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

Documentation/bpf/bpf_devel_QA.rst
  b7abcd9c656b ("bpf, doc: Link to submitting-patches.rst for general patch submission info")
  d56b0c461d19 ("bpf, docs: Fix link to netdev-FAQ target")
https://lore.kernel.org/all/20230307095812.236eb1be@canb.auug.org.au/

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

32 files changed, 237 insertions, 325 deletions

diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 03eb3d977075..9e4f7564201a 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -148,15 +148,12 @@
  *
  *****************************************************************************/
 
-#if defined(__GNUC__) && !defined(__INTEL_COMPILER)
+#if defined(__GNUC__)
 #include <acpi/platform/acgcc.h>
 
 #elif defined(_MSC_VER)
 #include "acmsvc.h"
 
-#elif defined(__INTEL_COMPILER)
-#include <acpi/platform/acintel.h>
-
 #endif
 
 #if defined(_LINUX) || defined(__linux__)
diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h
index 3a6b1db9a984..72cc7bab469e 100644
--- a/include/acpi/platform/acenvex.h
+++ b/include/acpi/platform/acenvex.h
@@ -35,7 +35,7 @@
 
 #endif
 
-#if defined(__GNUC__) && !defined(__INTEL_COMPILER)
+#if defined(__GNUC__)
 #include "acgccex.h"
 
 #elif defined(_MSC_VER)
diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h
deleted file mode 100644
index 85b1ae86ee63..000000000000
--- a/include/acpi/platform/acintel.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
-/******************************************************************************
- *
- * Name: acintel.h - VC specific defines, etc.
- *
- * Copyright (C) 2000 - 2022, Intel Corp.
- *
- *****************************************************************************/
-
-#ifndef __ACINTEL_H__
-#define __ACINTEL_H__
-
-/*
- * Use compiler specific <stdarg.h> is a good practice for even when
- * -nostdinc is specified (i.e., ACPI_USE_STANDARD_HEADERS undefined.
- */
-#ifndef va_arg
-#include <stdarg.h>
-#endif
-
-/* Configuration specific to Intel 64-bit C compiler */
-
-#define COMPILER_DEPENDENT_INT64    __int64
-#define COMPILER_DEPENDENT_UINT64   unsigned __int64
-#define ACPI_INLINE                 __inline
-
-/*
- * Calling conventions:
- *
- * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
- * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
- * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
- * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
- */
-#define ACPI_SYSTEM_XFACE
-#define ACPI_EXTERNAL_XFACE
-#define ACPI_INTERNAL_XFACE
-#define ACPI_INTERNAL_VAR_XFACE
-
-/* remark 981 - operands evaluated in no particular order */
-#pragma warning(disable:981)
-
-/* warn C4100: unreferenced formal parameter */
-#pragma warning(disable:4100)
-
-/* warn C4127: conditional expression is constant */
-#pragma warning(disable:4127)
-
-/* warn C4706: assignment within conditional expression */
-#pragma warning(disable:4706)
-
-/* warn C4214: bit field types other than int */
-#pragma warning(disable:4214)
-
-#endif				/* __ACINTEL_H__ */
diff --git a/include/linux/bcd.h b/include/linux/bcd.h
index 118bea36d7d4..abbc8149178e 100644
--- a/include/linux/bcd.h
+++ b/include/linux/bcd.h
@@ -14,8 +14,12 @@
 		const_bin2bcd(x) :			\
 		_bin2bcd(x))
 
+#define bcd_is_valid(x)					\
+		const_bcd_is_valid(x)
+
 #define const_bcd2bin(x)	(((x) & 0x0f) + ((x) >> 4) * 10)
 #define const_bin2bcd(x)	((((x) / 10) << 4) + (x) % 10)
+#define const_bcd_is_valid(x)	(((x) & 0x0f) < 10 && ((x) >> 4) < 10)
 
 unsigned _bcd2bin(unsigned char val) __attribute_const__;
 unsigned char _bin2bcd(unsigned val) __attribute_const__;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 779fba613bd0..dd5ce1137f04 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -473,6 +473,7 @@ enum hctx_type {
 
