summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/acpi/cppc_acpi.h2
-rw-r--r--include/acpi/processor.h2
-rw-r--r--include/asm-generic/qspinlock.h2
-rw-r--r--include/asm-generic/spinlock.h87
-rw-r--r--include/asm-generic/spinlock_types.h12
-rw-r--r--include/asm-generic/ticket_spinlock.h105
-rw-r--r--include/drm/drm_kunit_helpers.h4
-rw-r--r--include/kvm/arm_arch_timer.h3
-rw-r--r--include/kvm/arm_pmu.h18
-rw-r--r--include/kvm/arm_psci.h4
-rw-r--r--include/kvm/arm_vgic.h1
-rw-r--r--include/linux/alloc_tag.h16
-rw-r--r--include/linux/arch_topology.h4
-rw-r--r--include/linux/arm-smccc.h32
-rw-r--r--include/linux/bpf_mem_alloc.h3
-rw-r--r--include/linux/compiler-gcc.h4
-rw-r--r--include/linux/device.h3
-rw-r--r--include/linux/fs_context.h6
-rw-r--r--include/linux/input.h10
-rw-r--r--include/linux/iomap.h19
-rw-r--r--include/linux/ksm.h10
-rw-r--r--include/linux/kvm_host.h131
-rw-r--r--include/linux/mman.h28
-rw-r--r--include/linux/mmzone.h8
-rw-r--r--include/linux/nfslocalio.h3
-rw-r--r--include/linux/page-flags.h8
-rw-r--r--include/linux/soc/qcom/llcc-qcom.h2
-rw-r--r--include/linux/swap.h1
-rw-r--r--include/linux/tick.h8
-rw-r--r--include/linux/uaccess.h21
-rw-r--r--include/linux/user_namespace.h3
-rw-r--r--include/linux/userfaultfd_k.h5
-rw-r--r--include/net/cfg80211.h44
-rw-r--r--include/net/ieee80211_radiotap.h43
-rw-r--r--include/net/ip_tunnels.h2
-rw-r--r--include/net/netfilter/nf_tables.h4
-rw-r--r--include/trace/events/afs.h7
-rw-r--r--include/trace/events/kvm.h35
-rw-r--r--include/trace/events/rxrpc.h1
-rw-r--r--include/uapi/linux/elf.h1
-rw-r--r--include/uapi/linux/kvm.h8
-rw-r--r--include/uapi/linux/prctl.h5
-rw-r--r--include/uapi/linux/psci.h5
43 files changed, 487 insertions, 233 deletions
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 76e44e102780..62d368bcd9ec 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -65,7 +65,7 @@ struct cpc_desc {
int write_cmd_status;
int write_cmd_id;
/* Lock used for RMW operations in cpc_write() */
- spinlock_t rmw_lock;
+ raw_spinlock_t rmw_lock;
struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
struct acpi_psd_package domain_info;
struct kobject kobj;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index e6f6074eadbf..a17e97e634a6 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -465,4 +465,6 @@ extern int acpi_processor_ffh_lpi_probe(unsigned int cpu);
extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi);
#endif
+void acpi_processor_init_invariance_cppc(void);
+
#endif
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 0655aa5b57b2..bf47cca2c375 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -136,6 +136,7 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
}
#endif
+#ifndef __no_arch_spinlock_redefine
/*
* Remapping spinlock architecture specific functions to the corresponding
* queued spinlock functions.
@@ -146,5 +147,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
#define arch_spin_lock(l) queued_spin_lock(l)
#define arch_spin_trylock(l) queued_spin_trylock(l)
#define arch_spin_unlock(l) queued_spin_unlock(l)
+#endif
#endif /* __ASM_GENERIC_QSPINLOCK_H */
diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h
index 90803a826ba0..970590baf61b 100644
--- a/include/asm-generic/spinlock.h
+++ b/include/asm-generic/spinlock.h
@@ -1,94 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * 'Generic' ticket-lock implementation.
- *
- * It relies on atomic_fetch_add() having well defined forward progress
- * guarantees under contention. If your architecture cannot provide this, stick
- * to a test-and-set lock.
- *
- * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a
- * sub-word of the value. This is generally true for anything LL/SC although
- * you'd be hard pressed to find anything useful in architecture specifications
- * about this. If your architecture cannot do this you might be better off with
- * a test-and-set.
- *
- * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence
- * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with
- * a full fence after the spin to upgrade the otherwise-RCpc
- * atomic_cond_read_acquire().
- *
- * The implementation uses smp_cond_load_acquire() to spin, so if the
- * architecture has WFE like instructions to sleep instead of poll for word
- * modifications be sure to implement that (see ARM64 for example).
- *
- */
-
#ifndef __ASM_GENERIC_SPINLOCK_H
#define __ASM_GENERIC_SPINLOCK_H
-#include <linux/atomic.h>
-#include <asm-generic/spinlock_types.h>
-
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
- u32 val = atomic_fetch_add(1<<16, lock);
- u16 ticket = val >> 16;
-
- if (ticket == (u16)val)
- return;
-
- /*
- * atomic_cond_read_acquire() is RCpc, but rather than defining a
- * custom cond_read_rcsc() here we just emit a full fence. We only
- * need the prior reads before subsequent writes ordering from
- * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we
- * have no outstanding writes due to the atomic_fetch_add() the extra
- * orderings are free.
