diff options
Diffstat (limited to 'include/linux')
207 files changed, 5012 insertions, 2179 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4e495b29c640..a70e62d69dc7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -330,7 +330,6 @@ static inline bool acpi_sci_irq_valid(void) } extern int sbf_port; -extern unsigned long acpi_realmode_flags; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); diff --git a/include/linux/align.h b/include/linux/align.h index 2b4acec7b95a..55debf105a5d 100644 --- a/include/linux/align.h +++ b/include/linux/align.h @@ -2,14 +2,6 @@ #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) +#include <vdso/align.h> #endif /* _LINUX_ALIGN_H */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 67f6fdf2e7cd..a3863da1510e 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -179,6 +179,9 @@ #define ARM_SMCCC_KVM_FUNC_PKVM_RESV_62 62 #define ARM_SMCCC_KVM_FUNC_PKVM_RESV_63 63 /* End of pKVM hypercall range */ +#define ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_VER 64 +#define ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_CPUS 65 + #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -225,6 +228,18 @@ ARM_SMCCC_OWNER_VENDOR_HYP, \ ARM_SMCCC_KVM_FUNC_MMIO_GUARD) +#define ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_VER_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_VER) + +#define ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_CPUS_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_CPUS) + /* ptp_kvm counter type ID */ #define KVM_PTP_VIRT_COUNTER 0 #define KVM_PTP_PHYS_COUNTER 1 @@ -639,5 +654,45 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, method; \ }) +#ifdef CONFIG_ARM64 + +#define __fail_smccc_1_2(___res) \ + do { \ + if (___res) \ + ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ + } while (0) + +/* + * arm_smccc_1_2_invoke() - make an SMCCC v1.2 compliant call + * + * @args: SMC args are in the a0..a17 fields of the arm_smcc_1_2_regs structure + * @res: result values from registers 0 to 17 + * + * This macro will make either an HVC call or an SMC call depending on the + * current SMCCC conduit. If no valid conduit is available then -1 + * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied). + * + * The return value also provides the conduit that was used. + */ +#define arm_smccc_1_2_invoke(args, res) ({ \ + struct arm_smccc_1_2_regs *__args = args; \ + struct arm_smccc_1_2_regs *__res = res; \ + int method = arm_smccc_1_1_get_conduit(); \ + switch (method) { \ + case SMCCC_CONDUIT_HVC: \ + arm_smccc_1_2_hvc(__args, __res); \ + break; \ + case SMCCC_CONDUIT_SMC: \ + arm_smccc_1_2_smc(__args, __res); \ + break; \ + default: \ + __fail_smccc_1_2(__res); \ + method = SMCCC_CONDUIT_NONE; \ + break; \ + } \ + method; \ + }) +#endif /*CONFIG_ARM64*/ + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 74169dd0f659..5bded24dc24f 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -112,6 +112,7 @@ FIELD_PREP(FFA_MINOR_VERSION_MASK, (minor))) #define FFA_VERSION_1_0 FFA_PACK_VERSION_INFO(1, 0) #define FFA_VERSION_1_1 FFA_PACK_VERSION_INFO(1, 1) +#define FFA_VERSION_1_2 FFA_PACK_VERSION_INFO(1, 2) /** * FF-A specification mentions explicitly about '4K pages'. This should @@ -176,6 +177,7 @@ void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); void ffa_driver_unregister(struct ffa_driver *driver); +void ffa_devices_unregister(void); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else @@ -188,6 +190,8 @@ ffa_device_register(const struct ffa_partition_info *part_info, static inline void ffa_device_unregister(struct ffa_device *dev) {} +static inline void ffa_devices_unregister(void) {} + static inline int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name) @@ -237,8 +241,12 @@ struct ffa_partition_info { #define FFA_PARTITION_NOTIFICATION_RECV BIT(3) /* partition runs in the AArch64 execution state. */ #define FFA_PARTITION_AARCH64_EXEC BIT(8) +/* partition supports receipt of direct request2 */ +#define FFA_PARTITION_DIRECT_REQ2_RECV BIT(9) +/* partition can send direct request2. */ +#define FFA_PARTITION_DIRECT_REQ2_SEND BIT(10) u32 properties; - u32 uuid[4]; + uuid_t uuid; }; static inline @@ -256,6 +264,10 @@ bool ffa_partition_check_property(struct ffa_device *dev, u32 property) #define ffa_partition_supports_direct_recv(dev) \ ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV) +#define ffa_partition_supports_direct_req2_recv(dev) \ + (ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_REQ2_RECV) && \ + !dev->mode_32bit) + /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ struct ffa_send_direct_data { unsigned long data0; /* w3/x3 */ @@ -271,6 +283,7 @@ struct ffa_indirect_msg_hdr { u32 offset; u32 send_recv_id; u32 size; + uuid_t uuid; }; /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP}2 which pass data via registers */ @@ -439,7 +452,7 @@ struct ffa_msg_ops { int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); - int (*sync_send_receive2)(struct ffa_device *dev, const uuid_t *uuid, + int (*sync_send_receive2)(struct ffa_device *dev, struct ffa_send_direct_data2 *data); }; @@ -455,6 +468,7 @@ struct ffa_cpu_ops { typedef void (*ffa_sched_recv_cb)(u16 vcpu, bool is_per_vcpu, void *cb_data); typedef void (*ffa_notifier_cb)(int notify_id, void *cb_data); +typedef void (*ffa_fwk_notifier_cb)(int notify_id, void *cb_data, void *buf); struct ffa_notifier_ops { int (*sched_recv_cb_register)(struct ffa_device *dev, @@ -463,6 +477,10 @@ struct ffa_notifier_ops { int (*notify_request)(struct ffa_device *dev, bool per_vcpu, ffa_notifier_cb cb, void *cb_data, int notify_id); int (*notify_relinquish)(struct ffa_device *dev, int notify_id); + int (*fwk_notify_request)(struct ffa_device *dev, + ffa_fwk_notifier_cb cb, void *cb_data, + int notify_id); + int (*fwk_notify_relinquish)(struct ffa_device *dev, int notify_id); int (*notify_send)(struct ffa_device *dev, int notify_id, bool per_vcpu, u16 vcpu); }; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 13a11f3c09b8..cf0afa60e4a7 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -154,7 +154,10 @@ enum virtchnl_ops { VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, - /* opcode 57 - 65 are reserved */ + /* opcode 58 and 59 are reserved */ + VIRTCHNL_OP_1588_PTP_GET_CAPS = 60, + VIRTCHNL_OP_1588_PTP_GET_TIME = 61, + /* opcode 62 - 65 are reserved */ VIRTCHNL_OP_GET_QOS_CAPS = 66, /* opcode 68 through 111 are reserved */ VIRTCHNL_OP_CONFIG_QUEUE_BW = 112, @@ -270,6 +273,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) #define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) #define VIRTCHNL_VF_OFFLOAD_QOS BIT(29) +#define VIRTCHNL_VF_CAP_PTP BIT(31) #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -309,6 +313,60 @@ struct virtchnl_txq_info { VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); +/* RX descriptor IDs (range from 0 to 63) */ +enum virtchnl_rx_desc_ids { + VIRTCHNL_RXDID_0_16B_BASE = 0, + VIRTCHNL_RXDID_1_32B_BASE = 1, + VIRTCHNL_RXDID_2_FLEX_SQ_NIC = 2, + VIRTCHNL_RXDID_3_FLEX_SQ_SW = 3, + VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB = 4, + VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL = 5, + VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2 = 6, + VIRTCHNL_RXDID_7_HW_RSVD = 7, + /* 8 through 15 are reserved */ + VIRTCHNL_RXDID_16_COMMS_GENERIC = 16, + VIRTCHNL_RXDID_17_COMMS_AUX_VLAN = 17, + VIRTCHNL_RXDID_18_COMMS_AUX_IPV4 = 18, + VIRTCHNL_RXDID_19_COMMS_AUX_IPV6 = 19, + VIRTCHNL_RXDID_20_COMMS_AUX_FLOW = 20, + VIRTCHNL_RXDID_21_COMMS_AUX_TCP = 21, + /* 22 through 63 are reserved */ +}; + +#define VIRTCHNL_RXDID_BIT(x) BIT_ULL(VIRTCHNL_RXDID_##x) + +/* RX descriptor ID bitmasks */ +enum virtchnl_rx_desc_id_bitmasks { + VIRTCHNL_RXDID_0_16B_BASE_M = VIRTCHNL_RXDID_BIT(0_16B_BASE), + VIRTCHNL_RXDID_1_32B_BASE_M = VIRTCHNL_RXDID_BIT(1_32B_BASE), + VIRTCHNL_RXDID_2_FLEX_SQ_NIC_M = VIRTCHNL_RXDID_BIT(2_FLEX_SQ_NIC), + VIRTCHNL_RXDID_3_FLEX_SQ_SW_M = VIRTCHNL_RXDID_BIT(3_FLEX_SQ_SW), + VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB_M = VIRTCHNL_RXDID_BIT(4_FLEX_SQ_NIC_VEB), + VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL_M = VIRTCHNL_RXDID_BIT(5_FLEX_SQ_NIC_ACL), + VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2_M = VIRTCHNL_RXDID_BIT(6_FLEX_SQ_NIC_2), + VIRTCHNL_RXDID_7_HW_RSVD_M = VIRTCHNL_RXDID_BIT(7_HW_RSVD), + /* 8 through 15 are reserved */ + VIRTCHNL_RXDID_16_COMMS_GENERIC_M = VIRTCHNL_RXDID_BIT(16_COMMS_GENERIC), + VIRTCHNL_RXDID_17_COMMS_AUX_VLAN_M = VIRTCHNL_RXDID_BIT(17_COMMS_AUX_VLAN), + VIRTCHNL_RXDID_18_COMMS_AUX_IPV4_M = VIRTCHNL_RXDID_BIT(18_COMMS_AUX_IPV4), + VIRTCHNL_RXDID_19_COMMS_AUX_IPV6_M = VIRTCHNL_RXDID_BIT(19_COMMS_AUX_IPV6), + VIRTCHNL_RXDID_20_COMMS_AUX_FLOW_M = VIRTCHNL_RXDID_BIT(20_COMMS_AUX_FLOW), + VIRTCHNL_RXDID_21_COMMS_AUX_TCP_M = VIRTCHNL_RXDID_BIT(21_COMMS_AUX_TCP), + /* 22 through 63 are reserved */ +}; + +/* virtchnl_rxq_info_flags - definition of bits in the flags field of the + * virtchnl_rxq_info structure. + * + * @VIRTCHNL_PTP_RX_TSTAMP: request to enable Rx timestamping + * + * Other flag bits are currently reserved and they may be extended in the + * future. + */ +enum virtchnl_rxq_info_flags { + VIRTCHNL_PTP_RX_TSTAMP = BIT(0), +}; + /* VIRTCHNL_OP_CONFIG_RX_QUEUE * VF sends this message to set up parameters for one RX queue. * External data buffer contains one instance of virtchnl_rxq_info. @@ -331,8 +389,14 @@ struct virtchnl_rxq_info { u32 databuffer_size; u32 max_pkt_size; u8 crc_disable; - u8 rxdid; - u8 pad1[2]; + /* see enum virtchnl_rx_desc_ids; + * only used when VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is supported. Note + * that when the offload is not supported, the descriptor format aligns + * with VIRTCHNL_RXDID_1_32B_BASE. + */ + enum virtchnl_rx_desc_ids rxdid:8; + enum virtchnl_rxq_info_flags flags:8; /* see virtchnl_rxq_info_flags */ + u8 pad1; u64 dma_ring_addr; /* see enum virtchnl_rx_hsplit; deprecated with AVF 1.0 */ @@ -1032,10 +1096,6 @@ struct virtchnl_filter { VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); -struct virtchnl_supported_rxdids { - u64 supported_rxdids; -}; - /* VIRTCHNL_OP_EVENT * PF sends this message to inform the VF driver of events that may affect it. * No direct response is expected from the VF, though it may generate other @@ -1283,7 +1343,7 @@ struct virtchnl_proto_hdrs { * 2 - from the second inner layer * .... **/ - int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ + u32 count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ union { struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; @@ -1335,7 +1395,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_filter_action); struct virtchnl_filter_action_set { /* action number must be less then VIRTCHNL_MAX_NUM_ACTIONS */ - int count; + u32 count; struct virtchnl_filter_action actions[VIRTCHNL_MAX_NUM_ACTIONS]; }; @@ -1425,6 +1485,61 @@ struct virtchnl_fdir_del { VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); +#define VIRTCHNL_1588_PTP_CAP_RX_TSTAMP BIT(1) +#define VIRTCHNL_1588_PTP_CAP_READ_PHC BIT(2) + +/** + * struct virtchnl_ptp_caps - Defines the PTP caps available to the VF. + * @caps: On send, VF sets what capabilities it requests. On reply, PF + * indicates what has been enabled for this VF. The PF shall not set + * bits which were not requested by the VF. + * @rsvd: Reserved bits for future extension. + * + * Structure that defines the PTP capabilities available to the VF. The VF + * sends VIRTCHNL_OP_1588_PTP_GET_CAPS, and must fill in the ptp_caps field + * indicating what capabilities it is requesting. The PF will respond with the + * same message with the virtchnl_ptp_caps structure indicating what is + * enabled for the VF. + * + * VIRTCHNL_1588_PTP_CAP_RX_TSTAMP indicates that the VF receive queues have + * receive timestamps enabled in the flexible descriptors. Note that this + * requires a VF to also negotiate to enable advanced flexible descriptors in + * the receive path instead of the default legacy descriptor format. + * + * VIRTCHNL_1588_PTP_CAP_READ_PHC indicates that the VF may read the PHC time + * via the VIRTCHNL_OP_1588_PTP_GET_TIME command. + * + * Note that in the future, additional capability flags may be added which + * indicate additional extended support. All fields marked as reserved by this + * header will be set to zero. VF implementations should verify this to ensure + * that future extensions do not break compatibility. + */ +struct virtchnl_ptp_caps { + u32 caps; + u8 rsvd[44]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(48, virtchnl_ptp_caps); + +/** + * struct virtchnl_phc_time - Contains the 64bits of PHC clock time in ns. + * @time: PHC time in nanoseconds + * @rsvd: Reserved for future extension + * + * Structure received with VIRTCHNL_OP_1588_PTP_GET_TIME. Contains the 64bits + * of PHC clock time in nanoseconds. + * + * VIRTCHNL_OP_1588_PTP_GET_TIME may be sent to request the current time of + * the PHC. This op is available in case direct access via the PHC registers + * is not available. + */ +struct virtchnl_phc_time { + u64 time; + u8 rsvd[8]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_phc_time); + struct virtchnl_shaper_bw { /* Unit is Kbps */ u32 committed; @@ -1757,6 +1872,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, } } break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + valid_len = sizeof(struct virtchnl_ptp_caps); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + valid_len = sizeof(struct virtchnl_phc_time); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h index 670f2dae692f..996493917f36 100644 --- a/include/linux/badblocks.h +++ b/include/linux/badblocks.h @@ -48,11 +48,11 @@ struct badblocks_context { int ack; }; -int badblocks_check(struct badblocks *bb, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors); -int badblocks_set(struct badblocks *bb, sector_t s, int sectors, - int acknowledged); -int badblocks_clear(struct badblocks *bb, sector_t s, int sectors); +int badblocks_check(struct badblocks *bb, sector_t s, sector_t sectors, + sector_t *first_bad, sector_t *bad_sectors); +bool badblocks_set(struct badblocks *bb, sector_t s, sector_t sectors, + int acknowledged); +bool badblocks_clear(struct badblocks *bb, sector_t s, sector_t sectors); void ack_all_badblocks(struct badblocks *bb); ssize_t badblocks_show(struct badblocks *bb, char *page, int unack); ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 60d674af3080..1625c8529e70 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -64,7 +64,7 @@ struct linux_binprm { const char *fdpath; /* generated filename for execveat */ unsigned interp_flags; int execfd; /* File descriptor of the executable */ - unsigned long loader, exec; + unsigned long exec; struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */ diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h index 802f52e38efd..0a25716820fe 100644 --- a/include/linux/bio-integrity.h +++ b/include/linux/bio-integrity.h @@ -16,8 +16,6 @@ enum bip_flags { }; struct bio_integrity_payload { - struct bio *bip_bio; /* parent bio */ - struct bvec_iter bip_iter; unsigned short bip_vcnt; /* # of integrity bio_vecs */ @@ -25,12 +23,7 @@ struct bio_integrity_payload { unsigned short bip_flags; /* control flags */ u16 app_tag; /* application tag value */ - struct bvec_iter bio_iter; /* for rewinding parent bio */ - - struct work_struct bip_work; /* I/O completion */ - struct bio_vec *bip_vec; - struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \ @@ -74,6 +67,8 @@ static inline void bip_set_seed(struct bio_integrity_payload *bip, bip->bip_iter.bi_sector = seed; } +void bio_integrity_init(struct bio *bio, struct bio_integrity_payload *bip, + struct bio_vec *bvecs, unsigned int nr_vecs); struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr); int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, @@ -85,9 +80,6 @@ bool bio_integrity_prep(struct bio *bio); void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); void bio_integrity_trim(struct bio *bio); int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask); -int bioset_integrity_create(struct bio_set *bs, int pool_size); -void bioset_integrity_free(struct bio_set *bs); -void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ @@ -96,15 +88,6 @@ static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) return NULL; } -static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) -{ - return 0; -} - -static inline void bioset_integrity_free(struct bio_set *bs) -{ -} - static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) { return -EINVAL; @@ -139,10 +122,6 @@ static inline void bio_integrity_trim(struct bio *bio) { } -static inline void bio_integrity_init(void) -{ -} - static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; diff --git a/include/linux/bio.h b/include/linux/bio.h index 4b79bf50f4f0..cafc7c215de8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -625,10 +625,6 @@ struct bio_set { mempool_t bio_pool; mempool_t bvec_pool; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t bio_integrity_pool; - mempool_t bvec_integrity_pool; -#endif unsigned int back_pad; /* diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 2026953e2c4e..595217b7a6e7 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -560,9 +560,9 @@ void bitmap_replace(unsigned long *dst, * ...0..11...0..10 * dst: 0000001100000010 * - * A relationship exists between bitmap_scatter() and bitmap_gather(). + * A relationship exists between bitmap_scatter() and bitmap_gather(). See + * bitmap_gather() for the bitmap gather detailed operations. TL;DR: * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. - * See bitmap_scatter() for details related to this relationship. */ static __always_inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, @@ -608,7 +608,9 @@ void bitmap_scatter(unsigned long *dst, const unsigned long *src, * dst: 0000000000011010 * * A relationship exists between bitmap_gather() and bitmap_scatter(). See - * bitmap_scatter() for the bitmap scatter detailed operations. + * bitmap_scatter() for the bitmap scatter detailed operations. TL;DR: + * bitmap_scatter() can be seen as the 'reverse' bitmap_gather() operation. + * * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n). * The operation bitmap_gather(result, scattered, mask, n) leads to a result * equal or equivalent to src. diff --git a/include/linux/bits.h b/include/linux/bits.h index 61a75d3f294b..14fd0ca9a6cd 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -40,7 +40,7 @@ * Missing asm support * * __GENMASK_U128() depends on _BIT128() which would not work - * in the asm code, as it shifts an 'unsigned __init128' data + * in the asm code, as it shifts an 'unsigned __int128' data * type instead of direct representation of 128 bit constants * such as long and unsigned long. The fundamental problem is * that a 128 bit constant will get silently truncated by the diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h index 90ab33cb5d0e..4f39e9cd7576 100644 --- a/include/linux/blk-crypto-profile.h +++ b/include/linux/blk-crypto-profile.h @@ -57,6 +57,62 @@ struct blk_crypto_ll_ops { int (*keyslot_evict)(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot); + + /** + * @derive_sw_secret: Derive the software secret from a hardware-wrapped + * key in ephemerally-wrapped form. + * + * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED + * is supported. + * + * Must return 0 on success, -EBADMSG if the key is invalid, or another + * -errno code on other errors. + */ + int (*derive_sw_secret)(struct blk_crypto_profile *profile, + const u8 *eph_key, size_t eph_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]); + + /** + * @import_key: Create a hardware-wrapped key by importing a raw key. + * + * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED + * is supported. + * + * On success, must write the new key in long-term wrapped form to + * @lt_key and return its size in bytes. On failure, must return a + * -errno value. + */ + int (*import_key)(struct blk_crypto_profile *profile, + const u8 *raw_key, size_t raw_key_size, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); + + /** + * @generate_key: Generate a hardware-wrapped key. + * + * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED + * is supported. + * + * On success, must write the new key in long-term wrapped form to + * @lt_key and return its size in bytes. On failure, must return a + * -errno value. + */ + int (*generate_key)(struct blk_crypto_profile *profile, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); + + /** + * @prepare_key: Prepare a hardware-wrapped key to be used. + * + * Prepare a hardware-wrapped key to be used by converting it from + * long-term wrapped form to ephemerally-wrapped form. This only needs + * to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED is supported. + * + * On success, must write the key in ephemerally-wrapped form to + * @eph_key and return its size in bytes. On failure, must return + * -EBADMSG if the key is invalid, or another -errno on other error. + */ + int (*prepare_key)(struct blk_crypto_profile *profile, + const u8 *lt_key, size_t lt_key_size, + u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); }; /** @@ -85,6 +141,12 @@ struct blk_crypto_profile { unsigned int max_dun_bytes_supported; /** + * @key_types_supported: A bitmask of the supported key types: + * BLK_CRYPTO_KEY_TYPE_RAW and/or BLK_CRYPTO_KEY_TYPE_HW_WRAPPED. + */ + unsigned int key_types_supported; + + /** * @modes_supported: Array of bitmasks that specifies whether each * combination of crypto mode and data unit size is supported. * Specifically, the i'th bit of modes_supported[crypto_mode] is set if @@ -143,6 +205,17 @@ void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile); void blk_crypto_profile_destroy(struct blk_crypto_profile *profile); +int blk_crypto_import_key(struct blk_crypto_profile *profile, + const u8 *raw_key, size_t raw_key_size, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); + +int blk_crypto_generate_key(struct blk_crypto_profile *profile, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); + +int blk_crypto_prepare_key(struct blk_crypto_profile *profile, + const u8 *lt_key, size_t lt_key_size, + u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]); + void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent, const struct blk_crypto_profile *child); diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index 5e5822c18ee4..58b0c5254a67 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -6,7 +6,9 @@ #ifndef __LINUX_BLK_CRYPTO_H #define __LINUX_BLK_CRYPTO_H +#include <linux/minmax.h> #include <linux/types.h> +#include <uapi/linux/blk-crypto.h> enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_INVALID, @@ -17,7 +19,55 @@ enum blk_crypto_mode_num { BLK_ENCRYPTION_MODE_MAX, }; -#define BLK_CRYPTO_MAX_KEY_SIZE 64 +/* + * Supported types of keys. Must be bitflags due to their use in + * blk_crypto_profile::key_types_supported. + */ +enum blk_crypto_key_type { + /* + * Raw keys (i.e. "software keys"). These keys are simply kept in raw, + * plaintext form in kernel memory. + */ + BLK_CRYPTO_KEY_TYPE_RAW = 0x1, + + /* + * Hardware-wrapped keys. These keys are only present in kernel memory + * in ephemerally-wrapped form, and they can only be unwrapped by + * dedicated hardware. For details, see the "Hardware-wrapped keys" + * section of Documentation/block/inline-encryption.rst. + */ + BLK_CRYPTO_KEY_TYPE_HW_WRAPPED = 0x2, +}; + +/* + * Currently the maximum raw key size is 64 bytes, as that is the key size of + * BLK_ENCRYPTION_MODE_AES_256_XTS which takes the longest key. + * + * The maximum hardware-wrapped key size depends on the hardware's key wrapping + * algorithm, which is a hardware implementation detail, so it isn't precisely + * specified. But currently 128 bytes is plenty in practice. Implementations + * are recommended to wrap a 32-byte key for the hardware KDF with AES-256-GCM, + * which should result in a size closer to 64 bytes than 128. + * + * Both of these values can trivially be increased if ever needed. + */ +#define BLK_CRYPTO_MAX_RAW_KEY_SIZE 64 +#define BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE 128 + +#define BLK_CRYPTO_MAX_ANY_KEY_SIZE \ + MAX(BLK_CRYPTO_MAX_RAW_KEY_SIZE, BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE) + +/* + * Size of the "software secret" which can be derived from a hardware-wrapped + * key. This is currently always 32 bytes. Note, the choice of 32 bytes + * assumes that the software secret is only used directly for algorithms that + * don't require more than a 256-bit key to get the desired security strength. + * If it were to be used e.g. directly as an AES-256-XTS key, then this would + * need to be increased (which is possible if hardware supports it, but care + * would need to be taken to avoid breaking users who need exactly 32 bytes). + */ +#define BLK_CRYPTO_SW_SECRET_SIZE 32 + /** * struct blk_crypto_config - an inline encryption key's crypto configuration * @crypto_mode: encryption algorithm this key is for @@ -26,20 +76,23 @@ enum blk_crypto_mode_num { * ciphertext. This is always a power of 2. It might be e.g. the * filesystem block size or the disk sector size. * @dun_bytes: the maximum number of bytes of DUN used when using this key + * @key_type: the type of this key -- either raw or hardware-wrapped */ struct blk_crypto_config { enum blk_crypto_mode_num crypto_mode; unsigned int data_unit_size; unsigned int dun_bytes; + enum blk_crypto_key_type key_type; }; /** * struct blk_crypto_key - an inline encryption key - * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this - * key + * @crypto_cfg: the crypto mode, data unit size, key type, and other + * characteristics of this key and how it will be used * @data_unit_size_bits: log2 of data_unit_size - * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode) - * @raw: the raw bytes of this key. Only the first @size bytes are used. + * @size: size of this key in bytes. The size of a raw key is fixed for a given + * crypto mode, but the size of a hardware-wrapped key can vary. + * @bytes: the bytes of this key. Only the first @size bytes are significant. * * A blk_crypto_key is immutable once created, and many bios can reference it at * the same time. It must not be freed until all bios using it have completed @@ -49,7 +102,7 @@ struct blk_crypto_key { struct blk_crypto_config crypto_cfg; unsigned int data_unit_size_bits; unsigned int size; - u8 raw[BLK_CRYPTO_MAX_KEY_SIZE]; + u8 bytes[BLK_CRYPTO_MAX_ANY_KEY_SIZE]; }; #define BLK_CRYPTO_MAX_IV_SIZE 32 @@ -87,7 +140,9 @@ bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc, unsigned int bytes, const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]); -int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key, +int blk_crypto_init_key(struct blk_crypto_key *blk_key, + const u8 *key_bytes, size_t key_size, + enum blk_crypto_key_type key_type, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, unsigned int data_unit_size); @@ -103,6 +158,10 @@ bool blk_crypto_config_supported_natively(struct block_device *bdev, bool blk_crypto_config_supported(struct block_device *bdev, const struct blk_crypto_config *cfg); +int blk_crypto_derive_sw_secret(struct block_device *bdev, + const u8 *eph_key, size_t eph_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]); + #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool bio_has_crypt_ctx(struct bio *bio) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index aba9c24486aa..8eb9b3310167 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -1173,14 +1173,13 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) return max_t(unsigned short, rq->nr_phys_segments, 1); } -int __blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist, struct scatterlist **last_sg); -static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) +int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, + struct scatterlist **last_sg); +static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; - return __blk_rq_map_sg(q, rq, sglist, &last_sg); + return __blk_rq_map_sg(rq, sglist, &last_sg); } void blk_dump_rq_flags(struct request *, char *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d37751789bf5..e39c45bc0a97 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -268,10 +268,16 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +/* + * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) + * however we constrain this to what we can validate and test. + */ +#define BLK_MAX_BLOCK_SIZE SZ_64K + /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { - if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) + if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; @@ -562,7 +568,22 @@ struct request_queue { struct blk_flush_queue *fq; struct list_head flush_list; + /* + * Protects against I/O scheduler switching, particularly when updating + * q->elevator. Since the elevator update code path may also modify q-> + * nr_requests and wbt latency, this lock also protects the sysfs attrs + * nr_requests and wbt_lat_usec. Additionally the nr_hw_queues update + * may modify hctx tags, reserved-tags and cpumask, so this lock also + * helps protect the hctx sysfs/debugfs attrs. To ensure proper locking + * order during an elevator or nr_hw_queue update, first freeze the + * queue, then acquire ->elevator_lock. + */ + struct mutex elevator_lock; + struct mutex sysfs_lock; + /* + * Protects queue limits and also sysfs attribute read_ahead_kb. + */ struct mutex limits_lock; /* diff --git a/include/linux/cache.h b/include/linux/cache.h index ca2a05682a54..e69768f50d53 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -3,16 +3,13 @@ #define __LINUX_CACHE_H #include <uapi/linux/kernel.h> +#include <vdso/cache.h> #include <asm/cache.h> #ifndef L1_CACHE_ALIGN #define L1_CACHE_ALIGN(x) __ALIGN_KERNEL(x, L1_CACHE_BYTES) #endif -#ifndef SMP_CACHE_BYTES -#define SMP_CACHE_BYTES L1_CACHE_BYTES -#endif - /** * SMP_CACHE_ALIGN - align a value to the L2 cacheline size * @x: value to align @@ -63,10 +60,6 @@ #define __ro_after_init __section(".data..ro_after_init") #endif -#ifndef ____cacheline_aligned -#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) -#endif - #ifndef ____cacheline_aligned_in_smp #ifdef CONFIG_SMP #define ____cacheline_aligned_in_smp ____cacheline_aligned diff --git a/include/linux/cfi.h b/include/linux/cfi.h index f0df518e11dd..1db17ecbb86c 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -11,6 +11,8 @@ #include <linux/module.h> #include <asm/cfi.h> +extern bool cfi_warn; + #ifndef cfi_get_offset static inline int cfi_get_offset(void) { diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 17960a1e858d..485b651869d9 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -619,9 +619,8 @@ struct cgroup_root { */ struct cftype { /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. + * Name of the subsystem is prepended in cgroup_file_name(). + * Zero length string indicates end of cftype array. */ char name[MAX_CFTYPE_NAME]; unsigned long private; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f8ef47f8a634..28e999f2c642 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -113,6 +113,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); void cgroup_file_show(struct cgroup_file *cfile, bool show); @@ -689,8 +690,6 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_hold(struct cgroup *cgrp); -void cgroup_rstat_flush_release(struct cgroup *cgrp); /* * Basic resource stats. diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index ee2614adb785..2b32a5759b22 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -216,6 +216,23 @@ const volatile void * __must_check_fn(const volatile void *val) #define return_ptr(p) return no_free_ptr(p) +/* + * Only for situations where an allocation is handed in to another function + * and consumed by that function on success. + * + * struct foo *f __free(kfree) = kzalloc(sizeof(*f), GFP_KERNEL); + * + * setup(f); + * if (some_condition) + * return -EINVAL; + * .... + * ret = bar(f); + * if (!ret) + * retain_ptr(f); + * return ret; + */ +#define retain_ptr(p) \ + __get_and_null(p, NULL) /* * DEFINE_CLASS(name, type, exit, init, init_args...): @@ -291,11 +308,21 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond -#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ +#define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ + static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { return (void *)(__force unsigned long)*(_exp); } + +#define DEFINE_CLASS_IS_GUARD(_name) \ __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ + __DEFINE_GUARD_LOCK_PTR(_name, _T) + +#define DEFINE_CLASS_IS_COND_GUARD(_name) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, true); \ + __DEFINE_GUARD_LOCK_PTR(_name, _T) + +#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \ - static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ - { return (void *)(__force unsigned long)*_T; } + DEFINE_CLASS_IS_GUARD(_name) #define DEFINE_GUARD_COND(_name, _ext, _condlock) \ __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ @@ -375,11 +402,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ if (_T->lock) { _unlock; } \ } \ \ -static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ -{ \ - return (void *)(__force unsigned long)_T->lock; \ -} - +__DEFINE_GUARD_LOCK_PTR(_name, &_T->lock) #define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ static inline class_##_name##_t class_##_name##_constructor(_type *l) \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 155385754824..9fc30b6b80c9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -206,12 +206,38 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __must_be_byte_array(a) __BUILD_BUG_ON_ZERO_MSG(!