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

drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
  21234e3a84c7 ("net/mlx5e: Fix use after free in mlx5e_fs_init()")
  c7eafc5ed068 ("net/mlx5e: Convert ethtool_steering member of flow_steering struct to pointer")
https://lore.kernel.org/all/20220825104410.67d4709c@canb.auug.org.au/
https://lore.kernel.org/all/20220823055533.334471-1-saeed@kernel.org/

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

14 files changed, 96 insertions, 65 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index effee1dc715a..92294a5fb083 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -857,7 +857,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
 bool blk_mq_complete_request_remote(struct request *rq);
-bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_stop_hw_queues(struct request_queue *q);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ed53bfe7c46c..ac5d0515680e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
 	return NULL;
 }
 
-static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
-{
-	return NULL;
-}
-
 static inline bool cgroup_psi_enabled(void)
 {
 	return false;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 0d435d0edbcb..bd047864c7ac 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -202,12 +202,13 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 	return 0;
 }
 
-static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
-					     const struct cpumask *src2p) {
+static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+						      const struct cpumask *src2p)
+{
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline int cpumask_any_distribute(const struct cpumask *srcp)
+static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -261,7 +262,26 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+#if NR_CPUS == 1
+static inline
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	cpumask_check(start);
+	if (n != -1)
+		cpumask_check(n);
+
+	/*
+	 * Return the first available CPU when wrapping, or when starting before cpu0,
+	 * since there is only one valid option.
+	 */
+	if (wrap && n >= 0)
+		return nr_cpumask_bits;
+
+	return cpumask_first(mask);
+}
+#else
 unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+#endif
 
 /**
  * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1c480b1821e1..f4519d3689e1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -656,12 +656,12 @@ struct kvm_irq_routing_table {
 };
 #endif
 
-#ifndef KVM_PRIVATE_MEM_SLOTS
-#define KVM_PRIVATE_MEM_SLOTS 0
+#ifndef KVM_INTERNAL_MEM_SLOTS
+#define KVM_INTERNAL_MEM_SLOTS 0
 #endif
 
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
-#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
 #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
@@ -765,10 +765,10 @@ struct kvm {
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	struct mmu_notifier mmu_notifier;
-	unsigned long mmu_notifier_seq;
-	long mmu_notifier_count;
-	unsigned long mmu_notifier_range_start;
-	unsigned long mmu_notifier_range_end;
+	unsigned long mmu_invalidate_seq;
+	long mmu_invalidate_in_progress;
+	unsigned long mmu_invalidate_range_start;
+	unsigned long mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -1357,10 +1357,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end);
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1907,42 +1907,44 @@ extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
+static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
-	if (unlikely(kvm->mmu_notifier_count))
+	if (unlikely(kvm->mmu_invalidate_in_progress))
 		return 1;
 	/*
-	 * Ensure the read of mmu_notifier_count happens before the read
-	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
-	 * mmu_notifier_invalidate_range_end to make sure that the caller
-	 * either sees the old (non-zero) value of mmu_notifier_count or
-	 * the new (incremented) value of mmu_notifier_seq.
-	 * PowerPC Book3s HV KVM calls this under a per-page lock
-	 * rather than under kvm->mmu_lock, for scalability, so
-	 * can't rely on kvm->mmu_lock to keep things ordered.
+	 * Ensure the read of mmu_invalidate_in_progress happens before
+	 * the read of mmu_invalidate_seq.  This interacts with the
+	 * smp_wmb() in mmu_notifier_invalidate_range_end to make sure
+	 * that the caller either sees the old (non-zero) value of
+	 * mmu_invalidate_in_progress or the new (incremented) value of
+	 * mmu_invalidate_seq.
+	 *
+	 * PowerPC Book3s HV KVM calls this under a per-page lock rather
+	 * than under kvm->mmu_lock, for scalability, so can't rely on
+	 * kvm->mmu_lock to keep things ordered.
 	 */
 	smp_rmb();
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
 
-static inline int mmu_notifier_retry_hva(struct kvm *kvm,
-					 unsigned long mmu_seq,
-					 unsigned long hva)
+static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+					   unsigned long mmu_seq,
+					   unsigned long hva)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
-	 * If mmu_notifier_count is non-zero, then the range maintained by
-	 * kvm_mmu_notifier_invalidate_range_start contains all addresses that
-	 * might be being invalidated. Note that it may include some false
+	 * If mmu_invalidate_in_progress is non-zero, then the range maintained
+	 * by kvm_mmu_notifier_invalidate_range_start contains all addresses
+	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_notifier_count) &&
-	    hva >= kvm->mmu_notifier_range_start &&
-	    hva < kvm->mmu_notifier_range_end)
+	if (unlikely(kvm->mmu_invalidate_in_progress) &&
+	    hva >= kvm->mmu_invalidate_range_start &&
+	    hva < kvm->mmu_invalidate_range_end)
 		return 1;
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0269ff114f5a..698032e5ef2d 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1382,7 +1382,8 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	.proc_name		= drv_name,			\
 	.slave_destroy		= ata_scsi_slave_destroy,	\
 	.bios_param		= ata_std_bios_param,		\
-	.unlock_native_capacity	= ata_scsi_unlock_native_capacity
+	.unlock_native_capacity	= ata_scsi_unlock_native_capacity,\
+	.max_sectors		= ATA_MAX_SECTORS_LBA48
 
