Merge branch 'next' into for-linus

Prepare input updates for 7.1 merge window.

15 files changed, 310 insertions, 154 deletions

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 295c94a3ccc1..9aff61e7b8f2 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -32,6 +32,7 @@ mandatory-y += irq_work.h
 mandatory-y += kdebug.h
 mandatory-y += kmap_size.h
 mandatory-y += kprobes.h
+mandatory-y += kvm_types.h
 mandatory-y += linkage.h
 mandatory-y += local.h
 mandatory-y += local64.h
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 100d24b02e52..f22ccfc0df98 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -10,7 +10,7 @@
 #include <linux/types.h>
 
 typedef struct {
-	s64 counter;
+	s64 __aligned(sizeof(s64)) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
diff --git a/include/asm-generic/audit_change_attr.h b/include/asm-generic/audit_change_attr.h
index cc840537885f..ddd90bbe40df 100644
--- a/include/asm-generic/audit_change_attr.h
+++ b/include/asm-generic/audit_change_attr.h
@@ -26,6 +26,9 @@ __NR_fremovexattr,
 __NR_fchownat,
 __NR_fchmodat,
 #endif
+#ifdef __NR_fchmodat2
+__NR_fchmodat2,
+#endif
 #ifdef __NR_chown32
 __NR_chown32,
 __NR_fchown32,
diff --git a/include/asm-generic/audit_read.h b/include/asm-generic/audit_read.h
index 7bb7b5a83ae2..fb9991f53fb6 100644
--- a/include/asm-generic/audit_read.h
+++ b/include/asm-generic/audit_read.h
@@ -4,9 +4,15 @@ __NR_readlink,
 #endif
 __NR_quotactl,
 __NR_listxattr,
+#ifdef __NR_listxattrat
+__NR_listxattrat,
+#endif
 __NR_llistxattr,
 __NR_flistxattr,
 __NR_getxattr,
+#ifdef __NR_getxattrat
+__NR_getxattrat,
+#endif
 __NR_lgetxattr,
 __NR_fgetxattr,
 #ifdef __NR_readlinkat
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 387720933973..09e8eccee8ed 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -13,10 +13,19 @@
 #define BUGFLAG_ONCE		(1 << 1)
 #define BUGFLAG_DONE		(1 << 2)
 #define BUGFLAG_NO_CUT_HERE	(1 << 3)	/* CUT_HERE already sent */
+#define BUGFLAG_ARGS		(1 << 4)
 #define BUGFLAG_TAINT(taint)	((taint) << 8)
 #define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
 #endif
 
+#ifndef WARN_CONDITION_STR
+#ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED
+# define WARN_CONDITION_STR(cond_str) "[" cond_str "] "
+#else
+# define WARN_CONDITION_STR(cond_str)
+#endif
+#endif /* WARN_CONDITION_STR */
+
 #ifndef __ASSEMBLY__
 #include <linux/panic.h>
 #include <linux/printk.h>
@@ -29,19 +38,20 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 
 #ifdef CONFIG_BUG
 
-#ifdef CONFIG_GENERIC_BUG
-struct bug_entry {
 #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-	unsigned long	bug_addr;
+#define BUG_REL(type, name) type name
 #else
-	signed int	bug_addr_disp;
+#define BUG_REL(type, name) signed int name##_disp
 #endif
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-	const char	*file;
-#else
-	signed int	file_disp;
+
+#ifdef CONFIG_GENERIC_BUG
+struct bug_entry {
+	BUG_REL(unsigned long, bug_addr);
+#ifdef HAVE_ARCH_BUG_FORMAT
+	BUG_REL(const char *, format);
 #endif
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+	BUG_REL(const char *, file);
 	unsigned short	line;
 #endif
 	unsigned short	flags;
@@ -92,28 +102,50 @@ void warn_slowpath_fmt(const char *file, const int line, unsigned taint,
 		       const char *fmt, ...);
 extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
 
