diff options
Diffstat (limited to 'include/linux')
139 files changed, 1683 insertions, 979 deletions
diff --git a/include/linux/align.h b/include/linux/align.h new file mode 100644 index 000000000000..2b4acec7b95a --- /dev/null +++ b/include/linux/align.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ALIGN_H +#define _LINUX_ALIGN_H + +#include <linux/const.h> + +/* @a is a power of 2 value */ +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) +#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) +#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +#endif /* _LINUX_ALIGN_H */ diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index 450717299928..58e6c3806c09 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -10,6 +10,8 @@ #include <linux/types.h> +struct amd_iommu; + /* * This is mainly used to communicate information back-and-forth * between SVM and IOMMU for setting up and tearing down posted @@ -33,24 +35,6 @@ extern int amd_iommu_detect(void); extern int amd_iommu_init_hardware(void); /** - * amd_iommu_enable_device_erratum() - Enable erratum workaround for device - * in the IOMMUv2 driver - * @pdev: The PCI device the workaround is necessary for - * @erratum: The erratum workaround to enable - * - * The function needs to be called before amd_iommu_init_device(). - * Possible values for the erratum number are for now: - * - AMD_PRI_DEV_ERRATUM_ENABLE_RESET - Reset PRI capability when PRI - * is enabled - * - AMD_PRI_DEV_ERRATUM_LIMIT_REQ_ONE - Limit number of outstanding PRI - * requests to one - */ -#define AMD_PRI_DEV_ERRATUM_ENABLE_RESET 0 -#define AMD_PRI_DEV_ERRATUM_LIMIT_REQ_ONE 1 - -extern void amd_iommu_enable_device_erratum(struct pci_dev *pdev, u32 erratum); - -/** * amd_iommu_init_device() - Init device for use with IOMMUv2 driver * @pdev: The PCI device to initialize * @pasids: Number of PASIDs to support for this device @@ -212,4 +196,14 @@ static inline int amd_iommu_deactivate_guest_mode(void *data) } #endif /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */ +int amd_iommu_get_num_iommus(void); +bool amd_iommu_pc_supported(void); +u8 amd_iommu_pc_get_max_banks(unsigned int idx); +u8 amd_iommu_pc_get_max_counters(unsigned int idx); +int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, + u64 *value); +int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, + u64 *value); +struct amd_iommu *get_amd_iommu(unsigned int idx); + #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 62c54234576c..6861489a1890 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -55,6 +55,8 @@ #define ARM_SMCCC_OWNER_TRUSTED_OS 50 #define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 +#define ARM_SMCCC_FUNC_QUERY_CALL_UID 0xff01 + #define ARM_SMCCC_QUIRK_NONE 0 #define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ @@ -87,8 +89,47 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_FUNC_QUERY_CALL_UID) + +/* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +/* KVM "vendor specific" services */ +#define ARM_SMCCC_KVM_FUNC_FEATURES 0 +#define ARM_SMCCC_KVM_FUNC_PTP 1 +#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 +#define ARM_SMCCC_KVM_NUM_FUNCS 128 + +#define ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_FEATURES) + #define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 +/* + * ptp_kvm is a feature used for time sync between vm and host. + * ptp_kvm module in guest kernel will get service from host using + * this hypercall ID. + */ +#define ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_PTP) + +/* ptp_kvm counter type ID */ +#define KVM_PTP_VIRT_COUNTER 0 +#define KVM_PTP_PHYS_COUNTER 1 + /* Paravirtualised time calls (defined by ARM DEN0057A) */ #define ARM_SMCCC_HV_PV_TIME_FEATURES \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ diff --git a/include/linux/async.h b/include/linux/async.h index 0a17cd27f348..cce4ad31e8fc 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -112,7 +112,6 @@ async_schedule_dev_domain(async_func_t func, struct device *dev, return async_schedule_node_domain(func, dev, dev_to_node(dev), domain); } -void async_unregister_domain(struct async_domain *domain); extern void async_synchronize_full(void); extern void async_synchronize_full_domain(struct async_domain *domain); extern void async_synchronize_cookie(async_cookie_t cookie); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 70a932470b2d..a36cfcec4e77 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -4,10 +4,13 @@ #ifndef __ASSEMBLY__ -#include <linux/types.h> +#include <linux/align.h> #include <linux/bitops.h> +#include <linux/limits.h> #include <linux/string.h> -#include <linux/kernel.h> +#include <linux/types.h> + +struct device; /* * bitmaps provide bit arrays that consume one or more unsigned @@ -118,54 +121,59 @@ * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ -extern unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); -extern unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); -extern void bitmap_free(const unsigned long *bitmap); +unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); +unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); +void bitmap_free(const unsigned long *bitmap); + +/* Managed variants of the above. */ +unsigned long *devm_bitmap_alloc(struct device *dev, + unsigned int nbits, gfp_t flags); +unsigned long *devm_bitmap_zalloc(struct device *dev, + unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ -extern int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern bool __pure __bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits); -extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits); -extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits); -extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits); -extern void bitmap_cut(unsigned long *dst, const unsigned long *src, - unsigned int first, unsigned int cut, - unsigned int nbits); -extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +bool __pure __bitmap_or_equal(const unsigned long *src1, + const unsigned long *src2, + const unsigned long *src3, + unsigned int nbits); +void __bitmap_complement(unsigned long *dst, const unsigned long *src, + unsigned int nbits); +void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); +void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); +void bitmap_cut(unsigned long *dst, const unsigned long *src, + unsigned int first, unsigned int cut, unsigned int nbits); +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits); +int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); -extern void __bitmap_replace(unsigned long *dst, - const unsigned long *old, const unsigned long *new, - const unsigned long *mask, unsigned int nbits); -extern int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); -extern void __bitmap_set(unsigned long *map, unsigned int start, int len); -extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); - -extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask, - unsigned long align_offset); +int __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +void __bitmap_set(unsigned long *map, unsigned int start, int len); +void __bitmap_clear(unsigned long *map, unsigned int start, int len); + +unsigned long bitmap_find_next_zero_area_off(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask, + unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area @@ -190,46 +198,38 @@ bitmap_find_next_zero_area(unsigned long *map, align_mask, 0); } -extern int bitmap_parse(const char *buf, unsigned int buflen, +int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); -extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, +int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); -extern int bitmap_parselist(const char *buf, unsigned long *maskp, +int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); -extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, +int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); -extern void bitmap_remap(unsigned long *dst, const unsigned long *src, +void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); -extern int bitmap_bitremap(int oldbit, +int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); -extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, +void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); -extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, +void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); -extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); -extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); -extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); #ifdef __BIG_ENDIAN -extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); +void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else #define bitmap_copy_le bitmap_copy #endif -extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); -extern int bitmap_print_to_pagebuf(bool list, char *buf, +unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); +int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) -/* - * The static inlines below do not handle constant nbits==0 correctly, - * so make such users (should any ever turn up) call the out-of-line - * versions. - */ -#define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) - static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); @@ -265,9 +265,9 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, * therefore conversion is not needed when copying data from/to arrays of u32. */ #if BITS_PER_LONG == 64 -extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, +void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); -extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, +void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a5a48303b0f1..26bf15e6cd35 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -286,17 +286,5 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, }) #endif -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -extern unsigned long find_last_bit(const unsigned long *addr, - unsigned long size); -#endif - #endif /* __KERNEL__ */ #endif diff --git a/include/linux/bits.h b/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -22,7 +22,7 @@ #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 3bd3ee651143..359486940fa0 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -313,12 +313,12 @@ struct blk_mq_ops { */ void (*put_budget)(struct request_queue *, int); - /* - * @set_rq_budget_toekn: store rq's budget token + /** + * @set_rq_budget_token: store rq's budget token */ void (*set_rq_budget_token)(struct request *, int); - /* - * @get_rq_budget_toekn: retrieve rq's budget token + /** + * @get_rq_budget_token: retrieve rq's budget token */ int (*get_rq_budget_token)(struct request *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b91ba6207365..f69c75bd6d27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -11,7 +11,6 @@ #include <linux/minmax.h> #include <linux/timer.h> #include <linux/workqueue.h> -#include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> @@ -677,11 +676,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline bool blk_account_rq(struct request *rq) -{ - return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); -} - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6023a1367853..06841517ab1e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -302,10 +302,11 @@ struct bpf_verifier_state_list { }; /* Possible states for alu_state member. */ -#define BPF_ALU_SANITIZE_SRC 1U -#define BPF_ALU_SANITIZE_DST 2U +#define BPF_ALU_SANITIZE_SRC (1U << 0) +#define BPF_ALU_SANITIZE_DST (1U << 1) #define BPF_ALU_NEG_VALUE (1U << 2) #define BPF_ALU_NON_POINTER (1U << 3) +#define BPF_ALU_IMMEDIATE (1U << 4) #define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ BPF_ALU_SANITIZE_DST) diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6b47f94378c5..e7e99da31349 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,6 +194,8 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); +void invalidate_bh_lrus_cpu(int cpu); +bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); @@ -406,6 +408,8 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +static inline void invalidate_bh_lrus_cpu(int cpu) {} +static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ diff --git a/include/linux/bug.h b/include/linux/bug.h index f639bd0122f3..348acf2558f3 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -36,6 +36,9 @@ static inline int is_warning_bug(const struct bug_entry *bug) return bug->flags & BUGFLAG_WARNING; } +void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line); + struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); @@ -58,6 +61,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, return BUG_TRAP_TYPE_BUG; } +struct bug_entry; +static inline void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line) +{ + *file = NULL; + *line = 0; +} static inline void generic_bug_clear_once(void) {} diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 559ee05f86b2..fb8f6d2cd104 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -232,7 +232,7 @@ struct css_set { struct list_head task_iters; /* - * On the default hierarhcy, ->subsys[ssid] may point to a css + * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to @@ -668,7 +668,7 @@ struct cgroup_subsys { */ bool threaded:1; - /* the following two fields are initialized automtically during boot */ + /* the following two fields are initialized automatically during boot */ int id; const char *name; @@ -757,7 +757,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. * On boot, sock_cgroup_data records the cgroup that the sock was created * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overriden to carry prioidx and/or + * net_cls starts being used, the area is overridden to carry prioidx and/or * classid. The two modes are distinguished by whether the lowest bit is * set. Clear bit indicates cgroup pointer while set bit prioidx and * classid. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..6bc9c76680b2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -32,7 +32,7 @@ struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* - * All weight knobs on the default hierarhcy should use the following min, + * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index a247b089ca78..d6ab416ee2d2 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -17,6 +17,7 @@ #include <linux/timer.h> #include <linux/init.h> #include <linux/of.h> +#include <linux/clocksource_ids.h> #include <asm/div64.h> #include <asm/io.h> @@ -62,6 +63,10 @@ struct module; * 400-499: Perfect * The ideal clocksource. A must-use where * available. + * @id: Defaults to CSID_GENERIC. The id value is captured + * in certain snapshot functions to allow callers to + * validate the clocksource from which the snapshot was + * taken. * @flags: Flags describing special properties * @enable: Optional function to enable the clocksource * @disable: Optional function to disable the clocksource @@ -100,6 +105,7 @@ struct clocksource { const char *name; struct list_head list; int rating; + enum clocksource_ids id; enum vdso_clock_mode vdso_clock_mode; unsigned long flags; diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h new file mode 100644 index 000000000000..16775d7d8f8d --- /dev/null +++ b/include/linux/clocksource_ids.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CLOCKSOURCE_IDS_H +#define _LINUX_CLOCKSOURCE_IDS_H + +/* Enum to give clocksources a unique identifier */ +enum clocksource_ids { + CSID_GENERIC = 0, + CSID_ARM_ARCH_COUNTER, + CSID_MAX, +}; + +#endif diff --git a/include/linux/cma.h b/include/linux/cma.h index 217999c8a762..53fd8c3cdbd0 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -44,9 +44,9 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, const char *name, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, +extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); -extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); +extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); #endif diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ed4070ed41ef..4221888bdcd6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,7 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); diff --git a/include/linux/compat.h b/include/linux/compat.h index acac0b571df1..8855b1b702b2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -75,7 +75,6 @@ __diag_push(); \ __diag_ignore(GCC, 8, "-Wattribute-alias", \ "Type aliasing is used to sanitize syscall arguments");\ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_compat_sys##name)))); \ ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ @@ -214,12 +213,11 @@ typedef struct compat_siginfo { /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { compat_uptr_t _addr; /* faulting insn/memory ref. */ -#ifdef __ARCH_SI_TRAPNO - int _trapno; /* TRAP # which caused the signal */ -#endif #define __COMPAT_ADDR_BND_PKEY_PAD (__alignof__(compat_uptr_t) < sizeof(short) ? \ sizeof(short) : __alignof__(compat_uptr_t)) union { + /* used on alpha and sparc */ + int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO @@ -237,7 +235,10 @@ typedef struct compat_siginfo { u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ - compat_ulong_t _perf; + struct { + compat_ulong_t _data; + u32 _type; + } _perf; }; } _sigfault; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 48750243db4c..5d97ef738a57 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -90,15 +90,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -/* - * sparse (__CHECKER__) pretends to be gcc, but can't do constant - * folding in __builtin_bswap*() (yet), so don't set these for it. - */ -#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ #define __HAVE_BUILTIN_BSWAP16__ -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ #if GCC_VERSION >= 70000 #define KASAN_ABI_VERSION 5 diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 2e8c69b43c64..97cfd13bae51 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/* -*- mode: c; c-basic-offset: 8; -*- - * vim: noexpandtab sw=8 ts=8 sts=0: - * +/* * configfs.h - definitions for the device driver filesystem * * Based on sysfs: diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 153734816b49..d5b9c8d40c18 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -101,6 +101,7 @@ struct vc_data { unsigned int vc_rows; unsigned int vc_size_row; /* Bytes per row */ unsigned int vc_scan_lines; /* # of scan lines */ + unsigned int vc_cell_height; /* CRTC character cell height */ unsigned long vc_origin; /* [!] Start of real screen */ unsigned long vc_scr_end; /* [!] End of real screen */ unsigned long vc_visible_origin; /* [!] Top of visible window */ diff --git a/include/linux/const.h b/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/include/linux/const.h +++ b/include/linux/const.h @@ -3,4 +3,12 @@ #include <vdso/const.h> +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de> + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index bceb06498521..4d7fced3a39f 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -71,6 +71,19 @@ static inline void exception_exit(enum ctx_state prev_ctx) } } +static __always_inline bool context_tracking_guest_enter(void) +{ + if (context_tracking_enabled()) + __context_tracking_enter(CONTEXT_GUEST); + + return context_tracking_enabled_this_cpu(); +} + +static __always_inline void context_tracking_guest_exit(void) +{ + if (context_tracking_enabled()) + __context_tracking_exit(CONTEXT_GUEST); +} /** * ct_state() - return the current context tracking state if known @@ -92,6 +105,9 @@ static inline void user_exit_irqoff(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } +static inline bool context_tracking_guest_enter(void) { return false; } +static inline void context_tracking_guest_exit(void) { } + #endif /* !CONFIG_CONTEXT_TRACKING */ #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) @@ -102,80 +118,4 @@ extern void context_tracking_init(void); static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_FORCE */ - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) -{ - instrumentation_begin(); - if (vtime_accounting_enabled_this_cpu()) - vtime_guest_enter(current); - else - current->flags |= PF_VCPU; - instrumentation_end(); - - if (context_tracking_enabled()) - __context_tracking_enter(CONTEXT_GUEST); - - /* KVM does not hold any references to rcu protected data when it - * switches CPU into a guest mode. In fact switching to a guest mode - * is very similar to exiting to userspace from rcu point of view. In - * addition CPU may stay in a guest mode for quite a long time (up to - * one time slice). Lets treat guest mode as quiescent state, just like - * we do with user-mode execution. - */ - if (!context_tracking_enabled_this_cpu()) { - instrumentation_begin(); - rcu_virt_note_context_switch(smp_processor_id()); - instrumentation_end(); - } -} - -static __always_inline void guest_exit_irqoff(void) -{ - if (context_tracking_enabled()) - __context_tracking_exit(CONTEXT_GUEST); - - instrumentation_begin(); - if (vtime_accounting_enabled_this_cpu()) - vtime_guest_exit(current); - else - current->flags &= ~PF_VCPU; - instrumentation_end(); -} - -#else -static __always_inline void guest_enter_irqoff(void) -{ - /* - * This is running in ioctl context so its safe - * to assume that it's the stime pending cputime - * to flush. - */ - instrumentation_begin(); - vtime_account_kernel(current); - current->flags |= PF_VCPU; - rcu_virt_note_context_switch(smp_processor_id()); - instrumentation_end(); -} - -static __always_inline void guest_exit_irqoff(void) -{ - instrumentation_begin(); - /* Flush the guest cputime we spent on the guest */ - vtime_account_kernel(current); - current->flags &= ~PF_VCPU; - instrumentation_end(); -} -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ - -static inline void guest_exit(void) -{ - unsigned long flags; - - local_irq_save(flags); - guest_exit_irqoff(); - local_irq_restore(flags); -} - #endif diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 976ec2697610..85008a65e21f 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -50,6 +50,7 @@ enum coresight_dev_subtype_sink { CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, + CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM, }; enum coresight_dev_subtype_link { @@ -455,6 +456,18 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o } #endif /* CONFIG_64BIT */ +static inline bool coresight_is_percpu_source(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) && + (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC); +} + +static inline bool coresight_is_percpu_sink(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SINK) && + (csdev->subtype.sink_subtype == CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM); +} + extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index db82ce5304f9..4a62b3980642 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -57,7 +57,7 @@ enum cpuhp_state { CPUHP_PAGE_ALLOC_DEAD, CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, - CPUHP_IOMMU_INTEL_DEAD, + CPUHP_IOMMU_IOVA_DEAD, CPUHP_LUSTRE_CFS_DEAD, CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, @@ -169,6 +169,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, + CPUHP_AP_PERF_X86_IDXD_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_CFD_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, diff --git a/include/linux/crc8.h b/include/linux/crc8.h index 13c8dabb0441..674045c59a04 100644 --- a/include/linux/crc8.h +++ b/include/linux/crc8.h @@ -96,6 +96,6 @@ void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial); * Williams, Ross N., ross<at>ross.net * (see URL http://www.ross.net/crc/download/crc_v3.txt). */ -u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc); +u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc); #endif /* __CRC8_H_ */ diff --git a/include/linux/cred.h b/include/linux/cred.h index ac0e5f97d7d8..14971322e1a0 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -53,7 +53,6 @@ do { \ groups_free(group_info); \ } while (0) -extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c1e48014106f..9e23d33bb6f1 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -59,6 +59,7 @@ struct qstr { extern const struct qstr empty_name; extern const struct qstr slash_name; +extern const struct qstr dotdot_name; struct dentry_stat_t { long nr_dentry; @@ -300,8 +301,8 @@ char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); -extern char *dentry_path_raw(struct dentry *, char *, int); -extern char *dentry_path(struct dentry *, char *, int); +extern char *dentry_path_raw(const struct dentry *, char *, int); +extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 2d3bdcccf5eb..21651f946751 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -82,16 +82,16 @@ static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) return 0; } -static inline void delayacct_set_flag(int flag) +static inline void delayacct_set_flag(struct task_struct *p, int flag) { - if (current->delays) - current->delays->flags |= flag; + if (p->delays) + p->delays->flags |= flag; } -static inline void delayacct_clear_flag(int flag) +static inline void delayacct_clear_flag(struct task_struct *p, int flag) { - if (current->delays) - current->delays->flags &= ~flag; + if (p->delays) + p->delays->flags &= ~flag; } static inline void delayacct_tsk_init(struct task_struct *tsk) @@ -114,7 +114,7 @@ static inline void delayacct_tsk_free(struct task_struct *tsk) static inline void delayacct_blkio_start(void) { - delayacct_set_flag(DELAYACCT_PF_BLKIO); + delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -123,7 +123,7 @@ static inline void delayacct_blkio_end(struct task_struct *p) { if (p->delays) __delayacct_blkio_end(p); - delayacct_clear_flag(DELAYACCT_PF_BLKIO); + delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } static inline int delayacct_add_tsk(struct taskstats *d, @@ -166,9 +166,9 @@ static inline void delayacct_thrashing_end(void) } #else -static inline void delayacct_set_flag(int flag) +static inline void delayacct_set_flag(struct task_struct *p, int flag) {} -static inline void delayacct_clear_flag(int flag) +static inline void delayacct_clear_flag(struct task_struct *p, int flag) {} static inline void delayacct_init(void) {} diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 5c641f930caf..ff700fb6ce1d 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -574,11 +574,6 @@ struct dm_table *dm_swap_table(struct mapped_device *md, */ void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); -/* - * A wrapper around vmalloc. - */ -void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); - /*----------------------------------------------------------------- * Macros. *---------------------------------------------------------------*/ diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..f1a00040fa53 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -570,7 +570,7 @@ struct device { * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { @@ -583,9 +583,7 @@ struct device_link { u32 flags; refcount_t rpm_active; struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif + struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 706b68d1359b..6e75a2d689b4 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -40,6 +40,8 @@ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, struct iommu_domain *domain); +extern bool iommu_dma_forcedac; + #else /* CONFIG_IOMMU_DMA */ struct iommu_domain; @@ -81,10 +83,5 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he { } -static inline void iommu_dma_free_cpu_cached_iovas(unsigned int cpu, - struct iommu_domain *domain) -{ -} - #endif /* CONFIG_IOMMU_DMA */ #endif /* __DMA_IOMMU_H */ diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 51872e736e7b..0d53a96a3d64 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,6 +22,11 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); + struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs); + void (*free_noncontiguous)(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -198,6 +203,20 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ +/* + * This is the actual return value from the ->alloc_noncontiguous method. + * The users of the DMA API should only care about the sg_table, but to make + * the DMA-API internal vmaping and freeing easier we stash away the page + * array as well (except for the fallback case). This can go away any time, + * e.g. when a vmap-variant that takes a scatterlist comes along. + */ +struct dma_sgt_handle { + struct sg_table sgt; + struct page **pages; +}; +#define sgt_handle(sgt) \ + container_of((sgt), struct dma_sgt_handle, sgt) + int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2a984cb4d1e0..183e7103a66d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -95,7 +95,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { debug_dma_mapping_error(dev, dma_addr); - if (dma_addr == DMA_MAPPING_ERROR) + if (unlikely(dma_addr == DMA_MAPPING_ERROR)) return -ENOMEM; return 0; } @@ -144,6 +144,15 @@ u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); +struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); +void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); +void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt); +void dma_vunmap_noncontiguous(struct device *dev, void *vaddr); +int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, @@ -257,12 +266,37 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; } +static inline struct sg_table *dma_alloc_noncontiguous(struct device *dev, + size_t size, enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs) +{ + return NULL; +} +static inline void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ +} +static inline void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + return NULL; +} +static inline void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) +{ +} +static inline int dma_mmap_noncontiguous(struct device *dev, + struct vm_area_struct *vma, size_t size, struct sg_table *sgt) +{ + return -EINVAL; +} #endif /* CONFIG_HAS_DMA */ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); +int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, + size_t size, struct page *page); static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) @@ -401,7 +435,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev, static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_handle, gfp, (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index a57ee75342cf..dce631e678dd 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -32,6 +32,11 @@ struct _ddebug { #define _DPRINTK_FLAGS_INCL_FUNCNAME (1<<2) #define _DPRINTK_FLAGS_INCL_LINENO (1<<3) #define _DPRINTK_FLAGS_INCL_TID (1<<4) + +#define _DPRINTK_FLAGS_INCL_ANY \ + (_DPRINTK_FLAGS_INCL_MODNAME | _DPRINTK_FLAGS_INCL_FUNCNAME |\ + _DPRINTK_FLAGS_INCL_LINENO | _DPRINTK_FLAGS_INCL_TID) + #if defined DEBUG #define _DPRINTK_FLAGS_DEFAULT _DPRINTK_FLAGS_PRINT #else diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1fe8e105b83b..dcb2f9022c1d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -34,7 +34,7 @@ struct elevator_mq_ops { void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); - bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *, unsigned int); + bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index c6cc0a566ef5..5487a80617a3 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -168,7 +168,7 @@ struct f2fs_checkpoint { unsigned char alloc_type[MAX_ACTIVE_LOGS]; /* SIT and NAT version bitmap */ - unsigned char sit_nat_version_bitmap[1]; + unsigned char sit_nat_version_bitmap[]; } __packed; #define CP_CHKSUM_OFFSET 4092 /* default chksum offset in checkpoint */ diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bad41bcb25df..a16dbeced152 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -51,6 +51,10 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INIT_FLAGS (FANOTIFY_ADMIN_INIT_FLAGS | \ FANOTIFY_USER_INIT_FLAGS) +/* Internal group flags */ +#define FANOTIFY_UNPRIV 0x80000000 +#define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) + #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ FAN_MARK_FILESYSTEM) diff --git a/include/linux/file.h b/include/linux/file.h index 225982792fa2..2de2e4613d7b 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -92,23 +92,20 @@ extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); -extern int __receive_fd(int fd, struct file *file, int __user *ufd, +extern int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; - return __receive_fd(-1, file, ufd, o_flags); + return __receive_fd(file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { - return __receive_fd(-1, file, NULL, o_flags); -} -static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) -{ - return __receive_fd(fd, file, NULL, o_flags); + return __receive_fd(file, NULL, o_flags); } +int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 66e2423d9feb..9d1a5c175065 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,12 @@ enum pm_api_id { PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, + PM_PINCTRL_REQUEST = 28, + PM_PINCTRL_RELEASE = 29, + PM_PINCTRL_GET_FUNCTION = 30, + PM_PINCTRL_SET_FUNCTION = 31, + PM_PINCTRL_CONFIG_PARAM_GET = 32, + PM_PINCTRL_CONFIG_PARAM_SET = 33, PM_IOCTL = 34, PM_QUERY_DATA = 35, PM_CLOCK_ENABLE = 36, @@ -122,6 +128,12 @@ enum pm_query_id { PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS = 3, PM_QID_CLOCK_GET_PARENTS = 4, PM_QID_CLOCK_GET_ATTRIBUTES = 5, + PM_QID_PINCTRL_GET_NUM_PINS = 6, + PM_QID_PINCTRL_GET_NUM_FUNCTIONS = 7, + PM_QID_PINCTRL_GET_NUM_FUNCTION_GROUPS = 8, + PM_QID_PINCTRL_GET_FUNCTION_NAME = 9, + PM_QID_PINCTRL_GET_FUNCTION_GROUPS = 10, + PM_QID_PINCTRL_GET_PIN_GROUPS = 11, PM_QID_CLOCK_GET_NUM_CLOCKS = 12, PM_QID_CLOCK_GET_MAX_DIVISOR = 13, }; @@ -285,6 +297,44 @@ enum dll_reset_type { PM_DLL_RESET_PULSE = 2, }; +enum pm_pinctrl_config_param { + PM_PINCTRL_CONFIG_SLEW_RATE = 0, + PM_PINCTRL_CONFIG_BIAS_STATUS = 1, + PM_PINCTRL_CONFIG_PULL_CTRL = 2, + PM_PINCTRL_CONFIG_SCHMITT_CMOS = 3, + PM_PINCTRL_CONFIG_DRIVE_STRENGTH = 4, + PM_PINCTRL_CONFIG_VOLTAGE_STATUS = 5, + PM_PINCTRL_CONFIG_TRI_STATE = 6, + PM_PINCTRL_CONFIG_MAX = 7, +}; + +enum pm_pinctrl_slew_rate { + PM_PINCTRL_SLEW_RATE_FAST = 0, + PM_PINCTRL_SLEW_RATE_SLOW = 1, +}; + +enum pm_pinctrl_bias_status { + PM_PINCTRL_BIAS_DISABLE = 0, + PM_PINCTRL_BIAS_ENABLE = 1, +}; + +enum pm_pinctrl_pull_ctrl { + PM_PINCTRL_BIAS_PULL_DOWN = 0, + PM_PINCTRL_BIAS_PULL_UP = 1, +}; + +enum pm_pinctrl_schmitt_cmos { + PM_PINCTRL_INPUT_TYPE_CMOS = 0, + PM_PINCTRL_INPUT_TYPE_SCHMITT = 1, +}; + +enum pm_pinctrl_drive_strength { + PM_PINCTRL_DRIVE_STRENGTH_2MA = 0, + PM_PINCTRL_DRIVE_STRENGTH_4MA = 1, + PM_PINCTRL_DRIVE_STRENGTH_8MA = 2, + PM_PINCTRL_DRIVE_STRENGTH_12MA = 3, +}; + enum zynqmp_pm_shutdown_type { ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN = 0, ZYNQMP_PM_SHUTDOWN_TYPE_RESET = 1, @@ -353,6 +403,14 @@ int zynqmp_pm_write_pggs(u32 index, u32 value); int zynqmp_pm_read_pggs(u32 index, u32 *value); int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype); int zynqmp_pm_set_boot_health_status(u32 value); +int zynqmp_pm_pinctrl_request(const u32 pin); +int zynqmp_pm_pinctrl_release(const u32 pin); +int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id); +int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id); +int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, + u32 *value); +int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, + u32 value); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -532,6 +590,38 @@ static inline int zynqmp_pm_set_boot_health_status(u32 value) { return -ENODEV; } + +static inline int zynqmp_pm_pinctrl_request(const u32 pin) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_pinctrl_release(const u32 pin) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, + u32 *value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, + u32 value) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ diff --git a/include/linux/fs.h b/include/linux/fs.h index bf4e90d3ab18..c3c88fdb9b2a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -145,7 +145,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) -/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ +/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ @@ -442,7 +442,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping, * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. - * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). @@ -463,7 +462,6 @@ struct address_space { struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; - unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; @@ -2878,6 +2876,8 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +extern bool filemap_range_needs_writeback(struct address_space *, + loff_t lstart, loff_t lend); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 86e5028bfa20..a69f363b61bf 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -33,7 +33,7 @@ /* * If the arch's mcount caller does not support all of ftrace's * features, then it must call an indirect function that - * does. Or at least does enough to prevent any unwelcomed side effects. + * does. Or at least does enough to prevent any unwelcome side effects. */ #if !ARCH_SUPPORTS_FTRACE_OPS # define FTRACE_FORCE_LIST_FUNC 1 @@ -389,7 +389,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer); */ static inline void stack_tracer_disable(void) { - /* Preemption or interupts must be disabled */ + /* Preemption or interrupts must be disabled */ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_inc(disable_stack_tracer); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ed4e67a7ff1c..59828516ebaf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -187,5 +187,6 @@ extern u32 fw_devlink_get_flags(void); extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); void fwnode_links_purge(struct fwnode_handle *fwnode); +void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode); #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7e9660ea967d..6fc26f7bdf71 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -306,8 +306,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ -extern struct rw_semaphore bdev_lookup_sem; - dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 6cb82301d8e9..939b1a8f571b 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -404,4 +404,3 @@ s_fields \ /* }}}1 */ #endif /* GENL_MAGIC_FUNC_H */ -/* vim: set foldmethod=marker foldlevel=1 nofoldenable : */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index 35d21fddaf2d..f81d48987528 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -283,4 +283,3 @@ enum { \ /* }}}1 */ #endif /* GENL_MAGIC_STRUCT_H */ -/* vim: set foldmethod=marker nofoldenable : */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8572a1474e16..11da8af06704 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -490,7 +490,7 @@ static inline int gfp_zonelist(gfp_t flags) /* * We get the zone list from the current node and the gfp_mask. - * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. + * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * @@ -515,14 +515,25 @@ static inline int arch_make_page_accessible(struct page *page) } #endif -struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, - nodemask_t *nodemask); +struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask); -static inline struct page * -__alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) +unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, + nodemask_t *nodemask, int nr_pages, + struct list_head *page_list, + struct page **page_array); + +/* Bulk allocate order-0 pages */ +static inline unsigned long +alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) +{ + return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL); +} + +static inline unsigned long +alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { - return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); + return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); } /* @@ -535,7 +546,7 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); - return __alloc_pages(gfp_mask, order, nid); + return __alloc_pages(gfp_mask, order, nid, NULL); } /* @@ -553,13 +564,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, } #ifdef CONFIG_NUMA -extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); - -static inline struct page * -alloc_pages(gfp_t gfp_mask, unsigned int order) -{ - return alloc_pages_current(gfp_mask, order); -} +struct page *alloc_pages(gfp_t gfp, unsigned int order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); @@ -652,7 +657,7 @@ extern int alloc_contig_range(unsigned long start, unsigned long end, extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif -void free_contig_range(unsigned long pfn, unsigned int nr_pages); +void free_contig_range(unsigned long pfn, unsigned long nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 286de0520574..3a268781fcec 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -227,7 +227,7 @@ struct gpio_irq_chip { /** * @valid_mask: * - * If not %NULL holds bitmask of GPIOs which are valid to be included + * If not %NULL, holds bitmask of GPIOs which are valid to be included * in IRQ domain of the chip. */ unsigned long *valid_mask; @@ -346,7 +346,7 @@ struct gpio_irq_chip { * output. * * A gpio_chip can help platforms abstract various sources of GPIOs so - * they can all be accessed through a common programing interface. + * they can all be accessed through a common programming interface. * Example sources would be SOC controllers, FPGAs, multifunction * chips, dedicated GPIO expanders, and so on. * @@ -435,15 +435,15 @@ struct gpio_chip { /** * @valid_mask: * - * If not %NULL holds bitmask of GPIOs which are valid to be used + * If not %NULL, holds bitmask of GPIOs which are valid to be used * from the chip. */ unsigned long *valid_mask; #if defined(CONFIG_OF_GPIO) /* - * If CONFIG_OF is enabled, then all GPIO controllers described in the - * device tree automatically may have an OF translation + * If CONFIG_OF_GPIO is enabled, then all GPIO controllers described in + * the device tree automatically may have an OF translation */ /** @@ -508,7 +508,7 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, * for GPIOs will fail rudely. * * gpiochip_add_data() must only be called after gpiolib initialization, - * ie after core_initcall(). + * i.e. after core_initcall(). * * If gc->base is negative, this requests dynamic assignment of * a range of valid GPIOs. @@ -624,8 +624,17 @@ void gpiochip_irq_domain_deactivate(struct irq_domain *domain, bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, unsigned int offset); +#ifdef CONFIG_GPIOLIB_IRQCHIP int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain); +#else +static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc, + struct irq_domain *domain) +{ + WARN_ON(1); + return -EINVAL; +} +#endif