imp && moveimp > env->best_imp) {
- imp = moveimp - 1;
+ imp = moveimp;
cur = NULL;
goto assign;
}
/*
+ * If the NUMA importance is less than SMALLIMP,
+ * task migration might only result in ping pong
+ * of tasks and also hurt performance due to cache
+ * misses.
+ */
+ if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2)
+ goto unlock;
+
+ /*
* In the overloaded case, try and keep the load balanced.
*/
load = task_h_load(env->p) - task_h_load(cur);
@@ -1710,6 +1751,7 @@ static int task_numa_migrate(struct task_struct *p)
.best_cpu = -1,
};
struct sched_domain *sd;
+ struct rq *best_rq;
unsigned long taskweight, groupweight;
int nid, ret, dist;
long taskimp, groupimp;
@@ -1805,20 +1847,17 @@ static int task_numa_migrate(struct task_struct *p)
if (env.best_cpu == -1)
return -EAGAIN;
- /*
- * Reset the scan period if the task is being rescheduled on an
- * alternative node to recheck if the tasks is now properly placed.
- */
- p->numa_scan_period = task_scan_start(p);
-
+ best_rq = cpu_rq(env.best_cpu);
if (env.best_task == NULL) {
ret = migrate_task_to(p, env.best_cpu);
+ WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
return ret;
}
ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+ WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
@@ -2596,6 +2635,39 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
}
}
+static void update_scan_period(struct task_struct *p, int new_cpu)
+{
+ int src_nid = cpu_to_node(task_cpu(p));
+ int dst_nid = cpu_to_node(new_cpu);
+
+ if (!static_branch_likely(&sched_numa_balancing))
+ return;
+
+ if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING))
+ return;
+
+ if (src_nid == dst_nid)
+ return;
+
+ /*
+ * Allow resets if faults have been trapped before one scan
+ * has completed. This is most likely due to a new task that
+ * is pulled cross-node due to wakeups or load balancing.
+ */
+ if (p->numa_scan_seq) {
+ /*
+ * Avoid scan adjustments if moving to the preferred
+ * node or if the task was not previously running on
+ * the preferred node.
+ */
+ if (dst_nid == p->numa_preferred_nid ||
+ (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid))
+ return;
+ }
+
+ p->numa_scan_period = task_scan_start(p);
+}
+
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
@@ -2609,6 +2681,10 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
}
+static inline void update_scan_period(struct task_struct *p, int new_cpu)
+{
+}
+
#endif /* CONFIG_NUMA_BALANCING */
static void
@@ -6275,7 +6351,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se);
* cfs_rq_of(p) references at time of call are still valid and identify the
* previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
*/
-static void migrate_task_rq_fair(struct task_struct *p)
+static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
{
/*
* As blocked tasks retain absolute vruntime the migration needs to
@@ -6328,6 +6404,8 @@ static void migrate_task_rq_fair(struct task_struct *p)
/* We have migrated, no longer consider this task hot */
p->se.exec_start = 0;
+
+ update_scan_period(p, new_cpu);
}
static void task_dead_fair(struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4a2e8ca..455fa33 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -783,6 +783,7 @@ struct rq {
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
+ unsigned int numa_migrate_on;
#endif
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
@@ -1523,7 +1524,7 @@ struct sched_class {
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
- void (*migrate_task_rq)(struct task_struct *p);
+ void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
diff --git a/mm/migrate.c b/mm/migrate.c
index 9ba72c2..84381b5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1858,46 +1858,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
return newpage;
}
-/*
- * page migration rate limiting control.
- * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
- * window of time. Default here says do not migrate more than 1280M per second.
- */
-static unsigned int migrate_interval_millisecs __read_mostly = 100;
-static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
-
-/* Returns true if the node is migrate rate-limited after the update */
-static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
- unsigned long nr_pages)
-{
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
- spin_lock(&pgdat->numabalancing_migrate_lock);
- pgdat->numabalancing_migrate_nr_pages = 0;
- pgdat->numabalancing_migrate_next_window = jiffies +
- msecs_to_jiffies(migrate_interval_millisecs);
- spin_unlock(&pgdat->numabalancing_migrate_lock);
- }
- if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
- trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
- nr_pages);
- return true;
- }
-
- /*
- * This is an unlocked non-atomic update so errors are possible.