__is_byte_array(a), \ "must be byte array") +/* + * If the "nonstring" attribute isn't available, we have to return true + * so the __must_*() checks pass when "nonstring" isn't supported. + */ +#if __has_attribute(__nonstring__) && defined(__annotated) +#define __is_cstr(a) (!__annotated(a, nonstring)) +#define __is_noncstr(a) (__annotated(a, nonstring)) +#else +#define __is_cstr(a) (true) +#define __is_noncstr(a) (true) +#endif + /* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ #define __must_be_cstr(p) \ - __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") + __BUILD_BUG_ON_ZERO_MSG(!__is_cstr(p), \ + "must be C-string (NUL-terminated)") +#define __must_be_noncstr(p) \ + __BUILD_BUG_ON_ZERO_MSG(!__is_noncstr(p), \ + "must be non-C-string (not NUL-terminated)") #endif /* __KERNEL__ */ +#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +/* + * Force a reference to the external symbol so the compiler generates + * __kcfi_typid. + */ +#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym) +#else +#define KCFI_REFERENCE(sym) +#endif + /** * offset_to_ptr - convert a relative memory offset to an absolute pointer * @off: the address of the 32-bit offset value diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 981cc3d7e3aa..e09d323be845 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -349,6 +349,18 @@ struct ftrace_likely_data { #endif /* + * Optional: only supported since gcc >= 15 + * Optional: not supported by Clang + * + * gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 + */ +#ifdef CONFIG_CC_HAS_MULTIDIMENSIONAL_NONSTRING +# define __nonstring_array __attribute__((__nonstring__)) +#else +# define __nonstring_array +#endif + +/* * Apply __counted_by() when the Endianness matches to increase test coverage. */ #ifdef __LITTLE_ENDIAN @@ -360,7 +372,7 @@ struct ftrace_likely_data { #endif /* Do not trap wrapping arithmetic within an annotated function. */ -#ifdef CONFIG_UBSAN_SIGNED_WRAP +#ifdef CONFIG_UBSAN_INTEGER_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) #else # define __signed_wrap @@ -446,11 +458,14 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif -/* Determine if an attribute has been applied to a variable. */ +/* + * Determine if an attribute has been applied to a variable. + * Using __annotated needs to check for __annotated being available, + * or negative tests may fail when annotation cannot be checked. For + * example, see the definition of __is_cstr(). + */ #if __has_builtin(__builtin_has_attribute) #define __annotated(var, attr) __builtin_has_attribute(var, attr) -#else -#define __annotated(var, attr) (false) #endif /* diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index 20b5729903d7..2fd7ba75362a 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -32,6 +32,7 @@ struct cpu_rmap { #define CPU_RMAP_DIST_INF 0xffff extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags); +extern void cpu_rmap_get(struct cpu_rmap *rmap); extern int cpu_rmap_put(struct cpu_rmap *rmap); extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7fe0981a7e46..400fee6427a5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -144,6 +144,9 @@ struct cpufreq_policy { /* Per policy boost enabled flag. */ bool boost_enabled; + /* Per policy boost supported flag. */ + bool boost_supported; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; unsigned int cached_resolved_idx; @@ -210,6 +213,9 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { } #endif +/* Scope based cleanup macro for cpufreq_policy kobject reference counting */ +DEFINE_FREE(put_cpufreq_policy, struct cpufreq_policy *, if (_T) cpufreq_cpu_put(_T)) + static inline bool policy_is_inactive(struct cpufreq_policy *policy) { return cpumask_empty(policy->cpus); @@ -778,10 +784,8 @@ int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy, ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); #ifdef CONFIG_CPU_FREQ -int cpufreq_boost_trigger_state(int state); bool cpufreq_boost_enabled(void); -int cpufreq_enable_boost_support(void); -bool policy_has_boost_freq(struct cpufreq_policy *policy); +int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state); /* Find lowest freq at or above target in a table in ascending order */ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy, @@ -1150,23 +1154,14 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_ return 0; } #else -static inline int cpufreq_boost_trigger_state(int state) -{ - return 0; -} static inline bool cpufreq_boost_enabled(void) { return false; } -static inline int cpufreq_enable_boost_support(void) +static inline int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state) { - return -EINVAL; -} - -static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) -{ - return false; + return -EOPNOTSUPP; } static inline int @@ -1184,7 +1179,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_ } #endif -extern unsigned int arch_freq_get_on_cpu(int cpu); +extern int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale static __always_inline @@ -1198,7 +1193,6 @@ void arch_set_freq_scale(const struct cpumask *cpus, /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; -extern struct freq_attr *cpufreq_generic_attr[]; int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy); unsigned int cpufreq_generic_get(unsigned int cpu); diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 36a890d0dd57..f9a868384083 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -81,7 +81,7 @@ static __always_inline void set_nr_cpu_ids(unsigned int nr) * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated - * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online + * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * @@ -285,35 +285,52 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, } /** - * for_each_cpu - iterate over every cpu in a mask - * @cpu: the (optionally unsigned) integer iterator - * @mask: the cpumask pointer + * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from + * @n+1. If nothing found, wrap around and start from + * the beginning + * @n: the cpu prior to the place to search (i.e. search starts from @n+1) + * @src1p: the first cpumask pointer + * @src2p: the second cpumask pointer * - * After the loop, cpu is >= nr_cpu_ids. + * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty. */ -#define for_each_cpu(cpu, mask) \ - for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) - -#if NR_CPUS == 1 static __always_inline -unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) +unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p, + const struct cpumask *src2p) { - cpumask_check(start); + /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); + return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), + small_cpumask_bits, n + 1); +} - /* - * Return the first available CPU when wrapping, or when starting before cpu0, - * since there is only one valid option. - */ - if (wrap && n >= 0) - return nr_cpumask_bits; - - return cpumask_first(mask); +/** + * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing + * found, wrap around and start from the beginning + * @n: the cpu prior to the place to search (i.e. search starts from @n+1) + * @src: cpumask pointer + * + * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty. + */ +static __always_inline +unsigned int cpumask_next_wrap(int n, const struct cpumask *src) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1); } -#else -unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); -#endif + +/** + * for_each_cpu - iterate over every cpu in a mask + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask pointer + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu(cpu, mask) \ + for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location @@ -1033,11 +1050,21 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) + +#define for_each_possible_cpu_wrap(cpu, start) \ + for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) +#define for_each_online_cpu_wrap(cpu, start) \ + for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) + +#define for_each_possible_cpu_wrap(cpu, start) \ + for_each_cpu_wrap((cpu), cpu_possible_mask, (start)) +#define for_each_online_cpu_wrap(cpu, start) \ + for_each_cpu_wrap((cpu), cpu_online_mask, (start)) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 835e7b793f6a..5466c96a33db 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -125,9 +125,11 @@ static inline int cpuset_do_page_mem_spread(void) extern bool current_cpuset_is_being_rebound(void); +extern void dl_rebuild_rd_accounting(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); +extern void cpuset_reset_sched_domains(void); /* * read_mems_allowed_begin is required when making decisions involving @@ -259,11 +261,20 @@ static inline bool current_cpuset_is_being_rebound(void) return false; } +static inline void dl_rebuild_rd_accounting(void) +{ +} + static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } +static inline void cpuset_reset_sched_domains(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_print_current_mems_allowed(void) { } diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 16787c1cee21..a559fdff3f7e 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -4,9 +4,6 @@ #include <linux/types.h> -#define CRC_T10DIF_DIGEST_SIZE 2 -#define CRC_T10DIF_BLOCK_SIZE 1 - u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len); u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len); @@ -22,13 +19,4 @@ static inline u16 crc_t10dif(const u8 *p, size_t len) return crc_t10dif_update(0, p, len); } -#if IS_ENABLED(CONFIG_CRC_T10DIF_ARCH) -bool crc_t10dif_is_optimized(void); -#else -static inline bool crc_t10dif_is_optimized(void) -{ - return false; -} -#endif - #endif diff --git a/include/linux/crc32.h b/include/linux/crc32.h index e9bd40056687..69c2e8bb3782 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -8,33 +8,32 @@ #include <linux/types.h> #include <linux/bitrev.h> -u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len); -u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len); -u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len); -u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len); -u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len); -u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len); +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len); +u32 crc32_le_base(u32 crc, const u8 *p, size_t len); +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len); +u32 crc32_be_base(u32 crc, const u8 *p, size_t len); +u32 crc32c_arch(u32 crc, const u8 *p, size_t len); +u32 crc32c_base(u32 crc, const u8 *p, size_t len); -static inline u32 __pure crc32_le(u32 crc, const u8 *p, size_t len) +static inline u32 crc32_le(u32 crc, const void *p, size_t len) { if (IS_ENABLED(CONFIG_CRC32_ARCH)) return crc32_le_arch(crc, p, len); return crc32_le_base(crc, p, len); } -static inline u32 __pure crc32_be(u32 crc, const u8 *p, size_t len) +static inline u32 crc32_be(u32 crc, const void *p, size_t len) { if (IS_ENABLED(CONFIG_CRC32_ARCH)) return crc32_be_arch(crc, p, len); return crc32_be_base(crc, p, len); } -/* TODO: leading underscores should be dropped once callers have been updated */ -static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) +static inline u32 crc32c(u32 crc, const void *p, size_t len) { if (IS_ENABLED(CONFIG_CRC32_ARCH)) - return crc32c_le_arch(crc, p, len); - return crc32c_le_base(crc, p, len); + return crc32c_arch(crc, p, len); + return crc32c_base(crc, p, len); } /* @@ -45,7 +44,7 @@ static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len) */ #define CRC32_LE_OPTIMIZATION BIT(0) /* crc32_le() is optimized */ #define CRC32_BE_OPTIMIZATION BIT(1) /* crc32_be() is optimized */ -#define CRC32C_OPTIMIZATION BIT(2) /* __crc32c_le() is optimized */ +#define CRC32C_OPTIMIZATION BIT(2) /* crc32c() is optimized */ #if IS_ENABLED(CONFIG_CRC32_ARCH) u32 crc32_optimizations(void); #else @@ -70,36 +69,34 @@ static inline u32 crc32_optimizations(void) { return 0; } * with the same initializer as crc1, and crc2 seed was 0. See * also crc32_combine_test(). */ -u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len); +u32 crc32_le_shift(u32 crc, size_t len); static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2) { return crc32_le_shift(crc1, len2) ^ crc2; } +u32 crc32c_shift(u32 crc, size_t len); + /** - * __crc32c_le_combine - Combine two crc32c check values into one. For two - * sequences of bytes, seq1 and seq2 with lengths len1 - * and len2, __crc32c_le() check values were calculated - * for each, crc1 and crc2. + * crc32c_combine - Combine two crc32c check values into one. For two sequences + * of bytes, seq1 and seq2 with lengths len1 and len2, crc32c() + * check values were calculated for each, crc1 and crc2. * * @crc1: crc32c of the first block * @crc2: crc32c of the second block * @len2: length of the second block * - * Return: The __crc32c_le() check value of seq1 and seq2 concatenated, - * requiring only crc1, crc2, and len2. Note: If seq_full denotes - * the concatenated memory area of seq1 with seq2, and crc_full - * the __crc32c_le() value of seq_full, then crc_full == - * __crc32c_le_combine(crc1, crc2, len2) when crc_full was - * seeded with the same initializer as crc1, and crc2 seed - * was 0. See also crc32c_combine_test(). + * Return: The crc32c() check value of seq1 and seq2 concatenated, requiring + * only crc1, crc2, and len2. Note: If seq_full denotes the concatenated + * memory area of seq1 with seq2, and crc_full the crc32c() value of + * seq_full, then crc_full == crc32c_combine(crc1, crc2, len2) when + * crc_full was seeded with the same initializer as crc1, and crc2 seed + * was 0. See also crc_combine_test(). */ -u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len); - -static inline u32 __crc32c_le_combine(u32 crc1, u32 crc2, size_t len2) +static inline u32 crc32c_combine(u32 crc1, u32 crc2, size_t len2) { - return __crc32c_le_shift(crc1, len2) ^ crc2; + return crc32c_shift(crc1, len2) ^ crc2; } #define crc32(seed, data, length) crc32_le(seed, (unsigned char const *)(data), length) diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h index 47eb78003c26..b8cff2f4309a 100644 --- a/include/linux/crc32c.h +++ b/include/linux/crc32c.h @@ -4,12 +4,4 @@ #include <linux/crc32.h> -static inline u32 crc32c(u32 crc, const void *address, unsigned int length) -{ - return __crc32c_le(crc, address, length); -} - -/* This macro exists for backwards-compatibility. */ -#define crc32c_le crc32c - #endif /* _LINUX_CRC32C_H */ diff --git a/include/linux/crc64.h b/include/linux/crc64.h index e044c60d1e61..41de30b907df 100644 --- a/include/linux/crc64.h +++ b/include/linux/crc64.h @@ -7,12 +7,40 @@ #include <linux/types.h> -#define CRC64_ROCKSOFT_STRING "crc64-rocksoft" +u64 crc64_be_arch(u64 crc, const u8 *p, size_t len); +u64 crc64_be_generic(u64 crc, const u8 *p, size_t len); +u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len); +u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len); -u64 __pure crc64_be(u64 crc, const void *p, size_t len); -u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len); +/** + * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64 + * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation, + * or the previous crc64 value if computing incrementally. + * @p: pointer to buffer over which CRC64 is run + * @len: length of buffer @p + */ +static inline u64 crc64_be(u64 crc, const void *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC64_ARCH)) + return crc64_be_arch(crc, p, len); + return crc64_be_generic(crc, p, len); +} -u64 crc64_rocksoft(const unsigned char *buffer, size_t len); -u64 crc64_rocksoft_update(u64 crc, const unsigned char *buffer, size_t len); +/** + * crc64_nvme - Calculate CRC64-NVME + * @crc: seed value for computation. 0 for a new CRC calculation, or the + * previous crc64 value if computing incrementally. + * @p: pointer to buffer over which CRC64 is run + * @len: length of buffer @p + * + * This computes the CRC64 defined in the NVME NVM Command Set Specification, + * *including the bitwise inversion at the beginning and end*. + */ +static inline u64 crc64_nvme(u64 crc, const void *p, size_t len) +{ + if (IS_ENABLED(CONFIG_CRC64_ARCH)) + return ~crc64_nvme_arch(~crc, p, len); + return ~crc64_nvme_generic(~crc, p, len); +} #endif /* _LINUX_CRC64_H */ diff --git a/include/linux/crc7.h b/include/linux/crc7.h index b462842f3c32..61d34749e437 100644 --- a/include/linux/crc7.h +++ b/include/linux/crc7.h @@ -3,13 +3,6 @@ #define _LINUX_CRC7_H #include <linux/types.h> -extern const u8 crc7_be_syndrome_table[256]; - -static inline u8 crc7_be_byte(u8 crc, u8 data) -{ - return crc7_be_syndrome_table[crc ^ data]; -} - extern u8 crc7_be(u8 crc, const u8 *buffer, size_t len); #endif diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4afb60365675..8d1395f945bf 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -203,34 +203,34 @@ struct dentry_operations { #define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) +#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(13) /* Parent inode is watched by some fsnotify listener */ -#define DCACHE_DENTRY_KILLED BIT(15) +#define DCACHE_DENTRY_KILLED BIT(14) -#define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ -#define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ -#define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ +#define DCACHE_MOUNTED BIT(15) /* is a mountpoint */ +#define DCACHE_NEED_AUTOMOUNT BIT(16) /* handle automount on this dir */ +#define DCACHE_MANAGE_TRANSIT BIT(17) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) -#define DCACHE_LRU_LIST BIT(19) +#define DCACHE_LRU_LIST BIT(18) -#define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ -#define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ -#define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ -#define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ -#define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ -#define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ -#define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ -#define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ +#define DCACHE_ENTRY_TYPE (7 << 19) /* bits 19..21 are for storing type: */ +#define DCACHE_MISS_TYPE (0 << 19) /* Negative dentry */ +#define DCACHE_WHITEOUT_TYPE (1 << 19) /* Whiteout dentry (stop pathwalk) */ +#define DCACHE_DIRECTORY_TYPE (2 << 19) /* Normal directory */ +#define DCACHE_AUTODIR_TYPE (3 << 19) /* Lookupless directory (presumed automount) */ +#define DCACHE_REGULAR_TYPE (4 << 19) /* Regular file type */ +#define DCACHE_SPECIAL_TYPE (5 << 19) /* Other file type */ +#define DCACHE_SYMLINK_TYPE (6 << 19) /* Symlink */ -#define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ -#define DCACHE_OP_REAL BIT(26) +#define DCACHE_NOKEY_NAME BIT(22) /* Encrypted name encoded without key */ +#define DCACHE_OP_REAL BIT(23) -#define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ -#define DCACHE_DENTRY_CURSOR BIT(29) -#define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ +#define DCACHE_PAR_LOOKUP BIT(24) /* being looked up (with parent locked shared) */ +#define DCACHE_DENTRY_CURSOR BIT(25) +#define DCACHE_NORCU BIT(26) /* No RCU delay for freeing */ extern seqlock_t rename_lock; @@ -253,7 +253,6 @@ extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); -extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); @@ -520,12 +519,7 @@ static inline int simple_positive(const struct dentry *dentry) return d_really_is_positive(dentry) && !d_unhashed(dentry); } -extern int sysctl_vfs_cache_pressure; - -static inline unsigned long vfs_pressure_ratio(unsigned long val) -{ - return mult_frac(val, sysctl_vfs_cache_pressure, 100); -} +unsigned long vfs_pressure_ratio(unsigned long val); /** * d_inode - Get the actual inode of this dentry diff --git a/include/linux/device.h b/include/linux/device.h index 80a5b3268986..1655be8bda14 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -26,9 +26,9 @@ #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> -#include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> +#include <linux/device/devres.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> @@ -281,123 +281,6 @@ int __must_check device_create_bin_file(struct device *dev, void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); -/* device resource management */ -typedef void (*dr_release_t)(struct device *dev, void *res); -typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); - -void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, - int nid, const char *name) __malloc; -#define devres_alloc(release, size, gfp) \ - __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) -#define devres_alloc_node(release, size, gfp, nid) \ - __devres_alloc_node(release, size, gfp, nid, #release) - -void devres_for_each_res(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data, - void (*fn)(struct device *, void *, void *), - void *data); -void devres_free(void *res); -void devres_add(struct device *dev, void *res); -void *devres_find(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -void *devres_get(struct device *dev, void *new_res, - dr_match_t match, void *match_data); -void *devres_remove(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -int devres_destroy(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); -int devres_release(struct device *dev, dr_release_t release, - dr_match_t match, void *match_data); - -/* devres group */ -void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); -void devres_close_group(struct device *dev, void *id); -void devres_remove_group(struct device *dev, void *id); -int devres_release_group(struct device *dev, void *id); - -/* managed devm_k.alloc/kfree for device drivers */ -void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2); -void *devm_krealloc(struct device *dev, void *ptr, size_t size, - gfp_t gfp) __must_check __realloc_size(3); -__printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, - const char *fmt, va_list ap) __malloc; -__printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, - const char *fmt, ...) __malloc; -static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) -{ - return devm_kmalloc(dev, size, gfp | __GFP_ZERO); -} -static inline void *devm_kmalloc_array(struct device *dev, - size_t n, size_t size, gfp_t flags) -{ - size_t bytes; - - if (unlikely(check_mul_overflow(n, size, &bytes))) - return NULL; - - return devm_kmalloc(dev, bytes, flags); -} -static inline void *devm_kcalloc(struct device *dev, - size_t n, size_t size, gfp_t flags) -{ - return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); -} -static inline __realloc_size(3, 4) void * __must_check -devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) -{ - size_t bytes; - - if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) - return NULL; - - return devm_krealloc(dev, p, bytes, flags); -} - -void devm_kfree(struct device *dev, const void *p); -char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; -const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); -void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) - __realloc_size(3); - -unsigned long devm_get_free_pages(struct device *dev, - gfp_t gfp_mask, unsigned int order); -void devm_free_pages(struct device *dev, unsigned long addr); - -#ifdef CONFIG_HAS_IOMEM -void __iomem *devm_ioremap_resource(struct device *dev, - const struct resource *res); -void __iomem *devm_ioremap_resource_wc(struct device *dev, - const struct resource *res); - -void __iomem *devm_of_iomap(struct device *dev, - struct device_node *node, int index, - resource_size_t *size); -#else - -static inline -void __iomem *devm_ioremap_resource(struct device *dev, - const struct resource *res) -{ - return ERR_PTR(-EINVAL); -} - -static inline -void __iomem *devm_ioremap_resource_wc(struct device *dev, - const struct resource *res) -{ - return ERR_PTR(-EINVAL); -} - -static inline -void __iomem *devm_of_iomap(struct device *dev, - struct device_node *node, int index, - resource_size_t *size) -{ - return ERR_PTR(-EINVAL); -} - -#endif - /* allows to add/remove a custom action to devres stack */ int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); @@ -1025,6 +908,15 @@ static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) return !!(dev->power.driver_flags & flags); } +static inline bool dev_pm_smart_suspend(struct device *dev) +{ +#ifdef CONFIG_PM_SLEEP + return dev->power.smart_suspend; +#else + return false; +#endif +} + static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); diff --git a/include/linux/device/devres.h b/include/linux/device/devres.h new file mode 100644 index 000000000000..9b49f9915850 --- /dev/null +++ b/include/linux/device/devres.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _DEVICE_DEVRES_H_ +#define _DEVICE_DEVRES_H_ + +#include <linux/err.h> +#include <linux/gfp_types.h> +#include <linux/numa.h> +#include <linux/overflow.h> +#include <linux/stdarg.h> +#include <linux/types.h> + +struct device; +struct device_node; +struct resource; + +/* device resource management */ +typedef void (*dr_release_t)(struct device *dev, void *res); +typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); + +void * __malloc +__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name); +#define devres_alloc(release, size, gfp) \ + __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) +#define devres_alloc_node(release, size, gfp, nid) \ + __devres_alloc_node(release, size, gfp, nid, #release) + +void devres_for_each_res(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data, + void (*fn)(struct device *, void *, void *), + void *data); +void devres_free(void *res); +void devres_add(struct device *dev, void *res); +void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); +void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); +void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); +int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); +int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); + +/* devres group */ +void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); +void devres_close_group(struct device *dev, void *id); +void devres_remove_group(struct device *dev, void *id); +int devres_release_group(struct device *dev, void *id); + +/* managed devm_k.alloc/kfree for device drivers */ +void * __alloc_size(2) +devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); +void * __must_check __realloc_size(3) +devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp); +static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) +{ + return devm_kmalloc(dev, size, gfp | __GFP_ZERO); +} +static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + return devm_kmalloc(dev, bytes, flags); +} +static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) +{ + return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); +} +static inline __realloc_size(3, 4) void * __must_check +devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) + return NULL; + + return devm_krealloc(dev, p, bytes, flags); +} + +void devm_kfree(struct device *dev, const void *p); + +void * __realloc_size(3) +devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); +static inline void *devm_kmemdup_array(struct device *dev, const void *src, + size_t n, size_t size, gfp_t flags) +{ + return devm_kmemdup(dev, src, size_mul(size, n), flags); +} + +char * __malloc +devm_kstrdup(struct device *dev, const char *s, gfp_t gfp); +const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); +char * __printf(3, 0) __malloc +devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap); +char * __printf(3, 4) __malloc +devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); + +unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); +void devm_free_pages(struct device *dev, unsigned long addr); + +#ifdef CONFIG_HAS_IOMEM + +void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); +void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); + +void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, + resource_size_t *size); +#else + +static inline +void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) +{ + return IOMEM_ERR_PTR(-EINVAL); +} + +static inline +void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) +{ + return IOMEM_ERR_PTR(-EINVAL); +} + +static inline +void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, + resource_size_t *size) +{ + return IOMEM_ERR_PTR(-EINVAL); +} + +#endif + +#endif /* _DEVICE_DEVRES_H_ */ diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index d7e30d4f7503..f3bc0bcd7098 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -78,14 +78,18 @@ static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map) #define phys_to_dma_unencrypted phys_to_dma #endif #else -static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev, - phys_addr_t paddr) +static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { if (dev->dma_range_map) return translate_phys_to_dma(dev, paddr); return paddr; } +static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev, + phys_addr_t paddr) +{ + return dma_addr_unencrypted(__phys_to_dma(dev, paddr)); +} /* * If memory encryption is supported, phys_to_dma will set the memory encryption * bit in the DMA address, and dma_to_phys will clear it. @@ -94,19 +98,20 @@ static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev, */ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) { - return __sme_set(phys_to_dma_unencrypted(dev, paddr)); + return dma_addr_encrypted(__phys_to_dma(dev, paddr)); } static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr) { phys_addr_t paddr; + dma_addr = dma_addr_canonical(dma_addr); if (dev->dma_range_map) paddr = translate_dma_to_phys(dev, dma_addr); else paddr = dma_addr; - return __sme_clr(paddr); + return paddr; } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ diff --git a/include/linux/edac.h b/include/linux/edac.h index b4ee8961e623..451f9c152c99 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -661,4 +661,219 @@ static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci, return mci->dimms[index]; } + +#define EDAC_FEAT_NAME_LEN 128 + +/* RAS feature type */ +enum edac_dev_feat { + RAS_FEAT_SCRUB, + RAS_FEAT_ECS, + RAS_FEAT_MEM_REPAIR, + RAS_FEAT_MAX +}; + +/** + * struct edac_scrub_ops - scrub device operations (all elements optional) + * @read_addr: read base address of scrubbing range. + * @read_size: read offset of scrubbing range. + * @write_addr: set base address of the scrubbing range. + * @write_size: set offset of the scrubbing range. + * @get_enabled_bg: check if currently performing background scrub. + * @set_enabled_bg: start or stop a bg-scrub. + * @get_min_cycle: get minimum supported scrub cycle duration in seconds. + * @get_max_cycle: get maximum supported scrub cycle duration in seconds. + * @get_cycle_duration: get current scrub cycle duration in seconds. + * @set_cycle_duration: set current scrub cycle duration in seconds. + */ +struct edac_scrub_ops { + int (*read_addr)(struct device *dev, void *drv_data, u64 *base); + int (*read_size)(struct device *dev, void *drv_data, u64 *size); + int (*write_addr)(struct device *dev, void *drv_data, u64 base); + int (*write_size)(struct device *dev, void *drv_data, u64 size); + int (*get_enabled_bg)(struct device *dev, void *drv_data, bool *enable); + int (*set_enabled_bg)(struct device *dev, void *drv_data, bool enable); + int (*get_min_cycle)(struct device *dev, void *drv_data, u32 *min); + int (*get_max_cycle)(struct device *dev, void *drv_data, u32 *max); + int (*get_cycle_duration)(struct device *dev, void *drv_data, u32 *cycle); + int (*set_cycle_duration)(struct device *dev, void *drv_data, u32 cycle); +}; + +#if IS_ENABLED(CONFIG_EDAC_SCRUB) +int edac_scrub_get_desc(struct device *scrub_dev, + const struct attribute_group **attr_groups, + u8 instance); +#else +static inline int edac_scrub_get_desc(struct device *scrub_dev, + const struct attribute_group **attr_groups, + u8 instance) +{ return -EOPNOTSUPP; } +#endif /* CONFIG_EDAC_SCRUB */ + +/** + * struct edac_ecs_ops - ECS device operations (all elements optional) + * @get_log_entry_type: read the log entry type value. + * @set_log_entry_type: set the log entry type value. + * @get_mode: read the mode