| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <2024122720-shredder-stoning-528b@gregkh>
Date: Fri, 27 Dec 2024 14:45:20 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org,
akpm@...ux-foundation.org,
torvalds@...ux-foundation.org,
stable@...r.kernel.org
Cc: lwn@....net,
jslaby@...e.cz,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Subject: Re: Linux 6.12.7
diff --git a/Makefile b/Makefile
index c10952585c14..685a57f6c8d2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 12
-SUBLEVEL = 6
+SUBLEVEL = 7
EXTRAVERSION =
NAME = Baby Opossum Posse
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fbed433283c9..42791971f758 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2503,7 +2503,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 |
ID_AA64MMFR0_EL1_TGRAN4_2 |
ID_AA64MMFR0_EL1_TGRAN64_2 |
- ID_AA64MMFR0_EL1_TGRAN16_2)),
+ ID_AA64MMFR0_EL1_TGRAN16_2 |
+ ID_AA64MMFR0_EL1_ASIDBITS)),
ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
ID_AA64MMFR1_EL1_HCX |
ID_AA64MMFR1_EL1_TWED |
diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile
index 92d005958dfb..ff172cbe5881 100644
--- a/arch/hexagon/Makefile
+++ b/arch/hexagon/Makefile
@@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y)
TIR_NAME := r19
KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__
KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME)
+
+# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0
+# https://github.com/llvm/llvm-project/issues/99714
+ifneq ($(call clang-min-version, 190100),y)
+KBUILD_CFLAGS += -mllvm -hexagon-cext=false
+endif
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 2967d305c442..9f3b527596de 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -552,7 +552,7 @@ void kvm_riscv_aia_enable(void)
csr_set(CSR_HIE, BIT(IRQ_S_GEXT));
/* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */
if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF))
- csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF));
+ csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF));
}
void kvm_riscv_aia_disable(void)
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index c8f149ad77e5..c2ee0745f59e 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -231,6 +231,8 @@ static unsigned long get_vmem_size(unsigned long identity_size,
vsize = round_up(SZ_2G + max_mappable, rte_size) +
round_up(vmemmap_size, rte_size) +
FIXMAP_SIZE + MODULES_LEN + KASLR_LEN;
+ if (IS_ENABLED(CONFIG_KMSAN))
+ vsize += MODULES_LEN * 2;
return size_add(vsize, vmalloc_size);
}
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 145035f84a0e..3fa28db2fe59 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
pages++;
}
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_4K, pages);
}
@@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
}
pgtable_pte_populate(pmd, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_1M, pages);
}
@@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
}
pgtable_pmd_populate(pud, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_2G, pages);
}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f17bb7bf9392..5fa203f4bc6b 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
if (len >= sizeof(_value)) \
return -E2BIG; \
len = strscpy(_value, buf, sizeof(_value)); \
- if (len < 0) \
+ if ((ssize_t)len < 0) \
return len; \
strim(_value); \
return len; \
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index d18078834ded..dc12fe5ef3ca 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
hyperv_cleanup();
}
#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+ hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * Adjust the offsets used by hv tsc clocksource to
+ * account for the time spent before hibernation.
+ * adjusted value = reference counter (time) at suspend
+ * - reference counter (time) now.
+ */
+ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+ old_save_sched_clock_state();
+ save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+ restore_hv_clock_tsc_state();
+ old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+ return;
+
+ old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+ x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 41786b834b16..83bfecd1a6e4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -36,6 +36,26 @@
u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
EXPORT_SYMBOL_GPL(kvm_cpu_caps);
+struct cpuid_xstate_sizes {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+};
+
+static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init;
+
+void __init kvm_init_xstate_sizes(void)
+{
+ u32 ign;
+ int i;
+
+ for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) {
+ struct cpuid_xstate_sizes *xs = &xstate_sizes[i];
+
+ cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign);
+ }
+}
+
u32 xstate_required_size(u64 xstate_bv, bool compacted)
{
int feature_bit = 0;
@@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
xstate_bv &= XFEATURE_MASK_EXTEND;
while (xstate_bv) {
if (xstate_bv & 0x1) {
- u32 eax, ebx, ecx, edx, offset;
- cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
+ struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit];
+ u32 offset;
+
/* ECX[1]: 64B alignment in compacted form */
if (compacted)
- offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret;
+ offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret;
else
- offset = ebx;
- ret = max(ret, offset + eax);
+ offset = xs->ebx;
+ ret = max(ret, offset + xs->eax);
}
xstate_bv >>= 1;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 41697cca354e..ad479cfb91bc 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -32,6 +32,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
u32 *ecx, u32 *edx, bool exact_only);
+void __init kvm_init_xstate_sizes(void);
u32 xstate_required_size(u64 xstate_bv, bool compacted);
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9df3e1e5ae81..4543dd6bcab2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3199,15 +3199,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
if (data & ~supported_de_cfg)
return 1;
- /*
- * Don't let the guest change the host-programmed value. The
- * MSR is very model specific, i.e. contains multiple bits that
- * are completely unknown to KVM, and the one bit known to KVM
- * is simply a reflection of hardware capabilities.
- */
- if (!msr->host_initiated && data != svm->msr_decfg)
- return 1;
-
svm->msr_decfg = data;
break;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 83fe0a78146f..b49e2eb48930 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9991,7 +9991,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
{
u64 ret = vcpu->run->hypercall.ret;
- if (!is_64_bit_mode(vcpu))
+ if (!is_64_bit_hypercall(vcpu))
ret = (u32)ret;
kvm_rax_write(vcpu, ret);
++vcpu->stat.hypercalls;
@@ -14010,6 +14010,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault);
static int __init kvm_x86_init(void)
{
+ kvm_init_xstate_sizes();
+
kvm_mmu_x86_module_init();
mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible();
return 0;
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index cd5ea6eaa76b..156e9bb07abf 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -275,13 +275,15 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
unsigned long i;
- lockdep_assert_held(&q->sysfs_dir_lock);
-
+ mutex_lock(&q->sysfs_dir_lock);
if (!q->mq_sysfs_init_done)
- return;
+ goto unlock;
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
+
+unlock:
+ mutex_unlock(&q->sysfs_dir_lock);
}
int blk_mq_sysfs_register_hctxs(struct request_queue *q)
@@ -290,10 +292,9 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
unsigned long i;
int ret = 0;
- lockdep_assert_held(&q->sysfs_dir_lock);
-
+ mutex_lock(&q->sysfs_dir_lock);
if (!q->mq_sysfs_init_done)
- return ret;
+ goto unlock;
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
@@ -301,5 +302,8 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
break;
}
+unlock:
+ mutex_unlock(&q->sysfs_dir_lock);
+
return ret;
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index cc1b32023838..d5995021815d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4421,6 +4421,15 @@ struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
}
EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue);
+/*
+ * Only hctx removed from cpuhp list can be reused
+ */
+static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx)
+{
+ return hlist_unhashed(&hctx->cpuhp_online) &&
+ hlist_unhashed(&hctx->cpuhp_dead);
+}
+
static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
struct blk_mq_tag_set *set, struct request_queue *q,
int hctx_idx, int node)
@@ -4430,7 +4439,7 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
/* reuse dead hctx first */
spin_lock(&q->unused_hctx_lock);
list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) {
- if (tmp->numa_node == node) {
+ if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) {
hctx = tmp;
break;
}
@@ -4462,8 +4471,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
unsigned long i, j;
/* protect against switching io scheduler */
- lockdep_assert_held(&q->sysfs_lock);
-
+ mutex_lock(&q->sysfs_lock);
for (i = 0; i < set->nr_hw_queues; i++) {
int old_node;
int node = blk_mq_get_hctx_node(set, i);
@@ -4496,6 +4504,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
xa_for_each_start(&q->hctx_table, j, hctx, j)
blk_mq_exit_hctx(q, set, hctx, j);
+ mutex_unlock(&q->sysfs_lock);
/* unregister cpuhp callbacks for exited hctxs */
blk_mq_remove_hw_queues_cpuhp(q);
@@ -4527,14 +4536,10 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
xa_init(&q->hctx_table);
- mutex_lock(&q->sysfs_lock);
-
blk_mq_realloc_hw_ctxs(set, q);
if (!q->nr_hw_queues)
goto err_hctxs;
- mutex_unlock(&q->sysfs_lock);
-
INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
@@ -4553,7 +4558,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
return 0;
err_hctxs:
- mutex_unlock(&q->sysfs_lock);
blk_mq_release(q);
err_exit:
q->mq_ops = NULL;
@@ -4934,12 +4938,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
return false;
/* q->elevator needs protection from ->sysfs_lock */
- lockdep_assert_held(&q->sysfs_lock);
+ mutex_lock(&q->sysfs_lock);
/* the check has to be done with holding sysfs_lock */
if (!q->elevator) {
kfree(qe);
- goto out;
+ goto unlock;
}
INIT_LIST_HEAD(&qe->node);
@@ -4949,7 +4953,9 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
__elevator_get(qe->type);
list_add(&qe->node, head);
elevator_disable(q);
-out:
+unlock:
+ mutex_unlock(&q->sysfs_lock);
+
return true;
}
@@ -4978,9 +4984,11 @@ static void blk_mq_elv_switch_back(struct list_head *head,
list_del(&qe->node);
kfree(qe);
+ mutex_lock(&q->sysfs_lock);
elevator_switch(q, t);
/* drop the reference acquired in blk_mq_elv_switch_none */
elevator_put(t);
+ mutex_unlock(&q->sysfs_lock);
}
static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
@@ -5000,11 +5008,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
return;
- list_for_each_entry(q, &set->tag_list, tag_set_list) {
- mutex_lock(&q->sysfs_dir_lock);
- mutex_lock(&q->sysfs_lock);
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_freeze_queue(q);
- }
/*
* Switch IO scheduler to 'none', cleaning up the data associated
* with the previous scheduler. We will switch back once we are done
@@ -5060,11 +5065,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_elv_switch_back(&head, q);
- list_for_each_entry(q, &set->tag_list, tag_set_list) {
+ list_for_each_entry(q, &set->tag_list, tag_set_list)
blk_mq_unfreeze_queue(q);
- mutex_unlock(&q->sysfs_lock);
- mutex_unlock(&q->sysfs_dir_lock);
- }
/* Free the excess tags when nr_hw_queues shrink. */
for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 42c2cb97d778..207577145c54 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -690,11 +690,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
return res;
}
- mutex_lock(&q->sysfs_lock);
blk_mq_freeze_queue(q);
+ mutex_lock(&q->sysfs_lock);
res = entry->store(disk, page, length);
- blk_mq_unfreeze_queue(q);
mutex_unlock(&q->sysfs_lock);
+ blk_mq_unfreeze_queue(q);
return res;
}
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 1b409dbd332d..c8daffd90f30 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -406,7 +406,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
mutex_lock(&bo->lock);
drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u",
- bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size,
+ bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size,
bo->flags, kref_read(&bo->base.base.refcount));
if (bo->base.pages)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 59d3170f5e35..10b7ae0f866c 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -364,6 +364,7 @@ void ivpu_pm_init(struct ivpu_device *vdev)
pm_runtime_use_autosuspend(dev);
pm_runtime_set_autosuspend_delay(dev, delay);
+ pm_runtime_set_active(dev);
ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay);
}
@@ -378,7 +379,6 @@ void ivpu_pm_enable(struct ivpu_device *vdev)
{
struct device *dev = vdev->drm.dev;
- pm_runtime_set_active(dev);
pm_runtime_allow(dev);
pm_runtime_mark_last_busy(dev);
pm_runtime_put_autosuspend(dev);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d0432b1707ce..bf83a104086c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -524,6 +524,12 @@ static ssize_t backing_dev_store(struct device *dev,
}
nr_pages = i_size_read(inode) >> PAGE_SHIFT;
+ /* Refuse to use zero sized device (also prevents self reference) */
+ if (!nr_pages) {
+ err = -EINVAL;
+ goto out;
+ }
+
bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
if (!bitmap) {
@@ -1319,12 +1325,16 @@ static void zram_meta_free(struct zram *zram, u64 disksize)
size_t num_pages = disksize >> PAGE_SHIFT;
size_t index;
+ if (!zram->table)
+ return;
+
/* Free all pages that are still in this zram device */
for (index = 0; index < num_pages; index++)
zram_free_page(zram, index);
zs_destroy_pool(zram->mem_pool);
vfree(zram->table);
+ zram->table = NULL;
}
static bool zram_meta_alloc(struct zram *zram, u64 disksize)
@@ -2165,11 +2175,6 @@ static void zram_reset_device(struct zram *zram)
zram->limit_pages = 0;
- if (!init_done(zram)) {
- up_write(&zram->init_lock);
- return;
- }
-
set_capacity_and_notify(zram->disk, 0);
part_stat_set_all(zram->disk->part0, 0);
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 99177835cade..b39dee7b93af 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -27,7 +27,8 @@
#include <asm/mshyperv.h>
static struct clock_event_device __percpu *hv_clock_event;
-static u64 hv_sched_clock_offset __ro_after_init;
+/* Note: offset can hold negative values after hibernation. */
+static u64 hv_sched_clock_offset __read_mostly;
/*
* If false, we're using the old mechanism for stimer0 interrupts
@@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
}
+/*
+ * Called during resume from hibernation, from overridden
+ * x86_platform.restore_sched_clock_state routine. This is to adjust offsets
+ * used to calculate time for hv tsc page based sched_clock, to account for
+ * time spent before hibernation.
+ */
+void hv_adj_sched_clock_offset(u64 offset)
+{
+ hv_sched_clock_offset -= offset;
+}
+
#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK
static int hv_cs_enable(struct clocksource *cs)
{
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index dff618c708dc..a0d6e8d7f42c 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
struct cxl_region_params *p = &cxlr->params;
struct cxl_decoder *cxld = cxl_rr->decoder;
struct cxl_switch_decoder *cxlsd;
+ struct cxl_port *iter = port;
u16 eig, peig;
u8 eiw, peiw;
@@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port,
cxlsd = to_cxl_switch_decoder(&cxld->dev);
if (cxl_rr->nr_targets_set) {
- int i, distance;
+ int i, distance = 1;
+ struct cxl_region_ref *cxl_rr_iter;
/*
- * Passthrough decoders impose no distance requirements between
- * peers
+ * The "distance" between peer downstream ports represents which
+ * endpoint positions in the region interleave a given port can
+ * host.
+ *
+ * For example, at the root of a hierarchy the distance is
+ * always 1 as every index targets a different host-bridge. At
+ * each subsequent switch level those ports map every Nth region
+ * position where N is the width of the switch == distance.
*/
- if (cxl_rr->nr_targets == 1)
- distance = 0;
- else
- distance = p->nr_targets / cxl_rr->nr_targets;
+ do {
+ cxl_rr_iter = cxl_rr_load(iter, cxlr);
+ distance *= cxl_rr_iter->nr_targets;
+ iter = to_cxl_port(iter->dev.parent);
+ } while (!is_cxl_root(iter));
+ distance *= cxlrd->cxlsd.cxld.interleave_ways;
+
for (i = 0; i < cxl_rr->nr_targets_set; i++)
if (ep->dport == cxlsd->target[i]) {
rc = check_last_peer(cxled, ep, cxl_rr,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 188412d45e0d..6e553b5752b1 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -942,8 +942,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (rc)
return rc;
- rc = cxl_pci_ras_unmask(pdev);
- if (rc)
+ if (cxl_pci_ras_unmask(pdev))
dev_dbg(&pdev->dev, "No RAS reporting unmasked\n");
pci_save_state(pdev);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 8892bc701a66..afb8c1c50107 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -60,7 +60,7 @@ static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf)
{
}
-static void __dma_buf_debugfs_list_del(struct file *file)
+static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf)
{
}
#endif
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index a3638ccc15f5..5e836e4e5b44 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -256,15 +256,12 @@ static const struct dma_buf_ops udmabuf_ops = {
};
#define SEALS_WANTED (F_SEAL_SHRINK)
-#define SEALS_DENIED (F_SEAL_WRITE)
+#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE)
static int check_memfd_seals(struct file *memfd)
{
int seals;
- if (!memfd)
- return -EBADFD;
-
if (!shmem_file(memfd) && !is_file_hugepages(memfd))
return -EBADFD;
@@ -279,12 +276,10 @@ static int check_memfd_seals(struct file *memfd)
return 0;
}
-static int export_udmabuf(struct udmabuf *ubuf,
- struct miscdevice *device,
- u32 flags)
+static struct dma_buf *export_udmabuf(struct udmabuf *ubuf,
+ struct miscdevice *device)
{
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
- struct dma_buf *buf;
ubuf->device = device;
exp_info.ops = &udmabuf_ops;
@@ -292,24 +287,72 @@ static int export_udmabuf(struct udmabuf *ubuf,
exp_info.priv = ubuf;
exp_info.flags = O_RDWR;
- buf = dma_buf_export(&exp_info);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
+ return dma_buf_export(&exp_info);
+}
+
+static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd,
+ loff_t start, loff_t size)
+{
+ pgoff_t pgoff, pgcnt, upgcnt = ubuf->pagecount;
+ struct folio **folios = NULL;
+ u32 cur_folio, cur_pgcnt;
+ long nr_folios;
+ long ret = 0;
+ loff_t end;
+
+ pgcnt = size >> PAGE_SHIFT;
+ folios = kvmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL);
+ if (!folios)
+ return -ENOMEM;
+
+ end = start + (pgcnt << PAGE_SHIFT) - 1;
+ nr_folios = memfd_pin_folios(memfd, start, end, folios, pgcnt, &pgoff);
+ if (nr_folios <= 0) {
+ ret = nr_folios ? nr_folios : -EINVAL;
+ goto end;
+ }
- return dma_buf_fd(buf, flags);
+ cur_pgcnt = 0;
+ for (cur_folio = 0; cur_folio < nr_folios; ++cur_folio) {
+ pgoff_t subpgoff = pgoff;
+ size_t fsize = folio_size(folios[cur_folio]);
+
+ ret = add_to_unpin_list(&ubuf->unpin_list, folios[cur_folio]);
+ if (ret < 0)
+ goto end;
+
+ for (; subpgoff < fsize; subpgoff += PAGE_SIZE) {
+ ubuf->folios[upgcnt] = folios[cur_folio];
+ ubuf->offsets[upgcnt] = subpgoff;
+ ++upgcnt;
+
+ if (++cur_pgcnt >= pgcnt)
+ goto end;
+ }
+
+ /**
+ * In a given range, only the first subpage of the first folio
+ * has an offset, that is returned by memfd_pin_folios().
+ * The first subpages of other folios (in the range) have an
+ * offset of 0.
+ */
+ pgoff = 0;
+ }
+end:
+ ubuf->pagecount = upgcnt;
+ kvfree(folios);
+ return ret;
}
static long udmabuf_create(struct miscdevice *device,
struct udmabuf_create_list *head,
struct udmabuf_create_item *list)
{
- pgoff_t pgoff, pgcnt, pglimit, pgbuf = 0;
- long nr_folios, ret = -EINVAL;
- struct file *memfd = NULL;
- struct folio **folios;
+ pgoff_t pgcnt = 0, pglimit;
struct udmabuf *ubuf;
- u32 i, j, k, flags;
- loff_t end;
+ struct dma_buf *dmabuf;
+ long ret = -EINVAL;
+ u32 i, flags;
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
if (!ubuf)
@@ -318,93 +361,76 @@ static long udmabuf_create(struct miscdevice *device,
INIT_LIST_HEAD(&ubuf->unpin_list);
pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
for (i = 0; i < head->count; i++) {
- if (!IS_ALIGNED(list[i].offset, PAGE_SIZE))
+ if (!PAGE_ALIGNED(list[i].offset))
goto err;
- if (!IS_ALIGNED(list[i].size, PAGE_SIZE))
+ if (!PAGE_ALIGNED(list[i].size))
goto err;
- ubuf->pagecount += list[i].size >> PAGE_SHIFT;
- if (ubuf->pagecount > pglimit)
+
+ pgcnt += list[i].size >> PAGE_SHIFT;
+ if (pgcnt > pglimit)
goto err;
}
- if (!ubuf->pagecount)
+ if (!pgcnt)
goto err;
- ubuf->folios = kvmalloc_array(ubuf->pagecount, sizeof(*ubuf->folios),
- GFP_KERNEL);
+ ubuf->folios = kvmalloc_array(pgcnt, sizeof(*ubuf->folios), GFP_KERNEL);
if (!ubuf->folios) {
ret = -ENOMEM;
goto err;
}
- ubuf->offsets = kvcalloc(ubuf->pagecount, sizeof(*ubuf->offsets),
- GFP_KERNEL);
+
+ ubuf->offsets = kvcalloc(pgcnt, sizeof(*ubuf->offsets), GFP_KERNEL);
if (!ubuf->offsets) {
ret = -ENOMEM;
goto err;
}
- pgbuf = 0;
for (i = 0; i < head->count; i++) {
- memfd = fget(list[i].memfd);
- ret = check_memfd_seals(memfd);
- if (ret < 0)
- goto err;
-
- pgcnt = list[i].size >> PAGE_SHIFT;
- folios = kvmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL);
- if (!folios) {
- ret = -ENOMEM;
- goto err;
- }
+ struct file *memfd = fget(list[i].memfd);
- end = list[i].offset + (pgcnt << PAGE_SHIFT) - 1;
- ret = memfd_pin_folios(memfd, list[i].offset, end,
- folios, pgcnt, &pgoff);
- if (ret <= 0) {
- kvfree(folios);
- if (!ret)
- ret = -EINVAL;
+ if (!memfd) {
+ ret = -EBADFD;
goto err;
}
- nr_folios = ret;
- pgoff >>= PAGE_SHIFT;
- for (j = 0, k = 0; j < pgcnt; j++) {
- ubuf->folios[pgbuf] = folios[k];
- ubuf->offsets[pgbuf] = pgoff << PAGE_SHIFT;
-
- if (j == 0 || ubuf->folios[pgbuf-1] != folios[k]) {
- ret = add_to_unpin_list(&ubuf->unpin_list,
- folios[k]);
- if (ret < 0) {
- kfree(folios);
- goto err;
- }
- }
-
- pgbuf++;
- if (++pgoff == folio_nr_pages(folios[k])) {
- pgoff = 0;
- if (++k == nr_folios)
- break;
- }
- }
+ /*
+ * Take the inode lock to protect against concurrent
+ * memfd_add_seals(), which takes this lock in write mode.