 /**
  * struct blk_mq_tag_set - tag set that can be shared between request queues
+ * @ops:	   Pointers to functions that implement block driver behavior.
  * @map:	   One or more ctx -> hctx mappings. One map exists for each
  *		   hardware queue type (enum hctx_type) that the driver wishes
  *		   to support. There are no restrictions on maps being of the
@@ -480,7 +481,6 @@ enum hctx_type {
  *		   types.
  * @nr_maps:	   Number of elements in the @map array. A number in the range
  *		   [1, HCTX_MAX_TYPES].
- * @ops:	   Pointers to functions that implement block driver behavior.
  * @nr_hw_queues:  Number of hardware queues supported by the block driver that
  *		   owns this data structure.
  * @queue_depth:   Number of tags per hardware queue, reserved tags included.
@@ -505,9 +505,9 @@ enum hctx_type {
  *		   (BLK_MQ_F_BLOCKING).
  */
 struct blk_mq_tag_set {
+	const struct blk_mq_ops	*ops;
 	struct blk_mq_queue_map	map[HCTX_MAX_TYPES];
 	unsigned int		nr_maps;
-	const struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;
 	unsigned int		reserved_tags;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 41a41561b773..d1aee08f8c18 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1283,12 +1283,7 @@ static inline bool bdev_nowait(struct block_device *bdev)
 
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_zoned_model(q);
-
-	return BLK_ZONED_NONE;
+	return blk_queue_zoned_model(bdev_get_queue(bdev));
 }
 
 static inline bool bdev_is_zoned(struct block_device *bdev)
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 03c2a613ad40..0c356a517991 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -15,28 +15,25 @@
 
 #include <uapi/linux/capability.h>
 #include <linux/uidgid.h>
+#include <linux/bits.h>
 
 #define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3
-#define _KERNEL_CAPABILITY_U32S    _LINUX_CAPABILITY_U32S_3
 
 extern int file_caps_enabled;
 
-typedef struct kernel_cap_struct {
-	__u32 cap[_KERNEL_CAPABILITY_U32S];
-} kernel_cap_t;
+typedef struct { u64 val; } kernel_cap_t;
 
 /* same as vfs_ns_cap_data but in cpu endian and always filled completely */
 struct cpu_vfs_cap_data {
 	__u32 magic_etc;
+	kuid_t rootid;
 	kernel_cap_t permitted;
 	kernel_cap_t inheritable;
-	kuid_t rootid;
 };
 
 #define _USER_CAP_HEADER_SIZE  (sizeof(struct __user_cap_header_struct))
 #define _KERNEL_CAP_T_SIZE     (sizeof(kernel_cap_t))
 
-
 struct file;
 struct inode;
 struct dentry;
@@ -44,16 +41,6 @@ struct task_struct;
 struct user_namespace;
 struct mnt_idmap;
 
-extern const kernel_cap_t __cap_empty_set;
-extern const kernel_cap_t __cap_init_eff_set;
-
-/*
- * Internal kernel functions only
- */
-
-#define CAP_FOR_EACH_U32(__capi)  \
-	for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi)
-
 /*
  * CAP_FS_MASK and CAP_NFSD_MASKS:
  *
@@ -67,94 +54,52 @@ extern const kernel_cap_t __cap_init_eff_set;
  *   2. The security.* and trusted.* xattrs are fs-related MAC permissions
  */
 
-# define CAP_FS_MASK_B0     (CAP_TO_MASK(CAP_CHOWN)		\
-			    | CAP_TO_MASK(CAP_MKNOD)		\
-			    | CAP_TO_MASK(CAP_DAC_OVERRIDE)	\
-			    | CAP_TO_MASK(CAP_DAC_READ_SEARCH)	\
-			    | CAP_TO_MASK(CAP_FOWNER)		\
-			    | CAP_TO_MASK(CAP_FSETID))
-
-# define CAP_FS_MASK_B1     (CAP_TO_MASK(CAP_MAC_OVERRIDE))
+# define CAP_FS_MASK     (BIT_ULL(CAP_CHOWN)		\
+			| BIT_ULL(CAP_MKNOD)		\
+			| BIT_ULL(CAP_DAC_OVERRIDE)	\
+			| BIT_ULL(CAP_DAC_READ_SEARCH)	\
+			| BIT_ULL(CAP_FOWNER)		\
+			| BIT_ULL(CAP_FSETID)		\
+			| BIT_ULL(CAP_MAC_OVERRIDE))
+#define CAP_VALID_MASK	 (BIT_ULL(CAP_LAST_CAP+1)-1)
 
