summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Makefile2
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/entry/entry_64_compat.S6
-rw-r--r--arch/x86/include/asm/mmu_context.h18
-rw-r--r--arch/x86/kernel/crash.c1
-rw-r--r--arch/x86/kernel/hpet.c4
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c2
-rw-r--r--arch/x86/kernel/tsc.c30
-rw-r--r--arch/x86/lib/kaslr.c4
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c4
-rw-r--r--block/blk-core.c11
-rw-r--r--block/blk-merge.c10
-rw-r--r--drivers/edac/altera_edac.h4
-rw-r--r--drivers/irqchip/irq-gic-v3-its.c25
-rw-r--r--drivers/irqchip/irq-gic-v3-mbi.c2
-rw-r--r--drivers/irqchip/irq-madera.c2
-rw-r--r--drivers/irqchip/irq-stm32-exti.c1
-rw-r--r--include/linux/interrupt.h1
-rw-r--r--include/linux/sched/wake_q.h6
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/futex.c13
-rw-r--r--kernel/irq/irqdesc.c2
-rw-r--r--kernel/irq/manage.c3
-rw-r--r--kernel/locking/rwsem-xadd.c11
-rw-r--r--kernel/sched/core.c19
-rw-r--r--kernel/time/posix-cpu-timers.c1
-rw-r--r--mm/page_alloc.c12
-rw-r--r--tools/testing/selftests/x86/protection_keys.c41
28 files changed, 150 insertions, 89 deletions
diff --git a/Makefile b/Makefile
index f5b1d0d168e0..141653226f3c 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 0
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Shy Crocodile
# *DOCUMENTATION*
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4b4a7f32b68e..26387c7bf305 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -198,7 +198,7 @@ config X86
select IRQ_FORCED_THREADING
select NEED_SG_DMA_LENGTH
select PCI_DOMAINS if PCI
- select PCI_LOCKLESS_CONFIG
+ select PCI_LOCKLESS_CONFIG if PCI
select PERF_EVENTS
select RTC_LIB
select RTC_MC146818_LIB
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 8eaf8952c408..39913770a44d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat)
/* Need to switch before accessing the thread stack. */
SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
- movq %rsp, %rdi
+ /* In the Xen PV case we already run on the thread stack. */
+ ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq 6*8(%rdi) /* regs->ss */
@@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat)
pushq 3*8(%rdi) /* regs->cs */
pushq 2*8(%rdi) /* regs->ip */
pushq 1*8(%rdi) /* regs->orig_ax */
-
pushq (%rdi) /* pt_regs->di */
+.Lint80_keep_stack:
+
pushq %rsi /* pt_regs->si */
xorl %esi, %esi /* nospec si */
pushq %rdx /* pt_regs->dx */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 0ca50611e8ce..19d18fae6ec6 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
+/*
+ * Init a new mm. Used on mm copies, like at fork()
+ * and on mm's that are brand-new, like at execve().
+ */
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
@@ -228,8 +232,22 @@ do { \
} while (0)
#endif
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+ struct mm_struct *mm)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+ if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+ return;
+
+ /* Duplicate the oldmm pkey state in mm: */
+ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+ mm->context.execute_only_pkey = oldmm->context.execute_only_pkey;
+#endif
+}
+
static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
+ arch_dup_pkeys(oldmm, mm);
paravirt_arch_dup_mmap(oldmm, mm);
return ldt_dup_context(oldmm, mm);
}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c8b07d8ea5a2..17ffc869cab8 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image)
kbuf.memsz = kbuf.bufsz;
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+ kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
if (ret) {
vfree((void *)image->arch.elf_headers);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b0acb22e5a46..dfd3aca82c61 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -21,10 +21,6 @@
#define HPET_MASK CLOCKSOURCE_MASK(32)
-/* FSEC = 10^-15
- NSEC = 10^-9 */
-#define FSEC_PER_NSEC 1000000L
-
#define HPET_DEV_USED_BIT 2
#define HPET_DEV_USED (1 << HPET_DEV_USED_BIT)
#define HPET_DEV_VALID 0x8
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 278cd07228dd..0d5efa34f359 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -434,6 +434,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
kbuf.memsz = PAGE_ALIGN(header->init_size);
kbuf.buf_align = header->kernel_alignment;
kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+ kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
if (ret)
goto out_free_params;
@@ -448,6 +449,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
kbuf.bufsz = kbuf.memsz = initrd_len;
kbuf.buf_align = PAGE_SIZE;
kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+ kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
if (ret)