+ */
+ inode_lock_shared(file_inode(memfd));
+ ret = check_memfd_seals(memfd);
+ if (ret)
+ goto out_unlock;
- kvfree(folios);
+ ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset,
+ list[i].size);
+out_unlock:
+ inode_unlock_shared(file_inode(memfd));
fput(memfd);
- memfd = NULL;
+ if (ret)
+ goto err;
}
flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0;
- ret = export_udmabuf(ubuf, device, flags);
- if (ret < 0)
+ dmabuf = export_udmabuf(ubuf, device);
+ if (IS_ERR(dmabuf)) {
+ ret = PTR_ERR(dmabuf);
goto err;
+ }
+ /*
+ * Ownership of ubuf is held by the dmabuf from here.
+ * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the
+ * dmabuf and the ubuf (through udmabuf_ops.release).
+ */
+
+ ret = dma_buf_fd(dmabuf, flags);
+ if (ret < 0)
+ dma_buf_put(dmabuf);
return ret;
err:
- if (memfd)
- fput(memfd);
unpin_all_folios(&ubuf->unpin_list);
kvfree(ubuf->offsets);
kvfree(ubuf->folios);
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index ddfbdb66b794..5d356b7c4589 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3362,36 +3362,24 @@ static bool dct_ecc_enabled(struct amd64_pvt *pvt)
static bool umc_ecc_enabled(struct amd64_pvt *pvt)
{
- u8 umc_en_mask = 0, ecc_en_mask = 0;
- u16 nid = pvt->mc_node_id;
struct amd64_umc *umc;
- u8 ecc_en = 0, i;
+ bool ecc_en = false;
+ int i;
+ /* Check whether at least one UMC is enabled: */
for_each_umc(i) {
umc = &pvt->umc[i];
- /* Only check enabled UMCs. */
- if (!(umc->sdp_ctrl & UMC_SDP_INIT))
- continue;
-
- umc_en_mask |= BIT(i);
-
- if (umc->umc_cap_hi & UMC_ECC_ENABLED)
- ecc_en_mask |= BIT(i);
+ if (umc->sdp_ctrl & UMC_SDP_INIT &&
+ umc->umc_cap_hi & UMC_ECC_ENABLED) {
+ ecc_en = true;
+ break;
+ }
}
- /* Check whether at least one UMC is enabled: */
- if (umc_en_mask)
- ecc_en = umc_en_mask == ecc_en_mask;
- else
- edac_dbg(0, "Node %d: No enabled UMCs.\n", nid);
-
- edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled"));
+ edac_dbg(3, "Node %d: DRAM ECC %s.\n", pvt->mc_node_id, (ecc_en ? "enabled" : "disabled"));
- if (!ecc_en)
- return false;
- else
- return true;
+ return ecc_en;
}
static inline void
diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c
index eb17d03b66fe..dfda5ffc14db 100644
--- a/drivers/firmware/arm_ffa/bus.c
+++ b/drivers/firmware/arm_ffa/bus.c
@@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev)
return valid;
}
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops)
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops)
{
int id, ret;
+ uuid_t uuid;
struct device *dev;
struct ffa_device *ffa_dev;
+ if (!part_info)
+ return NULL;
+
id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL);
if (id < 0)
return NULL;
@@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id);
ffa_dev->id = id;
- ffa_dev->vm_id = vm_id;
+ ffa_dev->vm_id = part_info->id;
+ ffa_dev->properties = part_info->properties;
ffa_dev->ops = ops;
- uuid_copy(&ffa_dev->uuid, uuid);
+ import_uuid(&uuid, (u8 *)part_info->uuid);
+ uuid_copy(&ffa_dev->uuid, &uuid);
ret = device_register(&ffa_dev->dev);
if (ret) {
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index b14cbdae94e8..2c2ec3c35f15 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = {
static int ffa_setup_partitions(void)
{
int count, idx, ret;
- uuid_t uuid;
struct ffa_device *ffa_dev;
struct ffa_dev_part_info *info;
struct ffa_partition_info *pbuf, *tpbuf;
@@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void)
xa_init(&drv_info->partition_info);
for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) {
- import_uuid(&uuid, (u8 *)tpbuf->uuid);
-
/* Note that if the UUID will be uuid_null, that will require
* ffa_bus_notifier() to find the UUID of this partition id
* with help of ffa_device_match_uuid(). FF-A v1.1 and above
* provides UUID here for each partition as part of the
* discovery API and the same is passed.
*/
- ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops);
+ ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops);
if (!ffa_dev) {
pr_err("%s: failed to register partition ID 0x%x\n",
__func__, tpbuf->id);
continue;
}
- ffa_dev->properties = tpbuf->properties;
-
if (drv_info->version > FFA_VERSION_1_0 &&
!(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC))
ffa_mode_32bit_set(ffa_dev);
diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig
index 2883ed24a84d..a01bf5e47301 100644
--- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig
+++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig
@@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT
config IMX_SCMI_MISC_EXT
tristate "i.MX SCMI MISC EXTENSION"
depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF)
+ depends on IMX_SCMI_MISC_DRV
default y if ARCH_MXC
help
This enables i.MX System MISC control logic such as gpio expander
diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 477d3f32d99a..907cd149c40a 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -25,7 +25,6 @@ config IMX_SCU
config IMX_SCMI_MISC_DRV
tristate "IMX SCMI MISC Protocol driver"
- depends on IMX_SCMI_MISC_EXT || COMPILE_TEST
default y if ARCH_MXC
help
The System Controller Management Interface firmware (SCMI FW) is
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
index 5ac59b62020c..18b3b1aaa1d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c
@@ -345,11 +345,10 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check,
coredump->skip_vram_check = skip_vram_check;
coredump->reset_vram_lost = vram_lost;
- if (job && job->vm) {
- struct amdgpu_vm *vm = job->vm;
+ if (job && job->pasid) {
struct amdgpu_task_info *ti;
- ti = amdgpu_vm_get_task_info_vm(vm);
+ ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid);
if (ti) {
coredump->reset_task_info = *ti;
amdgpu_vm_put_task_info(ti);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 16f2605ac50b..1ce20a19be8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -253,7 +253,6 @@ void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds,
void amdgpu_job_free_resources(struct amdgpu_job *job)
{
- struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
struct dma_fence *f;
unsigned i;
@@ -266,7 +265,7 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
f = NULL;
for (i = 0; i < job->num_ibs; ++i)
- amdgpu_ib_free(ring->adev, &job->ibs[i], f);
+ amdgpu_ib_free(NULL, &job->ibs[i], f);
}
static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 8d2562d0f143..73e02141a6e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1260,10 +1260,9 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
* next command submission.
*/
if (amdgpu_vm_is_bo_always_valid(vm, bo)) {
- uint32_t mem_type = bo->tbo.resource->mem_type;
-
- if (!(bo->preferred_domains &
- amdgpu_mem_type_to_domain(mem_type)))
+ if (bo->tbo.resource &&
+ !(bo->preferred_domains &
+ amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type)))
amdgpu_vm_bo_evicted(&bo_va->base);
else
amdgpu_vm_bo_idle(&bo_va->base);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 47b47d21f464..6c19626ec59e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -4105,7 +4105,7 @@ static int gfx_v12_0_set_clockgating_state(void *handle,
if (amdgpu_sriov_vf(adev))
return 0;
- switch (adev->ip_versions[GC_HWIP][0]) {
+ switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
case IP_VERSION(12, 0, 0):
case IP_VERSION(12, 0, 1):
gfx_v12_0_update_gfx_clock_gating(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
index 0fbc3be81f14..f2ab5001b492 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
@@ -108,7 +108,7 @@ mmhub_v4_1_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
dev_err(adev->dev,
"MMVM_L2_PROTECTION_FAULT_STATUS_LO32:0x%08X\n",
status);
- switch (adev->ip_versions[MMHUB_HWIP][0]) {
+ switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
case IP_VERSION(4, 1, 0):
mmhub_cid = mmhub_client_ids_v4_1_0[cid][rw];
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index b1b57dcc5a73..d1032e9992b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -271,8 +271,19 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
.ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK,
};
+#define regRCC_DEV0_EPF6_STRAP4 0xd304
+#define regRCC_DEV0_EPF6_STRAP4_BASE_IDX 5
+
static void nbio_v7_0_init_registers(struct amdgpu_device *adev)
{
+ uint32_t data;
+
+ switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
+ case IP_VERSION(2, 5, 0):
+ data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4) & ~BIT(23);
+ WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4, data);
+ break;
+ }
}
#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 814ab59fdd4a..41421da63a08 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -275,7 +275,7 @@ static void nbio_v7_11_init_registers(struct amdgpu_device *adev)
if (def != data)
WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
- switch (adev->ip_versions[NBIO_HWIP][0]) {
+ switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
case IP_VERSION(7, 11, 0):
case IP_VERSION(7, 11, 1):
case IP_VERSION(7, 11, 2):
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index 1ac730328516..3fb6d2aa7e3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -247,7 +247,7 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
if (def != data)
WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data);
- switch (adev->ip_versions[NBIO_HWIP][0]) {
+ switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
case IP_VERSION(7, 7, 0):
data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23);
WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index b22fb7eafcd3..9ec53431f2c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -2108,7 +2108,7 @@ static int smu_v14_0_2_enable_gfx_features(struct smu_context *smu)
{
struct amdgpu_device *adev = smu->adev;
- if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(14, 0, 2))
+ if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 2))
return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableAllSmuFeatures,
FEATURE_PWR_GFX, NULL);
else
diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c
index 48b2df120086..90fe07a89260 100644
--- a/drivers/gpu/drm/display/drm_dp_tunnel.c
+++ b/drivers/gpu/drm/display/drm_dp_tunnel.c
@@ -1896,8 +1896,8 @@ static void destroy_mgr(struct drm_dp_tunnel_mgr *mgr)
*
* Creates a DP tunnel manager for @dev.
*
- * Returns a pointer to the tunnel manager if created successfully or NULL in
- * case of an error.
+ * Returns a pointer to the tunnel manager if created successfully or error
+ * pointer in case of failure.
*/
struct drm_dp_tunnel_mgr *
drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
@@ -1907,7 +1907,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
mgr = kzalloc(sizeof(*mgr), GFP_KERNEL);
if (!mgr)
- return NULL;
+ return ERR_PTR(-ENOMEM);
mgr->dev = dev;
init_waitqueue_head(&mgr->bw_req_queue);
@@ -1916,7 +1916,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
if (!mgr->groups) {
kfree(mgr);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
#ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG
@@ -1927,7 +1927,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
if (!init_group(mgr, &mgr->groups[i])) {
destroy_mgr(mgr);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
mgr->group_count++;
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 6ba167a33461..71573b85d924 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1287,14 +1287,11 @@ EXPORT_SYMBOL(drm_mode_set_name);
*/
int drm_mode_vrefresh(const struct drm_display_mode *mode)
{
- unsigned int num, den;
+ unsigned int num = 1, den = 1;
if (mode->htotal == 0 || mode->vtotal == 0)
return 0;
- num = mode->clock;
- den = mode->htotal * mode->vtotal;
-
if (mode->flags & DRM_MODE_FLAG_INTERLACE)
num *= 2;
if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
@@ -1302,6 +1299,12 @@ int drm_mode_vrefresh(const struct drm_display_mode *mode)
if (mode->vscan > 1)
den *= mode->vscan;
+ if (check_mul_overflow(mode->clock, num, &num))
+ return 0;
+
+ if (check_mul_overflow(mode->htotal * mode->vtotal, den, &den))
+ return 0;
+
return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(num, 1000), den);
}
EXPORT_SYMBOL(drm_mode_vrefresh);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index ba55c059063d..fe1f85e5dda3 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -343,6 +343,11 @@ struct intel_engine_guc_stats {
* @start_gt_clk: GT clock time of last idle to active transition.
*/
u64 start_gt_clk;
+
+ /**
+ * @total: The last value of total returned
+ */
+ u64 total;
};
union intel_engine_tlb_inv_reg {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index ed979847187f..ee12ee0ed418 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1243,6 +1243,21 @@ static void __get_engine_usage_record(struct intel_engine_cs *engine,
} while (++i < 6);
}
+static void __set_engine_usage_record(struct intel_engine_cs *engine,
+ u32 last_in, u32 id, u32 total)
+{
+ struct iosys_map rec_map = intel_guc_engine_usage_record_map(engine);
+
+#define record_write(map_, field_, val_) \
+ iosys_map_wr_field(map_, 0, struct guc_engine_usage_record, field_, val_)
+
+ record_write(&rec_map, last_switch_in_stamp, last_in);
+ record_write(&rec_map, current_context_index, id);
+ record_write(&rec_map, total_runtime, total);
+
+#undef record_write
+}
+
static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
{
struct intel_engine_guc_stats *stats = &engine->stats.guc;
@@ -1363,9 +1378,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
total += intel_gt_clock_interval_to_ns(gt, clk);
}
+ if (total > stats->total)
+ stats->total = total;
+
spin_unlock_irqrestore(&guc->timestamp.lock, flags);
- return ns_to_ktime(total);
+ return ns_to_ktime(stats->total);
}
static void guc_enable_busyness_worker(struct intel_guc *guc)
@@ -1431,8 +1449,21 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
guc_update_pm_timestamp(guc, &unused);
for_each_engine(engine, gt, id) {
+ struct intel_engine_guc_stats *stats = &engine->stats.guc;
+
guc_update_engine_gt_clks(engine);
- engine->stats.guc.prev_total = 0;
+
+ /*
+ * If resetting a running context, accumulate the active
+ * time as well since there will be no context switch.
+ */
+ if (stats->running) {
+ u64 clk = guc->timestamp.gt_stamp - stats->start_gt_clk;
+
+ stats->total_gt_clks += clk;
+ }
+ stats->prev_total = 0;
+ stats->running = 0;
}
spin_unlock_irqrestore(&guc->timestamp.lock, flags);
@@ -1543,6 +1574,9 @@ static void guc_timestamp_ping(struct work_struct *wrk)
static int guc_action_enable_usage_stats(struct intel_guc *guc)
{
+ struct intel_gt *gt = guc_to_gt(guc);
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
u32 offset = intel_guc_engine_usage_offset(guc);
u32 action[] = {
INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF,
@@ -1550,6 +1584,9 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc)
0,
};
+ for_each_engine(engine, gt, id)
+ __set_engine_usage_record(engine, 0, 0xffffffff, 0);
+
return intel_guc_send(guc, action, ARRAY_SIZE(action));
}
diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c
index 8b48bba18131..3644a7544b93 100644
--- a/drivers/gpu/drm/panel/panel-himax-hx83102.c
+++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c
@@ -565,6 +565,8 @@ static int hx83102_get_modes(struct drm_panel *panel,
struct drm_display_mode *mode;
mode = drm_mode_duplicate(connector->dev, m);
+ if (!mode)
+ return -ENOMEM;
mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
drm_mode_set_name(mode);
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c
index b036208f9356..08b22b592ab0 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c
@@ -481,9 +481,9 @@ static int nt35950_probe(struct mipi_dsi_device *dsi)
return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n");
nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info);
- if (!nt->dsi[1]) {
+ if (IS_ERR(nt->dsi[1])) {
dev_err(dev, "Cannot get secondary DSI node\n");
- return -ENODEV;
+ return PTR_ERR(nt->dsi[1]);
}
num_dsis++;
}
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
index eef03d04e0cd..1f72ef7ca74c 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
@@ -1177,6 +1177,7 @@ static int st7701_probe(struct device *dev, int connector_type)
return dev_err_probe(dev, ret, "Failed to get orientation\n");
drm_panel_init(&st7701->panel, dev, &st7701_funcs, connector_type);
+ st7701->panel.prepare_prev_first = true;
/**
* Once sleep out has been issued, ST7701 IC required to wait 120ms
diff --git a/drivers/gpu/drm/panel/panel-synaptics-r63353.c b/drivers/gpu/drm/panel/panel-synaptics-r63353.c
index 169c629746c7..17349825543f 100644
--- a/drivers/gpu/drm/panel/panel-synaptics-r63353.c
+++ b/drivers/gpu/drm/panel/panel-synaptics-r63353.c
@@ -325,7 +325,7 @@ static void r63353_panel_shutdown(struct mipi_dsi_device *dsi)
{
struct r63353_panel *rpanel = mipi_dsi_get_drvdata(dsi);
- r63353_panel_unprepare(&rpanel->base);
+ drm_panel_unprepare(&rpanel->base);
}
static const struct r63353_desc sharp_ls068b3sx02_data = {
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index d35b60c06114..77017d951826 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv)
*/
kvp_transaction.state = HVUTIL_DEVICE_INIT;
+ return 0;
+}
+
+int
+hv_kvp_init_transport(void)
+{
hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL,
kvp_on_msg, kvp_on_reset);
if (!hvt)
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 0d2184be1691..397f4c8fa46c 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -388,6 +388,12 @@ hv_vss_init(struct hv_util_service *srv)
*/
vss_transaction.state = HVUTIL_DEVICE_INIT;
+ return 0;
+}
+
+int
+hv_vss_init_transport(void)
+{
hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL,
vss_on_msg, vss_on_reset);
if (!hvt) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index c4f525325790..3d9360fd909a 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = {
static struct hv_util_service util_kvp = {
.util_cb = hv_kvp_onchannelcallback,
.util_init = hv_kvp_init,
+ .util_init_transport = hv_kvp_init_transport,
.util_pre_suspend = hv_kvp_pre_suspend,
.util_pre_resume = hv_kvp_pre_resume,
.util_deinit = hv_kvp_deinit,
@@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = {
static struct hv_util_service util_vss = {
.util_cb = hv_vss_onchannelcallback,
.util_init = hv_vss_init,
+ .util_init_transport = hv_vss_init_transport,
.util_pre_suspend = hv_vss_pre_suspend,
.util_pre_resume = hv_vss_pre_resume,
.util_deinit = hv_vss_deinit,
@@ -613,6 +615,13 @@ static int util_probe(struct hv_device *dev,
if (ret)
goto error;
+ if (srv->util_init_transport) {
+ ret = srv->util_init_transport();
+ if (ret) {
+ vmbus_close(dev->channel);
+ goto error;
+ }
+ }
return 0;
error:
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index d2856023d53c..52cb744b4d7f 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data);
void vmbus_on_msg_dpc(unsigned long data);
int hv_kvp_init(struct hv_util_service *srv);
+int hv_kvp_init_transport(void);
void hv_kvp_deinit(void);
int hv_kvp_pre_suspend(void);
int hv_kvp_pre_resume(void);
void hv_kvp_onchannelcallback(void *context);
int hv_vss_init(struct hv_util_service *srv);
+int hv_vss_init_transport(void);
void hv_vss_deinit(void);
int hv_vss_pre_suspend(void);
int hv_vss_pre_resume(void);
diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c
index 926d28cd3fab..1c2cb12071b8 100644
--- a/drivers/hwmon/tmp513.c
+++ b/drivers/hwmon/tmp513.c
@@ -182,7 +182,7 @@ struct tmp51x_data {
struct regmap *regmap;
};
-// Set the shift based on the gain 8=4, 4=3, 2=2, 1=1
+// Set the shift based on the gain: 8 -> 1, 4 -> 2, 2 -> 3, 1 -> 4
static inline u8 tmp51x_get_pga_shift(struct tmp51x_data *data)
{
return 5 - ffs(data->pga_gain);
@@ -204,7 +204,9 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos,
* 2's complement number shifted by one to four depending
* on the pga gain setting. 1lsb = 10uV
*/
- *val = sign_extend32(regval, 17 - tmp51x_get_pga_shift(data));
+ *val = sign_extend32(regval,
+ reg == TMP51X_SHUNT_CURRENT_RESULT ?