- */
- atomic_cond_read_acquire(lock, ticket == (u16)VAL);
- smp_mb();
-}
-
-static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock)
-{
- u32 old = atomic_read(lock);
-
- if ((old >> 16) != (old & 0xffff))
- return false;
-
- return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */
-}
-
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
- u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
- u32 val = atomic_read(lock);
-
- smp_store_release(ptr, (u16)val + 1);
-}
-
-static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
- u32 val = lock.counter;
-
- return ((val >> 16) == (val & 0xffff));
-}
-
-static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock)
-{
- arch_spinlock_t val = READ_ONCE(*lock);
-
- return !arch_spin_value_unlocked(val);
-}
-
-static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
- u32 val = atomic_read(lock);
-
- return (s16)((val >> 16) - (val & 0xffff)) > 1;
-}
-
+#include <asm-generic/ticket_spinlock.h>
#include <asm/qrwlock.h>
#endif /* __ASM_GENERIC_SPINLOCK_H */
diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h
index 8962bb730945..f534aa5de394 100644
--- a/include/asm-generic/spinlock_types.h
+++ b/include/asm-generic/spinlock_types.h
@@ -3,15 +3,7 @@
#ifndef __ASM_GENERIC_SPINLOCK_TYPES_H
#define __ASM_GENERIC_SPINLOCK_TYPES_H
-#include <linux/types.h>
-typedef atomic_t arch_spinlock_t;
-
-/*
- * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the
- * include.
- */
-#include <asm/qrwlock_types.h>
-
-#define __ARCH_SPIN_LOCK_UNLOCKED ATOMIC_INIT(0)
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
#endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */
diff --git a/include/asm-generic/ticket_spinlock.h b/include/asm-generic/ticket_spinlock.h
new file mode 100644
index 000000000000..325779970d8a
--- /dev/null
+++ b/include/asm-generic/ticket_spinlock.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * 'Generic' ticket-lock implementation.
+ *
+ * It relies on atomic_fetch_add() having well defined forward progress
+ * guarantees under contention. If your architecture cannot provide this, stick
+ * to a test-and-set lock.
+ *
+ * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a
+ * sub-word of the value. This is generally true for anything LL/SC although
+ * you'd be hard pressed to find anything useful in architecture specifications
+ * about this. If your architecture cannot do this you might be better off with
+ * a test-and-set.
+ *
+ * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence
+ * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with
+ * a full fence after the spin to upgrade the otherwise-RCpc
+ * atomic_cond_read_acquire().
+ *
+ * The implementation uses smp_cond_load_acquire() to spin, so if the
+ * architecture has WFE like instructions to sleep instead of poll for word
+ * modifications be sure to implement that (see ARM64 for example).
+ *
+ */
+
+#ifndef __ASM_GENERIC_TICKET_SPINLOCK_H
+#define __ASM_GENERIC_TICKET_SPINLOCK_H
+
+#include <linux/atomic.h>
+#include <asm-generic/spinlock_types.h>
+
+static __always_inline void ticket_spin_lock(arch_spinlock_t *lock)
+{
+ u32 val = atomic_fetch_add(1<<16, &lock->val);
+ u16 ticket = val >> 16;
+
+ if (ticket == (u16)val)
+ return;
+
+ /*
+ * atomic_cond_read_acquire() is RCpc, but rather than defining a
+ * custom cond_read_rcsc() here we just emit a full fence. We only
+ * need the prior reads before subsequent writes ordering from
+ * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we
+ * have no outstanding writes due to the atomic_fetch_add() the extra
+ * orderings are free.
+ */
+ atomic_cond_read_acquire(&lock->val, ticket == (u16)VAL);
+ smp_mb();
+}
+
+static __always_inline bool ticket_spin_trylock(arch_spinlock_t *lock)
+{
+ u32 old = atomic_read(&lock->val);
+
+ if ((old >> 16) != (old & 0xffff))
+ return false;
+
+ return atomic_try_cmpxchg(&lock->val, &old, old + (1<<16)); /* SC, for RCsc */
+}
+
+static __always_inline void ticket_spin_unlock(arch_spinlock_t *lock)
+{
+ u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+ u32 val = atomic_read(&lock->val);
+
+ smp_store_release(ptr, (u16)val + 1);
+}
+
+static __always_inline int ticket_spin_value_unlocked(arch_spinlock_t lock)
+{
+ u32 val = lock.val.counter;
+
+ return ((val >> 16) == (val & 0xffff));
+}
+
+static __always_inline int ticket_spin_is_locked(arch_spinlock_t *lock)
+{
+ arch_spinlock_t val = READ_ONCE(*lock);
+
+ return !ticket_spin_value_unlocked(val);
+}
+
+static __always_inline int ticket_spin_is_contended(arch_spinlock_t *lock)
+{
+ u32 val = atomic_read(&lock->val);
+
+ return (s16)((val >> 16) - (val & 0xffff)) > 1;
+}
+
+#ifndef __no_arch_spinlock_redefine
+/*
+ * Remapping spinlock architecture specific functions to the corresponding
+ * ticket spinlock functions.