-#if _KERNEL_CAPABILITY_U32S != 2
-# error Fix up hand-coded capability macro initializers
-#else /* HAND-CODED capability initializers */
+# define CAP_EMPTY_SET    ((kernel_cap_t) { 0 })
+# define CAP_FULL_SET     ((kernel_cap_t) { CAP_VALID_MASK })
+# define CAP_FS_SET       ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_LINUX_IMMUTABLE) })
+# define CAP_NFSD_SET     ((kernel_cap_t) { CAP_FS_MASK | BIT_ULL(CAP_SYS_RESOURCE) })
 
-#define CAP_LAST_U32			((_KERNEL_CAPABILITY_U32S) - 1)
-#define CAP_LAST_U32_VALID_MASK		(CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
+# define cap_clear(c)         do { (c).val = 0; } while (0)
 
-# define CAP_EMPTY_SET    ((kernel_cap_t){{ 0, 0 }})
-# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
-# define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0 \
-				    | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
-				    CAP_FS_MASK_B1 } })
-# define CAP_NFSD_SET     ((kernel_cap_t){{ CAP_FS_MASK_B0 \
-				    | CAP_TO_MASK(CAP_SYS_RESOURCE), \
-				    CAP_FS_MASK_B1 } })
-
-#endif /* _KERNEL_CAPABILITY_U32S != 2 */
-
-# define cap_clear(c)         do { (c) = __cap_empty_set; } while (0)
-
-#define cap_raise(c, flag)  ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag))
-#define cap_lower(c, flag)  ((c).cap[CAP_TO_INDEX(flag)] &= ~CAP_TO_MASK(flag))
-#define cap_raised(c, flag) ((c).cap[CAP_TO_INDEX(flag)] & CAP_TO_MASK(flag))
-
-#define CAP_BOP_ALL(c, a, b, OP)                                    \
-do {                                                                \
-	unsigned __capi;                                            \
-	CAP_FOR_EACH_U32(__capi) {                                  \
-		c.cap[__capi] = a.cap[__capi] OP b.cap[__capi];     \
-	}                                                           \
-} while (0)
-
-#define CAP_UOP_ALL(c, a, OP)                                       \
-do {                                                                \
-	unsigned __capi;                                            \
-	CAP_FOR_EACH_U32(__capi) {                                  \
-		c.cap[__capi] = OP a.cap[__capi];                   \
-	}                                                           \
-} while (0)
+#define cap_raise(c, flag)  ((c).val |= BIT_ULL(flag))
+#define cap_lower(c, flag)  ((c).val &= ~BIT_ULL(flag))
+#define cap_raised(c, flag) (((c).val & BIT_ULL(flag)) != 0)
 
 static inline kernel_cap_t cap_combine(const kernel_cap_t a,
 				       const kernel_cap_t b)
 {
-	kernel_cap_t dest;
-	CAP_BOP_ALL(dest, a, b, |);
-	return dest;
+	return (kernel_cap_t) { a.val | b.val };
 }
 
 static inline kernel_cap_t cap_intersect(const kernel_cap_t a,
 					 const kernel_cap_t b)
 {
-	kernel_cap_t dest;
-	CAP_BOP_ALL(dest, a, b, &);
-	return dest;
+	return (kernel_cap_t) { a.val & b.val };
 }
 
 static inline kernel_cap_t cap_drop(const kernel_cap_t a,
 				    const kernel_cap_t drop)
 {
-	kernel_cap_t dest;
-	CAP_BOP_ALL(dest, a, drop, &~);
-	return dest;
+	return (kernel_cap_t) { a.val &~ drop.val };
 }
 
-static inline kernel_cap_t cap_invert(const kernel_cap_t c)
+static inline bool cap_isclear(const kernel_cap_t a)
 {
-	kernel_cap_t dest;
-	CAP_UOP_ALL(dest, c, ~);
-	return dest;
+	return !a.val;
 }
 