+ 16 - tmp51x_get_pga_shift(data) : 15);
*val = DIV_ROUND_CLOSEST(*val * 10 * MILLI, data->shunt_uohms);
break;
case TMP51X_BUS_VOLTAGE_RESULT:
@@ -220,7 +222,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos,
break;
case TMP51X_BUS_CURRENT_RESULT:
// Current = (ShuntVoltage * CalibrationRegister) / 4096
- *val = sign_extend32(regval, 16) * data->curr_lsb_ua;
+ *val = sign_extend32(regval, 15) * (long)data->curr_lsb_ua;
*val = DIV_ROUND_CLOSEST(*val, MILLI);
break;
case TMP51X_LOCAL_TEMP_RESULT:
@@ -232,7 +234,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos,
case TMP51X_REMOTE_TEMP_LIMIT_2:
case TMP513_REMOTE_TEMP_LIMIT_3:
// 1lsb = 0.0625 degrees centigrade
- *val = sign_extend32(regval, 16) >> TMP51X_TEMP_SHIFT;
+ *val = sign_extend32(regval, 15) >> TMP51X_TEMP_SHIFT;
*val = DIV_ROUND_CLOSEST(*val * 625, 10);
break;
case TMP51X_N_FACTOR_AND_HYST_1:
diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c
index 1dafadda73af..135300f3b534 100644
--- a/drivers/i2c/busses/i2c-pnx.c
+++ b/drivers/i2c/busses/i2c-pnx.c
@@ -95,7 +95,7 @@ enum {
static inline int wait_timeout(struct i2c_pnx_algo_data *data)
{
- long timeout = data->timeout;
+ long timeout = jiffies_to_msecs(data->timeout);
while (timeout > 0 &&
(ioread32(I2C_REG_STS(data)) & mstatus_active)) {
mdelay(1);
@@ -106,7 +106,7 @@ static inline int wait_timeout(struct i2c_pnx_algo_data *data)
static inline int wait_reset(struct i2c_pnx_algo_data *data)
{
- long timeout = data->timeout;
+ long timeout = jiffies_to_msecs(data->timeout);
while (timeout > 0 &&
(ioread32(I2C_REG_CTL(data)) & mcntrl_reset)) {
mdelay(1);
diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c
index c7f3a4c02470..2c982199782f 100644
--- a/drivers/i2c/busses/i2c-riic.c
+++ b/drivers/i2c/busses/i2c-riic.c
@@ -352,7 +352,7 @@ static int riic_init_hw(struct riic_dev *riic)
if (brl <= (0x1F + 3))
break;
- total_ticks /= 2;
+ total_ticks = DIV_ROUND_UP(total_ticks, 2);
rate /= 2;
}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 8b6159f4cdaf..b0bfb61539c2 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -161,7 +161,22 @@ static bool cpus_have_group0 __ro_after_init;
static void __init gic_prio_init(void)
{
- cpus_have_security_disabled = gic_dist_security_disabled();
+ bool ds;
+
+ ds = gic_dist_security_disabled();
+ if (!ds) {
+ u32 val;
+
+ val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
+ val |= GICD_CTLR_DS;
+ writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+
+ ds = gic_dist_security_disabled();
+ if (ds)
+ pr_warn("Broken GIC integration, security disabled");
+ }
+
+ cpus_have_security_disabled = ds;
cpus_have_group0 = gic_has_group0();
/*
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 813bc20cfb5a..6e62415de2e5 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2924,6 +2924,7 @@ static int msdc_drv_probe(struct platform_device *pdev)
msdc_gate_clock(host);
platform_set_drvdata(pdev, NULL);
release_mem:
+ device_init_wakeup(&pdev->dev, false);
if (host->dma.gpd)
dma_free_coherent(&pdev->dev,
2 * sizeof(struct mt_gpdma_desc),
@@ -2957,6 +2958,7 @@ static void msdc_drv_remove(struct platform_device *pdev)
host->dma.gpd, host->dma.gpd_addr);
dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc),
host->dma.bd, host->dma.bd_addr);
+ device_init_wakeup(&pdev->dev, false);
}
static void msdc_save_reg(struct msdc_host *host)
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 1ad0a6b3a2eb..7b6b82bec855 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
SDHCI_QUIRK_SINGLE_POWER_WRITE |
SDHCI_QUIRK_NO_HISPD_BIT |
- SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER,
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 533bcb77c9f9..97cd8bbf2e32 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir)
static int m_can_interrupt_handler(struct m_can_classdev *cdev)
{
struct net_device *dev = cdev->net;
- u32 ir;
+ u32 ir = 0, ir_read;
int ret;
if (pm_runtime_suspended(cdev->dev))
return IRQ_NONE;
- ir = m_can_read(cdev, M_CAN_IR);
+ /* The m_can controller signals its interrupt status as a level, but
+ * depending in the integration the CPU may interpret the signal as
+ * edge-triggered (for example with m_can_pci). For these
+ * edge-triggered integrations, we must observe that IR is 0 at least
+ * once to be sure that the next interrupt will generate an edge.
+ */
+ while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) {
+ ir |= ir_read;
+
+ /* ACK all irqs */
+ m_can_write(cdev, M_CAN_IR, ir);
+
+ if (!cdev->irq_edge_triggered)
+ break;
+ }
+
m_can_coalescing_update(cdev, ir);
if (!ir)
return IRQ_NONE;
- /* ACK all irqs */
- m_can_write(cdev, M_CAN_IR, ir);
-
if (cdev->ops->clear_interrupts)
cdev->ops->clear_interrupts(cdev);
@@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
return -EINVAL;
}
+ /* Write the INIT bit, in case no hardware reset has happened before
+ * the probe (for example, it was observed that the Intel Elkhart Lake
+ * SoCs do not properly reset the CAN controllers on reboot)
+ */
+ err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT);
+ if (err)
+ return err;
+
if (!cdev->is_peripheral)
netif_napi_add(dev, &cdev->napi, m_can_poll);
@@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
return -EINVAL;
}
- /* Forcing standby mode should be redundant, as the chip should be in
- * standby after a reset. Write the INIT bit anyways, should the chip
- * be configured by previous stage.
- */
- return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT);
+ return 0;
}
static void m_can_stop(struct net_device *dev)
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index 92b2bd8628e6..ef39e8e527ab 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -99,6 +99,7 @@ struct m_can_classdev {
int pm_clock_support;
int pm_wake_source;
int is_peripheral;
+ bool irq_edge_triggered;
// Cached M_CAN_IE register content
u32 active_interrupts;
diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c
index d72fe771dfc7..9ad7419f88f8 100644
--- a/drivers/net/can/m_can/m_can_pci.c
+++ b/drivers/net/can/m_can/m_can_pci.c
@@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
mcan_class->pm_clock_support = 1;
mcan_class->pm_wake_source = 0;
mcan_class->can.clock.freq = id->driver_data;
+ mcan_class->irq_edge_triggered = true;
mcan_class->ops = &m_can_pci_ops;
pci_set_drvdata(pci, mcan_class);
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 77425c7a32db..78f7862ca006 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac)
static int bgmac_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
+ struct device_node *phy_node;
struct bgmac *bgmac;
struct resource *regs;
int ret;
@@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev)
bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset;
bgmac->get_bus_clock = platform_bgmac_get_bus_clock;
bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32;
- if (of_parse_phandle(np, "phy-handle", 0)) {
+ phy_node = of_parse_phandle(np, "phy-handle", 0);
+ if (phy_node) {
+ of_node_put(phy_node);
bgmac->phy_connect = platform_phy_connect;
} else {
bgmac->phy_connect = bgmac_phy_connect_direct;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
index 455a54708be4..a83e7d3c2485 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c
@@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
* driver. Once driver synthesizes cpl_pass_accpet_req the skb will go
* through the regular cpl_pass_accept_req processing in TOM.
*/
- skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req)
- - pktshift, GFP_ATOMIC);
+ skb = alloc_skb(size_add(gl->tot_len,
+ sizeof(struct cpl_pass_accept_req)) -
+ pktshift, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
__skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 890f213da8d1..ae1f523d6841 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -172,6 +172,7 @@ static int create_txqs(struct hinic_dev *nic_dev)
hinic_sq_dbgfs_uninit(nic_dev);
devm_kfree(&netdev->dev, nic_dev->txqs);
+ nic_dev->txqs = NULL;
return err;
}
@@ -268,6 +269,7 @@ static int create_rxqs(struct hinic_dev *nic_dev)
hinic_rq_dbgfs_uninit(nic_dev);
devm_kfree(&netdev->dev, nic_dev->rxqs);
+ nic_dev->rxqs = NULL;
return err;
}
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 3d72aa7b1305..ef93df520887 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
memset(ifh, 0, OCELOT_TAG_LEN);
ocelot_ifh_set_bypass(ifh, 1);
- ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
+ ocelot_ifh_set_src(ifh, ocelot->num_phys_ports);
ocelot_ifh_set_dest(ifh, BIT_ULL(port));
ocelot_ifh_set_qos_class(ifh, qos_class);
ocelot_ifh_set_tag_type(ifh, tag_type);
diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index f9c0dcd965c2..db200e4ec284 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -113,6 +113,7 @@ struct oa_tc6 {
struct mii_bus *mdiobus;
struct spi_device *spi;
struct mutex spi_ctrl_lock; /* Protects spi control transfer */
+ spinlock_t tx_skb_lock; /* Protects tx skb handling */
void *spi_ctrl_tx_buf;
void *spi_ctrl_rx_buf;
void *spi_data_tx_buf;
@@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6)
for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits;
used_tx_credits++) {
if (!tc6->ongoing_tx_skb) {
+ spin_lock_bh(&tc6->tx_skb_lock);
tc6->ongoing_tx_skb = tc6->waiting_tx_skb;
tc6->waiting_tx_skb = NULL;
+ spin_unlock_bh(&tc6->tx_skb_lock);
}
if (!tc6->ongoing_tx_skb)
break;
@@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data)
/* This kthread will be waken up if there is a tx skb or mac-phy
* interrupt to perform spi transfer with tx chunks.
*/
- wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb ||
- tc6->int_flag ||
+ wait_event_interruptible(tc6->spi_wq, tc6->int_flag ||
+ (tc6->waiting_tx_skb &&
+ tc6->tx_credits) ||
kthread_should_stop());
if (kthread_should_stop())
@@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb)
return NETDEV_TX_OK;
}
+ spin_lock_bh(&tc6->tx_skb_lock);
tc6->waiting_tx_skb = skb;
+ spin_unlock_bh(&tc6->tx_skb_lock);
/* Wake spi kthread to perform spi transfer */
wake_up_interruptible(&tc6->spi_wq);
@@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
tc6->netdev = netdev;
SET_NETDEV_DEV(netdev, &spi->dev);
mutex_init(&tc6->spi_ctrl_lock);
+ spin_lock_init(&tc6->tx_skb_lock);
/* Set the SPI controller to pump at realtime priority */
tc6->spi->rt = true;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 9e42d599840d..57edcde9e6f8 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic)
idev->phy_cmb_pages = 0;
idev->cmb_npages = 0;
- destroy_workqueue(ionic->wq);
+ if (ionic->wq) {
+ destroy_workqueue(ionic->wq);
+ ionic->wq = NULL;
+ }
mutex_destroy(&idev->cmb_inuse_lock);
}
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index dda22fa4448c..9b7f78b6cdb1 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -961,8 +961,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev,
len = min_t(u32, sizeof(xcvr->sprom), ee->len);
do {
- memcpy(data, xcvr->sprom, len);
- memcpy(tbuf, xcvr->sprom, len);
+ memcpy(data, &xcvr->sprom[ee->offset], len);
+ memcpy(tbuf, &xcvr->sprom[ee->offset], len);
/* Let's make sure we got a consistent copy */
if (!memcmp(data, tbuf, len))
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 40496587b2b3..3d3f936779f7 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3869,8 +3869,8 @@ int ionic_lif_register(struct ionic_lif *lif)
/* only register LIF0 for now */
err = register_netdev(lif->netdev);
if (err) {
- dev_err(lif->ionic->dev, "Cannot register net device, aborting\n");
- ionic_lif_unregister_phc(lif);
+ dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err);
+ ionic_lif_unregister(lif);
return err;
}
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 09117110e3dd..f86fcecb91a8 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -547,7 +547,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv)
desc = &gq->ts_ring[gq->ring_size];
desc->desc.die_dt = DT_LINKFIX;
rswitch_desc_set_dptr(&desc->desc, gq->ring_dma);
- INIT_LIST_HEAD(&priv->gwca.ts_info_list);
return 0;
}
@@ -1003,9 +1002,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv)
static void rswitch_ts(struct rswitch_private *priv)
{
struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue;
- struct rswitch_gwca_ts_info *ts_info, *ts_info2;
struct skb_shared_hwtstamps shhwtstamps;
struct rswitch_ts_desc *desc;
+ struct rswitch_device *rdev;
+ struct sk_buff *ts_skb;
struct timespec64 ts;
unsigned int num;
u32 tag, port;
@@ -1015,23 +1015,28 @@ static void rswitch_ts(struct rswitch_private *priv)
dma_rmb();
port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl));
- tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl));
-
- list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) {
- if (!(ts_info->port == port && ts_info->tag == tag))
- continue;
-
- memset(&shhwtstamps, 0, sizeof(shhwtstamps));
- ts.tv_sec = __le32_to_cpu(desc->ts_sec);
- ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff));
- shhwtstamps.hwtstamp = timespec64_to_ktime(ts);
- skb_tstamp_tx(ts_info->skb, &shhwtstamps);
- dev_consume_skb_irq(ts_info->skb);
- list_del(&ts_info->list);
- kfree(ts_info);
- break;
- }
+ if (unlikely(port >= RSWITCH_NUM_PORTS))
+ goto next;
+ rdev = priv->rdev[port];
+ tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl));
+ if (unlikely(tag >= TS_TAGS_PER_PORT))
+ goto next;
+ ts_skb = xchg(&rdev->ts_skb[tag], NULL);
+ smp_mb(); /* order rdev->ts_skb[] read before bitmap update */
+ clear_bit(tag, rdev->ts_skb_used);
+
+ if (unlikely(!ts_skb))
+ goto next;
+
+ memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+ ts.tv_sec = __le32_to_cpu(desc->ts_sec);
+ ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff));
+ shhwtstamps.hwtstamp = timespec64_to_ktime(ts);
+ skb_tstamp_tx(ts_skb, &shhwtstamps);
+ dev_consume_skb_irq(ts_skb);
+
+next:
gq->cur = rswitch_next_queue_index(gq, true, 1);
desc = &gq->ts_ring[gq->cur];
}
@@ -1576,8 +1581,9 @@ static int rswitch_open(struct net_device *ndev)
static int rswitch_stop(struct net_device *ndev)
{
struct rswitch_device *rdev = netdev_priv(ndev);
- struct rswitch_gwca_ts_info *ts_info, *ts_info2;
+ struct sk_buff *ts_skb;
unsigned long flags;
+ unsigned int tag;
netif_tx_stop_all_queues(ndev);
@@ -1594,12 +1600,13 @@ static int rswitch_stop(struct net_device *ndev)
if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS))
iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID);
- list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) {
- if (ts_info->port != rdev->port)
- continue;
- dev_kfree_skb_irq(ts_info->skb);
- list_del(&ts_info->list);
- kfree(ts_info);
+ for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT);
+ tag < TS_TAGS_PER_PORT;
+ tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) {
+ ts_skb = xchg(&rdev->ts_skb[tag], NULL);
+ clear_bit(tag, rdev->ts_skb_used);
+ if (ts_skb)
+ dev_kfree_skb(ts_skb);
}
return 0;
@@ -1612,20 +1619,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev,
desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) |
INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT);
if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
- struct rswitch_gwca_ts_info *ts_info;
+ unsigned int tag;
- ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC);
- if (!ts_info)
+ tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT);
+ if (tag == TS_TAGS_PER_PORT)
return false;
+ smp_mb(); /* order bitmap read before rdev->ts_skb[] write */
+ rdev->ts_skb[tag] = skb_get(skb);
+ set_bit(tag, rdev->ts_skb_used);
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
- rdev->ts_tag++;
- desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC);
-
- ts_info->skb = skb_get(skb);
- ts_info->port = rdev->port;
- ts_info->tag = rdev->ts_tag;
- list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list);
+ desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC);
skb_tx_timestamp(skb);
}
diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h
index e020800dcc57..d8d4ed7d7f8b 100644
--- a/drivers/net/ethernet/renesas/rswitch.h
+++ b/drivers/net/ethernet/renesas/rswitch.h
@@ -972,14 +972,6 @@ struct rswitch_gwca_queue {
};
};
-struct rswitch_gwca_ts_info {
- struct sk_buff *skb;
- struct list_head list;
-
- int port;
- u8 tag;
-};
-
#define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32))
struct rswitch_gwca {
unsigned int index;
@@ -989,7 +981,6 @@ struct rswitch_gwca {
struct rswitch_gwca_queue *queues;
int num_queues;
struct rswitch_gwca_queue ts_queue;
- struct list_head ts_info_list;
DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES);
u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS];
u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS];
@@ -997,6 +988,7 @@ struct rswitch_gwca {
};
#define NUM_QUEUES_PER_NDEV 2
+#define TS_TAGS_PER_PORT 256
struct rswitch_device {
struct rswitch_private *priv;
struct net_device *ndev;
@@ -1004,7 +996,8 @@ struct rswitch_device {
void __iomem *addr;
struct rswitch_gwca_queue *tx_queue;
struct rswitch_gwca_queue *rx_queue;
- u8 ts_tag;
+ struct sk_buff *ts_skb[TS_TAGS_PER_PORT];
+ DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT);
bool disabled;
int port;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 766213ee82c1..cf7b59b8cc64 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4220,8 +4220,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
struct stmmac_txq_stats *txq_stats;
struct stmmac_tx_queue *tx_q;
u32 pay_len, mss, queue;
+ dma_addr_t tso_des, des;
u8 proto_hdr_len, hdr;
- dma_addr_t des;
bool set_ic;
int i;
@@ -4317,14 +4317,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
/* If needed take extra descriptors to fill the remaining payload */
tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
+ tso_des = des;
} else {
stmmac_set_desc_addr(priv, first, des);
tmp_pay_len = pay_len;
- des += proto_hdr_len;
+ tso_des = des + proto_hdr_len;
pay_len = 0;
}
- stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
+ stmmac_tso_allocator(priv, tso_des, tmp_pay_len, (nfrags == 0), queue);
/* In case two or more DMA transmit descriptors are allocated for this
* non-paged SKB data, the DMA buffer address should be saved to
diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
index b156493d7084..aea0f0357568 100644
--- a/drivers/net/mdio/fwnode_mdio.c
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode)
static struct mii_timestamper *
fwnode_find_mii_timestamper(struct fwnode_handle *fwnode)
{
+ struct mii_timestamper *mii_ts;
struct of_phandle_args arg;
int err;
@@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode)
else if (err)
return ERR_PTR(err);
- if (arg.args_count != 1)
- return ERR_PTR(-EINVAL);
+ if (arg.args_count != 1) {
+ mii_ts = ERR_PTR(-EINVAL);
+ goto put_node;
+ }
+
+ mii_ts = register_mii_timestamper(arg.np, arg.args[0]);
- return register_mii_timestamper(arg.np, arg.args[0]);
+put_node:
+ of_node_put(arg.np);
+ return mii_ts;
}
int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c
index 70e8bdf34be9..688f05316b5e 100644
--- a/drivers/net/netdevsim/health.c
+++ b/drivers/net/netdevsim/health.c
@@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file,
char *break_msg;
int err;
+ if (count == 0 || count > PAGE_SIZE)
+ return -EINVAL;
break_msg = memdup_user_nul(data, count);
if (IS_ERR(break_msg))
return PTR_ERR(break_msg);
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 017a6102be0a..1b29d1d794a2 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -596,10 +596,10 @@ nsim_pp_hold_write(struct file *file, const char __user *data,
page_pool_put_full_page(ns->page->pp, ns->page, false);
ns->page = NULL;
}
- rtnl_unlock();
exit:
- return count;
+ rtnl_unlock();
+ return ret;
}
static const struct file_operations nsim_pp_hold_fops = {
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index 6ace5a74cddb..1c85dda83825 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -998,9 +998,13 @@ static void __team_compute_features(struct team *team)
unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
IFF_XMIT_DST_RELEASE_PERM;
+ rcu_read_lock();
+ if (list_empty(&team->port_list))
+ goto done;
+
vlan_features = netdev_base_features(vlan_features);
+ enc_features = netdev_base_features(enc_features);
- rcu_read_lock();
list_for_each_entry_rcu(port, &team->port_list, list) {
vlan_features = netdev_increment_features(vlan_features,
port->dev->vlan_features,
@@ -1010,11 +1014,11 @@ static void __team_compute_features(struct team *team)
port->dev->hw_enc_features,
TEAM_ENC_FEATURES);
-
dst_release_flag &= port->dev->priv_flags;
if (port->dev->hard_header_len > max_hard_header_len)
max_hard_header_len = port->dev->hard_header_len;
}
+done:
rcu_read_unlock();
team->dev->vlan_features = vlan_features;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9a0f6eb32016..03fe9e3ee7af 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1481,7 +1481,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
skb->truesize += skb->data_len;
for (i = 1; i < it->nr_segs; i++) {
- const struct iovec *iov = iter_iov(it);
+ const struct iovec *iov = iter_iov(it) + i;
size_t fragsz = iov->iov_len;
struct page *page;
void *frag;
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 286f0c161e33..a565b8c91da5 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -455,7 +455,8 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
}
if (ranges == NULL || rlen == 0) {
offset = of_read_number(addr, na);
- memset(addr, 0, pna * 4);
+ /* set address to zero, pass flags through */
+ memset(addr + pbus->flag_cells, 0, (pna - pbus->flag_cells) * 4);
pr_debug("empty ranges; 1:1 translation\n");
goto finish;
}
@@ -615,7 +616,7 @@ struct device_node *__of_get_dma_parent(const struct device_node *np)
if (ret < 0)
return of_get_parent(np);
- return of_node_get(args.np);
+ return args.np;
}
#endif
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 20603d3c9931..63161d0f72b4 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1455,8 +1455,10 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
map_len--;
/* Check if not found */
- if (!new)
+ if (!new) {
+ ret = -EINVAL;
goto put;
+ }
if (!of_device_is_available(new))
match = 0;
@@ -1466,17 +1468,20 @@ int of_parse_phandle_with_args_map(const struct device_node *np,
goto put;
/* Check for malformed properties */
- if (WARN_ON(new_size > MAX_PHANDLE_ARGS))
- goto put;
- if (map_len < new_size)
+ if (WARN_ON(new_size > MAX_PHANDLE_ARGS) ||
+ map_len < new_size) {
+ ret = -EINVAL;
goto put;
+ }
/* Move forward by new node's #<list>-cells amount */
map += new_size;
map_len -= new_size;
}
- if (!match)
+ if (!match) {
+ ret = -ENOENT;
goto put;
+ }
/* Get the <list>-map-pass-thru property (optional) */
pass = of_get_property(cur, pass_name, NULL);
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index a494f56a0d0e..1fb329c0a55b 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -111,6 +111,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph
else
np = of_find_node_by_phandle(be32_to_cpup(imap));
imap++;
+ len--;
/* Check if not found */
if (!np) {
@@ -354,6 +355,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
return of_irq_parse_oldworld(device, index, out_irq);
/* Get the reg property (if any) */
+ addr_len = 0;
addr = of_get_property(device, "reg", &addr_len);
/* Prevent out-of-bounds read in case of longer interrupt parent address size */
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 11b922fde7af..7bd8390f2fba 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1213,7 +1213,6 @@ DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells")
DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells")
DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells")
DEFINE_SIMPLE_PROP(io_backends, "io-backends", "#io-backend-cells")
-DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL)
DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells")
DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells")
DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells")
@@ -1359,7 +1358,6 @@ static const struct supplier_bindings of_supplier_bindings[] = {
{ .parse_prop = parse_mboxes, },
{ .parse_prop = parse_io_channels, },
{ .parse_prop = parse_io_backends, },
- { .parse_prop = parse_interrupt_parent, },
{ .parse_prop = parse_dmas, .optional = true, },
{ .parse_prop = parse_power_domains, },
{ .parse_prop = parse_hwlocks, },
diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c
index 31f38309b389..c56650b9ff96 100644
--- a/drivers/platform/x86/p2sb.c
+++ b/drivers/platform/x86/p2sb.c
@@ -42,6 +42,7 @@ struct p2sb_res_cache {
};
static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE];
+static bool p2sb_hidden_by_bios;
static void p2sb_get_devfn(unsigned int *devfn)
{
@@ -96,6 +97,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn)
static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
{
+ /*
+ * The BIOS prevents the P2SB device from being enumerated by the PCI
+ * subsystem, so we need to unhide and hide it back to lookup the BAR.