value. + * @set_mode: set the mode value. + * @reset: reset the ECS counter. + * @get_threshold: read the threshold count per gigabits of memory cells. + * @set_threshold: set the threshold count per gigabits of memory cells. + */ +struct edac_ecs_ops { + int (*get_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 *val); + int (*set_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 val); + int (*get_mode)(struct device *dev, void *drv_data, int fru_id, u32 *val); + int (*set_mode)(struct device *dev, void *drv_data, int fru_id, u32 val); + int (*reset)(struct device *dev, void *drv_data, int fru_id, u32 val); + int (*get_threshold)(struct device *dev, void *drv_data, int fru_id, u32 *threshold); + int (*set_threshold)(struct device *dev, void *drv_data, int fru_id, u32 threshold); +}; + +struct edac_ecs_ex_info { + u16 num_media_frus; +}; + +#if IS_ENABLED(CONFIG_EDAC_ECS) +int edac_ecs_get_desc(struct device *ecs_dev, + const struct attribute_group **attr_groups, + u16 num_media_frus); +#else +static inline int edac_ecs_get_desc(struct device *ecs_dev, + const struct attribute_group **attr_groups, + u16 num_media_frus) +{ return -EOPNOTSUPP; } +#endif /* CONFIG_EDAC_ECS */ + +enum edac_mem_repair_type { + EDAC_REPAIR_MAX +}; + +enum edac_mem_repair_cmd { + EDAC_DO_MEM_REPAIR = 1, +}; + +/** + * struct edac_mem_repair_ops - memory repair operations + * (all elements are optional except do_repair, set_hpa/set_dpa) + * @get_repair_type: get the memory repair type, listed in + * enum edac_mem_repair_function. + * @get_persist_mode: get the current persist mode. + * false - Soft repair type (temporary repair). + * true - Hard memory repair type (permanent repair). + * @set_persist_mode: set the persist mode of the memory repair instance. + * @get_repair_safe_when_in_use: get whether memory media is accessible and + * data is retained during repair operation. + * @get_hpa: get current host physical address (HPA) of memory to repair. + * @set_hpa: set host physical address (HPA) of memory to repair. + * @get_min_hpa: get the minimum supported host physical address (HPA). + * @get_max_hpa: get the maximum supported host physical address (HPA). + * @get_dpa: get current device physical address (DPA) of memory to repair. + * @set_dpa: set device physical address (DPA) of memory to repair. + * In some states of system configuration (e.g. before address decoders + * have been configured), memory devices (e.g. CXL) may not have an active + * mapping in the host physical address map. As such, the memory + * to repair must be identified by a device specific physical addressing + * scheme using a device physical address(DPA). The DPA and other control + * attributes to use for the repair operations will be presented in related + * error records. + * @get_min_dpa: get the minimum supported device physical address (DPA). + * @get_max_dpa: get the maximum supported device physical address (DPA). + * @get_nibble_mask: get current nibble mask of memory to repair. + * @set_nibble_mask: set nibble mask of memory to repair. + * @get_bank_group: get current bank group of memory to repair. + * @set_bank_group: set bank group of memory to repair. + * @get_bank: get current bank of memory to repair. + * @set_bank: set bank of memory to repair. + * @get_rank: get current rank of memory to repair. + * @set_rank: set rank of memory to repair. + * @get_row: get current row of memory to repair. + * @set_row: set row of memory to repair. + * @get_column: get current column of memory to repair. + * @set_column: set column of memory to repair. + * @get_channel: get current channel of memory to repair. + * @set_channel: set channel of memory to repair. + * @get_sub_channel: get current subchannel of memory to repair. + * @set_sub_channel: set subchannel of memory to repair. + * @do_repair: Issue memory repair operation for the HPA/DPA and + * other control attributes set for the memory to repair. + * + * All elements are optional except do_repair and at least one of set_hpa/set_dpa. + */ +struct edac_mem_repair_ops { + int (*get_repair_type)(struct device *dev, void *drv_data, const char **type); + int (*get_persist_mode)(struct device *dev, void *drv_data, bool *persist); + int (*set_persist_mode)(struct device *dev, void *drv_data, bool persist); + int (*get_repair_safe_when_in_use)(struct device *dev, void *drv_data, bool *safe); + int (*get_hpa)(struct device *dev, void *drv_data, u64 *hpa); + int (*set_hpa)(struct device *dev, void *drv_data, u64 hpa); + int (*get_min_hpa)(struct device *dev, void *drv_data, u64 *hpa); + int (*get_max_hpa)(struct device *dev, void *drv_data, u64 *hpa); + int (*get_dpa)(struct device *dev, void *drv_data, u64 *dpa); + int (*set_dpa)(struct device *dev, void *drv_data, u64 dpa); + int (*get_min_dpa)(struct device *dev, void *drv_data, u64 *dpa); + int (*get_max_dpa)(struct device *dev, void *drv_data, u64 *dpa); + int (*get_nibble_mask)(struct device *dev, void *drv_data, u32 *val); + int (*set_nibble_mask)(struct device *dev, void *drv_data, u32 val); + int (*get_bank_group)(struct device *dev, void *drv_data, u32 *val); + int (*set_bank_group)(struct device *dev, void *drv_data, u32 val); + int (*get_bank)(struct device *dev, void *drv_data, u32 *val); + int (*set_bank)(struct device *dev, void *drv_data, u32 val); + int (*get_rank)(struct device *dev, void *drv_data, u32 *val); + int (*set_rank)(struct device *dev, void *drv_data, u32 val); + int (*get_row)(struct device *dev, void *drv_data, u32 *val); + int (*set_row)(struct device *dev, void *drv_data, u32 val); + int (*get_column)(struct device *dev, void *drv_data, u32 *val); + int (*set_column)(struct device *dev, void *drv_data, u32 val); + int (*get_channel)(struct device *dev, void *drv_data, u32 *val); + int (*set_channel)(struct device *dev, void *drv_data, u32 val); + int (*get_sub_channel)(struct device *dev, void *drv_data, u32 *val); + int (*set_sub_channel)(struct device *dev, void *drv_data, u32 val); + int (*do_repair)(struct device *dev, void *drv_data, u32 val); +}; + +#if IS_ENABLED(CONFIG_EDAC_MEM_REPAIR) +int edac_mem_repair_get_desc(struct device *dev, + const struct attribute_group **attr_groups, + u8 instance); +#else +static inline int edac_mem_repair_get_desc(struct device *dev, + const struct attribute_group **attr_groups, + u8 instance) +{ return -EOPNOTSUPP; } +#endif /* CONFIG_EDAC_MEM_REPAIR */ + +/* EDAC device feature information structure */ +struct edac_dev_data { + union { + const struct edac_scrub_ops *scrub_ops; + const struct edac_ecs_ops *ecs_ops; + const struct edac_mem_repair_ops *mem_repair_ops; + }; + u8 instance; + void *private; +}; + +struct edac_dev_feat_ctx { + struct device dev; + void *private; + struct edac_dev_data *scrub; + struct edac_dev_data ecs; + struct edac_dev_data *mem_repair; +}; + +struct edac_dev_feature { + enum edac_dev_feat ft_type; + u8 instance; + union { + const struct edac_scrub_ops *scrub_ops; + const struct edac_ecs_ops *ecs_ops; + const struct edac_mem_repair_ops *mem_repair_ops; + }; + void *ctx; + struct edac_ecs_ex_info ecs_info; +}; + +int edac_dev_register(struct device *parent, char *dev_name, + void *parent_pvt_data, int num_features, + const struct edac_dev_feature *ras_features); #endif /* _LINUX_EDAC_H_ */ diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 78318d49276d..d8eabbf86a5b 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -167,13 +167,13 @@ struct em_data_callback { struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); int em_dev_update_perf_domain(struct device *dev, - struct em_perf_table __rcu *new_table); + struct em_perf_table *new_table); int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, - struct em_data_callback *cb, cpumask_t *span, - bool microwatts); + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); -struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); -void em_table_free(struct em_perf_table __rcu *table); +struct em_perf_table *em_table_alloc(struct em_perf_domain *pd); +void em_table_free(struct em_perf_table *table); int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int nr_states); int em_dev_update_chip_binning(struct device *dev); @@ -240,9 +240,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, struct em_perf_state *ps; int i; -#ifdef CONFIG_SCHED_DEBUG WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n"); -#endif if (!sum_util) return 0; @@ -346,8 +344,8 @@ struct em_data_callback {}; static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, - struct em_data_callback *cb, cpumask_t *span, - bool microwatts) + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) { return -EINVAL; } @@ -373,14 +371,14 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) return 0; } static inline -struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) +struct em_perf_table *em_table_alloc(struct em_perf_domain *pd) { return NULL; } -static inline void em_table_free(struct em_perf_table __rcu *table) {} +static inline void em_table_free(struct em_perf_table *table) {} static inline int em_dev_update_perf_domain(struct device *dev, - struct em_perf_table __rcu *new_table) + struct em_perf_table *new_table) { return -EINVAL; } diff --git a/include/linux/err.h b/include/linux/err.h index a4dacd745fcf..1d60aa86db53 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -44,6 +44,9 @@ static inline void * __must_check ERR_PTR(long error) /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) +/* Cast an error pointer to __iomem. */ +#define IOMEM_ERR_PTR(error) (__force void __iomem *)ERR_PTR(error) + /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 870994cc3ef7..8210ece94fa6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -210,6 +210,14 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); +struct link_mode_info { + int speed; + u8 lanes; + u8 duplex; +}; + +extern const struct link_mode_info link_mode_params[]; + /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) @@ -763,13 +771,12 @@ struct kernel_ethtool_ts_info { /** * struct ethtool_ops - optional netdev operations + * @supported_input_xfrm: supported types of input xfrm from %RXH_XFRM_*. * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS * contexts via legacy API, drivers implementing @create_rxfh_context * do not have to set this bit. - * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor - * RSS. * @rxfh_per_ctx_key: device supports setting different RSS key for each * additional context. Netlink API should report hfunc, key, and input_xfrm * for every context, not just context 0. @@ -995,9 +1002,9 @@ struct kernel_ethtool_ts_info { * of the generic netdev features interface. */ struct ethtool_ops { + u32 supported_input_xfrm:8; u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; - u32 cap_rss_sym_xor_supported:1; u32 rxfh_per_ctx_key:1; u32 cap_rss_rxnfc_adds:1; u32 rxfh_indir_space; diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 0c0d00fcd131..ccb478eb174b 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -25,6 +25,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long t /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); +/* Copy ready events to userspace */ +int epoll_sendevents(struct file *file, struct epoll_event __user *events, + int maxevents); + /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 64130ae19690..65655a5d1be2 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -65,6 +65,37 @@ enum execmem_range_flags { * Architectures that use EXECMEM_ROX_CACHE must implement this. */ void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); + +/** + * execmem_make_temp_rw - temporarily remap region with read-write + * permissions + * @ptr: address of the region to remap + * @size: size of the region to remap + * + * Remaps a part of the cached large page in the ROX cache in the range + * [@ptr, @ptr + @size) as writable and not executable. The caller must + * have exclusive ownership of this range and ensure nothing will try to + * execute code in this range. + * + * Return: 0 on success or negative error code on failure. + */ +int execmem_make_temp_rw(void *ptr, size_t size); + +/** + * execmem_restore_rox - restore read-only-execute permissions + * @ptr: address of the region to remap + * @size: size of the region to remap + * + * Restores read-only-execute permissions on a range [@ptr, @ptr + @size) + * after it was temporarily remapped as writable. Relies on architecture + * implementation of set_memory_rox() to restore mapping using large pages. + * + * Return: 0 on success or negative error code on failure. + */ +int execmem_restore_rox(void *ptr, size_t size); +#else +static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; } +static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } #endif /** diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 78f660ebc318..3c817dc6292e 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ #define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) -#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT) /* * fanotify_init() flags that require CAP_SYS_ADMIN. @@ -38,7 +38,8 @@ FAN_REPORT_PIDFD | \ FAN_REPORT_FD_ERROR | \ FAN_UNLIMITED_QUEUE | \ - FAN_UNLIMITED_MARKS) + FAN_UNLIMITED_MARKS | \ + FAN_REPORT_MNT) /* * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN. @@ -58,7 +59,7 @@ #define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ - FAN_MARK_FILESYSTEM) + FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS) #define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ FAN_MARK_FLUSH) @@ -109,10 +110,13 @@ /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ #define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) +#define FANOTIFY_MOUNT_EVENTS (FAN_MNT_ATTACH | FAN_MNT_DETACH) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ FANOTIFY_INODE_EVENTS | \ - FANOTIFY_ERROR_EVENTS) + FANOTIFY_ERROR_EVENTS | \ + FANOTIFY_MOUNT_EVENTS) /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h index 9b3a8d9b17ab..7db62fbc0500 100644 --- a/include/linux/file_ref.h +++ b/include/linux/file_ref.h @@ -61,6 +61,7 @@ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) atomic_long_set(&ref->refcnt, cnt - 1); } +bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt); bool __file_ref_put(file_ref_t *ref, unsigned long cnt); /** @@ -161,6 +162,39 @@ static __always_inline __must_check bool file_ref_put(file_ref_t *ref) } /** + * file_ref_put_close - drop a reference expecting it would transition to FILE_REF_NOREF + * @ref: Pointer to the reference count + * + * Semantically it is equivalent to calling file_ref_put(), but it trades lower + * performance in face of other CPUs also modifying the refcount for higher + * performance when this happens to be the last reference. + * + * For the last reference file_ref_put() issues 2 atomics. One to drop the + * reference and another to transition it to FILE_REF_DEAD. This routine does + * the work in one step, but in order to do it has to pre-read the variable which + * decreases scalability. + * + * Use with close() et al, stick to file_ref_put() by default. + */ +static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref) +{ + long old, new; + + old = atomic_long_read(&ref->refcnt); + do { + if (unlikely(old < 0)) + return __file_ref_put_badval(ref, old); + + if (old == FILE_REF_ONEREF) + new = FILE_REF_DEAD; + else + new = old - 1; + } while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new)); + + return new == FILE_REF_DEAD; +} + +/** * file_ref_read - Read the number of file references * @ref: Pointer to the reference count * @@ -174,4 +208,18 @@ static inline unsigned long file_ref_read(file_ref_t *ref) return c >= FILE_REF_RELEASED ? 0 : c + 1; } +/* + * __file_ref_read_raw - Return the value stored in ref->refcnt + * @ref: Pointer to the reference count + * + * Return: The raw value found in the counter + * + * A hack for file_needs_f_pos_lock(), you probably want to use + * file_ref_read() instead. + */ +static inline unsigned long __file_ref_read_raw(file_ref_t *ref) +{ + return atomic_long_read(&ref->refcnt); +} + #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index a3ea46281595..d36d5d5180b1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1508,6 +1508,7 @@ struct bpf_sock_ops_kern { void *skb_data_end; u8 op; u8 is_fullsock; + u8 is_locked_tcp_sock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling diff --git a/include/linux/firmware/samsung/exynos-acpm-protocol.h b/include/linux/firmware/samsung/exynos-acpm-protocol.h new file mode 100644 index 000000000000..76255b5d06b1 --- /dev/null +++ b/include/linux/firmware/samsung/exynos-acpm-protocol.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2020 Samsung Electronics Co., Ltd. + * Copyright 2020 Google LLC. + * Copyright 2024 Linaro Ltd. + */ + +#ifndef __EXYNOS_ACPM_PROTOCOL_H +#define __EXYNOS_ACPM_PROTOCOL_H + +#include <linux/types.h> + +struct acpm_handle; + +struct acpm_pmic_ops { + int (*read_reg)(const struct acpm_handle *handle, + unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan, + u8 *buf); + int (*bulk_read)(const struct acpm_handle *handle, + unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan, + u8 count, u8 *buf); + int (*write_reg)(const struct acpm_handle *handle, + unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan, + u8 value); + int (*bulk_write)(const struct acpm_handle *handle, + unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan, + u8 count, const u8 *buf); + int (*update_reg)(const struct acpm_handle *handle, + unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan, + u8 value, u8 mask); +}; + +struct acpm_ops { + struct acpm_pmic_ops pmic_ops; +}; + +/** + * struct acpm_handle - Reference to an initialized protocol instance + * @ops: + */ +struct acpm_handle { + struct acpm_ops ops; +}; + +struct device; + +const struct acpm_handle *devm_acpm_get_by_phandle(struct device *dev, + const char *property); +#endif /* __EXYNOS_ACPM_PROTOCOL_H */ diff --git a/include/linux/firmware/thead/thead,th1520-aon.h b/include/linux/firmware/thead/thead,th1520-aon.h new file mode 100644 index 000000000000..dae132b66873 --- /dev/null +++ b/include/linux/firmware/thead/thead,th1520-aon.h @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2021 Alibaba Group Holding Limited. + */ + +#ifndef _THEAD_AON_H +#define _THEAD_AON_H + +#include <linux/device.h> +#include <linux/types.h> + +#define AON_RPC_MSG_MAGIC (0xef) +#define TH1520_AON_RPC_VERSION 2 +#define TH1520_AON_RPC_MSG_NUM 7 + +struct th1520_aon_chan; + +enum th1520_aon_rpc_svc { + TH1520_AON_RPC_SVC_UNKNOWN = 0, + TH1520_AON_RPC_SVC_PM = 1, + TH1520_AON_RPC_SVC_MISC = 2, + TH1520_AON_RPC_SVC_AVFS = 3, + TH1520_AON_RPC_SVC_SYS = 4, + TH1520_AON_RPC_SVC_WDG = 5, + TH1520_AON_RPC_SVC_LPM = 6, + TH1520_AON_RPC_SVC_MAX = 0x3F, +}; + +enum th1520_aon_misc_func { + TH1520_AON_MISC_FUNC_UNKNOWN = 0, + TH1520_AON_MISC_FUNC_SET_CONTROL = 1, + TH1520_AON_MISC_FUNC_GET_CONTROL = 2, + TH1520_AON_MISC_FUNC_REGDUMP_CFG = 3, +}; + +enum th1520_aon_wdg_func { + TH1520_AON_WDG_FUNC_UNKNOWN = 0, + TH1520_AON_WDG_FUNC_START = 1, + TH1520_AON_WDG_FUNC_STOP = 2, + TH1520_AON_WDG_FUNC_PING = 3, + TH1520_AON_WDG_FUNC_TIMEOUTSET = 4, + TH1520_AON_WDG_FUNC_RESTART = 5, + TH1520_AON_WDG_FUNC_GET_STATE = 6, + TH1520_AON_WDG_FUNC_POWER_OFF = 7, + TH1520_AON_WDG_FUNC_AON_WDT_ON = 8, + TH1520_AON_WDG_FUNC_AON_WDT_OFF = 9, +}; + +enum th1520_aon_sys_func { + TH1520_AON_SYS_FUNC_UNKNOWN = 0, + TH1520_AON_SYS_FUNC_AON_RESERVE_MEM = 1, +}; + +enum th1520_aon_lpm_func { + TH1520_AON_LPM_FUNC_UNKNOWN = 0, + TH1520_AON_LPM_FUNC_REQUIRE_STR = 1, + TH1520_AON_LPM_FUNC_RESUME_STR = 2, + TH1520_AON_LPM_FUNC_REQUIRE_STD = 3, + TH1520_AON_LPM_FUNC_CPUHP = 4, + TH1520_AON_LPM_FUNC_REGDUMP_CFG = 5, +}; + +enum th1520_aon_pm_func { + TH1520_AON_PM_FUNC_UNKNOWN = 0, + TH1520_AON_PM_FUNC_SET_RESOURCE_REGULATOR = 1, + TH1520_AON_PM_FUNC_GET_RESOURCE_REGULATOR = 2, + TH1520_AON_PM_FUNC_SET_RESOURCE_POWER_MODE = 3, + TH1520_AON_PM_FUNC_PWR_SET = 4, + TH1520_AON_PM_FUNC_PWR_GET = 5, + TH1520_AON_PM_FUNC_CHECK_FAULT = 6, + TH1520_AON_PM_FUNC_GET_TEMPERATURE = 7, +}; + +struct th1520_aon_rpc_msg_hdr { + u8 ver; /* version of msg hdr */ + u8 size; /* msg size ,uinit in bytes,the size includes rpc msg header self */ + u8 svc; /* rpc main service id */ + u8 func; /* rpc sub func id of specific service, sent by caller */ +} __packed __aligned(1); + +struct th1520_aon_rpc_ack_common { + struct th1520_aon_rpc_msg_hdr hdr; + u8 err_code; +} __packed __aligned(1); + +#define RPC_SVC_MSG_TYPE_DATA 0 +#define RPC_SVC_MSG_TYPE_ACK 1 +#define RPC_SVC_MSG_NEED_ACK 0 +#define RPC_SVC_MSG_NO_NEED_ACK 1 + +#define RPC_GET_VER(MESG) ((MESG)->ver) +#define RPC_SET_VER(MESG, VER) ((MESG)->ver = (VER)) +#define RPC_GET_SVC_ID(MESG) ((MESG)->svc & 0x3F) +#define RPC_SET_SVC_ID(MESG, ID) ((MESG)->svc |= 0x3F & (ID)) +#define RPC_GET_SVC_FLAG_MSG_TYPE(MESG) (((MESG)->svc & 0x80) >> 7) +#define RPC_SET_SVC_FLAG_MSG_TYPE(MESG, TYPE) ((MESG)->svc |= (TYPE) << 7) +#define RPC_GET_SVC_FLAG_ACK_TYPE(MESG) (((MESG)->svc & 0x40) >> 6) +#define RPC_SET_SVC_FLAG_ACK_TYPE(MESG, ACK) ((MESG)->svc |= (ACK) << 6) + +#define RPC_SET_BE64(MESG, OFFSET, SET_DATA) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + u64 _set_data = (SET_DATA); \ + data[_offset + 7] = _set_data & 0xFF; \ + data[_offset + 6] = (_set_data & 0xFF00) >> 8; \ + data[_offset + 5] = (_set_data & 0xFF0000) >> 16; \ + data[_offset + 4] = (_set_data & 0xFF000000) >> 24; \ + data[_offset + 3] = (_set_data & 0xFF00000000) >> 32; \ + data[_offset + 2] = (_set_data & 0xFF0000000000) >> 40; \ + data[_offset + 1] = (_set_data & 0xFF000000000000) >> 48; \ + data[_offset + 0] = (_set_data & 0xFF00000000000000) >> 56; \ + } while (0) + +#define RPC_SET_BE32(MESG, OFFSET, SET_DATA) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + u64 _set_data = (SET_DATA); \ + data[_offset + 3] = (_set_data) & 0xFF; \ + data[_offset + 2] = (_set_data & 0xFF00) >> 8; \ + data[_offset + 1] = (_set_data & 0xFF0000) >> 16; \ + data[_offset + 0] = (_set_data & 0xFF000000) >> 24; \ + } while (0) + +#define RPC_SET_BE16(MESG, OFFSET, SET_DATA) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + u64 _set_data = (SET_DATA); \ + data[_offset + 1] = (_set_data) & 0xFF; \ + data[_offset + 0] = (_set_data & 0xFF00) >> 8; \ + } while (0) + +#define RPC_SET_U8(MESG, OFFSET, SET_DATA) \ + do { \ + u8 *data = (u8 *)(MESG); \ + data[OFFSET] = (SET_DATA) & 0xFF; \ + } while (0) + +#define RPC_GET_BE64(MESG, OFFSET, PTR) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + *(u32 *)(PTR) = \ + (data[_offset + 7] | data[_offset + 6] << 8 | \ + data[_offset + 5] << 16 | data[_offset + 4] << 24 | \ + data[_offset + 3] << 32 | data[_offset + 2] << 40 | \ + data[_offset + 1] << 48 | data[_offset + 0] << 56); \ + } while (0) + +#define RPC_GET_BE32(MESG, OFFSET, PTR) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + *(u32 *)(PTR) = \ + (data[_offset + 3] | data[_offset + 2] << 8 | \ + data[_offset + 1] << 16 | data[_offset + 0] << 24); \ + } while (0) + +#define RPC_GET_BE16(MESG, OFFSET, PTR) \ + do { \ + u8 *data = (u8 *)(MESG); \ + u64 _offset = (OFFSET); \ + *(u16 *)(PTR) = (data[_offset + 1] | data[_offset + 0] << 8); \ + } while (0) + +#define RPC_GET_U8(MESG, OFFSET, PTR) \ + do { \ + u8 *data = (u8 *)(MESG); \ + *(u8 *)(PTR) = (data[OFFSET]); \ + } while (0) + +/* + * Defines for SC PM Power Mode + */ +#define TH1520_AON_PM_PW_MODE_OFF 0 /* Power off */ +#define TH1520_AON_PM_PW_MODE_STBY 1 /* Power in standby */ +#define TH1520_AON_PM_PW_MODE_LP 2 /* Power in low-power */ +#define TH1520_AON_PM_PW_MODE_ON 3 /* Power on */ + +/* + * Defines for AON power islands + */ +#define TH1520_AON_AUDIO_PD 0 +#define TH1520_AON_VDEC_PD 1 +#define TH1520_AON_NPU_PD 2 +#define TH1520_AON_VENC_PD 3 +#define TH1520_AON_GPU_PD 4 +#define TH1520_AON_DSP0_PD 5 +#define TH1520_AON_DSP1_PD 6 + +struct th1520_aon_chan *th1520_aon_init(struct device *dev); +void th1520_aon_deinit(struct th1520_aon_chan *aon_chan); + +int th1520_aon_call_rpc(struct th1520_aon_chan *aon_chan, void *msg); +int th1520_aon_power_update(struct th1520_aon_chan *aon_chan, u16 rsrc, + bool power_on); + +#endif /* _THEAD_AON_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 2788df98080f..1a0e23a5d02d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> @@ -790,19 +791,8 @@ struct inode { static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { - int testlen; - - /* - * TODO: patch it into a debug-only check if relevant macros show up. - * In the meantime, since we are suffering strlen even on production kernels - * to find the right length, do a fixup if the wrong value got passed. - */ - testlen = strlen(link); - if (testlen != linklen) { - WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)", - link, linklen, testlen); - linklen = testlen; - } + VFS_WARN_ON_INODE(strlen(link) != linklen, inode); + VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; @@ -1067,7 +1057,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations @@ -1077,12 +1066,12 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener + * @f_owner: file owner * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file - * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file @@ -1090,9 +1079,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) + * @f_ref: reference count */ struct file { - file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1102,6 +1091,7 @@ struct file { unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; + struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { @@ -1115,7 +1105,6 @@ struct file { void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ - struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL @@ -1127,6 +1116,7 @@ struct file { struct file_ra_state f_ra; freeptr_t f_freeptr; }; + file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1981,8 +1971,8 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap, */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, @@ -2039,7 +2029,7 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); -extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, @@ -2211,8 +2201,8 @@ struct inode_operations { int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); @@ -2616,6 +2606,7 @@ struct file_system_type { #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ +#define FS_LBS 128 /* FS supports LBS */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2653,9 +2644,6 @@ static inline bool is_mgtime(const struct inode *inode) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2794,13 +2782,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) return mnt_idmap(mnt) != &nop_mnt_idmap; } -extern long vfs_truncate(const struct path *, loff_t); +int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); +int do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, @@ -2851,7 +2839,10 @@ extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); -extern struct filename *getname(const char __user *); +static inline struct filename *getname(const char __user *name) +{ + return getname_flags(name, 0); +} extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) @@ -2864,6 +2855,13 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f return __getname_maybe_null(name); } extern void putname(struct filename *name); +DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) + +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); @@ -3297,7 +3295,11 @@ static inline void __iget(struct inode *inode) extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode_pseudo(struct super_block *sb); +struct inode *alloc_inode(struct super_block *sb); +static inline struct inode *new_inode_pseudo(struct super_block *sb) +{ + return alloc_inode(sb); +} extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 4b4bfef6f053..a19e4bd32e4d 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -144,8 +144,6 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); -int reconfigure_single(struct super_block *s, - int flags, void *data); extern int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 18855cb44b1c..56fad33043d5 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -310,10 +310,8 @@ static inline void fscrypt_prepare_dentry(struct dentry *dentry, /* crypto.c */ void fscrypt_enqueue_decrypt_work(struct work_struct *); -struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs, - gfp_t gfp_flags); +struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, + size_t len, size_t offs, gfp_t gfp_flags); int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num, gfp_t gfp_flags); @@ -480,10 +478,8 @@ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { } -static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, - unsigned int len, - unsigned int offs, - gfp_t gfp_flags) +static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, + size_t len, size_t offs, gfp_t gfp_flags) { return ERR_PTR(-EOPNOTSUPP); } diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 83d3ac97f826..454d8e466958 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -320,6 +320,11 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) __fsnotify_vfsmount_delete(mnt); } +static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns) +{ + __fsnotify_mntns_delete(mntns); +} + /* * fsnotify_inoderemove - an inode is going away */ @@ -528,4 +533,19 @@ static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, NULL, NULL, NULL, 0); } +static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); +} + +static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_DETACH, ns, mnt); +} + +static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_MOVE, ns, mnt); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0d24a21a8e60..6cd8d1d28b8b 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -59,6 +59,10 @@ #define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ +#define FS_MNT_ATTACH 0x01000000 /* Mount was attached */ +#define FS_MNT_DETACH 0x02000000 /* Mount was detached */ +#define FS_MNT_MOVE (FS_MNT_ATTACH | FS_MNT_DETACH) + /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -80,6 +84,9 @@ */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) +/* Mount namespace events */ +#define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH) + /* Content events can be used to inspect file content */ #define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ FS_ACCESS_PERM) @@ -108,6 +115,7 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ + FSNOTIFY_MNT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ @@ -298,6 +306,7 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_MNT, FSNOTIFY_EVENT_ERROR, }; @@ -318,6 +327,11 @@ static inline const struct path *file_range_path(const struct file_range *range) return range->path; } +struct fsnotify_mnt { + const struct mnt_namespace *ns; + u64 mnt_id; +}; + static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { @@ -383,6 +397,24 @@ static inline struct super_block *fsnotify_data_sb(const void *data, } } +static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_MNT: + return data; + default: + return NULL; + } +} + +static inline u64 fsnotify_data_mnt_id(const void *data, int data_type) +{ + const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); + + return mnt_data ? mnt_data->mnt_id : 0; +} + static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) @@ -420,6 +452,7 @@ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, + FSNOTIFY_ITER_TYPE_MNTNS, FSNOTIFY_ITER_TYPE_COUNT }; @@ -429,6 +462,7 @@ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, + FSNOTIFY_OBJ_TYPE_MNTNS, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; @@ -613,8 +647,10 @@ extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); +extern void __fsnotify_mntns_delete(struct mnt_namespace *mntns); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); +extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { @@ -928,6 +964,9 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void fsnotify_sb_delete(struct super_block *sb) {} +static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns) +{} + static inline void fsnotify_sb_free(struct super_block *sb) {} @@ -942,6 +981,9 @@ static inline u32 fsnotify_get_cookie(void) static inline void fsnotify_unmount_inodes(struct super_block *sb) {} +static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) +{} + #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 6270150f4e29..c1ec62c11ed3 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -91,7 +91,7 @@ static inline int gpio_get_value_cansleep(unsigned gpio) } static inline void gpio_set_value_cansleep(unsigned gpio, int value) { - return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value); + gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value); } static inline int gpio_get_value(unsigned gpio) @@ -100,7 +100,7 @@ static inline int gpio_get_value(unsigned gpio) } static inline void gpio_set_value(unsigned gpio, int value) { - return gpiod_set_raw_value(gpio_to_desc(gpio), value); + gpiod_set_raw_value(gpio_to_desc(gpio), value); } static inline