diff options
Diffstat (limited to 'include')
53 files changed, 574 insertions, 439 deletions
diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index df30f11b4a46..699650f81970 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -126,7 +126,7 @@ static inline void put_unaligned_le24(const u32 val, void *p) __put_unaligned_le24(val, p); } -static inline void __put_unaligned_be48(const u64 val, __u8 *p) +static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = val >> 40; *p++ = val >> 32; diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 4b52e12c2ae8..ace3de8d1ee7 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -42,16 +42,15 @@ struct kunit_loc { /** * struct kunit_assert - Data for printing a failed assertion or expectation. - * @format: a function which formats the data in this kunit_assert to a string. * * Represents a failed expectation/assertion. Contains all the data necessary to * format a string to a user reporting the failure. */ -struct kunit_assert { - void (*format)(const struct kunit_assert *assert, - const struct va_format *message, - struct string_stream *stream); -}; +struct kunit_assert {}; + +typedef void (*assert_format_t)(const struct kunit_assert *assert, + const struct va_format *message, + struct string_stream *stream); void kunit_assert_prologue(const struct kunit_loc *loc, enum kunit_assert_type type, @@ -72,16 +71,6 @@ void kunit_fail_assert_format(const struct kunit_assert *assert, struct string_stream *stream); /** - * KUNIT_INIT_FAIL_ASSERT_STRUCT - Initializer for &struct kunit_fail_assert. - * - * Initializes a &struct kunit_fail_assert. Intended to be used in - * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. - */ -#define KUNIT_INIT_FAIL_ASSERT_STRUCT { \ - .assert = { .format = kunit_fail_assert_format }, \ -} - -/** * struct kunit_unary_assert - Represents a KUNIT_{EXPECT|ASSERT}_{TRUE|FALSE} * @assert: The parent of this type. * @condition: A string representation of a conditional expression. @@ -110,7 +99,6 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_UNARY_ASSERT_STRUCT(cond, expect_true) { \ - .assert = { .format = kunit_unary_assert_format }, \ .condition = cond, \ .expected_true = expect_true \ } @@ -145,7 +133,6 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_PTR_NOT_ERR_STRUCT(txt, val) { \ - .assert = { .format = kunit_ptr_not_err_assert_format }, \ .text = txt, \ .value = val \ } @@ -190,7 +177,6 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a binary assert like * kunit_binary_assert, kunit_binary_ptr_assert, etc. * - * @format_func: a function which formats the assert to a string. * @text_: Pointer to a kunit_binary_assert_text. * @left_val: The actual evaluated value of the expression in the left slot. * @right_val: The actual evaluated value of the expression in the right slot. @@ -200,11 +186,9 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * fields but with different types for left_val/right_val. * This is ultimately used by binary assertion macros like KUNIT_EXPECT_EQ, etc. */ -#define KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - text_, \ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(text_, \ left_val, \ right_val) { \ - .assert = { .format = format_func }, \ .text = text_, \ .left_value = left_val, \ .right_value = right_val \ diff --git a/include/kunit/resource.h b/include/kunit/resource.h index 09c2b34d1c61..cf6fb8f2ac1b 100644 --- a/include/kunit/resource.h +++ b/include/kunit/resource.h @@ -301,22 +301,6 @@ typedef bool (*kunit_resource_match_t)(struct kunit *test, void *match_data); /** - * kunit_resource_instance_match() - Match a resource with the same instance. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_data: The resource pointer to match against. - * - * An instance of kunit_resource_match_t that matches a resource whose - * allocation matches @match_data. - */ -static inline bool kunit_resource_instance_match(struct kunit *test, - struct kunit_resource *res, - void *match_data) -{ - return res->data == match_data; -} - -/** * kunit_resource_name_match() - Match a resource with the same name. * @test: Test case to which the resource belongs. * @res: The resource. diff --git a/include/kunit/test.h b/include/kunit/test.h index 20cc4770cb3f..b1ab6b32216d 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -473,30 +473,30 @@ void kunit_do_failed_assertion(struct kunit *test, const struct kunit_loc *loc, enum kunit_assert_type type, const struct kunit_assert *assert, + assert_format_t assert_format, const char *fmt, ...); -#define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ - if (unlikely(!(pass))) { \ - static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \ - struct assert_class __assertion = INITIALIZER; \ - kunit_do_failed_assertion(test, \ - &__loc, \ - assert_type, \ - &__assertion.assert, \ - fmt, \ - ##__VA_ARGS__); \ - } \ +#define _KUNIT_FAILED(test, assert_type, assert_class, assert_format, INITIALIZER, fmt, ...) do { \ + static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \ + const struct assert_class __assertion = INITIALIZER; \ + kunit_do_failed_assertion(test, \ + &__loc, \ + assert_type, \ + &__assertion.assert, \ + assert_format, \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) \ - KUNIT_ASSERTION(test, \ - assert_type, \ - false, \ - kunit_fail_assert, \ - KUNIT_INIT_FAIL_ASSERT_STRUCT, \ - fmt, \ - ##__VA_ARGS__) + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_fail_assert, \ + kunit_fail_assert_format, \ + {}, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_FAIL() - Always causes a test to fail when evaluated. @@ -521,14 +521,19 @@ void kunit_do_failed_assertion(struct kunit *test, expected_true, \ fmt, \ ...) \ - KUNIT_ASSERTION(test, \ - assert_type, \ - !!(condition) == !!expected_true, \ - kunit_unary_assert, \ - KUNIT_INIT_UNARY_ASSERT_STRUCT(#condition, \ - expected_true), \ - fmt, \ - ##__VA_ARGS__) +do { \ + if (likely(!!