+ */
+ pci_bus_write_config_dword(bus, devfn, P2SBC, 0);
+
/* Scan the P2SB device and cache its BAR0 */
p2sb_scan_and_cache_devfn(bus, devfn);
@@ -103,6 +110,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn)
if (devfn == P2SB_DEVFN_GOLDMONT)
p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT);
+ pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE);
+
if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res))
return -ENOENT;
@@ -128,7 +137,7 @@ static int p2sb_cache_resources(void)
u32 value = P2SBC_HIDE;
struct pci_bus *bus;
u16 class;
- int ret;
+ int ret = 0;
/* Get devfn for P2SB device itself */
p2sb_get_devfn(&devfn_p2sb);
@@ -151,22 +160,53 @@ static int p2sb_cache_resources(void)
*/
pci_lock_rescan_remove();
+ pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
+ p2sb_hidden_by_bios = value & P2SBC_HIDE;
+
/*
- * The BIOS prevents the P2SB device from being enumerated by the PCI
- * subsystem, so we need to unhide and hide it back to lookup the BAR.
- * Unhide the P2SB device here, if needed.
+ * If the BIOS does not hide the P2SB device then its resources
+ * are accesilble. Cache them only if the P2SB device is hidden.
*/
- pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value);
- if (value & P2SBC_HIDE)
- pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0);
+ if (p2sb_hidden_by_bios)
+ ret = p2sb_scan_and_cache(bus, devfn_p2sb);
- ret = p2sb_scan_and_cache(bus, devfn_p2sb);
+ pci_unlock_rescan_remove();
- /* Hide the P2SB device, if it was hidden */
- if (value & P2SBC_HIDE)
- pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE);
+ return ret;
+}
- pci_unlock_rescan_remove();
+static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn,
+ struct resource *mem)
+{
+ struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)];
+
+ if (cache->bus_dev_id != bus->dev.id)
+ return -ENODEV;
+
+ if (!p2sb_valid_resource(&cache->res))
+ return -ENOENT;
+
+ memcpy(mem, &cache->res, sizeof(*mem));
+
+ return 0;
+}
+
+static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn,
+ struct resource *mem)
+{
+ struct pci_dev *pdev;
+ int ret = 0;
+
+ pdev = pci_get_slot(bus, devfn);
+ if (!pdev)
+ return -ENODEV;
+
+ if (p2sb_valid_resource(pci_resource_n(pdev, 0)))
+ p2sb_read_bar0(pdev, mem);
+ else
+ ret = -ENOENT;
+
+ pci_dev_put(pdev);
return ret;
}
@@ -187,8 +227,6 @@ static int p2sb_cache_resources(void)
*/
int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
{
- struct p2sb_res_cache *cache;
-
bus = p2sb_get_bus(bus);
if (!bus)
return -ENODEV;
@@ -196,15 +234,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem)
if (!devfn)
p2sb_get_devfn(&devfn);
- cache = &p2sb_resources[PCI_FUNC(devfn)];
- if (cache->bus_dev_id != bus->dev.id)
- return -ENODEV;
+ if (p2sb_hidden_by_bios)
+ return p2sb_read_from_cache(bus, devfn, mem);
- if (!p2sb_valid_resource(&cache->res))
- return -ENOENT;
-
- memcpy(mem, &cache->res, sizeof(*mem));
- return 0;
+ return p2sb_read_from_dev(bus, devfn, mem);
}
EXPORT_SYMBOL_GPL(p2sb_bar);
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 7af2642b97cb..7c42e303740a 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -1520,6 +1520,14 @@ static struct pci_device_id nhi_ids[] = {
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1),
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI0),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI1),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI0),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI1),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) },
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 7a07c7c1a9c2..16744f25a9a0 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -92,6 +92,10 @@ extern const struct tb_nhi_ops icl_nhi_ops;
#define PCI_DEVICE_ID_INTEL_RPL_NHI1 0xa76d
#define PCI_DEVICE_ID_INTEL_LNL_NHI0 0xa833
#define PCI_DEVICE_ID_INTEL_LNL_NHI1 0xa834
+#define PCI_DEVICE_ID_INTEL_PTL_M_NHI0 0xe333
+#define PCI_DEVICE_ID_INTEL_PTL_M_NHI1 0xe334
+#define PCI_DEVICE_ID_INTEL_PTL_P_NHI0 0xe433
+#define PCI_DEVICE_ID_INTEL_PTL_P_NHI1 0xe434
#define PCI_CLASS_SERIAL_USB_USB4 0x0c0340
diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index 89d2919d0193..eeb64433ebbc 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -103,6 +103,7 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt)
err_nvm:
dev_dbg(&rt->dev, "NVM upgrade disabled\n");
+ rt->no_nvm_upgrade = true;
if (!IS_ERR(nvm))
tb_nvm_free(nvm);
@@ -182,8 +183,6 @@ static ssize_t nvm_authenticate_show(struct device *dev,
if (!rt->nvm)
ret = -EAGAIN;
- else if (rt->no_nvm_upgrade)
- ret = -EOPNOTSUPP;
else
ret = sysfs_emit(buf, "%#x\n", rt->auth_status);
@@ -323,8 +322,6 @@ static ssize_t nvm_version_show(struct device *dev,
if (!rt->nvm)
ret = -EAGAIN;
- else if (rt->no_nvm_upgrade)
- ret = -EOPNOTSUPP;
else
ret = sysfs_emit(buf, "%x.%x\n", rt->nvm->major, rt->nvm->minor);
@@ -342,6 +339,19 @@ static ssize_t vendor_show(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RO(vendor);
+static umode_t retimer_is_visible(struct kobject *kobj, struct attribute *attr,
+ int n)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct tb_retimer *rt = tb_to_retimer(dev);
+
+ if (attr == &dev_attr_nvm_authenticate.attr ||
+ attr == &dev_attr_nvm_version.attr)
+ return rt->no_nvm_upgrade ? 0 : attr->mode;
+
+ return attr->mode;
+}
+
static struct attribute *retimer_attrs[] = {
&dev_attr_device.attr,
&dev_attr_nvm_authenticate.attr,
@@ -351,6 +361,7 @@ static struct attribute *retimer_attrs[] = {
};
static const struct attribute_group retimer_group = {
+ .is_visible = retimer_is_visible,
.attrs = retimer_attrs,
};
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 4f777788e917..a7c6919fbf97 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -2059,6 +2059,37 @@ static void tb_exit_redrive(struct tb_port *port)
}
}
+static void tb_switch_enter_redrive(struct tb_switch *sw)
+{
+ struct tb_port *port;
+
+ tb_switch_for_each_port(sw, port)
+ tb_enter_redrive(port);
+}
+
+/*
+ * Called during system and runtime suspend to forcefully exit redrive
+ * mode without querying whether the resource is available.
+ */
+static void tb_switch_exit_redrive(struct tb_switch *sw)
+{
+ struct tb_port *port;
+
+ if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE))
+ return;
+
+ tb_switch_for_each_port(sw, port) {
+ if (!tb_port_is_dpin(port))
+ continue;
+
+ if (port->redrive) {
+ port->redrive = false;
+ pm_runtime_put(&sw->dev);
+ tb_port_dbg(port, "exit redrive mode\n");
+ }
+ }
+}
+
static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port)
{
struct tb_port *in, *out;
@@ -2909,6 +2940,7 @@ static int tb_start(struct tb *tb, bool reset)
tb_create_usb3_tunnels(tb->root_switch);
/* Add DP IN resources for the root switch */
tb_add_dp_resources(tb->root_switch);
+ tb_switch_enter_redrive(tb->root_switch);
/* Make the discovered switches available to the userspace */
device_for_each_child(&tb->root_switch->dev, NULL,
tb_scan_finalize_switch);
@@ -2924,6 +2956,7 @@ static int tb_suspend_noirq(struct tb *tb)
tb_dbg(tb, "suspending...\n");
tb_disconnect_and_release_dp(tb);
+ tb_switch_exit_redrive(tb->root_switch);
tb_switch_suspend(tb->root_switch, false);
tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */
tb_dbg(tb, "suspend finished\n");
@@ -3016,6 +3049,7 @@ static int tb_resume_noirq(struct tb *tb)
tb_dbg(tb, "tunnels restarted, sleeping for 100ms\n");
msleep(100);
}
+ tb_switch_enter_redrive(tb->root_switch);
/* Allow tb_handle_hotplug to progress events */
tcm->hotplug_active = true;
tb_dbg(tb, "resume finished\n");
@@ -3079,6 +3113,12 @@ static int tb_runtime_suspend(struct tb *tb)
struct tb_cm *tcm = tb_priv(tb);
mutex_lock(&tb->lock);
+ /*
+ * The below call only releases DP resources to allow exiting and
+ * re-entering redrive mode.
+ */
+ tb_disconnect_and_release_dp(tb);
+ tb_switch_exit_redrive(tb->root_switch);
tb_switch_suspend(tb->root_switch, true);
tcm->hotplug_active = false;
mutex_unlock(&tb->lock);
@@ -3110,6 +3150,7 @@ static int tb_runtime_resume(struct tb *tb)
tb_restore_children(tb->root_switch);
list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list)
tb_tunnel_restart(tunnel);
+ tb_switch_enter_redrive(tb->root_switch);
tcm->hotplug_active = true;
mutex_unlock(&tb->lock);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index f318864732f2..b267dae14d39 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1192,8 +1192,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
* Keep retrying until the EP starts and stops again, on
* chips where this is known to help. Wait for 100ms.
*/
- if (!(xhci->quirks & XHCI_NEC_HOST))
- break;
if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100)))
break;
fallthrough;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 9ba5584061c8..64317b390d22 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -625,6 +625,8 @@ static void option_instat_callback(struct urb *urb);
#define MEIGSMART_PRODUCT_SRM825L 0x4d22
/* MeiG Smart SLM320 based on UNISOC UIS8910 */
#define MEIGSMART_PRODUCT_SLM320 0x4d41
+/* MeiG Smart SLM770A based on ASR1803 */
+#define MEIGSMART_PRODUCT_SLM770A 0x4d57
/* Device flags */
@@ -1395,6 +1397,12 @@ static const struct usb_device_id option_ids[] = {
.driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff), /* Telit FN920C04 (MBIM) */
.driver_info = NCTRL(3) | RSVD(4) | RSVD(5) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff), /* Telit FE910C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff), /* Telit FE910C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -2247,6 +2255,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = NCTRL(2) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7127, 0xff, 0x00, 0x00),
.driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7129, 0xff, 0x00, 0x00), /* MediaTek T7XX */
+ .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) },
{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) },
{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MPL200),
.driver_info = RSVD(1) | RSVD(4) },
@@ -2375,6 +2385,18 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for Golbal EDU */
{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0x00, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
@@ -2382,9 +2404,14 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) },
+ { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */
+ .driver_info = NCTRL(1) },
+ { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */
+ .driver_info = NCTRL(3) },
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 7e0f9600b80c..3d2376caedfa 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -649,8 +649,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length)
map_length = min(map_length, bbio->fs_info->max_zone_append_size);
sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits,
&nr_segs, map_length);
- if (sector_offset)
- return sector_offset << SECTOR_SHIFT;
+ if (sector_offset) {
+ /*
+ * bio_split_rw_at() could split at a size smaller than our
+ * sectorsize and thus cause unaligned I/Os. Fix that by
+ * always rounding down to the nearest boundary.
+ */
+ return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize);
+ }
return map_length;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 317a3712270f..2034d3710833 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -370,6 +370,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi
WRITE_ONCE(root->last_trans, transid);
}
+/*
+ * Return the generation this root started with.
+ *
+ * Every normal root that is created with root->root_key.offset set to it's
+ * originating generation. If it is a snapshot it is the generation when the
+ * snapshot was created.
+ *
+ * However for TREE_RELOC roots root_key.offset is the objectid of the owning
+ * tree root. Thankfully we copy the root item of the owning tree root, which
+ * has it's last_snapshot set to what we would have root_key.offset set to, so
+ * return that if this is a TREE_RELOC root.
+ */
+static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root)
+{
+ if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
+ return btrfs_root_last_snapshot(&root->root_item);
+ return root->root_key.offset;
+}
+
/*
* Structure that conveys information about an extent that is going to replace
* all the extents in a file range.
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b43a8611aca5..f3e93ba7ec97 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5308,7 +5308,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control *
* reference to it.
*/
generation = btrfs_node_ptr_generation(eb, slot);
- if (!wc->update_ref || generation <= root->root_key.offset)
+ if (!wc->update_ref || generation <= btrfs_root_origin_generation(root))
return false;
/*
@@ -5363,7 +5363,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
goto reada;
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset)
+ generation <= btrfs_root_origin_generation(root))
continue;
/* We don't lock the tree block, it's OK to be racy here */
@@ -5706,7 +5706,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
* for the subtree
*/
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset) {
+ generation <= btrfs_root_origin_generation(root)) {
wc->lookup_info = 1;
return 1;
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 7b50263723bc..ffa5b83d3a4a 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf,
dref_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_extent_data_ref_count(leaf, dref);
break;
/* Contains parent bytenr and ref count */
@@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf,
inline_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_shared_data_ref_count(leaf, sref);
break;
case BTRFS_EXTENT_OWNER_REF_KEY:
@@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf,
{
u32 expect_item_size = 0;
- if (key->type == BTRFS_SHARED_DATA_REF_KEY)
+ if (key->type == BTRFS_SHARED_DATA_REF_KEY) {
+ struct btrfs_shared_data_ref *sref;
+
+ sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref);
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
+
expect_item_size = sizeof(struct btrfs_shared_data_ref);
+ }
if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) {
generic_err(leaf, slot,
@@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
offset, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
}
return 0;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 4b8d59ebda00..67468d88f139 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
if (ceph_inode_is_shutdown(inode))
return -EIO;
- if (!len)
+ if (!len || !i_size)
return 0;
/*
* flush any page cache pages in this range. this
@@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
int num_pages;
size_t page_off;
bool more;
- int idx;
+ int idx = 0;
size_t left;
struct ceph_osd_req_op *op;
u64 read_off = off;
@@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
len = read_off + read_len - off;
more = len < iov_iter_count(to);
+ op = &req->r_ops[0];
+ if (sparse) {
+ extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+ ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
+
num_pages = calc_pages_for(read_off, read_len);
page_off = offset_in_page(off);
pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
@@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
osd_req_op_extent_osd_data_pages(req, 0, pages, read_len,
offset_in_page(read_off),
- false, false);
-
- op = &req->r_ops[0];
- if (sparse) {
- extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
- ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
- if (ret) {
- ceph_osdc_put_request(req);
- break;
- }
- }
+ false, true);
ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
@@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
else if (ret == -ENOENT)
ret = 0;
- if (ret > 0 && IS_ENCRYPTED(inode)) {
+ if (ret < 0) {
+ ceph_osdc_put_request(req);
+ if (ret == -EBLOCKLISTED)
+ fsc->blocklisted = true;
+ break;
+ }
+
+ if (IS_ENCRYPTED(inode)) {
int fret;
fret = ceph_fscrypt_decrypt_extents(inode, pages,
@@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
ret = min_t(ssize_t, fret, len);
}
- ceph_osdc_put_request(req);
-
/* Short read but not EOF? Zero out the remainder. */
- if (ret >= 0 && ret < len && (off + ret < i_size)) {
+ if (ret < len && (off + ret < i_size)) {
int zlen = min(len - ret, i_size - off - ret);
int zoff = page_off + ret;
@@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
ret += zlen;
}
- idx = 0;
- if (ret <= 0)
- left = 0;
- else if (off + ret > i_size)
- left = i_size - off;
+ if (off + ret > i_size)
+ left = (i_size > off) ? i_size - off : 0;
else
left = ret;
+
while (left > 0) {
size_t plen, copied;
@@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
break;
}
}
- ceph_release_page_vector(pages, num_pages);
- if (ret < 0) {
- if (ret == -EBLOCKLISTED)
- fsc->blocklisted = true;
- break;
- }
+ ceph_osdc_put_request(req);
if (off >= i_size || !more)
break;
@@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
break;
}
+ op = &req->r_ops[0];
+ if (sparse) {
+ extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+ ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
+ if (ret) {
+ ceph_osdc_put_request(req);
+ break;
+ }
+ }
+
len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
if (len < 0) {
ceph_osdc_put_request(req);
@@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
if (len != size)
osd_req_op_extent_update(req, 0, len);
+ osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
+
/*
* To simplify error handling, allow AIO when IO within i_size
* or IO can be satisfied by single OSD request.
@@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req->r_mtime = mtime;
}
- osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
- op = &req->r_ops[0];
- if (sparse) {
- extent_cnt = __ceph_sparse_read_ext_count(inode, size);
- ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
- if (ret) {
- ceph_osdc_put_request(req);
- break;
- }
- }
-
if (aio_req) {
aio_req->total_len += len;
aio_req->num_reqs++;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index cf92b75745e2..f48242262b21 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2808,12 +2808,11 @@ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
if (pos < 0) {
/*
- * A rename didn't occur, but somehow we didn't end up where
- * we thought we would. Throw a warning and try again.
+ * The path is longer than PATH_MAX and this function
+ * cannot ever succeed. Creating paths that long is
+ * possible with Ceph, but Linux cannot use them.
*/
- pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n",
- pos);
- goto retry;
+ return ERR_PTR(-ENAMETOOLONG);
}
*pbase = base;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 86480e5a215e..c235f9a60394 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
switch (token) {
case Opt_snapdirname:
+ if (strlen(param->string) > NAME_MAX)
+ return invalfc(fc, "snapdirname too long");
kfree(fsopt->snapdir_name);
fsopt->snapdir_name = param->string;
param->string = NULL;
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 586446e02ef7..ec23da8405ff 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -51,7 +51,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
*
* VariableName-12345678-1234-1234-1234-1234567891bc
*/
-bool efivarfs_valid_name(const char *str, int len)
+static bool efivarfs_valid_name(const char *str, int len)
{
const char *s = str + len - EFI_VARIABLE_GUID_LEN;
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index d71d2e08422f..74f0602a9e01 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -60,7 +60,6 @@ bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
extern const struct file_operations efivarfs_file_operations;
extern const struct inode_operations efivarfs_dir_inode_operations;
-extern bool efivarfs_valid_name(const char *str, int len);
extern struct inode *efivarfs_get_inode(struct super_block *sb,
const struct inode *dir, int mode, dev_t dev,
bool is_removable);
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index a929f1b613be..beba15673be8 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -144,9 +144,6 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr)
const unsigned char *s = qstr->name;
unsigned int len = qstr->len;
- if (!efivarfs_valid_name(s, len))
- return -EINVAL;
-
while (len-- > EFI_VARIABLE_GUID_LEN)
hash = partial_name_hash(*s++, hash);
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index fa51437e1d99..722151d3fee8 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -63,10 +63,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
buf->file = NULL;
if (erofs_is_fileio_mode(sbi)) {
- buf->file = sbi->fdev; /* some fs like FUSE needs it */
+ buf->file = sbi->dif0.file; /* some fs like FUSE needs it */
buf->mapping = buf->file->f_mapping;
} else if (erofs_is_fscache_mode(sb))
- buf->mapping = sbi->s_fscache->inode->i_mapping;
+ buf->mapping = sbi->dif0.fscache->inode->i_mapping;
else
buf->mapping = sb->s_bdev->bd_mapping;
}
@@ -186,19 +186,13 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map)
}
static void erofs_fill_from_devinfo(struct erofs_map_dev *map,
- struct erofs_device_info *dif)
+ struct super_block *sb, struct erofs_device_info *dif)
{
+ map->m_sb = sb;
+ map->m_dif = dif;
map->m_bdev = NULL;
- map->m_fp = NULL;
- if (dif->file) {
- if (S_ISBLK(file_inode(dif->file)->i_mode))
- map->m_bdev = file_bdev(dif->file);
- else
- map->m_fp = dif->file;
- }
- map->m_daxdev = dif->dax_dev;
- map->m_dax_part_off = dif->dax_part_off;
- map->m_fscache = dif->fscache;
+ if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode))
+ map->m_bdev = file_bdev(dif->file);
}
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
@@ -208,12 +202,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
erofs_off_t startoff, length;
int id;
- map->m_bdev = sb->s_bdev;
- map->m_daxdev = EROFS_SB(sb)->dax_dev;
- map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
- map->m_fscache = EROFS_SB(sb)->s_fscache;
- map->m_fp = EROFS_SB(sb)->fdev;
-
+ erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0);
+ map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */
if (map->m_deviceid) {
down_read(&devs->rwsem);
dif = idr_find(&devs->tree, map->m_deviceid - 1);
@@ -226,7 +216,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
up_read(&devs->rwsem);
return 0;
}
- erofs_fill_from_devinfo(map, dif);
+ erofs_fill_from_devinfo(map, sb, dif);
up_read(&devs->rwsem);
} else if (devs->extra_devices && !devs->flatdev) {
down_read(&devs->rwsem);
@@ -239,7 +229,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
if (map->m_pa >= startoff &&
map->m_pa < startoff + length) {
map->m_pa -= startoff;
- erofs_fill_from_devinfo(map, dif);
+ erofs_fill_from_devinfo(map, sb, dif);
break;
}
}
@@ -309,7 +299,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
iomap->offset = map.m_la;
if (flags & IOMAP_DAX)
- iomap->dax_dev = mdev.m_daxdev;
+ iomap->dax_dev = mdev.m_dif->dax_dev;
else
iomap->bdev = mdev.m_bdev;
iomap->length = map.m_llen;
@@ -338,7 +328,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
iomap->type = IOMAP_MAPPED;
iomap->addr = mdev.m_pa;
if (flags & IOMAP_DAX)
- iomap->addr += mdev.m_dax_part_off;
+ iomap->addr += mdev.m_dif->dax_part_off;
}
return 0;
}
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 3af96b1e2c2a..33f8539dda4a 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -9,6 +9,7 @@ struct erofs_fileio_rq {
struct bio_vec bvecs[BIO_MAX_VECS];
struct bio bio;
struct kiocb iocb;
+ struct super_block *sb;
};
struct erofs_fileio {
@@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT;
rq->iocb.ki_ioprio = get_current_ioprio();
rq->iocb.ki_complete = erofs_fileio_ki_complete;
- rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ?