- * The consequences are failing to migrate when we potentiall should
- * have which is not severe enough to warrant locking. If it is ever
- * a problem, it can be converted to a per-cpu counter.
- */
- pgdat->numabalancing_migrate_nr_pages += nr_pages;
- return false;
-}
-
static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
int page_lru;
@@ -1970,14 +1930,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
if (page_is_file_cache(page) && PageDirty(page))
goto out;
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (numamigrate_update_ratelimit(pgdat, 1))
- goto out;
-
isolated = numamigrate_isolate_page(pgdat, page);
if (!isolated)
goto out;
@@ -2024,14 +1976,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
unsigned long mmun_start = address & HPAGE_PMD_MASK;
unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
- goto out_dropref;
-
new_page = alloc_pages_node(node,
(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
HPAGE_PMD_ORDER);
@@ -2128,7 +2072,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
out_fail:
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-out_dropref:
ptl = pmd_lock(mm, pmd);
if (pmd_same(*pmd, entry)) {
entry = pmd_modify(entry, vma->vm_page_prot);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89d2a2a..706a738 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
static void pgdat_init_numabalancing(struct pglist_data *pgdat)
{
spin_lock_init(&pgdat->numabalancing_migrate_lock);
- pgdat->numabalancing_migrate_nr_pages = 0;
- pgdat->numabalancing_migrate_next_window = jiffies;
}
#else
static void pgdat_init_numabalancing(struct pglist_data *pgdat) {}
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index b5282cbb..617ff1a 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -145,9 +145,11 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
if (!acomp->ops) {
request_module("i915");
/* 10s timeout */
- wait_for_completion_timeout(&bind_complete, 10 * 1000);
+ wait_for_completion_timeout(&bind_complete,
+ msecs_to_jiffies(10 * 1000));
}
if (!acomp->ops) {
+ dev_info(bus->dev, "couldn't bind with audio component\n");
snd_hdac_acomp_exit(bus);
return -ENODEV;
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1d117f0..3ac7ba9 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6409,6 +6409,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+ SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3),
SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 2352590..35edd61 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -17,6 +17,7 @@
#include <errno.h>
#include <sched.h>
#include <stdbool.h>
+#include <limits.h>
#ifndef SYS_getcpu
# ifdef __x86_64__
@@ -31,6 +32,14 @@
int nerrs = 0;
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+
+vgettime_t vdso_clock_gettime;
+
+typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz);
+
+vgtod_t vdso_gettimeofday;
+
typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
getcpu_t vgetcpu;
@@ -95,6 +104,15 @@ static void fill_function_pointers()
printf("Warning: failed to find getcpu in vDSO\n");
vgetcpu = (getcpu_t) vsyscall_getcpu();
+
+ vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+ if (!vdso_clock_gettime)
+ printf("Warning: failed to find clock_gettime in vDSO\n");
+
+ vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday");
+ if (!vdso_gettimeofday)
+ printf("Warning: failed to find gettimeofday in vDSO\n");
+
}
static long sys_getcpu(unsigned * cpu, unsigned * node,
@@ -103,6 +121,16 @@ static long sys_getcpu(unsigned * cpu, unsigned * node,
return syscall(__NR_getcpu, cpu, node, cache);
}
+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
+{
+ return syscall(__NR_clock_gettime, id, ts);
+}
+
+static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ return syscall(__NR_gettimeofday, tv, tz);
+}
+
static void test_getcpu(void)
{
printf("[RUN]\tTesting getcpu...\n");