int gpio_to_irq(unsigned gpio) diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index db2dfbae8edb..45b651c05b9c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -3,6 +3,7 @@ #define __LINUX_GPIO_CONSUMER_H #include <linux/bits.h> +#include <linux/err.h> #include <linux/types.h> struct acpi_device; @@ -110,8 +111,6 @@ int gpiod_get_direction(struct gpio_desc *desc); int gpiod_direction_input(struct gpio_desc *desc); int gpiod_direction_output(struct gpio_desc *desc, int value); int gpiod_direction_output_raw(struct gpio_desc *desc, int value); -int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); -int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); @@ -119,7 +118,7 @@ int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap); -void gpiod_set_value(struct gpio_desc *desc, int value); +int gpiod_set_value(struct gpio_desc *desc, int value); int gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, @@ -129,7 +128,7 @@ int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap); -void gpiod_set_raw_value(struct gpio_desc *desc, int value); +int gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, @@ -141,7 +140,7 @@ int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap); -void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); +int gpiod_set_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, @@ -151,7 +150,7 @@ int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap); -void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); +int gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, @@ -183,11 +182,9 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, #else /* CONFIG_GPIOLIB */ -#include <linux/err.h> +#include <linux/bug.h> #include <linux/kernel.h> -#include <asm/bug.h> - static inline int gpiod_count(struct device *dev, const char *con_id) { return 0; @@ -348,18 +345,6 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) WARN_ON(desc); return -ENOSYS; } -static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, - unsigned long flags) -{ - WARN_ON(desc); - return -ENOSYS; -} -static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, - unsigned long flags) -{ - WARN_ON(desc); - return -ENOSYS; -} static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ @@ -375,10 +360,11 @@ static inline int gpiod_get_array_value(unsigned int array_size, WARN_ON(desc_array); return 0; } -static inline void gpiod_set_value(struct gpio_desc *desc, int value) +static inline int gpiod_set_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ WARN_ON(desc); + return 0; } static inline int gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -404,10 +390,11 @@ static inline int gpiod_get_raw_array_value(unsigned int array_size, WARN_ON(desc_array); return 0; } -static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) +static inline int gpiod_set_raw_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ WARN_ON(desc); + return 0; } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -434,10 +421,11 @@ static inline int gpiod_get_array_value_cansleep(unsigned int array_size, WARN_ON(desc_array); return 0; } -static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) +static inline int gpiod_set_value_cansleep(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ WARN_ON(desc); + return 0; } static inline int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -463,11 +451,12 @@ static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, WARN_ON(desc_array); return 0; } -static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, - int value) +static inline int gpiod_set_raw_value_cansleep(struct gpio_desc *desc, + int value) { /* GPIO can never have been requested */ WARN_ON(desc); + return 0; } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -560,6 +549,31 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, #endif /* CONFIG_GPIOLIB */ +#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_HTE) +int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); +int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); +#else + +#include <linux/bug.h> + +static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + if (!IS_ENABLED(CONFIG_GPIOLIB)) + WARN_ON(desc); + + return -ENOSYS; +} +static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + if (!IS_ENABLED(CONFIG_GPIOLIB)) + WARN_ON(desc); + + return -ENOSYS; +} +#endif /* CONFIG_GPIOLIB && CONFIG_HTE */ + static inline struct gpio_desc *devm_fwnode_gpiod_get(struct device *dev, struct fwnode_handle *fwnode, @@ -608,8 +622,6 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ -#include <linux/err.h> - static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev, const struct acpi_gpio_mapping *gpios) { @@ -635,8 +647,6 @@ void gpiod_unexport(struct gpio_desc *desc); #else /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ -#include <asm/errno.h> - static inline int gpiod_export(struct gpio_desc *desc, bool direction_may_change) { @@ -655,4 +665,14 @@ static inline void gpiod_unexport(struct gpio_desc *desc) #endif /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */ +static inline int gpiod_multi_set_value_cansleep(struct gpio_descs *descs, + unsigned long *value_bitmap) +{ + if (IS_ERR_OR_NULL(descs)) + return PTR_ERR_OR_ZERO(descs); + + return gpiod_set_array_value_cansleep(descs->ndescs, descs->desc, + descs->info, value_bitmap); +} + #endif diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 2dd7cb9cc270..4c0294a9104d 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -14,6 +14,7 @@ #include <linux/property.h> #include <linux/spinlock_types.h> #include <linux/types.h> +#include <linux/util_macros.h> #ifdef CONFIG_GENERIC_MSI_IRQ #include <asm/msi.h> @@ -328,7 +329,8 @@ struct gpio_irq_chip { * @fwnode: optional fwnode providing this controller's properties * @owner: helps prevent removal of modules exporting active GPIOs * @request: optional hook for chip-specific activation, such as - * enabling module power and clock; may sleep + * enabling module power and clock; may sleep; must return 0 on success + * or negative error number on failure * @free: optional hook for chip-specific deactivation, such as * disabling module power and clock; may sleep * @get_direction: returns direction for signal "offset", 0=out, 1=in, @@ -344,10 +346,15 @@ struct gpio_irq_chip { * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error - * @set: assigns output value for signal "offset" - * @set_multiple: assigns output values for multiple signals defined by "mask" + * @set: **DEPRECATED** - please use set_rv() instead + * @set_multiple: **DEPRECATED** - please use set_multiple_rv() instead + * @set_rv: assigns output value for signal "offset", returns 0 on success or + * negative error value + * @set_multiple_rv: assigns output values for multiple signals defined by + * "mask", returns 0 on success or negative error value * @set_config: optional hook for all kinds of settings. Uses the same - * packed config format as generic pinconf. + * packed config format as generic pinconf. Must return 0 on success and + * a negative error number on failure. * @to_irq: optional hook supporting non-static gpiod_to_irq() mappings; * implementation may not sleep * @dbg_show: optional routine to show contents in debugfs; default code @@ -394,6 +401,7 @@ struct gpio_irq_chip { * @reg_dir_in: direction in setting register for generic GPIO * @bgpio_dir_unreadable: indicates that the direction register(s) cannot * be read and we need to rely on out internal state tracking. + * @bgpio_pinctrl: the generic GPIO uses a pin control backend. * @bgpio_bits: number of register bits used for a generic GPIO i.e. * <register width> * 8 * @bgpio_lock: used to lock chip->bgpio_data. Also, this is needed to keep @@ -441,6 +449,12 @@ struct gpio_chip { void (*set_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); + int (*set_rv)(struct gpio_chip *gc, + unsigned int offset, + int value); + int (*set_multiple_rv)(struct gpio_chip *gc, + unsigned long *mask, + unsigned long *bits); int (*set_config)(struct gpio_chip *gc, unsigned int offset, unsigned long config); @@ -478,6 +492,7 @@ struct gpio_chip { void __iomem *reg_dir_out; void __iomem *reg_dir_in; bool bgpio_dir_unreadable; + bool bgpio_pinctrl; int bgpio_bits; raw_spinlock_t bgpio_lock; unsigned long bgpio_data; @@ -499,14 +514,6 @@ struct gpio_chip { struct gpio_irq_chip irq; #endif /* CONFIG_GPIOLIB_IRQCHIP */ - /** - * @valid_mask: - * - * 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_GPIO is enabled, then all GPIO controllers described in @@ -516,11 +523,33 @@ struct gpio_chip { /** * @of_gpio_n_cells: * - * Number of cells used to form the GPIO specifier. + * Number of cells used to form the GPIO specifier. The standard is 2 + * cells: + * + * gpios = <&gpio offset flags>; + * + * some complex GPIO controllers instantiate more than one chip per + * device tree node and have 3 cells: + * + * gpios = <&gpio instance offset flags>; + * + * Legacy GPIO controllers may even have 1 cell: + * + * gpios = <&gpio offset>; */ unsigned int of_gpio_n_cells; /** + * @of_node_instance_match: + * + * Determine if a chip is the right instance. Must be implemented by + * any driver using more than one gpio_chip per device tree node. + * Returns true if gc is the instance indicated by i (which is the + * first cell in the phandles for GPIO lines and gpio-ranges). + */ + bool (*of_node_instance_match)(struct gpio_chip *gc, unsigned int i); + + /** * @of_xlate: * * Callback to translate a device tree GPIO specifier into a chip- @@ -550,19 +579,29 @@ DEFINE_CLASS(_gpiochip_for_each_data, const char **label, int *i) /** + * for_each_hwgpio_in_range - Iterates over all GPIOs in a given range + * @_chip: Chip to iterate over. + * @_i: Loop counter. + * @_base: First GPIO in the ranger. + * @_size: Amount of GPIOs to check starting from @base. + * @_label: Place to store the address of the label if the GPIO is requested. + * Set to NULL for unused GPIOs. + */ +#define for_each_hwgpio_in_range(_chip, _i, _base, _size, _label) \ + for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i); \ + _i < _size; \ + _i++, kfree(_label), _label = NULL) \ + for_each_if(!IS_ERR(_label = gpiochip_dup_line_label(_chip, _base + _i))) + +/** * for_each_hwgpio - Iterates over all GPIOs for given chip. * @_chip: Chip to iterate over. * @_i: Loop counter. * @_label: Place to store the address of the label if the GPIO is requested. * Set to NULL for unused GPIOs. */ -#define for_each_hwgpio(_chip, _i, _label) \ - for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i); \ - *_data.i < _chip->ngpio; \ - (*_data.i)++, kfree(*(_data.label)), *_data.label = NULL) \ - if (IS_ERR(*_data.label = \ - gpiochip_dup_line_label(_chip, *_data.i))) {} \ - else +#define for_each_hwgpio(_chip, _i, _label) \ + for_each_hwgpio_in_range(_chip, _i, 0, _chip->ngpio, _label) /** * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range @@ -573,13 +612,8 @@ DEFINE_CLASS(_gpiochip_for_each_data, * @_label: label of current GPIO */ #define for_each_requested_gpio_in_range(_chip, _i, _base, _size, _label) \ - for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i); \ - *_data.i < _size; \ - (*_data.i)++, kfree(*(_data.label)), *_data.label = NULL) \ - if ((*_data.label = \ - gpiochip_dup_line_label(_chip, _base + *_data.i)) == NULL) {} \ - else if (IS_ERR(*_data.label)) {} \ - else + for_each_hwgpio_in_range(_chip, _i, _base, _size, _label) \ + for_each_if(_label) /* Iterates over all requested GPIO of the given @chip */ #define for_each_requested_gpio(chip, i, label) \ @@ -678,6 +712,7 @@ bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); /* Sleep persistence inquiry for drivers */ bool gpiochip_line_is_persistent(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_valid(const struct gpio_chip *gc, unsigned int offset); +const unsigned long *gpiochip_query_valid_mask(const struct gpio_chip *gc); /* get driver data */ void *gpiochip_get_data(struct gpio_chip *gc); @@ -713,6 +748,7 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, #define BGPIOF_READ_OUTPUT_REG_SET BIT(4) /* reg_set stores output value */ #define BGPIOF_NO_OUTPUT BIT(5) /* only input */ #define BGPIOF_NO_SET_ON_INPUT BIT(6) +#define BGPIOF_PINCTRL_BACKEND BIT(7) /* Call pinctrl direction setters */ #ifdef CONFIG_GPIOLIB_IRQCHIP int gpiochip_irqchip_add_domain(struct gpio_chip *gc, @@ -865,7 +901,7 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, #define for_each_gpiochip_node(dev, child) \ device_for_each_child_node(dev, child) \ - if (!fwnode_property_present(child, "gpio-controller")) {} else + for_each_if(fwnode_property_present(child, "gpio-controller")) static inline unsigned int gpiochip_node_count(struct device *dev) { diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index a9f7b7faf57b..c722c67668c6 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -21,7 +21,7 @@ struct regmap; * 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 + * @ngpio: (Optional) Number of GPIOs * @names: (Optional) Array of names for gpios * @reg_dat_base: (Optional) (in) register base address * @reg_set_base: (Optional) set register base address @@ -30,7 +30,7 @@ struct regmap; * @reg_dir_out_base: (Optional) out setting register base address * @reg_stride: (Optional) May be set if the registers (of the * same type, dat, set, etc) are not consecutive. - * @ngpio_per_reg: Number of GPIOs per register + * @ngpio_per_reg: (Optional) Number of GPIOs per register * @irq_domain: (Optional) IRQ domain if the controller is * interrupt-capable * @reg_mask_xlate: (Optional) Translates base address and GPIO diff --git a/include/linux/hid.h b/include/linux/hid.h index cdc0dc13c87f..ef9a90ca0fbd 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -81,6 +81,8 @@ struct hid_item { #define HID_MAIN_ITEM_TAG_FEATURE 11 #define HID_MAIN_ITEM_TAG_BEGIN_COLLECTION 10 #define HID_MAIN_ITEM_TAG_END_COLLECTION 12 +#define HID_MAIN_ITEM_TAG_RESERVED_MIN 13 +#define HID_MAIN_ITEM_TAG_RESERVED_MAX 15 /* * HID report descriptor main item contents @@ -1222,12 +1224,6 @@ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); void hid_quirks_exit(__u16 bus); -#ifdef CONFIG_HID_PID -int hid_pidff_init(struct hid_device *hid); -#else -#define hid_pidff_init NULL -#endif - #define dbg_hid(fmt, ...) pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__) #define hid_err(hid, fmt, ...) \ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f7bfdcf0dda3..88e078871158 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -223,6 +223,11 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) } #endif +static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) +{ + return HRTIMER_NORESTART; +} + /* Exported timer functions: */ /* Initialize timers: */ @@ -333,6 +338,7 @@ static inline int hrtimer_callback_running(struct hrtimer *timer) static inline void hrtimer_update_function(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *)) { +#ifdef CONFIG_PROVE_LOCKING guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); if (WARN_ON_ONCE(hrtimer_is_queued(timer))) @@ -340,7 +346,7 @@ static inline void hrtimer_update_function(struct hrtimer *timer, if (WARN_ON_ONCE(!function)) return; - +#endif timer->function = function; } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 4179add2864b..675959fb97ba 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -371,19 +371,6 @@ struct vmtransfer_page_packet_header { struct vmtransfer_page_range ranges[]; } __packed; -struct vmgpadl_packet_header { - struct vmpacket_descriptor d; - u32 gpadl; - u32 reserved; -} __packed; - -struct vmadd_remove_transfer_page_set { - struct vmpacket_descriptor d; - u32 gpadl; - u16 xfer_pageset_id; - u16 reserved; -} __packed; - /* * This structure defines a range in guest physical space that can be made to * look virtually contiguous. @@ -395,30 +382,6 @@ struct gpa_range { }; /* - * This is the format for an Establish Gpadl packet, which contains a handle by - * which this GPADL will be known and a set of GPA ranges associated with it. - * This can be converted to a MDL by the guest OS. If there are multiple GPA - * ranges, then the resulting MDL will be "chained," representing multiple VA - * ranges. - */ -struct vmestablish_gpadl { - struct vmpacket_descriptor d; - u32 gpadl; - u32 range_cnt; - struct gpa_range range[1]; -} __packed; - -/* - * This is the format for a Teardown Gpadl packet, which indicates that the - * GPADL handle in the Establish Gpadl packet will never be referenced again. - */ -struct vmteardown_gpadl { - struct vmpacket_descriptor d; - u32 gpadl; - u32 reserved; /* for alignment to a 8-byte boundary */ -} __packed; - -/* * This is the format for a GPA-Direct packet, which contains a set of GPA * ranges, in addition to commands and/or data. */ @@ -429,25 +392,6 @@ struct vmdata_gpa_direct { struct gpa_range range[1]; } __packed; -/* This is the format for a Additional Data Packet. */ -struct vmadditional_data { - struct vmpacket_descriptor d; - u64 total_bytes; - u32 offset; - u32 byte_cnt; - unsigned char data[1]; -} __packed; - -union vmpacket_largest_possible_header { - struct vmpacket_descriptor simple_hdr; - struct vmtransfer_page_packet_header xfer_page_hdr; - struct vmgpadl_packet_header gpadl_hdr; - struct vmadd_remove_transfer_page_set add_rm_xfer_page_hdr; - struct vmestablish_gpadl establish_gpadl_hdr; - struct vmteardown_gpadl teardown_gpadl_hdr; - struct vmdata_gpa_direct data_gpa_direct_hdr; -}; - #define VMPACKET_DATA_START_ADDRESS(__packet) \ (void *)(((unsigned char *)__packet) + \ ((struct vmpacket_descriptor)__packet)->offset8 * 8) @@ -1661,6 +1605,7 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id, const guid_t *shv_host_servie_id); int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp); void vmbus_set_event(struct vmbus_channel *channel); +int vmbus_channel_set_cpu(struct vmbus_channel *channel, u32 target_cpu); /* Get the start of the ring buffer. */ static inline void * diff --git a/include/linux/idr.h b/include/linux/idr.h index da5f5fa4a3a6..cd729be369b3 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -15,6 +15,7 @@ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> +#include <linux/cleanup.h> struct idr { struct radix_tree_root idr_rt; @@ -124,6 +125,22 @@ void *idr_get_next_ul(struct idr *, unsigned long *nextid); void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); +struct __class_idr { + struct idr *idr; + int id; +}; + +#define idr_null ((struct __class_idr){ NULL, -1 }) +#define take_idr_id(id) __get_and_null(id, idr_null) + +DEFINE_CLASS(idr_alloc, struct __class_idr, + if (_T.id >= 0) idr_remove(_T.idr, _T.id), + ((struct __class_idr){ + .idr = idr, + .id = idr_alloc(idr, ptr, start, end, gfp), + }), + struct idr *idr, void *ptr, int start, int end, gfp_t gfp); + /** * idr_init_base() - Initialise an IDR. * @idr: IDR handle. diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 16741e542e81..508d466de1cc 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1543,6 +1543,10 @@ struct ieee80211_mgmt { u8 count; u8 variable[]; } __packed ml_reconf_resp; + struct { + u8 action_code; + u8 variable[]; + } __packed epcs; } u; } __packed action; DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */ @@ -3109,6 +3113,11 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 #define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 +#define IEEE80211_EHT_MAC_CAP1_EHT_TRS 0x02 +#define IEEE80211_EHT_MAC_CAP1_TXOP_RET 0x04 +#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS 0x08 +#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK 0x30 +#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS 0x40 /* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ #define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 @@ -5570,6 +5579,9 @@ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, fixed + prof->sta_info_len - 1 <= len; } +#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID 0x000f +#define IEEE80211_EPCS_ENA_RESP_BODY_LEN 3 + static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) { const struct ieee80211_ttlm_elem *t2l = (const void *)data; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3ff96ae31bf6..c5fe3b2a53e8 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -65,11 +65,9 @@ struct br_ip_list { #define BR_DEFAULT_AGEING_TIME (300 * HZ) struct net_bridge; -void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, - unsigned int cmd, struct ifreq *ifr, +void brioctl_set(int (*hook)(struct net *net, unsigned int cmd, void __user *uarg)); -int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, - struct ifreq *ifr, void __user *uarg); +int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg); #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 8a9792a6427a..61b7335aa037 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -19,6 +19,9 @@ #include <linux/skbuff.h> #include <uapi/linux/if_ether.h> +/* XX:XX:XX:XX:XX:XX */ +#define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1) + static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_mac_header(skb); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 523025106a64..0f7281e3e448 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -59,8 +59,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); -extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +struct rtnl_newlink_params; + +extern int macvlan_common_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); extern void macvlan_dellink(struct net_device *dev, struct list_head *head); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 8cd9327e4e78..c782a74d2a30 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -448,7 +448,7 @@ irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec, static inline void disable_irq_nosync_lockdep(unsigned int irq) { disable_irq_nosync(irq); -#ifdef CONFIG_LOCKDEP +#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT) local_irq_disable(); #endif } @@ -456,22 +456,14 @@ static inline void disable_irq_nosync_lockdep(unsigned int irq) static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags) { disable_irq_nosync(irq); -#ifdef CONFIG_LOCKDEP +#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT) local_irq_save(*flags); #endif } -static inline void disable_irq_lockdep(unsigned int irq) -{ - disable_irq(irq); -#ifdef CONFIG_LOCKDEP - local_irq_disable(); -#endif -} - static inline void enable_irq_lockdep(unsigned int irq) { -#ifdef CONFIG_LOCKDEP +#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT) local_irq_enable(); #endif enable_irq(irq); @@ -479,7 +471,7 @@ static inline void enable_irq_lockdep(unsigned int irq) static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags) { -#ifdef CONFIG_LOCKDEP +#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT) local_irq_restore(*flags); #endif enable_irq(irq); diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h index f32522bb3aa5..d3eade7cf663 100644 --- a/include/linux/io-64-nonatomic-hi-lo.h +++ b/include/linux/io-64-nonatomic-hi-lo.h @@ -101,22 +101,38 @@ static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr) #ifndef ioread64 #define ioread64_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define ioread64 __ioread64_hi_lo +#else #define ioread64 ioread64_hi_lo #endif +#endif #ifndef iowrite64 #define iowrite64_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define iowrite64 __iowrite64_hi_lo +#else #define iowrite64 iowrite64_hi_lo #endif +#endif #ifndef ioread64be #define ioread64be_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define ioread64be __ioread64be_hi_lo +#else #define ioread64be ioread64be_hi_lo #endif +#endif #ifndef iowrite64be #define iowrite64be_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define iowrite64be __iowrite64be_hi_lo +#else #define iowrite64be iowrite64be_hi_lo #endif +#endif #endif /* _LINUX_IO_64_NONATOMIC_HI_LO_H_ */ diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h index 448a21435dba..94e676ec3d3f 100644 --- a/include/linux/io-64-nonatomic-lo-hi.h +++ b/include/linux/io-64-nonatomic-lo-hi.h @@ -101,22 +101,38 @@ static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr) #ifndef ioread64 #define ioread64_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define ioread64 __ioread64_lo_hi +#else #define ioread64 ioread64_lo_hi #endif +#endif #ifndef iowrite64 #define iowrite64_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define iowrite64 __iowrite64_lo_hi +#else #define iowrite64 iowrite64_lo_hi #endif +#endif #ifndef ioread64be #define ioread64be_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define ioread64be __ioread64be_lo_hi +#else #define ioread64be ioread64be_lo_hi #endif +#endif #ifndef iowrite64be #define iowrite64be_is_nonatomic +#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT) +#define iowrite64be __iowrite64be_lo_hi +#else #define iowrite64be iowrite64be_lo_hi #endif +#endif #endif /* _LINUX_IO_64_NONATOMIC_LO_HI_H_ */ diff --git a/include/linux/io.h b/include/linux/io.h index 59ec5eea696c..6a6bc4d46d0a 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -9,13 +9,10 @@ #include <linux/sizes.h> #include <linux/types.h> #include <linux/init.h> -#include <linux/bug.h> -#include <linux/err.h> #include <asm/io.h> #include <asm/page.h> struct device; -struct resource; #ifndef __iowrite32_copy void __iowrite32_copy(void __iomem *to, const void *from, size_t count); @@ -65,8 +62,6 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr) } #endif -#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err) - void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index abd0c8bd950b..598cacda4aa3 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -4,6 +4,7 @@ #include <uapi/linux/io_uring.h> #include <linux/io_uring_types.h> +#include <linux/blk-mq.h> /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ #define IORING_URING_CMD_CANCELABLE (1U << 30) @@ -39,7 +40,9 @@ static inline void io_uring_cmd_private_sz_check(size_t cmd_sz) #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, - struct iov_iter *iter, void *ioucmd); + struct iov_iter *iter, + struct io_uring_cmd *ioucmd, + unsigned int issue_flags); /* * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd @@ -66,8 +69,10 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd); #else -static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, - struct iov_iter *iter, void *ioucmd) +static inline int +io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, + struct iov_iter *iter, struct io_uring_cmd *ioucmd, + unsigned int issue_flags) { return -EOPNOTSUPP; } @@ -123,4 +128,10 @@ static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_ur return cmd_to_io_kiocb(cmd)->async_data; } +int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, + void (*release)(void *), unsigned int index, + unsigned int issue_flags); +int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index, + unsigned int issue_flags); + #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3def525a1da3..72aac84dca93 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -292,6 +292,8 @@ struct io_ring_ctx { struct io_file_table file_table; struct io_rsrc_data buf_table; + struct io_alloc_cache node_cache; + struct io_alloc_cache imu_cache; struct io_submit_state submit_state; @@ -360,7 +362,6 @@ struct io_ring_ctx { spinlock_t completion_lock; - struct list_head io_buffers_comp; struct list_head cq_overflow_list; struct hlist_head waitid_list; @@ -379,8 +380,6 @@ struct io_ring_ctx { unsigned int file_alloc_start; unsigned int file_alloc_end; - struct list_head io_buffers_cache; - /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; @@ -439,8 +438,15 @@ struct io_ring_ctx { struct io_mapped_region param_region; }; +/* + * Token indicating function is called in task work context: + * ctx->uring_lock is held and any completions generated will be flushed. + * ONLY core io_uring.c should instantiate this struct. + */ struct io_tw_state { }; +/* Alias to use in code that doesn't instantiate struct io_tw_state */ +typedef struct io_tw_state io_tw_token_t; enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, @@ -566,7 +572,7 @@ enum { REQ_F_HAS_METADATA = IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT), }; -typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); +typedef void (*io_req_tw_func_t)(struct io_kiocb *req, io_tw_token_t tw); struct io_task_work { struct llist_node node; @@ -601,7 +607,11 @@ static inline void io_kiocb_cmd_sz_check(size_t cmd_sz) io_kiocb_cmd_sz_check(sizeof(cmd_type)) , \ ((cmd_type *)&(req)->cmd) \ ) -#define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr) + +static inline struct io_kiocb *cmd_to_io_kiocb(void *ptr) +{ + return ptr; +} struct io_kiocb { union { diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 75bf54e76f3b..02fe001feebb 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -56,6 +56,13 @@ struct vm_fault; * * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must * never be merged with the mapping before it. + * + * IOMAP_F_ANON_WRITE indicates that (write) I/O does not have a target block + * assigned to it yet and the file system will do that in the bio submission + * handler, splitting the I/O as needed. + * + * IOMAP_F_ATOMIC_BIO indicates that (write) I/O will be issued as an atomic + * bio, i.e. set REQ_ATOMIC. */ #define IOMAP_F_NEW (1U << 0) #define IOMAP_F_DIRTY (1U << 1) @@ -68,6 +75,8 @@ struct vm_fault; #endif /* CONFIG_BUFFER_HEAD */ #define IOMAP_F_XATTR (1U << 5) #define IOMAP_F_BOUNDARY (1U << 6) +#define IOMAP_F_ANON_WRITE (1U << 7) +#define IOMAP_F_ATOMIC_BIO (1U << 8) /* * Flags set by the core iomap code during operations: @@ -111,6 +120,8 @@ struct iomap { static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos) { + if (iomap->flags & IOMAP_F_ANON_WRITE) + return U64_MAX; /* invalid */ return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } @@ -182,7 +193,8 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ -#define IOMAP_ATOMIC (1 << 9) +#define IOMAP_ATOMIC (1 << 9) /* torn-write protection */ +#define IOMAP_DONTCACHE (1 << 10) struct iomap_ops { /* @@ -211,8 +223,10 @@ struct iomap_ops { * calls to iomap_iter(). Treat as read-only in the body. * @len: The remaining length of the file segment we're operating on. * It is updated at the same time as @pos. - * @processed: The number of bytes processed by the body in the most recent - * iteration, or a negative errno. 