+ */
+#define arch_spin_is_locked(l) ticket_spin_is_locked(l)
+#define arch_spin_is_contended(l) ticket_spin_is_contended(l)
+#define arch_spin_value_unlocked(l) ticket_spin_value_unlocked(l)
+#define arch_spin_lock(l) ticket_spin_lock(l)
+#define arch_spin_trylock(l) ticket_spin_trylock(l)
+#define arch_spin_unlock(l) ticket_spin_unlock(l)
+#endif
+
+#endif /* __ASM_GENERIC_TICKET_SPINLOCK_H */
diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h
index e7cc17ee4934..afdd46ef04f7 100644
--- a/include/drm/drm_kunit_helpers.h
+++ b/include/drm/drm_kunit_helpers.h
@@ -120,4 +120,8 @@ drm_kunit_helper_create_crtc(struct kunit *test,
const struct drm_crtc_funcs *funcs,
const struct drm_crtc_helper_funcs *helper_funcs);
+struct drm_display_mode *
+drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev,
+ u8 video_code);
+
#endif // DRM_KUNIT_HELPERS_H_
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index c819c5d16613..fd650a8789b9 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -147,6 +147,9 @@ u64 timer_get_cval(struct arch_timer_context *ctxt);
void kvm_timer_cpu_up(void);
void kvm_timer_cpu_down(void);
+/* CNTKCTL_EL1 valid bits as of DDI0487J.a */
+#define CNTKCTL_VALID_BITS (BIT(17) | GENMASK_ULL(9, 0))
+
static inline bool has_cntpoff(void)
{
return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index e08aeec5d936..e61dd7dd2286 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -47,7 +47,8 @@ static __always_inline bool kvm_arm_support_pmu_v3(void)
#define kvm_arm_pmu_irq_initialized(v) ((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
-u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
+u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu);
+u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu);
u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1);
void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
@@ -96,6 +97,8 @@ int kvm_arm_set_default_pmu(struct kvm *kvm);
u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm);
u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
+bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx);
+void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu);
#else
struct kvm_pmu {
};
@@ -113,7 +116,11 @@ static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
}
static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu,
u64 select_idx, u64 val) {}
-static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+static inline u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+static inline u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
{
return 0;
}
@@ -187,6 +194,13 @@ static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
return 0;
}
+static inline bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
+{
+ return false;
+}
+
+static inline void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) {}
+
#endif
#endif
diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h
index e8fb624013d1..cbaec804eb83 100644
--- a/include/kvm/arm_psci.h
+++ b/include/kvm/arm_psci.h
@@ -14,8 +14,10 @@
#define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2)
#define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0)
#define KVM_ARM_PSCI_1_1 PSCI_VERSION(1, 1)
+#define KVM_ARM_PSCI_1_2 PSCI_VERSION(1, 2)
+#define KVM_ARM_PSCI_1_3 PSCI_VERSION(1, 3)
-#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_1
+#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_3
static inline int kvm_psci_version(struct kvm_vcpu *vcpu)
{
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index f5172549f9ba..3a8ccfda34d2 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -26,7 +26,6 @@
#define VGIC_NR_SGIS 16
#define VGIC_NR_PPIS 16
#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1)
#define VGIC_MAX_SPI 1019
#define VGIC_MAX_RESERVED 1023
#define VGIC_MIN_LPI 8192
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 1f0a9ff23a2c..941deffc590d 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {}
#endif
/* Caller should verify both ref and tag to be valid */
-static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
{
alloc_tag_add_check(ref, tag);
if (!ref || !tag)
- return;
+ return false;
ref->ct = &tag->ct;
+ return true;
}
-static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
{
- __alloc_tag_ref_set(ref, tag);
+ if (unlikely(!__alloc_tag_ref_set(ref, tag)))
+ return false;
+
/*
* We need in increment the call counter every time we have a new
* allocation or when we split a large allocation into smaller ones.
@@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t
* counter because when we free each part the counter will be decremented.
*/
this_cpu_inc(tag->counters->calls);
+ return true;
}
static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes)
{
- alloc_tag_ref_set(ref, tag);
- this_cpu_add(tag->counters->bytes, bytes);
+ if (likely(alloc_tag_ref_set(ref, tag)))
+ this_cpu_add(tag->counters->bytes, bytes);
}
static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index b721f360d759..4a952c4885ed 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -11,10 +11,6 @@
void topology_normalize_cpu_scale(void);
int topology_update_cpu_topology(void);
-#ifdef CONFIG_ACPI_CPPC_LIB
-void topology_init_cpu_capacity_cppc(void);
-#endif
-
struct device_node;
bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index f59099a213d0..67f6fdf2e7cd 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -315,8 +315,6 @@ u32 arm_smccc_get_version(void);
void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
-extern u64 smccc_has_sve_hint;
-
/**
* arm_smccc_get_soc_id_version()
*
@@ -415,15 +413,6 @@ struct arm_smccc_quirk {
};
/**
- * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls
- *
- * Sets the SMCCC hint bit to indicate if there is live state in the SVE
- * registers, this modifies x0 in place and should never be called from C
- * code.