goto out_free_params;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e9f777bfed40..3fae23834069 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -297,15 +297,16 @@ static int __init tsc_setup(char *str)
__setup("tsc=", tsc_setup);
-#define MAX_RETRIES 5
-#define SMI_TRESHOLD 50000
+#define MAX_RETRIES 5
+#define TSC_DEFAULT_THRESHOLD 0x20000
/*
- * Read TSC and the reference counters. Take care of SMI disturbance
+ * Read TSC and the reference counters. Take care of any disturbances
*/
static u64 tsc_read_refs(u64 *p, int hpet)
{
u64 t1, t2;
+ u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD;
int i;
for (i = 0; i < MAX_RETRIES; i++) {
@@ -315,7 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet)
else
*p = acpi_pm_read_early();
t2 = get_cycles();
- if ((t2 - t1) < SMI_TRESHOLD)
+ if ((t2 - t1) < thresh)
return t2;
}
return ULLONG_MAX;
@@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
* zero. In each wait loop iteration we read the TSC and check
* the delta to the previous read. We keep track of the min
* and max values of that delta. The delta is mostly defined
- * by the IO time of the PIT access, so we can detect when a
- * SMI/SMM disturbance happened between the two reads. If the
+ * by the IO time of the PIT access, so we can detect when
+ * any disturbance happened between the two reads. If the
* maximum time is significantly larger than the minimum time,
* then we discard the result and have another try.
*
* 2) Reference counter. If available we use the HPET or the
* PMTIMER as a reference to check the sanity of that value.
* We use separate TSC readouts and check inside of the
- * reference read for a SMI/SMM disturbance. We dicard
+ * reference read for any possible disturbance. We dicard
* disturbed values here as well. We do that around the PIT
* calibration delay loop as we have to wait for a certain
* amount of time anyway.
@@ -744,7 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
if (ref1 == ref2)
continue;
- /* Check, whether the sampling was disturbed by an SMI */
+ /* Check, whether the sampling was disturbed */
if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
continue;
@@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
*/
static void tsc_refine_calibration_work(struct work_struct *work)
{
- static u64 tsc_start = -1, ref_start;
+ static u64 tsc_start = ULLONG_MAX, ref_start;
static int hpet;
u64 tsc_stop, ref_stop, delta;
unsigned long freq;
@@ -1283,14 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work)
* delayed the first time we expire. So set the workqueue
* again once we know timers are working.
*/
- if (tsc_start == -1) {
+ if (tsc_start == ULLONG_MAX) {
+restart:
/*
* Only set hpet once, to avoid mixing hardware
* if the hpet becomes enabled later.
*/
hpet = is_hpet_enabled();
- schedule_delayed_work(&tsc_irqwork, HZ);
tsc_start = tsc_read_refs(&ref_start, hpet);
+ schedule_delayed_work(&tsc_irqwork, HZ);
return;
}
@@ -1300,9 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work)
if (ref_start == ref_stop)
goto out;
- /* Check, whether the sampling was disturbed by an SMI */
- if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
- goto out;
+ /* Check, whether the sampling was disturbed */
+ if (tsc_stop == ULLONG_MAX)
+ goto restart;
delta = tsc_stop - tsc_start;
delta *= 1000000LL;
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 79778ab200e4..a53665116458 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -36,8 +36,8 @@ static inline u16 i8254(void)
u16 status, timer;
do {
- outb(I8254_PORT_CONTROL,
- I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+ outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+ I8254_PORT_CONTROL);
status = inb(I8254_PORT_COUNTER0);
timer = inb(I8254_PORT_COUNTER0);
timer |= inb(I8254_PORT_COUNTER0) << 8;
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index a19ef1a416ff..4aa9b1480866 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
pmd = pmd_offset(pud, ppd->vaddr);
if (pmd_none(*pmd)) {
pte = ppd->pgtable_area;
- memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
- ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+ memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE);
+ ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE;
set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
}
diff --git a/block/blk-core.c b/block/blk-core.c
index 1ccec27d20c3..3c5f61ceeb67 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1083,18 +1083,7 @@ blk_qc_t generic_make_request(struct bio *bio)
/* Create a fresh bio_list for all subordinate requests */
bio_list_on_stack[1] = bio_list_on_stack[0];
bio_list_init(&bio_list_on_stack[0]);
-
- /*
- * Since we're recursing into make_request here, ensure
- * that we mark this bio as already having entered the queue.
