Merge tag 'v5.15-rc6' into regulator-5.16

Linux 5.15-rc6

73 files changed, 368 insertions, 589 deletions

diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h
index a0212e67d6f4..027faa8883aa 100644
--- a/include/acpi/acpi_io.h
+++ b/include/acpi/acpi_io.h
@@ -14,14 +14,6 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 }
 #endif
 
-#ifndef acpi_os_memmap
-static inline void __iomem *acpi_os_memmap(acpi_physical_address phys,
-					    acpi_size size)
-{
-	return ioremap_cache(phys, size);
-}
-#endif
-
 extern bool acpi_permanent_mmap;
 
 void __iomem __ref
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index e93375c710b9..7ce93aaf69f8 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -957,7 +957,7 @@ static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
 
 #ifndef iounmap
 #define iounmap iounmap
-static inline void iounmap(void __iomem *addr)
+static inline void iounmap(volatile void __iomem *addr)
 {
 }
 #endif
@@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 	port &= IO_SPACE_LIMIT;
 	return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
 }
-#define __pci_ioport_unmap __pci_ioport_unmap
-static inline void __pci_ioport_unmap(void __iomem *p)
-{
-	uintptr_t start = (uintptr_t) PCI_IOBASE;
-	uintptr_t addr = (uintptr_t) p;
-
-	if (addr >= start && addr < start + IO_SPACE_LIMIT)
-		return;
-	iounmap(p);
-}
+#define ARCH_HAS_GENERIC_IOPORT_MAP
 #endif
 
 #ifndef ioport_unmap
@@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifndef CONFIG_GENERIC_IOMAP
-struct pci_dev;
-extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
-
-#ifndef __pci_ioport_unmap
-static inline void __pci_ioport_unmap(void __iomem *p) {}
-#endif
-
 #ifndef pci_iounmap
-#define pci_iounmap pci_iounmap
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
-{
-	__pci_ioport_unmap(p);
-}
+#define ARCH_WANTS_GENERIC_PCI_IOUNMAP
+#endif
 #endif
-#endif /* CONFIG_GENERIC_IOMAP */
 
 #ifndef xlate_dev_mem_ptr
 #define xlate_dev_mem_ptr xlate_dev_mem_ptr
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index 9b3eb6d86200..08237ae8b840 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size)
 }
 #endif
 
-#ifdef CONFIG_PCI
-/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
-struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
-#elif defined(CONFIG_GENERIC_IOMAP)
-struct pci_dev;
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
-{ }
-#endif
-
 #include <asm-generic/pci_iomap.h>
 
 #endif
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index c1ab6a6e72b5..d3eae6cdbacb 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -197,10 +197,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 	return hv_vp_index[cpu_number];
 }
 
-static inline int cpumask_to_vpset(struct hv_vpset *vpset,
-				    const struct cpumask *cpus)
+static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus,
+				    bool exclude_self)
 {
 	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
+	int this_cpu = smp_processor_id();
 
 	/* valid_bank_mask can represent up to 64 banks */
 	if (hv_max_vp_index / 64 >= 64)
@@ -218,6 +220,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	 * Some banks may end up being empty but this is acceptable.
 	 */
 	for_each_cpu(cpu, cpus) {
+		if (exclude_self && cpu == this_cpu)
+			continue;
 		vcpu = hv_cpu_number_to_vp_number(cpu);
 		if (vcpu == VP_INVAL)
 			return -1;
@@ -232,6 +236,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	return nr_bank;
 }
 
+static inline int cpumask_to_vpset(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	return __cpumask_to_vpset(vpset, cpus, false);
+}
+
+static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset,
+				    const struct cpumask *cpus)
+{
+	WARN_ON_ONCE(preemptible());
+	return __cpumask_to_vpset(vpset, cpus, true);
+}
+
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h
index df636c6d8e6c..5a2f9bf53384 100644
--- a/include/asm-generic/pci_iomap.h
+++ b/include/asm-generic/pci_iomap.h
@@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
 					unsigned long offset,
 					unsigned long maxlen);
+extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
 /* Create a virtual mapping cookie for a port on a given PCI device.
  * Do not call this directly, it exists to make it easier for architectures
  * to override */
@@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
 {
 	return NULL;
 }
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{ }
 #endif
 
 #endif /* __ASM_GENERIC_PCI_IOMAP_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index aa50bf2959fe..f2984af2b85b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -116,11 +116,7 @@
  * GCC 4.5 and later have a 32 bytes section alignment for structures.
  * Except GCC 4.9, that feels the need to align on 64 bytes.
  */
-#if __GNUC__ == 4 && __GNUC_MINOR__ == 9
-#define STRUCT_ALIGNMENT 64
-#else
 #define STRUCT_ALIGNMENT 32
-#endif
 #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT)
 
 /*
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 24b40e5c160b..018e776a34b9 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -613,7 +613,7 @@ void kunit_remove_resource(struct kunit *test, struct kunit_resource *res);
  * and is automatically cleaned up after the test case concludes. See &struct
  * kunit_resource for more information.
  */
-void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t flags);
+void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp);
 
 /**
  * kunit_kmalloc() - Like kmalloc() except the allocation is *test managed*.
@@ -657,9 +657,9 @@ static inline void *kunit_kzalloc(struct kunit *test, size_t size, gfp_t gfp)
  *
  * See kcalloc() and kunit_kmalloc_array() for more information.
  */
-static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp_t flags)
+static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp_t gfp)
 {
-	return kunit_kmalloc_array(test, n, size, flags | __GFP_ZERO);
+	return kunit_kmalloc_array(test, n, size, gfp | __GFP_ZERO);
 }
 
 void kunit_cleanup(struct kunit *test);
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 864b9997efb2..90f21898aad8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -61,7 +61,6 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
-int kvm_pmu_probe_pmuver(void);
 #else
 struct kvm_pmu {
 };
@@ -118,8 +117,6 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return 0;
 }
 
-static inline int kvm_pmu_probe_pmuver(void) { return 0xf; }
-
 #endif
 
 #endif
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 7d1cabe15262..63ccb5252190 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -321,10 +321,20 @@ asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
  * from register 0 to 3 on return from the SMC instruction.  An optional
  * quirk structure provides vendor specific behavior.
  */
+#ifdef CONFIG_HAVE_ARM_SMCCC
 asmlinkage void __arm_smccc_smc(unsigned long a0, unsigned long a1,
 			unsigned long a2, unsigned long a3, unsigned long a4,
 			unsigned long a5, unsigned long a6, unsigned long a7,
 			struct arm_smccc_res *res, struct arm_smccc_quirk *quirk);
+#else
+static inline void __arm_smccc_smc(unsigned long a0, unsigned long a1,
+			unsigned long a2, unsigned long a3, unsigned long a4,
+			unsigned long a5, unsigned long a6, unsigned long a7,
+			struct arm_smccc_res *res, struct arm_smccc_quirk *quirk)
+{
+	*res = (struct arm_smccc_res){};
+}
+#endif
 
 /**
  * __arm_smccc_hvc() - make HVC calls
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 c