Merge tag 'v6.5-rc6' into iommufd for-next

Required for following patches.

Resolve merge conflict by using the hunk from the for-next branch and
shifting the iommufd_object_deref_user() into iommufd_hw_pagetable_put()

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

19 files changed, 100 insertions, 44 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index c4f5b5228105..11984ed29cb8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -791,7 +791,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
 static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 {
 	bio->bi_opf |= REQ_POLLED;
-	if (!is_sync_kiocb(kiocb))
+	if (kiocb->ki_flags & IOCB_NOWAIT)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ed44a997f629..87d94be7825a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -969,7 +969,6 @@ struct blk_plug {
 
 	bool multiple_queues;
 	bool has_elevator;
-	bool nowait;
 
 	struct list_head cb_list; /* md requires an unplug callback */
 };
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 6e6e57ec69e8..e006c719182b 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -70,6 +70,10 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev,
 					char *buf);
 extern ssize_t cpu_show_retbleed(struct device *dev,
 				 struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev,
+					     struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_gds(struct device *dev,
+			    struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 0d2e2a38b92d..f10fb87d49db 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -175,8 +175,8 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 
 /**
  * cpumask_first_and - return the first cpu from *srcp1 & *srcp2
- * @src1p: the first input
- * @src2p: the second input
+ * @srcp1: the first input
+ * @srcp2: the second input
  *
  * Returns >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
@@ -1197,6 +1197,10 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
 /**
  * cpumap_print_list_to_buf  - copies the cpumask into the buffer as
  *	comma-separated list of cpus
+ * @buf: the buffer to copy into
+ * @mask: the cpumask to copy
+ * @off: in the string from which we are copying, we copy to @buf
+ * @count: the maximum number of bytes to print
  *
  * Everything is same with the above cpumap_print_bitmask_to_buf()
  * except the print format.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6867512907d6..562f2623c9c9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1780,7 +1780,6 @@ struct file_operations {
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
 			unsigned int flags);
-	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
@@ -1817,6 +1816,13 @@ struct file_operations {
 				unsigned int poll_flags);
 } __randomize_layout;
 
+/* Wrap a directory iterator that needs exclusive inode access */
+int wrap_directory_iterator(struct file *, struct dir_context *,
+			    int (*) (struct file *, struct dir_context *));
+#define WRAP_DIR_ITER(x) \
+	static int shared_##x(struct file *file , struct dir_context *ctx) \
+	{ return wrap_directory_iterator(file, ctx, x); }
+
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ce156c7704ee..aad9cf8876b5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -684,7 +684,6 @@ void __init
 ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 
 /* defined in arch */
-extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
@@ -859,9 +858,6 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 }
 #endif
 
-/* May be defined in arch */
-extern int ftrace_arch_read_dyn_info(char *buf, int size);
-
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
 extern void ftrace_module_enable(struct module *mod);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index bfbc37ce223b..3ac3974b3c78 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1239,9 +1239,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel,
 				     u32 *buffer_actual_len,
 				     u64 *requestid);
 
-
-extern void vmbus_ontimer(unsigned long data);
-
 /* Base driver object */
 struct hv_driver {
 	const char *name;
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index e6936cb25047..33f21bd85dbf 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -100,10 +100,16 @@ struct rapl_package;
 
 #define RAPL_DOMAIN_NAME_LENGTH 16
 
+union rapl_reg {
+	void __iomem *mmio;
+	u32 msr;
+	u64 val;
+};
+
 struct rapl_domain {
 	char name[RAPL_DOMAIN_NAME_LENGTH];
 	enum rapl_domain_type id;
-	u64 regs[RAPL_DOMAIN_REG_MAX];
+	union rapl_reg regs[RAPL_DOMAIN_REG_MAX];
 	struct powercap_zone power_zone;
 	struct rapl_domain_data rdd;
 	struct rapl_power_limit rpl[NR_POWER_LIMITS];
@@ -116,7 +122,7 @@ struct rapl_domain {
 };
 
 struct reg_action {
-	u64 reg;
+	union rapl_reg reg;
 	u64 mask;
 	u64 value;
 	int err;
@@ -143,8 +149,8 @@ struct rapl_if_priv {
 	enum rapl_if_type type;
 	struct powercap_control_type *control_type;
 	enum cpuhp_state pcap_rapl_online;
-	u64 reg_unit;
-	u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
+	union rapl_reg reg_unit;
+	union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
 	int limits[RAPL_DOMAIN_MAX];
 	int (*read_raw)(int id, struct reg_action *ra);
 	int (*write_raw)(int id, struct reg_action *ra);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2dd73e4f3d8e..406ab9ea818f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -641,8 +641,14 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
  */
 static inline bool vma_start_read(struct vm_area_struct *vma)
 {
-	/* Check before locking. A race might cause false locked result. */
-	if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
+	/*
+	 * Check before locking. A race might cause false locked result.
+	 * We can use READ_ONCE() for the mm_lock_seq here, and don't need
+	 * ACQUIRE semantics, because this is just a lockless check whose result
+	 * we don't rely on for anything - the mm_lock_seq read against which we
+	 * need ordering is below.
+	 */
+	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
 		return false;
 