0 causes the iteration to stop. + * @iter_start_pos: The original start pos for the current iomap. Used for + * incremental iter advance. + * @status: Status of the most recent iteration. Zero on success or a negative + * errno on error. * @flags: Zero or more of the iomap_begin flags above. * @iomap: Map describing the I/O iteration * @srcmap: Source map for COW operations @@ -221,7 +235,8 @@ struct iomap_iter { struct inode *inode; loff_t pos; u64 len; - s64 processed; + loff_t iter_start_pos; + int status; unsigned flags; struct iomap iomap; struct iomap srcmap; @@ -229,20 +244,46 @@ struct iomap_iter { }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); +int iomap_iter_advance(struct iomap_iter *iter, u64 *count); /** - * iomap_length - length of the current iomap iteration + * iomap_length_trim - trimmed length of the current iomap iteration * @iter: iteration structure + * @pos: File position to trim from. + * @len: Length of the mapping to trim to. * - * Returns the length that the operation applies to for the current iteration. + * Returns a trimmed length that the operation applies to for the current + * iteration. */ -static inline u64 iomap_length(const struct iomap_iter *iter) +static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos, + u64 len) { u64 end = iter->iomap.offset + iter->iomap.length; if (iter->srcmap.type != IOMAP_HOLE) end = min(end, iter->srcmap.offset + iter->srcmap.length); - return min(iter->len, end - iter->pos); + return min(len, end - pos); +} + +/** + * iomap_length - length of the current iomap iteration + * @iter: iteration structure + * + * Returns the length that the operation applies to for the current iteration. + */ +static inline u64 iomap_length(const struct iomap_iter *iter) +{ + return iomap_length_trim(iter, iter->pos, iter->len); +} + +/** + * iomap_iter_advance_full - advance by the full length of current map + */ +static inline int iomap_iter_advance_full(struct iomap_iter *iter) +{ + u64 length = iomap_length(iter); + + return iomap_iter_advance(iter, &length); } /** @@ -306,12 +347,11 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, const struct iomap_ops *ops); + bool *did_zero, const struct iomap_ops *ops, void *private); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops); -vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, - const struct iomap_ops *ops); - + const struct iomap_ops *ops, void *private); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, + void *private); typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, @@ -328,16 +368,42 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops); /* + * Flags for iomap_ioend->io_flags. + */ +/* shared COW extent */ +#define IOMAP_IOEND_SHARED (1U << 0) +/* unwritten extent */ +#define IOMAP_IOEND_UNWRITTEN (1U << 1) +/* don't merge into previous ioend */ +#define IOMAP_IOEND_BOUNDARY (1U << 2) +/* is direct I/O */ +#define IOMAP_IOEND_DIRECT (1U << 3) + +/* + * Flags that if set on either ioend prevent the merge of two ioends. + * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way) + */ +#define IOMAP_IOEND_NOMERGE_FLAGS \ + (IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT) + +/* * Structure for writeback I/O completions. + * + * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io + * for direct I/O) can split a bio generated by iomap. In that case the parent + * ioend it was split from is recorded in ioend->io_parent. */ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ - u16 io_type; - u16 io_flags; /* IOMAP_F_* */ + u16 io_flags; /* IOMAP_IOEND_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of data within eof */ + size_t io_size; /* size of the extent */ + atomic_t io_remaining; /* completetion defer count */ + int io_error; /* stashed away status */ + struct iomap_ioend *io_parent; /* parent for completions */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ + void *io_private; /* file system private data */ struct bio io_bio; /* MUST BE LAST! */ }; @@ -362,12 +428,14 @@ struct iomap_writeback_ops { loff_t offset, unsigned len); /* - * Optional, allows the file systems to perform actions just before - * submitting the bio and/or override the bio end_io handler for complex - * operations like copy on write extent manipulation or unwritten extent - * conversions. + * Optional, allows the file systems to hook into bio submission, + * including overriding the bi_end_io handler. + * + * Returns 0 if the bio was successfully submitted, or a negative + * error code if status was non-zero or another error happened and + * the bio could not be submitted. */ - int (*prepare_ioend)(struct iomap_ioend *ioend, int status); + int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status); /* * Optional, allows the file system to discard state on a page where @@ -383,6 +451,10 @@ struct iomap_writepage_ctx { u32 nr_folios; /* folios added to the ioend */ }; +struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, + loff_t file_offset, u16 ioend_flags); +struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend, + unsigned int max_len, bool is_append); void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); @@ -454,4 +526,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, # define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO) #endif /* CONFIG_SWAP */ +extern struct bio_set iomap_ioend_bioset; + #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 38c65e92ecd0..cf8c16ba04a0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -44,6 +44,8 @@ struct iommu_dma_cookie; struct iommu_fault_param; struct iommufd_ctx; struct iommufd_viommu; +struct msi_desc; +struct msi_msg; #define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ #define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ @@ -216,8 +218,16 @@ struct iommu_domain { struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; int (*iopf_handler)(struct iopf_group *group); - void *fault_data; - union { + +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr); +#endif + + union { /* Pointer usable by owner of the domain */ + struct iommufd_hw_pagetable *iommufd_hwpt; /* iommufd */ + }; + union { /* Fault handler */ struct { iommu_fault_handler_t handler; void *handler_token; @@ -234,6 +244,16 @@ struct iommu_domain { }; }; +static inline void iommu_domain_set_sw_msi( + struct iommu_domain *domain, + int (*sw_msi)(struct iommu_domain *domain, struct msi_desc *desc, + phys_addr_t msi_addr)) +{ +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) + domain->sw_msi = sw_msi; +#endif +} + static inline bool iommu_is_dma_domain(struct iommu_domain *domain) { return domain->type & __IOMMU_DOMAIN_DMA_API; @@ -1079,7 +1099,6 @@ struct iommu_mm_data { }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode); -void iommu_fwspec_free(struct device *dev); int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids); static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) @@ -1390,10 +1409,6 @@ static inline int iommu_fwspec_init(struct device *dev, return -ENODEV; } -static inline void iommu_fwspec_free(struct device *dev) -{ -} - static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) { @@ -1470,6 +1485,18 @@ static inline ioasid_t iommu_alloc_global_pasid(struct device *dev) static inline void iommu_free_global_pasid(ioasid_t pasid) {} #endif /* CONFIG_IOMMU_API */ +#ifdef CONFIG_IRQ_MSI_IOMMU +#ifdef CONFIG_IOMMU_API +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); +#else +static inline int iommu_dma_prepare_msi(struct msi_desc *desc, + phys_addr_t msi_addr) +{ + return 0; +} +#endif /* CONFIG_IOMMU_API */ +#endif /* CONFIG_IRQ_MSI_IOMMU */ + #if IS_ENABLED(CONFIG_LOCKDEP) && IS_ENABLED(CONFIG_IOMMU_API) void iommu_group_mutex_assert(struct device *dev); #else @@ -1503,32 +1530,12 @@ static inline void iommu_debugfs_setup(void) {} #endif #ifdef CONFIG_IOMMU_DMA -#include <linux/msi.h> - int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); - -int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); -void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); - #else /* CONFIG_IOMMU_DMA */ - -struct msi_desc; -struct msi_msg; - static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) { return -ENODEV; } - -static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) -{ - return 0; -} - -static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg) -{ -} - #endif /* CONFIG_IOMMU_DMA */ /* diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a6e2aadbb91b..5aeeed22f35b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -207,6 +207,7 @@ struct inet6_cork { struct ipv6_txoptions *opt; u8 hop_limit; u8 tclass; + u8 dontfrag:1; }; /* struct ipv6_pinfo - ipv6 private area */ diff --git a/include/linux/irq.h b/include/linux/irq.h index 8daa17f0107a..dd5df1e2d032 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -486,6 +486,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @ipi_send_mask: send an IPI to destination cpus in cpumask * @irq_nmi_setup: function called from core code before enabling an NMI * @irq_nmi_teardown: function called from core code after disabling an NMI + * @irq_force_complete_move: optional function to force complete pending irq move * @flags: chip specific flags */ struct irq_chip { @@ -537,6 +538,8 @@ struct irq_chip { int (*irq_nmi_setup)(struct irq_data *data); void (*irq_nmi_teardown)(struct irq_data *data); + void (*irq_force_complete_move)(struct irq_data *data); + unsigned long flags; }; @@ -612,6 +615,7 @@ extern int irq_affinity_online_cpu(unsigned int cpu); #endif #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ) +bool irq_can_move_in_process_context(struct irq_data *data); void __irq_move_irq(struct irq_data *data); static inline void irq_move_irq(struct irq_data *data) { @@ -619,11 +623,10 @@ static inline void irq_move_irq(struct irq_data *data) __irq_move_irq(data); } void irq_move_masked_irq(struct irq_data *data); -void irq_force_complete_move(struct irq_desc *desc); #else +static inline bool irq_can_move_in_process_context(struct irq_data *data) { return true; } static inline void irq_move_irq(struct irq_data *data) { } static inline void irq_move_masked_irq(struct irq_data *data) { } -static inline void irq_force_complete_move(struct irq_desc *desc) { } #endif extern int no_irq_affinity; diff --git a/include/linux/irqchip/irq-davinci-cp-intc.h b/include/linux/irqchip/irq-davinci-cp-intc.h deleted file mode 100644 index 8d71ed5b5a61..000000000000 --- a/include/linux/irqchip/irq-davinci-cp-intc.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2019 Texas Instruments - */ - -#ifndef _LINUX_IRQ_DAVINCI_CP_INTC_ -#define _LINUX_IRQ_DAVINCI_CP_INTC_ - -#include <linux/ioport.h> - -/** - * struct davinci_cp_intc_config - configuration data for davinci-cp-intc - * driver. - * - * @reg: register range to map - * @num_irqs: number of HW interrupts supported by the controller - */ -struct davinci_cp_intc_config { - struct resource reg; - unsigned int num_irqs; -}; - -int davinci_cp_intc_init(const struct davinci_cp_intc_config *config); - -#endif /* _LINUX_IRQ_DAVINCI_CP_INTC_ */ diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index e432b6a12a32..5126482515cb 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -281,6 +281,8 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) void irq_domain_free_fwnode(struct fwnode_handle *fwnode); +DEFINE_FREE(irq_domain_free_fwnode, struct fwnode_handle *, if (_T) irq_domain_free_fwnode(_T)) + struct irq_domain_chip_generic_info; /** @@ -350,13 +352,13 @@ struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, irq_hw_number_t first_hwirq, const struct irq_domain_ops *ops, void *host_data); -extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, - enum irq_domain_bus_token bus_token); -extern void irq_set_default_host(struct irq_domain *host); -extern struct irq_domain *irq_get_default_host(void); -extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, - irq_hw_number_t hwirq, int node, - const struct irq_affinity_desc *affinity); +struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token); +void irq_set_default_host(struct irq_domain *host); +struct irq_domain *irq_get_default_host(void); +int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, + irq_hw_number_t hwirq, int node, + const struct irq_affinity_desc *affinity); static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) { @@ -370,8 +372,8 @@ static inline bool is_fwnode_irqchip(const struct fwnode_handle *fwnode) return fwnode && fwnode->ops == &irqchip_fwnode_ops; } -extern void irq_domain_update_bus_token(struct irq_domain *domain, - enum irq_domain_bus_token bus_token); +void irq_domain_update_bus_token(struct irq_domain *domain, + enum irq_domain_bus_token bus_token); static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, @@ -454,7 +456,7 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod return IS_ERR(d) ? NULL : d; } -extern unsigned int irq_create_direct_mapping(struct irq_domain *host); +unsigned int irq_create_direct_mapping(struct irq_domain *host); #endif static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, @@ -507,19 +509,19 @@ static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fw return IS_ERR(d) ? NULL : d; } -extern void irq_domain_remove(struct irq_domain *host); +void irq_domain_remove(struct irq_domain *host); -extern int irq_domain_associate(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq); -extern void irq_domain_associate_many(struct irq_domain *domain, - unsigned int irq_base, - irq_hw_number_t hwirq_base, int count); +int irq_domain_associate(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq); +void irq_domain_associate_many(struct irq_domain *domain, + unsigned int irq_base, + irq_hw_number_t hwirq_base, int count); -extern unsigned int irq_create_mapping_affinity(struct irq_domain *host, - irq_hw_number_t hwirq, - const struct irq_affinity_desc *affinity); -extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); -extern void irq_dispose_mapping(unsigned int virq); +unsigned int irq_create_mapping_affinity(struct irq_domain *host, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity); +unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec); +void irq_dispose_mapping(unsigned int virq); static inline unsigned int irq_create_mapping(struct irq_domain *host, irq_hw_number_t hwirq) @@ -527,9 +529,9 @@ static inline unsigned int irq_create_mapping(struct irq_domain *host, return irq_create_mapping_affinity(host, hwirq, NULL); } -extern struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, - irq_hw_number_t hwirq, - unsigned int *irq); +struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq, + unsigned int *irq); static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) @@ -587,19 +589,21 @@ int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest); int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest); /* V2 interfaces to support hierarchy IRQ domains. */ -extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, - unsigned int virq); -extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, - const struct irq_chip *chip, - void *chip_data, irq_flow_handler_t handler, - void *handler_data, const char *handler_name); -extern void irq_domain_reset_irq_data(struct irq_data *irq_data); +struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq); +void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, + const struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name); +void irq_domain_reset_irq_data(struct irq_data *irq_data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY -extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, - unsigned int flags, unsigned int size, - struct fwnode_handle *fwnode, - const struct irq_domain_ops *ops, void *host_data); +struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, + unsigned int flags, + unsigned int size, + struct fwnode_handle *fwnode, + const struct irq_domain_ops *ops, + void *host_data); static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, unsigned int flags, @@ -613,13 +617,13 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par ops, host_data); } -extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, - unsigned int nr_irqs, int node, void *arg, - bool realloc, - const struct irq_affinity_desc *affinity); -extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); -extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early); -extern void irq_domain_deactivate_irq(struct irq_data *irq_data); +int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, + const struct irq_affinity_desc *affinity); +void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); +int irq_domain_activate_irq(struct irq_data *irq_data, bool early); +void irq_domain_deactivate_irq(struct irq_data *irq_data); static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs, int node, void *arg) @@ -628,32 +632,29 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, NULL); } -extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, - unsigned int irq_base, - unsigned int nr_irqs, void *arg); -extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, - unsigned int virq, - irq_hw_number_t hwirq, - const struct irq_chip *chip, - void *chip_data); -extern void irq_domain_free_irqs_common(struct irq_domain *domain, - unsigned int virq, - unsigned int nr_irqs); -extern void irq_domain_free_irqs_top(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs); - -extern int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg); -extern int irq_domain_pop_irq(struct irq_domain *domain, int virq); - -extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain, - unsigned int irq_base, - unsigned int nr_irqs, void *arg); - -extern void irq_domain_free_irqs_parent(struct irq_domain *domain, - unsigned int irq_base, - unsigned int nr_irqs); - -extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain, +int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, + unsigned int virq, + irq_hw_number_t hwirq, + const struct irq_chip *chip, + void *chip_data); +void irq_domain_free_irqs_common(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs); +void irq_domain_free_irqs_top(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs); + +int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg); +int irq_domain_pop_irq(struct irq_domain *domain, int virq); + +int irq_domain_alloc_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs, void *arg); + +void irq_domain_free_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs); + +int irq_domain_disconnect_hierarchy(struct irq_domain *domain, unsigned int virq); static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f0e9f8eda7a3..c840431eadda 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -68,8 +68,6 @@ extern note_buf_t __percpu *crash_notes; #define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE #endif -#define KEXEC_CORE_NOTE_NAME CRASH_CORE_NOTE_NAME - /* * This structure is used to hold the arguments that are used when loading * kernel binaries. diff --git a/include/linux/key.h b/include/linux/key.h index 074dca3222b9..ba05de8579ec 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -236,6 +236,7 @@ struct key { #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ +#define KEY_FLAG_FINAL_PUT 10 /* set if final put has happened on key */ /* the key type and key description string * - the desc is used to match a key against search criteria diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h index 7fcf29a4e0de..6ea897222af1 100644 --- a/include/linux/kstrtox.h +++ b/include/linux/kstrtox.h @@ -143,6 +143,7 @@ static inline int __must_check kstrtos32_from_user(const char __user *s, size_t */ extern unsigned long simple_strtoul(const char *,char **,unsigned int); +extern unsigned long simple_strntoul(const char *,char **,unsigned int,size_t); extern long simple_strtol(const char *,char **,unsigned int); extern unsigned long long simple_strtoull(const char *,char **,unsigned int); extern long long simple_strtoll(const char *,char **,unsigned int); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f34f4cfaa513..5438a1b446a6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -267,6 +267,7 @@ struct kvm_gfn_range { union kvm_mmu_notifier_arg arg; enum kvm_gfn_range_filter attr_filter; bool may_block; + bool lockless; }; 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); @@ -1746,7 +1747,6 @@ static inline void kvm_unregister_perf_callbacks(void) {} int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index e13d2f947b51..7283bc4cf413 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -5,7 +5,7 @@ * * Author : Etienne BASSET <etienne.basset@ensta.org> * - * All credits to : Stephen Smalley, <sds@tycho.nsa.gov> + * All credits to : Stephen Smalley * All BUGS to : Etienne BASSET <etienne.basset@ensta.org> */ #ifndef _LSM_COMMON_LOGGING_ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index e2f1ce37c41e..2bf909fa3394 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -445,7 +445,7 @@ LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) #ifdef CONFIG_PERF_EVENTS -LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) +LSM_HOOK(int, 0, perf_event_open, int type) LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) @@ -455,6 +455,7 @@ LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) +LSM_HOOK(int, 0, uring_allowed, void) #endif /* CONFIG_IO_URING */ LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void) diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index ae4526389261..07584c5e36fb 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -26,11 +26,34 @@ */ #define __sme_set(x) ((x) | sme_me_mask) #define __sme_clr(x) ((x) & ~sme_me_mask) + +#define dma_addr_encrypted(x) __sme_set(x) +#define dma_addr_canonical(x) __sme_clr(x) + #else #define __sme_set(x) (x) #define __sme_clr(x) (x) #endif +/* + * dma_addr_encrypted() and dma_addr_unencrypted() are for converting a given DMA + * address to the respective type of addressing. + * + * dma_addr_canonical() is used to reverse any conversions for encrypted/decrypted + * back to the canonical address. + */ +#ifndef dma_addr_encrypted +#define dma_addr_encrypted(x) (x) +#endif + +#ifndef dma_addr_unencrypted +#define dma_addr_unencrypted(x) (x) +#endif + +#ifndef dma_addr_canonical +#define dma_addr_canonical(x) (x) +#endif + #endif /* __ASSEMBLY__ */ #endif /* __MEM_ENCRYPT_H__ */ diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index 49eef10c8e59..4bf261d41a6d 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -60,7 +60,6 @@ struct misc_cg { struct misc_res res[MISC_CG_RES_TYPES]; }; -u64 misc_cg_res_total_usage(enum misc_res_type type); int misc_cg_set_capacity(enum misc_res_type type, u64 capacity); int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount); void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, u64 amount); @@ -104,11 +103,6 @@ static inline void put_misc_cg(struct misc_cg *cg) #else /* !CONFIG_CGROUP_MISC */ -static inline u64 misc_cg_res_total_usage(enum misc_res_type type) -{ - return 0; -} - static inline int misc_cg_set_capacity(enum misc_res_type type, u64 capacity) { return 0; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 27f42f713c89..f016263e1fcf 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1135,7 +1135,7 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, @@ -1415,7 +1415,6 @@ int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port, bool *vlan_offload_disabled); void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, struct _rule_hw *eth_header); -int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx); int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx); int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0c48b20f818a..904804e995aa 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -538,6 +538,7 @@ struct mlx5_cmd_layout { }; enum mlx5_rfr_severity_bit_offsets { + MLX5_CRR_BIT_OFFSET = 0x6, MLX5_RFR_BIT_OFFSET = 0x7, }; @@ -1250,6 +1251,7 @@ enum mlx5_cap_type { MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, MLX5_CAP_ADV_VIRTUALIZATION = 0x26, + MLX5_CAP_ADV_RDMA = 0x28, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1344,6 +1346,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap) +#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) \ + MLX5_CAP_ADV_RDMA(mdev, rdma_transport_rx_flow_table_properties.cap) + +#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) \ + MLX5_CAP_ADV_RDMA(mdev, rdma_transport_tx_flow_table_properties.cap) + #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) @@ -1383,6 +1391,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(adv_virtualization_cap, \ mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) +#define MLX5_CAP_ADV_RDMA(mdev, cap) \ + MLX5_GET(adv_rdma_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_RDMA]->cur, cap) + #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) @@ -1505,6 +1517,7 @@ enum { MLX5_PHYSICAL_LAYER_COUNTERS_GROUP = 0x12, MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, + MLX5_PHYSICAL_LAYER_RECOVERY_GROUP = 0x1a, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af86097641b0..d1dfbad9a447 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -54,7 +54,6 @@ #include <linux/mlx5/doorbell.h> #include <linux/mlx5/eq.h> #include <linux/timecounter.h> -#include <linux/ptp_clock_kernel.h> #include <net/devlink.h> #define MLX5_ADEV_NAME "mlx5_core" @@ -305,6 +304,8 @@ struct mlx5_cmd { struct semaphore sem; struct semaphore pages_sem; struct semaphore throttle_sem; + struct semaphore unprivileged_sem; + struct xarray privileged_uids; } vars; enum mlx5_cmdif_state state; void *cmd_alloc_buf; @@ -679,33 +680,8 @@ struct mlx5_rsvd_gids { struct ida ida; }; -#define MAX_PIN_NUM 8 -struct mlx5_pps { - u8 pin_caps[MAX_PIN_NUM]; - struct work_struct out_work; - u64 start[MAX_PIN_NUM]; - u8 enabled; - u64 min_npps_period; - u64 min_out_pulse_duration_ns; -}; - -struct mlx5_timer { - struct cyclecounter cycles; - struct timecounter tc; - u32 nominal_c_mult; - unsigned long overflow_period; -}; - -struct mlx5_clock { - struct mlx5_nb pps_nb; - seqlock_t lock; - struct hwtstamp_config hwtstamp_config; - struct ptp_clock *ptp; - struct ptp_clock_info ptp_info; - struct mlx5_pps pps_info; - struct mlx5_timer timer; -}; - +struct mlx5_clock; +struct mlx5_clock_dev_state; struct mlx5_dm; struct mlx5_fw_tracer; struct mlx5_vxlan; @@ -789,7 +765,8 @@ struct mlx5_core_dev { #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; #endif - struct mlx5_clock clock; + struct mlx5_clock *clock; + struct mlx5_clock_dev_state *clock_state; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; struct mlx5_rsc_dump *rsc_dump; @@ -989,6 +966,8 @@ struct mlx5_async_work { mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ u16 op_mod; /* cmd op_mod */ + u8 throttle_locked:1; + u8 unpriv_locked:1; void *out; /* pointer to the cmd output buffer */ }; @@ -1019,6 +998,8 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); +int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid); +void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index df73a2ccc9af..67256e776566 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -147,6 +147,8 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, /* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */ #define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0) +#define ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK \ + GENMASK(31 - ESW_RESERVED_BITS, ESW_ZONE_ID_BITS) u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 2a69d9d71276..939e58c2f386 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -40,6 +40,9 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) +#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 0 +#define MLX5_FS_MAX_POOL_SIZE BIT(30) + enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_NONE, MLX5_FLOW_DESTINATION_TYPE_VPORT, @@ -108,6 +111,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC, MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC, + MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX, + MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX, }; enum { @@ -192,9 +197,9 @@ struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); struct mlx5_flow_namespace * -mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev, - enum mlx5_flow_namespace_type type, - int vport); +mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type, + int vport_idx); struct mlx5_flow_table_attr { int prio; @@ -202,6 +207,7 @@ struct mlx5_flow_table_attr { u32 level; u32 flags; u16 uid; + u16 vport; struct mlx5_flow_table *next_ft; struct { @@ -238,6 +244,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); struct mlx5_exe_aso { u32 object_id; + int base_id; u8 type; u8 return_reg_id; union { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4f3716e124c9..2c09df4ee574 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1570,6 +1570,8 @@ enum { enum { MLX5_UCTX_CAP_RAW_TX = 1UL << 0, MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, + MLX5_UCTX_CAP_RDMA_CTRL = 1UL << 3, + MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA = 1UL << 4, }; #define MLX5_FC_BULK_SIZE_FACTOR 128 @@ -1991,7 +1993,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_options[0x8]; u8 reserved_at_568[0x3]; u8 max_geneve_tlv_option_data_len[0x5]; - u8 reserved_at_570[0x9]; + u8 reserved_at_570[0x1]; + u8 adv_rdma[0x1]; + u8 reserved_at_572[0x7]; u8 adv_virtualization[0x1]; u8 reserved_at_57a[0x6]; @@ -2140,7 +2144,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 log_min_mkey_entity_size[0x5]; u8 reserved_at_1b0[0x10]; - u8 reserved_at_1c0[0x60]; + u8 general_obj_types_127_64[0x40]; + u8 reserved_at_200[0x20]; u8 reserved_at_220[0x1]; u8 sw_vhca_id_valid[0x1]; @@ -2640,6 +2645,12 @@ struct mlx5_ifc_field_select_802_1qau_rp_bits { u8 field_select_8021qaurp[0x20]; }; +struct mlx5_ifc_phys_layer_recovery_cntrs_bits { + u8 total_successful_recovery_events[0x20]; + + u8 reserved_at_20[0x7a0]; +}; + struct mlx5_ifc_phys_layer_cntrs_bits { u8 time_since_last_clear_high[0x20]; @@ -4841,6 +4852,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; + struct mlx5_ifc_phys_layer_recovery_cntrs_bits phys_layer_recovery_cntrs; u8 reserved_at_0[0x7c0]; }; @@ -10579,7 +10591,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x1d]; + u8 reserved_at_0[0x10]; + u8 ppcnt_recovery_counters[0x1]; + u8 reserved_at_11[0xc]; u8 fec_200G_per_lane_in_pplm[0x1]; u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; @@ -11119,6 +11133,7 @@ enum { MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR = 0x12, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR = 0x13, }; struct mlx5_ifc_initial_seg_bits { @@ -12494,12 +12509,17 @@ enum { }; enum { + MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL = BIT_ULL(0x13), +}; + +enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47, + MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL = 0x53, MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15, }; @@ -13067,6 +13087,44 @@ struct mlx5_ifc_load_vhca_state_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_adv_rdma_cap_bits { + u8 rdma_transport_manager[0x1]; + u8 rdma_transport_manager_other_eswitch[0x1]; + u8 reserved_at_2[0x1e]; + + u8 rcx_type[0x8]; + u8 reserved_at_28[0x2]; + u8 ps_entry_log_max_value[0x6]; + u8 reserved_at_30[0x6]; + u8 qp_max_ps_num_entry[0xa]; + + u8 mp_max_num_queues[0x8]; + u8 ps_user_context_max_log_size[0x8]; + u8 message_based_qp_and_striding_wq[0x8]; + u8 reserved_at_58[0x8]; + + u8 max_receive_send_message_size_stride[0x10]; + u8 reserved_at_70[0x10]; + + u8 max_receive_send_message_size_byte[0x20]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_rx_flow_table_properties; + + struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_tx_flow_table_properties; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_bitmask_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_bitmask_support_2; + + u8 reserved_at_800[0x3800]; +}; + struct mlx5_ifc_adv_virtualization_cap_bits { u8 reserved_at_0[0x3]; u8 pg_track_log_max_num[0x5]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index e68d42b8ce65..58770b86f793 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -61,15 +61,6 @@ enum mlx5_an_status { #define MLX5_EEPROM_PAGE_LENGTH 256 #define MLX5_EEPROM_HIGH_PAGE_LENGTH 128 -struct mlx5_module_eeprom_query_params { - u16 size; - u16 offset; - u16 i2c_address; - u32 page; - u32 bank; - u32 module_number; -}; - enum mlx5e_link_mode { MLX5E_1000BASE_CX_SGMII = 0, MLX5E_1000BASE_KX = 1, @@ -115,9 +106,12 @@ enum mlx5e_ext_link_mode { MLX5E_100GAUI_1_100GBASE_CR_KR = 11, MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, MLX5E_200GAUI_2_200GBASE_CR2_KR2 = 13, + MLX5E_200GAUI_1_200GBASE_CR1_KR1 = 14, MLX5E_400GAUI_8_400GBASE_CR8 = 15, MLX5E_400GAUI_4_400GBASE_CR4_KR4 = 16, + MLX5E_400GAUI_2_400GBASE_CR2_KR2 = 17, MLX5E_800GAUI_8_800GBASE_CR8_KR8 = 19, + MLX5E_800GAUI_4_800GBASE_CR4_KR4 = 20, MLX5E_EXT_LINK_MODES_NUMBER, }; @@ -142,12 +136,6 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; -struct mlx5_port_eth_proto { - u32 cap; - u32 admin; - u32 oper; -}; - #define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ @@ -160,14 +148,7 @@ int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper, u16 *proto_oper, u8 local_port, u8 plane_index); -void mlx5_toggle_port_link(struct mlx5_core_dev *dev); -int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status *status); -int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration); - -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); + void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port); @@ -175,65 +156,4 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, u8 *vl_hw_cap, u8 local_port); -int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); -int mlx5_query_port_pause(struct mlx5_core_dev *dev, - u32 *rx_pause, u32 *tx_pause); - -int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); -int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, - u8 *pfc_en_rx); - -int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev, - u16 stall_critical_watermark, - u16 stall_minor_watermark); -int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev, - u16 *stall_critical_watermark, u16 *stall_minor_watermark); - -int mlx5_max_tc(struct mlx5_core_dev *mdev); - -int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); -int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev, - u8 prio, u8 *tc); -int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); -int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev, - u8 tc, u8 *tc_group); -int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); -int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev, - u8 tc, u8 *bw_pct); -int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, - u8 *max_bw_value, - u8 *max_bw_unit); -int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, - u8 *max_bw_value, - u8 *max_bw_unit); -int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode); -int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode); - -int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen); -int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen); -int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable); -void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported, - bool *enabled); -int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, - u16 offset, u16 size, u8 *data); -int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev, - struct mlx5_module_eeprom_query_params *params, u8 *data); - -int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); -int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); - -int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); -int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); -int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); -int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); - -int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, - struct mlx5_port_eth_proto *eproto); -bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev); -u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, - bool force_legacy); -u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, - bool force_legacy); -int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); - #endif /* __MLX5_PORT_H__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f80baddacc5..386c9a78cf9e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -40,8 +40,6 @@ struct user_struct; struct pt_regs; struct folio_batch; -extern int sysctl_page_lock_unfairness; - void mm_core_init(void); void init_mm_internals(void); @@ -78,8 +76,6 @@ static inline void totalram_pages_add(long count) } extern void * high_memory; -extern int page_cluster; -extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; @@ -209,17 +205,6 @@ extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; -extern int sysctl_overcommit_memory; -extern int sysctl_overcommit_ratio; -extern unsigned long sysctl_overcommit_kbytes; - -int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) #define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) @@ -2555,7 +2540,7 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -struct page *get_dump_page(unsigned long addr); +struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); bool folio_mark_dirty_lock(struct folio *folio); @@ -3809,12 +3794,6 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); -#ifdef CONFIG_SYSCTL -extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, - loff_t *); -#endif - void drop_slab(void); #ifndef CONFIG_MMU @@ -4086,8 +4065,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif -extern int sysctl_nr_trim_pages; - #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, diff --git a/include/linux/mman.h b/include/linux/mman.h index a842783ffa62..bce214fece16 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -59,8 +59,6 @@ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; -extern int sysctl_overcommit_ratio; -extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 274a2767ea49..1ed7b0d1e4f9 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -22,7 +22,6 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, unsigned int debounce); int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config); -void mmc_gpio_set_cd_isr(struct mmc_host *host, irq_handler_t isr); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on); void mmc_gpiod_request_cd_irq(struct mmc_host *host); bool mmc_can_gpio_cd(struct mmc_host *host); diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index b1b219bc3422..e71a6070a8f8 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -25,6 +25,11 @@ static_assert(sizeof(vfsgid_t) == sizeof(kgid_t)); static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val)); static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val)); +static inline bool is_valid_mnt_idmap(const struct mnt_idmap *idmap) +{ + return idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap; +} + #ifdef CONFIG_MULTIUSER static inline uid_t __vfsuid_val(vfsuid_t uid) { diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index d67614f7b7f1..bd7e60c0b72f 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -692,6 +692,7 @@ struct x86_cpu_id { __u16 feature; /* bit index */ /* Solely for kernel-internal use: DO NOT EXPORT to userspace! */ __u16 flags; + __u8 type; kernel_ulong_t driver_data; }; @@ -703,6 +704,7 @@ struct x86_cpu_id { #define X86_STEP_MIN 0 #define X86_STEP_MAX 0xf #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */ +#define X86_CPU_TYPE_ANY 0 /* * Generic table type for matching CPU features. diff --git a/include/linux/module.h b/include/linux/module.h index 30e5b19bafa9..9937e71a3b5b 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -370,7 +370,6 @@ enum mod_mem_type { struct module_memory { void *base; - void *rw_copy; bool is_rox; unsigned int size; @@ -772,16 +771,6 @@ static inline bool is_livepatch_module(struct module *mod) void set_module_sig_enforced(void); -void *__module_writable_address(struct module *mod, void *loc); - -static inline void *module_writable_address(struct module *mod, void *loc) -{ - if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod || - mod->state != MODULE_STATE_UNFORMED) - return loc; - return __module_writable_address(mod, loc); -} - #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -889,11 +878,6 @@ static inline bool module_is_coming(struct module *mod) { return false; } - -static inline void *module_writable_address(struct module *mod, void *loc) -{ - return loc; -} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 1f5507ba5a12..e395461d59e5 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); -int module_post_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *mod); - #ifdef CONFIG_MODULES void flush_module_init_free_work(void); #else diff --git a/include/linux/msi.h b/include/linux/msi.h index b10093c4d00e..e71c991d7f61 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -73,7 +73,6 @@ struct msi_msg { }; }; -extern int pci_msi_ignore_mask; /* Helper functions */ struct msi_desc; struct pci_dev; @@ -81,7 +80,6 @@ struct device_attribute; struct irq_domain; struct irq_affinity_desc; -void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); #else @@ -166,6 +164,10 @@ struct msi_desc_data { * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor + * @iommu_msi_iova: Optional shifted IOVA from the IOMMU to override the msi_addr. + * Only used if iommu_msi_shift != 0 + * @iommu_msi_shift: Indicates how many bits of the original address should be + * preserved when using iommu_msi_iova. * @sysfs_attr: Pointer to sysfs device attribute * * @write_msi_msg: Callback that may be called when the MSI message @@ -184,7 +186,8 @@ struct msi_desc { struct msi_msg msg; struct irq_affinity_desc *affinity; #ifdef CONFIG_IRQ_MSI_IOMMU - const void *iommu_cookie; + u64 iommu_msi_iova : 58; + u64 iommu_msi_shift : 6; #endif #ifdef CONFIG_SYSFS struct device_attribute *sysfs_attrs; @@ -225,8 +228,11 @@ struct msi_dev_domain { int msi_setup_device_data(struct device *dev); -void msi_lock_descs(struct device *dev); -void msi_unlock_descs(struct device *dev); +void __msi_lock_descs(struct device *dev); +void __msi_unlock_descs(struct device *dev); + +DEFINE_LOCK_GUARD_1(msi_descs_lock, struct device, __msi_lock_descs(_T->lock), + __msi_unlock_descs(_T->lock)); struct msi_desc *msi_domain_first_desc(struct device *dev, unsigned int domid, enum msi_desc_filter filter); @@ -285,28 +291,42 @@ struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid, #define msi_desc_to_dev(desc) ((desc)->dev) -#ifdef CONFIG_IRQ_MSI_IOMMU -static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) -{ - return desc->iommu_cookie; -} - -static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) -{ - desc->iommu_cookie = iommu_cookie; -} -#else -static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) +static inline void msi_desc_set_iommu_msi_iova(struct msi_desc *desc, u64 msi_iova, + unsigned int msi_shift) { - return NULL; +#ifdef CONFIG_IRQ_MSI_IOMMU + desc->iommu_msi_iova = msi_iova >> msi_shift; + desc->iommu_msi_shift = msi_shift; +#endif } -static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, - const void *iommu_cookie) +/** + * msi_msg_set_addr() - Set MSI address in an MSI message + * + * @desc: MSI descriptor that may carry an IOVA base address for MSI via @iommu_msi_iova/shift + * @msg: Target MSI message to set its address_hi and address_lo + * @msi_addr: Physical address to set the MSI message + * + * Notes: + * - Override @msi_addr using the IOVA base address in the @desc if @iommu_msi_shift is set + * - Otherwise, simply set @msi_addr to @msg + */ +static inline void msi_msg_set_addr(struct msi_desc *desc, struct msi_msg *msg, + phys_addr_t msi_addr) { -} +#ifdef CONFIG_IRQ_MSI_IOMMU + if (desc->iommu_msi_shift) { + u64 msi_iova = desc->iommu_msi_iova << desc->iommu_msi_shift; + + msg->address_hi = upper_32_bits(msi_iova); + msg->address_lo = lower_32_bits(msi_iova) | + (msi_addr & ((1 << desc->iommu_msi_shift) - 1)); + return; + } #endif + msg->address_hi = upper_32_bits(msi_addr); + msg->address_lo = lower_32_bits(msi_addr); +} int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, struct msi_desc *init_desc); @@ -556,6 +576,16 @@ enum { MSI_FLAG_PCI_MSIX_ALLOC_DYN = (1 << 20), /* PCI MSIs cannot be steered separately to CPU cores */ MSI_FLAG_NO_AFFINITY = (1 << 21), + /* Inhibit usage of entry masking */ + MSI_FLAG_NO_MASK = (1 << 22), +}; + +/* + * Flags for msi_parent_ops::chip_flags + */ +enum { + MSI_CHIP_FLAG_SET_EOI = (1 << 0), + MSI_CHIP_FLAG_SET_ACK = (1 << 1), }; /** @@ -563,6 +593,8 @@ enum { * * @supported_flags: Required: The supported MSI flags of the parent domain * @required_flags: Optional: The required MSI flags of the parent MSI domain + * @chip_flags: Optional: Select MSI chip callbacks to update with defaults + * in msi_lib_init_dev_msi_info(). * @bus_select_token: Optional: The bus token of the real parent domain for * irq_domain::select() * @bus_select_mask: Optional: A mask of supported BUS_DOMAINs for @@ -575,6 +607,7 @@ enum { struct msi_parent_ops { u32 supported_flags; u32 required_flags; + u32 chip_flags; u32 bus_select_token; u32 bus_select_mask; const char *prefix; @@ -603,8 +636,6 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid); bool msi_match_device_irq_domain(struct device *dev, unsigned int domid, enum irq_domain_bus_token bus_token); -int msi_domain_alloc_irqs_range_locked(struct device *dev, unsigned int domid, - unsigned int first, unsigned int last); int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid, unsigned int first, unsigned int last); int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int nirqs); @@ -613,8 +644,6 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u const struct irq_affinity_desc *affdesc, union msi_instance_cookie *cookie); -void msi_domain_free_irqs_range_locked(struct device *dev, unsigned int domid, - unsigned int first, unsigned int last); void msi_domain_free_irqs_range(struct device *dev, unsigned int domid, unsigned int first, unsigned int last); void msi_domain_free_irqs_all_locked(struct device *dev, unsigned int domid); diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h index 4d9b736ff8b7..cd7172e6c1bb 100644 --- a/include/linux/mtd/nand-qpic-common.h +++ b/include/linux/mtd/nand-qpic-common.h @@ -108,7 +108,7 @@ #define ECC_FORCE_CLK_OPEN BIT(30) /* NAND_DEV_CMD1 bits */ -#define READ_ADDR 0 +#define READ_ADDR_MASK GENMASK(7, 0) /* NAND_DEV_CMD_VLD bits */ #define READ_START_VLD BIT(0) @@ -119,6 +119,7 @@ /* NAND_EBI2_ECC_BUF_CFG bits */ #define NUM_STEPS 0 +#define NUM_STEPS_MASK GENMASK(9, 0) /* NAND_ERASED_CW_DETECT_CFG bits */ #define ERASED_CW_ECC_MASK 1 @@ -139,8 +140,11 @@ /* NAND_READ_LOCATION_n bits */ #define READ_LOCATION_OFFSET 0 +#define READ_LOCATION_OFFSET_MASK GENMASK(9, 0) #define READ_LOCATION_SIZE 16 +#define READ_LOCATION_SIZE_MASK GENMASK(25, 16) #define READ_LOCATION_LAST 31 +#define READ_LOCATION_LAST_MASK BIT(31) /* Version Mask */ #define NAND_VERSION_MAJOR_MASK 0xf0000000 @@ -325,6 +329,10 @@ struct nandc_regs { __le32 read_location_last1; __le32 read_location_last2; __le32 read_location_last3; + __le32 spi_cfg; + __le32 num_addr_cycle; + __le32 busy_wait_cnt; + __le32 flash_feature; __le32 erased_cw_detect_cfg_clr; __le32 erased_cw_detect_cfg_set; @@ -339,6 +347,7 @@ struct nandc_regs { * * @core_clk: controller clock * @aon_clk: another controller clock + * @iomacro_clk: io macro clock * * @regs: a contiguous chunk of memory for DMA register * writes. contains the register values to be @@ -348,6 +357,7 @@ struct nandc_regs { * initialized via DT match data * * @controller: base controller structure + * @qspi: qpic spi structure * @host_list: list containing all the chips attached to the * controller * @@ -392,6 +402,7 @@ struct qcom_nand_controller { const struct qcom_nandc_props *props; struct nand_controller *controller; + struct qpic_spi_nand *qspi; struct list_head host_list; union { diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0e2f228e8b4a..07486168d104 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -21,7 +21,7 @@ struct nand_device; * @oobsize: OOB area size * @pages_per_eraseblock: number of pages per eraseblock * @eraseblocks_per_lun: number of eraseblocks per LUN (Logical Unit Number) - * @max_bad_eraseblocks_per_lun: maximum number of eraseblocks per LUN + * @max_bad_eraseblocks_per_lun: maximum number of bad eraseblocks per LUN * @planes_per_lun: number of planes per LUN * @luns_per_target: number of LUN per target (target is a synonym for die) * @ntargets: total number of targets exposed by the NAND device diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 0da8a1c7740e..1e748958dad4 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -375,6 +375,67 @@ struct spinand_ondie_ecc_conf { }; /** + * struct spinand_otp_layout - structure to describe the SPI NAND OTP area + * @npages: number of pages in the OTP + * @start_page: start page of the user/factory OTP area. + */ +struct spinand_otp_layout { + unsigned int npages; + unsigned int start_page; +}; + +/** + * struct spinand_fact_otp_ops - SPI NAND OTP methods for factory area + * @info: get the OTP area information + * @read: read from the SPI NAND OTP area + */ +struct spinand_fact_otp_ops { + int (*info)(struct spinand_device *spinand, size_t len, + struct otp_info *buf, size_t *retlen); + int (*read)(struct spinand_device *spinand, loff_t from, size_t len, + size_t *retlen, u8 *buf); +}; + +/** + * struct spinand_user_otp_ops - SPI NAND OTP methods for user area + * @info: get the OTP area information + * @lock: lock an OTP region + * @erase: erase an OTP region + * @read: read from the SPI NAND OTP area + * @write: write to the SPI NAND OTP area + */ +struct spinand_user_otp_ops { + int (*info)(struct spinand_device *spinand, size_t len, + struct otp_info *buf, size_t *retlen); + int (*lock)(struct spinand_device *spinand, loff_t from, size_t len); + int (*erase)(struct spinand_device *spinand, loff_t from, size_t len); + int (*read)(struct spinand_device *spinand, loff_t from, size_t len, + size_t *retlen, u8 *buf); + int (*write)(struct spinand_device *spinand, loff_t from, size_t len, + size_t *retlen, const u8 *buf); +}; + +/** + * struct spinand_fact_otp - SPI NAND OTP grouping structure for factory area + * @layout: OTP region layout + * @ops: OTP access ops + */ +struct spinand_fact_otp { + const struct spinand_otp_layout layout; + const struct spinand_fact_otp_ops *ops; +}; + +/** + * struct spinand_user_otp - SPI NAND OTP grouping structure for user area + * @layout: OTP region layout + * @ops: OTP access ops + */ +struct spinand_user_otp { + const struct spinand_otp_layout layout; + const struct spinand_user_otp_ops *ops; +}; + +/** * struct spinand_info - Structure used to describe SPI NAND chips * @model: model name * @devid: device ID @@ -389,6 +450,10 @@ struct spinand_ondie_ecc_conf { * @select_target: function used to select a target/die. Required only for * multi-die chips * @set_cont_read: enable/disable continuous cached reads + * @fact_otp: SPI NAND factory OTP info. + * @user_otp: SPI NAND user OTP info. + * @read_retries: the number of read retry modes supported + * @set_read_retry: enable/disable read retry for data recovery * * Each SPI NAND manufacturer driver should have a spinand_info table * describing all the chips supported by the driver. @@ -409,6 +474,11 @@ struct spinand_info { unsigned int target); int (*set_cont_read)(struct spinand_device *spinand, bool enable); + struct spinand_fact_otp fact_otp; + struct spinand_user_otp user_otp; + unsigned int read_retries; + int (*set_read_retry)(struct spinand_device *spinand, + unsigned int read_retry); }; #define SPINAND_ID(__method, ...) \ @@ -432,10 +502,32 @@ struct spinand_info { } #define SPINAND_SELECT_TARGET(__func) \ - .select_target = __func, + .select_target = __func #define SPINAND_CONT_READ(__set_cont_read) \ - .set_cont_read = __set_cont_read, + .set_cont_read = __set_cont_read + +#define SPINAND_FACT_OTP_INFO(__npages, __start_page, __ops) \ + .fact_otp = { \ + .layout = { \ + .npages = __npages, \ + .start_page = __start_page, \ + }, \ + .ops = __ops, \ + } + +#define SPINAND_USER_OTP_INFO(__npages, __start_page, __ops) \ + .user_otp = { \ + .layout = { \ + .npages = __npages, \ + .start_page = __start_page, \ + }, \ + .ops = __ops, \ + } + +#define SPINAND_READ_RETRY(__read_retries, __set_read_retry) \ + .read_retries = __read_retries, \ + .set_read_retry = __set_read_retry #define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants, \ __flags, ...) \ @@ -487,6 +579,10 @@ struct spinand_dirmap { * actually relevant to enable this feature. * @set_cont_read: Enable/disable the continuous read feature * @priv: manufacturer private data + * @fact_otp: SPI NAND factory OTP info. + * @user_otp: SPI NAND user OTP info. + * @read_retries: the number of read retry modes supported + * @set_read_retry: Enable/disable the read retry feature */ struct spinand_device { struct nand_device base; @@ -519,6 +615,13 @@ struct spinand_device { bool cont_read_possible; int (*set_cont_read)(struct spinand_device *spinand, bool enable); + + const struct spinand_fact_otp *fact_otp; + const struct spinand_user_otp *user_otp; + + unsigned int read_retries; + int (*set_read_retry)(struct spinand_device *spinand, + unsigned int retry_mode); }; /** @@ -588,4 +691,26 @@ int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val); int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val); int spinand_select_target(struct spinand_device *spinand, unsigned int target); +int spinand_wait(struct spinand_device *spinand, unsigned long initial_delay_us, + unsigned long poll_delay_us, u8 *s); + +int spinand_read_page(struct spinand_device *spinand, + const struct nand_page_io_req *req); + +int spinand_write_page(struct spinand_device *spinand, + const struct nand_page_io_req *req); + +size_t spinand_otp_page_size(struct spinand_device *spinand); +size_t spinand_fact_otp_size(struct spinand_device *spinand); +size_t spinand_user_otp_size(struct spinand_device *spinand); + +int spinand_fact_otp_read(struct spinand_device *spinand, loff_t ofs, + size_t len, size_t *retlen, u8 *buf); +int spinand_user_otp_read(struct spinand_device *spinand, loff_t ofs, + size_t len, size_t *retlen, u8 *buf); +int spinand_user_otp_write(struct spinand_device *spinand, loff_t ofs, + size_t len, size_t *retlen, const u8 *buf); + +int spinand_set_mtd_otp_ops(struct spinand_device *spinand); + #endif /* __LINUX_MTD_SPINAND_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 8ec8fed3bce8..e3042176cdf4 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -18,35 +18,36 @@ enum { MAX_NESTED_LINKS = 8 }; enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ -#define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ -#define LOOKUP_DIRECTORY 0x0002 /* require a directory */ -#define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ -#define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ -#define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ -#define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ - -#define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ -#define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ +#define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ +#define LOOKUP_DIRECTORY BIT(1) /* require a directory */ +#define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ +#define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ +#define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ +#define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ +#define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ +#define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ +#define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ +#define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ +#define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ +/* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ -#define LOOKUP_OPEN 0x0100 /* ... in open */ -#define LOOKUP_CREATE 0x0200 /* ... in object creation */ -#define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ -#define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ +#define LOOKUP_OPEN BIT(16) /* ... in open */ +#define LOOKUP_CREATE BIT(17) /* ... in object creation */ +#define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ +#define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ -/* internal use only */ -#define LOOKUP_PARENT 0x0010 +/* 4 spare bits for intent */ /* Scoping flags for lookup. */ -#define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ -#define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ -#define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ -#define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ -#define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ -#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ -#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ +#define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ +#define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ +#define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ +#define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ +#define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) +/* 3 spare bits for scoping */ extern int path_pts(struct path *path); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index 1c1332e4df26..13274c3def66 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -78,6 +78,8 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); +int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry); +void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry); /* Structure representing auxiliary driver tailored information about the core * PCI dev, each auxiliary driver using the IIDC interface will have an diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 11be70a7929f..7a01c518e573 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -53,12 +53,12 @@ enum { NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ NETIF_F_GSO_FRAGLIST_BIT, /* ... Fraglist GSO */ + NETIF_F_GSO_ACCECN_BIT, /* TCP AccECN w/ TSO (no clear CWR) */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_FRAGLIST_BIT, + NETIF_F_GSO_ACCECN_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ - __UNUSED_NETIF_F_37, NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */ @@ -128,6 +128,7 @@ enum { #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) +#define NETIF_F_GSO_ACCECN __NETIF_F(GSO_ACCECN) #define NETIF_F_TSO __NETIF_F(TSO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) @@ -210,7 +211,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ + NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \ NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ab550a89b9bf..fa79145518d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -340,11 +340,27 @@ struct gro_list { }; /* - * size of gro hash buckets, must less than bit number of - * napi_struct::gro_bitmask + * size of gro hash buckets, must be <= the number of bits in + * gro_node::bitmask */ #define GRO_HASH_BUCKETS 8 +/** + * struct gro_node - structure to support Generic Receive Offload + * @bitmask: bitmask to indicate used buckets in @hash + * @hash: hashtable of pending aggregated skbs, separated by flows + * @rx_list: list of pending ``GRO_NORMAL`` skbs + * @rx_count: cached current length of @rx_list + * @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone + */ +struct gro_node { + unsigned long bitmask; + struct gro_list hash[GRO_HASH_BUCKETS]; + struct list_head rx_list; + u32 rx_count; + u32 cached_napi_id; +}; + /* * Structure for per-NAPI config */ @@ -352,6 +368,7 @@ struct napi_config { u64 gro_flush_timeout; u64 irq_suspend_timeout; u32 defer_hard_irqs; + cpumask_t affinity_mask; unsigned int napi_id; }; @@ -370,7 +387,6 @@ struct napi_struct { unsigned long state; int weight; u32 defer_hard_irqs_count; - unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL /* CPU actively polling if netpoll is configured */ @@ -379,11 +395,8 @@ struct napi_struct { /* CPU on which NAPI has been scheduled for processing */ int list_owner; struct net_device *dev; - struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; - struct list_head rx_list; /* Pending GRO_NORMAL skbs */ - int rx_count; /* length of rx_list */ - unsigned int napi_id; /* protected by netdev_lock */ + struct gro_node gro; struct hrtimer timer; /* all fields past this point are write-protected by netdev_lock */ struct task_struct *thread; @@ -391,9 +404,12 @@ struct napi_struct { unsigned long irq_suspend_timeout; u32 defer_hard_irqs; /* control-path-only fields follow */ + u32 napi_id; struct list_head dev_list; struct hlist_node napi_hash_node; int irq; + struct irq_affinity_notify notify; + int napi_rmap_idx; int index; struct napi_config *config; }; @@ -409,6 +425,7 @@ enum { NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ + NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */ }; enum { @@ -422,6 +439,7 @@ enum { NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), + NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER), }; enum gro_result { @@ -658,6 +676,7 @@ struct netdev_queue { struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; + const struct attribute_group **groups; #endif unsigned long tx_maxrate; /* @@ -691,7 +710,7 @@ struct netdev_queue { * slow- / control-path part */ /* NAPI instance for the queue - * Readers and writers must hold RTNL + * "ops protected", see comment about net_device::lock */ struct napi_struct *napi; @@ -1988,12 +2007,21 @@ enum netdev_reg_state { * * @threaded: napi threaded mode is enabled * + * @irq_affinity_auto: driver wants the core to store and re-assign the IRQ + * affinity. Set by netif_enable_irq_affinity(), then + * the driver must create a persistent napi by + * netif_napi_add_config() and finally bind the napi to + * IRQ (via netif_napi_set_irq()). + * + * @rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap. + * Set by calling netif_enable_cpu_rmap(). + * * @see_all_hwtstamp_requests: device wants to see calls to * ndo_hwtstamp_set() for all timestamp requests * regardless of source, even if those aren't * HWTSTAMP_SOURCE_NETDEV * @change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN - * @netns_local: interface can't change network namespaces + * @netns_immutable: interface can't change network namespaces * @fcoe_mtu: device supports maximum FCoE MTU, 2158 bytes * * @net_notifier_list: List of per-net netdev notifier block @@ -2395,11 +2423,13 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; bool proto_down; bool threaded; + bool irq_affinity_auto; + bool rx_cpu_rmap_auto; /* priv_flags_slow, ungrouped to save space */ unsigned long see_all_hwtstamp_requests:1; unsigned long change_proto_down:1; - unsigned long netns_local:1; + unsigned long netns_immutable:1; unsigned long fcoe_mtu:1; struct list_head net_notifier_list; @@ -2456,18 +2486,48 @@ struct net_device { bool up; /** + * @request_ops_lock: request the core to run all @netdev_ops and + * @ethtool_ops under the @lock. + */ + bool request_ops_lock; + + /** * @lock: netdev-scope lock, protects a small selection of fields. * Should always be taken using netdev_lock() / netdev_unlock() helpers. * Drivers are free to use it for other protection. * - * Protects: + * For the drivers that implement shaper or queue API, the scope + * of this lock is expanded to cover most ndo/queue/ethtool/sysfs + * operations. Drivers may opt-in to this behavior by setting + * @request_ops_lock. + * + * @lock protection mixes with rtnl_lock in multiple ways, fields are + * either: + * + * - simply protected by the instance @lock; + * + * - double protected - writers hold both locks, readers hold either; + * + * - ops protected - protected by the lock held around the NDOs + * and other callbacks, that is the instance lock on devices for + * which netdev_need_ops_lock() returns true, otherwise by rtnl_lock; + * + * - double ops protected - always protected by rtnl_lock but for + * devices for which netdev_need_ops_lock() returns true - also + * the instance lock. + * + * Simply protects: * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, * @net_shaper_hierarchy, @reg_state, @threaded * - * Partially protects (writers must hold both @lock and rtnl_lock): + * Double protects: * @up * - * Also protects some fields in struct napi_struct. + * Double ops protects: + * @real_num_rx_queues, @real_num_tx_queues + * + * Also protects some fields in: + * struct napi_struct, struct netdev_queue, struct netdev_rx_queue * * Ordering: take after rtnl_lock. */ @@ -2590,21 +2650,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } -#define netdev_lockdep_set_classes(dev) \ -{ \ - static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_xmit_lock_key; \ - static struct lock_class_key dev_addr_list_lock_key; \ - unsigned int i; \ - \ - (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - lockdep_set_class(&(dev)->addr_list_lock, \ - &dev_addr_list_lock_key); \ - for (i = 0; i < (dev)->num_tx_queues; i++) \ - lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ - &qdisc_xmit_lock_key); \ -} - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, @@ -2710,23 +2755,9 @@ static inline void netdev_unlock(struct net_device *dev) { mutex_unlock(&dev->lock); } +/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */ -static inline void netdev_assert_locked(struct net_device *dev) -{ - lockdep_assert_held(&dev->lock); -} - -static inline void netdev_assert_locked_or_invisible(struct net_device *dev) -{ - if (dev->reg_state == NETREG_REGISTERED || - dev->reg_state == NETREG_UNREGISTERING) - netdev_assert_locked(dev); -} - -static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) -{ - napi->irq = irq; -} +void netif_napi_set_irq_locked(struct napi_struct *napi, int irq); static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) { @@ -2864,6 +2895,9 @@ static inline void netif_napi_del(struct napi_struct *napi) synchronize_net(); } +int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs); +void netif_set_affinity_auto(struct net_device *dev); + struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; @@ -3297,9 +3331,12 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); +int netif_open(struct net_device *dev, struct netlink_ext_ack *extack); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); +void netif_close(struct net_device *dev); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); +void netif_disable_lro(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, @@ -4045,17 +4082,7 @@ static inline bool netif_is_multiqueue(const struct net_device *dev) } int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); - -#ifdef CONFIG_SYSFS int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); -#else -static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxqs) -{ - dev->real_num_rx_queues = rxqs; - return 0; -} -#endif int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq); @@ -4114,8 +4141,14 @@ int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); -void napi_gro_flush(struct napi_struct *napi, bool flush_old); +gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb); + +static inline gro_result_t napi_gro_receive(struct napi_struct *napi, + struct sk_buff *skb) +{ + return gro_receive_skb(&napi->gro, skb); +} + struct sk_buff *napi_get_frags(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); @@ -4141,6 +4174,8 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd); int generic_hwtstamp_get_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg); int generic_hwtstamp_set_lower(struct net_device *dev, @@ -4150,22 +4185,25 @@ int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); +int netif_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); +int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); -int __dev_change_net_namespace(struct net_device *dev, struct net *net, - const char *pat, int new_ifindex); -static inline +int netif_change_net_namespace(struct net_device *dev, struct net *net, + const char *pat, int new_ifindex, + struct netlink_ext_ack *extack); int dev_change_net_namespace(struct net_device *dev, struct net *net, - const char *pat) -{ - return __dev_change_net_namespace(dev, net, pat, 0); -} + const char *pat); int __dev_set_mtu(struct net_device *, int); +int netif_set_mtu(struct net_device *dev, int new_mtu); int dev_set_mtu(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); +int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, @@ -4181,6 +4219,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); @@ -4249,7 +4288,17 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return 0; } -bool dev_nit_active(struct net_device *dev); +bool dev_nit_active_rcu(const struct net_device *dev); +static inline bool dev_nit_active(const struct net_device *dev) +{ + bool ret; + + rcu_read_lock(); + ret = dev_nit_active_rcu(dev); + rcu_read_unlock(); + return ret; +} + void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); static inline void __dev_put(struct net_device *dev) @@ -4923,6 +4972,7 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); +int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); void __netdev_notify_peers(struct net_device *dev); @@ -5241,6 +5291,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_TCP_ACCECN != + (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f91e50a76efd..0477208ed9ff 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -25,7 +25,13 @@ union inet_addr { struct netpoll { struct net_device *dev; netdevice_tracker dev_tracker; + /* + * Either dev_name or dev_mac can be used to specify the local + * interface - dev_name is used if it is a nonempty string, else + * dev_mac is used. + */ char dev_name[IFNAMSIZ]; + u8 dev_mac[ETH_ALEN]; const char *name; union inet_addr local_ip, remote_ip; @@ -33,6 +39,7 @@ struct netpoll { u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; struct sk_buff_head skb_pool; + struct work_struct refill_wq; }; struct netpoll_info { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9155a6ffc370..d66c61cbbd1d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1802,7 +1802,7 @@ struct nfs_rpc_ops { int (*link) (struct inode *, struct inode *, const struct qstr *); int (*symlink) (struct inode *, struct dentry *, struct folio *, unsigned int, struct iattr *); - int (*mkdir) (struct inode *, struct dentry *, struct iattr *); + struct dentry *(*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *); int (*mknod) (struct inode *, struct dentry *, struct iattr *, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a8dfb38c9bb6..e78fa535f61d 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -17,7 +17,6 @@ void lockup_detector_init(void); void lockup_detector_retry_init(void); void lockup_detector_soft_poweroff(void); -void lockup_detector_cleanup(void); extern int watchdog_user_enabled; extern int watchdog_thresh; @@ -37,7 +36,6 @@ extern int sysctl_hardlockup_all_cpu_backtrace; static inline void lockup_detector_init(void) { } static inline void lockup_detector_retry_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } -static inline void lockup_detector_cleanup(void) { } #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -104,12 +102,10 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs); #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); -extern void hardlockup_detector_perf_cleanup(void); extern void hardlockup_config_perf_event(const char *str); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } -static inline void hardlockup_detector_perf_cleanup(void) { } static inline void hardlockup_config_perf_event(const char *str) { } #endif diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 9fd7a0ce9c1a..f0ac0633366b 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -94,7 +94,6 @@ #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> -#include <linux/numa.