 #define ATA_SUBBASE_SHT(drv_name)				\
 	__ATA_BASE_SHT(drv_name),				\
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 96b16fbe1aa4..7b7ce602c808 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -779,6 +779,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
+	struct lock_class_key	lock_key;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	profile;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3bedc449c14d..982f2607180b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2885,7 +2885,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 #define FOLL_REMOTE	0x2000	/* we are working on non-current tsk/mm */
-#define FOLL_COW	0x4000	/* internal GUP flag */
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8839abc1f941..eec35f9b6616 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -640,9 +640,23 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return !IS_ENABLED(CONFIG_SYSCTL) ||
-	       !sysctl_fb_tunnels_only_for_init_net ||
-	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
+#if IS_ENABLED(CONFIG_SYSCTL)
+	int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
+
+	return !fb_tunnels_only_for_init_net ||
+		(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
+#else
+	return true;
+#endif
+}
+
+static inline int net_inherit_devconf(void)
+{
+#if IS_ENABLED(CONFIG_SYSCTL)
+	return READ_ONCE(sysctl_devconf_inherit_init_net);
+#else
+	return 0;
+#endif
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h
index a13296d6c7ce..fd533552a062 100644
--- a/include/linux/netfilter_bridge/ebtables.h
+++ b/include/linux/netfilter_bridge/ebtables.h
@@ -94,10 +94,6 @@ struct ebt_table {
 	struct ebt_replace_kernel *table;
 	unsigned int valid_hooks;
 	rwlock_t lock;
-	/* e.g. could be the table explicitly only allows certain
-	 * matches, targets, ... 0 == let it in */
-	int (*check)(const struct ebt_table_info *info,
-	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
 	struct nf_hook_ops *ops;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b32ed68e7dc4..7931fa472561 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -83,7 +83,6 @@ struct nfs_open_context {
 	fmode_t mode;
 
 	unsigned long flags;
-#define NFS_CONTEXT_RESEND_WRITES	(1)
 #define NFS_CONTEXT_BAD			(2)
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
@@ -182,6 +181,7 @@ struct nfs_inode {
 		/* Regular file */
 		struct {
 			atomic_long_t	nrequests;
+			atomic_long_t	redirtied_pages;
 			struct nfs_mds_commit_info commit_info;
 			struct mutex	commit_mutex;
 		};
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 89784763d19e..dd74411ac21d 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, size_t nbytes, enum psi_res res);
+			char *buf, enum psi_res res);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 1b6c4013f691..ff0b990de83d 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -29,15 +29,10 @@ struct shmem_inode_info {
 	struct inode		vfs_inode;
 };
 
-#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE
-#define SHMEM_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE
-#define SHMEM_FL_INHERITED FS_FL_USER_MODIFIABLE
-
-/* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define SHMEM_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
-
-/* Flags that are appropriate for non-directories/regular files. */
-#define SHMEM_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
+#define SHMEM_FL_USER_VISIBLE		FS_FL_USER_VISIBLE
+#define SHMEM_FL_USER_MODIFIABLE \
+	(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL)
+#define SHMEM_FL_INHERITED		(FS_NODUMP_FL | FS_NOATIME_FL)
 
 struct shmem_sb_info {
 	unsigned long max_blocks;   /* How many blocks are allowed */
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 732b522bacb7..e1b8a915e9e9 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -73,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, atomic_t *mmap_changing);
+extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
+			  unsigned long start, unsigned long len, bool enable_wp);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 404024486fa5..f3fc36cd2276 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -20,12 +20,19 @@
 #define HIGHMEM_ZONE(xx)
 #endif
 
-#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE
+#ifdef CONFIG_ZONE_DEVICE
+#define DEVICE_ZONE(xx) xx##_DEVICE,
+#else
+#define DEVICE_ZONE(xx)
+#endif
+
+#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, \
+	HIGHMEM_ZONE(xx) xx##_MOVABLE, DEVICE_ZONE(xx)
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
-		FOR_ALL_ZONES(PGALLOC),
-		FOR_ALL_ZONES(ALLOCSTALL),
-		FOR_ALL_ZONES(PGSCAN_SKIP),
+		FOR_ALL_ZONES(PGALLOC)
+		FOR_ALL_ZONES(ALLOCSTALL)
+		FOR_ALL_ZONES(PGSCAN_SKIP)
 		PGFREE, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,