- */
-asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
-
-/**
* __arm_smccc_smc() - make SMC calls
* @a0-a7: arguments passed in registers 0 to 7
* @res: result values from registers 0 to 3
@@ -490,20 +479,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
#endif
-/* nVHE hypervisor doesn't have a current thread so needs separate checks */
-#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__)
-
-#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \
- ARM64_SVE)
-#define smccc_sve_clobbers "x16", "x30", "cc",
-
-#else
-
-#define SMCCC_SVE_CHECK
-#define smccc_sve_clobbers
-
-#endif
-
#define __constraint_read_2 "r" (arg0)
#define __constraint_read_3 __constraint_read_2, "r" (arg1)
#define __constraint_read_4 __constraint_read_3, "r" (arg2)
@@ -574,12 +549,11 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
register unsigned long r3 asm("r3"); \
CONCATENATE(__declare_arg_, \
COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__); \
- asm volatile(SMCCC_SVE_CHECK \
- inst "\n" : \
+ asm volatile(inst "\n" : \
"=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \
: CONCATENATE(__constraint_read_, \
COUNT_ARGS(__VA_ARGS__)) \
- : smccc_sve_clobbers "memory"); \
+ : "memory"); \
if (___res) \
*___res = (typeof(*___res)){r0, r1, r2, r3}; \
} while (0)
@@ -628,7 +602,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
asm ("" : \
: CONCATENATE(__constraint_read_, \
COUNT_ARGS(__VA_ARGS__)) \
- : smccc_sve_clobbers "memory"); \
+ : "memory"); \
if (___res) \
___res->a0 = SMCCC_RET_NOT_SUPPORTED; \
} while (0)
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index aaf004d94322..e45162ef59bb 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+/* Check the allocation size for kmalloc equivalent allocator */
+int bpf_mem_alloc_check_size(bool percpu, size_t size);
+
/* kmalloc/kfree equivalent: */
void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index f805adaa316e..cd6f9aae311f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -80,7 +80,11 @@
#define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
#endif
+#ifdef __SANITIZE_HWADDRESS__
+#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress")))
+#else
#define __no_sanitize_address __attribute__((__no_sanitize_address__))
+#endif
#if defined(__SANITIZE_THREAD__)
#define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
diff --git a/include/linux/device.h b/include/linux/device.h
index b4bde8d22697..667cb6db9019 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data,
int (*fn)(struct device *dev, void *data));
int device_for_each_child_reverse(struct device *dev, void *data,
int (*fn)(struct device *dev, void *data));
+int device_for_each_child_reverse_from(struct device *parent,
+ struct device *from, const void *data,
+ int (*fn)(struct device *, const void *));
struct device *device_find_child(struct device *dev, void *data,
int (*match)(struct device *dev, void *data));
struct device *device_find_child_by_name(struct device *parent,
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index c13e99cbbf81..4b4bfef6f053 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc,
int setup_bdev_super(struct super_block *sb, int sb_flags,
struct fs_context *fc);
+
+#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001
+int get_tree_bdev_flags(struct fs_context *fc,
+ int (*fill_super)(struct super_block *sb,
+ struct fs_context *fc), unsigned int flags);
+
extern int get_tree_bdev(struct fs_context *fc,
int (*fill_super)(struct super_block *sb,
struct fs_context *fc));
diff --git a/include/linux/input.h b/include/linux/input.h
index 89a0be6ee0e2..cd866b020a01 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -339,12 +339,16 @@ struct input_handler {
* @name: name given to the handle by handler that created it
* @dev: input device the handle is attached to
* @handler: handler that works with the device through this handle
+ * @handle_events: event sequence handler. It is set up by the input core
+ * according to event handling method specified in the @handler. See
+ * input_handle_setup_event_handler().
+ * This method is being called by the input core with interrupts disabled
+ * and dev->event_lock spinlock held and so it may not sleep.
* @d_node: used to put the handle on device's list of attached handles
* @h_node: used to put the handle on handler's list of handles from which
* it gets events
*/
struct input_handle {
-
void *private;
int open;
@@ -353,6 +357,10 @@ struct input_handle {
struct input_dev *dev;
struct input_handler *handler;
+ unsigned int (*handle_events)(struct input_handle *handle,
+ struct input_value *vals,
+ unsigned int count);
+
struct list_head d_node;
struct list_head h_node;
};
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index d0420e962ffd..f61407e3b121 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -270,6 +270,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
return round_up(pos + written, i_blocksize(inode));
}
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+ return (iter->iomap.flags & IOMAP_F_SHARED) &&
+ iter->srcmap.type == IOMAP_MAPPED;
+}
+
ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
const struct iomap_ops *ops, void *private);
int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 11690dacd986..ec9c05044d4f 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
return atomic_long_read(&mm->ksm_zero_pages);
}
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
+ /* Adding mm to ksm is best effort on fork. */
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
- return __ksm_enter(mm);
-
- return 0;
+ __ksm_enter(mm);
}
static inline int ksm_execve(struct mm_struct *mm)
@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
return 0;
}
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
- return 0;
}
static inline int ksm_execve(struct mm_struct *mm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 45be36e5285f..401439bb21e3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -97,6 +97,7 @@
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4)
/*
* error pfns indicate that the gfn is in slot but faild to
@@ -153,13 +154,6 @@ static inline bool kvm_is_error_gpa(gpa_t gpa)
return gpa == INVALID_GPA;
}
-#define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT))
-
-static inline bool is_error_page(struct page *page)
-{
- return IS_ERR(page);
-}
-
#define KVM_REQUEST_MASK GENMASK(7,0)
#define KVM_REQUEST_NO_WAKEUP BIT(8)
#define KVM_REQUEST_WAIT BIT(9)
@@ -219,6 +213,7 @@ enum kvm_bus {
KVM_PIO_BUS,
KVM_VIRTIO_CCW_NOTIFY_BUS,
KVM_FAST_MMIO_BUS,
+ KVM_IOCSR_BUS,
KVM_NR_BUSES
};
@@ -279,21 +274,19 @@ enum {
READING_SHADOW_PAGE_TABLES,
};
-#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA)
-
struct kvm_host_map {
/*
* Only valid if the 'pfn' is managed by the host kernel (i.e. There is
* a 'struct page' for it. When using mem= kernel parameter some memory
* can be used as guest memory but they are not managed by host
* kernel).
- * If 'pfn' is not managed by the host kernel, this field is
- * initialized to KVM_UNMAPPED_PAGE.