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; @@ -191,6 +190,13 @@ static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *s bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } +#define nodes_copy(dst, src) __nodes_copy(&(dst), &(src), MAX_NUMNODES) +static __always_inline void __nodes_copy(nodemask_t *dstp, + const nodemask_t *srcp, unsigned int nbits) +{ + bitmap_copy(dstp->bits, srcp->bits, nbits); +} + #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h index 6b28d97ea6ed..f850a48742f1 100644 --- a/include/linux/nodemask_types.h +++ b/include/linux/nodemask_types.h @@ -3,7 +3,16 @@ #define __LINUX_NODEMASK_TYPES_H #include <linux/bitops.h> -#include <linux/numa.h> + +#ifdef CONFIG_NODES_SHIFT +#define NODES_SHIFT CONFIG_NODES_SHIFT +#else +#define NODES_SHIFT 0 +#endif + +#define MAX_NUMNODES (1 << NODES_SHIFT) + +#define NUMA_NO_NODE (-1) typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; diff --git a/include/linux/numa.h b/include/linux/numa.h index 3567e40329eb..e6baaf6051bc 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -3,16 +3,8 @@ #define _LINUX_NUMA_H #include <linux/init.h> #include <linux/types.h> +#include <linux/nodemask.h> -#ifdef CONFIG_NODES_SHIFT -#define NODES_SHIFT CONFIG_NODES_SHIFT -#else -#define NODES_SHIFT 0 -#endif - -#define MAX_NUMNODES (1 << NODES_SHIFT) - -#define NUMA_NO_NODE (-1) #define NUMA_NO_MEMBLK (-1) static inline bool numa_valid_node(int nid) @@ -39,6 +31,8 @@ void __init alloc_offline_node_data(int nid); /* Generic implementation available */ int numa_nearest_node(int node, unsigned int state); +int nearest_node_nodemask(int node, nodemask_t *mask); + #ifndef memory_add_physaddr_to_nid int memory_add_physaddr_to_nid(u64 start); #endif @@ -55,6 +49,11 @@ static inline int numa_nearest_node(int node, unsigned int state) return NUMA_NO_NODE; } +static inline int nearest_node_nodemask(int node, nodemask_t *mask) +{ + return NUMA_NO_NODE; +} + static inline int memory_add_physaddr_to_nid(u64 start) { return 0; diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index c1d0bc5d9624..60e069a6757f 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -40,5 +40,12 @@ int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm, int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm, u8 *ctrl_key, size_t ctrl_key_len, u8 *sess_key, size_t sess_key_len); +int nvme_auth_generate_psk(u8 hmac_id, u8 *skey, size_t skey_len, + u8 *c1, u8 *c2, size_t hash_len, + u8 **ret_psk, size_t *ret_len); +int nvme_auth_generate_digest(u8 hmac_id, u8 *psk, size_t psk_len, + char *subsysnqn, char *hostnqn, u8 **ret_digest); +int nvme_auth_derive_tls_psk(int hmac_id, u8 *psk, size_t psk_len, + u8 *psk_digest, u8 **ret_psk); #endif /* _NVME_AUTH_H */ diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h index 19d2b256180f..ab8971afa973 100644 --- a/include/linux/nvme-keyring.h +++ b/include/linux/nvme-keyring.h @@ -6,15 +6,25 @@ #ifndef _NVME_KEYRING_H #define _NVME_KEYRING_H +#include <linux/key.h> + #if IS_ENABLED(CONFIG_NVME_KEYRING) +struct key *nvme_tls_psk_refresh(struct key *keyring, + const char *hostnqn, const char *subnqn, u8 hmac_id, + u8 *data, size_t data_len, const char *digest); key_serial_t nvme_tls_psk_default(struct key *keyring, const char *hostnqn, const char *subnqn); key_serial_t nvme_keyring_id(void); struct key *nvme_tls_key_lookup(key_serial_t key_id); #else - +static inline struct key *nvme_tls_psk_refresh(struct key *keyring, + const char *hostnqn, char *subnqn, u8 hmac_id, + u8 *data, size_t data_len, const char *digest) +{ + return ERR_PTR(-ENOTSUPP); +} static inline key_serial_t nvme_tls_psk_default(struct key *keyring, const char *hostnqn, const char *subnqn) { diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2dc05b1c3283..2479ed10f53e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1772,6 +1772,13 @@ enum { NVME_AUTH_DHGROUP_INVALID = 0xff, }; +enum { + NVME_AUTH_SECP_NOSC = 0x00, + NVME_AUTH_SECP_SC = 0x01, + NVME_AUTH_SECP_NEWTLSPSK = 0x02, + NVME_AUTH_SECP_REPLACETLSPSK = 0x03, +}; + union nvmf_auth_protocol { struct nvmf_auth_dhchap_protocol_descriptor dhchap; }; diff --git a/include/linux/objpool.h b/include/linux/objpool.h index cb1758eaa2d3..b713a1fe7521 100644 --- a/include/linux/objpool.h +++ b/include/linux/objpool.h @@ -170,17 +170,16 @@ static inline void *objpool_pop(struct objpool_head *pool) { void *obj = NULL; unsigned long flags; - int i, cpu; + int start, cpu; /* disable local irq to avoid preemption & interruption */ raw_local_irq_save(flags); - cpu = raw_smp_processor_id(); - for (i = 0; i < pool->nr_possible_cpus; i++) { + start = raw_smp_processor_id(); + for_each_possible_cpu_wrap(cpu, start) { obj = __objpool_try_get_slot(pool, cpu); if (obj) break; - cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); } raw_local_irq_restore(flags); diff --git a/include/linux/objtool.h b/include/linux/objtool.h index c722a921165b..3ca965a2ddc8 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -128,7 +128,7 @@ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) -#define __ASM_ANNOTATE(label, type) +#define __ASM_ANNOTATE(label, type) "" #define ASM_ANNOTATE(type) #else .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 @@ -147,6 +147,8 @@ * these relocations will never be used for indirect calls. */ #define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) +#define ANNOTATE_NOENDBR_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR)) + /* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline diff --git a/include/linux/of.h b/include/linux/of.h index eaf0e2a2b75c..dbd022d1cdc0 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -301,6 +301,8 @@ extern struct device_node *of_get_compatible_child(const struct device_node *par const char *compatible); extern struct device_node *of_get_child_by_name(const struct device_node *node, const char *name); +extern struct device_node *of_get_available_child_by_name(const struct device_node *node, + const char *name); /* cache lookup */ extern struct device_node *of_find_next_cache_node(const struct device_node *); @@ -314,6 +316,9 @@ extern struct property *of_find_property(const struct device_node *np, extern bool of_property_read_bool(const struct device_node *np, const char *propname); extern int of_property_count_elems_of_size(const struct device_node *np, const char *propname, int elem_size); +extern int of_property_read_u16_index(const struct device_node *np, + const char *propname, + u32 index, u16 *out_value); extern int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value); @@ -578,6 +583,13 @@ static inline struct device_node *of_get_child_by_name( return NULL; } +static inline struct device_node *of_get_available_child_by_name( + const struct device_node *node, + const char *name) +{ + return NULL; +} + static inline int of_device_is_compatible(const struct device_node *device, const char *name) { @@ -627,6 +639,12 @@ static inline int of_property_count_elems_of_size(const struct device_node *np, return -ENOSYS; } +static inline int of_property_read_u16_index(const struct device_node *np, + const char *propname, u32 index, u16 *out_value) +{ + return -ENOSYS; +} + static inline int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value) { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 36d283552f80..df9234e5f478 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -925,14 +925,15 @@ FOLIO_FLAG_FALSE(has_hwpoisoned) enum pagetype { /* 0x00-0x7f are positive numbers, ie mapcount */ /* Reserve 0x80-0xef for mapcount overflow. */ - PGTY_buddy = 0xf0, - PGTY_offline = 0xf1, - PGTY_table = 0xf2, - PGTY_guard = 0xf3, - PGTY_hugetlb = 0xf4, - PGTY_slab = 0xf5, - PGTY_zsmalloc = 0xf6, - PGTY_unaccepted = 0xf7, + PGTY_buddy = 0xf0, + PGTY_offline = 0xf1, + PGTY_table = 0xf2, + PGTY_guard = 0xf3, + PGTY_hugetlb = 0xf4, + PGTY_slab = 0xf5, + PGTY_zsmalloc = 0xf6, + PGTY_unaccepted = 0xf7, + PGTY_large_kmalloc = 0xf8, PGTY_mapcount_underflow = 0xff }; @@ -1075,6 +1076,7 @@ PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) * Serialized with zone lock. */ PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted) +FOLIO_TYPE_OPS(large_kmalloc, large_kmalloc) /** * PageHuge - Determine if the page belongs to hugetlbfs diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 47bfc6b1b632..d2432cb02fa0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1044,21 +1044,23 @@ static inline pgoff_t page_pgoff(const struct folio *folio, return folio->index + folio_page_idx(folio, page); } -/* - * Return byte-offset into filesystem object for page. +/** + * folio_pos - Returns the byte position of this folio in its file. + * @folio: The folio. */ -static inline loff_t page_offset(struct page *page) +static inline loff_t folio_pos(const struct folio *folio) { - return ((loff_t)page->index) << PAGE_SHIFT; + return ((loff_t)folio->index) * PAGE_SIZE; } -/** - * folio_pos - Returns the byte position of this folio in its file. - * @folio: The folio. +/* + * Return byte-offset into filesystem object for page. */ -static inline loff_t folio_pos(struct folio *folio) +static inline loff_t page_offset(struct page *page) { - return page_offset(&folio->page); + struct folio *folio = page_folio(page); + + return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* @@ -1603,34 +1605,6 @@ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, } /** - * page_mkwrite_check_truncate - check if page was truncated - * @page: the page to check - * @inode: the inode to check the page against - * - * Returns the number of bytes in the page up to EOF, - * or -EFAULT if the page was truncated. - */ -static inline int page_mkwrite_check_truncate(struct page *page, - struct inode *inode) -{ - loff_t size = i_size_read(inode); - pgoff_t index = size >> PAGE_SHIFT; - int offset = offset_in_page(size); - - if (page->mapping != inode->i_mapping) - return -EFAULT; - - /* page is wholly inside EOF */ - if (page->index < index) - return PAGE_SIZE; - /* page is wholly past EOF */ - if (page->index > index || !offset) - return -EFAULT; - /* page is partially inside EOF */ - return offset; -} - -/** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1a2594a38199..41dfb3b0d9b9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -569,6 +569,7 @@ #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 +#define PCI_DEVICE_ID_AMD_17H_M40H_DF_F3 0x13f3 #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F3 0x1727 diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 733f4ddd2ef1..e40f554ff717 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -50,8 +50,7 @@ struct dw_xpcs; struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs); int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); -int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, - int enable); +void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact); struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr); struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode); void xpcs_destroy(struct dw_xpcs *xpcs); diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 5b520fe86b60..0fcacb909778 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -26,13 +26,11 @@ #define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned" #define PER_CPU_ALIGNED_SECTION "..shared_aligned" #endif -#define PER_CPU_FIRST_SECTION "..first" #else #define PER_CPU_SHARED_ALIGNED_SECTION "" #define PER_CPU_ALIGNED_SECTION "..shared_aligned" -#define PER_CPU_FIRST_SECTION "" #endif @@ -115,14 +113,17 @@ DEFINE_PER_CPU_SECTION(type, name, "") /* - * Declaration/definition used for per-CPU variables that must come first in - * the set of variables. + * Declaration/definition used for per-CPU variables that are frequently + * accessed and should be in a single cacheline. + * + * For use only by architecture and core code. Only use scalar or pointer + * types to maximize density. */ -#define DECLARE_PER_CPU_FIRST(type, name) \ - DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION) +#define DECLARE_PER_CPU_CACHE_HOT(type, name) \ + DECLARE_PER_CPU_SECTION(type, name, "..hot.." #name) -#define DEFINE_PER_CPU_FIRST(type, name) \ - DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION) +#define DEFINE_PER_CPU_CACHE_HOT(type, name) \ + DEFINE_PER_CPU_SECTION(type, name, "..hot.." #name) /* * Declaration/definition used for per-CPU variables that must be cacheline diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index c012df33a9f0..af7d75ede619 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -8,6 +8,7 @@ #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> +#include <linux/cleanup.h> struct percpu_rw_semaphore { struct rcu_sync rss; @@ -125,6 +126,13 @@ extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); +DEFINE_GUARD(percpu_read, struct percpu_rw_semaphore *, + percpu_down_read(_T), percpu_up_read(_T)) +DEFINE_GUARD_COND(percpu_read, _try, percpu_down_read_trylock(_T)) + +DEFINE_GUARD(percpu_write, struct percpu_rw_semaphore *, + percpu_down_write(_T), percpu_up_write(_T)) + static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) { return atomic_read(&sem->block); diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 4b5b83677e3f..6dc5e0cd76ca 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -84,7 +84,6 @@ struct arm_pmu { struct pmu pmu; cpumask_t supported_cpus; char *name; - int pmuver; irqreturn_t (*handle_irq)(struct arm_pmu *pmu); void (*enable)(struct perf_event *event); void (*disable)(struct perf_event *event); @@ -100,20 +99,26 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); + /* + * Called by KVM to map the PMUv3 event space onto non-PMUv3 hardware. + */ + int (*map_pmuv3_event)(unsigned int eventsel); DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS); bool secure_access; /* 32-bit ARM only */ -#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 - DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); -#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE 0x4000 - DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; struct hlist_node node; struct notifier_block cpu_pm_nb; /* the attr_groups array must be NULL-terminated */ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1]; - /* store the PMMIR_EL1 to expose slots */ + + /* PMUv3 only */ + int pmuver; u64 reg_pmmir; +#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 + DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); +#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE 0x4000 + DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); /* Only to be used by ACPI probing code */ unsigned long acpi_cpuid; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8333f132f4a9..5a9bf15d4461 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -343,8 +343,7 @@ struct pmu { */ unsigned int scope; - int __percpu *pmu_disable_count; - struct perf_cpu_pmu_context __percpu *cpu_pmu_context; + struct perf_cpu_pmu_context * __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; @@ -495,7 +494,7 @@ struct pmu { * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, - bool sched_in); + struct task_struct *task, bool sched_in); /* * Kmem cache of PMU specific data @@ -503,16 +502,6 @@ struct pmu { struct kmem_cache *task_ctx_cache; /* - * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) - * can be synchronized using this function. See Intel LBR callstack support - * implementation and Perf core context switch handling callbacks for usage - * examples. - */ - void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc, - struct perf_event_pmu_context *next_epc); - /* optional */ - - /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, @@ -673,13 +662,16 @@ struct swevent_hlist { struct rcu_head rcu_head; }; -#define PERF_ATTACH_CONTEXT 0x01 -#define PERF_ATTACH_GROUP 0x02 -#define PERF_ATTACH_TASK 0x04 -#define PERF_ATTACH_TASK_DATA 0x08 -#define PERF_ATTACH_ITRACE 0x10 -#define PERF_ATTACH_SCHED_CB 0x20 -#define PERF_ATTACH_CHILD 0x40 +#define PERF_ATTACH_CONTEXT 0x0001 +#define PERF_ATTACH_GROUP 0x0002 +#define PERF_ATTACH_TASK 0x0004 +#define PERF_ATTACH_TASK_DATA 0x0008 +#define PERF_ATTACH_GLOBAL_DATA 0x0010 +#define PERF_ATTACH_SCHED_CB 0x0020 +#define PERF_ATTACH_CHILD 0x0040 +#define PERF_ATTACH_EXCLUSIVE 0x0080 +#define PERF_ATTACH_CALLCHAIN 0x0100 +#define PERF_ATTACH_ITRACE 0x0200 struct bpf_prog; struct perf_cgroup; @@ -921,7 +913,7 @@ struct perf_event_pmu_context { struct list_head pinned_active; struct list_head flexible_active; - /* Used to avoid freeing per-cpu perf_event_pmu_context */ + /* Used to identify the per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; @@ -931,7 +923,6 @@ struct perf_event_pmu_context { atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; - void *task_ctx_data; /* pmu specific data */ /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to @@ -979,7 +970,6 @@ struct perf_event_context { int nr_user; int is_active; - int nr_task_data; int nr_stat; int nr_freq; int rotate_disable; @@ -1020,6 +1010,41 @@ struct perf_event_context { local_t nr_no_switch_fast; }; +/** + * struct perf_ctx_data - PMU specific data for a task + * @rcu_head: To avoid the race on free PMU specific data + * @refcount: To track users + * @global: To track system-wide users + * @ctx_cache: Kmem cache of PMU specific data + * @data: PMU specific data + * + * Currently, the struct is only used in Intel LBR call stack mode to + * save/restore the call stack of a task on context switches. + * + * The rcu_head is used to prevent the race on free the data. + * The data only be allocated when Intel LBR call stack mode is enabled. + * The data will be freed when the mode is disabled. + * The content of the data will only be accessed in context switch, which + * should be protected by rcu_read_lock(). + * + * Because of the alignment requirement of Intel Arch LBR, the Kmem cache + * is used to allocate the PMU specific data. The ctx_cache is to track + * the Kmem cache. + * + * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct. + * When system-wide Intel LBR call stack mode is enabled, a buffer with + * constant size will be allocated for each task. + * Also, system memory consumption can further grow when the size of + * struct perf_ctx_data enlarges. + */ +struct perf_ctx_data { + struct rcu_head rcu_head; + refcount_t refcount; + int global; + struct kmem_cache *ctx_cache; + void *data; +}; + struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; @@ -1029,6 +1054,7 @@ struct perf_cpu_pmu_context { int active_oncpu; int exclusive; + int pmu_disable_count; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; @@ -1062,7 +1088,13 @@ struct perf_output_handle { struct perf_buffer *rb; unsigned long wakeup; unsigned long size; - u64 aux_flags; + union { + u64 flags; /* perf_output*() */ + u64 aux_flags; /* perf_aux_output*() */ + struct { + u64 skip_read : 1; + }; + }; union { void *addr; unsigned long head; @@ -1339,6 +1371,9 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data, if (branch_sample_hw_index(event)) size += sizeof(u64); + + brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr); + size += brs->nr * sizeof(struct perf_branch_entry); /* @@ -1646,19 +1681,10 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 } extern int sysctl_perf_event_paranoid; -extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; -extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int perf_event_max_stack_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); - /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 @@ -1672,22 +1698,22 @@ static inline int perf_is_paranoid(void) return sysctl_perf_event_paranoid > -1; } -int perf_allow_kernel(struct perf_event_attr *attr); +int perf_allow_kernel(void); -static inline int perf_allow_cpu(struct perf_event_attr *attr) +static inline int perf_allow_cpu(void) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; - return security_perf_event_open(attr, PERF_SECURITY_CPU); + return security_perf_event_open(PERF_SECURITY_CPU); } -static inline int perf_allow_tracepoint(struct perf_event_attr *attr) +static inline int perf_allow_tracepoint(void) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; - return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); + return security_perf_event_open(PERF_SECURITY_TRACEPOINT); } extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); diff --git a/include/linux/phy.h b/include/linux/phy.h index 19f076a71f94..a2bfae80c449 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -37,10 +37,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; @@ -54,11 +51,6 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; -extern const int phy_10_100_features_array[4]; -extern const int phy_basic_t1_features_array[3]; -extern const int phy_basic_t1s_p2mp_features_array[2]; -extern const int phy_gbit_features_array[2]; -extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, @@ -89,7 +81,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay - * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay + * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal TX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface @@ -189,13 +181,6 @@ static inline void phy_interface_set_rgmii(unsigned long *intf) __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); } -/* - * phy_supported_speeds - return all speeds currently supported by a PHY device - */ -unsigned int phy_supported_speeds(struct phy_device *phy, - unsigned int *speeds, - unsigned int size); - /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value @@ -303,13 +288,11 @@ static inline long rgmii_clock(int speed) } } -#define PHY_INIT_TIMEOUT 100000 -#define PHY_FORCE_TIMEOUT 10 - #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" +#define PHY_ID_SIZE (MII_BUS_ID_SIZE + 3) #define MII_BUS_ID_SIZE 61 @@ -338,41 +321,6 @@ struct mdio_bus_stats { }; /** - * struct phy_package_shared - Shared information in PHY packages - * @base_addr: Base PHY address of PHY package used to combine PHYs - * in one package and for offset calculation of phy_package_read/write - * @np: Pointer to the Device Node if PHY package defined in DT - * @refcnt: Number of PHYs connected to this shared data - * @flags: Initialization of PHY package - * @priv_size: Size of the shared private data @priv - * @priv: Driver private data shared across a PHY package - * - * Represents a shared structure between different phydev's in the same - * package, for example a quad PHY. See phy_package_join() and - * phy_package_leave(). - */ -struct phy_package_shared { - u8 base_addr; - /* With PHY package defined in DT this points to the PHY package node */ - struct device_node *np; - refcount_t refcnt; - unsigned long flags; - size_t priv_size; - - /* private data pointer */ - /* note that this pointer is shared between different phydevs and - * the user has to take care of appropriate locking. It is allocated - * and freed automatically by phy_package_join() and - * phy_package_leave(). - */ - void *priv; -}; - -/* used as bit number in atomic bitops */ -#define PHY_SHARED_F_INIT_DONE 0 -#define PHY_SHARED_F_PROBE_DONE 1 - -/** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device @@ -611,7 +559,7 @@ struct macsec_ops; * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host - * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited + * @eee_disabled_modes: Energy efficient ethernet modes not to be advertised * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode * @link: Current link state @@ -727,7 +675,7 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); /* Energy efficient ethernet modes which should be prohibited */ - __ETHTOOL_DECLARE_LINK_MODE_MASK(eee_broken_modes); + __ETHTOOL_DECLARE_LINK_MODE_MASK(eee_disabled_modes); bool enable_tx_lpi; bool eee_active; struct eee_config eee_cfg; @@ -1189,8 +1137,16 @@ struct phy_driver { int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); - /** @set_loopback: Set the loopback mood of the PHY */ - int (*set_loopback)(struct phy_device *dev, bool enable); + /** + * @set_loopback: Set the loopback mode of the PHY + * enable selects if the loopback mode is enabled or disabled. If the + * loopback mode is enabled, then the speed of the loopback mode can be + * requested with the speed argument. If the speed argument is zero, + * then any speed can be selected. If the speed argument is > 0, then + * this speed shall be selected for the loopback mode or EOPNOTSUPP + * shall be returned if speed selection is not supported. + */ + int (*set_loopback)(struct phy_device *dev, bool enable, int speed); /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ @@ -1273,13 +1229,23 @@ struct phy_driver { */ int (*led_polarity_set)(struct phy_device *dev, int index, unsigned long modes); + + /** + * @get_next_update_time: Get the time until the next update event + * @dev: PHY device + * + * Callback to determine the time (in jiffies) until the next + * update event for the PHY state machine. Allows PHY drivers to + * dynamically adjust polling intervals based on link state or other + * conditions. + * + * Returns the time in jiffies until the next update event. + */ + unsigned int (*get_next_update_time)(struct phy_device *dev); }; #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -#define PHY_ANY_ID "MATCH ANY PHY" -#define PHY_ANY_UID 0xffffffff - #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) @@ -1312,62 +1278,36 @@ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); } -/* A Structure for boards to register fixups with the PHY Lib */ -struct phy_fixup { - struct list_head list; - char bus_id[MII_BUS_ID_SIZE + 3]; - u32 phy_uid; - u32 phy_uid_mask; - int (*run)(struct phy_device *phydev); -}; - const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); -/* A structure for mapping a particular speed and duplex - * combination to a particular SUPPORTED and ADVERTISED value - */ -struct phy_setting { - u32 speed; - u8 duplex; - u8 bit; -}; - -const struct phy_setting * -phy_lookup_setting(int speed, int duplex, const unsigned long *mask, - bool exact); -size_t phy_speeds(unsigned int *speeds, size_t size, - unsigned long *mask); -void of_set_phy_supported(struct phy_device *phydev); -void of_set_phy_eee_broken(struct phy_device *phydev); -void of_set_phy_timing_role(struct phy_device *phydev); -int phy_speed_down_core(struct phy_device *phydev); - /** - * phy_set_eee_broken - Mark an EEE mode as broken so that it isn't advertised. + * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct - * @link_mode: The broken EEE mode */ -static inline void phy_set_eee_broken(struct phy_device *phydev, u32 link_mode) +static inline bool phy_is_started(struct phy_device *phydev) { - linkmode_set_bit(link_mode, phydev->eee_broken_modes); + return phydev->state >= PHY_UP; } /** - * phy_is_started - Convenience function to check whether PHY is started + * phy_disable_eee_mode - Don't advertise an EEE mode. * @phydev: The phy_device struct + * @link_mode: The EEE mode to be disabled */ -static inline bool phy_is_started(struct phy_device *phydev) +static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode) { - return phydev->state >= PHY_UP; + WARN_ON(phy_is_started(phydev)); + + linkmode_set_bit(link_mode, phydev->eee_disabled_modes); + linkmode_clear_bit(link_mode, phydev->advertising_eee); } void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); -void phy_check_downshift(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register @@ -1747,15 +1687,6 @@ static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) } /** - * phy_is_internal - Convenience function for testing if a PHY is internal - * @phydev: the phy_device struct - */ -static inline bool phy_is_internal(struct phy_device *phydev) -{ - return phydev->is_internal; -} - -/** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ @@ -1878,7 +1809,7 @@ int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); -int phy_loopback(struct phy_device *phydev, bool enable); +int phy_loopback(struct phy_device *phydev, bool enable, int speed); int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); @@ -1993,7 +1924,7 @@ int genphy_read_status(struct phy_device *phydev); int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); -int genphy_loopback(struct phy_device *phydev, bool enable); +int genphy_loopback(struct phy_device *phydev, bool enable, int speed); int genphy_soft_reset(struct phy_device *phydev); irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); @@ -2035,7 +1966,7 @@ int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); -int genphy_c45_loopback(struct phy_device *phydev, bool enable); +int genphy_c45_loopback(struct phy_device *phydev, bool enable, int speed); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); @@ -2045,14 +1976,12 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); -int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp); +int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); -int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; @@ -2078,7 +2007,6 @@ int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); -void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); @@ -2114,11 +2042,13 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx); +int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev, + enum ethtool_link_mode_bit_indices linkmode, + u32 *val); + void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); -int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, - int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, @@ -2142,13 +2072,6 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); -int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); -int of_phy_package_join(struct phy_device *phydev, size_t priv_size); -void phy_package_leave(struct phy_device *phydev); -int