Merge tag 'v5.15' into rdma.git for-next

Pull in the accepted for-rc patches as the next merge needs a newer base.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

12 files changed, 55 insertions, 50 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 020a7d5bf470..3db6f6c95489 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -929,8 +929,11 @@ struct bpf_array_aux {
 	 * stored in the map to make sure that all callers and callees have
 	 * the same prog type and JITed flag.
 	 */
-	enum bpf_prog_type type;
-	bool jited;
+	struct {
+		spinlock_t lock;
+		enum bpf_prog_type type;
+		bool jited;
+	} owner;
 	/* Programs with direct jumps into programs part of this array. */
 	struct list_head poke_progs;
 	struct bpf_map *map;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9c81724e4b98..bbe1eefa4c8a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
-#ifdef CONFIG_NET
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 #ifdef CONFIG_BPF_LSM
 BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
+#ifdef CONFIG_NET
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
 BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 832d8a74fa59..991911048857 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -72,6 +72,8 @@ enum cpuhp_state {
 	CPUHP_SLUB_DEAD,
 	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
+	/* Must be after CPUHP_MM_VMSTAT_DEAD */
+	CPUHP_MM_DEMOTION_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
@@ -240,6 +242,8 @@ enum cpuhp_state {
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
+	/* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
+	CPUHP_AP_MM_DEMOTION_ONLINE,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
 	CPUHP_AP_DTPM_CPU_ONLINE,
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 2aaa15779d50..957ebec35aad 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -109,7 +109,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg
 #endif
 }
 
-#if defined(CONFIG_UM) || defined(CONFIG_IA64)
+#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64)
 /*
  * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out
  * extra segments containing the gate DSO contents.  Dumping its
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12543ee..ef03ff34234d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1051,6 +1051,7 @@ extern int bpf_jit_enable;
 extern int bpf_jit_harden;
 extern int bpf_jit_kallsyms;
 extern long bpf_jit_limit;
+extern long bpf_jit_limit_max;
 
 typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
 
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 7efc0a7c14c9..182c606adb06 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -160,7 +160,10 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 #define register_hotmemory_notifier(nb)		register_memory_notifier(nb)
 #define unregister_hotmemory_notifier(nb) 	unregister_memory_notifier(nb)
 #else
-#define hotplug_memory_notifier(fn, pri)	({ 0; })
+static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
+{
+	return 0;
+}
 /* These aren't inline functions due to a GCC bug. */
 #define register_hotmemory_notifier(nb)    ({ (void)(nb); 0; })
 #define unregister_hotmemory_notifier(nb)  ({ (void)(nb); })
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 441a2f8715f8..5cc19b9483b9 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1118,7 +1118,6 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
 int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
-bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_master(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a558d67ee86f..fbfd3fad48f2 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -171,6 +171,15 @@ enum pageflags {
 	/* Compound pages. Stored in first tail page's flags */
 	PG_double_map = PG_workingset,
 
+#ifdef CONFIG_MEMORY_FAILURE
+	/*
+	 * Compound pages. Stored in first tail page's flags.
+	 * Indicates that at least one subpage is hwpoisoned in the
+	 * THP.
+	 */
+	PG_has_hwpoisoned = PG_mappedtodisk,
+#endif
+
 	/* non-lru isolated movable page */
 	PG_isolated = PG_reclaim,
 
@@ -668,6 +677,20 @@ PAGEFLAG_FALSE(DoubleMap)
 	TESTSCFLAG_FALSE(DoubleMap)
 #endif
 
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+/*
+ * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the
+ * compound page.
+ *
+ * This flag is set by hwpoison handler.  Cleared by THP split or free page.
+ */
+PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+	TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+#else
+PAGEFLAG_FALSE(HasHWPoisoned)
+	TESTSCFLAG_FALSE(HasHWPoisoned)
+#endif
+
 /*
  * Check if a page is currently marked HWPoisoned. Note that this check is
  * best effort only and inherently racy: there is no way to synchronize with
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
index 21c3771e6a56..988528b5da43 100644
--- a/include/linux/secretmem.h
+++ b/include/linux/secretmem.h
@@ -23,7 +23,7 @@ static inline bool page_is_secretmem(struct page *page)
 	mapping = (struct address_space *)
 		((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
 
-	if (mapping != page->mapping)
+	if (!mapping || mapping != page->mapping)
 		return false;
 
 	return mapping->a_ops == &secretmem_aops;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 14ab0c0bc924..1ce9a9eb223b 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes);
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags);
+bool sk_msg_is_readable(struct sock *sk);
 
 static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
 {
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index a9f9c5714e65..fe95f0922526 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -16,23 +16,8 @@
  *  When function tracing occurs, the following steps are made:
  *   If arch does not support a ftrace feature:
  *    call internal function (uses INTERNAL bits) which calls...
- *   If callback is registered to the "global" list, the list
- *    function is called and recursion checks the GLOBAL bits.
- *    then this function calls...
  *   The function callback, which can use the FTRACE bits to
  *    check for recursion.
- *
- * Now if the arch does not support a feature, and it calls
- * the global list function which calls the ftrace callback
- * all three of these steps will do a recursion protection.
- * There's no reason to do one if the previous caller already
- * did. The recursion that we are protecting against will
- * go through the same steps again.
- *
- * To prevent the multiple recursion checks, if a recursion
- * bit is set that is higher than the MAX bit of the current
- * check, then we know that the check was made by the previous
- * caller, and we can skip the current check.
  */
 enum {
 	/* Function recursion bits */
@@ -40,12 +25,14 @@ enum {
 	TRACE_FTRACE_NMI_BIT,
 	TRACE_FTRACE_IRQ_BIT,
 	TRACE_FTRACE_SIRQ_BIT,
+	TRACE_FTRACE_TRANSITION_BIT,
 
-	/* INTERNAL_BITs must be greater than FTRACE_BITs */
+	/* Internal use recursion bits */
 	TRACE_INTERNAL_BIT,
 	TRACE_INTERNAL_NMI_BIT,
 	TRACE_INTERNAL_IRQ_BIT,
 	TRACE_INTERNAL_SIRQ_BIT,
+	TRACE_INTERNAL_TRANSITION_BIT,
 
 	TRACE_BRANCH_BIT,
 /*
@@ -86,12 +73,6 @@ enum {
 	 */
 	TRACE_GRAPH_NOTRACE_BIT,
 
-	/*
-	 * When transitioning between context, the preempt_count() may
-	 * not be correct. Allow for a single recursion to cover this case.
-	 */
-	TRACE_TRANSITION_BIT,
-
 	/* Used to prevent recursion recording from recursing. */
 	TRACE_RECORD_RECURSION_BIT,
 };
@@ -113,12 +94,10 @@ enum {
 #define TRACE_CONTEXT_BITS	4
 
 #define TRACE_FTRACE_START	TRACE_FTRACE_BIT
-#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
 
 #define TRACE_LIST_START	TRACE_INTERNAL_BIT
-#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
 
-#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
+#define TRACE_CONTEXT_MASK	((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
 
 /*
  * Used for setting context
@@ -132,6 +111,7 @@ enum {
 	TRACE_CTX_IRQ,
 	TRACE_CTX_SOFTIRQ,
 	TRACE_CTX_NORMAL,
+	TRACE_CTX_TRANSITION,
 };
 
 static __always_inline int trace_get_context_bit(void)
@@ -160,45 +140,34 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
 #endif
 
 static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
-							int start, int max)
+							int start)
 {
 	unsigned int val = READ_ONCE(current->trace_recursion);
 	int bit;
 
-	/* A previous recursion check was made */
-	if ((val & TRACE_CONTEXT_MASK) > max)
-		return 0;
-
 	bit = trace_get_context_bit() + start;
 	if (unlikely(val & (1 << bit))) {
 		/*
 		 * It could be that preempt_count has not been updated during
 		 * a switch between contexts. Allow for a single recursion.
 		 */
-		bit = TRACE_TRANSITION_BIT;
+		bit = TRACE_CTX_TRANSITION + start;
 		if (val & (1 << bit)) {
 			do_ftrace_record_recursion(ip, pip);
 			return -1;
 		}
-	} else {
-		/* Normal check passed, clear the transition to allow it again */
-		val &= ~(1 << TRACE_TRANSITION_BIT);
 	}
 
 	val |= 1 << bit;
 	current->trace_recursion = val;
 	barrier();
 
-	return bit + 1;
+	return bit;
 }
 
 static __always_inline void trace_clear_recursion(int bit)
 {
-	if (!bit)
-		return;
-
 	barrier();
-	bit--;
 	trace_recursion_clear(bit);
 }
 
@@ -214,7 +183,7 @@ static __always_inline void trace_clear_recursion(int bit)
 static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
 							 unsigned long parent_ip)
 {
-	return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START);
 }
 
 /**
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index eb70cabe6e7f..33a4240e6a6f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -127,6 +127,8 @@ static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type t
 
 long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
 bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type);
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type);
 bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
 
 static inline void set_rlimit_ucount_max(struct user_namespace *ns,