-#ifndef __WARN_FLAGS
-#define __WARN()		__WARN_printf(TAINT_WARN, NULL)
+#ifdef __WARN_FLAGS
+#define __WARN()		__WARN_FLAGS("", BUGFLAG_TAINT(TAINT_WARN))
+
+#ifndef WARN_ON
+#define WARN_ON(condition) ({						\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_FLAGS(#condition,				\
+			     BUGFLAG_TAINT(TAINT_WARN));		\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+
+#ifndef WARN_ON_ONCE
+#define WARN_ON_ONCE(condition) ({					\
+	int __ret_warn_on = !!(condition);				\
+	if (unlikely(__ret_warn_on))					\
+		__WARN_FLAGS(#condition,				\
+			     BUGFLAG_ONCE |				\
+			     BUGFLAG_TAINT(TAINT_WARN));		\
+	unlikely(__ret_warn_on);					\
+})
+#endif
+#endif /* __WARN_FLAGS */
+
+#if defined(__WARN_FLAGS) && !defined(__WARN_printf)
 #define __WARN_printf(taint, arg...) do {				\
 		instrumentation_begin();				\
-		warn_slowpath_fmt(__FILE__, __LINE__, taint, arg);	\
+		__warn_printk(arg);					\
+		__WARN_FLAGS("", BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
 		instrumentation_end();					\
 	} while (0)
-#else
-#define __WARN()		__WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN))
+#endif
+
+#ifndef __WARN_printf
 #define __WARN_printf(taint, arg...) do {				\
 		instrumentation_begin();				\
-		__warn_printk(arg);					\
-		__WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
+		warn_slowpath_fmt(__FILE__, __LINE__, taint, arg);	\
 		instrumentation_end();					\
 	} while (0)
-#define WARN_ON_ONCE(condition) ({				\
-	int __ret_warn_on = !!(condition);			\
-	if (unlikely(__ret_warn_on))				\
-		__WARN_FLAGS(BUGFLAG_ONCE |			\
-			     BUGFLAG_TAINT(TAINT_WARN));	\
-	unlikely(__ret_warn_on);				\
-})
+#endif
+
+#ifndef __WARN
+#define __WARN()		__WARN_printf(TAINT_WARN, NULL)
 #endif
 
 /* used internally by panic.c */
@@ -148,8 +180,10 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
 	DO_ONCE_LITE_IF(condition, WARN_ON, 1)
 #endif
 
+#ifndef WARN_ONCE
 #define WARN_ONCE(condition, format...)				\
 	DO_ONCE_LITE_IF(condition, WARN, 1, format)
+#endif
 
 #define WARN_TAINT_ONCE(condition, taint, format...)		\
 	DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format)
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index dcb8727f2b82..e1a2e1b7c8e7 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -97,14 +97,6 @@ static inline int huge_pte_none(pte_t pte)
 }
 #endif
 
-/* Please refer to comments above pte_none_mostly() for the usage */
-#ifndef __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY
-static inline int huge_pte_none_mostly(pte_t pte)
-{
-	return huge_pte_none(pte) || is_pte_marker(pte);
-}
-#endif
-
 #ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 		unsigned long addr, pte_t *ptep)
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index 64ba6bc807d9..d37b68238c97 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -62,6 +62,8 @@ struct ms_hyperv_info {
 		};
 	};
 	u64 shared_gpa_boundary;
+	bool msi_ext_dest_id;
+	bool confidential_vmbus_available;
 };
 extern struct ms_hyperv_info ms_hyperv;
 extern bool hv_nested;
@@ -124,10 +126,12 @@ static inline unsigned int hv_repcomp(u64 status)
 
 /*
  * Rep hypercalls. Callers of this functions are supposed to ensure that
- * rep_count and varhead_size comply with Hyper-V hypercall definition.
+ * rep_count, varhead_size, and rep_start comply with Hyper-V hypercall
+ * definition.
  */
-static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
-				      void *input, void *output)
+static inline u64 hv_do_rep_hypercall_ex(u16 code, u16 rep_count,
+					 u16 varhead_size, u16 rep_start,
+					 void *input, void *output)
 {
 	u64 control = code;
 	u64 status;
@@ -135,6 +139,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 
 	control |= (u64)varhead_size << HV_HYPERCALL_VARHEAD_OFFSET;
 	control |= (u64)rep_count << HV_HYPERCALL_REP_COMP_OFFSET;
+	control |= (u64)rep_start << HV_HYPERCALL_REP_START_OFFSET;
 
 	do {
 		status = hv_do_hypercall(control, input, output);
@@ -152,6 +157,14 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 	return status;
 }
 