- IOCB_DIRECT : 0;
+ if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) &&
+ rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT)
+ rq->iocb.ki_flags = IOCB_DIRECT;
iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt,
rq->bio.bi_iter.bi_size);
ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter);
@@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev)
GFP_KERNEL | __GFP_NOFAIL);
bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ);
- rq->iocb.ki_filp = mdev->m_fp;
+ rq->iocb.ki_filp = mdev->m_dif->file;
+ rq->sb = mdev->m_sb;
return rq;
}
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index fda16eedafb5..ce3d8737df85 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev)
io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL);
bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ);
- io->io.private = mdev->m_fscache->cookie;
+ io->io.private = mdev->m_dif->fscache->cookie;
io->io.end_io = erofs_fscache_bio_endio;
refcount_set(&io->io.ref, 1);
return &io->bio;
@@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req)
if (!io)
return -ENOMEM;
iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count);
- ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie,
+ ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie,
mdev.m_pa + (pos - map.m_la), io);
erofs_fscache_req_io_put(io);
@@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb)
if (IS_ERR(fscache))
return PTR_ERR(fscache);
- sbi->s_fscache = fscache;
+ sbi->dif0.fscache = fscache;
return 0;
}
@@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
- erofs_fscache_unregister_cookie(sbi->s_fscache);
+ erofs_fscache_unregister_cookie(sbi->dif0.fscache);
if (sbi->domain)
erofs_fscache_domain_put(sbi->domain);
else
fscache_relinquish_volume(sbi->volume, NULL, false);
- sbi->s_fscache = NULL;
+ sbi->dif0.fscache = NULL;
sbi->volume = NULL;
sbi->domain = NULL;
}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 9b03c8f323a7..77e785a6dfa7 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -113,6 +113,7 @@ struct erofs_xattr_prefix_item {
};
struct erofs_sb_info {
+ struct erofs_device_info dif0;
struct erofs_mount_opts opt; /* options */
#ifdef CONFIG_EROFS_FS_ZIP
/* list for all registered superblocks, mainly for shrinker */
@@ -130,13 +131,9 @@ struct erofs_sb_info {
struct erofs_sb_lz4_info lz4;
#endif /* CONFIG_EROFS_FS_ZIP */
- struct file *fdev;
struct inode *packed_inode;
struct erofs_dev_context *devs;
- struct dax_device *dax_dev;
- u64 dax_part_off;
u64 total_blocks;
- u32 primarydevice_blocks;
u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
@@ -172,7 +169,6 @@ struct erofs_sb_info {
/* fscache support */
struct fscache_volume *volume;
- struct erofs_fscache *s_fscache;
struct erofs_domain *domain;
char *fsid;
char *domain_id;
@@ -186,6 +182,7 @@ struct erofs_sb_info {
#define EROFS_MOUNT_POSIX_ACL 0x00000020
#define EROFS_MOUNT_DAX_ALWAYS 0x00000040
#define EROFS_MOUNT_DAX_NEVER 0x00000080
+#define EROFS_MOUNT_DIRECT_IO 0x00000100
#define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option)
#define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option)
@@ -193,7 +190,7 @@ struct erofs_sb_info {
static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi)
{
- return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev;
+ return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file;
}
static inline bool erofs_is_fscache_mode(struct super_block *sb)
@@ -370,11 +367,9 @@ enum {
};
struct erofs_map_dev {
- struct erofs_fscache *m_fscache;
+ struct super_block *m_sb;
+ struct erofs_device_info *m_dif;
struct block_device *m_bdev;
- struct dax_device *m_daxdev;
- struct file *m_fp;
- u64 m_dax_part_off;
erofs_off_t m_pa;
unsigned int m_deviceid;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 2dd7d819572f..5b279977c9d5 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -218,7 +218,7 @@ static int erofs_scan_devices(struct super_block *sb,
struct erofs_device_info *dif;
int id, err = 0;
- sbi->total_blocks = sbi->primarydevice_blocks;
+ sbi->total_blocks = sbi->dif0.blocks;
if (!erofs_sb_has_device_table(sbi))
ondisk_extradevs = 0;
else
@@ -322,7 +322,7 @@ static int erofs_read_superblock(struct super_block *sb)
sbi->sb_size);
goto out;
}
- sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
+ sbi->dif0.blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
@@ -379,14 +379,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
}
enum {
- Opt_user_xattr,
- Opt_acl,
- Opt_cache_strategy,
- Opt_dax,
- Opt_dax_enum,
- Opt_device,
- Opt_fsid,
- Opt_domain_id,
+ Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
+ Opt_device, Opt_fsid, Opt_domain_id, Opt_directio,
Opt_err
};
@@ -413,6 +407,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
fsparam_string("device", Opt_device),
fsparam_string("fsid", Opt_fsid),
fsparam_string("domain_id", Opt_domain_id),
+ fsparam_flag_no("directio", Opt_directio),
{}
};
@@ -526,6 +521,16 @@ static int erofs_fc_parse_param(struct fs_context *fc,
errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
#endif
+ case Opt_directio:
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+ if (result.boolean)
+ set_opt(&sbi->opt, DIRECT_IO);
+ else
+ clear_opt(&sbi->opt, DIRECT_IO);
+#else
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+#endif
+ break;
default:
return -ENOPARAM;
}
@@ -617,9 +622,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
return -EINVAL;
}
- sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
- &sbi->dax_part_off,
- NULL, NULL);
+ sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
+ &sbi->dif0.dax_part_off, NULL, NULL);
}
err = erofs_read_superblock(sb);
@@ -642,7 +646,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
}
if (test_opt(&sbi->opt, DAX_ALWAYS)) {
- if (!sbi->dax_dev) {
+ if (!sbi->dif0.dax_dev) {
errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
clear_opt(&sbi->opt, DAX_ALWAYS);
} else if (sbi->blkszbits != PAGE_SHIFT) {
@@ -718,16 +722,18 @@ static int erofs_fc_get_tree(struct fs_context *fc)
GET_TREE_BDEV_QUIET_LOOKUP : 0);
#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
if (ret == -ENOTBLK) {
+ struct file *file;
+
if (!fc->source)
return invalf(fc, "No source specified");
- sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
- if (IS_ERR(sbi->fdev))
- return PTR_ERR(sbi->fdev);
+ file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+ sbi->dif0.file = file;
- if (S_ISREG(file_inode(sbi->fdev)->i_mode) &&
- sbi->fdev->f_mapping->a_ops->read_folio)
+ if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) &&
+ sbi->dif0.file->f_mapping->a_ops->read_folio)
return get_tree_nodev(fc, erofs_fc_fill_super);
- fput(sbi->fdev);
}
#endif
return ret;
@@ -778,19 +784,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs)
kfree(devs);
}
-static void erofs_fc_free(struct fs_context *fc)
+static void erofs_sb_free(struct erofs_sb_info *sbi)
{
- struct erofs_sb_info *sbi = fc->s_fs_info;
-
- if (!sbi)
- return;
-
erofs_free_dev_context(sbi->devs);
kfree(sbi->fsid);
kfree(sbi->domain_id);
+ if (sbi->dif0.file)
+ fput(sbi->dif0.file);
kfree(sbi);
}
+static void erofs_fc_free(struct fs_context *fc)
+{
+ struct erofs_sb_info *sbi = fc->s_fs_info;
+
+ if (sbi) /* free here if an error occurs before transferring to sb */
+ erofs_sb_free(sbi);
+}
+
static const struct fs_context_operations erofs_context_ops = {
.parse_param = erofs_fc_parse_param,
.get_tree = erofs_fc_get_tree,
@@ -824,19 +835,14 @@ static void erofs_kill_sb(struct super_block *sb)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
- if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev)
+ if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) ||
+ sbi->dif0.file)
kill_anon_super(sb);
else
kill_block_super(sb);
-
- erofs_free_dev_context(sbi->devs);
- fs_put_dax(sbi->dax_dev, NULL);
+ fs_put_dax(sbi->dif0.dax_dev, NULL);
erofs_fscache_unregister_fs(sb);
- kfree(sbi->fsid);
- kfree(sbi->domain_id);
- if (sbi->fdev)
- fput(sbi->fdev);
- kfree(sbi);
+ erofs_sb_free(sbi);
sb->s_fs_info = NULL;
}
@@ -962,6 +968,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",dax=always");
if (test_opt(opt, DAX_NEVER))
seq_puts(seq, ",dax=never");
+ if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
+ seq_puts(seq, ",directio");
#ifdef CONFIG_EROFS_FS_ONDEMAND
if (sbi->fsid)
seq_printf(seq, ",fsid=%s", sbi->fsid);
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index a569ff9dfd04..1a00f061798a 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1679,9 +1679,9 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
erofs_fscache_submit_bio(bio);
else
submit_bio(bio);
- if (memstall)
- psi_memstall_leave(&pflags);
}
+ if (memstall)
+ psi_memstall_leave(&pflags);
/*
* although background is preferred, no one is pending for submission.
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 90fbab6b6f03..1a06e462b6ef 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1373,7 +1373,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
break;
}
}
- wake_up(&ep->wq);
+ if (sync)
+ wake_up_sync(&ep->wq);
+ else
+ wake_up(&ep->wq);
}
if (waitqueue_active(&ep->poll_wait))
pwake++;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5cf327337e22..c0856585bb63 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -893,7 +893,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
error = PTR_ERR(folio);
goto out;
}
- folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size));
+ folio_zero_user(folio, addr);
__folio_mark_uptodate(folio);
error = hugetlb_add_to_page_cache(folio, mapping, index);
if (unlikely(error)) {
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0d16b383a452..5f582713bf05 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
enum pnfs_iomode *iomode)
{
/* Serialise LAYOUTGET/LAYOUTRETURN */
- if (atomic_read(&lo->plh_outstanding) != 0)
+ if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0)
return false;
if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
return false;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 501ad7be5174..54a3fa0cf67e 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode)
ii->i_flags = 0;
memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap));
mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS);
+ btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
}
void nilfs_btnode_cache_clear(struct address_space *btnc)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index ace22253fed0..2dbb15767df1 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode)
inode->i_mode = S_IFREG;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
- inode->i_mapping->a_ops = &empty_aops;
+ inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
ii->i_flags = 0;
nilfs_bmap_init_gc(ii->i_bmap);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index be6acf6e2bfc..aaca34ec678f 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -307,6 +307,10 @@ const struct address_space_operations nilfs_aops = {
.is_partially_uptodate = block_is_partially_uptodate,
};
+const struct address_space_operations nilfs_buffer_cache_aops = {
+ .invalidate_folio = block_invalidate_folio,
+};
+
static int nilfs_insert_inode_locked(struct inode *inode,
struct nilfs_root *root,
unsigned long ino)
@@ -575,8 +579,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
inode = nilfs_iget_locked(sb, root, ino);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
+
+ if (!(inode->i_state & I_NEW)) {
+ if (!inode->i_nlink) {
+ iput(inode);
+ return ERR_PTR(-ESTALE);
+ }
return inode;
+ }
err = __nilfs_read_inode(sb, root, ino, inode);
if (unlikely(err)) {
@@ -706,6 +716,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode)
NILFS_I(s_inode)->i_flags = 0;
memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap));
mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS);
+ s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops;
err = nilfs_attach_btree_node_cache(s_inode);
if (unlikely(err)) {
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9b108052d9f7..1d836a5540f3 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
inode = NULL;
} else {
inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino);
+ if (inode == ERR_PTR(-ESTALE)) {
+ nilfs_error(dir->i_sb,
+ "deleted inode referenced: %lu", ino);
+ return ERR_PTR(-EIO);
+ }
}
return d_splice_alias(inode, dentry);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 45d03826eaf1..dff241c53fc5 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations;
extern const struct inode_operations nilfs_file_inode_operations;
extern const struct file_operations nilfs_file_operations;
extern const struct address_space_operations nilfs_aops;
+extern const struct address_space_operations nilfs_buffer_cache_aops;
extern const struct inode_operations nilfs_dir_inode_operations;
extern const struct inode_operations nilfs_special_inode_operations;
extern const struct inode_operations nilfs_symlink_inode_operations;
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 5df34561c551..d1aa04a5af1b 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
start = count = 0;
left = le32_to_cpu(alloc->id1.bitmap1.i_total);
- while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) <
- left) {
- if (bit_off == start) {
+ while (1) {
+ bit_off = ocfs2_find_next_zero_bit(bitmap, left, start);
+ if ((bit_off < left) && (bit_off == start)) {
count++;
start++;
continue;
@@ -998,6 +998,8 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb,
}
}
+ if (bit_off >= left)
+ break;
count = 1;
start = bit_off + 1;
}
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index feff3324d39c..fe40152b915d 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -987,9 +987,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
msleep(125);
if (cifs_rdma_enabled(server))
smbd_destroy(server);
+
if (server->ssocket) {
sock_release(server->ssocket);
server->ssocket = NULL;
+
+ /* Release netns reference for the socket. */
+ put_net(cifs_net_ns(server));
}
if (!list_empty(&server->pending_mid_q)) {
@@ -1037,6 +1041,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server)
*/
}
+ /* Release netns reference for this server. */
put_net(cifs_net_ns(server));
kfree(server->leaf_fullpath);
kfree(server);
@@ -1713,6 +1718,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
tcp_ses->ops = ctx->ops;
tcp_ses->vals = ctx->vals;
+
+ /* Grab netns reference for this server. */
cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId);
@@ -1844,6 +1851,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
out_err_crypto_release:
cifs_crypto_secmech_release(tcp_ses);
+ /* Release netns reference for this server. */
put_net(cifs_net_ns(tcp_ses));
out_err:
@@ -1852,8 +1860,10 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
cifs_put_tcp_session(tcp_ses->primary_server, false);
kfree(tcp_ses->hostname);
kfree(tcp_ses->leaf_fullpath);
- if (tcp_ses->ssocket)
+ if (tcp_ses->ssocket) {
sock_release(tcp_ses->ssocket);
+ put_net(cifs_net_ns(tcp_ses));
+ }
kfree(tcp_ses);
}
return ERR_PTR(rc);
@@ -3111,20 +3121,20 @@ generic_ip_connect(struct TCP_Server_Info *server)
socket = server->ssocket;
} else {
struct net *net = cifs_net_ns(server);
- struct sock *sk;
- rc = __sock_create(net, sfamily, SOCK_STREAM,
- IPPROTO_TCP, &server->ssocket, 1);
+ rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket);
if (rc < 0) {
cifs_server_dbg(VFS, "Error %d creating socket\n", rc);
return rc;
}
- sk = server->ssocket->sk;
- __netns_tracker_free(net, &sk->ns_tracker, false);
- sk->sk_net_refcnt = 1;
- get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
- sock_inuse_add(net, 1);
+ /*
+ * Grab netns reference for the socket.
+ *
+ * It'll be released here, on error, or in clean_demultiplex_info() upon server
+ * teardown.
+ */
+ get_net(net);
/* BB other socket options to set KEEPALIVE, NODELAY? */
cifs_dbg(FYI, "Socket created\n");
@@ -3138,8 +3148,10 @@ generic_ip_connect(struct TCP_Server_Info *server)
}
rc = bind_socket(server);
- if (rc < 0)
+ if (rc < 0) {
+ put_net(cifs_net_ns(server));
return rc;
+ }
/*
* Eventually check for other socket options to change from
@@ -3176,6 +3188,7 @@ generic_ip_connect(struct TCP_Server_Info *server)
if (rc < 0) {
cifs_dbg(FYI, "Error %d connecting to server\n", rc);
trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc);
+ put_net(cifs_net_ns(server));
sock_release(socket);
server->ssocket = NULL;
return rc;
@@ -3184,6 +3197,9 @@ generic_ip_connect(struct TCP_Server_Info *server)
if (sport == htons(RFC1001_PORT))
rc = ip_rfc1001_connect(server);
+ if (rc < 0)
+ put_net(cifs_net_ns(server));
+
return rc;
}
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index e6a72f75ab94..bf45822db5d5 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void)
atomic_set(&conn->req_running, 0);
atomic_set(&conn->r_count, 0);
atomic_set(&conn->refcnt, 1);
- atomic_set(&conn->mux_smb_requests, 0);
conn->total_credits = 1;
conn->outstanding_credits = 0;
@@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work)
if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE)
requests_queue = &conn->requests;
+ atomic_inc(&conn->req_running);
if (requests_queue) {
- atomic_inc(&conn->req_running);
spin_lock(&conn->request_lock);
list_add_tail(&work->request_entry, requests_queue);
spin_unlock(&conn->request_lock);
@@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work)
{
struct ksmbd_conn *conn = work->conn;
+ atomic_dec(&conn->req_running);
+ if (waitqueue_active(&conn->req_running_q))
+ wake_up(&conn->req_running_q);
+
if (list_empty(&work->request_entry) &&
list_empty(&work->async_request_entry))
return;
- atomic_dec(&conn->req_running);
spin_lock(&conn->request_lock);
list_del_init(&work->request_entry);
spin_unlock(&conn->request_lock);
@@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p)
{
struct ksmbd_conn *conn = (struct ksmbd_conn *)p;
struct ksmbd_transport *t = conn->transport;
- unsigned int pdu_size, max_allowed_pdu_size;
+ unsigned int pdu_size, max_allowed_pdu_size, max_req;
char hdr_buf[4] = {0,};
int size;
@@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p)
if (t->ops->prepare && t->ops->prepare(t))
goto out;
+ max_req = server_conf.max_inflight_req;
conn->last_active = jiffies;
set_freezable();
while (ksmbd_conn_alive(conn)) {
@@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p)
kvfree(conn->request_buf);
conn->request_buf = NULL;
+recheck:
+ if (atomic_read(&conn->req_running) + 1 > max_req) {
+ wait_event_interruptible(conn->req_running_q,
+ atomic_read(&conn->req_running) < max_req);
+ goto recheck;
+ }
+
size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1);
if (size != sizeof(hdr_buf))
break;
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 8ddd5a3c7baf..b379ae4fdcdf 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -107,7 +107,6 @@ struct ksmbd_conn {
__le16 signing_algorithm;
bool binding;
atomic_t refcnt;
- atomic_t mux_smb_requests;
};
struct ksmbd_conn_ops {
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index 698af37e988d..d146b0e7c3a9 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk)
ksmbd_conn_try_dequeue_request(work);
ksmbd_free_work_struct(work);
- atomic_dec(&conn->mux_smb_requests);
/*
* Checking waitqueue to dropping pending requests on
* disconnection. waitqueue_active is safe because it
@@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn)
if (err)
return 0;
- if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) {
- atomic_dec_return(&conn->mux_smb_requests);
- return -ENOSPC;
- }
-
work = ksmbd_alloc_work_struct();
if (!work) {
pr_err("allocation for work failed\n");
@@ -367,6 +361,7 @@ static int server_conf_init(void)
server_conf.auth_mechs |= KSMBD_AUTH_KRB5 |
KSMBD_AUTH_MSKRB5;
#endif
+ server_conf.max_inflight_req = SMB2_MAX_CREDITS;
return 0;
}
diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h
index 4fc529335271..94187628ff08 100644
--- a/fs/smb/server/server.h
+++ b/fs/smb/server/server.h
@@ -42,6 +42,7 @@ struct ksmbd_server_config {
struct smb_sid domain_sid;
unsigned int auth_mechs;
unsigned int max_connections;
+ unsigned int max_inflight_req;
char *conf[SERVER_CONF_WORK_GROUP + 1];
struct task_struct *dh_task;
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 2f27afb695f6..6de351cc2b60 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
init_smb2_max_write_size(req->smb2_max_write);
if (req->smb2_max_trans)
init_smb2_max_trans_size(req->smb2_max_trans);
- if (req->smb2_max_credits)
+ if (req->smb2_max_credits) {
init_smb2_max_credits(req->smb2_max_credits);
+ server_conf.max_inflight_req =
+ req->smb2_max_credits;
+ }
if (req->smbd_max_io_size)
init_smbd_max_io_size(req->smbd_max_io_size);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 271855227514..6258527315f2 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -855,7 +855,8 @@ xfs_ialloc_ag_alloc(
* the end of the AG.