-static inline bool cap_isclear(const kernel_cap_t a)
+static inline bool cap_isidentical(const kernel_cap_t a, const kernel_cap_t b)
 {
-	unsigned __capi;
-	CAP_FOR_EACH_U32(__capi) {
-		if (a.cap[__capi] != 0)
-			return false;
-	}
-	return true;
+	return a.val == b.val;
 }
 
 /*
@@ -166,39 +111,31 @@ static inline bool cap_isclear(const kernel_cap_t a)
  */
 static inline bool cap_issubset(const kernel_cap_t a, const kernel_cap_t set)
 {
-	kernel_cap_t dest;
-	dest = cap_drop(a, set);
-	return cap_isclear(dest);
+	return !(a.val & ~set.val);
 }
 
 /* Used to decide between falling back on the old suser() or fsuser(). */
 
 static inline kernel_cap_t cap_drop_fs_set(const kernel_cap_t a)
 {
-	const kernel_cap_t __cap_fs_set = CAP_FS_SET;
-	return cap_drop(a, __cap_fs_set);
+	return cap_drop(a, CAP_FS_SET);
 }
 
 static inline kernel_cap_t cap_raise_fs_set(const kernel_cap_t a,
 					    const kernel_cap_t permitted)
 {
-	const kernel_cap_t __cap_fs_set = CAP_FS_SET;
-	return cap_combine(a,
-			   cap_intersect(permitted, __cap_fs_set));
+	return cap_combine(a, cap_intersect(permitted, CAP_FS_SET));
 }
 
 static inline kernel_cap_t cap_drop_nfsd_set(const kernel_cap_t a)
 {
-	const kernel_cap_t __cap_fs_set = CAP_NFSD_SET;
-	return cap_drop(a, __cap_fs_set);
+	return cap_drop(a, CAP_NFSD_SET);
 }
 
 static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a,
 					      const kernel_cap_t permitted)
 {
-	const kernel_cap_t __cap_nfsd_set = CAP_NFSD_SET;
-	return cap_combine(a,
-			   cap_intersect(permitted, __cap_nfsd_set));
+	return cap_combine(a, cap_intersect(permitted, CAP_NFSD_SET));
 }
 
 #ifdef CONFIG_MULTIUSER
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
deleted file mode 100644
index b17f3cd18334..000000000000
--- a/include/linux/compiler-intel.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_COMPILER_TYPES_H
-#error "Please don't include <linux/compiler-intel.h> directly, include <linux/compiler.h> instead."
-#endif
-
-#ifdef __ECC
-
-/* Compiler specific definitions for Intel ECC compiler */
-
-#include <asm/intrinsics.h>
-
-/* Intel ECC compiler doesn't support gcc specific asm stmts.
- * It uses intrinsics to do the equivalent things.
- */
-
-#define barrier() __memory_barrier()
-#define barrier_data(ptr) barrier()
-
-#define RELOC_HIDE(ptr, off)					\
-  ({ unsigned long __ptr;					\
-     __ptr = (unsigned long) (ptr);				\
-    (typeof(ptr)) (__ptr + (off)); })
-
-/* This should act as an optimization barrier on var.
- * Given that this compiler does not have inline assembly, a compiler barrier
- * is the best we can do.
- */
-#define OPTIMIZER_HIDE_VAR(var) barrier()
-
-#endif
-
-/* icc has this, but it's called _bswap16 */
-#define __HAVE_BUILTIN_BSWAP16__
-#define __builtin_bswap16 _bswap16
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 4a3bd114a24f..e659cb6fded3 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -64,16 +64,10 @@
  * compiler should see some alignment anyway, when the return value is
  * massaged by 'flags = ptr & 3; ptr &= ~3;').
  *
- * Optional: not supported by icc
- *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute
  * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned
  */
-#if __has_attribute(__assume_aligned__)
-# define __assume_aligned(a, ...)       __attribute__((__assume_aligned__(a, ## __VA_ARGS__)))
-#else
-# define __assume_aligned(a, ...)
-#endif
+#define __assume_aligned(a, ...)        __attribute__((__assume_aligned__(a, ## __VA_ARGS__)))
 