(condition) == !!expected_true)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_unary_assert, \ + kunit_unary_assert_format, \ + KUNIT_INIT_UNARY_ASSERT_STRUCT(#condition, \ + expected_true), \ + fmt, \ + ##__VA_ARGS__); \ +} while (0) #define KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, fmt, ...) \ KUNIT_UNARY_ASSERTION(test, \ @@ -578,16 +583,18 @@ do { \ .right_text = #right, \ }; \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - __left op __right, \ - assert_class, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - &__text, \ - __left, \ - __right), \ - fmt, \ - ##__VA_ARGS__); \ + if (likely(__left op __right)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + assert_class, \ + format_func, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(&__text, \ + __left, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_BINARY_INT_ASSERTION(test, \ @@ -636,16 +643,19 @@ do { \ .right_text = #right, \ }; \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - strcmp(__left, __right) op 0, \ - kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT(kunit_binary_str_assert_format,\ - &__text, \ - __left, \ - __right), \ - fmt, \ - ##__VA_ARGS__); \ + if (likely(strcmp(__left, __right) op 0)) \ + break; \ + \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_binary_str_assert, \ + kunit_binary_str_assert_format, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(&__text, \ + __left, \ + __right), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) #define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ @@ -656,14 +666,16 @@ do { \ do { \ const typeof(ptr) __ptr = (ptr); \ \ - KUNIT_ASSERTION(test, \ - assert_type, \ - !IS_ERR_OR_NULL(__ptr), \ - kunit_ptr_not_err_assert, \ - KUNIT_INIT_PTR_NOT_ERR_STRUCT(#ptr, \ - __ptr), \ - fmt, \ - ##__VA_ARGS__); \ + if (!IS_ERR_OR_NULL(__ptr)) \ + break; \ + \ + _KUNIT_FAILED(test, \ + assert_type, \ + kunit_ptr_not_err_assert, \ + kunit_ptr_not_err_assert_format, \ + KUNIT_INIT_PTR_NOT_ERR_STRUCT(#ptr, __ptr), \ + fmt, \ + ##__VA_ARGS__); \ } while (0) /** diff --git a/include/linux/bitops.h b/include/linux/bitops.h index d7dd83fafeba..2ba557e067fe 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -347,10 +347,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ new__ = (old__ & ~mask__) | bits__; \ - } while (cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) @@ -362,11 +362,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ + if (old__ & test__) \ + break; \ new__ = old__ & ~clear__; \ - } while (!(old__ & test__) && \ - cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3e187a02924f..50e358a19d98 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -580,9 +580,9 @@ struct request_queue { #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ + (1UL << QUEUE_FLAG_SAME_COMP) | \ + (1UL << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e7f2fb2fc207..99c1726be6ee 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -207,7 +207,6 @@ struct ceph_msg_data_cursor { struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ - bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK @@ -498,8 +497,7 @@ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq); void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor, struct ceph_msg *msg, size_t length); struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, - size_t *page_offset, size_t *length, - bool *last_piece); + size_t *page_offset, size_t *length); void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes); u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..6e01f10f0d88 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 23b102b4349e..f2a9f2274c3b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -682,11 +682,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2108b5695327..267cd06b54a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,15 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * @@ -118,8 +129,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually @@ -1303,6 +1315,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); diff --git a/include/linux/clk.h b/include/linux/clk.h index c13061cabdfc..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -799,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 3484309b59bf..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include <linux/bits.h> + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2f065ad97541..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -174,8 +174,9 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -188,8 +189,9 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -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); } @@ -229,8 +231,9 @@ static inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -260,8 +263,8 @@ static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - /* n is a prior cpu */ - cpumask_check(n + 1); + if (n != -1) + cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, diff --git a/include/linux/damon.h b/include/linux/damon.h index ed5470f50bab..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,6 +484,12 @@ static inline struct damon_region *damon_first_region(struct damon_target *t) return list_first_entry(&t->regions_list, struct damon_region, list); } +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 84a466b176cf..d95ab85f96ba 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -253,7 +253,6 @@ static __always_inline void arch_exit_to_user_mode(void) { } /** * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs - * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 95fda85aa195..8b4f93e84868 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -214,8 +214,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, @@ -327,8 +327,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } diff --git a/include/linux/init.h b/include/linux/init.h index a0a90cd73ebe..077d7f93b402 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -/* Used for contructor calls. */ +/* Used for constructor calls. */ typedef void (*ctor_fn_t)(void); struct file_system_type; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index