*/
args.min_agbno = args.mp->m_sb.sb_inoalignmt;
- args.max_agbno = round_down(args.mp->m_sb.sb_agblocks,
+ args.max_agbno = round_down(xfs_ag_block_count(args.mp,
+ pag->pag_agno),
args.mp->m_sb.sb_inoalignmt) -
igeo->ialloc_blks;
@@ -2332,9 +2333,9 @@ xfs_difree(
return -EINVAL;
}
agbno = XFS_AGINO_TO_AGBNO(mp, agino);
- if (agbno >= mp->m_sb.sb_agblocks) {
- xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
- __func__, agbno, mp->m_sb.sb_agblocks);
+ if (agbno >= xfs_ag_block_count(mp, pag->pag_agno)) {
+ xfs_warn(mp, "%s: agbno >= xfs_ag_block_count (%d >= %d).",
+ __func__, agbno, xfs_ag_block_count(mp, pag->pag_agno));
ASSERT(0);
return -EINVAL;
}
@@ -2457,7 +2458,7 @@ xfs_imap(
*/
agino = XFS_INO_TO_AGINO(mp, ino);
agbno = XFS_AGINO_TO_AGBNO(mp, agino);
- if (agbno >= mp->m_sb.sb_agblocks ||
+ if (agbno >= xfs_ag_block_count(mp, pag->pag_agno) ||
ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
error = -EINVAL;
#ifdef DEBUG
@@ -2467,11 +2468,12 @@ xfs_imap(
*/
if (flags & XFS_IGET_UNTRUSTED)
return error;
- if (agbno >= mp->m_sb.sb_agblocks) {
+ if (agbno >= xfs_ag_block_count(mp, pag->pag_agno)) {
xfs_alert(mp,
"%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)",
__func__, (unsigned long long)agbno,
- (unsigned long)mp->m_sb.sb_agblocks);
+ (unsigned long)xfs_ag_block_count(mp,
+ pag->pag_agno));
}
if (ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) {
xfs_alert(mp,
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 02ebcbc4882f..e27b63281d01 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -391,6 +391,21 @@ xfs_validate_sb_common(
sbp->sb_inoalignmt, align);
return -EINVAL;
}
+
+ if (sbp->sb_spino_align &&
+ (sbp->sb_spino_align > sbp->sb_inoalignmt ||
+ (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) {
+ xfs_warn(mp,
+"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).",
+ sbp->sb_spino_align,
+ sbp->sb_inoalignmt);
+ return -EINVAL;
+ }
+ } else if (sbp->sb_spino_align) {
+ xfs_warn(mp,
+ "Sparse inode alignment (%u) should be zero.",
+ sbp->sb_spino_align);
+ return -EINVAL;
}
} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index da30f926cbe6..0f2f1852d58f 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -59,6 +59,30 @@ xchk_superblock_xref(
/* scrub teardown will take care of sc->sa for us */
}
+/*
+ * Calculate the ondisk superblock size in bytes given the feature set of the
+ * mounted filesystem (aka the primary sb). This is subtlely different from
+ * the logic in xfs_repair, which computes the size of a secondary sb given the
+ * featureset listed in the secondary sb.
+ */
+STATIC size_t
+xchk_superblock_ondisk_size(
+ struct xfs_mount *mp)
+{
+ if (xfs_has_metauuid(mp))
+ return offsetofend(struct xfs_dsb, sb_meta_uuid);
+ if (xfs_has_crc(mp))
+ return offsetofend(struct xfs_dsb, sb_lsn);
+ if (xfs_sb_version_hasmorebits(&mp->m_sb))
+ return offsetofend(struct xfs_dsb, sb_bad_features2);
+ if (xfs_has_logv2(mp))
+ return offsetofend(struct xfs_dsb, sb_logsunit);
+ if (xfs_has_sector(mp))
+ return offsetofend(struct xfs_dsb, sb_logsectsize);
+ /* only support dirv2 or more recent */
+ return offsetofend(struct xfs_dsb, sb_dirblklog);
+}
+
/*
* Scrub the filesystem superblock.
*
@@ -75,6 +99,7 @@ xchk_superblock(
struct xfs_buf *bp;
struct xfs_dsb *sb;
struct xfs_perag *pag;
+ size_t sblen;
xfs_agnumber_t agno;
uint32_t v2_ok;
__be32 features_mask;
@@ -350,8 +375,8 @@ xchk_superblock(
}
/* Everything else must be zero. */
- if (memchr_inv(sb + 1, 0,
- BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
+ sblen = xchk_superblock_ondisk_size(mp);
+ if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen))
xchk_block_set_corrupt(sc, bp);
xchk_superblock_xref(sc, bp);
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index ae18ab86e608..8712b891defb 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -162,7 +162,8 @@ struct xfs_getfsmap_info {
xfs_daddr_t next_daddr; /* next daddr we expect */
/* daddr of low fsmap key when we're using the rtbitmap */
xfs_daddr_t low_daddr;
- xfs_daddr_t end_daddr; /* daddr of high fsmap key */
+ /* daddr of high fsmap key, or the last daddr on the device */
+ xfs_daddr_t end_daddr;
u64 missing_owner; /* owner of holes */
u32 dev; /* device id */
/*
@@ -306,7 +307,7 @@ xfs_getfsmap_helper(
* Note that if the btree query found a mapping, there won't be a gap.
*/
if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL)
- rec_daddr = info->end_daddr;
+ rec_daddr = info->end_daddr + 1;
/* Are we just counting mappings? */
if (info->head->fmh_count == 0) {
@@ -898,7 +899,10 @@ xfs_getfsmap(
struct xfs_trans *tp = NULL;
struct xfs_fsmap dkeys[2]; /* per-dev keys */
struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS];
- struct xfs_getfsmap_info info = { NULL };
+ struct xfs_getfsmap_info info = {
+ .fsmap_recs = fsmap_recs,
+ .head = head,
+ };
bool use_rmap;
int i;
int error = 0;
@@ -963,9 +967,6 @@ xfs_getfsmap(
info.next_daddr = head->fmh_keys[0].fmr_physical +
head->fmh_keys[0].fmr_length;
- info.end_daddr = XFS_BUF_DADDR_NULL;
- info.fsmap_recs = fsmap_recs;
- info.head = head;
/* For each device we support... */
for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
@@ -978,17 +979,23 @@ xfs_getfsmap(
break;
/*
- * If this device number matches the high key, we have
- * to pass the high key to the handler to limit the
- * query results. If the device number exceeds the
- * low key, zero out the low key so that we get
- * everything from the beginning.
+ * If this device number matches the high key, we have to pass
+ * the high key to the handler to limit the query results, and
+ * set the end_daddr so that we can synthesize records at the
+ * end of the query range or device.
*/
if (handlers[i].dev == head->fmh_keys[1].fmr_device) {
dkeys[1] = head->fmh_keys[1];
info.end_daddr = min(handlers[i].nr_sectors - 1,
dkeys[1].fmr_physical);
+ } else {
+ info.end_daddr = handlers[i].nr_sectors - 1;
}
+
+ /*
+ * If the device number exceeds the low key, zero out the low
+ * key so that we get everything from the beginning.
+ */
if (handlers[i].dev > head->fmh_keys[0].fmr_device)
memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 6cdc873ac907..aa5233b1eba9 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void);
extern unsigned long hv_get_tsc_pfn(void);
extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+extern void hv_adj_sched_clock_offset(u64 offset);
+
static __always_inline bool
hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
u64 *cur_tsc, u64 *time)
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 941deffc590d..6073a8f13c41 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -48,7 +48,12 @@ static inline void set_codetag_empty(union codetag_ref *ref)
#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
static inline bool is_codetag_empty(union codetag_ref *ref) { return false; }
-static inline void set_codetag_empty(union codetag_ref *ref) {}
+
+static inline void set_codetag_empty(union codetag_ref *ref)
+{
+ if (ref)
+ ref->ct = NULL;
+}
#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index a28e2a6a13d0..74169dd0f659 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev)
return dev_get_drvdata(&fdev->dev);
}
+struct ffa_partition_info;
+
#if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT)
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops);
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops);
void ffa_device_unregister(struct ffa_device *ffa_dev);
int ffa_driver_register(struct ffa_driver *driver, struct module *owner,
const char *mod_name);
@@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver);
bool ffa_device_is_valid(struct ffa_device *ffa_dev);
#else
-static inline
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
- const struct ffa_ops *ops)
+static inline struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+ const struct ffa_ops *ops)
{
return NULL;
}
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 22c22fb91042..02a226bcf0ed 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1559,6 +1559,7 @@ struct hv_util_service {
void *channel;
void (*util_cb)(void *);
int (*util_init)(struct hv_util_service *);
+ int (*util_init_transport)(void);
void (*util_deinit)(void);
int (*util_pre_suspend)(void);
int (*util_pre_resume)(void);
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index e123d5e17b52..85fe4e6b275c 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,10 +15,8 @@ bool io_is_uring_fops(struct file *file);
static inline void io_uring_files_cancel(void)
{
- if (current->io_uring) {
- io_uring_unreg_ringfd();
+ if (current->io_uring)
__io_uring_cancel(false);
- }
}
static inline void io_uring_task_cancel(void)
{
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 74aa9fbbdae7..48c66b846682 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -860,18 +860,10 @@ static inline void ClearPageCompound(struct page *page)
ClearPageHead(page);
}
FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)
-FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-/*
- * PG_partially_mapped is protected by deferred_split split_queue_lock,
- * so its safe to use non-atomic set/clear.
- */
-__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
+FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
#else
FOLIO_FLAG_FALSE(large_rmappable)
-FOLIO_TEST_FLAG_FALSE(partially_mapped)
-__FOLIO_SET_FLAG_NOOP(partially_mapped)
-__FOLIO_CLEAR_FLAG_NOOP(partially_mapped)
+FOLIO_FLAG_FALSE(partially_mapped)
#endif
#define PG_head_mask ((1UL << PG_head))
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bb343136ddd0..c14446c6164d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -656,6 +656,12 @@ struct sched_dl_entity {
* @dl_defer_armed tells if the deferrable server is waiting
* for the replenishment timer to activate it.
*
+ * @dl_server_active tells if the dlserver is active(started).
+ * dlserver is started on first cfs enqueue on an idle runqueue
+ * and is stopped when a dequeue results in 0 cfs tasks on the
+ * runqueue. In other words, dlserver is active only when cpu's
+ * runqueue has atleast one cfs task.
+ *
* @dl_defer_running tells if the deferrable server is actually
* running, skipping the defer phase.
*/
@@ -664,6 +670,7 @@ struct sched_dl_entity {
unsigned int dl_non_contending : 1;
unsigned int dl_overrun : 1;
unsigned int dl_server : 1;
+ unsigned int dl_server_active : 1;
unsigned int dl_defer : 1;
unsigned int dl_defer_armed : 1;
unsigned int dl_defer_running : 1;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 42bedcddd511..4df2ff81d3de 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -285,7 +285,8 @@ struct trace_event_fields {
const char *name;
const int size;
const int align;
- const int is_signed;
+ const unsigned int is_signed:1;
+ unsigned int needs_test:1;
const int filter_type;
const int len;
};
@@ -337,6 +338,7 @@ enum {
TRACE_EVENT_FL_EPROBE_BIT,
TRACE_EVENT_FL_FPROBE_BIT,
TRACE_EVENT_FL_CUSTOM_BIT,
+ TRACE_EVENT_FL_TEST_STR_BIT,
};
/*
@@ -354,6 +356,7 @@ enum {
* CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint)
* This is set when the custom event has not been attached
* to a tracepoint yet, then it is cleared when it is.
+ * TEST_STR - The event has a "%s" that points to a string outside the event
*/
enum {
TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT),
@@ -367,6 +370,7 @@ enum {
TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT),
TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT),
TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT),
+ TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT),
};
#define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 8aa3372f21a0..2b322a9b88a2 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -221,6 +221,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head);
#define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL)
#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1)
#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0)
+#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL)
#define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index b2736e3491b8..9849da128364 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -515,7 +515,11 @@ static void io_queue_iowq(struct io_kiocb *req)
struct io_uring_task *tctx = req->task->io_uring;
BUG_ON(!tctx);
- BUG_ON(!tctx->io_wq);
+
+ if ((current->flags & PF_KTHREAD) || !tctx->io_wq) {
+ io_req_task_queue_fail(req, -ECANCELED);
+ return;
+ }
/* init ->work of the whole link before punting */
io_prep_async_link(req);
@@ -3230,6 +3234,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
void __io_uring_cancel(bool cancel_all)
{
+ io_uring_unreg_ringfd();
io_uring_cancel_generic(cancel_all, NULL);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6cc12777bb11..d07dc87787df 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1300,7 +1300,7 @@ bool sched_can_stop_tick(struct rq *rq)
if (scx_enabled() && !scx_can_stop_tick(rq))
return false;
- if (rq->cfs.nr_running > 1)
+ if (rq->cfs.h_nr_running > 1)
return false;
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fc6f41ac33eb..a17c23b53049 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1647,6 +1647,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
if (!dl_se->dl_runtime)
return;
+ dl_se->dl_server_active = 1;
enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
resched_curr(dl_se->rq);
@@ -1661,6 +1662,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
hrtimer_try_to_cancel(&dl_se->dl_timer);
dl_se->dl_defer_armed = 0;
dl_se->dl_throttled = 0;
+ dl_se->dl_server_active = 0;
}
void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
@@ -2420,8 +2422,10 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
if (dl_server(dl_se)) {
p = dl_se->server_pick_task(dl_se);
if (!p) {
- dl_se->dl_yielded = 1;
- update_curr_dl_se(rq, dl_se, 0);
+ if (dl_server_active(dl_se)) {
+ dl_se->dl_yielded = 1;
+ update_curr_dl_se(rq, dl_se, 0);
+ }
goto again;
}
rq->dl_server = dl_se;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index f4035c7a0fa1..82b165bf48c4 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -844,6 +844,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+ SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed);
SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running",
cfs_rq->idle_nr_running);
SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 782ce70ebd1b..1ca96c99872f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1159,8 +1159,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
trace_sched_stat_runtime(p, delta_exec);
account_group_exec_runtime(p, delta_exec);
cgroup_account_cputime(p, delta_exec);
- if (p->dl_server)
- dl_server_update(p->dl_server, delta_exec);
}
static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
@@ -1237,11 +1235,16 @@ static void update_curr(struct cfs_rq *cfs_rq)
update_curr_task(p, delta_exec);
/*
- * Any fair task that runs outside of fair_server should
- * account against fair_server such that it can account for
- * this time and possibly avoid running this period.
+ * If the fair_server is active, we need to account for the
+ * fair_server time whether or not the task is running on
+ * behalf of fair_server or not:
+ * - If the task is running on behalf of fair_server, we need
+ * to limit its time based on the assigned runtime.
+ * - Fair task that runs outside of fair_server should account
+ * against fair_server such that it can account for this time
+ * and possibly avoid running this period.
*/
- if (p->dl_server != &rq->fair_server)
+ if (dl_server_active(&rq->fair_server))
dl_server_update(&rq->fair_server, delta_exec);
}
@@ -5471,9 +5474,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
-static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+static void set_delayed(struct sched_entity *se)
+{
+ se->sched_delayed = 1;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ cfs_rq->h_nr_delayed++;
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+ }
+}
+
+static void clear_delayed(struct sched_entity *se)
{
se->sched_delayed = 0;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ cfs_rq->h_nr_delayed--;
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+ }
+}
+
+static inline void finish_delayed_dequeue_entity(struct sched_entity *se)
+{
+ clear_delayed(se);
if (sched_feat(DELAY_ZERO) && se->vlag > 0)
se->vlag = 0;
}
@@ -5484,6 +5511,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
bool sleep = flags & DEQUEUE_SLEEP;
update_curr(cfs_rq);
+ clear_buddies(cfs_rq, se);
if (flags & DEQUEUE_DELAYED) {
SCHED_WARN_ON(!se->sched_delayed);
@@ -5500,10 +5528,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (sched_feat(DELAY_DEQUEUE) && delay &&
!entity_eligible(cfs_rq, se)) {
- if (cfs_rq->next == se)
- cfs_rq->next = NULL;
update_load_avg(cfs_rq, se, 0);
- se->sched_delayed = 1;
+ set_delayed(se);
return false;
}
}
@@ -5526,8 +5552,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_stats_dequeue_fair(cfs_rq, se, flags);
- clear_buddies(cfs_rq, se);
-
update_entity_lag(cfs_rq, se);
if (sched_feat(PLACE_REL_DEADLINE) && !sleep) {
se->deadline -= se->vruntime;
@@ -5923,7 +5947,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long task_delta, idle_task_delta, dequeue = 1;
+ long task_delta, idle_task_delta, delayed_delta, dequeue = 1;
long rq_h_nr_running = rq->cfs.h_nr_running;
raw_spin_lock(&cfs_b->lock);
@@ -5956,6 +5980,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
task_delta = cfs_rq->h_nr_running;
idle_task_delta = cfs_rq->idle_h_nr_running;
+ delayed_delta = cfs_rq->h_nr_delayed;
for_each_sched_entity(se) {
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
int flags;
@@ -5979,6 +6004,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
qcfs_rq->h_nr_running -= task_delta;
qcfs_rq->idle_h_nr_running -= idle_task_delta;
+ qcfs_rq->h_nr_delayed -= delayed_delta;
if (qcfs_rq->load.weight) {
/* Avoid re-evaluating load for this entity: */
@@ -6001,6 +6027,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
qcfs_rq->h_nr_running -= task_delta;
qcfs_rq->idle_h_nr_running -= idle_task_delta;
+ qcfs_rq->h_nr_delayed -= delayed_delta;
}
/* At this point se is NULL and we are at root level*/
@@ -6026,7 +6053,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long task_delta, idle_task_delta;
+ long task_delta, idle_task_delta, delayed_delta;
long rq_h_nr_running = rq->cfs.h_nr_running;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -6062,6 +6089,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
task_delta = cfs_rq->h_nr_running;
idle_task_delta = cfs_rq->idle_h_nr_running;
+ delayed_delta = cfs_rq->h_nr_delayed;
for_each_sched_entity(se) {
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
@@ -6079,6 +6107,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
qcfs_rq->h_nr_running += task_delta;
qcfs_rq->idle_h_nr_running += idle_task_delta;
+ qcfs_rq->h_nr_delayed += delayed_delta;
/* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(qcfs_rq))
@@ -6096,6 +6125,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
qcfs_rq->h_nr_running += task_delta;
qcfs_rq->idle_h_nr_running += idle_task_delta;
+ qcfs_rq->h_nr_delayed += delayed_delta;
/* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(qcfs_rq))
@@ -6949,7 +6979,7 @@ requeue_delayed_entity(struct sched_entity *se)
}
update_load_avg(cfs_rq, se, 0);
- se->sched_delayed = 0;
+ clear_delayed(se);
}
/*
@@ -6963,6 +6993,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
int idle_h_nr_running = task_has_idle_policy(p);
+ int h_nr_delayed = 0;
int task_new = !(flags & ENQUEUE_WAKEUP);
int rq_h_nr_running = rq->cfs.h_nr_running;
u64 slice = 0;
@@ -6989,6 +7020,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (p->in_iowait)
cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT);
+ if (task_new)
+ h_nr_delayed = !!se->sched_delayed;
+
for_each_sched_entity(se) {
if (se->on_rq) {
if (se->sched_delayed)
@@ -7011,6 +7045,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
cfs_rq->h_nr_running++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
+ cfs_rq->h_nr_delayed += h_nr_delayed;
if (cfs_rq_is_idle(cfs_rq))
idle_h_nr_running = 1;
@@ -7034,6 +7069,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
cfs_rq->h_nr_running++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
+ cfs_rq->h_nr_delayed += h_nr_delayed;
if (cfs_rq_is_idle(cfs_rq))
idle_h_nr_running = 1;
@@ -7096,6 +7132,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
struct task_struct *p = NULL;
int idle_h_nr_running = 0;
int h_nr_running = 0;
+ int h_nr_delayed = 0;
struct cfs_rq *cfs_rq;
u64 slice = 0;
@@ -7103,6 +7140,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
p = task_of(se);
h_nr_running = 1;
idle_h_nr_running = task_has_idle_policy(p);
+ if (!task_sleep && !task_delayed)
+ h_nr_delayed = !!se->sched_delayed;
} else {
cfs_rq = group_cfs_rq(se);
slice = cfs_rq_min_slice(cfs_rq);
@@ -7120,6 +7159,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
cfs_rq->h_nr_running -= h_nr_running;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+ cfs_rq->h_nr_delayed -= h_nr_delayed;
if (cfs_rq_is_idle(cfs_rq))
idle_h_nr_running = h_nr_running;
@@ -7158,6 +7198,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
cfs_rq->h_nr_running -= h_nr_running;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+ cfs_rq->h_nr_delayed -= h_nr_delayed;
if (cfs_rq_is_idle(cfs_rq))
idle_h_nr_running = h_nr_running;
@@ -8786,7 +8827,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
return;
- if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
+ if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) {
set_next_buddy(pse);
}
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a9c65d97b3ca..171a802420a1 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
{
if (___update_load_sum(now, &cfs_rq->avg,
scale_load_down(cfs_rq->load.weight),
- cfs_rq->h_nr_running,
+ cfs_rq->h_nr_running - cfs_rq->h_nr_delayed,
cfs_rq->curr != NULL)) {
___update_load_avg(&cfs_rq->avg, 1);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c03b3d7b320e..f2ef520513c4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -398,6 +398,11 @@ extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq
extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
u64 runtime, u64 period, bool init);
+static inline bool dl_server_active(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_server_active;
+}
+
#ifdef CONFIG_CGROUP_SCHED
extern struct list_head task_groups;
@@ -649,6 +654,7 @@ struct cfs_rq {
unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */
unsigned int idle_nr_running; /* SCHED_IDLE */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
+ unsigned int h_nr_delayed;
s64 avg_vruntime;
u64 avg_load;
@@ -898,8 +904,11 @@ struct dl_rq {
static inline void se_update_runnable(struct sched_entity *se)
{
- if (!entity_is_task(se))
- se->runnable_weight = se->my_q->h_nr_running;
+ if (!entity_is_task(se)) {
+ struct cfs_rq *cfs_rq = se->my_q;
+
+ se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed;
+ }
}
static inline long se_runnable(struct sched_entity *se)
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 69e226a48daa..72bcbfad53db 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1160,7 +1160,7 @@ void fgraph_update_pid_func(void)
static int start_graph_tracing(void)
{
unsigned long **ret_stack_list;
- int ret;
+ int ret, cpu;
ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
sizeof(*ret_stack_list), GFP_KERNEL);
@@ -1168,6 +1168,12 @@ static int start_graph_tracing(void)
if (!ret_stack_list)
return -ENOMEM;
+ /* The cpu_boot init_task->ret_stack will never be freed */
+ for_each_online_cpu(cpu) {
+ if (!idle_task(cpu)->ret_stack)
+ ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+ }
+
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 366eb4c4f28e..703978b2d557 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer,
lockdep_assert_held(&cpu_buffer->mapping_lock);
nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */
- nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */
+ nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */
+ if (nr_pages <= pgoff)
+ return -EINVAL;
+
+ nr_pages -= pgoff;
nr_vma_pages = vma_pages(vma);
if (!nr_vma_pages || nr_vma_pages > nr_pages)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 17d2ffde0bb6..35515192aa0f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3635,17 +3635,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter)
}
/* Returns true if the string is safe to dereference from an event */
-static bool trace_safe_str(struct trace_iterator *iter, const char *str,
- bool star, int len)
+static bool trace_safe_str(struct trace_iterator *iter, const char *str)
{
unsigned long addr = (unsigned long)str;
struct trace_event *trace_event;
struct trace_event_call *event;
- /* Ignore strings with no length */
- if (star && !len)
- return true;
-
/* OK if part of the event data */
if ((addr >= (unsigned long)iter->ent) &&
(addr < (unsigned long)iter->ent + iter->ent_size))
@@ -3685,181 +3680,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
return false;
}
-static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
-
-static int test_can_verify_check(const char *fmt, ...)