- * If not, and the queue is going away, we can get stuck
- * forever on waiting for the queue reference to drop. But
- * that will never happen, as we're already holding a
- * reference to it.
- */
- bio_set_flag(bio, BIO_QUEUE_ENTERED);
ret = q->make_request_fn(q, bio);
- bio_clear_flag(bio, BIO_QUEUE_ENTERED);
/* sort new bios into those for a lower level
* and those for the same level
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d79a22f111d1..71e9ac03f621 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -272,6 +272,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
/* there isn't chance to merge the splitted bio */
split->bi_opf |= REQ_NOMERGE;
+ /*
+ * Since we're recursing into make_request here, ensure
+ * that we mark this bio as already having entered the queue.
+ * If not, and the queue is going away, we can get stuck
+ * forever on waiting for the queue reference to drop. But
+ * that will never happen, as we're already holding a
+ * reference to it.
+ */
+ bio_set_flag(*bio, BIO_QUEUE_ENTERED);
+
bio_chain(split, *bio);
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
generic_make_request(*bio);
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index 4213cb0bb2a7..f8664bac9fa8 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -295,8 +295,8 @@ struct altr_sdram_mc_data {
#define S10_SYSMGR_ECC_INTSTAT_DERR_OFST 0xA0
/* Sticky registers for Uncorrected Errors */
-#define S10_SYSMGR_UE_VAL_OFST 0x120
-#define S10_SYSMGR_UE_ADDR_OFST 0x124
+#define S10_SYSMGR_UE_VAL_OFST 0x220
+#define S10_SYSMGR_UE_ADDR_OFST 0x224
#define S10_DDR0_IRQ_MASK BIT(16)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index db20e992a40f..7f2a45445b00 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2399,13 +2399,14 @@ static void its_free_device(struct its_device *its_dev)
kfree(its_dev);
}
-static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq)
+static int its_alloc_device_irq(struct its_device *dev, int nvecs, irq_hw_number_t *hwirq)
{
int idx;
- idx = find_first_zero_bit(dev->event_map.lpi_map,
- dev->event_map.nr_lpis);
- if (idx == dev->event_map.nr_lpis)
+ idx = bitmap_find_free_region(dev->event_map.lpi_map,
+ dev->event_map.nr_lpis,
+ get_count_order(nvecs));
+ if (idx < 0)
return -ENOSPC;
*hwirq = dev->event_map.lpi_base + idx;
@@ -2501,21 +2502,21 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
int err;
int i;
- for (i = 0; i < nr_irqs; i++) {
- err = its_alloc_device_irq(its_dev, &hwirq);
- if (err)
- return err;
+ err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq);
+ if (err)
+ return err;
- err = its_irq_gic_domain_alloc(domain, virq + i, hwirq);
+ for (i = 0; i < nr_irqs; i++) {
+ err = its_irq_gic_domain_alloc(domain, virq + i, hwirq + i);
if (err)
return err;
irq_domain_set_hwirq_and_chip(domain, virq + i,
- hwirq, &its_irq_chip, its_dev);
+ hwirq + i, &its_irq_chip, its_dev);
irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i)));
pr_debug("ID:%d pID:%d vID:%d\n",
- (int)(hwirq - its_dev->event_map.lpi_base),
- (int) hwirq, virq + i);
+ (int)(hwirq + i - its_dev->event_map.lpi_base),
+ (int)(hwirq + i), virq + i);
}
return 0;
diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c
index ad70e7c416e3..fbfa7ff6deb1 100644
--- a/drivers/irqchip/irq-gic-v3-mbi.c
+++ b/drivers/irqchip/irq-gic-v3-mbi.c
@@ -24,7 +24,7 @@ struct mbi_range {
unsigned long *bm;
};
-static struct mutex mbi_lock;
+static DEFINE_MUTEX(mbi_lock);
static phys_addr_t mbi_phys_base;
static struct mbi_range *mbi_ranges;
static unsigned int mbi_range_nr;
diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c
index e9256dee1a45..8b81271c823c 100644
--- a/drivers/irqchip/irq-madera.c
+++ b/drivers/irqchip/irq-madera.c
@@ -7,7 +7,6 @@
*/
#include <linux/module.h>
-#include <linux/gpio.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
@@ -16,7 +15,6 @@
#include <linux/slab.h>
#include <linux/of.h>
#include <linux/of_device.h>
-#include <linux/of_gpio.h>
#include <linux/of_irq.h>
