Merge tag 'loongarch-kvm-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.8

1. Optimization for memslot hugepage checking.
2. Cleanup and fix some HW/SW timer issues.
3. Add LSX/LASX (128bit/256bit SIMD) support.

73 files changed, 416 insertions, 208 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index afeed6e72049..1216d72c650f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -542,6 +542,7 @@ int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_init_power(struct acpi_device *device);
 int acpi_device_fix_up_power(struct acpi_device *device);
 void acpi_device_fix_up_power_extended(struct acpi_device *adev);
+void acpi_device_fix_up_power_children(struct acpi_device *adev);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 int acpi_device_update_power(struct acpi_device *device, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 995513fa2690..0655aa5b57b2 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
  */
 static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
 {
-	return !atomic_read(&lock.val);
+	return !lock.val.counter;
 }
 
 /**
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3..006b5c977ad7 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state);
 
 #define DRM_PLANE_COMMIT_ACTIVE_ONLY			BIT(0)
 #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET	BIT(1)
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index bdfafc4a7705..c7a0594bdab1 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 
 #ifndef __DRM_GPUVM_H__
 #define __DRM_GPUVM_H__
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e697..2a1d01e5b56b 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
+struct drm_file;
 
 /* core prime functions */
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
 /* helper functions for exporting */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f41..4db54e928b36 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,7 +15,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
-#include <linux/fw_table.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -25,22 +24,13 @@ struct irq_domain_ops;
 #endif
 #include <acpi/acpi.h>
 
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
-
 #ifdef	CONFIG_ACPI
 
 #include <linux/list.h>
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/fw_table.h>
 
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
@@ -48,6 +38,16 @@ struct irq_domain_ops;
 #include <acpi/acpi_io.h>
 #include <asm/acpi.h>
 
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
 static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 {
 	return adev ? adev->handle : NULL;
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f84606..6ad02ad9c7b4 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -70,6 +70,10 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
 
 	u32	max_freq;
 	u32	min_freq;
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 1abedb5b2e48..3d0fde57ba90 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
+extern struct bus_type ffa_bus_type;
+
 /* FFA transport related */
 struct ffa_partition_info {
 	u16 id;
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
index 2580e05a8ab6..004b38a538ff 100644
--- a/include/linux/blk-pm.h
+++ b/include/linux/blk-pm.h
@@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q);
 extern void blk_post_runtime_suspend(struct request_queue *q, int err);
 extern void blk_pre_runtime_resume(struct request_queue *q);
 extern void blk_post_runtime_resume(struct request_queue *q);
-extern void blk_set_runtime_active(struct request_queue *q);
 #else
 static inline void blk_pm_runtime_init(struct request_queue *q,
 				       struct device *dev) {}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..b29ebd53417d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,9 +49,10 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
@@ -69,6 +70,7 @@ struct block_device {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	bool			bd_ro_warned;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4825d3cdb29..cff5bb08820e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -56,7 +56,7 @@ extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
 extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
-extern bool bpf_global_ma_set, bpf_global_percpu_ma_set;
+extern bool bpf_global_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
@@ -909,10 +909,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static bool bpf_is_ldimm64(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
 static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
 {
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
+	return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
 }
 
 struct bpf_prog_ops {
@@ -3171,6 +3175,9 @@ enum bpf_text_poke_type {
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old);
+
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
 int bpf_arch_text_invalidate(void *dst, size_t len);
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 24213a99cc79..aa4d19d0bc94 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -301,6 +301,17 @@ struct bpf_func_state {
 	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
+	/* For callback calling functions that limit number of possible
+	 * callback executions (e.g. bpf_loop) keeps track of current
+	 * simulated iteration number.
+	 * Value in frame N refers to number of times callback with frame
+	 * N+1 was simulated, e.g. for the following call:
+	 *
+	 *   bpf_loop(..., fn, ...); | suppose current frame is N
+	 *                           | fn would be simulated in frame N+1
+	 *                           | number of simulations is tracked in frame N
+	 */
+	u32 callback_depth;
 
