Merge tag 'v4.20-rc6' into for-4.21/block

Pull in v4.20-rc6 to resolve the conflict in NVMe, but also to get the
two corruption fixes. We're going to be overhauling the direct dispatch
path, and we need to do that on top of the changes we made for that
in mainline.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

16 files changed, 109 insertions, 42 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 450b28db9533..0dd316a74a29 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -7,6 +7,8 @@
 #include <linux/radix-tree.h>
 #include <asm/pgtable.h>
 
+typedef unsigned long dax_entry_t;
+
 struct iomap_ops;
 struct dax_device;
 struct dax_operations {
@@ -88,8 +90,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
-bool dax_lock_mapping_entry(struct page *page);
-void dax_unlock_mapping_entry(struct page *page);
+dax_entry_t dax_lock_page(struct page *page);
+void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
 static inline bool bdev_dax_supported(struct block_device *bdev,
 		int blocksize)
@@ -122,14 +124,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 	return -EOPNOTSUPP;
 }
 
-static inline bool dax_lock_mapping_entry(struct page *page)
+static inline dax_entry_t dax_lock_page(struct page *page)
 {
 	if (IS_DAX(page->mapping->host))
-		return true;
-	return false;
+		return ~0UL;
+	return 0;
 }
 
-static inline void dax_unlock_mapping_entry(struct page *page)
+static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
 {
 }
 #endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 448dcc448f1f..795ff0b869bb 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -449,6 +449,13 @@ struct sock_reuseport;
 	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2)				\
 	offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1
+#if BITS_PER_LONG == 64
+# define bpf_ctx_range_ptr(TYPE, MEMBER)					\
+	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
+#else
+# define bpf_ctx_range_ptr(TYPE, MEMBER)					\
+	offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1
+#endif /* BITS_PER_LONG == 64 */
 
 #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE)				\
 	({									\
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 76f8db0b0e71..0705164f928c 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -510,18 +510,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
-			int node);
+			int node, bool hugepage);
+#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
+	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
+	alloc_pages(gfp_mask, order)
+#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index b3e24368930a..14131b6fae68 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -905,6 +905,13 @@ struct vmbus_channel {
 
 	bool probe_done;
 
+	/*
+	 * We must offload the handling of the primary/sub channels
+	 * from the single-threaded vmbus_connection.work_queue to
+	 * two different workqueue, otherwise we can block
+	 * vmbus_connection.work_queue and hang: see vmbus_process_offer().
+	 */
+	struct work_struct add_channel_work;
 };
 
 static inline bool is_hvsock_channel(const struct vmbus_channel *c)
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index bac395f1d00a..5228c62af416 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -139,8 +139,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 		unsigned long addr);
-struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
-						unsigned long addr);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index d37518e89db2..d9d9de3fcf8e 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -224,7 +224,7 @@ struct sfp_eeprom_ext {
  *
  * See the SFF-8472 specification and related documents for the definition
  * of these structure members. This can be obtained from
- * ftp://ftp.seagate.com/sff
+ * https://www.snia.org/technology-communities/sff/specifications
  */
 struct sfp_eeprom_id {
 	struct sfp_eeprom_base base;
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 43106ffa6788..2ec128060239 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -72,7 +72,6 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 	buf->head[0].iov_base = start;
 	buf->head[0].iov_len = len;
 	buf->tail[0].iov_len = 0;
-	buf->bvec = NULL;
 	buf->pages = NULL;
 	buf->page_len = 0;
 	buf->flags = 0;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 414db2bce715..392138fe59b6 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -556,6 +556,7 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx);
 extern void tty_release_struct(struct tty_struct *tty, int idx);
 extern int tty_release(struct inode *inode, struct file *filp);
 extern void tty_init_termios(struct tty_struct *tty);
+extern void tty_save_termios(struct tty_struct *tty);
 extern int tty_standard_install(struct tty_driver *driver,
 		struct tty_struct *tty);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 4cdd515a4385..5e49e82c4368 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -407,11 +407,11 @@ struct usb_host_bos {
 };
 
 int __usb_get_extra_descriptor(char *buffer, unsigned size,
-	unsigned char type, void **ptr);
+	unsigned char type, void **ptr, size_t min);
 #define usb_get_extra_descriptor(ifpoint, type, ptr) \
 				__usb_get_extra_descriptor((ifpoint)->extra, \
 				(ifpoint)->extralen, \
-				type, (void **)ptr)
+				type, (void **)ptr, sizeof(**(ptr)))
 
 /* ----------------------------------------------------------------------- */
 
diff --git a/include/media/media-request.h b/include/media/media-request.h
index 0ce75c35131f..bd36d7431698 100644
--- a/include/media/media-request.h
+++ b/include/media/media-request.h
@@ -68,7 +68,7 @@ struct media_request {
 	unsigned int access_count;
 	struct list_head objects;
 	unsigned int num_incomplete_objects;
-	struct wait_queue_head poll_wait;
+	wait_queue_head_t poll_wait;
 	spinlock_t lock;
 };
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index f58b384aa6c9..665990c7dec8 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -454,6 +454,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 
 static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
+	unsigned int hh_alen = 0;
 	unsigned int seq;
 	unsigned int hh_len;
 