*/
+ struct page *pinned_page;
struct page *page;
void *hva;
kvm_pfn_t pfn;
kvm_pfn_t gfn;
+ bool writable;
};
/*
@@ -342,7 +335,8 @@ struct kvm_vcpu {
#ifndef __KVM_HAVE_ARCH_WQP
struct rcuwait wait;
#endif
- struct pid __rcu *pid;
+ struct pid *pid;
+ rwlock_t pid_lock;
int sigset_active;
sigset_t sigset;
unsigned int halt_poll_ns;
@@ -1176,6 +1170,10 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_
kvm_memslot_iter_is_valid(iter, end); \
kvm_memslot_iter_next(iter))
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
+struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
+struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
+
/*
* KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
* - create a new memory slot
@@ -1214,33 +1212,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm);
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot);
-int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
- struct page **pages, int nr_pages);
+int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct page **pages, int nr_pages);
+
+struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write);
+static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+ return __gfn_to_page(kvm, gfn, true);
+}
-struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
bool *writable);
+
+static inline void kvm_release_page_unused(struct page *page)
+{
+ if (!page)
+ return;
+
+ put_page(page);
+}
+
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
-kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
- bool *writable);
-kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool interruptible, bool *async,
- bool write_fault, bool *writable, hva_t *hva);
-
-void kvm_release_pfn_clean(kvm_pfn_t pfn);
-void kvm_release_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
+static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page,
+ bool unused, bool dirty)
+{
+ lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused);
+
+ if (!page)
+ return;
+
+ /*
+ * If the page that KVM got from the *primary MMU* is writable, and KVM
+ * installed or reused a SPTE, mark the page/folio dirty. Note, this
+ * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if
+ * the GFN is write-protected. Folios can't be safely marked dirty
+ * outside of mmu_lock as doing so could race with writeback on the
+ * folio. As a result, KVM can't mark folios dirty in the fast page
+ * fault handler, and so KVM must (somewhat) speculatively mark the
+ * folio dirty if KVM could locklessly make the SPTE writable.
+ */
+ if (unused)
+ kvm_release_page_unused(page);
+ else if (dirty)
+ kvm_release_page_dirty(page);
+ else
+ kvm_release_page_clean(page);
+}
+
+kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn,
+ unsigned int foll, bool *writable,
+ struct page **refcounted_page);
+
+static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
+ bool write, bool *writable,
+ struct page **refcounted_page)
+{
+ return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn,
+ write ? FOLL_WRITE : 0, writable, refcounted_page);
+}
+
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -1304,17 +1339,28 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
})
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
-struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
-struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
+int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map,
+ bool writable);
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map);
+
+static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa,
+ struct kvm_host_map *map)
+{
+ return __kvm_vcpu_map(vcpu, gpa, map, true);
+}
+
+static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa,
+ struct kvm_host_map *map)
+{
+ return __kvm_vcpu_map(vcpu, gpa, map, false);
+}
+
unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
@@ -1686,9 +1732,6 @@ void kvm_arch_sync_events(struct kvm *kvm);
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
-struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn);
-bool kvm_is_zone_device_page(struct page *page);
-
struct kvm_irq_ack_notifier {
struct hlist_node link;
unsigned gsi;
@@ -2382,12 +2425,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
}
#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */
-typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data);
-
-int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
- uintptr_t data, const char *name,
- struct task_struct **thread_ptr);
-
#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
{
@@ -2461,11 +2498,13 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
#ifdef CONFIG_KVM_PRIVATE_MEM
int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
- gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+ gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
+ int *max_order);
#else
static inline int kvm_gmem_get_pfn(struct kvm *kvm,
struct kvm_memory_slot *slot, gfn_t gfn,
- kvm_pfn_t *pfn, int *max_order)
+ kvm_pfn_t *pfn, struct page **page,
+ int *max_order)
{
KVM_BUG_ON(1, kvm);
return -EIO;
diff --git a/include/linux/mman.h b/include/linux/mman.h
index bcb201ab7a41..a842783ffa62 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -2,6 +2,7 @@
#ifndef _LINUX_MMAN_H
#define _LINUX_MMAN_H
+#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/percpu_counter.h>
@@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages)
#endif
#ifndef arch_calc_vm_flag_bits
-#define arch_calc_vm_flag_bits(flags) 0
+#define arch_calc_vm_flag_bits(file, flags) 0
#endif
#ifndef arch_validate_prot
@@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
* Combine the mmap "flags" argument into "vm_flags" used internally.