 	if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
@@ -653,8 +659,13 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
 	 * False unlocked result is impossible because we modify and check
 	 * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
 	 * modification invalidates all existing locks.
+	 *
+	 * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
+	 * racing with vma_end_write_all(), we only start reading from the VMA
+	 * after it has been unlocked.
+	 * This pairs with RELEASE semantics in vma_end_write_all().
 	 */
-	if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
+	if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
 		up_read(&vma->vm_lock->lock);
 		return false;
 	}
@@ -676,7 +687,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
 	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
 	 * mm->mm_lock_seq can't be concurrently modified.
 	 */
-	*mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
+	*mm_lock_seq = vma->vm_mm->mm_lock_seq;
 	return (vma->vm_lock_seq == *mm_lock_seq);
 }
 
@@ -688,7 +699,13 @@ static inline void vma_start_write(struct vm_area_struct *vma)
 		return;
 
 	down_write(&vma->vm_lock->lock);
-	vma->vm_lock_seq = mm_lock_seq;
+	/*
+	 * We should use WRITE_ONCE() here because we can have concurrent reads
+	 * from the early lockless pessimistic check in vma_start_read().
+	 * We don't really care about the correctness of that early check, but
+	 * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
+	 */
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 }
 
@@ -702,7 +719,7 @@ static inline bool vma_try_start_write(struct vm_area_struct *vma)
 	if (!down_write_trylock(&vma->vm_lock->lock))
 		return false;
 
-	vma->vm_lock_seq = mm_lock_seq;
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 	return true;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index de10fc797c8e..5e74ce4a28cd 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -514,6 +514,20 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Can only be written (using WRITE_ONCE()) while holding both:
+	 *  - mmap_lock (in write mode)
+	 *  - vm_lock->lock (in write mode)
+	 * Can be read reliably while holding one of:
+	 *  - mmap_lock (in read or write mode)
+	 *  - vm_lock->lock (in read or write mode)
+	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+	 * while holding nothing (except RCU to keep the VMA struct allocated).
+	 *
+	 * This sequence counter is explicitly allowed to overflow; sequence
+	 * counter reuse can only lead to occasional unnecessary use of the
+	 * slowpath.
+	 */
 	int vm_lock_seq;
 	struct vma_lock *vm_lock;
 
@@ -679,6 +693,20 @@ struct mm_struct {
 					  * by mmlist_lock
 					  */
 #ifdef CONFIG_PER_VMA_LOCK
+		/*
+		 * This field has lock-like semantics, meaning it is sometimes
+		 * accessed with ACQUIRE/RELEASE semantics.
+		 * Roughly speaking, incrementing the sequence number is
+		 * equivalent to releasing locks on VMAs; reading the sequence
+		 * number can be part of taking a read lock on a VMA.
+		 *
+		 * Can be modified under write mmap_lock using RELEASE
+		 * semantics.
+		 * Can be read with no other protection when holding write
+		 * mmap_lock.
+		 * Can be read with ACQUIRE semantics if not holding write
+		 * mmap_lock.
+		 */
 		int mm_lock_seq;
 #endif
 
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index aab8f1b28d26..e05e167dbd16 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -76,8 +76,14 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 static inline void vma_end_write_all(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
-	/* No races during update due to exclusive mmap_lock being held */
-	WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+	/*
+	 * Nobody can concurrently modify mm->mm_lock_seq due to exclusive
+	 * mmap_lock being held.
+	 * We need RELEASE semantics here to ensure that preceding stores into
+	 * the VMA take effect before we unlock it with this store.
+	 * Pairs with ACQUIRE semantics in vma_start_read().
+	 */
+	smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
 }
 #else
 static inline void vma_end_write_all(struct mm_struct *mm) {}
diff --git a/include/linux/nls.h b/include/linux/nls.h
index 499e486b3722..e0bf8367b274 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -47,7 +47,7 @@ enum utf16_endian {
 /* nls_base.c */
 extern int __register_nls(struct nls_table *, struct module *);
 extern int unregister_nls(struct nls_table *);
-extern struct nls_table *load_nls(char *);
+extern struct nls_table *load_nls(const char *charset);
 extern void unload_nls(struct nls_table *);
 extern struct nls_table *load_nls_default(void);
 #define register_nls(nls) __register_nls((nls), THIS_MODULE)
diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h
index dd42d16945d0..d9642c6cf852 100644
--- a/include/linux/pm_wakeirq.h
+++ b/include/linux/pm_wakeirq.h
@@ -10,8 +10,6 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq);
 extern void dev_pm_clear_wake_irq(struct device *dev);
-extern void dev_pm_enable_wake_irq(struct device *dev);
-extern void dev_pm_disable_wake_irq(struct device *dev);
 