@@ -155,10 +183,154 @@ static void test_getcpu(void)
}
}
+static bool ts_leq(const struct timespec *a, const struct timespec *b)
+{
+ if (a->tv_sec != b->tv_sec)
+ return a->tv_sec < b->tv_sec;
+ else
+ return a->tv_nsec <= b->tv_nsec;
+}
+
+static bool tv_leq(const struct timeval *a, const struct timeval *b)
+{
+ if (a->tv_sec != b->tv_sec)
+ return a->tv_sec < b->tv_sec;
+ else
+ return a->tv_usec <= b->tv_usec;
+}
+
+static char const * const clocknames[] = {
+ [0] = "CLOCK_REALTIME",
+ [1] = "CLOCK_MONOTONIC",
+ [2] = "CLOCK_PROCESS_CPUTIME_ID",
+ [3] = "CLOCK_THREAD_CPUTIME_ID",
+ [4] = "CLOCK_MONOTONIC_RAW",
+ [5] = "CLOCK_REALTIME_COARSE",
+ [6] = "CLOCK_MONOTONIC_COARSE",
+ [7] = "CLOCK_BOOTTIME",
+ [8] = "CLOCK_REALTIME_ALARM",
+ [9] = "CLOCK_BOOTTIME_ALARM",
+ [10] = "CLOCK_SGI_CYCLE",
+ [11] = "CLOCK_TAI",
+};
+
+static void test_one_clock_gettime(int clock, const char *name)
+{
+ struct timespec start, vdso, end;
+ int vdso_ret, end_ret;
+
+ printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock);
+
+ if (sys_clock_gettime(clock, &start) < 0) {
+ if (errno == EINVAL) {
+ vdso_ret = vdso_clock_gettime(clock, &vdso);
+ if (vdso_ret == -EINVAL) {
+ printf("[OK]\tNo such clock.\n");
+ } else {
+ printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret);
+ nerrs++;
+ }
+ } else {
+ printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno);
+ }
+ return;
+ }
+
+ vdso_ret = vdso_clock_gettime(clock, &vdso);
+ end_ret = sys_clock_gettime(clock, &end);
+
+ if (vdso_ret != 0 || end_ret != 0) {
+ printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+ vdso_ret, errno);
+ nerrs++;
+ return;
+ }
+
+ printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+ (unsigned long long)start.tv_sec, start.tv_nsec,
+ (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
+ (unsigned long long)end.tv_sec, end.tv_nsec);
+
+ if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) {
+ printf("[FAIL]\tTimes are out of sequence\n");
+ nerrs++;
+ }
+}
+
+static void test_clock_gettime(void)
+{
+ for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
+ clock++) {
+ test_one_clock_gettime(clock, clocknames[clock]);
+ }
+
+ /* Also test some invalid clock ids */
+ test_one_clock_gettime(-1, "invalid");
+ test_one_clock_gettime(INT_MIN, "invalid");
+ test_one_clock_gettime(INT_MAX, "invalid");
+}
+
+static void test_gettimeofday(void)
+{
+ struct timeval start, vdso, end;
+ struct timezone sys_tz, vdso_tz;
+ int vdso_ret, end_ret;
+
+ if (!vdso_gettimeofday)
+ return;
+
+ printf("[RUN]\tTesting gettimeofday...\n");
+
+ if (sys_gettimeofday(&start, &sys_tz) < 0) {
+ printf("[FAIL]\tsys_gettimeofday failed (%d)\n", errno);
+ nerrs++;
+ return;
+ }
+
+ vdso_ret = vdso_gettimeofday(&vdso, &vdso_tz);
+ end_ret = sys_gettimeofday(&end, NULL);
+
+ if (vdso_ret != 0 || end_ret != 0) {
+ printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+ vdso_ret, errno);
+ nerrs++;
+ return;
+ }
+
+ printf("\t%llu.%06ld %llu.%06ld %llu.%06ld\n",
+ (unsigned long long)start.tv_sec, start.tv_usec,
+ (unsigned long long)vdso.tv_sec, vdso.tv_usec,
+ (unsigned long long)end.tv_sec, end.tv_usec);
+
+ if (!tv_leq(&start, &vdso) || !tv_leq(&vdso, &end)) {
+ printf("[FAIL]\tTimes are out of sequence\n");
+ nerrs++;
+ }
+
+ if (sys_tz.tz_minuteswest == vdso_tz.tz_minuteswest &&
+ sys_tz.tz_dsttime == vdso_tz.tz_dsttime) {
+ printf("[OK]\ttimezones match: minuteswest=%d, dsttime=%d\n",
+ sys_tz.tz_minuteswest, sys_tz.tz_dsttime);
+ } else {
+ printf("[FAIL]\ttimezones do not match\n");
+ nerrs++;
+ }
+
+ /* And make sure that passing NULL for tz doesn't crash. */
+ vdso_gettimeofday(&vdso, NULL);
+}
+
int main(int argc, char **argv)
{
fill_function_pointers();
+ test_clock_gettime();
+ test_gettimeofday();
+
+ /*
+ * Test getcpu() last so that, if something goes wrong setting affinity,
+ * we still run the other tests.
+ */
test_getcpu();
return nerrs ? 1 : 0;