*/
static inline unsigned long
-calc_vm_flag_bits(unsigned long flags)
+calc_vm_flag_bits(struct file *file, unsigned long flags)
{
return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) |
_calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) |
_calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) |
_calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) |
- arch_calc_vm_flag_bits(flags);
+ arch_calc_vm_flag_bits(file, flags);
}
unsigned long vm_commit_limit(void);
@@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void)
*
* d) mmap(PROT_READ | PROT_EXEC)
* mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
*/
-static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags)
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
{
+ /* If MDWE is disabled, we have nothing to deny. */
if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
return false;
- if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
+ /* If the new VMA is not executable, we have nothing to deny. */
+ if (!(new & VM_EXEC))
+ return false;
+
+ /* Under MDWE we do not accept newly writably executable VMAs... */
+ if (new & VM_WRITE)
return true;
- if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
+ /* ...nor previously non-executable VMAs becoming executable. */
+ if (!(old & VM_EXEC))
return true;
return false;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 17506e4a2835..80bc5640bb60 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -458,9 +458,7 @@ struct lru_gen_folio {
enum {
MM_LEAF_TOTAL, /* total leaf entries */
- MM_LEAF_OLD, /* old leaf entries */
MM_LEAF_YOUNG, /* young leaf entries */
- MM_NONLEAF_TOTAL, /* total non-leaf entries */
MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */
MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */
NR_MM_STATS
@@ -557,7 +555,7 @@ struct lru_gen_memcg {
void lru_gen_init_pgdat(struct pglist_data *pgdat);
void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
void lru_gen_init_memcg(struct mem_cgroup *memcg);
void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
{
}
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
{
+ return false;
}
static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
@@ -824,6 +823,7 @@ struct zone {
unsigned long watermark_boost;
unsigned long nr_reserved_highatomic;
+ unsigned long nr_free_highatomic;
/*
* We don't know if the memory that we're going to allocate will be
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index b0dd9b1eef4f..3982fea79919 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -32,7 +32,8 @@ typedef struct {
struct auth_domain *dom; /* auth_domain for localio */
} nfs_uuid_t;
-void nfs_uuid_begin(nfs_uuid_t *);
+void nfs_uuid_init(nfs_uuid_t *);
+bool nfs_uuid_begin(nfs_uuid_t *);
void nfs_uuid_end(nfs_uuid_t *);
void nfs_uuid_is_local(const uuid_t *, struct list_head *,
struct net *, struct auth_domain *, struct module *);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1b3a76710487..cc839e4365c1 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \
} \
static __always_inline void __folio_set_##fname(struct folio *folio) \
{ \
+ if (folio_test_##fname(folio)) \
+ return; \
VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \
folio); \
folio->page.page_type = (unsigned int)PGTY_##lname << 24; \
} \
static __always_inline void __folio_clear_##fname(struct folio *folio) \
{ \
+ if (folio->page.page_type == UINT_MAX) \
+ return; \
VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \
folio->page.page_type = UINT_MAX; \
}
@@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page) \
} \
static __always_inline void __SetPage##uname(struct page *page) \
{ \
+ if (Page##uname(page)) \
+ return; \
VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \
page->page_type = (unsigned int)PGTY_##lname << 24; \
} \
static __always_inline void __ClearPage##uname(struct page *page) \
{ \
+ if (page->page_type == UINT_MAX) \
+ return; \
VM_BUG_ON_PAGE(!Page##uname(page), page); \
page->page_type = UINT_MAX; \
}
diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h
index 9e9f528b1370..2f20281d4ad4 100644
--- a/include/linux/soc/qcom/llcc-qcom.h
+++ b/include/linux/soc/qcom/llcc-qcom.h
@@ -125,6 +125,7 @@ struct llcc_edac_reg_offset {
* @num_banks: Number of llcc banks
* @bitmap: Bit map to track the active slice ids
* @ecc_irq: interrupt for llcc cache error detection and reporting
+ * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation
* @version: Indicates the LLCC version
*/
struct llcc_drv_data {
@@ -139,6 +140,7 @@ struct llcc_drv_data {
u32 num_banks;
unsigned long *bitmap;
int ecc_irq;
+ bool ecc_irq_configured;
u32 version;
};
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ca533b478c21..f3e0ac20c2e8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -335,6 +335,7 @@ struct swap_info_struct {
* list.
*/
struct work_struct discard_work; /* discard worker */
+ struct work_struct reclaim_work; /* reclaim worker */
struct list_head discard_clusters; /* discard clusters list */
struct plist_node avail_lists[]; /*
* entries in swap_avail_heads, one
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 72744638c5b0..99c9c5a7252a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
if (tick_nohz_full_enabled())
tick_nohz_dep_set_task(tsk, bit);
}
+
static inline void tick_dep_clear_task(struct task_struct *tsk,
enum tick_dep_bits bit)
{
if (tick_nohz_full_enabled())
tick_nohz_dep_clear_task(tsk, bit);
}
+
+static inline void tick_dep_init_task(struct task_struct *tsk)
+{
+ atomic_set(&tsk->tick_dep_mask, 0);
+}
+
static inline void tick_dep_set_signal(struct task_struct *tsk,
enum tick_dep_bits bit)
{
@@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
enum tick_dep_bits bit) { }
static inline void tick_dep_clear_task(struct task_struct *tsk,
enum tick_dep_bits bit) { }
+static inline void tick_dep_init_task(struct task_struct *tsk) { }
static inline void tick_dep_set_signal(struct task_struct *tsk,
enum tick_dep_bits bit) { }
static inline void tick_dep_clear_signal(struct signal_struct *signal,
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 39c7cf82b0c2..43844510d5d0 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -38,6 +38,7 @@
#else
#define can_do_masked_user_access() 0
#define masked_user_access_begin(src) NULL
+ #define mask_user_address(src) (src)
#endif
/*
@@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
might_fault();
- if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+ if (should_fail_usercopy())
+ goto fail;
+ if (can_do_masked_user_access())
+ from = mask_user_address(from);
+ else {
+ if (!access_ok(from, n))
+ goto fail;
/*
* Ensure that bad access_ok() speculation will not
* lead to nasty side effects *after* the copy is
* finished:
*/
barrier_nospec();
- instrument_copy_from_user_before(to, from, n);
- res = raw_copy_from_user(to, from, n);
- instrument_copy_from_user_after(to, from, n, res);
}
- if (unlikely(res))
- memset(to + (n - res), 0, res);
+ instrument_copy_from_user_before(to, from, n);
+ res = raw_copy_from_user(to, from, n);
+ instrument_copy_from_user_after(to, from, n, res);
+ if (likely(!res))
+ return 0;
+fail:
+ memset(to + (n - res), 0, res);
return res;
}
extern __must_check unsigned long
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 3625096d5f85..7183e5aca282 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty
long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+ bool override_rlimit);
void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type);
bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9fc6ce15c499..cb40f1a1d081 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
extern void dup_userfaultfd_complete(struct list_head *);
+void dup_userfaultfd_fail(struct list_head *);
extern void mremap_userfaultfd_prep(struct vm_area_struct *,
struct vm_userfaultfd_ctx *);
@@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l)
{
}
+static inline void dup_userfaultfd_fail(struct list_head *l)
+{
+}
+
static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
struct vm_userfaultfd_ctx *ctx)
{
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 69ec1eb41a09..941dc62f3027 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6130,6 +6130,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
struct wiphy_delayed_work *dwork);
/**
+ * wiphy_delayed_work_pending - Find out whether a wiphy delayable
+ * work item is currently pending.