#include <linux/irqchip/irq-madera.h>
#include <linux/mfd/madera/core.h>
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 6edfd4bfa169..a93296b9b45d 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -822,6 +822,7 @@ out_unmap:
static const struct irq_domain_ops stm32_exti_h_domain_ops = {
.alloc = stm32_exti_h_domain_alloc,
.free = irq_domain_free_irqs_common,
+ .xlate = irq_domain_xlate_twocell,
};
static int
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c672f34235e7..4a728dba02e2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -260,6 +260,7 @@ struct irq_affinity {
/**
* struct irq_affinity_desc - Interrupt affinity descriptor
* @mask: cpumask to hold the affinity assignment
+ * @is_managed: 1 if the interrupt is managed internally
*/
struct irq_affinity_desc {
struct cpumask mask;
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a192b2d..545f37138057 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -24,9 +24,13 @@
* called near the end of a function. Otherwise, the list can be
* re-initialized for later re-use by wake_q_init().
*
- * Note that this can cause spurious wakeups. schedule() callers
+ * NOTE that this can cause spurious wakeups. schedule() callers
* must ensure the call is done inside a loop, confirming that the
* wakeup condition has in fact occurred.
+ *
+ * NOTE that there is no guarantee the wakeup will happen any later than the
+ * wake_q_add() location. Therefore task must be ready to be woken at the
+ * location of the wake_q_add().
*/
#include <linux/sched.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 284f2fe9a293..3fb7be001964 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -307,7 +307,7 @@ void rcuwait_wake_up(struct rcuwait *w)
* MB (A) MB (B)
* [L] cond [L] tsk
*/
- smp_rmb(); /* (B) */
+ smp_mb(); /* (B) */
/*
* Avoid using task_rcu_dereference() magic as long as we are careful,
diff --git a/kernel/futex.c b/kernel/futex.c
index be3bff2315ff..fdd312da0992 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1452,11 +1452,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
return;
- /*
- * Queue the task for later wakeup for after we've released
- * the hb->lock. wake_q_add() grabs reference to p.
- */
- wake_q_add(wake_q, p);
+ get_task_struct(p);
__unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -1466,6 +1462,13 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
* plist_del in __unqueue_futex().
*/
smp_store_release(&q->lock_ptr, NULL);
+
+ /*
+ * Queue the task for later wakeup for after we've released
+ * the hb->lock. wake_q_add() grabs reference to p.
+ */
+ wake_q_add(wake_q, p);
+ put_task_struct(p);
}
/*
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index ee062b7939d3..ef8ad36cadcf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -457,7 +457,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
/* Validate affinity mask(s) */
if (affinity) {
- for (i = 0; i < cnt; i++, i++) {
+ for (i = 0; i < cnt; i++) {
if (cpumask_empty(&affinity[i].mask))
return -EINVAL;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a4888ce4667a..84b54a17b95d 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -393,6 +393,9 @@ int irq_setup_affinity(struct irq_desc *desc)
}
cpumask_and(&mask, cpu_online_mask, set);
+ if (cpumask_empty(&mask))
+ cpumask_copy(&mask, cpu_online_mask);
+
if (node != NUMA_NO_NODE) {
const struct cpumask *nodemask = cpumask_of_node(node);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09b180063ee1..50d9af615dc4 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -198,15 +198,22 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
woken++;
tsk = waiter->task;
- wake_q_add(wake_q, tsk);
+ get_task_struct(tsk);
list_del(&waiter->list);
/*
- * Ensure that the last operation is setting the reader
+ * Ensure calling get_task_struct() before setting the reader
* waiter to nil such that rwsem_down_read_failed() cannot
* race with do_exit() by always holding a reference count
* to the task to wakeup.