+/* For the typical case where rep_start is 0 */
+static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
+				      void *input, void *output)
+{
+	return hv_do_rep_hypercall_ex(code, rep_count, varhead_size, 0,
+				      input, output);
+}
+
 /* Generate the guest OS identifier as described in the Hyper-V TLFS */
 static inline u64 hv_generate_guest_id(u64 kernel_version)
 {
@@ -163,46 +176,6 @@ static inline u64 hv_generate_guest_id(u64 kernel_version)
 	return guest_id;
 }
 
-#if IS_ENABLED(CONFIG_HYPERV_VMBUS)
-/* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
-{
-	/*
-	 * On crash we're reading some other CPU's message page and we need
-	 * to be careful: this other CPU may already had cleared the header
-	 * and the host may already had delivered some other message there.
-	 * In case we blindly write msg->header.message_type we're going
-	 * to lose it. We can still lose a message of the same type but
-	 * we count on the fact that there can only be one
-	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
-	 * on crash.
-	 */
-	if (cmpxchg(&msg->header.message_type, old_msg_type,
-		    HVMSG_NONE) != old_msg_type)
-		return;
-
-	/*
-	 * The cmxchg() above does an implicit memory barrier to
-	 * ensure the write to MessageType (ie set to
-	 * HVMSG_NONE) happens before we read the
-	 * MessagePending and EOMing. Otherwise, the EOMing
-	 * will not deliver any more messages since there is
-	 * no empty slot
-	 */
-	if (msg->header.message_flags.msg_pending) {
-		/*
-		 * This will cause message queue rescan to
-		 * possibly deliver another msg from the
-		 * hypervisor
-		 */
-		hv_set_msr(HV_MSR_EOM, 0);
-	}
-}
-
-extern int vmbus_interrupt;
-extern int vmbus_irq;
-#endif /* CONFIG_HYPERV_VMBUS */
-
 int hv_get_hypervisor_version(union hv_hypervisor_version_info *info);
 
 void hv_setup_vmbus_handler(void (*handler)(void));
@@ -336,6 +309,10 @@ bool hv_is_isolation_supported(void);
 bool hv_isolation_type_snp(void);
 u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
 u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
+void hv_enable_coco_interrupt(unsigned int cpu, unsigned int vector, bool set);
+void hv_para_set_sint_proxy(bool enable);
+u64 hv_para_get_synic_register(unsigned int reg);
+void hv_para_set_synic_register(unsigned int reg, u64 val);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
 void hv_setup_dma_ops(struct device *dev, bool coherent);
@@ -365,6 +342,9 @@ static inline bool hv_parent_partition(void)
 {
 	return hv_root_partition() || hv_l1vh_partition();
 }
+
+bool hv_result_needs_memory(u64 status);
+int hv_deposit_memory_node(int node, u64 partition_id, u64 status);
 int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
 int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
 int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
@@ -373,6 +353,11 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
 static inline bool hv_root_partition(void) { return false; }
 static inline bool hv_l1vh_partition(void) { return false; }
 static inline bool hv_parent_partition(void) { return false; }
+static inline bool hv_result_needs_memory(u64 status) { return false; }
+static inline int hv_deposit_memory_node(int node, u64 partition_id, u64 status)
+{
+	return -EOPNOTSUPP;
+}
 static inline int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
 {
 	return -EOPNOTSUPP;
@@ -387,6 +372,11 @@ static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u3
 }
 #endif /* CONFIG_MSHV_ROOT */
 
+static inline int hv_deposit_memory(u64 partition_id, u64 status)
+{
+	return hv_deposit_memory_node(NUMA_NO_NODE, partition_id, status);
+}
+
 #if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
 u8 __init get_vtl(void);
 #else
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 02aeca21479a..6628670bcb90 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_GENERIC_PERCPU_H_
 #define _ASM_GENERIC_PERCPU_H_
 