int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset); void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset); diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index ad76f3d0a6ba..334dd928042b 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -4,6 +4,7 @@ #define _LINUX_GPIO_REGMAP_H struct device; +struct fwnode_handle; struct gpio_regmap; struct irq_domain; struct regmap; @@ -16,6 +17,8 @@ struct regmap; * @parent: The parent device * @regmap: The regmap used to access the registers * given, the name of the device is used + * @fwnode: (Optional) The firmware node. + * If not given, the fwnode of the parent is used. * @label: (Optional) Descriptive name for GPIO controller. * If not given, the name of the device is used. * @ngpio: Number of GPIOs @@ -57,6 +60,7 @@ struct regmap; struct gpio_regmap_config { struct device *parent; struct regmap *regmap; + struct fwnode_handle *fwnode; const char *label; int ngpio; diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 44170f312ae7..832b49b50c7b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -332,4 +332,11 @@ static inline void memcpy_to_page(struct page *page, size_t offset, kunmap_local(to); } +static inline void memzero_page(struct page *page, size_t offset, size_t len) +{ + char *addr = kmap_atomic(page); + memset(addr + offset, 0, len); + kunmap_atomic(addr); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ba973efcd369..9626fda5efce 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -87,9 +87,6 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, -#ifdef CONFIG_DEBUG_VM - TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, -#endif }; struct kobject; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index cccd1aab69dd..b92f25ccef58 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -11,6 +11,7 @@ #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> +#include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; @@ -134,11 +135,14 @@ void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); +#ifdef CONFIG_USERFAULTFD int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep); +#endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); @@ -152,7 +156,8 @@ void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); -pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); +pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pud_t *pud); struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); @@ -161,7 +166,7 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); @@ -187,6 +192,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); bool is_hugetlb_entry_migration(pte_t pte); +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -308,16 +314,19 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, BUG(); } +#ifdef CONFIG_USERFAULTFD static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep) { BUG(); return 0; } +#endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) @@ -368,6 +377,8 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, return 0; } +static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } + #endif /* !CONFIG_HUGETLB_PAGE */ /* * hugepages at page global directory. If arch support @@ -555,6 +566,7 @@ HPAGEFLAG(Freed, freed) #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { + struct mutex resize_lock; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; @@ -583,6 +595,7 @@ struct huge_bootmem_page { struct hstate *hstate; }; +int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, @@ -865,6 +878,12 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline int isolate_or_dissolve_huge_page(struct page *page, + struct list_head *list) +{ + return -ENOMEM; +} + static inline struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) @@ -1039,4 +1058,14 @@ static inline __init void hugetlb_cma_check(void) } #endif +bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); + +#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +/* + * ARCHes with special requirements for evicting HUGETLB backing TLB entries can + * implement this. + */ +#define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 56622658b215..e8f2ac8c9c3d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -51,6 +51,9 @@ struct module; struct property_entry; #if IS_ENABLED(CONFIG_I2C) +/* Return the Frequency mode string based on the bus frequency */ +const char *i2c_freq_mode_string(u32 bus_freq_hz); + /* * The master routines are the ones normally used to transmit data to devices * on a bus (or read from them). Apart from two basic transfer functions to @@ -306,6 +309,8 @@ struct i2c_driver { * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. + * @devres_group_id: id of the devres group that will be created for resources + * acquired when probing this device. * * An i2c_client identifies a single device (i.e. chip) connected to an * i2c bus. The behaviour exposed to Linux is defined by the driver @@ -334,6 +339,7 @@ struct i2c_client { #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif + void *devres_group_id; /* ID of probe devres group */ }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) @@ -391,7 +397,7 @@ static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } * @platform_data: stored in i2c_client.dev.platform_data * @of_node: pointer to OpenFirmware device node * @fwnode: device node supplied by the platform firmware - * @properties: additional device properties for the device + * @swnode: software node for the device * @resources: resources associated with the device * @num_resources: number of resources in the @resources array * @irq: stored in i2c_client.irq @@ -415,7 +421,7 @@ struct i2c_board_info { void *platform_data; struct device_node *of_node; struct fwnode_handle *fwnode; - const struct property_entry *properties; + const struct software_node *swnode; const struct resource *resources; unsigned int num_resources; int irq; @@ -687,6 +693,8 @@ struct i2c_adapter_quirks { #define I2C_AQ_NO_ZERO_LEN_READ BIT(5) #define I2C_AQ_NO_ZERO_LEN_WRITE BIT(6) #define I2C_AQ_NO_ZERO_LEN (I2C_AQ_NO_ZERO_LEN_READ | I2C_AQ_NO_ZERO_LEN_WRITE) +/* adapter cannot do repeated START */ +#define I2C_AQ_NO_REP_START BIT(7) /* * i2c_adapter is the structure used to identify a physical i2c bus along @@ -844,6 +852,7 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) */ #if IS_ENABLED(CONFIG_I2C) int i2c_add_adapter(struct i2c_adapter *adap); +int devm_i2c_add_adapter(struct device *dev, struct i2c_adapter *adapter); void i2c_del_adapter(struct i2c_adapter *adap); int i2c_add_numbered_adapter(struct i2c_adapter *adap); diff --git a/include/linux/init.h b/include/linux/init.h index 045ad1650ed1..d82b4b2e1d25 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -242,7 +242,8 @@ extern bool initcall_debug; asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ ".long " __stringify(__stub) " - . \n" \ - ".previous \n"); + ".previous \n"); \ + static_assert(__same_type(initcall_t, &fn)); #else #define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index b2412b4d4c20..40fc5813cf93 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,7 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; extern struct nsproxy init_nsproxy; -extern struct group_info init_groups; extern struct cred init_cred; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 85c15717af34..1bbe9af48dc3 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -20,8 +20,10 @@ extern void free_initrd_mem(unsigned long, unsigned long); #ifdef CONFIG_BLK_DEV_INITRD extern void __init reserve_initrd_mem(void); +extern void wait_for_initramfs(void); #else static inline void __init reserve_initrd_mem(void) {} +static inline void wait_for_initramfs(void) {} #endif extern phys_addr_t phys_initrd_start; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 1bc46b88711a..03faf20a6817 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -20,6 +20,7 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/dmar.h> #include <linux/ioasid.h> +#include <linux/bitfield.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -80,6 +81,7 @@ #define DMAR_IQ_SHIFT 4 /* Invalidation queue head/tail shift */ #define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */ #define DMAR_ICS_REG 0x9c /* Invalidation complete status register */ +#define DMAR_IQER_REG 0xb0 /* Invalidation queue error record register */ #define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */ #define DMAR_PQH_REG 0xc0 /* Page request queue head register */ #define DMAR_PQT_REG 0xc8 /* Page request queue tail register */ @@ -126,6 +128,10 @@ #define DMAR_VCMD_REG 0xe10 /* Virtual command register */ #define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ +#define DMAR_IQER_REG_IQEI(reg) FIELD_GET(GENMASK_ULL(3, 0), reg) +#define DMAR_IQER_REG_ITESID(reg) FIELD_GET(GENMASK_ULL(47, 32), reg) +#define DMAR_IQER_REG_ICESID(reg) FIELD_GET(GENMASK_ULL(63, 48), reg) + #define OFFSET_STRIDE (9) #define dmar_readq(a) readq(a) @@ -372,6 +378,7 @@ enum { /* PASID cache invalidation granu */ #define QI_PC_ALL_PASIDS 0 #define QI_PC_PASID_SEL 1 +#define QI_PC_GLOBAL 3 #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_EIOTLB_IH(ih) (((u64)ih) << 6) @@ -763,14 +770,11 @@ u32 intel_svm_get_pasid(struct iommu_sva *handle); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); -struct svm_dev_ops; - struct intel_svm_dev { struct list_head list; struct rcu_head rcu; struct device *dev; struct intel_iommu *iommu; - struct svm_dev_ops *ops; struct iommu_sva sva; u32 pasid; int users; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 39d368a810b8..10fa80eef13a 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -8,13 +8,6 @@ #ifndef __INTEL_SVM_H__ #define __INTEL_SVM_H__ -struct device; - -struct svm_dev_ops { - void (*fault_cb)(struct device *dev, u32 pasid, u64 address, - void *private, int rwxp, int response); -}; - /* Values for rxwp in fault_cb callback */ #define SVM_REQ_READ (1<<3) #define SVM_REQ_WRITE (1<<2) @@ -22,16 +15,6 @@ struct svm_dev_ops { #define SVM_REQ_PRIV (1<<0) /* - * The SVM_FLAG_PRIVATE_PASID flag requests a PASID which is *not* the "main" - * PASID for the current process. Even if a PASID already exists, a new one - * will be allocated. And the PASID allocated with SVM_FLAG_PRIVATE_PASID - * will not be given to subsequent callers. This facility allows a driver to - * disambiguate between multiple device contexts which access the same MM, - * if there is no other way to do so. It should be used sparingly, if at all. - */ -#define SVM_FLAG_PRIVATE_PASID (1<<0) - -/* * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only * for access to kernel addresses. No IOTLB flushes are automatically done * for kernel mappings; it is valid only for access to the kernel's static @@ -42,18 +25,18 @@ struct svm_dev_ops { * It is unlikely that we will ever hook into flush_tlb_kernel_range() to * do such IOTLB flushes automatically. */ -#define SVM_FLAG_SUPERVISOR_MODE (1<<1) +#define SVM_FLAG_SUPERVISOR_MODE BIT(0) /* * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest * processes. Compared to the host bind, the primary differences are: * 1. mm life cycle management * 2. fault reporting */ -#define SVM_FLAG_GUEST_MODE (1<<2) +#define SVM_FLAG_GUEST_MODE BIT(1) /* * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, * which requires guest and host PASID translation at both directions. */ -#define SVM_FLAG_GUEST_PASID (1<<3) +#define SVM_FLAG_GUEST_PASID BIT(2) #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index c093e81310a9..e9743cfd8585 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -220,3 +220,6 @@ io_mapping_free(struct io_mapping *iomap) } #endif /* _LINUX_IO_MAPPING_H */ + +int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, unsigned long size); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index a4c9ca2c31f1..4d40dfa75b55 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -204,10 +204,6 @@ struct io_pgtable { #define io_pgtable_ops_to_pgtable(x) container_of((x), struct io_pgtable, ops) -struct io_pgtable_domain_attr { - unsigned long quirks; -}; - static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop) { if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_all) diff --git a/include/linux/io.h b/include/linux/io.h index 61ff7d6278b6..9595151d800d 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -31,15 +31,6 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end, } #endif -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -void __init ioremap_huge_init(void); -int arch_ioremap_p4d_supported(void); -int arch_ioremap_pud_supported(void); -int arch_ioremap_pmd_supported(void); -#else -static inline void ioremap_huge_init(void) { } -#endif - /* * Managed iomap interface */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index d202fd2d0f91..c87d0cb0de6d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -198,7 +198,6 @@ struct iomap_ioend { struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ - void *io_private; /* file system private data */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ }; @@ -234,9 +233,7 @@ struct iomap_writepage_ctx { void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, - struct list_head *more_ioends, - void (*merge_private)(struct iomap_ioend *ioend, - struct iomap_ioend *next)); + struct list_head *more_ioends); void iomap_sort_ioends(struct list_head *ioend_list); int iomap_writepage(struct page *page, struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5e7fe519430a..32d448050bf7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -96,32 +96,6 @@ enum iommu_cap { IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ }; -/* - * Following constraints are specifc to FSL_PAMUV1: - * -aperture must be power of 2, and naturally aligned - * -number of windows must be power of 2, and address space size - * of each window is determined by aperture size / # of windows - * -the actual size of the mapped region of a window must be power - * of 2 starting with 4KB and physical address must be naturally - * aligned. - * DOMAIN_ATTR_FSL_PAMUV1 corresponds to the above mentioned contraints. - * The caller can invoke iommu_domain_get_attr to check if the underlying - * iommu implementation supports these constraints. - */ - -enum iommu_attr { - DOMAIN_ATTR_GEOMETRY, - DOMAIN_ATTR_PAGING, - DOMAIN_ATTR_WINDOWS, - DOMAIN_ATTR_FSL_PAMU_STASH, - DOMAIN_ATTR_FSL_PAMU_ENABLE, - DOMAIN_ATTR_FSL_PAMUV1, - DOMAIN_ATTR_NESTING, /* two stages of translation */ - DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, - DOMAIN_ATTR_IO_PGTABLE_CFG, - DOMAIN_ATTR_MAX, -}; - /* These are the possible reserved region types */ enum iommu_resv_type { /* Memory regions which must be mapped 1:1 at all times */ @@ -156,10 +130,24 @@ struct iommu_resv_region { enum iommu_resv_type type; }; -/* Per device IOMMU features */ +/** + * enum iommu_dev_features - Per device IOMMU features + * @IOMMU_DEV_FEAT_AUX: Auxiliary domain feature + * @IOMMU_DEV_FEAT_SVA: Shared Virtual Addresses + * @IOMMU_DEV_FEAT_IOPF: I/O Page Faults such as PRI or Stall. Generally + * enabling %IOMMU_DEV_FEAT_SVA requires + * %IOMMU_DEV_FEAT_IOPF, but some devices manage I/O Page + * Faults themselves instead of relying on the IOMMU. When + * supported, this feature must be enabled before and + * disabled after %IOMMU_DEV_FEAT_SVA. + * + * Device drivers query whether a feature is supported using + * iommu_dev_has_feature(), and enable it using iommu_dev_enable_feature(). + */ enum iommu_dev_features { - IOMMU_DEV_FEAT_AUX, /* Aux-domain feature */ - IOMMU_DEV_FEAT_SVA, /* Shared Virtual Addresses */ + IOMMU_DEV_FEAT_AUX, + IOMMU_DEV_FEAT_SVA, + IOMMU_DEV_FEAT_IOPF, }; #define IOMMU_PASID_INVALID (-1U) @@ -203,13 +191,11 @@ struct iommu_iotlb_gather { * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain * @device_group: find iommu group for a particular device - * @domain_get_attr: Query domain attributes - * @domain_set_attr: Change domain attributes + * @enable_nesting: Enable nesting + * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @get_resv_regions: Request list of reserved regions for a device * @put_resv_regions: Free list of reserved regions for a device * @apply_resv_region: Temporary helper call-back for iova reserved ranges - * @domain_window_enable: Configure and enable a particular window for a domain - * @domain_window_disable: Disable a particular window for a domain * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) @@ -255,10 +241,9 @@ struct iommu_ops { void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); - int (*domain_get_attr)(struct iommu_domain *domain, - enum iommu_attr attr, void *data); - int (*domain_set_attr)(struct iommu_domain *domain, - enum iommu_attr attr, void *data); + int (*enable_nesting)(struct iommu_domain *domain); + int (*set_pgtable_quirks)(struct iommu_domain *domain, + unsigned long quirks); /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); @@ -267,11 +252,6 @@ struct iommu_ops { struct iommu_domain *domain, struct iommu_resv_region *region); - /* Window handling functions */ - int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t paddr, u64 size, int prot); - void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); @@ -353,6 +333,7 @@ struct iommu_fault_param { * struct dev_iommu - Collection of per-device IOMMU data * * @fault_param: IOMMU detected device fault reporting data + * @iopf_param: I/O Page Fault queue and data * @fwspec: IOMMU fwspec data * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data @@ -363,12 +344,15 @@ struct iommu_fault_param { struct dev_iommu { struct mutex lock; struct iommu_fault_param *fault_param; + struct iopf_device_param *iopf_param; struct iommu_fwspec *fwspec; struct iommu_device *iommu_dev; void *priv; }; -int iommu_device_register(struct iommu_device *iommu); +int iommu_device_register(struct iommu_device *iommu, + const struct iommu_ops *ops, + struct device *hwdev); void iommu_device_unregister(struct iommu_device *iommu); int iommu_device_sysfs_add(struct iommu_device *iommu, struct device *parent, @@ -379,25 +363,6 @@ int iommu_device_link(struct iommu_device *iommu, struct device *link); void iommu_device_unlink(struct iommu_device *iommu, struct device *link); int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain); -static inline void __iommu_device_set_ops(struct iommu_device *iommu, - const struct iommu_ops *ops) -{ - iommu->ops = ops; -} - -#define iommu_device_set_ops(iommu, ops) \ -do { \ - struct iommu_ops *__ops = (struct iommu_ops *)(ops); \ - __ops->owner = THIS_MODULE; \ - __iommu_device_set_ops(iommu, __ops); \ -} while (0) - -static inline void iommu_device_set_fwnode(struct iommu_device *iommu, - struct fwnode_handle *fwnode) -{ - iommu->fwnode = fwnode; -} - static inline struct iommu_device *dev_to_iommu_device(struct device *dev) { return (struct iommu_device *)dev_get_drvdata(dev); @@ -507,15 +472,12 @@ extern int iommu_page_response(struct device *dev, extern int iommu_group_id(struct iommu_group *group); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); -extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, - void *data); -extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, - void *data); +int iommu_enable_nesting(struct iommu_domain *domain); +int iommu_set_pgtable_quirks(struct iommu_domain *domain, + unsigned long quirks); -/* Window handling function prototypes */ -extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t offset, u64 size, - int prot); +void iommu_set_dma_strict(bool val); +bool iommu_get_dma_strict(struct iommu_domain *domain); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); @@ -547,7 +509,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, * structure can be rewritten. */ if (gather->pgsize != size || - end < gather->start || start > gather->end) { + end + 1 < gather->start || start > gather->end + 1) { if (gather->pgsize) iommu_iotlb_sync(domain, gather); gather->pgsize = size; @@ -571,8 +533,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev); * struct iommu_fwspec - per-device IOMMU instance data * @ops: ops for this device's IOMMU * @iommu_fwnode: firmware handle for this device's IOMMU - * @iommu_priv: IOMMU driver private data for this device - * @num_pasid_bits: number of PASID bits supported by this device + * @flags: IOMMU_FWSPEC_* flags * @num_ids: number of associated device IDs * @ids: IDs which this device may present to the IOMMU */ @@ -580,7 +541,6 @@ struct iommu_fwspec { const struct iommu_ops *ops; struct fwnode_handle *iommu_fwnode; u32 flags; - u32 num_pasid_bits; unsigned int num_ids; u32 ids[]; }; @@ -742,13 +702,6 @@ static inline void iommu_iotlb_sync(struct iommu_domain *domain, { } -static inline int iommu_domain_window_enable(struct iommu_domain *domain, - u32 wnd_nr, phys_addr_t paddr, - u64 size, int prot) -{ - return -ENODEV; -} - static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { return 0; @@ -889,33 +842,19 @@ static inline int iommu_group_id(struct iommu_group *group) return -ENODEV; } -static inline int iommu_domain_get_attr(struct iommu_domain *domain, - enum iommu_attr attr, void *data) -{ - return -EINVAL; -} - -static inline int iommu_domain_set_attr(struct iommu_domain *domain, - enum iommu_attr attr, void *data) +static inline int iommu_set_pgtable_quirks(struct iommu_domain *domain, + unsigned long quirks) { - return -EINVAL; + return 0; } -static inline int iommu_device_register(struct iommu_device *iommu) +static