Merge tag 'irqchip-5.16' into irq/core

Merge irqchip updates for Linux 5.16 from Marc Zyngier:

- A large cross-arch rework to move irq_enter()/irq_exit() into
  the arch code, and removing it from the generic irq code.
  Thanks to Mark Rutland for the huge effort!

- A few irqchip drivers are made modular (broadcom, meson), because
  that's apparently a thing...

- A new driver for the Microchip External Interrupt Controller

- The irq_cpu_offline()/irq_cpu_online() API is now deprecated and
  can only be selected on the Cavium Octeon platform. Once this
  platform is removed, the API will be removed at the same time.

- A sprinkle of devm_* helper, as people seem to love that.

- The usual spattering of small fixes and minor improvements.

* tag 'irqchip-5.16': (912 commits)
  h8300: Fix linux/irqchip.h include mess
  dt-bindings: irqchip: renesas-irqc: Document r8a774e1 bindings
  MIPS: irq: Avoid an unused-variable error
  genirq: Hide irq_cpu_{on,off}line() behind a deprecated option
  irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()
  MIPS: loongson64: Drop call to irq_cpu_offline()
  irq: remove handle_domain_{irq,nmi}()
  irq: remove CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: riscv: perform irqentry in entry code
  irq: openrisc: perform irqentry in entry code
  irq: csky: perform irqentry in entry code
  irq: arm64: perform irqentry in entry code
  irq: arm: perform irqentry in entry code
  irq: add a (temporary) CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: nds32: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: arc: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: add generic_handle_arch_irq()
  irq: unexport handle_irq_desc()
  irq: simplify handle_domain_{irq,nmi}()
  irq: mips: simplify do_domain_IRQ()
  ...

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211029083332.3680101-1-maz@kernel.org

31 files changed, 131 insertions, 330 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f4c16f19f83e..020a7d5bf470 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -578,11 +578,12 @@ struct btf_func_model {
  * programs only. Should not be used with normal calls and indirect calls.
  */
 #define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
-
 /* Store IP address of the caller on the trampoline stack,
  * so it's available for trampoline's programs.
  */
 #define BPF_TRAMP_F_IP_ARG		BIT(3)
+/* Return the return value of fentry prog. Only used by bpf_struct_ops. */
+#define BPF_TRAMP_F_RET_FENTRY_RET	BIT(4)
 
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 6486d3c19463..36f33685c8c0 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(int cpu);
+void invalidate_bh_lrus_cpu(void);
 bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
@@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
-static inline void invalidate_bh_lrus_cpu(int cpu) {}
+static inline void invalidate_bh_lrus_cpu(void) {}
 static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e1c705fdfa7c..db2e147e069f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
  * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
  * per-socket cgroup information except for memcg association.
  *
- * On legacy hierarchies, net_prio and net_cls controllers directly set
- * attributes on each sock which can then be tested by the network layer.
- * On the default hierarchy, each sock is associated with the cgroup it was
- * created in and the networking layer can match the cgroup directly.
- *
- * To avoid carrying all three cgroup related fields separately in sock,
- * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
- * On boot, sock_cgroup_data records the cgroup that the sock was created
- * in so that cgroup2 matches can be made; however, once either net_prio or
- * net_cls starts being used, the area is overridden to carry prioidx and/or
- * classid.  The two modes are distinguished by whether the lowest bit is
- * set.  Clear bit indicates cgroup pointer while set bit prioidx and
- * classid.
- *
- * While userland may start using net_prio or net_cls at any time, once
- * either is used, cgroup2 matching no longer works.  There is no reason to
- * mix the two and this is in line with how legacy and v2 compatibility is
- * handled.  On mode switch, cgroup references which are already being
- * pointed to by socks may be leaked.  While this can be remedied by adding
- * synchronization around sock_cgroup_data, given that the number of leaked
- * cgroups is bound and highly unlikely to be high, this seems to be the
- * better trade-off.
+ * On legacy hierarchies, net_prio and net_cls controllers directly
+ * set attributes on each sock which can then be tested by the network
+ * layer. On the default hierarchy, each sock is associated with the
+ * cgroup it was created in and the networking layer can match the
+ * cgroup directly.
  */
 struct sock_cgroup_data {
-	union {
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	is_data : 1;
-			u8	no_refcnt : 1;
-			u8	unused : 6;
-			u8	padding;
-			u16	prioidx;
-			u32	classid;
-		} __packed;
-#else
-		struct {
-			u32	classid;
-			u16	prioidx;
-			u8	padding;
-			u8	unused : 6;
-			u8	no_refcnt : 1;
-			u8	is_data : 1;
-		} __packed;
+	struct cgroup	*cgroup; /* v2 */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	u32		classid; /* v1 */
+#endif
+#ifdef CONFIG_CGROUP_NET_PRIO
+	u16		prioidx; /* v1 */
 #endif
-		u64		val;
-	};
 };
 