+#ifndef __ASSEMBLER__
+
 #include <linux/compiler.h>
 #include <linux/threads.h>
 #include <linux/percpu-defs.h>
@@ -557,4 +559,5 @@ do {									\
 	this_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 3c8ec3bfea44..57137d3ac159 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -18,8 +18,7 @@
  */
 static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 {
-	struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL &
-			~__GFP_HIGHMEM, 0);
+	struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL, 0);
 
 	if (!ptdesc)
 		return NULL;
@@ -28,6 +27,8 @@ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
 		return NULL;
 	}
 
+	ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
@@ -146,6 +147,10 @@ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long ad
 		pagetable_free(ptdesc);
 		return NULL;
 	}
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
@@ -172,13 +177,16 @@ static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	gfp &= ~__GFP_HIGHMEM;
 
 	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 
 	pagetable_pud_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
@@ -226,13 +234,16 @@ static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	gfp &= ~__GFP_HIGHMEM;
 
 	ptdesc = pagetable_alloc_noprof(gfp, 0);
 	if (!ptdesc)
 		return NULL;
 
 	pagetable_p4d_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __p4d_alloc_one(...)	alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
@@ -270,13 +281,16 @@ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order
 
 	if (mm == &init_mm)
 		gfp = GFP_PGTABLE_KERNEL;
-	gfp &= ~__GFP_HIGHMEM;
 
 	ptdesc = pagetable_alloc_noprof(gfp, order);
 	if (!ptdesc)
 		return NULL;
 
 	pagetable_pgd_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
 	return ptdesc_address(ptdesc);
 }
 #define __pgd_alloc(...)	alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
index 828966d4c281..0d85791efdf7 100644
--- a/include/asm-generic/pgtable_uffd.h
+++ b/include/asm-generic/pgtable_uffd.h
@@ -1,6 +1,23 @@
 #ifndef _ASM_GENERIC_PGTABLE_UFFD_H
 #define _ASM_GENERIC_PGTABLE_UFFD_H
 
+/*
+ * Some platforms can customize the uffd-wp bit, making it unavailable
+ * even if the architecture provides the resource.
+ * Adding this API allows architectures to add their own checks for the
+ * devices on which the kernel is running.
+ * Note: When overriding it, please make sure the
+ * CONFIG_HAVE_ARCH_USERFAULTFD_WP is part of this macro.
+ */
+#ifndef pgtable_supports_uffd_wp
+#define pgtable_supports_uffd_wp()	IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP)
+#endif
+
+static inline bool uffd_supports_wp_marker(void)
+{
+	return pgtable_supports_uffd_wp() && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP);
+}
+
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 static __always_inline int pte_uffd_wp(pte_t pte)
 {
diff --git a/include/asm-generic/rqspinlock.h b/include/asm-generic/rqspinlock.h
index 6d4244d643df..151d267a496b 100644
--- a/include/asm-generic/rqspinlock.h
+++ b/include/asm-generic/rqspinlock.h
@@ -28,7 +28,7 @@ struct rqspinlock {
  */
 struct bpf_res_spin_lock {
 	u32 val;
-};
+} __aligned(__alignof__(struct rqspinlock));
 
 struct qspinlock;
 #ifdef CONFIG_QUEUED_SPINLOCKS
@@ -129,8 +129,8 @@ dec:
 	 * <error> for lock B
 	 * release_held_lock_entry
 	 *
-	 * try_cmpxchg_acquire for lock A
 	 * grab_held_lock_entry
+	 * try_cmpxchg_acquire for lock A
 	 *
 	 * Lack of any ordering means reordering may occur such that dec, inc
 	 * are done before entry is overwritten. This permits a remote lock
@@ -139,13 +139,8 @@ dec:
 	 * CPU holds a lock it is attempting to acquire, leading to false ABBA
 	 * diagnosis).
 	 *
-	 * In case of unlock, we will always do a release on the lock word after
-	 * releasing the entry, ensuring that other CPUs cannot hold the lock
-	 * (and make conclusions about deadlocks) until the entry has been
-	 * cleared on the local CPU, preventing any anomalies. Reordering is
-	 * still possible there, but a remote CPU cannot observe a lock in our
-	 * table which it is already holding, since visibility entails our
-	 * release store for the said lock has not retired.
+	 * The case of unlock is treated differently due to NMI reentrancy, see
+	 * comments in res_spin_unlock.
 	 *
 	 * In theory we don't have a problem if the dec and WRITE_ONCE above get
 	 * reordered with each other, we either notice an empty NULL entry on
@@ -175,16 +170,28 @@ static __always_inline int res_spin_lock(rqspinlock_t *lock)
 {
 	int val = 0;
 