aa4d90a53866..f5b687a787a3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,9 +34,6 @@ struct io_file_table { unsigned int alloc_hint; }; -struct io_notif; -struct io_notif_slot; - struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -242,8 +239,6 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; - struct io_notif_slot *notif_slots; - unsigned nr_notif_slots; struct io_submit_state submit_state; diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h new file mode 100644 index 000000000000..c006cf0a25f3 --- /dev/null +++ b/include/linux/iova_bitmap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Oracle and/or its affiliates. + * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved + */ +#ifndef _IOVA_BITMAP_H_ +#define _IOVA_BITMAP_H_ + +#include <linux/types.h> + +struct iova_bitmap; + +typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque); + +struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, + unsigned long page_size, + u64 __user *data); +void iova_bitmap_free(struct iova_bitmap *bitmap); +int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, + iova_bitmap_fn_t fn); +void iova_bitmap_set(struct iova_bitmap *bitmap, + unsigned long iova, size_t length); + +#endif diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e3e8c8662b49..e8240cf2611a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -11,6 +11,7 @@ #include <linux/refcount.h> #include <linux/rhashtable-types.h> #include <linux/sysctl.h> +#include <linux/percpu_counter.h> struct user_namespace; @@ -36,8 +37,8 @@ struct ipc_namespace { unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; - atomic_t msg_bytes; - atomic_t msg_hdrs; + struct percpu_counter percpu_msg_bytes; + struct percpu_counter percpu_msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 3a091d0710ae..d5e6024cb2a8 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -44,7 +44,8 @@ static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ .data = typecheck_irq_init_cb(fn), }, -#define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ + +#define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ {}, \ }; \ MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ @@ -56,6 +57,7 @@ static struct platform_driver drv_name##_driver = { \ .owner = THIS_MODULE, \ .of_match_table = drv_name##_irqchip_match_table, \ .suppress_bind_attrs = true, \ + __VA_ARGS__ \ }, \ }; \ builtin_platform_driver(drv_name##_driver) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 1cd4e36890fb..844a8e30e6de 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -169,6 +169,7 @@ int generic_handle_irq_safe(unsigned int irq); * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); +int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq); int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3bfebde5a1a6..e27bd4f55d84 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode) static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { - u64 cur, old; + u64 cur = inode_peek_iversion_raw(inode); - cur = inode_peek_iversion_raw(inode); - for (;;) { + do { if (cur > val) break; - old = atomic64_cmpxchg(&inode->i_version, cur, val); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** @@ -177,56 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) I_VERSION_QUERIED); } -/** - * inode_maybe_inc_iversion - increments i_version - * @inode: inode with the i_version that should be updated - * @force: increment the counter even if it's not necessary? - * - * Every time the inode is modified, the i_version field must be seen to have - * changed by any observer. - * - * If "force" is set or the QUERIED flag is set, then ensure that we increment - * the value, and clear the queried flag. - * - * In the common case where neither is set, then we can return "false" without - * updating i_version. - * - * If this function returns false, and no other metadata has changed, then we - * can avoid logging the metadata. - */ -static inline bool -inode_maybe_inc_iversion(struct inode *inode, bool force) -{ - u64 cur, old, new; - - /* - * The i_version field is not strictly ordered with any other inode - * information, but the legacy inode_inc_iversion code used a spinlock - * to serialize increments. - * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. - * - * This barrier pairs with the barrier in inode_query_iversion() - */ - smp_mb(); - cur = inode_peek_iversion_raw(inode); - for (;;) { - /* If flag is clear then we needn't do anything */ - if (!force && !(cur & I_VERSION_QUERIED)) - return false; - - /* Since lowest bit is flag, add 2 to avoid it */ - new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } - return true; -} - +bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version @@ -304,10 +250,10 @@ inode_peek_iversion(const struct inode *inode) static inline u64 inode_query_iversion(struct inode *inode) { - u64 cur, old, new; + u64 cur, new; cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* @@ -320,11 +266,7 @@ inode_query_iversion(struct inode *inode) } new = cur | I_VERSION_QUERIED; - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 13e6c4b58f07..41a686996aaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -427,7 +427,7 @@ extern int kexec_load_disabled; extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); +ssize_t crash_get_memory_size(void); #ifndef arch_kexec_protect_crashkres /* diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 47ad3b104d9e..139d05b26f82 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -10,6 +10,9 @@ #ifndef MDEV_H #define MDEV_H +#include <linux/device.h> +#include <linux/uuid.h> + struct mdev_type; struct mdev_device { @@ -20,67 +23,67 @@ struct mdev_device { bool active; }; -static inline struct mdev_device *to_mdev_device(struct device *dev) -{ - return container_of(dev, struct mdev_device, dev); -} +struct mdev_type { + /* set by the driver before calling mdev_register parent: */ + const char *sysfs_name; + const char *pretty_name; -unsigned int mdev_get_type_group_id(struct mdev_device *mdev); -unsigned int mtype_get_type_group_id(struct