-/*
- * There's a theoretical window where the following accessors race with
- * updaters and return part of the previous pointer as the prioidx or
- * classid.  Such races are short-lived and the result isn't critical.
- */
 static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 1 which is always the ID of the root cgroup */
-	return (skcd->is_data & 1) ? skcd->prioidx : 1;
+#ifdef CONFIG_CGROUP_NET_PRIO
+	return READ_ONCE(skcd->prioidx);
+#else
+	return 1;
+#endif
 }
 
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 0 which is the unconfigured default classid */
-	return (skcd->is_data & 1) ? skcd->classid : 0;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	return READ_ONCE(skcd->classid);
+#else
+	return 0;
+#endif
 }
 
-/*
- * If invoked concurrently, the updaters may clobber each other.  The
- * caller is responsible for synchronization.
- */
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.prioidx = prioidx;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_PRIO
+	WRITE_ONCE(skcd->prioidx, prioidx);
+#endif
 }
 
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_classid(&skcd_buf) == classid)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.classid = classid;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	WRITE_ONCE(skcd->classid, classid);
+#endif
 }
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7bf60454a313..75c151413fda 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-extern spinlock_t cgroup_sk_update_lock;
-#endif
-
-void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
 void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 {
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-	unsigned long v;
-
-	/*
-	 * @skcd->val is 64bit but the following is safe on 32bit too as we
-	 * just need the lower ulong to be written and read atomically.
-	 */
-	v = READ_ONCE(skcd->val);
-
-	if (v & 3)
-		return &cgrp_dfl_root.cgrp;
-
-	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
-#else
-	return (struct cgroup *)(unsigned long)skcd->val;
-#endif
+	return skcd->cgroup;
 }
 
 #else	/* CONFIG_CGROUP_DATA */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 49b0ac8b6fd3..3c4de9b6c6e3 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -62,19 +62,6 @@
 #define __no_sanitize_coverage
 #endif
 
-/*
- * Not all versions of clang implement the type-generic versions
- * of the builtin overflow checkers. Fortunately, clang implements
- * __has_builtin allowing us to avoid awkward version
- * checks. Unfortunately, we don't know which version of gcc clang
- * pretends to be, so the macro may or may not be defined.
- */
-#if __has_builtin(__builtin_mul_overflow) && \
-    __has_builtin(__builtin_add_overflow) && \
-    __has_builtin(__builtin_sub_overflow)
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 21c36b69eb06..bd2b881c6b63 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -95,10 +95,8 @@
 
 #if GCC_VERSION >= 70000
 #define KASAN_ABI_VERSION 5
-#elif GCC_VERSION >= 50000
+#else
 #define KASAN_ABI_VERSION 4
-#elif GCC_VERSION >= 40902
-#define KASAN_ABI_VERSION 3
 #endif
 
 #if __has_attribute(__no_sanitize_address__)
@@ -125,10 +123,6 @@
 #define __no_sanitize_coverage
 #endif
 
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b67261a1e3e9..3d5af56337bd 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+#define absolute_pointer(val)	RELOC_HIDE((void *)(val), 0)
+
 #ifndef OPTIMIZER_HIDE_VAR
 /* Make the optimizer believe the variable can be manipulated arbitrarily. */
 #define OPTIMIZER_HIDE_VAR(var)						\
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 8f2106e9e5c1..e6ec63403965 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -21,29 +21,6 @@
  */
 