 /*
  * Note the long name.
@@ -85,7 +79,6 @@
 /*
  * Optional: only supported since gcc >= 9
  * Optional: not supported by clang
- * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-copy-function-attribute
  */
@@ -98,7 +91,6 @@
 /*
  * Optional: not supported by gcc
  * Optional: only supported since clang >= 14.0
- * Optional: not supported by icc
  *
  * clang: https://clang.llvm.org/docs/AttributeReference.html#diagnose_as_builtin
  */
@@ -122,7 +114,6 @@
 
 /*
  * Optional: not supported by clang
- * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute
  */
@@ -236,7 +227,6 @@
 /*
  * Optional: only supported since gcc >= 8
  * Optional: not supported by clang
- * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute
  */
@@ -267,7 +257,6 @@
 
 /*
  * Optional: not supported by gcc.
- * Optional: not supported by icc.
  *
  * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable
  */
@@ -287,7 +276,6 @@
  * Note: the "type" argument should match any __builtin_object_size(p, type) usage.
  *
  * Optional: not supported by gcc.
- * Optional: not supported by icc.
  *
  * clang: https://clang.llvm.org/docs/AttributeReference.html#pass-object-size-pass-dynamic-object-size
  */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 690c7c826fbf..547ea1ff806e 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -120,8 +120,6 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 /* Compiler specific macros. */
 #ifdef __clang__
 #include <linux/compiler-clang.h>
-#elif defined(__INTEL_COMPILER)
-#include <linux/compiler-intel.h>
 #elif defined(__GNUC__)
 /* The above compilers also define __GNUC__, so order is important here. */
 #include <linux/compiler-gcc.h>
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 10c92bd9b807..63d637d18e79 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -50,8 +50,41 @@ static inline void set_nr_cpu_ids(unsigned int nr)
 #endif
 }
 
-/* Deprecated. Always use nr_cpu_ids. */
-#define nr_cpumask_bits	nr_cpu_ids
+/*
+ * We have several different "preferred sizes" for the cpumask
+ * operations, depending on operation.
+ *
+ * For example, the bitmap scanning and operating operations have
+ * optimized routines that work for the single-word case, but only when
+ * the size is constant. So if NR_CPUS fits in one single word, we are
+ * better off using that small constant, in order to trigger the
+ * optimized bit finding. That is 'small_cpumask_size'.
+ *
+ * The clearing and copying operations will similarly perform better
+ * with a constant size, but we limit that size arbitrarily to four
+ * words. We call this 'large_cpumask_size'.
+ *
+ * Finally, some operations just want the exact limit, either because
+ * they set bits or just don't have any faster fixed-sized versions. We
+ * call this just 'nr_cpumask_bits'.
+ *
+ * Note that these optional constants are always guaranteed to be at
+ * least as big as 'nr_cpu_ids' itself is, and all our cpumask
+ * allocations are at least that size (see cpumask_size()). The
+ * optimization comes from being able to potentially use a compile-time
+ * constant instead of a run-time generated exact number of CPUs.
+ */
+#if NR_CPUS <= BITS_PER_LONG
+  #define small_cpumask_bits ((unsigned int)NR_CPUS)
+  #define large_cpumask_bits ((unsigned int)NR_CPUS)
+#elif NR_CPUS <= 4*BITS_PER_LONG
+  #define small_cpumask_bits nr_cpu_ids
+  #define large_cpumask_bits ((unsigned int)NR_CPUS)
+#else
+  #define small_cpumask_bits nr_cpu_ids
+  #define large_cpumask_bits nr_cpu_ids
+#endif
+#define nr_cpumask_bits nr_cpu_ids
 
 /*
  * The following particular system cpumasks and operations manage
@@ -126,7 +159,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  */
 static inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
-	return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits);
+	return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
 
 /**
@@ -137,7 +170,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  */
 static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
-	return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits);
+	return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
 
 /**
@@ -150,7 +183,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 static inline
 unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
-	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits);
+	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
 /**
@@ -161,7 +194,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
  */
 static inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
-	return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits);
+	return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
 
 /**
@@ -177,7 +210,7 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
 	/* -1 is a legal arg here. */
 	if (n != -1)
 		cpumask_check(n);
-	return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+	return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1);
 }
 
 /**
@@ -192,7 +225,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 	/* -1 is a legal arg here. */
 	if (n != -1)
 		cpumask_check(n);
-	return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
+	return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1);
 }
 