-{
- char buf[16];
- va_list ap;
- int ret;
-
- /*
- * The verifier is dependent on vsnprintf() modifies the va_list
- * passed to it, where it is sent as a reference. Some architectures
- * (like x86_32) passes it by value, which means that vsnprintf()
- * does not modify the va_list passed to it, and the verifier
- * would then need to be able to understand all the values that
- * vsnprintf can use. If it is passed by value, then the verifier
- * is disabled.
- */
- va_start(ap, fmt);
- vsnprintf(buf, 16, "%d", ap);
- ret = va_arg(ap, int);
- va_end(ap);
-
- return ret;
-}
-
-static void test_can_verify(void)
-{
- if (!test_can_verify_check("%d %d", 0, 1)) {
- pr_info("trace event string verifier disabled\n");
- static_branch_inc(&trace_no_verify);
- }
-}
-
/**
- * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
+ * ignore_event - Check dereferenced fields while writing to the seq buffer
* @iter: The iterator that holds the seq buffer and the event being printed
- * @fmt: The format used to print the event
- * @ap: The va_list holding the data to print from @fmt.
*
- * This writes the data into the @iter->seq buffer using the data from
- * @fmt and @ap. If the format has a %s, then the source of the string
- * is examined to make sure it is safe to print, otherwise it will
- * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
- * pointer.
+ * At boot up, test_event_printk() will flag any event that dereferences
+ * a string with "%s" that does exist in the ring buffer. It may still
+ * be valid, as the string may point to a static string in the kernel
+ * rodata that never gets freed. But if the string pointer is pointing
+ * to something that was allocated, there's a chance that it can be freed
+ * by the time the user reads the trace. This would cause a bad memory
+ * access by the kernel and possibly crash the system.
+ *
+ * This function will check if the event has any fields flagged as needing
+ * to be checked at runtime and perform those checks.
+ *
+ * If it is found that a field is unsafe, it will write into the @iter->seq
+ * a message stating what was found to be unsafe.
+ *
+ * @return: true if the event is unsafe and should be ignored,
+ * false otherwise.
*/
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
- va_list ap)
+bool ignore_event(struct trace_iterator *iter)
{
- long text_delta = 0;
- long data_delta = 0;
- const char *p = fmt;
- const char *str;
- bool good;
- int i, j;
+ struct ftrace_event_field *field;
+ struct trace_event *trace_event;
+ struct trace_event_call *event;
+ struct list_head *head;
+ struct trace_seq *seq;
+ const void *ptr;
- if (WARN_ON_ONCE(!fmt))
- return;
+ trace_event = ftrace_find_event(iter->ent->type);
- if (static_branch_unlikely(&trace_no_verify))
- goto print;
+ seq = &iter->seq;
- /*
- * When the kernel is booted with the tp_printk command line
- * parameter, trace events go directly through to printk().
- * It also is checked by this function, but it does not
- * have an associated trace_array (tr) for it.
- */
- if (iter->tr) {
- text_delta = iter->tr->text_delta;
- data_delta = iter->tr->data_delta;
+ if (!trace_event) {
+ trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type);
+ return true;
}
- /* Don't bother checking when doing a ftrace_dump() */
- if (iter->fmt == static_fmt_buf)
- goto print;
-
- while (*p) {
- bool star = false;
- int len = 0;
-
- j = 0;
-
- /*
- * We only care about %s and variants
- * as well as %p[sS] if delta is non-zero
- */
- for (i = 0; p[i]; i++) {
- if (i + 1 >= iter->fmt_size) {
- /*
- * If we can't expand the copy buffer,
- * just print it.
- */
- if (!trace_iter_expand_format(iter))
- goto print;
- }
-
- if (p[i] == '\\' && p[i+1]) {
- i++;
- continue;
- }
- if (p[i] == '%') {
- /* Need to test cases like %08.*s */
- for (j = 1; p[i+j]; j++) {
- if (isdigit(p[i+j]) ||
- p[i+j] == '.')
- continue;
- if (p[i+j] == '*') {
- star = true;
- continue;
- }
- break;
- }
- if (p[i+j] == 's')
- break;
-
- if (text_delta && p[i+1] == 'p' &&
- ((p[i+2] == 's' || p[i+2] == 'S')))
- break;
-
- star = false;
- }
- j = 0;
- }
- /* If no %s found then just print normally */
- if (!p[i])
- break;
-
- /* Copy up to the %s, and print that */
- strncpy(iter->fmt, p, i);
- iter->fmt[i] = '\0';
- trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+ event = container_of(trace_event, struct trace_event_call, event);
+ if (!(event->flags & TRACE_EVENT_FL_TEST_STR))
+ return false;
- /* Add delta to %pS pointers */
- if (p[i+1] == 'p') {
- unsigned long addr;
- char fmt[4];
+ head = trace_get_fields(event);
+ if (!head) {
+ trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n",
+ trace_event_name(event));
+ return true;
+ }
- fmt[0] = '%';
- fmt[1] = 'p';
- fmt[2] = p[i+2]; /* Either %ps or %pS */
- fmt[3] = '\0';
+ /* Offsets are from the iter->ent that points to the raw event */
+ ptr = iter->ent;
- addr = va_arg(ap, unsigned long);
- addr += text_delta;
- trace_seq_printf(&iter->seq, fmt, (void *)addr);
+ list_for_each_entry(field, head, link) {
+ const char *str;
+ bool good;
- p += i + 3;
+ if (!field->needs_test)
continue;
- }
- /*
- * If iter->seq is full, the above call no longer guarantees
- * that ap is in sync with fmt processing, and further calls
- * to va_arg() can return wrong positional arguments.
- *
- * Ensure that ap is no longer used in this case.
- */
- if (iter->seq.full) {
- p = "";
- break;
- }
+ str = *(const char **)(ptr + field->offset);
- if (star)
- len = va_arg(ap, int);
-
- /* The ap now points to the string data of the %s */
- str = va_arg(ap, const char *);
-
- good = trace_safe_str(iter, str, star, len);
-
- /* Could be from the last boot */
- if (data_delta && !good) {
- str += data_delta;
- good = trace_safe_str(iter, str, star, len);
- }
+ good = trace_safe_str(iter, str);
/*
* If you hit this warning, it is likely that the
@@ -3870,44 +3753,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
* instead. See samples/trace_events/trace-events-sample.h
* for reference.
*/
- if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'",
- fmt, seq_buf_str(&iter->seq.seq))) {
- int ret;
-
- /* Try to safely read the string */
- if (star) {
- if (len + 1 > iter->fmt_size)
- len = iter->fmt_size - 1;
- if (len < 0)
- len = 0;
- ret = copy_from_kernel_nofault(iter->fmt, str, len);
- iter->fmt[len] = 0;
- star = false;
- } else {
- ret = strncpy_from_kernel_nofault(iter->fmt, str,
- iter->fmt_size);
- }
- if (ret < 0)
- trace_seq_printf(&iter->seq, "(0x%px)", str);
- else
- trace_seq_printf(&iter->seq, "(0x%px:%s)",
- str, iter->fmt);
- str = "[UNSAFE-MEMORY]";
- strcpy(iter->fmt, "%s");
- } else {
- strncpy(iter->fmt, p + i, j + 1);
- iter->fmt[j+1] = '\0';
+ if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'",
+ trace_event_name(event), field->name)) {
+ trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n",
+ trace_event_name(event), field->name);
+ return true;
}
- if (star)
- trace_seq_printf(&iter->seq, iter->fmt, len, str);
- else
- trace_seq_printf(&iter->seq, iter->fmt, str);
-
- p += i + j + 1;
}
- print:
- if (*p)
- trace_seq_vprintf(&iter->seq, p, ap);
+ return false;
}
const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
@@ -4377,6 +4230,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
if (event) {
if (tr->trace_flags & TRACE_ITER_FIELDS)
return print_event_fields(iter, event);
+ /*
+ * For TRACE_EVENT() events, the print_fmt is not
+ * safe to use if the array has delta offsets
+ * Force printing via the fields.
+ */
+ if ((tr->text_delta || tr->data_delta) &&
+ event->type > __TRACE_LAST_TYPE)
+ return print_event_fields(iter, event);
+
return event->funcs->trace(iter, sym_flags, event);
}
@@ -10794,8 +10656,6 @@ __init static int tracer_alloc_buffers(void)
register_snapshot_cmd();
- test_can_verify();
-
return 0;
out_free_pipe_cpumask:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 30d6675c78cf..04ea327198ba 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -664,9 +664,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
bool trace_is_tracepoint_string(const char *str);
const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
- va_list ap) __printf(2, 0);
char *trace_iter_expand_format(struct trace_iterator *iter);
+bool ignore_event(struct trace_iterator *iter);
int trace_empty(struct trace_iterator *iter);
@@ -1402,7 +1401,8 @@ struct ftrace_event_field {
int filter_type;
int offset;
int size;
- int is_signed;
+ unsigned int is_signed:1;
+ unsigned int needs_test:1;
int len;
};
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7266ec2a4eea..7149cd6fd479 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system)
}
static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
+__find_event_field(struct list_head *head, const char *name)
{
struct ftrace_event_field *field;
@@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name)
static int __trace_define_field(struct list_head *head, const char *type,
const char *name, int offset, int size,
- int is_signed, int filter_type, int len)
+ int is_signed, int filter_type, int len,
+ int need_test)
{
struct ftrace_event_field *field;
@@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
field->offset = offset;
field->size = size;
field->is_signed = is_signed;
+ field->needs_test = need_test;
field->len = len;
list_add(&field->link, head);
@@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type,
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type, 0);
+ is_signed, filter_type, 0, 0);
}
EXPORT_SYMBOL_GPL(trace_define_field);
static int trace_define_field_ext(struct trace_event_call *call, const char *type,
const char *name, int offset, int size, int is_signed,
- int filter_type, int len)
+ int filter_type, int len, int need_test)
{
struct list_head *head;
@@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type, len);
+ is_signed, filter_type, len, need_test);
}
#define __generic_field(type, item, filter_type) \
ret = __trace_define_field(&ftrace_generic_fields, #type, \
#item, 0, 0, is_signed_type(type), \
- filter_type, 0); \
+ filter_type, 0, 0); \
if (ret) \
return ret;
@@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
"common_" #item, \
offsetof(typeof(ent), item), \
sizeof(ent.item), \
- is_signed_type(type), FILTER_OTHER, 0); \
+ is_signed_type(type), FILTER_OTHER, \
+ 0, 0); \
if (ret) \
return ret;
@@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call)
return tail->offset + tail->size;
}
-/*
- * Check if the referenced field is an array and return true,
- * as arrays are OK to dereference.
- */
-static bool test_field(const char *fmt, struct trace_event_call *call)
+
+static struct trace_event_fields *find_event_field(const char *fmt,
+ struct trace_event_call *call)
{
struct trace_event_fields *field = call->class->fields_array;
- const char *array_descriptor;
const char *p = fmt;
int len;
if (!(len = str_has_prefix(fmt, "REC->")))
- return false;
+ return NULL;
fmt += len;
for (p = fmt; *p; p++) {
if (!isalnum(*p) && *p != '_')
@@ -265,16 +265,129 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
len = p - fmt;
for (; field->type; field++) {
- if (strncmp(field->name, fmt, len) ||
- field->name[len])
+ if (strncmp(field->name, fmt, len) || field->name[len])
continue;
- array_descriptor = strchr(field->type, '[');
- /* This is an array and is OK to dereference. */
- return array_descriptor != NULL;
+
+ return field;
+ }
+ return NULL;
+}
+
+/*
+ * Check if the referenced field is an array and return true,
+ * as arrays are OK to dereference.
+ */
+static bool test_field(const char *fmt, struct trace_event_call *call)
+{
+ struct trace_event_fields *field;
+
+ field = find_event_field(fmt, call);
+ if (!field)
+ return false;
+
+ /* This is an array and is OK to dereference. */
+ return strchr(field->type, '[') != NULL;
+}
+
+/* Look for a string within an argument */
+static bool find_print_string(const char *arg, const char *str, const char *end)
+{
+ const char *r;
+
+ r = strstr(arg, str);
+ return r && r < end;
+}
+
+/* Return true if the argument pointer is safe */
+static bool process_pointer(const char *fmt, int len, struct trace_event_call *call)
+{
+ const char *r, *e, *a;
+
+ e = fmt + len;
+
+ /* Find the REC-> in the argument */
+ r = strstr(fmt, "REC->");
+ if (r && r < e) {
+ /*
+ * Addresses of events on the buffer, or an array on the buffer is
+ * OK to dereference. There's ways to fool this, but
+ * this is to catch common mistakes, not malicious code.
+ */
+ a = strchr(fmt, '&');
+ if ((a && (a < r)) || test_field(r, call))
+ return true;
+ } else if (find_print_string(fmt, "__get_dynamic_array(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_sockaddr(", e)) {
+ return true;
+ } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) {
+ return true;
}
return false;
}
+/* Return true if the string is safe */
+static bool process_string(const char *fmt, int len, struct trace_event_call *call)
+{
+ struct trace_event_fields *field;
+ const char *r, *e, *s;
+
+ e = fmt + len;
+
+ /*
+ * There are several helper functions that return strings.
+ * If the argument contains a function, then assume its field is valid.
+ * It is considered that the argument has a function if it has:
+ * alphanumeric or '_' before a parenthesis.
+ */
+ s = fmt;
+ do {
+ r = strstr(s, "(");
+ if (!r || r >= e)
+ break;
+ for (int i = 1; r - i >= s; i++) {
+ char ch = *(r - i);
+ if (isspace(ch))
+ continue;
+ if (isalnum(ch) || ch == '_')
+ return true;
+ /* Anything else, this isn't a function */
+ break;
+ }
+ /* A function could be wrapped in parethesis, try the next one */
+ s = r + 1;
+ } while (s < e);
+
+ /*
+ * If there's any strings in the argument consider this arg OK as it
+ * could be: REC->field ? "foo" : "bar" and we don't want to get into
+ * verifying that logic here.
+ */
+ if (find_print_string(fmt, "\"", e))
+ return true;
+
+ /* Dereferenced strings are also valid like any other pointer */
+ if (process_pointer(fmt, len, call))
+ return true;
+
+ /* Make sure the field is found */
+ field = find_event_field(fmt, call);
+ if (!field)
+ return false;
+
+ /* Test this field's string before printing the event */
+ call->flags |= TRACE_EVENT_FL_TEST_STR;
+ field->needs_test = 1;
+
+ return true;
+}
+
/*
* Examine the print fmt of the event looking for unsafe dereference
* pointers using %p* that could be recorded in the trace event and
@@ -284,13 +397,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call)
static void test_event_printk(struct trace_event_call *call)
{
u64 dereference_flags = 0;
+ u64 string_flags = 0;
bool first = true;
- const char *fmt, *c, *r, *a;
+ const char *fmt;
int parens = 0;
char in_quote = 0;
int start_arg = 0;
int arg = 0;
- int i;
+ int i, e;
fmt = call->print_fmt;
@@ -374,8 +488,16 @@ static void test_event_printk(struct trace_event_call *call)
star = true;
continue;
}
- if ((fmt[i + j] == 's') && star)
- arg++;
+ if ((fmt[i + j] == 's')) {
+ if (star)
+ arg++;
+ if (WARN_ONCE(arg == 63,
+ "Too many args for event: %s",
+ trace_event_name(call)))
+ return;
+ dereference_flags |= 1ULL << arg;
+ string_flags |= 1ULL << arg;
+ }
break;
}
break;
@@ -403,42 +525,47 @@ static void test_event_printk(struct trace_event_call *call)
case ',':
if (in_quote || parens)
continue;
+ e = i;
i++;
while (isspace(fmt[i]))
i++;
- start_arg = i;
- if (!(dereference_flags & (1ULL << arg)))
- goto next_arg;
- /* Find the REC-> in the argument */
- c = strchr(fmt + i, ',');
- r = strstr(fmt + i, "REC->");
- if (r && (!c || r < c)) {
- /*
- * Addresses of events on the buffer,
- * or an array on the buffer is
- * OK to dereference.
- * There's ways to fool this, but
- * this is to catch common mistakes,
- * not malicious code.
- */
- a = strchr(fmt + i, '&');
- if ((a && (a < r)) || test_field(r, call))
+ /*
+ * If start_arg is zero, then this is the start of the
+ * first argument. The processing of the argument happens
+ * when the end of the argument is found, as it needs to
+ * handle paranthesis and such.
+ */
+ if (!start_arg) {
+ start_arg = i;
+ /* Balance out the i++ in the for loop */
+ i--;
+ continue;
+ }
+
+ if (dereference_flags & (1ULL << arg)) {
+ if (string_flags & (1ULL << arg)) {
+ if (process_string(fmt + start_arg, e - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ } else if (process_pointer(fmt + start_arg, e - start_arg, call))
dereference_flags &= ~(1ULL << arg);
- } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) &&
- (!c || r < c)) {
- dereference_flags &= ~(1ULL << arg);
- } else if ((r = strstr(fmt + i, "__get_sockaddr(")) &&
- (!c || r < c)) {
- dereference_flags &= ~(1ULL << arg);
}
- next_arg:
- i--;
+ start_arg = i;
arg++;
+ /* Balance out the i++ in the for loop */
+ i--;
}
}
+ if (dereference_flags & (1ULL << arg)) {
+ if (string_flags & (1ULL << arg)) {
+ if (process_string(fmt + start_arg, i - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ } else if (process_pointer(fmt + start_arg, i - start_arg, call))
+ dereference_flags &= ~(1ULL << arg);
+ }
+
/*
* If you triggered the below warning, the trace event reported
* uses an unsafe dereference pointer %p*. As the data stored
@@ -2471,7 +2598,7 @@ event_define_fields(struct trace_event_call *call)
ret = trace_define_field_ext(call, field->type, field->name,
offset, field->size,
field->is_signed, field->filter_type,
- field->len);
+ field->len, field->needs_test);
if (WARN_ON_ONCE(ret)) {
pr_err("error code is %d\n", ret);
break;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index c14573e5a903..6e7090e8bf30 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep);
void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...)
{
+ struct trace_seq *s = &iter->seq;
va_list ap;
+ if (ignore_event(iter))
+ return;
+
va_start(ap, fmt);
- trace_check_vprintf(iter, trace_event_format(iter, fmt), ap);
+ trace_seq_vprintf(s, trace_event_format(iter, fmt), ap);
va_end(ap);
}
EXPORT_SYMBOL(trace_event_printf);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5734d5d5060f..7e0f72cd9fd4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3503,7 +3503,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
if (folio_test_partially_mapped(folio)) {
- __folio_clear_partially_mapped(folio);
+ folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
@@ -3615,7 +3615,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
if (!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
if (folio_test_partially_mapped(folio)) {
- __folio_clear_partially_mapped(folio);
+ folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
@@ -3659,7 +3659,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (partially_mapped) {
if (!folio_test_partially_mapped(folio)) {
- __folio_set_partially_mapped(folio);
+ folio_set_partially_mapped(folio);
if (folio_test_pmd_mappable(folio))
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
@@ -3752,7 +3752,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
} else {
/* We lost race with folio_put() */
if (folio_test_partially_mapped(folio)) {
- __folio_clear_partially_mapped(folio);
+ folio_clear_partially_mapped(folio);
mod_mthp_stat(folio_order(folio),
MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 190fa05635f4..5dc57b74a8fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5333,7 +5333,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
break;
}
ret = copy_user_large_folio(new_folio, pte_folio,
- ALIGN_DOWN(addr, sz), dst_vma);
+ addr, dst_vma);
folio_put(pte_folio);
if (ret) {
folio_put(new_folio);
@@ -6632,8 +6632,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
*foliop = NULL;
goto out;
}
- ret = copy_user_large_folio(folio, *foliop,
- ALIGN_DOWN(dst_addr, size), dst_vma);
+ ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma);
folio_put(*foliop);
*foliop = NULL;
if (ret) {
diff --git a/mm/memory.c b/mm/memory.c
index bdf77a3ec47b..d322ddfe6791 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6780,9 +6780,10 @@ static inline int process_huge_page(
return 0;
}
-static void clear_gigantic_page(struct folio *folio, unsigned long addr,
+static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint,
unsigned int nr_pages)
{
+ unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio));
int i;
might_sleep();
@@ -6816,13 +6817,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint)
}
static int copy_user_gigantic_page(struct folio *dst, struct folio *src,
- unsigned long addr,
+ unsigned long addr_hint,
struct vm_area_struct *vma,
unsigned int nr_pages)
{
- int i;
+ unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst));
struct page *dst_page;
struct page *src_page;
+ int i;
for (i = 0; i < nr_pages; i++) {
dst_page = folio_page(dst, i);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b6958333054d..de65e8b4f75f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page,
if (order > pageblock_order)
order = pageblock_order;
- while (pfn != end) {
+ do {
int mt = get_pfnblock_migratetype(page, pfn);
__free_one_page(page, pfn, zone, order, mt, fpi);
pfn += 1 << order;
+ if (pfn == end)
+ break;
page = pfn_to_page(pfn);
- }
+ } while (1);
}
static void free_one_page(struct zone *zone, struct page *page,
diff --git a/mm/shmem.c b/mm/shmem.c
index 568bb290bdce..b03ced0c3d48 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -779,6 +779,14 @@ static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static void shmem_update_stats(struct folio *folio, int nr_pages)
+{
+ if (folio_test_pmd_mappable(folio))
+ __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages);
+ __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages);
+ __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages);
+}
+
/*
* Somewhat like filemap_add_folio, but error if expected item has gone.