 /*
- * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support gcc < 5, we implement __has_attribute
- * by hand.
- */
-#ifndef __has_attribute
-# define __has_attribute(x) __GCC4_has_attribute_##x
-# define __GCC4_has_attribute___assume_aligned__      1
-# define __GCC4_has_attribute___copy__                0
-# define __GCC4_has_attribute___designated_init__     0
-# define __GCC4_has_attribute___error__               1
-# define __GCC4_has_attribute___externally_visible__  1
-# define __GCC4_has_attribute___no_caller_saved_registers__ 0
-# define __GCC4_has_attribute___noclone__             1
-# define __GCC4_has_attribute___no_profile_instrument_function__ 0
-# define __GCC4_has_attribute___nonstring__           0
-# define __GCC4_has_attribute___no_sanitize_address__ 1
-# define __GCC4_has_attribute___no_sanitize_undefined__ 1
-# define __GCC4_has_attribute___no_sanitize_coverage__ 0
-# define __GCC4_has_attribute___fallthrough__         0
-# define __GCC4_has_attribute___warning__             1
-#endif
-
-/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute
  */
 #define __alias(symbol)                 __attribute__((__alias__(#symbol)))
@@ -77,7 +54,6 @@
  * compiler should see some alignment anyway, when the return value is
  * massaged by 'flags = ptr & 3; ptr &= ~3;').
  *
- * Optional: only supported since gcc >= 4.9
  * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 5d4d07a9e1ed..1e7399fc69c0 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -996,14 +996,15 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
  * cpumask; Typically used by bin_attribute to export cpumask bitmask
  * ABI.
  *
- * Returns the length of how many bytes have been copied.
+ * Returns the length of how many bytes have been copied, excluding
+ * terminating '\0'.
  */
 static inline ssize_t
 cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
 		loff_t off, size_t count)
 {
 	return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask),
-				   nr_cpu_ids, off, count);
+				   nr_cpu_ids, off, count) - 1;
 }
 
 /**
@@ -1018,7 +1019,7 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
 		loff_t off, size_t count)
 {
 	return bitmap_print_list_to_buf(buf, cpumask_bits(mask),
-				   nr_cpu_ids, off, count);
+				   nr_cpu_ids, off, count) - 1;
 }
 
 #if NR_CPUS <= BITS_PER_LONG
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index c6bc45ae5e03..435777a0073c 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0
- * Copyright 2019-2021 NXP Semiconductors
+ * Copyright 2019-2021 NXP
  */
 
 #ifndef _NET_DSA_TAG_OCELOT_H
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 59828516ebaf..9f4ad719bfe3 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -22,10 +22,15 @@ struct device;
  * LINKS_ADDED:	The fwnode has already be parsed to add fwnode links.
  * NOT_DEVICE:	The fwnode will never be populated as a struct device.
  * INITIALIZED: The hardware corresponding to fwnode has been initialized.
+ * NEEDS_CHILD_BOUND_ON_ADD: For this fwnode/device to probe successfully, its
+ *			     driver needs its child devices to be bound with
+ *			     their respective drivers as soon as they are
+ *			     added.
  */
-#define FWNODE_FLAG_LINKS_ADDED		BIT(0)
-#define FWNODE_FLAG_NOT_DEVICE		BIT(1)
-#define FWNODE_FLAG_INITIALIZED		BIT(2)
+#define FWNODE_FLAG_LINKS_ADDED			BIT(0)
+#define FWNODE_FLAG_NOT_DEVICE			BIT(1)
+#define FWNODE_FLAG_INITIALIZED			BIT(2)
+#define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD	BIT(3)
 