mdev_type *mtype); -struct device *mtype_get_parent_dev(struct mdev_type *mtype); + /* set by the core, can be used drivers */ + struct mdev_parent *parent; -/* interface for exporting mdev supported type attributes */ -struct mdev_type_attribute { - struct attribute attr; - ssize_t (*show)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf); - ssize_t (*store)(struct mdev_type *mtype, - struct mdev_type_attribute *attr, const char *buf, - size_t count); + /* internal only */ + struct kobject kobj; + struct kobject *devices_kobj; }; -#define MDEV_TYPE_ATTR(_name, _mode, _show, _store) \ -struct mdev_type_attribute mdev_type_attr_##_name = \ - __ATTR(_name, _mode, _show, _store) -#define MDEV_TYPE_ATTR_RW(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RW(_name) -#define MDEV_TYPE_ATTR_RO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_RO(_name) -#define MDEV_TYPE_ATTR_WO(_name) \ - struct mdev_type_attribute mdev_type_attr_##_name = __ATTR_WO(_name) +/* embedded into the struct device that the mdev devices hang off */ +struct mdev_parent { + struct device *dev; + struct mdev_driver *mdev_driver; + struct kset *mdev_types_kset; + /* Synchronize device creation/removal with parent unregistration */ + struct rw_semaphore unreg_sem; + struct mdev_type **types; + unsigned int nr_types; + atomic_t available_instances; +}; + +static inline struct mdev_device *to_mdev_device(struct device *dev) +{ + return container_of(dev, struct mdev_device, dev); +} /** * struct mdev_driver - Mediated device driver + * @device_api: string to return for the device_api sysfs + * @max_instances: maximum number of instances supported (optional) * @probe: called when new device created * @remove: called when device removed - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. + * @get_available: Return the max number of instances that can be created + * @show_description: Print a description of the mtype * @driver: device driver structure - * **/ struct mdev_driver { + const char *device_api; + unsigned int max_instances; int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); - struct attribute_group **supported_type_groups; + unsigned int (*get_available)(struct mdev_type *mtype); + ssize_t (*show_description)(struct mdev_type *mtype, char *buf); struct device_driver driver; }; -extern struct bus_type mdev_bus_type; - -int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver); -void mdev_unregister_device(struct device *dev); +int mdev_register_parent(struct mdev_parent *parent, struct device *dev, + struct mdev_driver *mdev_driver, struct mdev_type **types, + unsigned int nr_types); +void mdev_unregister_parent(struct mdev_parent *parent); int mdev_register_driver(struct mdev_driver *drv); void mdev_unregister_driver(struct mdev_driver *drv); -struct device *mdev_parent_dev(struct mdev_device *mdev); static inline struct device *mdev_dev(struct mdev_device *mdev) { return &mdev->dev; } -static inline struct mdev_device *mdev_from_dev(struct device *dev) -{ - return dev->bus == &mdev_bus_type ? to_mdev_device(dev) : NULL; -} #endif /* MDEV_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 704a04f5a074..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -197,11 +199,24 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 8a30de08e913..c726ea781255 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -293,6 +293,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 83fccd0c9bba..d6d3eae2f145 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -37,9 +37,8 @@ extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); -extern void of_irq_init(const struct of_device_id *matches); - #ifdef CONFIG_OF_IRQ +extern void of_irq_init(const struct of_device_id *matches); extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); @@ -57,6 +56,9 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline void of_irq_init(const struct of_device_id *matches) +{ +} static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 01861eebed79..8ed5fba6d156 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -15,6 +15,9 @@ #include <linux/types.h> #include <linux/gfp.h> +/* percpu_counter batch for local add or sub */ +#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX + #ifdef CONFIG_SMP struct percpu_counter { @@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +/* + * With percpu_counter_add_local() and percpu_counter_sub_local(), counts + * are accumulated in local per cpu counter and not in fbc->count until + * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter + * write efficient. + * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be + * used to add up the counts from each CPU to account for all the local + * counts. So percpu_counter_add_local() and percpu_counter_sub_local() + * should be used when a counter is updated frequently and read rarely. + */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); +} + static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); @@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) preempt_enable(); } +/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, amount); +} + static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { @@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) percpu_counter_add(fbc, -amount); } +static inline void +percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_local(fbc, -amount); +} + #endif /* _LINUX_PERCPU_COUNTER_H */ diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/poll.h> #include <linux/cgroup-defs.h> +#include <linux/cgroup.h> struct seq_file; struct css_set; @@ -18,10 +19,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); @@ -34,9 +31,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -16,13 +16,6 @@ enum psi_task_count { NR_MEMSTALL, NR_RUNNING, /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, - /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. * For memory it's not so simple because of page reclaimers: @@ -32,22 +25,27 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -63,11 +61,17 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -147,6 +151,9 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -188,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 77f68f8b795c..ffb6eb55cd13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -870,8 +870,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 81cab4b01edc..d6c48163c6de 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -127,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr) void put_task_struct_rcu_user(struct task_struct *task); +/* Free all architecture-specific resources held by a thread. */ +void release_thread(struct task_struct *dead_task); + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9fcf534f2d92..7be5bb4c94b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -803,6 +803,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -982,6 +983,7 @@ struct sk_buff { #endif __u8 slow_gro:1; __u8 csum_not_inet:1; + __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 75eea5ebb179..770ef2cb5775 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -246,6 +246,7 @@ void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt); +void rpc_clnt_disconnect(struct rpc_clnt *clnt); void rpc_cleanup_clids(void); static inline int rpc_reply_expected(struct rpc_task *task) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index baeca2f564dc..b8ca3ecaf8d7 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -209,11 +209,17 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req); void rpc_put_task(struct rpc_task *); void rpc_put_task_async(struct rpc_task *); +bool rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status); +void rpc_task_try_cancel(struct rpc_task *task, int error); void rpc_signal_task(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); void rpc_killall_tasks(struct rpc_clnt *); +unsigned long rpc_cancel_tasks(struct rpc_clnt *clnt, int error, + bool (*fnmatch)(const struct rpc_task *, + const void *), + const void *data); void rpc_execute(struct rpc_task *); void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *); void rpc_init_wait_queue(struct rpc_wait_queue *, const char *); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e05ddc6fe6a5..e7cebeb875dd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -14,6 +14,7 @@ #include <linux/workqueue.h> #include <linux/poll.h> #include <uapi/linux/vfio.h> +#include <linux/iova_bitmap.h> struct kvm; @@ -33,10 +34,11 @@ struct vfio_device { struct device *dev; const struct vfio_device_ops *ops; /* - * mig_ops is a static property of the vfio_device which must be set - * prior to registering the vfio_device. + * mig_ops/log_ops is a static property of the vfio_device which must + * be set prior to registering the vfio_device. */ const struct vfio_migration_ops *mig_ops; + const struct vfio_log_ops *log_ops; struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; @@ -45,7 +47,9 @@ struct vfio_device { struct kvm *kvm; /* Members below here are private, not for driver use */ - refcount_t refcount; + unsigned int index; + struct device device; /* device.kref covers object life circle */ + refcount_t refcount; /* user count on registered device*/ unsigned int open_count; struct completion comp; struct list_head group_next; @@ -55,6 +59,8 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @init: initialize private fields in device structure + * @release: Reclaim private fields in device structure * @open_device: Called when the first file descriptor is opened for this device * @close_device: Opposite of open_device * @read: Perform read(2) on device file descriptor @@ -72,6 +78,8 @@ struct vfio_device { */ struct vfio_device_ops { char *name; + int (*init)(struct vfio_device *vdev); + void (*release)(struct vfio_device *vdev); int (*open_device)(struct vfio_device *vdev); void (*close_device)(struct vfio_device *vdev); ssize_t (*read)(struct vfio_device *vdev, char __user *buf, @@ -109,6 +117,28 @@ struct vfio_migration_ops { }; /** + * @log_start: Optional callback to ask the device start DMA logging. + * @log_stop: Optional callback to ask the device stop DMA logging. + * @log_read_and_clear: Optional callback to ask the device read + * and clear the dirty DMAs in some given range. + * + * The vfio core implementation of the DEVICE_FEATURE_DMA_LOGGING_ set + * of features does not track logging state relative to the device, + * therefore the device implementation of vfio_log_ops must handle + * arbitrary user requests. This includes rejecting subsequent calls + * to log_start without an intervening log_stop, as well as graceful + * handling of log_stop and log_read_and_clear from invalid states. + */ +struct vfio_log_ops { + int (*log_start)(struct vfio_device *device, + struct rb_root_cached *ranges, u32 nnodes, u64 *page_size); + int (*log_stop)(struct vfio_device *device); + int (*log_read_and_clear)(struct vfio_device *device, + unsigned long iova, unsigned long length, + struct iova_bitmap *dirty); +}; + +/** * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl * @flags: Arg from the device_feature op * @argsz: Arg from the device_feature op @@ -137,9 +167,23 @@ static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, return 1; } -void vfio_init_group_dev(struct vfio_device *device, struct device *dev, - const struct vfio_device_ops *ops); -void vfio_uninit_group_dev(struct vfio_device *device); +struct vfio_device *_vfio_alloc_device(size_t size, struct device *dev, + const struct vfio_device_ops *ops); +#define vfio_alloc_device(dev_struct, member, dev, ops) \ + container_of(_vfio_alloc_device(sizeof(struct dev_struct) + \ + BUILD_BUG_ON_ZERO(offsetof( \ + struct dev_struct, member)), \ + dev, ops), \ + struct dev_struct, member) + +int vfio_init_device(struct vfio_device *device, struct device *dev, + const struct vfio_device_ops *ops); +void vfio_free_device(struct vfio_device *device); +static inline void vfio_put_device(struct vfio_device *device) +{ + put_device(&device->device); +} + int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); @@ -155,6 +199,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, * External user API */ struct iommu_group *vfio_file_iommu_group(struct file *file); +bool vfio_file_is_group(struct file *file); bool vfio_file_enforced_coherent(struct file *file); void vfio_file_set_kvm(struct file *file, struct kvm *kvm); bool vfio_file_has_dev(struct file *file, struct vfio_device *device); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 5579ece4347b..367fd79226a3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -20,39 +20,10 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 - #define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) -/* Special capability IDs predefined access */ -#define PCI_CAP_ID_INVALID 0xFF /* default raw access */ -#define PCI_CAP_ID_INVALID_VIRT 0xFE /* default virt access */ - -/* Cap maximum number of ioeventfds per device (arbitrary) */ -#define VFIO_PCI_IOEVENTFD_MAX 1000 - -struct vfio_pci_ioeventfd { - struct list_head next; - struct vfio_pci_core_device *vdev; - struct virqfd *virqfd; - void __iomem *addr; - uint64_t data; - loff_t pos; - int bar; - int count; - bool test_mem; -}; - -struct vfio_pci_irq_ctx { - struct eventfd_ctx *trigger; - struct virqfd *unmask; - struct virqfd *mask; - char *name; - bool masked; - struct irq_bypass_producer producer; -}; - struct vfio_pci_core_device; struct vfio_pci_region; @@ -78,23 +49,6 @@ struct vfio_pci_region { u32 flags; }; -struct vfio_pci_dummy_resource { - struct resource resource; - int index; - struct list_head res_next; -}; - -struct vfio_pci_vf_token { - struct mutex lock; - uuid_t uuid; - int users; -}; - -struct vfio_pci_mmap_vma { - struct vm_area_struct *vma; - struct list_head vma_next; -}; - struct vfio_pci_core_device { struct vfio_device vdev; struct pci_dev *pdev; @@ -124,11 +78,14 @@ struct vfio_pci_core_device { bool needs_reset; bool nointx; bool needs_pm_restore; + bool pm_intx_masked; + bool pm_runtime_engaged; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr; struct eventfd_ctx *err_trigger; struct eventfd_ctx *req_trigger; + struct eventfd_ctx *pm_wake_eventfd_ctx; struct list_head dummy_resources_list; struct mutex ioeventfds_lock; struct list_head ioeventfds_list; @@ -141,100 +98,17 @@ struct vfio_pci_core_device { struct rw_semaphore memory_lock; }; -#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) -#define is_msi(vdev) (vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX) -#define is_msix(vdev) (vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX) -#define is_irq_none(vdev) (!(is_intx(vdev) || is_msi(vdev) || is_msix(vdev))) -#define irq_is(vdev, type) (vdev->irq_type == type) - -void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev); -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev); - -int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, - uint32_t flags, unsigned index, - unsigned start, unsigned count, void *data); - -ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite); - -ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); - -#ifdef CONFIG_VFIO_PCI_VGA -ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, - size_t count, loff_t *ppos, bool iswrite); -#else -static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, - char __user *buf, size_t count, - loff_t *ppos, bool iswrite) -{ - return -EINVAL; -} -#endif - -long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, - uint64_t data, int count, int fd); - -int vfio_pci_init_perm_bits(void); -void vfio_pci_uninit_perm_bits(void); - -int vfio_config_init(struct vfio_pci_core_device *vdev); -void vfio_config_free(struct vfio_pci_core_device *vdev); - -int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data); - -int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, - pci_power_t state); - -bool __vfio_pci_memory_enabled(struct vfio_pci_core_device *vdev); -void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev); -u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev); -void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, - u16 cmd); - -#ifdef CONFIG_VFIO_PCI_IGD -int vfio_pci_igd_init(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_igd_init(struct vfio_pci_core_device *vdev) -{ - return -ENODEV; -} -#endif - -#ifdef CONFIG_VFIO_PCI_ZDEV_KVM -int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps); -int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev); -void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev); -#else -static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, - struct vfio_info_cap *caps) -{ - return -ENODEV; -} - -static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) -{ - return 0; -} - -static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev) -{} -#endif - /* Will be exported for vfio pci drivers usage */ +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga, bool is_disable_idle_d3); void vfio_pci_core_close_device(struct vfio_device *core_vdev); -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops); +int vfio_pci_core_init_dev(struct vfio_device *core_vdev); +void vfio_pci_core_release_dev(struct vfio_device *core_vdev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); extern const struct pci_error_handlers vfio_pci_core_err_handlers; int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, @@ -256,9 +130,4 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); -static inline bool vfio_pci_is_vga(struct pci_dev *pdev) -{ - return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA; -} - #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 2d1b54556eff..e6e34d74dda0 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -26,7 +26,15 @@ struct compat_iw_point { struct __compat_iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ - compat_caddr_t pointer; + + union { + compat_caddr_t pointer; + + /* we need ptr_bytes to make memcpy() run-time destination + * buffer bounds checking happy, nothing special + */ + DECLARE_FLEX_ARRAY(__u8, ptr_bytes); + }; }; #define IW_EV_COMPAT_LCP_LEN offsetof(struct __compat_iw_event, pointer) #define IW_EV_COMPAT_POINT_OFF offsetof(struct compat_iw_point, length) diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index a8994f307fc3..03b64bf876a4 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -185,21 +185,27 @@ static inline int ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) { struct ieee802154_addr_sa *sa; + int ret = 0; sa = &daddr->addr; if (len < IEEE802154_MIN_NAMELEN) return -EINVAL; switch (sa->addr_type) { + case IEEE802154_ADDR_NONE: + break; case IEEE802154_ADDR_SHORT: if (len < IEEE802154_NAMELEN_SHORT) - return -EINVAL; + ret = -EINVAL; break; case IEEE802154_ADDR_LONG: if (len < IEEE802154_NAMELEN_LONG) - return -EINVAL; + ret = -EINVAL; + break; + default: + ret = -EINVAL; break; } - return 0; + return ret; } static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d664ba5812d8..37943ba3a73c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1182,6 +1182,8 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); +void inet6_cleanup_sock(struct sock *sk); +void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, diff --git a/include/net/udp.h b/include/net/udp.h index 5ee88ddf79c3..fee053bcd17c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -247,7 +247,7 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, } /* net/ipv4/udp.c */ -void udp_destruct_sock(struct sock *sk); +void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/udplite.h b/include/net/udplite.h index 0143b373602e..299c14ce2bb9 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -25,14 +25,6 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, return copy_from_iter_full(to, len, &msg->msg_iter) ? 0 : -EFAULT; } -/* Designate sk as UDP-Lite socket */ -static inline int udplite_sk_init(struct sock *sk) -{ - udp_init_sock(sk); - udp_sk(sk)->pcflag = UDPLITE_BIT; - return 0; -} - /* * Checksumming routines */ diff --git a/include/soc/sifive/sifive_ccache.h b/include/soc/sifive/sifive_ccache.h new file mode 100644 index 000000000000..4d4ed49388a0 --- /dev/null +++ b/include/soc/sifive/sifive_ccache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive Composable Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_CCACHE_H +#define __SOC_SIFIVE_CCACHE_H + +extern int register_sifive_ccache_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_ccache_error_notifier(struct notifier_block *nb); + +#define SIFIVE_CCACHE_ERR_TYPE_CE 0 +#define SIFIVE_CCACHE_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_CCACHE_H */ diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h deleted file mode 100644 index 92ade10ed67e..000000000000 --- a/include/soc/sifive/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef __SOC_SIFIVE_L2_CACHE_H -#define __SOC_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* __SOC_SIFIVE_L2_CACHE_H */ diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index ddff03e546e9..35778f953a3f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -592,11 +592,11 @@ int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, #define snd_hdac_stream_readb(dev, reg) \ snd_hdac_reg_readb((dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readb_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readb, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readl_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readl, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) /* update a register, pass without AZX_REG_ prefix */ #define snd_hdac_stream_updatel(dev, reg, mask, val) \ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index eed0315a77a6..0d5d4419139a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1177,6 +1177,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 +#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 733a1cddde30..d7d8e0922376 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -986,6 +986,148 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING_P2P = 5, }; +/* + * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power + * state with the platform-based power management. Device use of lower power + * states depends on factors managed by the runtime power management core, + * including system level support and coordinating support among dependent + * devices. Enabling device low power entry does not guarantee lower power + * usage by the device, nor is a mechanism provided through this feature to + * know the current power state of the device. If any device access happens + * (either from the host or through the vfio uAPI) when the device is in the + * low power state, then the host will move the device out of the low power + * state as necessary prior to the access. Once the access is completed, the + * device may re-enter the low power state. For single shot low power support + * with wake-up notification, see + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below. Access to mmap'd + * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after + * calling LOW_POWER_EXIT. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3 + +/* + * This device feature has the same behavior as + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user + * provides an eventfd for wake-up notification. When the device moves out of + * the low power state for the wake-up, the host will not allow the device to + * re-enter a low power state without a subsequent user call to one of the low + * power entry device feature IOCTLs. Access to mmap'd device regions is + * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the + * low power exit. The low power exit can happen either through LOW_POWER_EXIT + * or through any other access (where the wake-up notification has been + * generated). The access to mmap'd device regions will not trigger low power + * exit. + * + * The notification through the provided eventfd will be generated only when + * the device has entered and is resumed from a low power state after + * calling this device feature IOCTL. A device that has not entered low power + * state, as managed through the runtime power management core, will