+ *
+ * @wiphy: the wiphy, for debug purposes
+ * @dwork: the delayed work in question
+ *
+ * Return: true if timer is pending, false otherwise
+ *
+ * How wiphy_delayed_work_queue() works is by setting a timer which
+ * when it expires calls wiphy_work_queue() to queue the wiphy work.
+ * Because wiphy_delayed_work_queue() uses mod_timer(), if it is
+ * called twice and the second call happens before the first call
+ * deadline, the work will rescheduled for the second deadline and
+ * won't run before that.
+ *
+ * wiphy_delayed_work_pending() can be used to detect if calling
+ * wiphy_work_delayed_work_queue() would start a new work schedule
+ * or delayed a previous one. As seen below it cannot be used to
+ * detect precisely if the work has finished to execute nor if it
+ * is currently executing.
+ *
+ * CPU0 CPU1
+ * wiphy_delayed_work_queue(wk)
+ * mod_timer(wk->timer)
+ * wiphy_delayed_work_pending(wk) -> true
+ *
+ * [...]
+ * expire_timers(wk->timer)
+ * detach_timer(wk->timer)
+ * wiphy_delayed_work_pending(wk) -> false
+ * wk->timer->function() |
+ * wiphy_work_queue(wk) | delayed work pending
+ * list_add_tail() | returns false but
+ * queue_work(cfg80211_wiphy_work) | wk->func() has not
+ * | been run yet
+ * [...] |
+ * cfg80211_wiphy_work() |
+ * wk->func() V
+ *
+ */
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+ struct wiphy_delayed_work *dwork);
+
+/**
* enum ieee80211_ap_reg_power - regulatory power for an Access Point
*
* @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 02fbc036f34e..813e163ce27c 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -24,25 +24,27 @@
* struct ieee80211_radiotap_header - base radiotap header
*/
struct ieee80211_radiotap_header {
- /**
- * @it_version: radiotap version, always 0
- */
- uint8_t it_version;
-
- /**
- * @it_pad: padding (or alignment)
- */
- uint8_t it_pad;
-
- /**
- * @it_len: overall radiotap header length
- */
- __le16 it_len;
-
- /**
- * @it_present: (first) present word
- */
- __le32 it_present;
+ __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed,
+ /**
+ * @it_version: radiotap version, always 0
+ */
+ uint8_t it_version;
+
+ /**
+ * @it_pad: padding (or alignment)
+ */
+ uint8_t it_pad;
+
+ /**
+ * @it_len: overall radiotap header length
+ */
+ __le16 it_len;
+
+ /**
+ * @it_present: (first) present word
+ */
+ __le32 it_present;
+ );
/**
* @it_optional: all remaining presence bitmaps
@@ -50,6 +52,9 @@ struct ieee80211_radiotap_header {
__le32 it_optional[];
} __packed;
+static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed),
+ "struct member likely outside of __struct_group()");
+
/* version is always 0 */
#define PKTHDR_RADIOTAP_VERSION 0
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6194fbb564c6..6a070478254d 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
memset(fl4, 0, sizeof(*fl4));
if (oif) {
- fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+ fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif);
/* Legacy VRF/l3mdev use case */
fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
}
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 91ae20cb7648..066a3ea33b12 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1103,6 +1103,7 @@ struct nft_rule_blob {
* @name: name of the chain
* @udlen: user data length
* @udata: user data in the chain
+ * @rcu_head: rcu head for deferred release
* @blob_next: rule blob pointer to the next in the chain
*/
struct nft_chain {
@@ -1120,6 +1121,7 @@ struct nft_chain {
char *name;
u16 udlen;
u8 *udata;
+ struct rcu_head rcu_head;
/* Only used during control plane commit phase: */
struct nft_rule_blob *blob_next;
@@ -1263,6 +1265,7 @@ static inline void nft_use_inc_restore(u32 *use)
* @sets: sets in the table
* @objects: stateful objects in the table
* @flowtables: flow tables in the table
+ * @net: netnamespace this table belongs to
* @hgenerator: handle generator state
* @handle: table handle
* @use: number of chain references to this table
@@ -1282,6 +1285,7 @@ struct nft_table {
struct list_head sets;
struct list_head objects;
struct list_head flowtables;
+ possible_net_t net;
u64 hgenerator;
u64 handle;
u32 use;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 450c44c83a5d..a0aed1a428a1 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -331,7 +331,11 @@ enum yfs_cm_operation {
EM(afs_edit_dir_delete, "delete") \
EM(afs_edit_dir_delete_error, "d_err ") \
EM(afs_edit_dir_delete_inval, "d_invl") \
- E_(afs_edit_dir_delete_noent, "d_nent")
+ EM(afs_edit_dir_delete_noent, "d_nent") \
+ EM(afs_edit_dir_update_dd, "u_ddot") \
+ EM(afs_edit_dir_update_error, "u_fail") \
+ EM(afs_edit_dir_update_inval, "u_invl") \
+ E_(afs_edit_dir_update_nodd, "u_nodd")
#define afs_edit_dir_reasons \
EM(afs_edit_dir_for_create, "Create") \
@@ -340,6 +344,7 @@ enum yfs_cm_operation {
