up to 5.15.135

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 134
+SUBLEVEL = 135
 EXTRAVERSION =
 NAME = Trick or Treat
 

arch/arm64/include/asm/cpufeature.h

@@ -839,7 +839,11 @@ static inline bool cpu_has_hw_af(void)
 	if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM))
 		return false;
 
-	mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+	/*
+	 * Use cached version to avoid emulated msr operation on KVM
+	 * guests.
+	 */
+	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
 	return cpuid_feature_extract_unsigned_field(mmfr1,
 						ID_AA64MMFR1_HADBS_SHIFT);
 }

arch/arm64/include/asm/cputype.h

@@ -79,6 +79,7 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
@@ -130,6 +131,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)

arch/parisc/include/asm/ldcw.h

@@ -2,14 +2,28 @@
 #ifndef __PARISC_LDCW_H
 #define __PARISC_LDCW_H
 
-#ifndef CONFIG_PA20
 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
    and GCC only guarantees 8-byte alignment for stack locals, we can't
    be assured of 16-byte alignment for atomic lock data even if we
    specify "__attribute ((aligned(16)))" in the type declaration.  So,
    we use a struct containing an array of four ints for the atomic lock
    type and dynamically select the 16-byte aligned int from the array
-   for the semaphore.  */
+   for the semaphore. */
+
+/* From: "Jim Hull" <jim.hull of hp.com>
+   I've attached a summary of the change, but basically, for PA 2.0, as
+   long as the ",CO" (coherent operation) completer is implemented, then the
+   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
+   they only require "natural" alignment (4-byte for ldcw, 8-byte for
+   ldcd).
+
+   Although the cache control hint is accepted by all PA 2.0 processors,
+   it is only implemented on PA8800/PA8900 CPUs. Prior PA8X00 CPUs still
+   require 16-byte alignment. If the address is unaligned, the operation
+   of the instruction is undefined. The ldcw instruction does not generate
+   unaligned data reference traps so misaligned accesses are not detected.
+   This hid the problem for years. So, restore the 16-byte alignment dropped
+   by Kyle McMartin in "Remove __ldcw_align for PA-RISC 2.0 processors". */
 
 #define __PA_LDCW_ALIGNMENT	16
 #define __PA_LDCW_ALIGN_ORDER	4
@@ -19,22 +33,12 @@
 		& ~(__PA_LDCW_ALIGNMENT - 1);			\
 	(volatile unsigned int *) __ret;			\
 })
-#define __LDCW	"ldcw"
 
-#else /*CONFIG_PA20*/
-/* From: "Jim Hull" <jim.hull of hp.com>
-   I've attached a summary of the change, but basically, for PA 2.0, as
-   long as the ",CO" (coherent operation) completer is specified, then the
-   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
-   they only require "natural" alignment (4-byte for ldcw, 8-byte for
-   ldcd). */
-
-#define __PA_LDCW_ALIGNMENT	4
-#define __PA_LDCW_ALIGN_ORDER	2
-#define __ldcw_align(a) (&(a)->slock)
+#ifdef CONFIG_PA20
 #define __LDCW	"ldcw,co"
-
-#endif /*!CONFIG_PA20*/
+#else
+#define __LDCW	"ldcw"
+#endif
 
 /* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.
    We don't explicitly expose that "*a" may be written as reload

arch/parisc/include/asm/spinlock_types.h

@@ -3,13 +3,8 @@
 #define __ASM_SPINLOCK_TYPES_H
 
 typedef struct {
-#ifdef CONFIG_PA20
-	volatile unsigned int slock;
-# define __ARCH_SPIN_LOCK_UNLOCKED { 1 }
-#else
 	volatile unsigned int lock[4];
 # define __ARCH_SPIN_LOCK_UNLOCKED	{ { 1, 1, 1, 1 } }
-#endif
 } arch_spinlock_t;
 
 

block/blk-core.c

@@ -405,8 +405,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		blk_mq_sched_free_requests(q);
 	mutex_unlock(&q->sysfs_lock);
 
-	percpu_ref_exit(&q->q_usage_counter);
-
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }

block/blk-sysfs.c

@@ -748,6 +748,8 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 {
 	struct request_queue *q = container_of(rcu_head, struct request_queue,
 					       rcu_head);
+
+	percpu_ref_exit(&q->q_usage_counter);
 	kmem_cache_free(blk_requestq_cachep, q);
 }
 

drivers/base/regmap/regcache-rbtree.c

@@ -453,7 +453,8 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
 		if (!rbnode)
 			return -ENOMEM;
 		regcache_rbtree_set_register(map, rbnode,
-					     reg - rbnode->base_reg, value);
+					     (reg - rbnode->base_reg) / map->reg_stride,
+					     value);
 		regcache_rbtree_insert(map, &rbtree_ctx->root, rbnode);
 		rbtree_ctx->cached_rbnode = rbnode;
 	}