not + * generate a notification through the provided eventfd on access. Calling the + * LOW_POWER_EXIT feature is optional in the case where notification has been + * signaled on the provided eventfd that a resume from low power has occurred. + */ +struct vfio_device_low_power_entry_with_wakeup { + __s32 wakeup_eventfd; + __u32 reserved; +}; + +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as + * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features. + * This device feature IOCTL may itself generate a wakeup eventfd notification + * in the latter case if the device had previously entered a low power state. + */ +#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5 + +/* + * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging. + * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports + * DMA logging. + * + * DMA logging allows a device to internally record what DMAs the device is + * initiating and report them back to userspace. It is part of the VFIO + * migration infrastructure that allows implementing dirty page tracking + * during the pre copy phase of live migration. Only DMA WRITEs are logged, + * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. + * + * When DMA logging is started a range of IOVAs to monitor is provided and the + * device can optimize its logging to cover only the IOVA range given. Each + * DMA that the device initiates inside the range will be logged by the device + * for later retrieval. + * + * page_size is an input that hints what tracking granularity the device + * should try to achieve. If the device cannot do the hinted page size then + * it's the driver choice which page size to pick based on its support. + * On output the device will return the page size it selected. + * + * ranges is a pointer to an array of + * struct vfio_device_feature_dma_logging_range. + * + * The core kernel code guarantees to support by minimum num_ranges that fit + * into a single kernel page. User space can try higher values but should give + * up if the above can't be achieved as of some driver limitations. + * + * A single call to start device DMA logging can be issued and a matching stop + * should follow at the end. Another start is not allowed in the meantime. + */ +struct vfio_device_feature_dma_logging_control { + __aligned_u64 page_size; + __u32 num_ranges; + __u32 __reserved; + __aligned_u64 ranges; +}; + +struct vfio_device_feature_dma_logging_range { + __aligned_u64 iova; + __aligned_u64 length; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6 + +/* + * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started + * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START + */ +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7 + +/* + * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log + * + * Query the device's DMA log for written pages within the given IOVA range. + * During querying the log is cleared for the IOVA range. + * + * bitmap is a pointer to an array of u64s that will hold the output bitmap + * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits + * is given by: + * bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64)) + * + * The input page_size can be any power of two value and does not have to + * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver + * will format its internal logging to match the reporting page size, possibly + * by replicating bits if the internal page size is lower than requested. + * + * The LOGGING_REPORT will only set bits in the bitmap and never clear or + * perform any initialization of the user provided bitmap. + * + * If any error is returned userspace should assume that the dirty log is + * corrupted. Error recovery is to consider all memory dirty and try to + * restart the dirty tracking, or to abort/restart the whole migration. + * + * If DMA logging is not enabled, an error will be returned. + * + */ +struct vfio_device_feature_dma_logging_report { + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 bitmap; +}; + +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8 + /* -------- API for Type1 VFIO IOMMU -------- */ /** diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index b69e9ba6742b..dcb179de4358 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -247,6 +247,7 @@ enum { * @vid_hdr_offset: VID header offset (use defaults if %0) * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs * @padding: reserved for future, not used, has to be zeroed + * @disable_fm: whether disable fastmap * * This data structure is used to specify MTD device UBI has to attach and the * parameters it has to use. The number which should be assigned to the new UBI @@ -281,13 +282,18 @@ enum { * eraseblocks for new bad eraseblocks, but attempts to use available * eraseblocks (if any). The accepted range is 0-768. If 0 is given, the * default kernel value of %CONFIG_MTD_UBI_BEB_LIMIT will be used. + * + * If @disable_fm is not zero, ubi doesn't create new fastmap even the module + * param 'fm_autoconvert' is set, and existed old fastmap will be destroyed + * after doing full scanning. */ struct ubi_attach_req { __s32 ubi_num; __s32 mtd_num; __s32 vid_hdr_offset; __s16 max_beb_per1024; - __s8 padding[10]; + __s8 disable_fm; + __s8 padding[9]; }; /* diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index dae0f350c678..a34f4271a2e9 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -219,6 +219,7 @@ static inline void xen_preemptible_hcall_end(void) { } void xen_grant_setup_dma_ops(struct device *dev); bool xen_is_grant_dma_device(struct device *dev); bool xen_virtio_mem_acc(struct virtio_device *dev); +bool xen_virtio_restricted_mem_acc(struct virtio_device *dev); #else static inline void xen_grant_setup_dma_ops(struct device *dev) { @@ -234,6 +235,11 @@ static inline bool xen_virtio_mem_acc(struct virtio_device *dev) { return false; } + +static inline bool xen_virtio_restricted_mem_acc(struct virtio_device *dev) +{ + return false; +} #endif /* CONFIG_XEN_GRANT_DMA_OPS */ #endif /* INCLUDE_XEN_OPS_H */ |