@@ -461,16 +462,33 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 		seq = read_seqbegin(&hh->hh_lock);
 		hh_len = hh->hh_len;
 		if (likely(hh_len <= HH_DATA_MOD)) {
-			/* this is inlined by gcc */
-			memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+			hh_alen = HH_DATA_MOD;
+
+			/* skb_push() would proceed silently if we have room for
+			 * the unaligned size but not for the aligned size:
+			 * check headroom explicitly.
+			 */
+			if (likely(skb_headroom(skb) >= HH_DATA_MOD)) {
+				/* this is inlined by gcc */
+				memcpy(skb->data - HH_DATA_MOD, hh->hh_data,
+				       HH_DATA_MOD);
+			}
 		} else {
-			unsigned int hh_alen = HH_DATA_ALIGN(hh_len);
+			hh_alen = HH_DATA_ALIGN(hh_len);
 
-			memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+			if (likely(skb_headroom(skb) >= hh_alen)) {
+				memcpy(skb->data - hh_alen, hh->hh_data,
+				       hh_alen);
+			}
 		}
 	} while (read_seqretry(&hh->hh_lock, seq));
 
-	skb_push(skb, hh_len);
+	if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	__skb_push(skb, hh_len);
 	return dev_queue_xmit(skb);
 }
 
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index ab9242e51d9e..2abbc15824af 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -620,4 +620,9 @@ static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
 	return false;
 }
 
+static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize)
+{
+	return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize);
+}
+
 #endif /* __net_sctp_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a11f93790476..feada358d872 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2075,6 +2075,8 @@ struct sctp_association {
 
 	__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
 	__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+
+	struct rcu_head rcu;
 };
 
 
diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 2dd37cada7c0..888a833d3b00 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -254,11 +254,13 @@ static inline int snd_interval_empty(const struct snd_interval *i)
 static inline int snd_interval_single(const struct snd_interval *i)
 {
 	return (i->min == i->max || 
-		(i->min + 1 == i->max && i->openmax));
+		(i->min + 1 == i->max && (i->openmin || i->openmax)));
 }
 
 static inline int snd_interval_value(const struct snd_interval *i)
 {
+	if (i->openmin && !i->openmax)
+		return i->max;
 	return i->min;
 }
 
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 538546edbfbd..c7f3321fbe43 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -760,8 +760,10 @@ __SYSCALL(__NR_rseq, sys_rseq)
 #define __NR_ftruncate __NR3264_ftruncate
 #define __NR_lseek __NR3264_lseek
 #define __NR_sendfile __NR3264_sendfile
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
 #define __NR_newfstatat __NR3264_fstatat
 #define __NR_fstat __NR3264_fstat
+#endif
 #define __NR_mmap __NR3264_mmap
 #define __NR_fadvise64 __NR3264_fadvise64
 #ifdef __NR3264_stat
@@ -776,8 +778,10 @@ __SYSCALL(__NR_rseq, sys_rseq)
 #define __NR_ftruncate64 __NR3264_ftruncate
 #define __NR_llseek __NR3264_lseek
 #define __NR_sendfile64 __NR3264_sendfile
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
 #define __NR_fstatat64 __NR3264_fstatat
 #define __NR_fstat64 __NR3264_fstat
+#endif
 #define __NR_mmap2 __NR3264_mmap
 #define __NR_fadvise64_64 __NR3264_fadvise64
 #ifdef __NR3264_stat
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 852dc17ab47a..72c453a8bf50 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2170,7 +2170,7 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
- * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2187,12 +2187,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2201,8 +2203,10 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
- * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for UDP socket matching *tuple*, optionally in a child
  *		network namespace *netns*. The return value must be checked,
@@ -2219,12 +2223,14 @@ union bpf_attr {
  *		**sizeof**\ (*tuple*\ **->ipv6**)
  *			Look for an IPv6 socket.
  *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
  *
  *		All values for *flags* are reserved for future usage, and must
  *		be left at zero.
@@ -2233,6 +2239,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, the *struct bpf_sock*
+ *		result is from reuse->socks[] using the hash of the tuple.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
@@ -2405,6 +2413,9 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)
 
+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS		(-1L)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -2422,6 +2433,12 @@ enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6_INLINE
 };
 
+#define __bpf_md_ptr(type, name)	\
+union {					\
+	type name;			\
+	__u64 :64;			\
+} __attribute__((aligned(8)))
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -2456,7 +2473,7 @@ struct __sk_buff {
 	/* ... here. */
 
 	__u32 data_meta;
-	struct bpf_flow_keys *flow_keys;
+	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 };
 
 struct bpf_tunnel_key {
@@ -2572,8 +2589,8 @@ enum sk_action {
  * be added to the end of this structure
  */
 struct sk_msg_md {
-	void *data;
-	void *data_end;
+	__bpf_md_ptr(void *, data);
+	__bpf_md_ptr(void *, data_end);
 
 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -2589,8 +2606,9 @@ struct sk_reuseport_md {
 	 * Start of directly accessible data. It begins from
 	 * the tcp/udp header.
 	 */
-	void *data;
-	void *data_end;		/* End of directly accessible data */
+	__bpf_md_ptr(void *, data);
+	/* End of directly accessible data */
+	__bpf_md_ptr(void *, data_end);
 	/*
 	 * Total length of packet (starting from the tcp/udp header).
 	 * Note that the directly accessible bytes (data_end - data)