 #if NR_CPUS == 1
@@ -235,7 +268,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 	if (n != -1)
 		cpumask_check(n);
 	return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
-		nr_cpumask_bits, n + 1);
+		small_cpumask_bits, n + 1);
 }
 
 /**
@@ -246,17 +279,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu(cpu, mask)				\
-	for_each_set_bit(cpu, cpumask_bits(mask), nr_cpumask_bits)
-
-/**
- * for_each_cpu_not - iterate over every cpu in a complemented mask
- * @cpu: the (optionally unsigned) integer iterator
- * @mask: the cpumask pointer
- *
- * After the loop, cpu is >= nr_cpu_ids.
- */
-#define for_each_cpu_not(cpu, mask)				\
-	for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits)
+	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 #if NR_CPUS == 1
 static inline
@@ -290,7 +313,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu_wrap(cpu, mask, start)				\
-	for_each_set_bit_wrap(cpu, cpumask_bits(mask), nr_cpumask_bits, start)
+	for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start)
 
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
@@ -307,7 +330,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu_and(cpu, mask1, mask2)				\
-	for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
+	for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
 
 /**
  * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding
@@ -325,7 +348,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * After the loop, cpu is >= nr_cpu_ids.
  */
 #define for_each_cpu_andnot(cpu, mask1, mask2)				\
-	for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
+	for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
 
 /**
  * cpumask_any_but - return a "random" in a cpumask, but not this one.
@@ -356,7 +379,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  */
 static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
 {
-	return find_nth_bit(cpumask_bits(srcp), nr_cpumask_bits, cpumask_check(cpu));
+	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
 }
 
 /**
@@ -372,7 +395,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
 	return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
-				nr_cpumask_bits, cpumask_check(cpu));
+				small_cpumask_bits, cpumask_check(cpu));
 }
 
 /**
@@ -388,7 +411,7 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
 	return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
-				nr_cpumask_bits, cpumask_check(cpu));
+				small_cpumask_bits, cpumask_check(cpu));
 }
 
 /**
@@ -408,7 +431,7 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp
 	return find_nth_and_andnot_bit(cpumask_bits(srcp1),
 					cpumask_bits(srcp2),
 					cpumask_bits(srcp3),
-					nr_cpumask_bits, cpumask_check(cpu));
+					small_cpumask_bits, cpumask_check(cpu));
 }
 
 #define CPU_BITS_NONE						\
@@ -498,6 +521,10 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *
  */
 static inline void cpumask_setall(struct cpumask *dstp)
 {
+	if (small_const_nbits(small_cpumask_bits)) {
+		cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
+		return;
+	}
 	bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits);
 }
 
@@ -507,7 +534,7 @@ static inline void cpumask_setall(struct cpumask *dstp)
  */
 static inline void cpumask_clear(struct cpumask *dstp)
 {
-	bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits);
+	bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
 }
 
 /**
@@ -523,7 +550,7 @@ static inline bool cpumask_and(struct cpumask *dstp,
 			       const struct cpumask *src2p)
 {
 	return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
-				       cpumask_bits(src2p), nr_cpumask_bits);
+				       cpumask_bits(src2p), small_cpumask_bits);
 }
 
 /**
@@ -536,7 +563,7 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
 			      const struct cpumask *src2p)
 {
 	bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
-				      cpumask_bits(src2p), nr_cpumask_bits);
+				      cpumask_bits(src2p), small_cpumask_bits);
 }
 
 /**
@@ -550,7 +577,7 @@ static inline void cpumask_xor(struct cpumask *dstp,
 			       const struct cpumask *src2p)
 {
 	bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
-				       cpumask_bits(src2p), nr_cpumask_bits);
+				       cpumask_bits(src2p), small_cpumask_bits);
 }
 
 /**
@@ -566,19 +593,7 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
 				  const struct cpumask *src2p)
 {
 	return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
-					  cpumask_bits(src2p), nr_cpumask_bits);
-}
-
-/**
- * cpumask_complement - *dstp = ~*srcp
- * @dstp: the cpumask result
- * @srcp: the input to invert
- */
-static inline void cpumask_complement(struct cpumask *dstp,
-				      const