EM(afs_edit_dir_for_rename_0, "Renam0") \
EM(afs_edit_dir_for_rename_1, "Renam1") \
EM(afs_edit_dir_for_rename_2, "Renam2") \
+ EM(afs_edit_dir_for_rename_sub, "RnmSub") \
EM(afs_edit_dir_for_rmdir, "RmDir ") \
EM(afs_edit_dir_for_silly_0, "S_Ren0") \
EM(afs_edit_dir_for_silly_1, "S_Ren1") \
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 74e40d5d4af4..fc7d0f8ff078 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -236,6 +236,41 @@ TRACE_EVENT(kvm_mmio,
__entry->len, __entry->gpa, __entry->val)
);
+#define KVM_TRACE_IOCSR_READ_UNSATISFIED 0
+#define KVM_TRACE_IOCSR_READ 1
+#define KVM_TRACE_IOCSR_WRITE 2
+
+#define kvm_trace_symbol_iocsr \
+ { KVM_TRACE_IOCSR_READ_UNSATISFIED, "unsatisfied-read" }, \
+ { KVM_TRACE_IOCSR_READ, "read" }, \
+ { KVM_TRACE_IOCSR_WRITE, "write" }
+
+TRACE_EVENT(kvm_iocsr,
+ TP_PROTO(int type, int len, u64 gpa, void *val),
+ TP_ARGS(type, len, gpa, val),
+
+ TP_STRUCT__entry(
+ __field( u32, type )
+ __field( u32, len )
+ __field( u64, gpa )
+ __field( u64, val )
+ ),
+
+ TP_fast_assign(
+ __entry->type = type;
+ __entry->len = len;
+ __entry->gpa = gpa;
+ __entry->val = 0;
+ if (val)
+ memcpy(&__entry->val, val,
+ min_t(u32, sizeof(__entry->val), len));
+ ),
+
+ TP_printk("iocsr %s len %u gpa 0x%llx val 0x%llx",
+ __print_symbolic(__entry->type, kvm_trace_symbol_iocsr),
+ __entry->len, __entry->gpa, __entry->val)
+);
+
#define kvm_fpu_load_symbol \
{0, "unload"}, \
{1, "load"}
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a1b126a6b0d7..cc22596c7250 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -287,6 +287,7 @@
EM(rxrpc_call_see_input, "SEE input ") \
EM(rxrpc_call_see_release, "SEE release ") \
EM(rxrpc_call_see_userid_exists, "SEE u-exists") \
+ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \
E_(rxrpc_call_see_zap, "SEE zap ")
#define rxrpc_txqueue_traces \
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index b9935988da5c..a920cf8934dc 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -450,6 +450,7 @@ typedef struct elf64_shdr {
#define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */
#define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */
#define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */
+#define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */
#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */
#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */
#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 637efc055145..502ea63b5d2e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1158,7 +1158,15 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME
KVM_DEV_TYPE_RISCV_AIA,
#define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA
+ KVM_DEV_TYPE_LOONGARCH_IPI,
+#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI
+ KVM_DEV_TYPE_LOONGARCH_EIOINTC,
+#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC
+ KVM_DEV_TYPE_LOONGARCH_PCHPIC,
+#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC
+
KVM_DEV_TYPE_MAX,
+
};
struct kvm_vfio_spapr_tce {
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 35791791a879..cefd656ebf43 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -230,7 +230,7 @@ struct prctl_mm_map {
# define PR_PAC_APDBKEY (1UL << 3)
# define PR_PAC_APGAKEY (1UL << 4)
-/* Tagged user address controls for arm64 */
+/* Tagged user address controls for arm64 and RISC-V */
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
@@ -244,6 +244,9 @@ struct prctl_mm_map {
# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
/* Unused; kept only for source compatibility */
# define PR_MTE_TCF_SHIFT 1
+/* RISC-V pointer masking tag length */
+# define PR_PMLEN_SHIFT 24
+# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
index 42a40ad3fb62..81759ff385e6 100644
--- a/include/uapi/linux/psci.h
+++ b/include/uapi/linux/psci.h
@@ -59,6 +59,7 @@
#define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18)
#define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19)
#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20)
+#define PSCI_1_3_FN_SYSTEM_OFF2 PSCI_0_2_FN(21)
#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12)
#define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13)
@@ -68,6 +69,7 @@
#define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18)
#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20)
+#define PSCI_1_3_FN64_SYSTEM_OFF2 PSCI_0_2_FN64(21)
/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
@@ -100,6 +102,9 @@
#define PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET 0
#define PSCI_1_1_RESET_TYPE_VENDOR_START 0x80000000U
+/* PSCI v1.3 hibernate type for SYSTEM_OFF2 */
+#define PSCI_1_3_OFF_TYPE_HIBERNATE_OFF BIT(0)
+
/* PSCI version decoding (independent of PSCI version) */
#define PSCI_VERSION_MAJOR_SHIFT 16
#define PSCI_VERSION_MINOR_MASK \