*/
smp_store_release(&waiter->task, NULL);
+ /*
+ * Ensure issuing the wakeup (either by us or someone else)
+ * after setting the reader waiter to nil.
+ */
+ wake_q_add(wake_q, tsk);
+ /* wake_q_add() already take the task ref */
+ put_task_struct(tsk);
}
adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a674c7db2f29..d8d76a65cfdd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,6 +396,18 @@ static bool set_nr_if_polling(struct task_struct *p)
#endif
#endif
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
struct wake_q_node *node = &task->wake_q;
@@ -405,10 +417,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
* its already queued (either by us or someone else) and will get the
* wakeup due to that.
*
- * This cmpxchg() executes a full barrier, which pairs with the full
- * barrier executed by the wakeup in wake_up_q().
+ * In order to ensure that a pending wakeup will observe our pending
+ * state, even in the failed case, an explicit smp_mb() must be used.
*/
- if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+ smp_mb__before_atomic();
+ if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
return;
get_task_struct(task);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8f0644af40be..80f955210861 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -685,6 +685,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* set up the signal and overrun bookkeeping.
*/
timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
+ timer->it_interval = ns_to_ktime(timer->it.cpu.incr);
/*
* This acts as a modification timestamp for the timer,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d295c9bc01a8..35fdde041f5c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5701,18 +5701,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
cond_resched();
}
}
-#ifdef CONFIG_SPARSEMEM
- /*
- * If the zone does not span the rest of the section then
- * we should at least initialize those pages. Otherwise we
- * could blow up on a poisoned page in some paths which depend
- * on full sections being initialized (e.g. memory hotplug).
- */
- while (end_pfn % PAGES_PER_SECTION) {
- __init_single_page(pfn_to_page(end_pfn), end_pfn, zone, nid);
- end_pfn++;
- }
-#endif
}
#ifdef CONFIG_ZONE_DEVICE
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index 460b4bdf4c1e..5d546dcdbc80 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -1133,6 +1133,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
pkey_assert(err);
}
+void become_child(void)
+{
+ pid_t forkret;
+
+ forkret = fork();
+ pkey_assert(forkret >= 0);
+ dprintf3("[%d] fork() ret: %d\n", getpid(), forkret);
+
+ if (!forkret) {
+ /* in the child */
+ return;
+ }
+ exit(0);
+}
+
/* Assumes that all pkeys other than 'pkey' are unallocated */
void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
{
@@ -1141,7 +1156,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
int nr_allocated_pkeys = 0;
int i;
- for (i = 0; i < NR_PKEYS*2; i++) {
+ for (i = 0; i < NR_PKEYS*3; i++) {
int new_pkey;
dprintf1("%s() alloc loop: %d\n", __func__, i);
new_pkey = alloc_pkey();
@@ -1152,21 +1167,27 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
if ((new_pkey == -1) && (errno == ENOSPC)) {
dprintf2("%s() failed to allocate pkey after %d tries\n",
__func__, nr_allocated_pkeys);
- break;
+ } else {
+ /*
+ * Ensure the number of successes never
+ * exceeds the number of keys supported
+ * in the hardware.
+ */
+ pkey_assert(nr_allocated_pkeys < NR_PKEYS);
+ allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
}
- pkey_assert(nr_allocated_pkeys < NR_PKEYS);
- allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+
+ /*
+ * Make sure that allocation state is properly
+ * preserved across fork().
+ */
+ if (i == NR_PKEYS*2)
+ become_child();
}
dprintf3("%s()::%d\n", __func__, __LINE__);
/*
- * ensure it did not reach the end of the loop without
- * failure:
- */
- pkey_assert(i < NR_PKEYS*2);
-
- /*
* There are 16 pkeys supported in hardware. Three are
* allocated by the time we get here:
* 1. The default key (0)