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
@@ -400,6 +411,7 @@ struct bpf_verifier_state {
 	struct bpf_idx_pair *jmp_history;
 	u32 jmp_history_cnt;
 	u32 dfs_depth;
+	u32 callback_unroll_depth;
 };
 
 #define bpf_get_spilled_reg(slot, frame, mask)				\
@@ -511,6 +523,10 @@ struct bpf_insn_aux_data {
 	 * this instruction, regardless of any heuristics
 	 */
 	bool force_checkpoint;
+	/* true if instruction is a call to a helper function that
+	 * accepts callback function as a parameter.
+	 */
+	bool calls_callback;
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/include/linux/closure.h b/include/linux/closure.h
index de7bb47d8a46..c554c6a08768 100644
--- a/include/linux/closure.h
+++ b/include/linux/closure.h
@@ -104,7 +104,7 @@
 
 struct closure;
 struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
+typedef void (closure_fn) (struct work_struct *);
 extern struct dentry *bcache_debug;
 
 struct closure_waitlist {
@@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl)
 		INIT_WORK(&cl->work, cl->work.func);
 		BUG_ON(!queue_work(wq, &cl->work));
 	} else
-		cl->fn(cl);
+		cl->fn(&cl->work);
 }
 
 /**
@@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list)
 	__closure_wake_up(list);
 }
 
+#define CLOSURE_CALLBACK(name)	void name(struct work_struct *ws)
+#define closure_type(name, type, member)				\
+	struct closure *cl = container_of(ws, struct closure, work);	\
+	type *name = container_of(cl, type, member)
+
 /**
  * continue_at - jump to another function with barrier
  *
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d305db70674b..efc0c0b07efb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -195,6 +195,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
+	CPUHP_AP_HRTIMERS_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
diff --git a/include/linux/cred.h b/include/linux/cred.h
index af8d353a4b86..2976f534a7a3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -109,14 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  * same context as task->real_cred.
  */
 struct cred {
-	atomic_t	usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_t	subscribers;	/* number of processes subscribed */
-	void		*put_addr;
-	unsigned	magic;
-#define CRED_MAGIC	0x43736564
-#define CRED_MAGIC_DEAD	0x44656144
-#endif
+	atomic_long_t	usage;
 	kuid_t		uid;		/* real UID of the task */
 	kgid_t		gid;		/* real GID of the task */
 	kuid_t		suid;		/* saved UID of the task */
@@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
-				     const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
-				    const char *file, unsigned line)
-{
-	if (unlikely(creds_are_invalid(cred)))
-		__invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred)				\
-do {							\
-	__validate_creds((cred), __FILE__, __LINE__);	\
-} while(0)
-
-#define validate_process_creds()				\
-do {								\
-	__validate_process_creds(current, __FILE__, __LINE__);	\
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
@@ -229,7 +182,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
  */
 static inline struct cred *get_new_cred_many(struct cred *cred, int nr)
 {
-	atomic_add(nr, &cred->usage);
+	atomic_long_add(nr, &cred->usage);
 	return cred;
 }
 
@@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return cred;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return get_new_cred_many(nonconst_cred, nr);
 }
@@ -288,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return NULL;
-	if (!atomic_inc_not_zero(&nonconst_cred->usage))
+	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return cred;
 }
@@ -312,8 +263,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr)
 	struct cred *cred = (struct cred *) _cred;
 
 	if (cred) {
-		validate_creds(cred);
-		if (atomic_sub_and_test(nr, &cred->usage))
+		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
 }
diff --git a/include/linux/damon.h b/include/linux/damon.h
index ab2f17d9926b..e00ddf1ed39c 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -559,6 +559,8 @@ struct damon_ctx {
 	 * update
 	 */
 	unsigned long next_ops_update_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
 
 /* public: */
 	struct task_struct *kdamond;
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c7..c9c65b132c0f 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos);