Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/testing/selftests/net/.gitignore
  sort the net-next version and use it

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

24 files changed, 106 insertions, 33 deletions

diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
index 3d5ebd24652b..564a8c675d85 100644
--- a/include/asm-generic/bitops/generic-non-atomic.h
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -4,6 +4,7 @@
 #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
 
 #include <linux/bits.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
@@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * const_*() definitions provide good compile-time optimizations when
  * the passed arguments can be resolved at compile time.
@@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr)
 #define const___test_and_set_bit	generic___test_and_set_bit
 #define const___test_and_clear_bit	generic___test_and_clear_bit
 #define const___test_and_change_bit	generic___test_and_change_bit
+#define const_test_bit_acquire		generic_test_bit_acquire
 
 /**
  * const_test_bit - Determine whether a bit is set
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 988a3bbfba34..2b238b161a62 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 5c37ced343ae..71f8d54a5195 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -13,6 +13,7 @@
 #define arch___test_and_change_bit generic___test_and_change_bit
 
 #define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h
index bdb9b1ffaee9..0ddc78dfc358 100644
--- a/include/asm-generic/bitops/non-instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h
@@ -12,5 +12,6 @@
 #define ___test_and_change_bit	arch___test_and_change_bit
 
 #define _test_bit		arch_test_bit
+#define _test_bit_acquire	arch_test_bit_acquire
 
 #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d0f7bdd2fdf2..db13bb620f52 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -97,7 +97,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt,
 /**
  * memory_intersects - checks if the region occupied by an object intersects
  *                     with another memory region
- * @begin: virtual address of the beginning of the memory regien
+ * @begin: virtual address of the beginning of the memory region
  * @end: virtual address of the end of the memory region
  * @virt: virtual address of the memory object
  * @size: size of the memory object
@@ -110,7 +110,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt,
 {
 	void *vend = virt + size;
 
-	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+	if (virt < end && vend > begin)
+		return true;
+
+	return false;
 }
 
 /**
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf9bf65039f2..3b89c64bcfd8 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w);
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
+#define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
 /*
  * Include this here because some architectures need generic_ffs/fls in
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index def8b8d30ccc..089c9ade4325 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -156,7 +156,7 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 01ce94b58b42..7713d7bcdaea 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -240,6 +240,12 @@ static inline void *offset_to_ptr(const int *off)
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
 /*
+ * Whether 'type' is a signed type or an unsigned type. Supports scalar types,
+ * bool and also pointer types.
+ */
+#define is_signed_type(type) (((type)(-1)) < (__force type)1)
+
+/*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
  */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 720874e6ee94..36e5dd84cf59 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -258,7 +258,7 @@ struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume,
 
 /**
  * fscache_use_cookie - Request usage of cookie attached to an object
- * @object: Object description
+ * @cookie: The cookie representing the cache object
  * @will_modify: If cache is expected to be modified locally
  *
  * Request usage of the cookie attached to an object.  The caller should tell
@@ -274,7 +274,7 @@ static inline void fscache_use_cookie(struct fscache_cookie *cookie,
 
 /**
  * fscache_unuse_cookie - Cease usage of cookie attached to an object
- * @object: Object description
+ * @cookie: The cookie representing the cache object
  * @aux_data: Updated auxiliary data (or NULL)
  * @object_size: Revised size of the object (or NULL)
  *
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 806448173033..60fff133c0b1 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -407,4 +407,5 @@ LSM_HOOK(int, 0, perf_event_write, struct perf_event *event)
 #ifdef CONFIG_IO_URING
 LSM_HOOK(int, 0, uring_override_creds, const struct cred *new)
 LSM_HOOK(int, 0, uring_sqpoll, void)
+LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
 #endif /* CONFIG_IO_URING */
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 84a0d7e02176..3aa6030302f5 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1582,6 +1582,9 @@
  *      Check whether the current task is allowed to spawn a io_uring polling
  *      thread (IORING_SETUP_SQPOLL).
  *
+ * @uring_cmd:
+ *      Check whether the file_operations uring_cmd is allowed to run.
+ *
  */
 union security_list_options {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4d31ce55b1c0..6257867fbf95 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -987,19 +987,30 @@ static inline void mod_memcg_page_state(struct page *page,
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 982f2607180b..21f8b27bd9fd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1544,9 +1544,16 @@ static inline bool is_longterm_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	return !(is_device_coherent_page(page) ||
-		 is_zone_movable_page(page) ||
-		 is_zero_pfn(page_to_pfn(page)));
+	/* The zero page may always be pinned */
+	if (is_zero_pfn(page_to_pfn(page)))
+		return true;
+
+	/* Coherent device memory must always allow eviction. */
+	if (is_device_coherent_page(page))
+		return false;
+
+	/* Otherwise, non-movable zone pages can be pinned. */
+	return !is_zone_movable_page(page);
 }
 #else
 static inline bool is_longterm_pinnable_page(struct page *page)
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index f1221d11f8e5..0eb3b192f07a 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -30,7 +30,6 @@
  * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
  * credit to Christian Biere.
  */
-#define is_signed_type(type)       (((type)(-1)) < (type)1)
 #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
 #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
 #define type_min(T) ((T)((T)-type_max(T)-(T)1))
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bf80adca980b..b89b4b86951f 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -41,12 +41,15 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
-	 * Count of child anon_vmas and VMAs which points to this anon_vma.
+	 * Count of child anon_vmas. Equals to the count of all anon_vmas that
+	 * have ->parent pointing to this one, including itself.
 	 *
 	 * This counter is used for making decision about reusing anon_vma
 	 * instead of forking new one. See comments in function anon_vma_clone.
 	 */
-	unsigned degree;
+	unsigned long num_children;
+	/* Count of VMAs whose ->anon_vma pointer points to this object. */
+	unsigned long num_active_vmas;
 
 	struct anon_vma *parent;	/* Parent of this anon_vma */
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 1bc362cb413f..7bd0c490703d 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2060,6 +2060,7 @@ static inline int security_perf_event_write(struct perf_event *event)
 #ifdef CONFIG_SECURITY
 extern int security_uring_override_creds(const struct cred *new);
 extern int security_uring_sqpoll(void);
+extern int security_uring_cmd(struct io_uring_cmd *ioucmd);
 #else
 static inline int security_uring_override_creds(const struct cred *new)
 {
@@ -2069,6 +2070,10 @@ static inline int security_uring_sqpoll(void)
 {
 	return 0;
 }
+static inline int security_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	return 0;
+}
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_IO_URING */
 
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index b18759a673c6..8401dec93c15 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -814,8 +814,6 @@ extern int trace_add_event_call(struct trace_event_call *call);
 extern int trace_remove_event_call(struct trace_event_call *call);
 extern int trace_event_get_offsets(struct trace_event_call *call);
 
-#define is_signed_type(type)	(((type)(-1)) < (type)1)
-
 int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
 int trace_set_clr_event(const char *system, const char *event, int set);
 int trace_array_set_clr_event(struct trace_array *tr, const char *system,
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 7dec36aecbd9..7725b7579b78 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 63fac94f9ace..ced80e2f8b58 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -246,7 +246,8 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 				       __be32 daddr, __be32 saddr,
 				       __be32 key, __u8 tos,
 				       struct net *net, int oif,
-				       __u32 mark, __u32 tun_inner_hash)
+				       __u32 mark, __u32 tun_inner_hash,
+				       __u8 flow_flags)
 {
 	memset(fl4, 0, sizeof(*fl4));
 
@@ -263,6 +264,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 	fl4->fl4_gre_key = key;
 	fl4->flowi4_mark = mark;
 	fl4->flowi4_multipath_hash = tun_inner_hash;
+	fl4->flowi4_flags = flow_flags;
 }
 
 int ip_tunnel_init(struct net_device *dev);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index c7320ef356d9..6320a76cefdc 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -179,6 +179,8 @@ struct netns_ipv4 {
 	unsigned int sysctl_tcp_fastopen_blackhole_timeout;
 	atomic_t tfo_active_disable_times;
 	unsigned long tfo_active_disable_stamp;
+	u32 tcp_challenge_timestamp;
+	u32 tcp_challenge_count;
 
 	int sysctl_udp_wmem_min;
 	int sysctl_udp_rmem_min;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 934a2a8beb87..1d6085e15fc8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -79,7 +79,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[];	/* Arbitrary size */
+	__u8	data[0];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 1463cfecb56b..9e0b5c8d92ce 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -12,6 +12,10 @@
 #include <linux/types.h>
 #include <linux/time_types.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /*
  * IO submission data structure (Submission Queue Entry)
  */
@@ -661,4 +665,8 @@ struct io_uring_recvmsg_out {
 	__u32 flags;
 };
 
+#ifdef __cplusplus
+}
+#endif
+
 #endif
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 29ced55514d4..6cb842ea8979 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -56,7 +56,7 @@
 #define VIRTIO_NET_F_MQ	22	/* Device supports Receive Flow
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
-#define VIRTIO_NET_F_NOTF_COAL	53	/* Guest can handle notifications coalescing */
+#define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
 #define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
 #define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
 #define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
@@ -364,24 +364,24 @@ struct virtio_net_hash_config {
  */
 #define VIRTIO_NET_CTRL_NOTF_COAL		6
 /*
- * Set the tx-usecs/tx-max-packets patameters.
- * tx-usecs - Maximum number of usecs to delay a TX notification.
- * tx-max-packets - Maximum number of packets to send before a TX notification.
+ * Set the tx-usecs/tx-max-packets parameters.
  */
 struct virtio_net_ctrl_coal_tx {
+	/* Maximum number of packets to send before a TX notification */
 	__le32 tx_max_packets;
+	/* Maximum number of usecs to delay a TX notification */
 	__le32 tx_usecs;
 };
 
 #define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET		0
 
 /*
- * Set the rx-usecs/rx-max-packets patameters.
- * rx-usecs - Maximum number of usecs to delay a RX notification.
- * rx-max-frames - Maximum number of packets to receive before a RX notification.
+ * Set the rx-usecs/rx-max-packets parameters.
  */
 struct virtio_net_ctrl_coal_rx {
+	/* Maximum number of packets to receive before a RX notification */
 	__le32 rx_max_packets;
+	/* Maximum number of usecs to delay a RX notification */
 	__le32 rx_usecs;
 };
 
diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h
index f81aa95ffbc4..f525566a0864 100644
--- a/include/ufs/ufshci.h
+++ b/include/ufs/ufshci.h
@@ -135,11 +135,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 
 #define UFSHCD_UIC_MASK		(UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK)
 
-#define UFSHCD_ERROR_MASK	(UIC_ERROR |\
-				DEVICE_FATAL_ERROR |\
-				CONTROLLER_FATAL_ERROR |\
-				SYSTEM_BUS_FATAL_ERROR |\
-				CRYPTO_ENGINE_FATAL_ERROR)
+#define UFSHCD_ERROR_MASK	(UIC_ERROR | INT_FATAL_ERRORS)
 
 #define INT_FATAL_ERRORS	(DEVICE_FATAL_ERROR |\
 				CONTROLLER_FATAL_ERROR |\