*/
@@ -813,10 +821,7 @@ static int shmem_add_to_page_cache(struct folio *folio,
xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
- if (folio_test_pmd_mappable(folio))
- __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr);
- __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
- __lruvec_stat_mod_folio(folio, NR_SHMEM, nr);
+ shmem_update_stats(folio, nr);
mapping->nrpages += nr;
unlock:
xas_unlock_irq(&xas);
@@ -844,8 +849,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap)
error = shmem_replace_entry(mapping, folio->index, folio, radswap);
folio->mapping = NULL;
mapping->nrpages -= nr;
- __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
- __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr);
+ shmem_update_stats(folio, -nr);
xa_unlock_irq(&mapping->i_pages);
folio_put_refs(folio, nr);
BUG_ON(error);
@@ -1944,10 +1948,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
}
if (!error) {
mem_cgroup_replace_folio(old, new);
- __lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages);
- __lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages);
- __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages);
- __lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages);
+ shmem_update_stats(new, nr_pages);
+ shmem_update_stats(old, -nr_pages);
}
xa_unlock_irq(&swap_mapping->i_pages);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 0161cb4391e1..3f9255dfacb0 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3369,7 +3369,8 @@ void vfree(const void *addr)
struct page *page = vm->pages[i];
BUG_ON(!page);
- mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
+ if (!(vm->flags & VM_MAP_PUT_PAGES))
+ mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
/*
* High-order allocs for huge vmallocs are split, so
* can be freed as an array of order-0 allocations
@@ -3377,7 +3378,8 @@ void vfree(const void *addr)
__free_page(page);
cond_resched();
}
- atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
+ if (!(vm->flags & VM_MAP_PUT_PAGES))
+ atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
kvfree(vm->pages);
kfree(vm);
}
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index d2baa1af9df0..7ce22f40db5b 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -359,10 +359,10 @@ static int
netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx,
u32 q_type, const struct genl_info *info)
{
- int err = 0;
+ int err;
if (!(netdev->flags & IFF_UP))
- return err;
+ return -ENOENT;
err = netdev_nl_queue_validate(netdev, q_idx, q_type);
if (err)
@@ -417,24 +417,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp,
struct netdev_nl_dump_ctx *ctx)
{
int err = 0;
- int i;
if (!(netdev->flags & IFF_UP))
return err;
- for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) {
- err = netdev_nl_queue_fill_one(rsp, netdev, i,
+ for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) {
+ err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx,
NETDEV_QUEUE_TYPE_RX, info);
if (err)
return err;
- ctx->rxq_idx = i++;
}
- for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) {
- err = netdev_nl_queue_fill_one(rsp, netdev, i,
+ for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) {
+ err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx,
NETDEV_QUEUE_TYPE_TX, info);
if (err)
return err;
- ctx->txq_idx = i++;
}
return err;
@@ -600,7 +597,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
i, info);
if (err)
return err;
- ctx->rxq_idx = i++;
+ ctx->rxq_idx = ++i;
}
i = ctx->txq_idx;
while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) {
@@ -608,7 +605,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
i, info);
if (err)
return err;
- ctx->txq_idx = i++;
+ ctx->txq_idx = ++i;
}
ctx->rxq_idx = 0;
diff --git a/net/dsa/tag.h b/net/dsa/tag.h
index d5707870906b..5d80ddad4ff6 100644
--- a/net/dsa/tag.h
+++ b/net/dsa/tag.h
@@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb,
* dsa_software_vlan_untag: Software VLAN untagging in DSA receive path
* @skb: Pointer to socket buffer (packet)
*
- * Receive path method for switches which cannot avoid tagging all packets
- * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or
- * ds->untag_vlan_aware_bridge_pvid is set to true.
+ * Receive path method for switches which send some packets as VLAN-tagged
+ * towards the CPU port (generally from VLAN-aware bridge ports) even when the
+ * packet was not tagged on the wire. Called when ds->untag_bridge_pvid
+ * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true.
*
* As a side effect of this method, any VLAN tag from the skb head is moved
* to hwaccel.
@@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb)
{
struct dsa_port *dp = dsa_user_to_port(skb->dev);
struct net_device *br = dsa_port_bridge_dev_get(dp);
- u16 vid;
+ u16 vid, proto;
+ int err;
/* software untagging for standalone ports not yet necessary */
if (!br)
return skb;
+ err = br_vlan_get_proto(br, &proto);
+ if (err)
+ return skb;
+
/* Move VLAN tag from data to hwaccel */
- if (!skb_vlan_tag_present(skb)) {
+ if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
skb = skb_vlan_untag(skb);
if (!skb)
return NULL;
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 597e9cf5aa64..3f2bd65ff5e3 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
msk = NULL;
rc = -EINVAL;
- /* we may be receiving a locally-routed packet; drop source sk
- * accounting
+ /* We may be receiving a locally-routed packet; drop source sk
+ * accounting.
+ *
+ * From here, we will either queue the skb - either to a frag_queue, or
+ * to a receiving socket. When that succeeds, we clear the skb pointer;
+ * a non-NULL skb on exit will be otherwise unowned, and hence
+ * kfree_skb()-ed.
*/
skb_orphan(skb);
@@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
* pending key.
*/
if (flags & MCTP_HDR_FLAG_EOM) {
- sock_queue_rcv_skb(&msk->sk, skb);
+ rc = sock_queue_rcv_skb(&msk->sk, skb);
+ if (!rc)
+ skb = NULL;
if (key) {
/* we've hit a pending reassembly; not much we
* can do but drop it
@@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
MCTP_TRACE_KEY_REPLIED);
key = NULL;
}
- rc = 0;
goto out_unlock;
}
@@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
* this function.
*/
rc = mctp_key_add(key, msk);
- if (!rc)
+ if (!rc) {
trace_mctp_key_acquire(key);
+ skb = NULL;
+ }
/* we don't need to release key->lock on exit, so
* clean up here and suppress the unlock via
@@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
key = NULL;
} else {
rc = mctp_frag_queue(key, skb);
+ if (!rc)
+ skb = NULL;
}
}
@@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
else
rc = mctp_frag_queue(key, skb);
+ if (rc)
+ goto out_unlock;
+
+ /* we've queued; the queue owns the skb now */
+ skb = NULL;
+
/* end of message? deliver to socket, and we're done with
* the reassembly/response key
*/
- if (!rc && flags & MCTP_HDR_FLAG_EOM) {
- sock_queue_rcv_skb(key->sk, key->reasm_head);
- key->reasm_head = NULL;
+ if (flags & MCTP_HDR_FLAG_EOM) {
+ rc = sock_queue_rcv_skb(key->sk, key->reasm_head);
+ if (!rc)
+ key->reasm_head = NULL;
__mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED);
key = NULL;
}
@@ -527,8 +544,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
if (any_key)
mctp_key_unref(any_key);
out:
- if (rc)
- kfree_skb(skb);
+ kfree_skb(skb);
return rc;
}
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 8551dab1d1e6..17165b86ce22 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test)
mctp_test_route_input_multiple_nets_key_fini(test, &t2);
}
+/* Input route to socket, using a single-packet message, where sock delivery
+ * fails. Ensure we're handling the failure appropriately.
+ */
+static void mctp_test_route_input_sk_fail_single(struct kunit *test)
+{
+ const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO);
+ struct mctp_test_route *rt;
+ struct mctp_test_dev *dev;
+ struct socket *sock;
+ struct sk_buff *skb;
+ int rc;
+
+ __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY);
+
+ /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will
+ * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this.
+ */
+ lock_sock(sock->sk);
+ WRITE_ONCE(sock->sk->sk_rcvbuf, 0);
+ release_sock(sock->sk);
+
+ skb = mctp_test_create_skb(&hdr, 10);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+ skb_get(skb);
+
+ mctp_test_skb_set_dev(skb, dev);
+
+ /* do route input, which should fail */
+ rc = mctp_route_input(&rt->rt, skb);
+ KUNIT_EXPECT_NE(test, rc, 0);
+
+ /* we should hold the only reference to skb */
+ KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1);
+ kfree_skb(skb);
+
+ __mctp_route_test_fini(test, dev, rt, sock);
+}
+
+/* Input route to socket, using a fragmented message, where sock delivery fails.
+ */
+static void mctp_test_route_input_sk_fail_frag(struct kunit *test)
+{
+ const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) };
+ struct mctp_test_route *rt;
+ struct mctp_test_dev *dev;
+ struct sk_buff *skbs[2];
+ struct socket *sock;
+ unsigned int i;
+ int rc;
+
+ __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY);
+
+ lock_sock(sock->sk);
+ WRITE_ONCE(sock->sk->sk_rcvbuf, 0);
+ release_sock(sock->sk);
+
+ for (i = 0; i < ARRAY_SIZE(skbs); i++) {
+ skbs[i] = mctp_test_create_skb(&hdrs[i], 10);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]);
+ skb_get(skbs[i]);
+
+ mctp_test_skb_set_dev(skbs[i], dev);
+ }
+
+ /* first route input should succeed, we're only queueing to the
+ * frag list
+ */
+ rc = mctp_route_input(&rt->rt, skbs[0]);
+ KUNIT_EXPECT_EQ(test, rc, 0);
+
+ /* final route input should fail to deliver to the socket */
+ rc = mctp_route_input(&rt->rt, skbs[1]);
+ KUNIT_EXPECT_NE(test, rc, 0);
+
+ /* we should hold the only reference to both skbs */
+ KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1);
+ kfree_skb(skbs[0]);
+
+ KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1);
+ kfree_skb(skbs[1]);
+
+ __mctp_route_test_fini(test, dev, rt, sock);
+}
+
#if IS_ENABLED(CONFIG_MCTP_FLOWS)
static void mctp_test_flow_init(struct kunit *test,
@@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = {
mctp_route_input_sk_reasm_gen_params),
KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys,
mctp_route_input_sk_keys_gen_params),
+ KUNIT_CASE(mctp_test_route_input_sk_fail_single),
+ KUNIT_CASE(mctp_test_route_input_sk_fail_frag),
KUNIT_CASE(mctp_test_route_input_multiple_nets_bind),
KUNIT_CASE(mctp_test_route_input_multiple_nets_key),
KUNIT_CASE(mctp_test_packet_flow),
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index bfae7066936b..db794fe1300e 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size)
return true;
}
+static struct lock_class_key list_set_lockdep_key;
+
static int
list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
u32 flags)
@@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
if (size < IP_SET_LIST_MIN_SIZE)
size = IP_SET_LIST_MIN_SIZE;
+ lockdep_set_class(&set->lock, &list_set_lockdep_key);
set->variant = &set_variant;
set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem),
__alignof__(struct set_elem));
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 98d7dbe3d787..c0289f83f96d 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1495,8 +1495,8 @@ int __init ip_vs_conn_init(void)
max_avail -= 2; /* ~4 in hash row */
max_avail -= 1; /* IPVS up to 1/2 of mem */
max_avail -= order_base_2(sizeof(struct ip_vs_conn));
- max = clamp(max, min, max_avail);
- ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max);
+ max = clamp(max_avail, min, max);
+ ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max);
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1;
diff --git a/net/psample/psample.c b/net/psample/psample.c
index a0ddae8a65f9..25f92ba0840c 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group,
nla_total_size_64bit(sizeof(u64)) + /* timestamp */
nla_total_size(sizeof(u16)) + /* protocol */
(md->user_cookie_len ?
- nla_total_size(md->user_cookie_len) : 0); /* user cookie */
+ nla_total_size(md->user_cookie_len) : 0) + /* user cookie */
+ (md->rate_as_probability ?
+ nla_total_size(0) : 0); /* rate as probability */
#ifdef CONFIG_INET
tun_info = skb_tunnel_info(skb);
@@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group,
md->user_cookie))
goto error;
- if (md->rate_as_probability)
- nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY);
+ if (md->rate_as_probability &&
+ nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY))
+ goto error;
genlmsg_end(nl_skb, data);
genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0,
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index f2f9b75008bb..8d8b2db4653c 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1525,7 +1525,6 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
b->backlogs[idx] -= len;
b->tin_backlog -= len;
sch->qstats.backlog -= len;
- qdisc_tree_reduce_backlog(sch, 1, len);
flow->dropped++;
b->tin_dropped++;
@@ -1536,6 +1535,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
__qdisc_drop(skb, to_free);
sch->q.qlen--;
+ qdisc_tree_reduce_backlog(sch, 1, len);
cake_heapify(q, 0);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 91072010923d..757b89292e7e 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -123,10 +123,10 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
if (idx == q->tail)
choke_zap_tail_holes(q);
+ --sch->q.qlen;
qdisc_qstats_backlog_dec(sch, skb);
qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
qdisc_drop(skb, sch, to_free);
- --sch->q.qlen;
}
struct choke_skb_cb {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9e6c69d18581..6cc7b846cff1 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2032,6 +2032,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc,
if (pclc->hdr.typev1 == SMC_TYPE_N)
return 0;
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+ if (!pclc_prfx)
+ return -EPROTO;
if (smc_clc_prfx_match(newclcsock, pclc_prfx))
return SMC_CLC_DECL_DIFFPREFIX;
@@ -2145,6 +2147,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
pclc_smcd = smc_get_clc_msg_smcd(pclc);
smc_v2_ext = smc_get_clc_v2_ext(pclc);
smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
+ if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext)
+ goto not_found;
mutex_lock(&smcd_dev_list.mutex);
if (pclc_smcd->ism.chid) {
@@ -2221,7 +2225,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
int rc = 0;
/* check if ISM V1 is available */
- if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
+ if (!(ini->smcd_version & SMC_V1) ||
+ !smcd_indicated(ini->smc_type_v1) ||
+ !pclc_smcd)
goto not_found;
ini->is_smcd = true; /* prepare ISM check */
ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid);
@@ -2272,7 +2278,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc,
goto not_found;
smc_v2_ext = smc_get_clc_v2_ext(pclc);
- if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL))
+ if (!smc_v2_ext ||
+ !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL))
goto not_found;
/* prepare RDMA check */
@@ -2881,6 +2888,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock,
} else {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+
+ if (sk->sk_state != SMC_INIT) {
+ /* Race breaker the same way as tcp_poll(). */
+ smp_mb__after_atomic();
+ if (atomic_read(&smc->conn.sndbuf_space))
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ }
}
if (atomic_read(&smc->conn.bytes_to_rcv))
mask |= EPOLLIN | EPOLLRDNORM;
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 33fa787c28eb..521f5df80e10 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
struct smc_clc_msg_hdr *hdr = &pclc->hdr;
struct smc_clc_v2_extension *v2_ext;
- v2_ext = smc_get_clc_v2_ext(pclc);
pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+ if (!pclc_prfx ||
+ pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX)
+ return false;
+
if (hdr->version == SMC_V1) {
if (hdr->typev1 == SMC_TYPE_N)
return false;
@@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
sizeof(struct smc_clc_msg_trail))
return false;
} else {
+ v2_ext = smc_get_clc_v2_ext(pclc);
+ if ((hdr->typev2 != SMC_TYPE_N &&
+ (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) ||
+ (smcd_indicated(hdr->typev2) &&
+ v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES))
+ return false;
+
if (ntohs(hdr->length) !=
sizeof(*pclc) +
sizeof(struct smc_clc_msg_smcd) +
@@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
SMC_CLC_RECV_BUF_LEN : datlen;
iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen);
len = sock_recvmsg(smc->clcsock, &msg, krflags);
+ if (len < recvlen) {
+ smc->sk.sk_err = EPROTO;
+ reason_code = -EPROTO;
+ goto out;
+ }
datlen -= len;
}
if (clcm->type == SMC_CLC_DECLINE) {
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 5625fda2960b..1a7676227f16 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */
static inline struct smc_clc_msg_proposal_prefix *
smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
{
+ u16 offset = ntohs(pclc->iparea_offset);
+
+ if (offset > sizeof(struct smc_clc_msg_smcd))
+ return NULL;
return (struct smc_clc_msg_proposal_prefix *)
- ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
+ ((u8 *)pclc + sizeof(*pclc) + offset);
}
static inline bool smcr_indicated(int smc_type)
@@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension *
smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
{
struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop);
+ u16 max_offset;
- if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset))
+ max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) -
+ offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) -
+ offsetofend(struct smc_clc_msg_smcd, v2_ext_offset);
+
+ if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) ||
+ ntohs(prop_smcd->v2_ext_offset) > max_offset)
return NULL;
return (struct smc_clc_v2_extension *)
@@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
static inline struct smc_clc_smcd_v2_extension *
smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
{
+ u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) -
+ offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) -
+ offsetof(struct smc_clc_v2_extension, hdr) -
+ offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset);
+
if (!prop_v2ext)
return NULL;
- if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset))
+ if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) ||
+ ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset)
return NULL;
return (struct smc_clc_smcd_v2_extension *)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 4e694860ece4..68515a41d776 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk)
{
if (smc_link_downing(&lnk->state)) {
trace_smcr_link_down(lnk, __builtin_return_address(0));
- schedule_work(&lnk->link_down_wrk);
+ smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */
+ if (!schedule_work(&lnk->link_down_wrk))
+ smcr_link_put(lnk);
}
}
@@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work)
struct smc_link_group *lgr = link->lgr;
if (list_empty(&lgr->list))
- return;
+ goto out;
wake_up_all(&lgr->llc_msg_waiter);
down_write(&lgr->llc_conf_mutex);
smcr_link_down(link);
up_write(&lgr->llc_conf_mutex);
+
+out:
+ smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */
}
static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index e283751abfef..678540b78280 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -29,6 +29,7 @@ config SND_SOC_FSL_SAI
config SND_SOC_FSL_MQS
tristate "Medium Quality Sound (MQS) module support"
depends on SND_SOC_FSL_SAI
+ depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV
select REGMAP_MMIO
help
Say Y if you want to add Medium Quality Sound (MQS)
diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c
index 7a00f3066a98..12743d7f164f 100644
--- a/tools/hv/hv_fcopy_uio_daemon.c
+++ b/tools/hv/hv_fcopy_uio_daemon.c
@@ -35,8 +35,6 @@
#define WIN8_SRV_MINOR 1
#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
-#define MAX_FOLDER_NAME 15
-#define MAX_PATH_LEN 15
#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio"
#define FCOPY_VER_COUNT 1
@@ -51,7 +49,7 @@ static const int fw_versions[] = {
#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */
-unsigned char desc[HV_RING_SIZE];
+static unsigned char desc[HV_RING_SIZE];
static int target_fd;
static char target_fname[PATH_MAX];
@@ -409,8 +407,8 @@ int main(int argc, char *argv[])
struct vmbus_br txbr, rxbr;
void *ring;
uint32_t len = HV_RING_SIZE;
- char uio_name[MAX_FOLDER_NAME] = {0};
- char uio_dev_path[MAX_PATH_LEN] = {0};
+ char uio_name[NAME_MAX] = {0};
+ char uio_dev_path[PATH_MAX] = {0};
static struct option long_options[] = {
{"help", no_argument, 0, 'h' },
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index 440a91b35823..2f8baed2b8f7 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1
cp $1 /etc/sysconfig/network-scripts/
-chmod 600 $2
+umask 0177
interface=$(echo $2 | awk -F - '{ print $2 }')
filename="${2##*/}"
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index c22c22bf2cb7..a3f741fed0a3 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -553,10 +553,10 @@ class YnlFamily(SpecFamily):
if attr["type"] == 'nest':
nl_type |= Netlink.NLA_F_NESTED
attr_payload = b''
- sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs)
+ sub_space = attr['nested-attributes']
+ sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs)
for subname, subvalue in value.items():
- attr_payload += self._add_attr(attr['nested-attributes'],
- subname, subvalue, sub_attrs)
+ attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs)
elif attr["type"] == 'flag':
if not value:
# If value is absent or false then skip attribute creation.
diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
index ca0162b4dc57..1fcfa5160231 100644
--- a/tools/testing/selftests/bpf/sdt.h
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -102,6 +102,8 @@
# define STAP_SDT_ARG_CONSTRAINT nZr
# elif defined __arm__
# define STAP_SDT_ARG_CONSTRAINT g
+# elif defined __loongarch__
+# define STAP_SDT_ARG_CONSTRAINT nmr
# else
# define STAP_SDT_ARG_CONSTRAINT nor
# endif
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 95af2d78fd31..0a0b55516028 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -9,6 +9,7 @@
#include <fcntl.h>
#include <linux/memfd.h>
#include <sched.h>
+#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <signal.h>
@@ -1557,6 +1558,11 @@ static void test_share_fork(char *banner, char *b_suffix)
close(fd);
}
+static bool pid_ns_supported(void)
+{
+ return access("/proc/self/ns/pid", F_OK) == 0;
+}
+
int main(int argc, char **argv)
{
pid_t pid;
@@ -1591,8 +1597,12 @@ int main(int argc, char **argv)
test_seal_grow();
test_seal_resize();
- test_sysctl_simple();
- test_sysctl_nested();
+ if (pid_ns_supported()) {
+ test_sysctl_simple();
+ test_sysctl_nested();
+ } else {
+ printf("PID namespaces are not supported; skipping sysctl tests\n");
+ }
test_share_dup("SHARE-DUP", "");
test_share_mmap("SHARE-MMAP", "");
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index cc0bfae2bafa..960e1ab4dd04 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -171,8 +171,10 @@ ovs_add_netns_and_veths () {
ovs_add_if "$1" "$2" "$4" -u || return 1
fi
- [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \
- tcpdump -i any -s 65535
+ if [ $TRACING -eq 1 ]; then
+ ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553
+ ovs_wait grep -q "listening on any" ${ovs_dir}/stderr
+ fi
return 0
}
Powered by blists - more mailing lists