-	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) {
-		grab_held_lock_entry(lock);
+	/*
+	 * Grab the deadlock detection entry before doing the cmpxchg, so that
+	 * reentrancy due to NMIs between the succeeding cmpxchg and creation of
+	 * held lock entry can correctly detect an acquisition attempt in the
+	 * interrupted context.
+	 *
+	 * cmpxchg lock A
+	 * <NMI>
+	 * res_spin_lock(A) --> missed AA, leads to timeout
+	 * </NMI>
+	 * grab_held_lock_entry(A)
+	 */
+	grab_held_lock_entry(lock);
+
+	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
 		return 0;
-	}
 	return resilient_queued_spin_lock_slowpath(lock, val);
 }
 
 #else
 
-#define res_spin_lock(lock) resilient_tas_spin_lock(lock)
+#define res_spin_lock(lock) ({ grab_held_lock_entry(lock); resilient_tas_spin_lock(lock); })
 
 #endif /* CONFIG_QUEUED_SPINLOCKS */
 
@@ -192,28 +199,25 @@ static __always_inline void res_spin_unlock(rqspinlock_t *lock)
 {
 	struct rqspinlock_held *rqh = this_cpu_ptr(&rqspinlock_held_locks);
 
-	if (unlikely(rqh->cnt > RES_NR_HELD))
-		goto unlock;
-	WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL);
-unlock:
 	/*
-	 * Release barrier, ensures correct ordering. See release_held_lock_entry
-	 * for details.  Perform release store instead of queued_spin_unlock,
-	 * since we use this function for test-and-set fallback as well. When we
-	 * have CONFIG_QUEUED_SPINLOCKS=n, we clear the full 4-byte lockword.
+	 * Release barrier, ensures correct ordering. Perform release store
+	 * instead of queued_spin_unlock, since we use this function for the TAS
+	 * fallback as well. When we have CONFIG_QUEUED_SPINLOCKS=n, we clear
+	 * the full 4-byte lockword.
 	 *
-	 * Like release_held_lock_entry, we can do the release before the dec.
-	 * We simply care about not seeing the 'lock' in our table from a remote
-	 * CPU once the lock has been released, which doesn't rely on the dec.
+	 * Perform the smp_store_release before clearing the lock entry so that
+	 * NMIs landing in the unlock path can correctly detect AA issues. The
+	 * opposite order shown below may lead to missed AA checks:
 	 *
-	 * Unlike smp_wmb(), release is not a two way fence, hence it is
-	 * possible for a inc to move up and reorder with our clearing of the
-	 * entry. This isn't a problem however, as for a misdiagnosis of ABBA,
-	 * the remote CPU needs to hold this lock, which won't be released until
-	 * the store below is done, which would ensure the entry is overwritten
-	 * to NULL, etc.
+	 * WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL)
+	 * <NMI>
+	 * res_spin_lock(A) --> missed AA, leads to timeout
+	 * </NMI>
+	 * smp_store_release(A->locked, 0)
 	 */
 	smp_store_release(&lock->locked, 0);
+	if (likely(rqh->cnt <= RES_NR_HELD))
+		WRITE_ONCE(rqh->locks[rqh->cnt - 1], NULL);
 	this_cpu_dec(rqspinlock_held_locks.cnt);
 }
 
diff --git a/include/asm-generic/thread_info_tif.h b/include/asm-generic/thread_info_tif.h
index ee3793e9b1a4..da1610a78f92 100644
--- a/include/asm-generic/thread_info_tif.h
+++ b/include/asm-generic/thread_info_tif.h
@@ -45,4 +45,7 @@
 # define _TIF_RESTORE_SIGMASK	BIT(TIF_RESTORE_SIGMASK)
 #endif
 