inline int iommu_device_register(struct iommu_device *iommu, + const struct iommu_ops *ops, + struct device *hwdev) { return -ENODEV; } -static inline void iommu_device_set_ops(struct iommu_device *iommu, - const struct iommu_ops *ops) -{ -} - -static inline void iommu_device_set_fwnode(struct iommu_device *iommu, - struct fwnode_handle *fwnode) -{ -} - static inline struct iommu_device *dev_to_iommu_device(struct device *dev) { return NULL; diff --git a/include/linux/iova.h b/include/linux/iova.h index c834c01c0a5b..71d8a2de6635 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -95,6 +95,7 @@ struct iova_domain { flush-queues */ atomic_t fq_timer_on; /* 1 when timer is active, 0 when not */ + struct hlist_node cpuhp_dead; }; static inline unsigned long iova_size(struct iova *iova) @@ -156,7 +157,6 @@ int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); -void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad); #else static inline int iova_cache_get(void) { @@ -233,10 +233,6 @@ static inline void put_iova_domain(struct iova_domain *iovad) { } -static inline void free_cpu_cached_iovas(unsigned int cpu, - struct iova_domain *iovad) -{ -} #endif #endif diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 7a1dd7b969b6..62a8e3d23829 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -256,11 +256,11 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); -struct irq_domain *irq_domain_add_simple(struct device_node *of_node, - unsigned int size, - unsigned int first_irq, - const struct irq_domain_ops *ops, - void *host_data); +struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data); struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, unsigned int size, unsigned int first_irq, @@ -325,6 +325,15 @@ static inline struct irq_domain *irq_find_host(struct device_node *node) return d; } +static inline struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + return irq_domain_create_simple(of_node_to_fwnode(of_node), size, first_irq, ops, host_data); +} + /** * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 99d3cd051ac3..db0e1920cb12 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -61,7 +61,7 @@ void __jbd2_debug(int level, const char *file, const char *func, #define jbd_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else -#define jbd_debug(n, fmt, a...) /**/ +#define jbd_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); @@ -594,18 +594,22 @@ struct transaction_s */ unsigned long t_log_start; - /* Number of buffers on the t_buffers list [j_list_lock] */ + /* + * Number of buffers on the t_buffers list [j_list_lock, no locks + * needed for jbd2 thread] + */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet - * modified by this transaction [j_list_lock] + * modified by this transaction [j_list_lock, no locks needed fo + * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this - * transaction [j_list_lock] + * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; @@ -629,9 +633,11 @@ struct transaction_s struct journal_head *t_checkpoint_io_list; /* - * Doubly-linked circular list of metadata buffers being shadowed by log - * IO. The IO buffers on the iobuf list and the shadow buffers on this - * list match each other one for one at all times. [j_list_lock] + * Doubly-linked circular list of metadata buffers being + * shadowed by log IO. The IO buffers on the iobuf list and + * the shadow buffers on this list match each other one for + * one at all times. [j_list_lock, no locks needed for jbd2 + * thread] */ struct journal_head *t_shadow_list; @@ -768,7 +774,8 @@ enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; struct journal_s { /** - * @j_flags: General journaling state flags [j_state_lock] + * @j_flags: General journaling state flags [j_state_lock, + * no lock for quick racy checks] */ unsigned long j_flags; @@ -808,7 +815,8 @@ struct journal_s /** * @j_barrier_count: * - * Number of processes waiting to create a barrier lock [j_state_lock] + * Number of processes waiting to create a barrier lock [j_state_lock, + * no lock for quick racy checks] */ int j_barrier_count; @@ -821,7 +829,8 @@ struct journal_s * @j_running_transaction: * * Transactions: The current running transaction... - * [j_state_lock] [caller holding open handle] + * [j_state_lock, no lock for quick racy checks] [caller holding + * open handle] */ transaction_t *j_running_transaction; @@ -1033,7 +1042,7 @@ struct journal_s * @j_commit_sequence: * * Sequence number of the most recently committed transaction - * [j_state_lock]. + * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; @@ -1041,7 +1050,7 @@ struct journal_s * @j_commit_request: * * Sequence number of the most recent transaction wanting commit - * [j_state_lock] + * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d53ea3c047bc..b1678a61e6a7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -30,7 +30,8 @@ struct kunit_kasan_expectation { /* Software KASAN implementations use shadow memory. */ #ifdef CONFIG_KASAN_SW_TAGS -#define KASAN_SHADOW_INIT 0xFF +/* This matches KASAN_TAG_INVALID. */ +#define KASAN_SHADOW_INIT 0xFE #else #define KASAN_SHADOW_INIT 0 #endif @@ -95,6 +96,11 @@ static __always_inline bool kasan_enabled(void) return static_branch_likely(&kasan_flag_enabled); } +static inline bool kasan_has_integrated_init(void) +{ + return kasan_enabled(); +} + #else /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_enabled(void) @@ -102,6 +108,11 @@ static inline bool kasan_enabled(void) return true; } +static inline bool kasan_has_integrated_init(void) +{ + return false; +} + #endif /* CONFIG_KASAN_HW_TAGS */ slab_flags_t __kasan_never_merge(void); @@ -119,20 +130,20 @@ static __always_inline void kasan_unpoison_range(const void *addr, size_t size) __kasan_unpoison_range(addr, size); } -void __kasan_alloc_pages(struct page *page, unsigned int order); +void __kasan_alloc_pages(struct page *page, unsigned int order, bool init); static __always_inline void kasan_alloc_pages(struct page *page, - unsigned int order) + unsigned int order, bool init) { if (kasan_enabled()) - __kasan_alloc_pages(page, order); + __kasan_alloc_pages(page, order, init); } -void __kasan_free_pages(struct page *page, unsigned int order); +void __kasan_free_pages(struct page *page, unsigned int order, bool init); static __always_inline void kasan_free_pages(struct page *page, - unsigned int order) + unsigned int order, bool init) { if (kasan_enabled()) - __kasan_free_pages(page, order); + __kasan_free_pages(page, order, init); } void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size, @@ -192,11 +203,13 @@ static __always_inline void * __must_check kasan_init_slab_obj( return (void *)object; } -bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip); -static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) +bool __kasan_slab_free(struct kmem_cache *s, void *object, + unsigned long ip, bool init); +static __always_inline bool kasan_slab_free(struct kmem_cache *s, + void *object, bool init) { if (kasan_enabled()) - return __kasan_slab_free(s, object, _RET_IP_); + return __kasan_slab_free(s, object, _RET_IP_, init); return false; } @@ -215,12 +228,12 @@ static __always_inline void kasan_slab_free_mempool(void *ptr) } void * __must_check __kasan_slab_alloc(struct kmem_cache *s, - void *object, gfp_t flags); + void *object, gfp_t flags, bool init); static __always_inline void * __must_check kasan_slab_alloc( - struct kmem_cache *s, void *object, gfp_t flags) + struct kmem_cache *s, void *object, gfp_t flags, bool init) { if (kasan_enabled()) - return __kasan_slab_alloc(s, object, flags); + return __kasan_slab_alloc(s, object, flags, init); return object; } @@ -276,13 +289,17 @@ static inline bool kasan_enabled(void) { return false; } +static inline bool kasan_has_integrated_init(void) +{ + return false; +} static inline slab_flags_t kasan_never_merge(void) { return 0; } static inline void kasan_unpoison_range(const void *address, size_t size) {} -static inline void kasan_alloc_pages(struct page *page, unsigned int order) {} -static inline void kasan_free_pages(struct page *page, unsigned int order) {} +static inline void kasan_alloc_pages(struct page *page, unsigned int order, bool init) {} +static inline void kasan_free_pages(struct page *page, unsigned int order, bool init) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} @@ -298,14 +315,14 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache, { return (void *)object; } -static inline bool kasan_slab_free(struct kmem_cache *s, void *object) +static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init) { return false; } static inline void kasan_kfree_large(void *ptr) {} static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, - gfp_t flags) + gfp_t flags, bool init) { return object; } diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 24a59cb06963..cc8fa109cfa3 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -70,10 +70,4 @@ */ #define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) -/* - * IF_ENABLED(CONFIG_FOO, ptr) evaluates to (ptr) if CONFIG_FOO is set to 'y' - * or 'm', NULL otherwise. - */ -#define IF_ENABLED(option, ptr) (IS_ENABLED(option) ? (ptr) : NULL) - #endif /* __LINUX_KCONFIG_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5b7ed6dc99ac..15d8bad3d2f2 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -3,6 +3,7 @@ #define _LINUX_KERNEL_H #include <stdarg.h> +#include <linux/align.h> #include <linux/limits.h> #include <linux/linkage.h> #include <linux/stddef.h> @@ -30,14 +31,6 @@ */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) -/* @a is a power of 2 value */ -#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) -#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) -#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) -#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) -#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) -#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) - /* generic data direction definitions */ #define READ 0 #define WRITE 1 @@ -48,6 +41,8 @@ */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) +#define PTR_IF(cond, ptr) ((cond) ? (ptr) : NULL) + #define u64_to_user_ptr(x) ( \ { \ typecheck(u64, (x)); \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1b65e7204344..76102efbf079 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -10,6 +10,7 @@ #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> +#include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> @@ -146,7 +147,7 @@ static inline bool is_error_page(struct page *page) */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQUEST_ARCH_BASE 8 @@ -192,8 +193,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); @@ -218,6 +219,20 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif +#ifdef KVM_ARCH_WANT_MMU_NOTIFIER +struct kvm_gfn_range { + struct kvm_memory_slot *slot; + gfn_t start; + gfn_t end; + pte_t pte; + bool may_block; +}; +bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); +bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); +bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); +bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); +#endif + enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, @@ -251,6 +266,11 @@ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) return !!map->hva; } +static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) +{ + return single_task_running() && !need_resched() && ktime_before(cur, stop); +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -324,6 +344,51 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; }; +/* must be called with irqs disabled */ +static __always_inline void guest_enter_irqoff(void) +{ + /* + * This is running in ioctl context so its safe to assume that it's the + * stime pending cputime to flush. + */ + instrumentation_begin(); + vtime_account_guest_enter(); + instrumentation_end(); + + /* + * KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspace from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + if (!context_tracking_guest_enter()) { + instrumentation_begin(); + rcu_virt_note_context_switch(smp_processor_id()); + instrumentation_end(); + } +} + +static __always_inline void guest_exit_irqoff(void) +{ + context_tracking_guest_exit(); + + instrumentation_begin(); + /* Flush the guest cputime we spent on the guest */ + vtime_account_guest_exit(); + instrumentation_end(); +} + +static inline void guest_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_exit_irqoff(); + local_irq_restore(flags); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* @@ -640,6 +705,7 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) @@ -886,7 +952,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, - struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot); #else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, @@ -945,6 +1011,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); @@ -1116,7 +1183,7 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) } static inline unsigned long -__gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +__gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 01f251b6e36c..89b69e645ac7 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -141,7 +141,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, struct nvdimm_bus; struct module; -struct device; struct nd_blk_region; struct nd_blk_region_desc { int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 61f04f7dc1a4..04c01794de83 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -59,6 +59,7 @@ LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) +LSM_HOOK(void, LSM_RET_VOID, sb_delete, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts) LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index ba2ccd950833..5c4c5c0602cb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -108,6 +108,9 @@ * allocated. * @sb contains the super_block structure to be modified. * Return 0 if operation was successful. + * @sb_delete: + * Release objects tied to a superblock (e.g. inodes). + * @sb contains the super_block structure being released. * @sb_free_security: * Deallocate and clear the sb->s_security field. * @sb contains the super_block structure to be modified. @@ -1585,6 +1588,7 @@ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_inode; + int lbs_superblock; int lbs_ipc; int lbs_msg_msg; int lbs_task; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c04d39a7967..c193be760709 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -76,10 +76,27 @@ enum mem_cgroup_events_target { }; struct memcg_vmstats_percpu { - long stat[MEMCG_NR_STAT]; - unsigned long events[NR_VM_EVENT_ITEMS]; - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; + /* Local (CPU and cgroup) page state & events */ + long state[MEMCG_NR_STAT]; + unsigned long events[NR_VM_EVENT_ITEMS]; + + /* Delta calculation for lockless upward propagation */ + long state_prev[MEMCG_NR_STAT]; + unsigned long events_prev[NR_VM_EVENT_ITEMS]; + + /* Cgroup1: threshold notifications & softlimit tree updates */ + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + +struct memcg_vmstats { + /* Aggregated (CPU and subtree) page state & events */ + long state[MEMCG_NR_STAT]; + unsigned long events[NR_VM_EVENT_ITEMS]; + + /* Pending child counts during tree propagation */ + long state_pending[MEMCG_NR_STAT]; + unsigned long events_pending[NR_VM_EVENT_ITEMS]; }; struct mem_cgroup_reclaim_iter { @@ -97,12 +114,13 @@ struct batched_lruvec_stat { }; /* - * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, - * which have elements charged to this memcg. + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to this memcg. */ -struct memcg_shrinker_map { +struct shrinker_info { struct rcu_head rcu; - unsigned long map[]; + atomic_long_t *nr_deferred; + unsigned long *map; }; /* @@ -128,7 +146,7 @@ struct mem_cgroup_per_node { struct mem_cgroup_reclaim_iter iter; - struct memcg_shrinker_map __rcu *shrinker_map; + struct shrinker_info __rcu *shrinker_info; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ @@ -287,8 +305,8 @@ struct mem_cgroup { MEMCG_PADDING(_pad1_); - atomic_long_t vmstats[MEMCG_NR_STAT]; - atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; + /* memory.stat */ + struct memcg_vmstats vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; @@ -315,10 +333,6 @@ struct mem_cgroup { atomic_t moving_account; struct task_struct *move_lock_task; - /* Legacy local VM stats and events */ - struct memcg_vmstats_percpu __percpu *vmstats_local; - - /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK @@ -358,6 +372,62 @@ enum page_memcg_data_flags { #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) +static inline bool PageMemcgKmem(struct page *page); + +/* + * After the initialization objcg->memcg is always pointing at + * a valid memcg, but can be atomically swapped to the parent memcg. + * + * The caller must ensure that the returned memcg won't be released: + * e.g. acquire the rcu_read_lock or css_set_lock. + */ +static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) +{ + return READ_ONCE(objcg->memcg); +} + +/* + * __page_memcg - get the memory cgroup associated with a non-kmem page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper memory cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages or + * kmem pages. + */ +static inline struct mem_cgroup *__page_memcg(struct page *page) +{ + unsigned long memcg_data = page->memcg_data; + + VM_BUG_ON_PAGE(PageSlab(page), page); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * __page_objcg - get the object cgroup associated with a kmem page + * @page: a pointer to the page struct + * + * Returns a pointer to the object cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper object cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages or + * LRU pages. + */ +static inline struct obj_cgroup *__page_objcg(struct page *page) +{ + unsigned long memcg_data = page->memcg_data; + + VM_BUG_ON_PAGE(PageSlab(page), page); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); + VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page); + + return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + /* * page_memcg - get the memory cgroup associated with a page * @page: a pointer to the page struct @@ -367,20 +437,23 @@ enum page_memcg_data_flags { * proper memory cgroup pointer. It's not safe to call this function * against some type of pages, e.g. slab pages or ex-slab pages. * - * Any of the following ensures page and memcg binding stability: + * For a non-kmem page any of the following ensures page and memcg binding + * stability: + * * - the page lock * - LRU isolation * - lock_page_memcg() * - exclusive reference + * + * For a kmem page a caller should hold an rcu read lock to protect memcg + * associated with a kmem page from being released. */ static inline struct mem_cgroup *page_memcg(struct page *page) { - unsigned long memcg_data = page->memcg_data; - - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + if (PageMemcgKmem(page)) + return obj_cgroup_memcg(__page_objcg(page)); + else + return __page_memcg(page); } /* @@ -394,11 +467,19 @@ static inline struct mem_cgroup *page_memcg(struct page *page) */ static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { + unsigned long memcg_data = READ_ONCE(page->memcg_data); + VM_BUG_ON_PAGE(PageSlab(page), page); WARN_ON_ONCE(!rcu_read_lock_held()); - return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) & - ~MEMCG_DATA_FLAGS_MASK); + if (memcg_data & MEMCG_DATA_KMEM) { + struct obj_cgroup *objcg; + + objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return obj_cgroup_memcg(objcg); + } + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* @@ -406,15 +487,21 @@ static inline struct mem_cgroup *page_memcg_rcu(struct page *page) * @page: a pointer to the page struct * * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function unlike page_memcg() can take any page + * or NULL. This function unlike page_memcg() can take any page * as an argument. It has to be used in cases when it's not known if a page - * has an associated memory cgroup pointer or an object cgroups vector. + * has an associated memory cgroup pointer or an object cgroups vector or + * an object cgroup. + * + * For a non-kmem page any of the following ensures page and memcg binding + * stability: * - * Any of the following ensures page and memcg binding stability: * - the page lock * - LRU isolation * - lock_page_memcg() * - exclusive reference + * + * For a kmem page a caller should hold an rcu read lock to protect memcg + * associated with a kmem page from being released. */ static inline struct mem_cgroup *page_memcg_check(struct page *page) { @@ -427,9 +514,17 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) if (memcg_data & MEMCG_DATA_OBJCGS) return NULL; + if (memcg_data & MEMCG_DATA_KMEM) { + struct obj_cgroup *objcg; + + objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return obj_cgroup_memcg(objcg); + } + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +#ifdef CONFIG_MEMCG_KMEM /* * PageMemcgKmem - check if the page has MemcgKmem flag set * @page: a pointer to the page struct @@ -444,7 +539,6 @@ static inline bool PageMemcgKmem(struct page *page) return page->memcg_data & MEMCG_DATA_KMEM; } -#ifdef CONFIG_MEMCG_KMEM /* * page_objcgs - get the object cgroups vector associated with a page * @page: a pointer to the page struct @@ -486,6 +580,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #else +static inline bool PageMemcgKmem(struct page *page) +{ + return false; +} + static inline struct obj_cgroup **page_objcgs(struct page *page) { return NULL; @@ -596,18 +695,15 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) } int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); +int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, + gfp_t gfp, swp_entry_t entry); +void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); -static struct mem_cgroup_per_node * -mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) -{ - return memcg->nodeinfo[nid]; -} - /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec @@ -631,7 +727,7 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, if (!memcg) memcg = root_mem_cgroup; - mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* @@ -708,21 +804,15 @@ static inline void obj_cgroup_get(struct obj_cgroup *objcg) percpu_ref_get(&objcg->refcnt); } -static inline void obj_cgroup_put(struct obj_cgroup *objcg) +static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, + unsigned long nr) { - percpu_ref_put(&objcg->refcnt); + percpu_ref_get_many(&objcg->refcnt, nr); } -/* - * After the initialization objcg->memcg is always pointing at - * a valid memcg, but can be atomically swapped to the parent memcg. - * - * The caller must ensure that the returned memcg won't be released: - * e.g. acquire the rcu_read_lock or css_set_lock. - */ -static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) +static inline void obj_cgroup_put(struct obj_cgroup *objcg) { - return READ_ONCE(objcg->memcg); + percpu_ref_put(&objcg->refcnt); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) @@ -867,43 +957,9 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); extern bool cgroup_memory_noswap; #endif -struct mem_cgroup *lock_page_memcg(struct page *page); -void __unlock_page_memcg(struct mem_cgroup *memcg); +void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); -/* - * idx can be of type enum memcg_stat_item or node_stat_item. - * Keep in sync with memcg_exact_page_state(). - */ -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - long x = atomic_long_read(&memcg->vmstats[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} - -/* - * idx can be of type enum memcg_stat_item or node_stat_item. - * Keep in sync with memcg_exact_page_state(). - */ -static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, - int idx) -{ - long x = 0; - int cpu; - - for_each_possible_cpu(cpu) - x += per_cpu(memcg->vmstats_local->stat[idx], cpu); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} - void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ @@ -979,10 +1035,6 @@ static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, local_irq_restore(flags); } -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); - void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); @@ -1063,13 +1115,15 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, void split_page_memcg(struct page *head, unsigned int nr); +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); + #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 -struct mem_cgroup; - static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; @@ -1139,6 +1193,16 @@ static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, return 0; } +static inline int mem_cgroup_swapin_charge_page(struct page *page, + struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) +{ + return 0; +} + +static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) +{ +} + static inline void mem_cgroup_uncharge(struct page *page) { } @@ -1171,6 +1235,10 @@ static inline bool lruvec_holds_page_lru_lock(struct page *page, return lruvec == &pgdat->__lruvec; } +static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +{ +} + static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; @@ -1289,12 +1357,7 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline struct mem_cgroup *lock_page_memcg(struct page *page) -{ - return NULL; -} - -static inline void __unlock_page_memcg(struct mem_cgroup *memcg) +static inline void lock_page_memcg(struct page *page) { } @@ -1334,17 +1397,6 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } -static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) -{ - return 0; -} - -static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, - int idx) -{ - return 0; -} - static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) @@ -1390,18 +1442,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, mod_node_page_state(page_pgdat(page), idx, val); } -static inline -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - return 0; -} - -static inline void split_page_memcg(struct page *head, unsigned int nr) -{ -} - static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) @@ -1424,8 +1464,16 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline void split_page_memcg(struct page *head, unsigned int nr) +{ +} + +static inline +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { + return 0; } #endif /* CONFIG_MEMCG */ @@ -1563,10 +1611,10 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -extern int memcg_expand_shrinker_maps(int new_id); - -extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id); +int alloc_shrinker_info(struct mem_cgroup *memcg); +void free_shrinker_info(struct mem_cgroup *memcg); +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); +void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; @@ -1576,8 +1624,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) return false; } -static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, - int nid, int shrinker_id) +static inline void set_shrinker_bit(struct mem_cgroup *memcg, + int nid, int shrinker_id) { } #endif diff --git a/include/linux/memory.h b/include/linux/memory.h index 4da95e684e20..97e92e8b556a 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -29,6 +29,11 @@ struct memory_block { int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ struct device dev; + /* + * Number of vmemmap pages. These pages + * lay at the beginning of the memory block. + */ + unsigned long nr_vmemmap_pages; }; int arch_get_memory_phys_device(unsigned long start_pfn); @@ -80,7 +85,8 @@ static inline int memory_notify(unsigned long val, void *v) #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -int create_memory_block_devices(unsigned long start, unsigned long size); +int create_memory_block_devices(unsigned long start, unsigned long size, + unsigned long vmemmap_pages); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7288aa5ef73b..28f32fd00fe9 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -56,6 +56,14 @@ typedef int __bitwise mhp_t; #define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* + * We want memmap (struct page array) to be self contained. + * To do so, we will use the beginning of the hot-added range to build + * the page tables for the memmap array that describes the entire range. + * Only selected architectures support it with SPARSE_VMEMMAP. + */ +#define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1)) + +/* * Extended parameters for memory hotplug: * altmap: alternative allocator for memmap array (optional) * pgprot: page protection flags to apply to newly created page tables @@ -99,9 +107,13 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); +extern void adjust_present_page_count(struct zone *zone, long nr_pages); /* VM interface that may be used by firmware interface */ +extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, + struct zone *zone); +extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, - int online_type, int nid); + struct zone *zone); extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, @@ -359,6 +371,7 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_ extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); +extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f5b464daeeca..45a79da89c5f 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -17,7 +17,7 @@ struct device; * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { - const unsigned long base_pfn; + unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3a389633b68f..4bb4e519e3f5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -27,6 +27,7 @@ enum migrate_reason { MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, MR_CONTIG_RANGE, + MR_LONGTERM_PIN, MR_TYPES }; @@ -43,10 +44,7 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); extern struct page *alloc_migration_target(struct page *page, unsigned long private); extern int isolate_movable_page(struct page *page, isolate_mode_t mode); -extern void putback_movable_page(struct page *page); -extern void migrate_prep(void); -extern void migrate_prep_local(void); extern void migrate_page_states(struct page *newpage, struct page *page); extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, @@ -66,9 +64,6 @@ static inline struct page *alloc_migration_target(struct page *page, static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) { return -EBUSY; } -static inline int migrate_prep(void) { return -ENOSYS; } -static inline int migrate_prep_local(void) { return -ENOSYS; } - static inline void migrate_page_states(struct page *newpage, struct page *page) { } diff --git a/include/linux/minmax.h b/include/linux/minmax.h index c0f57b0c64d9..5433c08fcc68 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -2,6 +2,8 @@ #ifndef _LINUX_MINMAX_H #define _LINUX_MINMAX_H +#include <linux/const.h> + /* * min()/max()/clamp() macros must accomplish three things: * @@ -17,14 +19,6 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* - * This returns a constant expression while determining if an argument is - * a constant expression, most importantly without evaluating the argument. - * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de> - */ -#define __is_constexpr(x) \ - (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) - #define __no_side_effects(x, y) \ (__is_constexpr(x) && __is_constexpr(y)) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4e531c2aab52..020a8f7fdbdd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -703,6 +703,27 @@ struct mlx5_hv_vhca; #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) +enum { + MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, +}; + +enum { + MR_CACHE_LAST_STD_ENTRY = 20, + MLX5_IMR_MTT_CACHE_ENTRY, + MLX5_IMR_KSM_CACHE_ENTRY, + MAX_MR_CACHE_ENTRIES +}; + +struct mlx5_profile { + u64 mask; + u8 log_max_qp; + struct { + int size; + int limit; + } mr_cache[MAX_MR_CACHE_ENTRIES]; +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -731,7 +752,7 @@ struct mlx5_core_dev { struct mutex intf_state_mutex; unsigned long intf_state; struct mlx5_priv priv; - struct mlx5_profile *profile; + struct mlx5_profile profile; u32 issi; struct mlx5e_resources mlx5e_res; struct mlx5_dm *dm; @@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey) return mkey & 0xff; } -enum { - MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, -}; - -enum { - MR_CACHE_LAST_STD_ENTRY = 20, - MLX5_IMR_MTT_CACHE_ENTRY, - MLX5_IMR_KSM_CACHE_ENTRY, - MAX_MR_CACHE_ENTRIES -}; - /* Async-atomic event notifier used by mlx5 core to forward FW * evetns recived from event queue to mlx5 consumers. * Optimise event queue dipatching. @@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -struct mlx5_profile { - u64 mask; - u8 log_max_qp; - struct { - int size; - int limit; - } mr_cache[MAX_MR_CACHE_ENTRIES]; -}; - enum { MLX5_PCI_DEV_IS_VF = 1 << 0, }; @@ -1236,7 +1236,7 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; -static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) +static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev) { struct devlink *devlink = priv_to_devlink(dev); union devlink_param_value val; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 52b7cabcde08..6d16eed6850e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -133,6 +133,7 @@ enum { MLX5_CMD_OP_PAGE_FAULT_RESUME = 0x204, MLX5_CMD_OP_ALLOC_MEMIC = 0x205, MLX5_CMD_OP_DEALLOC_MEMIC = 0x206, + MLX5_CMD_OP_MODIFY_MEMIC = 0x207, MLX5_CMD_OP_CREATE_EQ = 0x301, MLX5_CMD_OP_DESTROY_EQ = 0x302, MLX5_CMD_OP_QUERY_EQ = 0x303, @@ -1031,7 +1032,11 @@ struct mlx5_ifc_device_mem_cap_bits { u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x680]; + u8 reserved_at_180[0x80]; + + u8 memic_operations[0x20]; + + u8 reserved_at_220[0x5e0]; }; struct mlx5_ifc_device_event_cap_bits { @@ -10498,6 +10503,41 @@ struct mlx5_ifc_destroy_vport_lag_in_bits { u8 reserved_at_40[0x40]; }; +enum { + MLX5_MODIFY_MEMIC_OP_MOD_ALLOC, + MLX5_MODIFY_MEMIC_OP_MOD_DEALLOC, +}; + +struct mlx5_ifc_modify_memic_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x18]; + u8 memic_operation_type[0x8]; + + u8 memic_start_addr[0x40]; + + u8 reserved_at_c0[0x140]; +}; + +struct mlx5_ifc_modify_memic_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 memic_operation_addr[0x40]; + + u8 reserved_at_c0[0x140]; +}; + struct mlx5_ifc_alloc_memic_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h new file mode 100644 index 000000000000..bf700c8d5516 --- /dev/null +++ b/include/linux/mlx5/mpfs.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2021 Mellanox Technologies Ltd. + */ + +#ifndef _MLX5_MPFS_ +#define _MLX5_MPFS_ + +struct mlx5_core_dev; + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif + +#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 21115933b9b8..c274f75efcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -106,7 +106,7 @@ extern int mmap_rnd_compat_bits __read_mostly; * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. - * It's defined as noop for arcitectures that don't support memory tagging. + * It's defined as noop for architectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) @@ -372,6 +372,13 @@ extern unsigned int kobjsize(const void *objp); # define VM_GROWSUP VM_NONE #endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +# define VM_UFFD_MINOR_BIT 37 +# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ +#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +# define VM_UFFD_MINOR VM_NONE +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) @@ -432,8 +439,7 @@ extern unsigned int kobjsize(const void *objp); extern pgprot_t protection_map[16]; /** - * Fault flag definitions. - * + * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. @@ -464,16 +470,18 @@ extern pgprot_t protection_map[16]; * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. */ -#define FAULT_FLAG_WRITE 0x01 -#define FAULT_FLAG_MKWRITE 0x02 -#define FAULT_FLAG_ALLOW_RETRY 0x04 -#define FAULT_FLAG_RETRY_NOWAIT 0x08 -#define FAULT_FLAG_KILLABLE 0x10 -#define FAULT_FLAG_TRIED 0x20 -#define FAULT_FLAG_USER 0x40 -#define FAULT_FLAG_REMOTE 0x80 -#define FAULT_FLAG_INSTRUCTION 0x100 -#define FAULT_FLAG_INTERRUPTIBLE 0x200 +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, +}; /* * The default fault flags that should be used by most of the @@ -485,6 +493,7 @@ extern pgprot_t protection_map[16]; /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time + * @flags: Fault flags. * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition @@ -495,7 +504,7 @@ extern pgprot_t protection_map[16]; * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ -static inline bool fault_flag_allow_retry_first(unsigned int flags) +static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); @@ -530,7 +539,7 @@ struct vm_fault { pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ }; - unsigned int flags; /* FAULT_FLAG_xxx flags + enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ @@ -580,7 +589,7 @@ struct vm_operations_struct { void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); - int (*mremap)(struct vm_area_struct *area, unsigned long flags); + int (*mremap)(struct vm_area_struct *area); /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not @@ -1132,6 +1141,11 @@ static inline bool is_zone_device_page(const struct page *page) } #endif +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} + #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); @@ -1265,13 +1279,16 @@ static inline void put_page(struct page *page) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); +void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, + bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); /** - * page_maybe_dma_pinned() - report if a page is pinned for DMA. + * page_maybe_dma_pinned - Report if a page is pinned for DMA. + * @page: The page. * * This function checks if a page has been pinned via a call to - * pin_user_pages*(). + * a function in the pin_user_pages() family. * * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably @@ -1289,9 +1306,8 @@ void unpin_user_pages(struct page **pages, unsigned long npages); * * For more information, please see Documentation/core-api/pin_user_pages.rst. * - * @page: pointer to page to be queried. - * @Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. + * Return: True, if it is likely that the page has been "dma-pinned". + * False, if the page is definitely not dma-pinned. */ static inline bool page_maybe_dma_pinned(struct page *page) { @@ -1539,6 +1555,20 @@ static inline unsigned long page_to_section(const struct page *page) } #endif +/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ +#ifdef CONFIG_MIGRATION +static inline bool is_pinnable_page(struct page *page) +{ + return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || + is_zero_pfn(page_to_pfn(page)); +} +#else +static inline bool is_pinnable_page(struct page *page) +{ + return true; +} +#endif + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); @@ -1629,7 +1659,6 @@ static inline pgoff_t page_index(struct page *page) bool page_mapped(struct page *page); struct address_space *page_mapping(struct page *page); -struct address_space *page_mapping_file(struct page *page); /* * Return true only if the page has been allocated with @@ -2357,7 +2386,7 @@ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); -extern void mem_init_print_info(const char *str); +extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); @@ -2731,6 +2760,8 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); +int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); @@ -2790,7 +2821,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ #define FOLL_POPULATE 0x40 /* fault in page */ -#define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ @@ -3186,5 +3216,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..5aacc1c10a45 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -97,10 +97,10 @@ struct page { }; struct { /* page_pool used by netstack */ /** - * @dma_addr: might require a 64-bit value even on + * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ - dma_addr_t dma_addr; + unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 47946cec7584..0d53eba1c383 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -55,7 +55,7 @@ enum migratetype { * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. What is important though * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger then + * MAX_ORDER_NR_PAGES should biggest page be bigger than * a single pageblock. */ MIGRATE_CMA, @@ -407,8 +407,13 @@ enum zone_type { * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might - * essentially turn such pages unmovable. Memory offlining might - * retry a long time. + * essentially turn such pages unmovable. Therefore, we do not allow + * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and + * faulted, they come from the right zone right away. However, it is + * still possible that address space already has pages in + * ZONE_MOVABLE at the time when pages are pinned (i.e. user has + * touches that memory before pinning). In such case we migrate them + * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. @@ -427,6 +432,15 @@ enum zone_type { * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). + * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create + * situations where ZERO_PAGE(0) which is allocated differently + * on different platforms may end up in a movable zone. ZERO_PAGE(0) + * cannot be migrated. + * 7. Memory-hotplug: when using memmap_on_memory and onlining the + * memory to the MOVABLE zone, the vmemmap pages are also placed in + * such zone. Such pages cannot be really moved around as they are + * self-stored in the range, but they are treated as movable when + * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) @@ -993,7 +1007,8 @@ static inline int is_highmem_idx(enum zone_type idx) * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. - * @zone - pointer to struct zone variable + * @zone: pointer to struct zone variable + * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { @@ -1044,7 +1059,7 @@ extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes - * @pgdat - pointer to a pg_data_t variable + * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ @@ -1052,7 +1067,7 @@ extern struct zone *next_zone(struct zone *zone); pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones - * @zone - pointer to struct zone variable + * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. @@ -1091,15 +1106,18 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z, /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point - * @z - The cursor used as a starting point for the search - * @highest_zoneidx - The zone index of the highest zone to return - * @nodes - An optional nodemask