 struct fwnode_handle {
 	struct fwnode_handle *secondary;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c8293c817646..848e1e12c5c6 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -524,9 +524,10 @@ struct irq_chip {
 	void		(*irq_bus_lock)(struct irq_data *data);
 	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
+#ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE
 	void		(*irq_cpu_online)(struct irq_data *data);
 	void		(*irq_cpu_offline)(struct irq_data *data);
-
+#endif
 	void		(*irq_suspend)(struct irq_data *data);
 	void		(*irq_resume)(struct irq_data *data);
 	void		(*irq_pm_shutdown)(struct irq_data *data);
@@ -606,8 +607,10 @@ struct irqaction;
 extern int setup_percpu_irq(unsigned int irq, struct irqaction *new);
 extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
+#ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE
 extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
+#endif
 extern int irq_set_affinity_locked(struct irq_data *data,
 				   const struct cpumask *cpumask, bool force);
 extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
@@ -1261,6 +1264,7 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *));
  * top-level IRQ handler.
  */
 extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init;
+asmlinkage void generic_handle_arch_irq(struct pt_regs *regs);
 #else
 #ifndef set_handle_irq
 #define set_handle_irq(handle_irq)		\
diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index 67351aac65ef..3a091d0710ae 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -14,8 +14,15 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/platform_device.h>
 
+/* Undefined on purpose */
+extern of_irq_init_cb_t typecheck_irq_init_cb;
+
+#define typecheck_irq_init_cb(fn)					\
+	(__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn)
+
 /*
  * This macro must be used by the different irqchip drivers to declare
  * the association between their DT compatible string and their
@@ -23,24 +30,27 @@
  *
  * @name: name that must be unique across all IRQCHIP_DECLARE of the
  * same file.
- * @compstr: compatible string of the irqchip driver
+ * @compat: compatible string of the irqchip driver
  * @fn: initialization function
  */
-#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn)
+#define IRQCHIP_DECLARE(name, compat, fn)	\
+	OF_DECLARE_2(irqchip, name, compat, typecheck_irq_init_cb(fn))
 
 extern int platform_irqchip_probe(struct platform_device *pdev);
 
 #define IRQCHIP_PLATFORM_DRIVER_BEGIN(drv_name) \
 static const struct of_device_id drv_name##_irqchip_match_table[] = {
 
-#define IRQCHIP_MATCH(compat, fn) { .compatible = compat, .data = fn },
+#define IRQCHIP_MATCH(compat, fn) { .compatible = compat,		\
+				    .data = typecheck_irq_init_cb(fn), },
 
 #define IRQCHIP_PLATFORM_DRIVER_END(drv_name)				\
 	{},								\
 };									\
 MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table);		\
-static struct platform_driver drv_name##_driver = {		\
-	.probe  = platform_irqchip_probe,				\
+static struct platform_driver drv_name##_driver = {			\
+	.probe  = IS_ENABLED(CONFIG_IRQCHIP) ? 				\
+			platform_irqchip_probe : NULL,			\
 	.driver = {							\
 		.name = #drv_name,					\
 		.owner = THIS_MODULE,					\
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 59aea39785bf..93d270ca0c56 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -168,14 +168,7 @@ int generic_handle_irq(unsigned int irq);
  * conversion failed.
  */
 int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq);
-
-#ifdef CONFIG_HANDLE_DOMAIN_IRQ
-int handle_domain_irq(struct irq_domain *domain,
-		      unsigned int hwirq, struct pt_regs *regs);
-
-int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
-		      struct pt_regs *regs);
-#endif
+int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq);
 #endif
 
 /* Test to see if a driver has successfully requested an irq */
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 23e4ee523576..9ee238ad29ce 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -251,7 +251,7 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa)
 }
 
 void irq_domain_free_fwnode(struct fwnode_handle *fwnode);
-struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
+struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
 				    irq_hw_number_t hwirq_max, int direct_max,
 				    const struct irq_domain_ops *ops,
 				    void *host_data);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 041ca7f15ea4..0f18df7fe874 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -608,7 +608,6 @@ struct kvm {
 	unsigned long mmu_notifier_range_start;
 	unsigned long mmu_notifier_range_end;
 #endif
-	long tlbs_dirty;
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
 	struct dentry *debugfs_dentry;
@@ -721,11 +720,6 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 	return NULL;
 }
 