+#define TIF_RSEQ		11	// Run RSEQ fast path
+#define _TIF_RSEQ		BIT(TIF_RSEQ)
+
 #endif /* _ASM_GENERIC_THREAD_INFO_TIF_H_ */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 1fff717cae51..4aeac0c3d3f0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -46,7 +46,8 @@
  *
  * The mmu_gather API consists of:
  *
- *  - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu()
+ *  - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() /
+ *    tlb_finish_mmu()
  *
  *    start and finish a mmu_gather
  *
@@ -212,7 +213,7 @@ struct mmu_table_batch {
 #define MAX_TABLE_BATCH		\
 	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
 
-#ifndef __HAVE_ARCH_TLB_REMOVE_TABLE
+#ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE
 static inline void __tlb_remove_table(void *table)
 {
 	struct ptdesc *ptdesc = (struct ptdesc *)table;
@@ -286,8 +287,7 @@ struct mmu_gather_batch {
  */
 #define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
 
-extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
-		bool delay_rmap, int page_size);
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size);
 bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
 		unsigned int nr_pages, bool delay_rmap);
 
@@ -364,6 +364,20 @@ struct mmu_gather {
 	unsigned int		vma_huge : 1;
 	unsigned int		vma_pfn  : 1;
 
+	/*
+	 * Did we unshare (unmap) any shared page tables? For now only
+	 * used for hugetlb PMD table sharing.
+	 */
+	unsigned int		unshared_tables : 1;
+
+	/*
+	 * Did we unshare any page tables such that they are now exclusive
+	 * and could get reused+modified by the new owner? When setting this
+	 * flag, "unshared_tables" will be set as well. For now only used
+	 * for hugetlb PMD table sharing.
+	 */
+	unsigned int		fully_unshared_tables : 1;
+
 	unsigned int		batch_count;
 
 #ifndef CONFIG_MMU_GATHER_NO_GATHER
@@ -400,6 +414,7 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	tlb->cleared_pmds = 0;
 	tlb->cleared_puds = 0;
 	tlb->cleared_p4ds = 0;
+	tlb->unshared_tables = 0;
 	/*
 	 * Do not reset mmu_gather::vma_* fields here, we do not
 	 * call into tlb_start_vma() again to set them if there is an
@@ -484,7 +499,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 	 * these bits.
 	 */
 	if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds ||
-	      tlb->cleared_puds || tlb->cleared_p4ds))
+	      tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables))
 		return;
 
 	tlb_flush(tlb);
@@ -494,7 +509,7 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 					struct page *page, int page_size)
 {
-	if (__tlb_remove_page_size(tlb, page, false, page_size))
+	if (__tlb_remove_page_size(tlb, page, page_size))
 		tlb_flush_mmu(tlb);
 }
 
@@ -773,6 +788,63 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
 }
 #endif
 
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt,
+					  unsigned long addr)
+{
+	/*
+	 * The caller must make sure that concurrent unsharing + exclusive
+	 * reuse is impossible until tlb_flush_unshared_tables() was called.
+	 */
+	VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt));
+	ptdesc_pmd_pts_dec(pt);
+
+	/* Clearing a PUD pointing at a PMD table with PMD leaves. */
+	tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE);
+
+	/*
+	 * If the page table is now exclusively owned, we fully unshared
+	 * a page table.
+	 */
+	if (!ptdesc_pmd_is_shared(pt))
+		tlb->fully_unshared_tables = true;
+	tlb->unshared_tables = true;
+}
+
+static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb)
+{
+	/*
+	 * As soon as the caller drops locks to allow for reuse of
+	 * previously-shared tables, these tables could get modified and
+	 * even reused outside of hugetlb context, so we have to make sure that
+	 * any page table walkers (incl. TLB, GUP-fast) are aware of that
+	 * change.
+	 *
+	 * Even if we are not fully unsharing a PMD table, we must
+	 * flush the TLB for the unsharer now.
+	 */
+	if (tlb->unshared_tables)
+		tlb_flush_mmu_tlbonly(tlb);
+
+	/*
+	 * Similarly, we must make sure that concurrent GUP-fast will not
+	 * walk previously-shared page tables that are getting modified+reused
+	 * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast.
+	 *
+	 * We only perform this when we are the last sharer of a page table,
+	 * as the IPI will reach all CPUs: any GUP-fast.
+	 *
+	 * Note that on configs where tlb_remove_table_sync_one() is a NOP,
+	 * the expectation is that the tlb_flush_mmu_tlbonly() would have issued
+	 * required IPIs already for us.
+	 */
+	if (tlb->fully_unshared_tables) {
+		tlb_remove_table_sync_one();
+		tlb->fully_unshared_tables = false;
+	}
+}
+#endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */
+
 #endif /* CONFIG_MMU */
 