to filter the zonelist with + * @z: The cursor used as a starting point for the search + * @highest_zoneidx: The zone index of the highest zone to return + * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. + * + * Return: the next zone at or below highest_zoneidx within the allowed + * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, @@ -1112,10 +1130,9 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist - * @zonelist - The zonelist to search for a suitable zone - * @highest_zoneidx - The zone index of the highest zone to return - * @nodes - An optional nodemask to filter the zonelist with - * @return - Zoneref pointer for the first suitable zone found (see below) + * @zonelist: The zonelist to search for a suitable zone + * @highest_zoneidx: The zone index of the highest zone to return + * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be @@ -1125,6 +1142,8 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. + * + * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, @@ -1136,11 +1155,11 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask - * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->_zonerefs being iterated - * @zlist - The zonelist being iterated - * @highidx - The zone index of the highest zone to return - * @nodemask - Nodemask allowed by the allocator + * @zone: The current zone in the iterator + * @z: The current pointer within zonelist->_zonerefs being iterated + * @zlist: The zonelist being iterated + * @highidx: The zone index of the highest zone to return + * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask @@ -1160,10 +1179,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index - * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->zones being iterated - * @zlist - The zonelist being iterated - * @highidx - The zone index of the highest zone to return + * @zone: The current zone in the iterator + * @z: The current pointer within zonelist->zones being iterated + * @zlist: The zonelist being iterated + * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ @@ -1378,10 +1397,8 @@ static inline int online_section_nr(unsigned long nr) #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); -#ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif -#endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { diff --git a/include/linux/msi.h b/include/linux/msi.h index aef35fd1cf11..6aff469e511d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -240,8 +240,7 @@ void pci_msi_unmask_irq(struct irq_data *data); /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific - * code if needed. These hooks must be enabled by the architecture or by - * drivers which depend on them via msi_controller based MSI handling. + * code if needed. These hooks can only be enabled by the architecture. * * If CONFIG_PCI_MSI_ARCH_FALLBACKS is not selected they are replaced by * stubs with warnings. @@ -251,7 +250,6 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -void default_teardown_msi_irqs(struct pci_dev *dev); #else static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { @@ -272,19 +270,6 @@ static inline void arch_teardown_msi_irqs(struct pci_dev *dev) void arch_restore_msi_irqs(struct pci_dev *dev); void default_restore_msi_irqs(struct pci_dev *dev); -struct msi_controller { - struct module *owner; - struct device *dev; - struct device_node *of_node; - struct list_head list; - - int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev, - struct msi_desc *desc); - int (*setup_irqs)(struct msi_controller *chip, struct pci_dev *dev, - int nvec, int type); - void (*teardown_irq)(struct msi_controller *chip, unsigned int irq); -}; - #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN #include <linux/irqhandler.h> diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 2aab9612f6ab..4f9a4b3c5892 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,8 +53,7 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); -void arpt_unregister_table_pre_exit(struct net *net, const char *name, - const struct nf_hook_ops *ops); +void arpt_unregister_table_pre_exit(struct net *net, const char *name); extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5b4c67c91f56..15004c469807 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -452,6 +452,7 @@ enum lock_type4 { #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_CLONE_BLKSIZE (1UL << 13) +#define FATTR4_WORD2_CHANGE_ATTR_TYPE (1UL << 15) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) #define FATTR4_WORD2_MODE_UMASK (1UL << 17) #define FATTR4_WORD2_XATTR_SUPPORT (1UL << 18) @@ -709,6 +710,14 @@ struct nl4_server { } u; }; +enum nfs4_change_attr_type { + NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0, + NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1, + NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2, + NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3, + NFS4_CHANGE_TYPE_IS_UNDEFINED = 4, +}; + /* * Options for setxattr. These match the flags for setxattr(2). */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index eadaabd18dc7..ffba254d2098 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -246,11 +246,15 @@ struct nfs4_copy_state { BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ +#define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */ +#define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ | NFS_INO_INVALID_MTIME \ | NFS_INO_INVALID_SIZE \ + | NFS_INO_INVALID_NLINK \ + | NFS_INO_INVALID_MODE \ | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* @@ -386,7 +390,7 @@ extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); -extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); +extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a28d71b45b5f..d71a0e90faeb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -156,6 +156,7 @@ struct nfs_server { #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 + unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ unsigned int rpages; /* read size (in pages) */ @@ -180,6 +181,9 @@ struct nfs_server { #define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */ #define NFS_OPTION_MIGRATION 0x00000002 /* - NFSv4 migration enabled */ + enum nfs4_change_attr_type + change_attr_type;/* Description of change attribute */ + struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ struct timespec64 time_delta; /* smallest time granularity */ @@ -265,16 +269,7 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) -/* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ #define NFS_CAP_LGOPEN (1U << 5) -#define NFS_CAP_FILEID (1U << 6) -#define NFS_CAP_MODE (1U << 7) -#define NFS_CAP_NLINK (1U << 8) -#define NFS_CAP_OWNER (1U << 9) -#define NFS_CAP_OWNER_GROUP (1U << 10) -#define NFS_CAP_ATIME (1U << 11) -#define NFS_CAP_CTIME (1U << 12) -#define NFS_CAP_MTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3327239fa2f9..717ecc87c9e7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -15,6 +15,8 @@ #define NFS_DEF_FILE_IO_SIZE (4096U) #define NFS_MIN_FILE_IO_SIZE (1024U) +#define NFS_BITMASK_SZ 3 + struct nfs4_string { unsigned int len; char *data; @@ -150,6 +152,8 @@ struct nfs_fsinfo { __u32 layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */ __u32 blksize; /* preferred pnfs io block size */ __u32 clone_blksize; /* granularity of a CLONE operation */ + enum nfs4_change_attr_type + change_attr_type; /* Info about change attr */ __u32 xattr_support; /* User xattrs supported */ }; @@ -525,7 +529,8 @@ struct nfs_closeargs { struct nfs_seqid * seqid; fmode_t fmode; u32 share_access; - u32 * bitmask; + const u32 * bitmask; + u32 bitmask_store[NFS_BITMASK_SZ]; struct nfs4_layoutreturn_args *lr_args; }; @@ -608,7 +613,8 @@ struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; const nfs4_stateid *stateid; - u32 * bitmask; + const u32 *bitmask; + u32 bitmask_store[NFS_BITMASK_SZ]; struct nfs4_layoutreturn_args *lr_args; }; @@ -648,7 +654,8 @@ struct nfs_pgio_args { union { unsigned int replen; /* used by read */ struct { - u32 * bitmask; /* used by write */ + const u32 * bitmask; /* used by write */ + u32 bitmask_store[NFS_BITMASK_SZ]; /* used by write */ enum nfs3_stable_how stable; /* used by write */ }; }; diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 7d4ec26d8a3e..ef1e3e736e14 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -21,16 +21,17 @@ #elif MAX_NR_ZONES <= 8 #define ZONES_SHIFT 3 #else -#error ZONES_SHIFT -- too many zones configured adjust calculation +#error ZONES_SHIFT "Too many zones configured" #endif +#define ZONES_WIDTH ZONES_SHIFT + #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> - -/* SECTION_SHIFT #bits space required to store a section # */ #define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS) - -#endif /* CONFIG_SPARSEMEM */ +#else +#define SECTIONS_SHIFT 0 +#endif #ifndef BUILD_VDSO32_64 /* @@ -54,17 +55,28 @@ #define SECTIONS_WIDTH 0 #endif -#define ZONES_WIDTH ZONES_SHIFT - -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT -#else -#ifdef CONFIG_SPARSEMEM_VMEMMAP +#elif defined(CONFIG_SPARSEMEM_VMEMMAP) #error "Vmemmap: No space for nodes field in page flags" -#endif +#else #define NODES_WIDTH 0 #endif +/* + * Note that this #define MUST have a value so that it can be tested with + * the IS_ENABLED() macro. + */ +#if NODES_SHIFT != 0 && NODES_WIDTH == 0 +#define NODE_NOT_IN_PAGE_FLAGS 1 +#endif + +#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) +#define KASAN_TAG_WIDTH 8 +#else +#define KASAN_TAG_WIDTH 0 +#endif + #ifdef CONFIG_NUMA_BALANCING #define LAST__PID_SHIFT 8 #define LAST__PID_MASK ((1 << LAST__PID_SHIFT)-1) @@ -77,36 +89,20 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) -#define KASAN_TAG_WIDTH 8 -#else -#define KASAN_TAG_WIDTH 0 -#endif - -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \ +#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \ <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 #endif -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \ - > BITS_PER_LONG - NR_PAGEFLAGS -#error "Not enough bits in page flags" -#endif - -/* - * We are going to use the flags for the page to node mapping if its in - * there. This includes the case where there is no node, so it is implicit. - * Note that this #define MUST have a value so that it can be tested with - * the IS_ENABLED() macro. - */ -#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) -#define NODE_NOT_IN_PAGE_FLAGS 1 +#if LAST_CPUPID_SHIFT != 0 && LAST_CPUPID_WIDTH == 0 +#define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif -#if defined(CONFIG_NUMA_BALANCING) && LAST_CPUPID_WIDTH == 0 -#define LAST_CPUPID_NOT_IN_PAGE_FLAGS +#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \ + > BITS_PER_LONG - NR_PAGEFLAGS +#error "Not enough bits in page flags" #endif #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4686f9ab0636..e89df447fae3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -18,6 +18,11 @@ struct pagevec; +static inline bool mapping_empty(struct address_space *mapping) +{ + return xa_empty(&mapping->i_pages); +} + /* * Bits in mapping->flags. */ @@ -158,6 +163,16 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) void release_pages(struct page **pages, int nr); /* + * For file cache pages, return the address_space, otherwise return NULL + */ +static inline struct address_space *page_mapping_file(struct page *page) +{ + if (unlikely(PageSwapCache(page))) + return NULL; + return page_mapping(page); +} + +/* * speculatively take a reference to a page. * If the page is free (_refcount == 0), then _refcount is untouched, and 0 * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned. @@ -982,9 +997,9 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(struct readahead_control *rac) { - return (loff_t)rac->_nr_pages * PAGE_SIZE; + return rac->_nr_pages * PAGE_SIZE; } /** @@ -1009,7 +1024,7 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline loff_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index b1cb6b753abb..ac7b38ad5903 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -7,7 +7,7 @@ struct mm_walk; /** - * mm_walk_ops - callbacks for walk_page_range + * struct mm_walk_ops - callbacks for walk_page_range * @pgd_entry: if set, called for each non-empty PGD (top-level) entry * @p4d_entry: if set, called for each non-empty P4D entry * @pud_entry: if set, called for each non-empty PUD entry @@ -71,7 +71,7 @@ enum page_walk_action { }; /** - * mm_walk - walk_page_range data + * struct mm_walk - walk_page_range data * @ops: operation to call during the walk * @mm: mm_struct representing the target process of page table walk * @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL) diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 65d3d83015c3..fbdadd4d8377 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -85,6 +85,7 @@ extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */ extern const struct pci_ecam_ops xgene_v1_pcie_ecam_ops; /* APM X-Gene PCIe v1 */ extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */ extern const struct pci_ecam_ops al_pcie_ops; /* Amazon Annapurna Labs PCIe */ +extern const struct pci_ecam_ops tegra194_pcie_ops; /* Tegra194 PCIe */ #endif #if IS_ENABLED(CONFIG_PCI_HOST_COMMON) diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fa104ee13d9..c20211e59a57 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -458,7 +458,6 @@ struct pci_dev { u32 saved_config_space[16]; /* Config space saved at suspend time */ struct hlist_head saved_cap_space; - struct bin_attribute *rom_attr; /* Attribute descriptor for sysfs ROM entry */ int rom_attr_enabled; /* Display of ROM attribute enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */ @@ -540,7 +539,6 @@ struct pci_host_bridge { int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); void *release_data; - struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* For entire hierarchy */ unsigned int no_ext_tags:1; /* No Extended Tags */ unsigned int native_aer:1; /* OS may use PCIe AER */ @@ -551,6 +549,7 @@ struct pci_host_bridge { unsigned int native_dpc:1; /* OS may use PCIe DPC */ unsigned int preserve_config:1; /* Preserve FW resource setup */ unsigned int size_windows:1; /* Enable root bus sizing */ + unsigned int msi_domain:1; /* Bridge wants MSI domain */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, @@ -621,7 +620,6 @@ struct pci_bus { struct resource busn_res; /* Bus numbers routed to this bus */ struct pci_ops *ops; /* Configuration access functions */ - struct msi_controller *msi; /* MSI controller */ void *sysdata; /* Hook for sys-specific extension */ struct proc_dir_entry *procdir; /* Directory entry in /proc/bus/pci */ @@ -1085,6 +1083,7 @@ u8 pci_find_next_ht_capability(struct pci_dev *dev, u8 pos, int ht_cap); u16 pci_find_ext_capability(struct pci_dev *dev, int cap); u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); +u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap); u64 pci_get_dsn(struct pci_dev *dev); @@ -1209,6 +1208,7 @@ int __must_check pci_set_mwi(struct pci_dev *dev); int __must_check pcim_set_mwi(struct pci_dev *dev); int pci_try_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); +void pci_disable_parity(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); bool pci_check_and_mask_intx(struct pci_dev *dev); bool pci_check_and_unmask_intx(struct pci_dev *dev); @@ -1310,7 +1310,6 @@ void pci_unlock_rescan_remove(void); /* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); -int pci_set_vpd_size(struct pci_dev *dev, size_t len); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); @@ -2319,14 +2318,13 @@ static inline u8 pci_vpd_info_field_size(const u8 *info_field) /** * pci_vpd_find_tag - Locates the Resource Data Type tag provided * @buf: Pointer to buffered vpd data - * @off: The offset into the buffer at which to begin the search * @len: The length of the vpd buffer * @rdt: The Resource Data Type to search for * * Returns the index where the Resource Data Type was found or * -ENOENT otherwise. */ -int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt); +int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt); /** * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a763928a0e41..f5a6a2f069ed 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -954,8 +954,6 @@ extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); -extern int perf_num_counters(void); -extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 5e772392a379..46b13780c2c8 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -426,7 +426,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres /* * On some architectures hardware does not set page access bit when accessing - * memory page, it is responsibilty of software setting this bit. It brings + * memory page, it is responsibility of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms @@ -519,7 +519,7 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we - * can't race with CPU which sets these bits and non-atomic aproach is fine. + * can't race with CPU which sets these bits and non-atomic approach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) @@ -852,7 +852,7 @@ static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the - * pte; the appropriate pte lock must be held over the transation. + * pte; the appropriate pte lock must be held over the transaction. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely @@ -1111,6 +1111,7 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif +#ifdef CONFIG_MMU #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { @@ -1134,6 +1135,17 @@ static inline unsigned long my_zero_pfn(unsigned long addr) return zero_pfn; } #endif +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + return 0; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_MMU */ #ifdef CONFIG_MMU @@ -1269,13 +1281,13 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) * * The complete check uses is_pmd_migration_entry() in linux/swapops.h * But using that requires moving current function and pmd_trans_unstable() - * to linux/swapops.h to resovle dependency, which is too much code move. + * to linux/swapops.h to resolve dependency, which is too much code move. * * !pmd_present() is equivalent to is_pmd_migration_entry() currently, * because !pmd_present() pages can only be under migration not swapped * out. * - * pmd_none() is preseved for future condition checks on pmd migration + * pmd_none() is preserved for future condition checks on pmd migration * entries and not confusing with this function name, although it is * redundant with !pmd_present(). */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 60d2b26026a2..852743f07e3e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -496,6 +496,11 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. + * Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * Bits [23:16] are currently reserved for future use. + * Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 6aeb711f7cd1..e18ab3d5908f 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -76,10 +76,11 @@ struct pinctrl_map; * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, * schmitt-trigger mode is disabled. - * @PIN_CONFIG_LOW_POWER_MODE: this will configure the pin for low power + * @PIN_CONFIG_MODE_LOW_POWER: this will configure the pin for low power * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. + * @PIN_CONFIG_MODE_PWM: this will configure the pin for PWM * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode * without driving a value there. For most platforms this reduces to * enable the output buffers and then let the pin controller current @@ -90,6 +91,7 @@ struct pinctrl_map; * value on the line. Use argument 1 to indicate high level, argument 0 to * indicate low level. (Please see Documentation/driver-api/pinctl.rst, * section "GPIO mode pitfalls" for a discussion around this parameter.) + * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. @@ -101,7 +103,6 @@ struct pinctrl_map; * or latch delay (on outputs) this parameter (in a custom format) * specifies the clock skew or latch delay. It typically controls how * many double inverters are put in front of the line. - * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. @@ -124,14 +125,15 @@ enum pin_config_param { PIN_CONFIG_INPUT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_SCHMITT_ENABLE, - PIN_CONFIG_LOW_POWER_MODE, + PIN_CONFIG_MODE_LOW_POWER, + PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, + PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, PIN_CONFIG_SLEEP_HARDWARE_STATE, PIN_CONFIG_SLEW_RATE, PIN_CONFIG_SKEW_DELAY, - PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_END = 0x7F, PIN_CONFIG_MAX = 0xFF, }; diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 6035d9a98fb8..45f53afc46e2 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5679,6 +5679,7 @@ enum tcpc_cc_polarity { #define PD_STATUS_EVENT_SOP_DISC_DONE BIT(0) #define PD_STATUS_EVENT_SOP_PRIME_DISC_DONE BIT(1) +#define PD_STATUS_EVENT_HARD_RESET BIT(2) struct ec_params_typec_status { uint8_t port; diff --git a/include/linux/pm.h b/include/linux/pm.h index c9657408fee1..1d8209c09686 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -601,6 +601,7 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; + unsigned int needs_force_resume:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 000cc0533c33..069c7fd95396 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -32,6 +32,7 @@ struct proc_ops { ssize_t (*proc_read)(struct file *, char __user *, size_t, loff_t *); ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *); ssize_t (*proc_write)(struct file *, const char __user *, size_t, loff_t *); + /* mandatory unless nonseekable_open() or equivalent is used */ loff_t (*proc_lseek)(struct file *, loff_t, int); int (*proc_release)(struct inode *, struct file *); __poll_t (*proc_poll)(struct file *, struct poll_table_struct *); diff --git a/include/linux/profile.h b/include/linux/profile.h index bad18ca43150..fd18ca96f557 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -15,7 +15,6 @@ #define KVM_PROFILING 4 struct proc_dir_entry; -struct pt_regs; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) @@ -84,8 +83,6 @@ int task_handoff_unregister(struct notifier_block * n); int profile_event_register(enum profile_type, struct notifier_block * n); int profile_event_unregister(enum profile_type, struct notifier_block * n); -struct pt_regs; - #else #define prof_on 0 diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index b801ead1e2bb..d48a7192e881 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -73,6 +73,7 @@ enum sev_cmd { SEV_CMD_SEND_UPDATE_DATA = 0x041, SEV_CMD_SEND_UPDATE_VMSA = 0x042, SEV_CMD_SEND_FINISH = 0x043, + SEV_CMD_SEND_CANCEL = 0x044, /* Guest migration commands (incoming) */ SEV_CMD_RECEIVE_START = 0x050, @@ -326,11 +327,11 @@ struct sev_data_send_start { u64 pdh_cert_address; /* In */ u32 pdh_cert_len; /* In */ u32 reserved1; - u64 plat_cert_address; /* In */ - u32 plat_cert_len; /* In */ + u64 plat_certs_address; /* In */ + u32 plat_certs_len; /* In */ u32 reserved2; - u64 amd_cert_address; /* In */ - u32 amd_cert_len; /* In */ + u64 amd_certs_address; /* In */ + u32 amd_certs_len; /* In */ u32 reserved3; u64 session_address; /* In */ u32 session_len; /* In/Out */ @@ -393,6 +394,15 @@ struct sev_data_send_finish { } __packed; /** + * struct sev_data_send_cancel - SEND_CANCEL command parameters + * + * @handle: handle of the VM to process + */ +struct sev_data_send_cancel { + u32 handle; /* In */ +} __packed; + +/** * struct sev_data_receive_start - RECEIVE_START command parameters * * @handle: handle of the VM to perform receive operation diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h new file mode 100644 index 000000000000..f960a719f0d5 --- /dev/null +++ b/include/linux/ptp_kvm.