 #else	/* !CONFIG_PM */
 
@@ -34,13 +32,5 @@ static inline void dev_pm_clear_wake_irq(struct device *dev)
 {
 }
 
-static inline void dev_pm_enable_wake_irq(struct device *dev)
-{
-}
-
-static inline void dev_pm_disable_wake_irq(struct device *dev)
-{
-}
-
 #endif	/* CONFIG_PM */
 #endif	/* _LINUX_PM_WAKEIRQ_H */
diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h
index b83a3f944f28..b068e2e60939 100644
--- a/include/linux/prefetch.h
+++ b/include/linux/prefetch.h
@@ -25,11 +25,10 @@ struct page;
 	prefetch() should be defined by the architecture, if not, the 
 	#define below provides a no-op define.	
 	
-	There are 3 prefetch() macros:
+	There are 2 prefetch() macros:
 	
 	prefetch(x)  	- prefetches the cacheline at "x" for read
 	prefetchw(x)	- prefetches the cacheline at "x" for write
-	spin_lock_prefetch(x) - prefetches the spinlock *x for taking
 	
 	there is also PREFETCH_STRIDE which is the architecure-preferred 
 	"lookahead" size for prefetching streamed operations.
@@ -44,10 +43,6 @@ struct page;
 #define prefetchw(x) __builtin_prefetch(x,1)
 #endif
 
-#ifndef ARCH_HAS_SPINLOCK_PREFETCH
-#define spin_lock_prefetch(x) prefetchw(x)
-#endif
-
 #ifndef PREFETCH_STRIDE
 #define PREFETCH_STRIDE (4*L1_CACHE_BYTES)
 #endif
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 054d7911bfc9..c1637515a8a4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -62,6 +62,7 @@ struct sk_psock_progs {
 
 enum sk_psock_state_bits {
 	SK_PSOCK_TX_ENABLED,
+	SK_PSOCK_RX_STRP_ENABLED,
 };
 
 struct sk_psock_link {
diff --git a/include/linux/spi/corgi_lcd.h b/include/linux/spi/corgi_lcd.h
index 0b857616919c..fc6c1515dc54 100644
--- a/include/linux/spi/corgi_lcd.h
+++ b/include/linux/spi/corgi_lcd.h
@@ -15,4 +15,6 @@ struct corgi_lcd_platform_data {
 	void (*kick_battery)(void);
 };
 
+void corgi_lcd_limit_intensity(int limit);
+
 #endif /* __LINUX_SPI_CORGI_LCD_H */
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 8e984d75f5b6..6b0a7dc48a4b 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -101,6 +101,7 @@ struct spi_mem_op {
 		u8 nbytes;
 		u8 buswidth;
 		u8 dtr : 1;
+		u8 __pad : 7;
 		u16 opcode;
 	} cmd;
 
@@ -108,6 +109,7 @@ struct spi_mem_op {
 		u8 nbytes;
 		u8 buswidth;
 		u8 dtr : 1;
+		u8 __pad : 7;
 		u64 val;
 	} addr;
 
@@ -115,12 +117,14 @@ struct spi_mem_op {
 		u8 nbytes;
 		u8 buswidth;
 		u8 dtr : 1;
+		u8 __pad : 7;
 	} dummy;
 
 	struct {
 		u8 buswidth;
 		u8 dtr : 1;
 		u8 ecc : 1;
+		u8 __pad : 6;
 		enum spi_mem_data_dir dir;
 		unsigned int nbytes;
 		union {
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 87837094d549..dee66ade89a0 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -301,14 +301,14 @@ int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #ifdef CONFIG_THERMAL
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
 		void *, struct thermal_zone_device_ops *,
-		struct thermal_zone_params *, int, int);
+		const struct thermal_zone_params *, int, int);
 
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
 struct thermal_zone_device *
 thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int, int,
 					void *, struct thermal_zone_device_ops *,
-					struct thermal_zone_params *, int, int);
+					const struct thermal_zone_params *, int, int);
 
 void *thermal_zone_device_priv(struct thermal_zone_device *tzd);
 const char *thermal_zone_device_type(struct thermal_zone_device *tzd);
@@ -348,7 +348,7 @@ void thermal_zone_device_critical(struct thermal_zone_device *tz);
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
 	struct thermal_zone_device_ops *ops,
-	struct thermal_zone_params *tzp,
+	const struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 { return ERR_PTR(-ENODEV); }
 static inline void thermal_zone_device_unregister(
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 6a1e8f157255..4ee9d13749ad 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -283,6 +283,7 @@ enum tpm_chip_flags {
 	TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED	= BIT(6),
 	TPM_CHIP_FLAG_FIRMWARE_UPGRADE		= BIT(7),
 	TPM_CHIP_FLAG_SUSPENDED			= BIT(8),
+	TPM_CHIP_FLAG_HWRNG_DISABLED		= BIT(9),
 };
 
 #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)