-static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
-{
-	return vcpu->vcpu_idx;
-}
-
 #define kvm_for_each_memslot(memslot, slots)				\
 	for (memslot = &slots->memslots[0];				\
 	     memslot < slots->memslots + slots->used_slots; memslot++)	\
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index ffb787d5ebde..5e6dc38f418e 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -80,6 +80,9 @@ struct mdio_driver {
 
 	/* Clears up any memory if needed */
 	void (*remove)(struct mdio_device *mdiodev);
+
+	/* Quiesces the device on system shutdown, turns off interrupts etc */
+	void (*shutdown)(struct mdio_device *mdiodev);
 };
 
 static inline struct mdio_driver *
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b066024c62e3..34de69b3b8ba 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
+void memblock_free_ptr(void *ptr, size_t size);
 void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 326250996b4e..c8077e936691 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -19,6 +19,11 @@ struct migration_target_control;
  */
 #define MIGRATEPAGE_SUCCESS		0
 
+/*
+ * Keep sync with:
+ * - macro MIGRATE_REASON in include/trace/events/migrate.h
+ * - migrate_reason_names[MR_TYPES] in mm/debug.c
+ */
 enum migrate_reason {
 	MR_COMPACTION,
 	MR_MEMORY_FAILURE,
@@ -32,7 +37,6 @@ enum migrate_reason {
 	MR_TYPES
 };
 
-/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
 extern const char *migrate_reason_names[MR_TYPES];
 
 #ifdef CONFIG_MIGRATION
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index b179f1e3541a..96e113e23d04 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_lock);
 }
 
-static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
-{
-	if (mmap_read_trylock(mm)) {
-		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
-		return true;
-	}
-	return false;
-}
-
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, false);
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 923dada24eb4..c0c0cefc3b92 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -150,6 +150,20 @@ static inline int nvmem_cell_read_u64(struct device *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int nvmem_cell_read_variable_le_u32(struct device *dev,
+						 const char *cell_id,
+						 u32 *val)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int nvmem_cell_read_variable_le_u64(struct device *dev,
+						  const char *cell_id,
+						  u64 *val)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct nvmem_device *nvmem_device_get(struct device *dev,
 						    const char *name)
 {
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 0f12345c21fb..4669632bd72b 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -6,12 +6,9 @@
 #include <linux/limits.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	return unlikely(overflow);
 }
 
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	__builtin_mul_overflow(__a, __b, __d);	\
 }))
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d)))
-
-#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d)))
-
-#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d)))
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /** check_shl_overflow() - Calculate a left-shifted value and check overflow
  *
  * @a: Value to be shifted
diff --git a/include/linux/packing.h b/include/linux/packing.h
index 54667735cc67..8d6571feb95d 100644
--- a/include/linux/packing.h
+++ b/include/linux/packing.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: BSD-3-Clause
- * Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright 2016-2018 NXP
  * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _LINUX_PACKING_H
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 505480217cf1..2512e2f9cd4e 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,6 +163,12 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
+#ifdef CONFIG_KVM
+void kvm_host_pmu_init(struct arm_pmu *pmu);
+#else
+#define kvm_host_pmu_init(x)	do { } while(0)
+#endif
+
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fe156a8170aa..9b60bb89d86a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -683,7 +683,9 @@ struct perf_event {
 	/*
 	 * timestamp shadows the actual context timing but it can
 	 * be safely used in NMI interrupt context. It reflects the
-	 * context time as it was when the event was last scheduled in.
+	 * context time as it was when the event was last scheduled in,
+	 * or when ctx_sched_in failed to schedule the event because we
+	 * run out of PMC.
 	 *
 	 * ctx_time already accounts for ctx->timestamp. Therefore to
 	 * compute ctx_time for a sample, simply add perf_clock().
diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h
index 6beb26b7151d..86be8bf27b41 100644
--- a/include/linux/pkeys.h
+++ b/include/linux/pkeys.h
@@ -4,6 +4,8 @@
 