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Virtual PTP 1588 clock for use with KVM guests + * + * Copyright (C) 2017 Red Hat Inc. + */ + +#ifndef _PTP_KVM_H_ +#define _PTP_KVM_H_ + +struct timespec64; +struct clocksource; + +int kvm_arch_ptp_init(void); +int kvm_arch_ptp_get_clock(struct timespec64 *ts); +int kvm_arch_ptp_get_crosststamp(u64 *cycle, + struct timespec64 *tspec, struct clocksource **cs); + +#endif /* _PTP_KVM_H_ */ diff --git a/include/linux/pwm.h b/include/linux/pwm.h index e4d84d4db293..5bb90af4997e 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -91,6 +91,11 @@ struct pwm_device { * pwm_get_state() - retrieve the current PWM state * @pwm: PWM device * @state: state to fill with the current PWM state + * + * The returned PWM state represents the state that was applied by a previous call to + * pwm_apply_state(). Drivers may have to slightly tweak that state before programming it to + * hardware. If pwm_apply_state() was never called, this returns either the current hardware + * state (if supported) or the default settings. */ static inline void pwm_get_state(const struct pwm_device *pwm, struct pwm_state *state) @@ -392,8 +397,6 @@ int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); -int pwmchip_add_with_polarity(struct pwm_chip *chip, - enum pwm_polarity polarity); int pwmchip_add(struct pwm_chip *chip); int pwmchip_remove(struct pwm_chip *chip); struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index fd80fab663a9..bebc911161b6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -38,7 +38,7 @@ void *__builtin_alloca(size_t size); u32 offset = raw_cpu_read(kstack_offset); \ u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ - asm volatile("" : "=o"(*ptr) :: "memory"); \ + asm volatile("" :: "r"(ptr) : "memory"); \ } \ } while (0) diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index f28ee75d1005..8b795b544f75 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -315,6 +315,7 @@ struct rproc; /** * struct rproc_mem_entry - memory entry descriptor * @va: virtual address + * @is_iomem: io memory * @dma: dma address * @len: length, in bytes * @da: device address @@ -329,6 +330,7 @@ struct rproc; */ struct rproc_mem_entry { void *va; + bool is_iomem; dma_addr_t dma; size_t len; u32 da; @@ -361,6 +363,7 @@ enum rsc_handling_status { * @start: power on the device and boot it * @stop: power off the device * @attach: attach to a device that his already powered up + * @detach: detach from a device, leaving it powered up * @kick: kick a virtqueue (virtqueue id given as a parameter) * @da_to_va: optional platform hook to perform address translations * @parse_fw: parse firmware to extract information (e.g. resource table) @@ -368,7 +371,9 @@ enum rsc_handling_status { * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled and a * negative value on error * @load_rsc_table: load resource table from firmware image - * @find_loaded_rsc_table: find the loaded resouce table + * @find_loaded_rsc_table: find the loaded resource table from firmware image + * @get_loaded_rsc_table: get resource table installed in memory + * by external entity * @load: load firmware to memory, where the remote processor * expects to find it * @sanity_check: sanity check the fw image @@ -383,13 +388,16 @@ struct rproc_ops { int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); int (*attach)(struct rproc *rproc); + int (*detach)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); - void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len); + void * (*da_to_va)(struct rproc *rproc, u64 da, size_t len, bool *is_iomem); int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); int (*handle_rsc)(struct rproc *rproc, u32 rsc_type, void *rsc, int offset, int avail); struct resource_table *(*find_loaded_rsc_table)( struct rproc *rproc, const struct firmware *fw); + struct resource_table *(*get_loaded_rsc_table)( + struct rproc *rproc, size_t *size); int (*load)(struct rproc *rproc, const struct firmware *fw); int (*sanity_check)(struct rproc *rproc, const struct firmware *fw); u64 (*get_boot_addr)(struct rproc *rproc, const struct firmware *fw); @@ -405,6 +413,8 @@ struct rproc_ops { * @RPROC_RUNNING: device is up and running * @RPROC_CRASHED: device has crashed; need to start recovery * @RPROC_DELETED: device is deleted + * @RPROC_ATTACHED: device has been booted by another entity and the core + * has attached to it * @RPROC_DETACHED: device has been booted by another entity and waiting * for the core to attach to it * @RPROC_LAST: just keep this one at the end @@ -421,8 +431,9 @@ enum rproc_state { RPROC_RUNNING = 2, RPROC_CRASHED = 3, RPROC_DELETED = 4, - RPROC_DETACHED = 5, - RPROC_LAST = 6, + RPROC_ATTACHED = 5, + RPROC_DETACHED = 6, + RPROC_LAST = 7, }; /** @@ -505,11 +516,12 @@ struct rproc_dump_segment { * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. * @table_ptr: pointer to the resource table in effect + * @clean_table: copy of the resource table without modifications. Used + * when a remote processor is attached or detached from the core * @cached_table: copy of the resource table * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started - * @autonomous: true if an external entity has booted the remote processor * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc * @char_dev: character device of the rproc @@ -542,11 +554,11 @@ struct rproc { bool recovery_disabled; int max_notifyid; struct resource_table *table_ptr; + struct resource_table *clean_table; struct resource_table *cached_table; size_t table_sz; bool has_iommu; bool auto_boot; - bool autonomous; struct list_head dump_segments; int nb_vdev; u8 elf_class; @@ -655,6 +667,7 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); +int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); void rproc_coredump_using_sections(struct rproc *rproc); diff --git a/include/linux/reset.h b/include/linux/reset.h index 46e6372cb431..db0e6115a2f6 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -76,6 +76,11 @@ static inline int reset_control_reset(struct reset_control *rstc) return 0; } +static inline int reset_control_rearm(struct reset_control *rstc) +{ + return 0; +} + static inline int reset_control_assert(struct reset_control *rstc) { return 0; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 136ea0997e6d..dac53fd3afea 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -61,7 +61,8 @@ enum ring_buffer_type { unsigned ring_buffer_event_length(struct ring_buffer_event *event); void *ring_buffer_event_data(struct ring_buffer_event *event); -u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event); +u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, + struct ring_buffer_event *event); /* * ring_buffer_discard_commit will remove an event that has not @@ -180,7 +181,7 @@ unsigned long ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cp unsigned long ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu); unsigned long ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu); -u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu); +u64 ring_buffer_time_stamp(struct trace_buffer *buffer); void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer, int cpu, u64 *ts); void ring_buffer_set_clock(struct trace_buffer *buffer, diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index a5db828b2420..d97dcd049f18 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -18,8 +18,7 @@ #include <linux/mutex.h> #include <linux/poll.h> #include <linux/rpmsg/byteorder.h> - -#define RPMSG_ADDR_ANY 0xFFFFFFFF +#include <uapi/linux/rpmsg.h> struct rpmsg_device; struct rpmsg_endpoint; diff --git a/include/linux/sched.h b/include/linux/sched.h index d7d07aa0facf..d2c881384517 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -841,6 +841,10 @@ struct task_struct { /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif +#ifdef CONFIG_PAGE_OWNER + /* Used by page_owner=on to detect recursion in page tracking. */ + unsigned in_page_owner:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -1579,7 +1583,7 @@ extern struct pid *cad_pid; #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ -#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 90b2a0bce11c..e24b1fe348e3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -151,12 +151,13 @@ static inline bool in_vfork(struct task_struct *tsk) * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS + * PF_MEMALLOC_PIN implies !GFP_MOVABLE */ static inline gfp_t current_gfp_context(gfp_t flags) { unsigned int pflags = READ_ONCE(current->flags); - if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) { + if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence @@ -165,6 +166,9 @@ static inline gfp_t current_gfp_context(gfp_t flags) flags &= ~(__GFP_IO | __GFP_FS); else if (pflags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; + + if (pflags & PF_MEMALLOC_PIN) + flags &= ~__GFP_MOVABLE; } return flags; } @@ -271,29 +275,18 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } -#ifdef CONFIG_CMA -static inline unsigned int memalloc_nocma_save(void) +static inline unsigned int memalloc_pin_save(void) { - unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; + unsigned int flags = current->flags & PF_MEMALLOC_PIN; - current->flags |= PF_MEMALLOC_NOCMA; + current->flags |= PF_MEMALLOC_PIN; return flags; } -static inline void memalloc_nocma_restore(unsigned int flags) -{ - current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; -} -#else -static inline unsigned int memalloc_nocma_save(void) -{ - return 0; -} - -static inline void memalloc_nocma_restore(unsigned int flags) +static inline void memalloc_pin_restore(unsigned int flags) { + current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags; } -#endif #ifdef CONFIG_MEMCG DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3f6a0fcaa10c..7f4278fa21fe 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -326,6 +326,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); +int force_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); diff --git a/include/linux/security.h b/include/linux/security.h index 9aeda3f9e838..06f7c50ce77f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -291,6 +291,7 @@ void security_bprm_committed_creds(struct linux_binprm *bprm); int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc); int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param); int security_sb_alloc(struct super_block *sb); +void security_sb_delete(struct super_block *sb); void security_sb_free(struct super_block *sb); void security_free_mnt_opts(void **mnt_opts); int security_sb_eat_lsm_opts(char *options, void **mnt_opts); @@ -633,6 +634,9 @@ static inline int security_sb_alloc(struct super_block *sb) return 0; } +static inline void security_sb_delete(struct super_block *sb) +{ } + static inline void security_sb_free(struct super_block *sb) { } diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 9d6c28cc4d8f..5b31c5147969 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -72,6 +72,31 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) } /** + * seq_buf_terminate - Make sure buffer is nul terminated + * @s: the seq_buf descriptor to terminate. + * + * This makes sure that the buffer in @s is nul terminated and + * safe to read as a string. + * + * Note, if this is called when the buffer has overflowed, then + * the last byte of the buffer is zeroed, and the len will still + * point passed it. + * + * After this function is called, s->buffer is safe to use + * in string operations. + */ +static inline void seq_buf_terminate(struct seq_buf *s) +{ + if (WARN_ON(s->size == 0)) + return; + + if (seq_buf_buffer_left(s)) + s->buffer[s->len] = 0; + else + s->buffer[s->size - 1] = 0; +} + +/** * seq_buf_get_buf - get buffer to write arbitrary data to * @s: the seq_buf handle * @bufp: the beginning of the buffer is stored here diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 0f80123650e2..1eac79ce57d4 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -79,13 +79,14 @@ struct shrinker { #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Flags */ -#define SHRINKER_NUMA_AWARE (1 << 0) -#define SHRINKER_MEMCG_AWARE (1 << 1) +#define SHRINKER_REGISTERED (1 << 0) +#define SHRINKER_NUMA_AWARE (1 << 1) +#define SHRINKER_MEMCG_AWARE (1 << 2) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ -#define SHRINKER_NONSLAB (1 << 2) +#define SHRINKER_NONSLAB (1 << 3) extern int prealloc_shrinker(struct shrinker *shrinker); extern void register_shrinker_prepared(struct shrinker *shrinker); diff --git a/include/linux/signal.h b/include/linux/signal.h index 0dbfda8d99d0..201f88e3738b 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -40,6 +40,7 @@ enum siginfo_layout { SIL_TIMER, SIL_POLL, SIL_FAULT, + SIL_FAULT_TRAPNO, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, diff --git a/include/linux/smp.h b/include/linux/smp.h index 84a0b4828f66..510519e8a1eb 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -53,7 +53,15 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); -int smp_call_function_single_async(int cpu, call_single_data_t *csd); +int smp_call_function_single_async(int cpu, struct __call_single_data *csd); + +/* + * Cpus stopping functions in panic. All have default weak definitions. + * Architecture-dependent code may override them. + */ +void panic_smp_self_stop(void); +void nmi_panic_self_stop(struct pt_regs *regs); +void crash_smp_send_stop(void); /* * Call a function on all processors diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 360a3bc767ca..74239d65c7fd 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -644,8 +644,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; - u8 unused_native_cs; - u8 max_native_cs; + s8 unused_native_cs; + s8 max_native_cs; /* statistics */ struct spi_statistics statistics; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d2e97ee802af..61b622e334ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -247,6 +247,7 @@ struct rpc_xprt { struct rpc_task * snd_task; /* Task blocked in send */ struct list_head xmit_queue; /* Send queue */ + atomic_long_t xmit_queuelen; struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) @@ -367,6 +368,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); static inline int xprt_enable_swap(struct rpc_xprt *xprt) diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 4441ad667c3f..6ff9c58b3e17 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -98,9 +98,9 @@ struct ssam_device_uid { | (((fun) != SSAM_ANY_FUN) ? SSAM_MATCH_FUNCTION : 0), \ .domain = d, \ .category = cat, \ - .target = ((tid) != SSAM_ANY_TID) ? (tid) : 0, \ - .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0, \ - .function = ((fun) != SSAM_ANY_FUN) ? (fun) : 0 \ + .target = __builtin_choose_expr((tid) != SSAM_ANY_TID, (tid), 0), \ + .instance = __builtin_choose_expr((iid) != SSAM_ANY_IID, (iid), 0), \ + .function = __builtin_choose_expr((fun) != SSAM_ANY_FUN, (fun), 0) /** * SSAM_VDEV() - Initialize a &struct ssam_device_id as virtual device with diff --git a/include/linux/swap.h b/include/linux/swap.h index 4cc6ec3bf0ab..144727041e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -10,8 +10,10 @@ #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> +#include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; @@ -339,6 +341,20 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file, extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void mark_page_accessed(struct page *); + +extern atomic_t lru_disable_count; + +static inline bool lru_cache_disabled(void) +{ + return atomic_read(&lru_disable_count); +} + +static inline void lru_cache_enable(void) +{ + atomic_dec(&lru_disable_count); +} + +extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); @@ -378,6 +394,12 @@ extern int sysctl_min_slab_ratio; #define node_reclaim_mode 0 #endif +static inline bool node_reclaim_enabled(void) +{ + /* Is any node_reclaim_mode bit set? */ + return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); +} + extern void check_move_unevictable_pages(struct pagevec *pvec); extern int kswapd_run(int nid); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5857a937c637..216854a5e513 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -6,6 +6,7 @@ #include <linux/init.h> #include <linux/types.h> #include <linux/limits.h> +#include <linux/spinlock.h> struct device; struct page; @@ -36,20 +37,11 @@ enum swiotlb_force { extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); -extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern int swiotlb_late_init_with_default_size(size_t default_size); extern void __init swiotlb_update_mem_attributes(void); -/* - * Enumeration for sync targets - */ -enum dma_sync_target { - SYNC_FOR_CPU = 0, - SYNC_FOR_DEVICE = 1, -}; - phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); @@ -57,32 +49,70 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, - size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); -extern void swiotlb_tbl_sync_single(struct device *hwdev, - phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target); - +void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); +void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; -extern phys_addr_t io_tlb_start, io_tlb_end; + +/** + * struct io_tlb_mem - IO TLB Memory Pool Descriptor + * + * @start: The start address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @end: The end address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and + * @end. This is command line adjustable via setup_io_tlb_npages. + * @used: The number of used IO TLB block. + * @list: The free list describing the number of free entries available + * from each index. + * @index: The index to start searching in the next round. + * @orig_addr: The original address corresponding to a mapped entry. + * @alloc_size: Size of the allocated buffer. + * @lock: The lock to protect the above data structures in the map and + * unmap calls. + * @debugfs: The dentry to debugfs. + * @late_alloc: %true if allocated using the page allocator + */ +struct io_tlb_mem { + phys_addr_t start; + phys_addr_t end; + unsigned long nslabs; + unsigned long used; + unsigned int index; + spinlock_t lock; + struct dentry *debugfs; + bool late_alloc; + struct io_tlb_slot { + phys_addr_t orig_addr; + size_t alloc_size; + unsigned int list; + } slots[]; +}; +extern struct io_tlb_mem *io_tlb_default_mem; static inline bool is_swiotlb_buffer(phys_addr_t paddr) { - return paddr >= io_tlb_start && paddr < io_tlb_end; + struct io_tlb_mem *mem = io_tlb_default_mem; + + return mem && paddr >= mem->start && paddr < mem->end; } void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(void); -void __init swiotlb_adjust_size(unsigned long new_size); +void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE static inline bool is_swiotlb_buffer(phys_addr_t paddr) @@ -106,7 +136,7 @@ static inline bool is_swiotlb_active(void) return false; } -static inline void swiotlb_adjust_size(unsigned long new_size) +static inline void swiotlb_adjust_size(unsigned long size) { } #endif /* CONFIG_SWIOTLB */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a672bbe28577..050511e8f1f8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -69,6 +69,8 @@ struct io_uring_params; struct clone_args; struct open_how; struct mount_attr; +struct landlock_ruleset_attr; +enum landlock_rule_type; #include <linux/types.h> #include <linux/aio_abi.h> @@ -1043,6 +1045,11 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig, siginfo_t __user *info, unsigned int flags); asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags); +asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr __user *attr, + size_t size, __u32 flags); +asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type, + const void __user *rule_attr, __u32 flags); +asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); /* * Architecture-specific system calls diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 6ac7bb1d2b1f..d296f3b88fb9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -91,7 +91,7 @@ struct thermal_cooling_device_ops { struct thermal_cooling_device { int id; - char type[THERMAL_NAME_LENGTH]; + char *type; struct device device; struct device_node *np; void *devdata; @@ -390,7 +390,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -void thermal_notify_framework(struct thermal_zone_device *, int); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); void thermal_zone_device_critical(struct thermal_zone_device *tz); @@ -436,10 +435,6 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline void thermal_notify_framework(struct thermal_zone_device *tz, - int trip) -{ } - static inline int thermal_zone_device_enable(struct thermal_zone_device *tz) { return -ENODEV; } diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index c6792cf01bc7..78a98bdff76d 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -3,6 +3,7 @@ #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> +#include <linux/clocksource_ids.h> /* Included from linux/ktime.h */ @@ -243,11 +244,12 @@ struct ktime_timestamps { * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { - u64 cycles; - ktime_t real; - ktime_t raw; - unsigned int clock_was_set_seq; - u8 cs_was_changed_seq; + u64 cycles; + ktime_t real; + ktime_t raw; + enum clocksource_ids cs_id; + unsigned int clock_was_set_seq; + u8 cs_was_changed_seq; }; /** diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 28e7af1406f2..ad413b382a3c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -206,7 +206,7 @@ static inline unsigned int tracing_gen_ctx_dec(void) trace_ctx = tracing_gen_ctx(); /* - * Subtract one from the preeption counter if preemption is enabled, + * Subtract one from the preemption counter if preemption is enabled, * see trace_event_buffer_reserve()for details. */ if (IS_ENABLED(CONFIG_PREEMPTION)) @@ -404,7 +404,6 @@ trace_get_fields(struct trace_event_call *event_call) return event_call->class->get_fields(event_call); } -struct trace_array; struct trace_subsystem_dir; enum { @@ -640,7 +639,8 @@ enum event_trigger_type { extern int filter_match_preds(struct event_filter *filter, void *rec); extern enum event_trigger_type -event_triggers_call(struct trace_event_file *file, void *rec, +event_triggers_call(struct trace_event_file *file, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event); extern void event_triggers_post_call(struct trace_event_file *file, @@ -664,7 +664,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL, NULL); + event_triggers_call(file, NULL, NULL, NULL); if (eflags & EVENT_FILE_FL_SOFT_DISABLED) return true; if (eflags & EVENT_FILE_FL_PID_FILTER) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 9cfb099da58f..13f65420f188 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -465,7 +465,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * * * * The declared 'local variable' is called '__entry' * * - * * __field(pid_t, prev_prid) is equivalent to a standard declariton: + * * __field(pid_t, prev_prid) is equivalent to a standard declaration: * * * * pid_t prev_pid; * * diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index a8e5f3ea9bb2..794d1538b8ba 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -17,6 +17,9 @@ #include <linux/mm.h> #include <asm-generic/pgtable_uffd.h> +/* The set of all possible UFFD-related VM flags. */ +#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) + /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want @@ -34,6 +37,22 @@ extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); +/* + * The mode of operation for __mcopy_atomic and its helpers. + * + * This is almost an implementation detail (mcopy_atomic below doesn't take this + * as a parameter), but it's exposed here because memory-kind-specific + * implementations (e.g. hugetlbfs) need to know the mode of operation. + */ +enum mcopy_atomic_mode { + /* A normal copy_from_user into the destination range. */ + MCOPY_ATOMIC_NORMAL, + /* Don't copy; map the destination range to the zero page. */ + MCOPY_ATOMIC_ZEROPAGE, + /* Just install pte(s) with the existing page(s) in the page cache. */ + MCOPY_ATOMIC_CONTINUE, +}; + extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode); @@ -41,6 +60,8 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, bool *mmap_changing); +extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, bool *mmap_changing); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, bool *mmap_changing); @@ -52,6 +73,22 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } +/* + * Never enable huge pmd sharing on some uffd registered vmas: + * + * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. + * + * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for + * VMAs which share huge pmds. (If you have two mappings to the same + * underlying pages, and fault in the non-UFFD-registered one with a write, + * with huge pmd sharing this would *also* setup the second UFFD-registered + * mapping, and we'd not get minor faults.) + */ +static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -62,6 +99,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return vma->vm_flags & VM_UFFD_WP; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_UFFD_MINOR; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { @@ -76,7 +118,7 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, static inline bool userfaultfd_armed(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP); + return vma->vm_flags & __VM_UFFD_FLAGS; } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); @@ -123,6 +165,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return false; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 15fa085fab05..f311d227aa1b 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -8,7 +8,7 @@ #include <linux/vhost_iotlb.h> /** - * vDPA callback definition. + * struct vdpa_calllback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function */ @@ -18,7 +18,7 @@ struct vdpa_callback { }; /** - * vDPA notification area + * struct vdpa_notification_area - vDPA notification area * @addr: base address of the notification area * @size: size of the notification area */ @@ -28,7 +28,7 @@ struct vdpa_notification_area { }; /** - * vDPA vq_state definition + * struct vdpa_vq_state - vDPA vq_state definition * @avail_index: available index */ struct vdpa_vq_state { @@ -38,7 +38,7 @@ struct vdpa_vq_state { struct vdpa_mgmt_dev; /** - * vDPA device - representation of a vDPA device + * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. @@ -59,7 +59,7 @@ struct vdpa_device { }; /** - * vDPA IOVA range - the IOVA range support by the device + * struct vdpa_iova_range - the IOVA range support by the device * @first: start of the IOVA range * @last: end of the IOVA range */ @@ -69,7 +69,7 @@ struct vdpa_iova_range { }; /** - * vDPA_config_ops - operations for configuring a vDPA device. + * struct vdpa_config_ops - operations for configuring a vDPA device. * Note: vDPA device drivers are required to implement all of the * operations unless it is mentioned to be optional in the following * list. @@ -150,6 +150,9 @@ struct vdpa_iova_range { * @set_status: Set the device status * @vdev: vdpa device * @status: virtio device status + * @get_config_size: Get the size of the configuration space + * @vdev: vdpa device + * Returns size_t: configuration size * @get_config: Read from device specific configuration space * @vdev: vdpa device * @offset: offset from the beginning of @@ -231,6 +234,7 @@ struct vdpa_config_ops { u32 (*get_vendor_id)(struct vdpa_device *vdev); u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); + size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void (*set_config)(struct vdpa_device *vdev, unsigned int offset, @@ -267,7 +271,7 @@ int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** - * vdpa_driver - operations for a vDPA driver + * struct vdpa_driver - operations for a vDPA driver * @driver: underlying device driver * @probe: the function to call when a device is found. Returns 0 or -errno. * @remove: the function to call when a device is removed. @@ -344,18 +348,18 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, } /** - * vdpa_mgmtdev_ops - vdpa device ops - * @dev_add: Add a vdpa device using alloc and register - * @mdev: parent device to use for device addition - * @name: name of the new vdpa device - * Driver need to add a new device using _vdpa_register_device() - * after fully initializing the vdpa device. Driver must return 0 - * on success or appropriate error code. - * @dev_del: Remove a vdpa device using unregister - * @mdev: parent device to use for device removal - * @dev: vdpa device to remove - * Driver need to remove the specified device by calling - * _vdpa_unregister_device(). + * struct vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). */ struct vdpa_mgmtdev_ops { int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index f26acbeec965..6a95b58fd0f4 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -13,6 +13,8 @@ struct virtio_pci_modern_device { void __iomem *device; /* Base of vq notifications (non-legacy mode). */ void __iomem *notify_base; + /* Physical base of vq notifications */ + resource_size_t notify_pa; /* Where to read and clear interrupt */ u8 __iomem *isr; @@ -99,13 +101,8 @@ void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, u16 idx); u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); -u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, - u16 idx); -void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, - size_t minlen, - u32 align, - u32 start, u32 size, - size_t *len); +void __iomem * vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, + u16 index, resource_size_t *pa); int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); #endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 18e75974d4e3..ae0dd1948c2b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,6 +71,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif +#ifdef CONFIG_CMA + CMA_ALLOC_SUCCESS, + CMA_ALLOC_FAIL, +#endif UNEVICTABLE_PGCULLED, /* culled to noreclaim list */ UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */ UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */ @@ -121,6 +125,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, SWAP_RA, SWAP_RA_HIT, #endif +#ifdef CONFIG_X86 + DIRECT_MAP_LEVEL2_SPLIT, + DIRECT_MAP_LEVEL3_SPLIT, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3de7be6dd17c..4d668abb6391 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,13 +26,14 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ +#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ /* * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. * * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after * shadow memory has been mapped. It's used to handle allocation errors so that - * we don't try to poision shadow on free if it was never allocated. + * we don't try to poison shadow on free if it was never allocated. * * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to * determine which allocations need the module shadow freed. @@ -42,7 +43,7 @@ struct notifier_block; /* in notifier.h */ /* * Maximum alignment for ioremap() regions. - * Can be overriden by arch-specific value. + * Can be overridden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ @@ -54,6 +55,9 @@ struct vm_struct { unsigned long size; unsigned long flags; struct page **pages; +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC + unsigned int page_order; +#endif unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; @@ -78,6 +82,28 @@ struct vmap_area { }; }; +/* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ +#ifndef arch_vmap_p4d_supported +static inline bool arch_vmap_p4d_supported(pgprot_t prot) +{ + return false; +} +#endif + +#ifndef arch_vmap_pud_supported +static inline bool arch_vmap_pud_supported(pgprot_t prot) +{ + return false; +} +#endif + +#ifndef arch_vmap_pmd_supported +static inline bool arch_vmap_pmd_supported(pgprot_t prot) +{ + return false; +} +#endif + /* * Highlevel APIs for driver use */ @@ -166,13 +192,27 @@ void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); +static inline bool is_vm_area_hugepages(const void *addr) +{ + /* + * This may not 100% tell if the area is mapped with > PAGE_SIZE + * page table entries, if for some reason the architecture indicates + * larger sizes are available but decides not to use them, nothing + * prevents that. This only indicates the size of the physical page + * allocated in the vmalloc layer. + */ +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC + return find_vm_area(addr)->page_order > 0; +#else + return false; +#endif +} + #ifdef CONFIG_MMU -extern int map_kernel_range_noflush(unsigned long start, unsigned long size, - pgprot_t prot, struct page **pages); -int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, - struct page **pages); -extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); -extern void unmap_kernel_range(unsigned long addr, unsigned long size); +int vmap_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift); +void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); @@ -180,27 +220,15 @@ static inline void set_vm_flush_reset_perms(void *addr) if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } + #else -static inline int -map_kernel_range_noflush(unsigned long start, unsigned long size, - pgprot_t prot, struct page **pages) -{ - return size >> PAGE_SHIFT; -} -#define map_kernel_range map_kernel_range_noflush -static inline void -unmap_kernel_range_noflush(unsigned long addr, unsigned long size) -{ -} -#define unmap_kernel_range unmap_kernel_range_noflush static inline void set_vm_flush_reset_perms(void *addr) { } #endif -/* for /dev/kmem */ +/* for /proc/kcore */ extern long vread(char *buf, char *addr, unsigned long count); -extern long vwrite(char *buf, char *addr, unsigned long count); /* * Internals. Dont't use.. diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 506d625163a1..3299cd69e4ca 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -512,16 +512,10 @@ static inline void mod_lruvec_page_state(struct page *page, #endif /* CONFIG_MEMCG */ -static inline void __inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - __mod_lruvec_state(lruvec, idx, 1); -} - -static inline void __dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) +static inline void inc_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx) { - __mod_lruvec_state(lruvec, idx, -1); + mod_lruvec_state(lruvec, idx, 1); } static inline void __inc_lruvec_page_state(struct page *page, @@ -536,18 +530,6 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); -} - -static inline void dec_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, -1); -} - static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 59bd50f99291..84db7b8f912f 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -46,6 +46,9 @@ struct vringh { /* IOTLB for this vring */ struct vhost_iotlb *iotlb; + /* spinlock to synchronize IOTLB accesses */ + spinlock_t *iotlb_lock; + /* The function to call to notify the guest about added buffers */ void (*notify)(struct vringh *); }; @@ -196,6 +199,19 @@ static inline void vringh_kiov_cleanup(struct vringh_kiov *kiov) kiov->iov = NULL; } +static inline size_t vringh_kiov_length(struct vringh_kiov *kiov) +{ + size_t len = 0; + int i; + + for (i = kiov->i; i < kiov->used; i++) + len += kiov->iov[i].iov_len; + + return len; +} + +void vringh_kiov_advance(struct vringh_kiov *kiov, size_t len); + int vringh_getdesc_kern(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, @@ -258,7 +274,8 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) #if IS_REACHABLE(CONFIG_VHOST_IOTLB) -void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb); +void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb, + spinlock_t *iotlb_lock); int vringh_init_iotlb(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 041d6524d144..3684487d01e1 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -3,12 +3,46 @@ #define _LINUX_KERNEL_VTIME_H #include <linux/context_tracking_state.h> +#include <linux/sched.h> + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <asm/vtime.h> #endif +/* + * Common vtime APIs + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +extern void vtime_account_kernel(struct task_struct *tsk); +extern void vtime_account_idle(struct task_struct *tsk); +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ -struct task_struct; +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void arch_vtime_task_switch(struct task_struct *tsk); +extern void vtime_user_enter(struct task_struct *tsk); +extern void vtime_user_exit(struct task_struct *tsk); +extern void vtime_guest_enter(struct task_struct *tsk); +extern void vtime_guest_exit(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk, int cpu); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ +static inline void vtime_user_enter(struct task_struct *tsk) { } +static inline void vtime_user_exit(struct task_struct *tsk) { } +static inline void vtime_guest_enter(struct task_struct *tsk) { } +static inline void vtime_guest_exit(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } +#endif + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); +extern void vtime_account_softirq(struct task_struct *tsk); +extern void vtime_account_hardirq(struct task_struct *tsk); +extern void vtime_flush(struct task_struct *tsk); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } +static inline void vtime_account_softirq(struct task_struct *tsk) { } +static inline void vtime_account_hardirq(struct task_struct *tsk) { } +static inline void vtime_flush(struct task_struct *tsk) { } +#endif /* * vtime_accounting_enabled_this_cpu() definitions/declarations @@ -18,6 +52,18 @@ struct task_struct; static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); +static __always_inline void vtime_account_guest_enter(void) +{ + vtime_account_kernel(current); + current->flags |= PF_VCPU; +} + +static __always_inline void vtime_account_guest_exit(void) +{ + vtime_account_kernel(current); + current->flags &= ~PF_VCPU; +} + #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* @@ -49,49 +95,37 @@ static inline void vtime_task_switch(struct task_struct *prev) vtime_task_switch_generic(prev); } +static __always_inline void vtime_account_guest_enter(void) +{ + if (vtime_accounting_enabled_this_cpu()) + vtime_guest_enter(current); + else + current->flags |= PF_VCPU; +} + +static __always_inline void vtime_account_guest_exit(void) +{ + if (vtime_accounting_enabled_this_cpu()) + vtime_guest_exit(current); + else + current->flags &= ~PF_VCPU; +} + #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; } static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } -#endif - -/* - * Common vtime APIs - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void vtime_account_kernel(struct task_struct *tsk); -extern void vtime_account_idle(struct task_struct *tsk); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline void vtime_account_kernel(struct task_struct *tsk) { } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static __always_inline void vtime_account_guest_enter(void) +{ + current->flags |= PF_VCPU; +} -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_user_enter(struct task_struct *tsk); -extern void vtime_user_exit(struct task_struct *tsk); -extern void vtime_guest_enter(struct task_struct *tsk); -extern void vtime_guest_exit(struct task_struct *tsk); -extern void vtime_init_idle(struct task_struct *tsk, int cpu); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void vtime_user_enter(struct task_struct *tsk) { } -static inline void vtime_user_exit(struct task_struct *tsk) { } -static inline void vtime_guest_enter(struct task_struct *tsk) { } -static inline void vtime_guest_exit(struct task_struct *tsk) { } -static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } -#endif +static __always_inline void vtime_account_guest_exit(void) +{ + current->flags &= ~PF_VCPU; +} -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); -extern void vtime_account_softirq(struct task_struct *tsk); -extern void vtime_account_hardirq(struct task_struct *tsk); -extern void vtime_flush(struct task_struct *tsk); -#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ -static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } -static inline void vtime_account_softirq(struct task_struct *tsk) { } -static inline void vtime_account_hardirq(struct task_struct *tsk) { } -static inline void vtime_flush(struct task_struct *tsk) { } #endif |