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 4dbe715be65b..9865ba48c5b1 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -45,11 +45,7 @@
 #endif
 
 #ifndef cpumask_of_node
-  #ifdef CONFIG_NUMA
-    #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
-  #else
-    #define cpumask_of_node(node)	((void)(node), cpu_online_mask)
-  #endif
+#define cpumask_of_node(node)	((void)(node), cpu_online_mask)
 #endif
 #ifndef pcibus_to_node
 #define pcibus_to_node(bus)	((void)(bus), -1)
@@ -61,7 +57,7 @@
 				 cpumask_of_node(pcibus_to_node(bus)))
 #endif
 
-#endif	/* CONFIG_NUMA */
+#endif	/* !CONFIG_NUMA */
 
 #if !defined(CONFIG_NUMA) || !defined(CONFIG_HAVE_MEMORYLESS_NODES)
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index e04d56a5332e..1e1580febe4b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -87,39 +87,56 @@
 #define ALIGN_FUNCTION()  . = ALIGN(CONFIG_FUNCTION_ALIGNMENT)
 
 /*
- * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which
- * generates .data.identifier sections, which need to be pulled in with
- * .data. We don't want to pull in .data..other sections, which Linux
- * has defined. Same for text and bss.
+ * Support -ffunction-sections by matching .text and .text.*,
+ * but exclude '.text..*', .text.startup[.*], and .text.exit[.*].
  *
- * With LTO_CLANG, the linker also splits sections by default, so we need
- * these macros to combine the sections during the final link.
+ * .text.startup and .text.startup.* are matched later by INIT_TEXT, and
+ * .text.exit and .text.exit.* are matched later by EXIT_TEXT, so they must be
+ * explicitly excluded here.
  *
- * With AUTOFDO_CLANG and PROPELLER_CLANG, by default, the linker splits
- * text sections and regroups functions into subsections.
+ * Other .text.* sections that are typically grouped separately, such as
+ * .text.unlikely or .text.hot, must be matched explicitly before using
+ * TEXT_MAIN.
  *
- * RODATA_MAIN is not used because existing code already defines .rodata.x
- * sections to be brought in with rodata.
+ * NOTE: builds *with* and *without* -ffunction-sections are both supported by
+ * this single macro.  Even with -ffunction-sections, there may be some objects
+ * NOT compiled with the flag due to the use of a specific Makefile override
+ * like cflags-y or AUTOFDO_PROFILE_foo.o.  So this single catchall rule is
+ * needed to support mixed object builds.
+ *
+ * One implication is that functions named startup(), exit(), split(),
+ * unlikely(), hot(), and unknown() are not allowed in the kernel due to the
+ * ambiguity of their section names with -ffunction-sections.  For example,
+ * .text.startup could be __attribute__((constructor)) code in a *non*
+ * ffunction-sections object, which should be placed in .init.text; or it could
+ * be an actual function named startup() in an ffunction-sections object, which
+ * should be placed in .text.  The build will detect and complain about any such
+ * ambiguously named functions.
+ */
+#define TEXT_MAIN							\
+	.text								\
+	.text.[_0-9A-Za-df-rt-z]*					\
+	.text.s[_0-9A-Za-su-z]*		.text.s		.text.s.*	\
+	.text.st[_0-9A-Zb-z]*		.text.st	.text.st.*	\
+	.text.sta[_0-9A-Za-qs-z]*	.text.sta	.text.sta.*	\
+	.text.star[_0-9A-Za-su-z]*	.text.star	.text.star.*	\
+	.text.start[_0-9A-Za-tv-z]*	.text.start	.text.start.*	\
+	.text.startu[_0-9A-Za-oq-z]*	.text.startu	.text.startu.*	\
+	.text.startup[_0-9A-Za-z]*					\
+	.text.e[_0-9A-Za-wy-z]*		.text.e		.text.e.*	\
+	.text.ex[_0-9A-Za-hj-z]*	.text.ex	.text.ex.*	\
+	.text.exi[_0-9A-Za-su-z]*	.text.exi	.text.exi.*	\
+	.text.exit[_0-9A-Za-z]*
+
+/*
+ * Support -fdata-sections by matching .data, .data.*, and others,
+ * but exclude '.data..*'.
  */
-#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \
-defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
-#define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
-#else
-#define TEXT_MAIN .text
-#endif
-#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG)
 #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data.rel.* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L*
 #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
 #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L*
 #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral*
 #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
-#else
-#define DATA_MAIN .data .data.rel .data.rel.local
-#define SDATA_MAIN .sdata
-#define RODATA_MAIN .rodata
-#define BSS_MAIN .bss
-#define SBSS_MAIN .sbss
-#endif
 