 #include <linux/mm.h>
 
+#define ARCH_DEFAULT_PKEY	0
+
 #ifdef CONFIG_ARCH_HAS_PKEYS
 #include <asm/pkeys.h>
 #else /* ! CONFIG_ARCH_HAS_PKEYS */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e12b524426b0..c1a927ddec64 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1471,6 +1471,7 @@ struct task_struct {
 					mce_whole_page : 1,
 					__mce_reserved : 62;
 	struct callback_head		mce_kill_me;
+	int				mce_count;
 #endif
 
 #ifdef CONFIG_KRETPROBES
@@ -1719,7 +1720,7 @@ extern struct pid *cad_pid;
 #define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
 #define used_math()				tsk_used_math(current)
 
-static inline bool is_percpu_thread(void)
+static __always_inline bool is_percpu_thread(void)
 {
 #ifdef CONFIG_SMP
 	return (current->flags & PF_NO_SETAFFINITY) &&
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6bdb0db3e825..841e2f0f5240 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk,
 	WRITE_ONCE(newsk->prev, prev);
 	WRITE_ONCE(next->prev, newsk);
 	WRITE_ONCE(prev->next, newsk);
-	list->qlen++;
+	WRITE_ONCE(list->qlen, list->qlen + 1);
 }
 
 static inline void __skb_queue_splice(const struct sk_buff_head *list,
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 3e80c4bc66f7..2564b7434b4d 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -197,6 +197,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 
 	mem_cgroup_handle_over_high();
 	blkcg_maybe_throttle_current();
+
+	rseq_handle_notify_resume(NULL, regs);
 }
 
 /*
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 5265024e8b90..207101a9c5c3 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -27,6 +27,12 @@ enum iter_type {
 	ITER_DISCARD,
 };
 
+struct iov_iter_state {
+	size_t iov_offset;
+	size_t count;
+	unsigned long nr_segs;
+};
+
 struct iov_iter {
 	u8 iter_type;
 	bool data_source;
@@ -47,7 +53,6 @@ struct iov_iter {
 		};
 		loff_t xarray_start;
 	};
-	size_t truncated;
 };
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
@@ -55,6 +60,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 	return i->iter_type;
 }
 
+static inline void iov_iter_save_state(struct iov_iter *iter,
+				       struct iov_iter_state *state)
+{
+	state->iov_offset = iter->iov_offset;
+	state->count = iter->count;
+	state->nr_segs = iter->nr_segs;
+}
+
 static inline bool iter_is_iovec(const struct iov_iter *i)
 {
 	return iov_iter_type(i) == ITER_IOVEC;
@@ -233,6 +246,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
 ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
+void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
 
 const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
 
@@ -255,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
 	 * conversion in assignement is by definition greater than all
 	 * values of size_t, including old i->count.
 	 */
-	if (i->count > count) {
-		i->truncated += i->count - count;
+	if (i->count > count)
 		i->count = count;
-	}
 }
 
 /*
@@ -267,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
  */
 static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
-	i->truncated -= count - i->count;
 	i->count = count;
 }
 
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 548a028f2dab..2c1fc9212cf2 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -124,6 +124,7 @@ struct usb_hcd {
 #define HCD_FLAG_RH_RUNNING		5	/* root hub is running? */
 #define HCD_FLAG_DEAD			6	/* controller has died? */
 #define HCD_FLAG_INTF_AUTHORIZED	7	/* authorize interfaces? */
+#define HCD_FLAG_DEFER_RH_REGISTER	8	/* Defer roothub registration */
 
 	/* The flags can be tested using these macros; they are likely to
 	 * be slightly faster than test_bit().
@@ -134,6 +135,7 @@ struct usb_hcd {
 #define HCD_WAKEUP_PENDING(hcd)	((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING))
 #define HCD_RH_RUNNING(hcd)	((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING))
 #define HCD_DEAD(hcd)		((hcd)->flags & (1U << HCD_FLAG_DEAD))
+#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER))
 
 	/*
 	 * Specifies if interfaces are authorized by default