 /*
  * GCC 4.5 and later have a 32 bytes section alignment for structures.
@@ -581,9 +598,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  * during second ld run in second ld pass when generating System.map
  *
  * TEXT_MAIN here will match symbols with a fixed pattern (for example,
- * .text.hot or .text.unlikely) if dead code elimination or
- * function-section is enabled. Match these symbols first before
- * TEXT_MAIN to ensure they are grouped together.
+ * .text.hot or .text.unlikely).  Match those before TEXT_MAIN to ensure
+ * they get grouped together.
  *
  * Also placing .text.hot section at the beginning of a page, this
  * would help the TLB performance.
@@ -729,16 +745,16 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
-	*(.text.startup)
+	*(.text.startup .text.startup.*)
 
 #define EXIT_DATA							\
 	*(.exit.data .exit.data.*)					\
 	*(.fini_array .fini_array.*)					\
-	*(.dtors .dtors.*)						\
+	*(.dtors .dtors.*)
 
 #define EXIT_TEXT							\
 	*(.exit.text)							\
-	*(.text.exit)							\
+	*(.text.exit .text.exit.*)
 
 #define EXIT_CALL							\
 	*(.exitcall.exit)
@@ -832,12 +848,14 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 
 /* Required sections not related to debugging. */
 #define ELF_DETAILS							\
-		.modinfo : { *(.modinfo) . = ALIGN(8); }		\
 		.comment 0 : { *(.comment) }				\
 		.symtab 0 : { *(.symtab) }				\
 		.strtab 0 : { *(.strtab) }				\
 		.shstrtab 0 : { *(.shstrtab) }
 
+#define MODINFO								\
+		.modinfo : { *(.modinfo) . = ALIGN(8); }
+
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
 	. = ALIGN(8);							\
@@ -955,7 +973,9 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 
 #define RUNTIME_CONST_VARIABLES						\
 		RUNTIME_CONST(shift, d_hash_shift)			\
-		RUNTIME_CONST(ptr, dentry_hashtable)
+		RUNTIME_CONST(ptr, dentry_hashtable)			\
+		RUNTIME_CONST(ptr, __dentry_cache)			\
+		RUNTIME_CONST(ptr, __names_cache)
 
 /* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
 #define KUNIT_TABLE()							\
@@ -1048,6 +1068,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	*(.no_trim_symbol)						\
 	/* ld.bfd warns about .gnu.version* even when not emitted */	\
 	*(.gnu.version*)						\
+	*(__tracepoint_check)						\
 
 #define DISCARDS							\
 	/DISCARD/ : {							\