devm_phy_package_join(struct device *dev, struct phy_device *phydev, - int base_addr, size_t priv_size); -int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, - size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); @@ -2178,104 +2101,6 @@ int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); -static inline int phy_package_address(struct phy_device *phydev, - unsigned int addr_offset) -{ - struct phy_package_shared *shared = phydev->shared; - u8 base_addr = shared->base_addr; - - if (addr_offset >= PHY_MAX_ADDR - base_addr) - return -EIO; - - /* we know that addr will be in the range 0..31 and thus the - * implicit cast to a signed int is not a problem. - */ - return base_addr + addr_offset; -} - -static inline int phy_package_read(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return mdiobus_read(phydev->mdio.bus, addr, regnum); -} - -static inline int __phy_package_read(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return __mdiobus_read(phydev->mdio.bus, addr, regnum); -} - -static inline int phy_package_write(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum, - u16 val) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return mdiobus_write(phydev->mdio.bus, addr, regnum, val); -} - -static inline int __phy_package_write(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum, - u16 val) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); -} - -int __phy_package_read_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum); - -int phy_package_read_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum); - -int __phy_package_write_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum, u16 val); - -int phy_package_write_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum, u16 val); - -static inline bool __phy_package_set_once(struct phy_device *phydev, - unsigned int b) -{ - struct phy_package_shared *shared = phydev->shared; - - if (!shared) - return false; - - return !test_and_set_bit(b, &shared->flags); -} - -static inline bool phy_package_init_once(struct phy_device *phydev) -{ - return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); -} - -static inline bool phy_package_probe_once(struct phy_device *phydev) -{ - return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); -} - extern const struct bus_type mdio_bus_type; struct mdio_board_info { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 898b00451bbf..1f5773ab5660 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -442,7 +442,6 @@ struct phylink_pcs_ops; * are supported by this PCS. * @ops: a pointer to the &struct phylink_pcs_ops structure * @phylink: pointer to &struct phylink_config - * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes * @rxc_always_on: The MAC driver requires the reference clock * to always be on. Standalone PCS drivers which @@ -459,7 +458,6 @@ struct phylink_pcs { DECLARE_PHY_INTERFACE_MASK(supported_interfaces); const struct phylink_pcs_ops *ops; struct phylink *phylink; - bool neg_mode; bool poll; bool rxc_always_on; }; @@ -477,6 +475,10 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_disable_eee: optional notification to PCS that EEE has been disabled + * at the MAC. + * @pcs_enable_eee: optional notification to PCS that EEE will be enabled at + * the MAC. * @pcs_pre_init: configure PCS components necessary for MAC hardware * initialization e.g. RX clock for stmmac. */ @@ -500,6 +502,8 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + void (*pcs_disable_eee)(struct phylink_pcs *pcs); + void (*pcs_enable_eee)(struct phylink_pcs *pcs); int (*pcs_pre_init)(struct phylink_pcs *pcs); }; @@ -591,6 +595,14 @@ void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, * The %neg_mode argument should be tested via the phylink_mode_*() family of * functions, or for PCS that set pcs->neg_mode true, should be tested * against the PHYLINK_PCS_NEG_* definitions. + * + * pcs_config() will be called when configuration of the PCS is required + * or when the advertisement is possibly updated. It must not unnecessarily + * disrupt an established link. + * + * When an autonegotiation restart is required for 802.3z modes, .pcs_config() + * should return a positive non-zero integer (e.g. 1) to indicate to phylink + * to call the pcs_an_restart() method. */ int pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, @@ -626,6 +638,22 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); /** + * pcs_disable_eee() - Disable EEE at the PCS + * @pcs: a pointer to a &struct phylink_pcs + * + * Optional method informing the PCS that EEE has been disabled at the MAC. + */ +void pcs_disable_eee(struct phylink_pcs *pcs); + +/** + * pcs_enable_eee() - Enable EEE at the PCS + * @pcs: a pointer to a &struct phylink_pcs + * + * Optional method informing the PCS that EEE is about to be enabled at the MAC. + */ +void pcs_enable_eee(struct phylink_pcs *pcs); + +/** * pcs_pre_init() - Configure PCS components necessary for MAC initialization * @pcs: a pointer to a &struct phylink_pcs. * @@ -678,7 +706,11 @@ int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs); void phylink_start(struct phylink *); void phylink_stop(struct phylink *); +void phylink_rx_clk_stop_block(struct phylink *); +void phylink_rx_clk_stop_unblock(struct phylink *); + void phylink_suspend(struct phylink *pl, bool mac_wol); +void phylink_prepare_resume(struct phylink *pl); void phylink_resume(struct phylink *pl); void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); @@ -694,7 +726,6 @@ void phylink_ethtool_get_pauseparam(struct phylink *, int phylink_ethtool_set_pauseparam(struct phylink *, struct ethtool_pauseparam *); int phylink_get_eee_err(struct phylink *); -int phylink_init_eee(struct phylink *, bool); int phylink_ethtool_get_eee(struct phylink *link, struct ethtool_keee *eee); int phylink_ethtool_set_eee(struct phylink *link, struct ethtool_keee *eee); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); @@ -737,6 +768,18 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) } } +/** + * phylink_mac_implements_lpi() - determine if MAC implements LPI ops + * @ops: phylink_mac_ops structure + * + * Returns true if the phylink MAC operations structure indicates that the + * LPI operations have been implemented, false otherwise. + */ +static inline bool phylink_mac_implements_lpi(const struct phylink_mac_ops *ops) +{ + return ops && ops->mac_disable_tx_lpi && ops->mac_enable_tx_lpi; +} + void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, unsigned int neg_mode, u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, diff --git a/include/linux/pid.h b/include/linux/pid.h index 98837a1ff0f3..311ecebd7d56 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -101,9 +101,9 @@ extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); -extern void detach_pid(struct task_struct *task, enum pid_type); -extern void change_pid(struct task_struct *task, enum pid_type, - struct pid *pid); +void detach_pid(struct pid **pids, struct task_struct *task, enum pid_type); +void change_pid(struct pid **pids, struct task_struct *task, enum pid_type, + struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); @@ -129,6 +129,7 @@ extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); +void free_pids(struct pid **pids); extern void disable_pid_allocation(struct pid_namespace *ns); /* diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 7c830d0dec9a..05e6f8f4a026 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -6,6 +6,7 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); void pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); +void pidfs_exit(struct task_struct *tsk); extern const struct dentry_operations pidfs_dentry_operations; #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index b698758000f8..9d42d473d201 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -108,7 +108,7 @@ struct pipe_inode_info { #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif - struct page *tmp_page; + struct page *tmp_page[2]; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; diff --git a/include/linux/platform_data/huawei-gaokun-ec.h b/include/linux/platform_data/huawei-gaokun-ec.h new file mode 100644 index 000000000000..faa15d315128 --- /dev/null +++ b/include/linux/platform_data/huawei-gaokun-ec.h @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Huawei Matebook E Go Embedded Controller + * + * Copyright (C) 2024-2025 Pengyu Luo <mitltlatltl@gmail.com> + */ + +#ifndef __HUAWEI_GAOKUN_EC_H__ +#define __HUAWEI_GAOKUN_EC_H__ + +#define GAOKUN_UCSI_CCI_SIZE 4 +#define GAOKUN_UCSI_MSGI_SIZE 16 +#define GAOKUN_UCSI_READ_SIZE (GAOKUN_UCSI_CCI_SIZE + GAOKUN_UCSI_MSGI_SIZE) +#define GAOKUN_UCSI_WRITE_SIZE 24 /* 8B CTRL, 16B MSGO */ + +#define GAOKUN_UCSI_NO_PORT_UPDATE (-1) + +#define GAOKUN_SMART_CHARGE_DATA_SIZE 4 /* mode, delay, start, end */ + +/* -------------------------------------------------------------------------- */ + +struct gaokun_ec; +struct gaokun_ucsi_reg; +struct notifier_block; + +#define GAOKUN_MOD_NAME "huawei_gaokun_ec" +#define GAOKUN_DEV_PSY "psy" +#define GAOKUN_DEV_UCSI "ucsi" + +/* -------------------------------------------------------------------------- */ +/* Common API */ + +int gaokun_ec_register_notify(struct gaokun_ec *ec, + struct notifier_block *nb); +void gaokun_ec_unregister_notify(struct gaokun_ec *ec, + struct notifier_block *nb); + +int gaokun_ec_read(struct gaokun_ec *ec, const u8 *req, + size_t resp_len, u8 *resp); +int gaokun_ec_write(struct gaokun_ec *ec, const u8 *req); +int gaokun_ec_read_byte(struct gaokun_ec *ec, const u8 *req, u8 *byte); + +/* -------------------------------------------------------------------------- */ +/* API for PSY */ + +int gaokun_ec_psy_multi_read(struct gaokun_ec *ec, u8 reg, + size_t resp_len, u8 *resp); + +static inline int gaokun_ec_psy_read_byte(struct gaokun_ec *ec, + u8 reg, u8 *byte) +{ + return gaokun_ec_psy_multi_read(ec, reg, sizeof(*byte), byte); +} + +static inline int gaokun_ec_psy_read_word(struct gaokun_ec *ec, + u8 reg, u16 *word) +{ + return gaokun_ec_psy_multi_read(ec, reg, sizeof(*word), (u8 *)word); +} + +int gaokun_ec_psy_get_smart_charge(struct gaokun_ec *ec, + u8 resp[GAOKUN_SMART_CHARGE_DATA_SIZE]); +int gaokun_ec_psy_set_smart_charge(struct gaokun_ec *ec, + const u8 req[GAOKUN_SMART_CHARGE_DATA_SIZE]); + +int gaokun_ec_psy_get_smart_charge_enable(struct gaokun_ec *ec, bool *on); +int gaokun_ec_psy_set_smart_charge_enable(struct gaokun_ec *ec, bool on); + +/* -------------------------------------------------------------------------- */ +/* API for UCSI */ + +int gaokun_ec_ucsi_read(struct gaokun_ec *ec, u8 resp[GAOKUN_UCSI_READ_SIZE]); +int gaokun_ec_ucsi_write(struct gaokun_ec *ec, + const u8 req[GAOKUN_UCSI_WRITE_SIZE]); + +int gaokun_ec_ucsi_get_reg(struct gaokun_ec *ec, struct gaokun_ucsi_reg *ureg); +int gaokun_ec_ucsi_pan_ack(struct gaokun_ec *ec, int port_id); + +#endif /* __HUAWEI_GAOKUN_EC_H__ */ diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h new file mode 100644 index 000000000000..6e603a8c075f --- /dev/null +++ b/include/linux/platform_data/x86/intel_pmc_ipc.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel Core SoC Power Management Controller Header File + * + * Copyright (c) 2025, Intel Corporation. + * All Rights Reserved. + * + */ +#ifndef INTEL_PMC_IPC_H +#define INTEL_PMC_IPC_H +#include <linux/acpi.h> + +#define IPC_SOC_REGISTER_ACCESS 0xAA +#define IPC_SOC_SUB_CMD_READ 0x00 +#define IPC_SOC_SUB_CMD_WRITE 0x01 +#define PMC_IPCS_PARAM_COUNT 7 +#define VALID_IPC_RESPONSE 5 + +struct pmc_ipc_cmd { + u32 cmd; + u32 sub_cmd; + u32 size; + u32 wbuf[4]; +}; + +struct pmc_ipc_rbuf { + u32 buf[4]; +}; + +/** + * intel_pmc_ipc() - PMC IPC Mailbox accessor + * @ipc_cmd: Prepared input command to send + * @rbuf: Allocated array for returned IPC data + * + * Return: 0 on success. Non-zero on mailbox error + */ +static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf *rbuf) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object params[PMC_IPCS_PARAM_COUNT] = { + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + }; + struct acpi_object_list arg_list = { PMC_IPCS_PARAM_COUNT, params }; + union acpi_object *obj; + int status; + + if (!ipc_cmd || !rbuf) + return -EINVAL; + + /* + * 0: IPC Command + * 1: IPC Sub Command + * 2: Size + * 3-6: Write Buffer for offset + */ + params[0].integer.value = ipc_cmd->cmd; + params[1].integer.value = ipc_cmd->sub_cmd; + params[2].integer.value = ipc_cmd->size; + params[3].integer.value = ipc_cmd->wbuf[0]; + params[4].integer.value = ipc_cmd->wbuf[1]; + params[5].integer.value = ipc_cmd->wbuf[2]; + params[6].integer.value = ipc_cmd->wbuf[3]; + + status = acpi_evaluate_object(NULL, "\\IPCS", &arg_list, &buffer); + if (ACPI_FAILURE(status)) + return -ENODEV; + + obj = buffer.pointer; + + if (obj && obj->type == ACPI_TYPE_PACKAGE && + obj->package.count == VALID_IPC_RESPONSE) { + const union acpi_object *objs = obj->package.elements; + + if ((u8)objs[0].integer.value != 0) + return -EINVAL; + + rbuf->buf[0] = objs[1].integer.value; + rbuf->buf[1] = objs[2].integer.value; + rbuf->buf[2] = objs[3].integer.value; + rbuf->buf[3] = objs[4].integer.value; + } else { + return -EINVAL; + } + + return 0; +} + +#endif /* INTEL_PMC_IPC_H */ diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index 8c9df7dadd5d..a299225ab92e 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -50,7 +50,7 @@ struct platform_profile_ops { struct device *platform_profile_register(struct device *dev, const char *name, void *drvdata, const struct platform_profile_ops *ops); -int platform_profile_remove(struct device *dev); +void platform_profile_remove(struct device *dev); struct device *devm_platform_profile_register(struct device *dev, const char *name, void *drvdata, const struct platform_profile_ops *ops); diff --git a/include/linux/pm.h b/include/linux/pm.h index 78855d794342..f0bd8fbae4f2 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -597,6 +597,7 @@ enum rpm_status { RPM_RESUMING, RPM_SUSPENDED, RPM_SUSPENDING, + RPM_BLOCKED, }; /* @@ -678,9 +679,9 @@ struct dev_pm_info { bool wakeup_path:1; bool syscore:1; bool no_pm_callbacks:1; /* Owned by the PM core */ - bool async_in_progress:1; /* Owned by the PM core */ + bool work_in_progress:1; /* Owned by the PM core */ + bool smart_suspend:1; /* Owned by the PM core */ bool must_resume:1; /* Owned by the PM core */ - bool set_active:1; /* Owned by the PM core */ bool may_skip_resume:1; /* Set by subsystems */ #else bool should_wakeup:1; @@ -838,10 +839,8 @@ extern int pm_generic_resume_early(struct device *dev); extern int pm_generic_resume_noirq(struct device *dev); extern int pm_generic_resume(struct device *dev); extern int pm_generic_freeze_noirq(struct device *dev); -extern int pm_generic_freeze_late(struct device *dev); extern int pm_generic_freeze(struct device *dev); extern int pm_generic_thaw_noirq(struct device *dev); -extern int pm_generic_thaw_early(struct device *dev); extern int pm_generic_thaw(struct device *dev); extern int pm_generic_restore_noirq(struct device *dev); extern int pm_generic_restore_early(struct device *dev); @@ -883,10 +882,8 @@ static inline void dpm_for_each_dev(void *data, void (*fn)(struct device *, void #define pm_generic_resume_noirq NULL #define pm_generic_resume NULL #define pm_generic_freeze_noirq NULL -#define pm_generic_freeze_late NULL #define pm_generic_freeze NULL #define pm_generic_thaw_noirq NULL -#define pm_generic_thaw_early NULL #define pm_generic_thaw NULL #define pm_generic_restore_noirq NULL #define pm_generic_restore_early NULL diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 68669ce18720..c3b46fa358d3 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -41,9 +41,7 @@ extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); extern int pm_clk_add(struct device *dev, const char *con_id); extern int pm_clk_add_clk(struct device *dev, struct clk *clk); -extern int of_pm_clk_add_clk(struct device *dev, const char *name); extern int of_pm_clk_add_clks(struct device *dev); -extern void pm_clk_remove(struct device *dev, const char *con_id); extern void pm_clk_remove_clk(struct device *dev, struct clk *clk); extern int pm_clk_suspend(struct device *dev); extern int pm_clk_resume(struct device *dev); @@ -76,9 +74,6 @@ static inline int of_pm_clk_add_clks(struct device *dev) { return -EINVAL; } -static inline void pm_clk_remove(struct device *dev, const char *con_id) -{ -} #define pm_clk_suspend NULL #define pm_clk_resume NULL static inline void pm_clk_remove_clk(struct device *dev, struct clk *clk) diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1aab31370065..d56a78af4af1 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -261,6 +261,7 @@ struct generic_pm_domain_data { unsigned int rpm_pstate; unsigned int opp_token; bool hw_mode; + bool rpm_always_on; void *data; }; @@ -293,6 +294,7 @@ ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev); void dev_pm_genpd_synced_poweroff(struct device *dev); int dev_pm_genpd_set_hwmode(struct device *dev, bool enable); bool dev_pm_genpd_get_hwmode(struct device *dev); +int dev_pm_genpd_rpm_always_on(struct device *dev, bool on); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -376,6 +378,11 @@ static inline bool dev_pm_genpd_get_hwmode(struct device *dev) return false; } +static inline int dev_pm_genpd_rpm_always_on(struct device *dev, bool on) +{ + return -EOPNOTSUPP; +} + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index d39dc863f612..7fb5a459847e 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -66,6 +66,7 @@ static inline bool queue_pm_work(struct work_struct *work) extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); +extern bool pm_runtime_need_not_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); @@ -77,6 +78,8 @@ extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); +extern bool pm_runtime_block_if_disabled(struct device *dev); +extern void pm_runtime_unblock(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); @@ -197,6 +200,17 @@ static inline bool pm_runtime_enabled(struct device *dev) } /** + * pm_runtime_blocked - Check if runtime PM enabling is blocked. + * @dev: Target device. + * + * Do not call this function outside system suspend/resume code paths. + */ +static inline bool pm_runtime_blocked(struct device *dev) +{ + return dev->power.last_status == RPM_BLOCKED; +} + +/** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * @@ -241,6 +255,7 @@ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } +static inline bool pm_runtime_need_not_resume(struct device *dev) {return true; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } @@ -271,8 +286,11 @@ static inline int pm_runtime_get_if_active(struct device *dev) static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } +static inline bool pm_runtime_block_if_disabled(struct device *dev) { return true; } +static inline void pm_runtime_unblock(struct device *dev) {} static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} +static inline bool pm_runtime_blocked(struct device *dev) { return true; } static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} @@ -556,11 +574,18 @@ static inline int pm_runtime_set_suspended(struct device *dev) * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * - * Prevent the runtime PM framework from working with @dev (by incrementing its - * "blocking" counter). + * Prevent the runtime PM framework from working with @dev by incrementing its + * "disable" counter. + * + * If the counter is zero when this function runs and there is a pending runtime + * resume request for @dev, it will be resumed. If the counter is still zero at + * that point, all of the pending runtime PM requests for @dev will be canceled + * and all runtime PM operations in progress involving it will be waited for to + * complete. * - * For each invocation of this function for @dev there must be a matching - * pm_runtime_enable() call in order for runtime PM to be enabled for it. + * For each invocation of this function for @dev, there must be a matching + * pm_runtime_enable() call, so that runtime PM is eventually enabled for it + * again. */ static inline void pm_runtime_disable(struct device *dev) { diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index d501c09c60cd..51e0e8dd5f9e 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -205,17 +205,17 @@ static inline void device_set_awake_path(struct device *dev) static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) { - return pm_wakeup_ws_event(ws, msec, false); + pm_wakeup_ws_event(ws, msec, false); } static inline void pm_wakeup_event(struct device *dev, unsigned int msec) { - return pm_wakeup_dev_event(dev, msec, false); + pm_wakeup_dev_event(dev, msec, false); } static inline void pm_wakeup_hard_event(struct device *dev) { - return pm_wakeup_dev_event(dev, 0, true); + pm_wakeup_dev_event(dev, 0, true); } /** diff --git a/include/linux/pnp.h b/include/linux/pnp.h index b7a7158aaf65..23fe3eaf242d 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -290,7 +290,7 @@ static inline void pnp_set_drvdata(struct pnp_dev *pdev, void *data) } struct pnp_fixup { - char id[7]; + char id[8]; void (*quirk_function) (struct pnp_dev *dev); /* fixup function */ }; diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index ef8619f48920..a500d3160fe8 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -95,10 +95,13 @@ struct posix_clock { * struct posix_clock_context - represents clock file operations context * * @clk: Pointer to the clock + * @fp: Pointer to the file used to open the clock * @private_clkdata: Pointer to user data * * Drivers should use struct posix_clock_context during specific character - * device file operation methods to access the posix clock. + * device file operation methods to access the posix clock. In particular, + * the file pointer can be used to verify correct access mode for ioctl() + * calls. * * Drivers can store a private data structure during the open operation * if they have specific information that is required in other file @@ -106,6 +109,7 @@ struct posix_clock { */ struct posix_clock_context { struct posix_clock *clk; + struct file *fp; void *private_clkdata; }; diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index f11f10c97bd9..dd48c64b605e 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -114,6 +114,7 @@ bool posixtimer_init_sigqueue(struct sigqueue *q); void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); +long posixtimer_create_prctl(unsigned long ctrl); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ @@ -140,6 +141,7 @@ static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } +static inline long posixtimer_create_prctl(unsigned long ctrl) { return -EINVAL; } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -177,23 +179,26 @@ static inline void posix_cputimers_init_work(void) { } * @rcu: RCU head for freeing the timer. */ struct k_itimer { - struct hlist_node list; - struct hlist_node ignored_list; + /* 1st cacheline contains read-mostly fields */ struct hlist_node t_hash; - spinlock_t it_lock; - const struct k_clock *kclock; - clockid_t it_clock; + struct hlist_node list; timer_t it_id; + clockid_t it_clock; + int it_sigev_notify; + enum pid_type it_pid_type; + struct signal_struct *it_signal; + const struct k_clock *kclock; + + /* 2nd cacheline and above contain fields which are modified regularly */ + spinlock_t it_lock; int it_status; bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; unsigned int it_sigqueue_seq; - int it_sigev_notify; - enum pid_type it_pid_type; ktime_t it_interval; - struct signal_struct *it_signal; + struct hlist_node ignored_list; union { struct pid *it_pid; struct task_struct *it_process; @@ -210,7 +215,7 @@ struct k_itimer { } alarm; } it; struct rcu_head rcu; -}; +} ____cacheline_aligned_in_smp; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); @@ -240,6 +245,13 @@ static inline void posixtimer_sigqueue_putref(struct sigqueue *q) posixtimer_putref(tmr); } + +static inline bool posixtimer_valid(const struct k_itimer *timer) +{ + unsigned long val = (unsigned long)timer->it_signal; + + return !(val & 0x1UL); +} #else /* CONFIG_POSIX_TIMERS */ static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index 45e6e427ceb8..f73fbea0dbc2 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -42,8 +42,7 @@ struct ppp_channel { int hdrlen; /* amount of headroom channel needs */ void *ppp; /* opaque to channel */ int speed; /* transfer rate (bytes/second) */ - /* the following is not used at present */ - int latency; /* overhead time in milliseconds */ + bool direct_xmit; /* no qdisc, xmit directly */ }; #ifdef __KERNEL__ diff --git a/include/linux/preempt.h b/include/linux/preempt.h index ca86235ac15c..b0af8d4ef6e6 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -319,6 +319,7 @@ do { \ #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; +struct task_struct; /** * preempt_ops - notifiers called when a task is preempted and rescheduled @@ -515,6 +516,8 @@ static inline bool preempt_model_rt(void) return IS_ENABLED(CONFIG_PREEMPT_RT); } +extern const char *preempt_model_str(void); + /* * Does the preemption model allow non-cooperative preemption? * diff --git a/include/linux/printk.h b/include/linux/printk.h index 4217a9f412b2..5b462029d03c 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -207,6 +207,7 @@ void printk_legacy_allow_panic_sync(void); extern bool nbcon_device_try_acquire(struct console *con); extern void nbcon_device_release(struct console *con); void nbcon_atomic_flush_unsafe(void); +bool pr_flush(int timeout_ms, bool reset_on_progress); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -315,6 +316,11 @@ static inline void nbcon_atomic_flush_unsafe(void) { } +static inline bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return true; +} + #endif bool this_cpu_in_panic(void); diff --git a/include/linux/pwm.h b/include/linux/pwm.h index a2df509056ac..9ece4e5d3815 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -379,7 +379,7 @@ static inline void pwmchip_set_drvdata(struct pwm_chip *chip, void *data) dev_set_drvdata(&chip->dev, data); } -#if IS_ENABLED(CONFIG_PWM) +#if IS_REACHABLE(CONFIG_PWM) /* PWM consumer APIs */ int pwm_round_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf); @@ -661,7 +661,7 @@ struct pwm_lookup { PWM_LOOKUP_WITH_MODULE(_provider, _index, _dev_id, _con_id, _period, \ _polarity, NULL) -#if IS_ENABLED(CONFIG_PWM) +#if IS_REACHABLE(CONFIG_PWM) void pwm_add_table(struct pwm_lookup *table, size_t num); void pwm_remove_table(struct pwm_lookup *table, size_t num); #else diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 5b67cd03276e..aa29ac53b833 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -267,7 +267,7 @@ struct qed_ll2_ops { int qed_ll2_alloc_if(struct qed_dev *); void qed_ll2_dealloc_if(struct qed_dev *); #else -static const struct qed_ll2_ops qed_ll2_ops_pass = { +static __maybe_unused const struct qed_ll2_ops qed_ll2_ops_pass = { .start = NULL, .stop = NULL, .start_xmit = NULL, diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 48e5c03df1dd..f8159f8a7d73 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -95,9 +95,9 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { - preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); + preempt_enable(); } static inline int rcu_preempt_depth(void) @@ -121,12 +121,6 @@ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); -#ifdef CONFIG_TASKS_RCU_GENERIC -void rcu_init_tasks_generic(void); -#else -static inline void rcu_init_tasks_generic(void) { } -#endif - #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); @@ -806,11 +800,9 @@ do { \ * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * - * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also - * wait for regions of code with preemption disabled, including regions of - * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which - * define synchronize_sched(), only code enclosed within rcu_read_lock() - * and rcu_read_unlock() are guaranteed to be waited for. + * Both synchronize_rcu() and call_rcu() also wait for regions of code + * with preemption disabled, including regions of code with interrupts or + * softirqs disabled. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen @@ -865,11 +857,10 @@ static __always_inline void rcu_read_lock(void) * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. - * In recent kernels that have consolidated synchronize_sched() and - * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity - * also extends to the scheduler's runqueue and priority-inheritance - * spinlocks, courtesy of the quiescent-state deferral that is carried - * out when rcu_read_unlock() is invoked with interrupts disabled. + * This deadlock immunity also extends to the scheduler's runqueue + * and priority-inheritance spinlocks, courtesy of the quiescent-state + * deferral that is carried out when rcu_read_unlock() is invoked with + * interrupts disabled. * * See rcu_read_lock() for more information. */ @@ -1025,12 +1016,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) -/* - * Does the specified offset indicate that the corresponding rcu_head - * structure can be handled by kvfree_rcu()? - */ -#define __is_kvfree_rcu_offset(offset) ((offset) < 4096) - /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. @@ -1041,11 +1026,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * - * The kfree_rcu() function handles this issue. Rather than encoding a - * function address in the embedded rcu_head structure, kfree_rcu() instead - * encodes the offset of the rcu_head structure within the base structure. - * Because the functions are not allowed in the low-order 4096 bytes of - * kernel virtual memory, offsets up to 4095 bytes can be accommodated. + * The kfree_rcu() function handles this issue. In order to have a universal + * callback function handling different offsets of rcu_head, the callback needs + * to determine the starting address of the freed object, which can be a large + * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to + * page boundary for those, only offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to @@ -1082,14 +1067,23 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) +/* + * In mm/slab_common.c, no suitable header to include here. + */ +void kvfree_call_rcu(struct rcu_head *head, void *ptr); + +/* + * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the + * comment of kfree_rcu() for details. + */ #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ - if (___p) { \ - BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ - kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ - } \ + if (___p) { \ + BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \ + kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ + } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index f9bed3d3f78d..4c92d4291cce 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -16,6 +16,9 @@ struct rcu_synchronize { struct rcu_head head; struct completion completion; + + /* This is for debugging. */ + struct rcu_gp_oldstate oldstate; }; void wakeme_after_rcu(struct rcu_head *head); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index fe42315f667f..f519cd680228 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -90,41 +90,6 @@ static inline void synchronize_rcu_expedited(void) synchronize_rcu(); } -/* - * Add one more declaration of kvfree() here. It is - * not so straight forward to just include <linux/mm.h> - * where it is defined due to getting many compile - * errors caused by that include. - */ -extern void kvfree(const void *addr); - -static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr) -{ - if (head) { - call_rcu(head, (rcu_callback_t) ((void *) head - ptr)); - return; - } - - // kvfree_rcu(one_arg) call. - might_sleep(); - synchronize_rcu(); - kvfree(ptr); -} - -static inline void kvfree_rcu_barrier(void) -{ - rcu_barrier(); -} - -#ifdef CONFIG_KASAN_GENERIC -void kvfree_call_rcu(struct rcu_head *head, void *ptr); -#else -static inline void kvfree_call_rcu(struct rcu_head *head, void *ptr) -{ - __kvfree_call_rcu(head, ptr); -} -#endif - void rcu_qs(void); static inline void rcu_softirq_qs(void) @@ -164,7 +129,6 @@ static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_inkernel_boot_has_ended(void) { return true; } static inline bool rcu_is_watching(void) { return true; } static inline void rcu_momentary_eqs(void) { } -static inline void kfree_rcu_scheduler_running(void) { } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 27d86d912781..9d2d7bd251d4 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -34,12 +34,9 @@ static inline void rcu_virt_note_context_switch(void) } void synchronize_rcu_expedited(void); -void kvfree_call_rcu(struct rcu_head *head, void *ptr); -void kvfree_rcu_barrier(void); void rcu_barrier(void); void rcu_momentary_eqs(void); -void kfree_rcu_scheduler_running(void); struct rcu_gp_oldstate { unsigned long rgos_norm; @@ -103,7 +100,7 @@ extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); -#ifndef CONFIG_PREEMPTION +#ifndef CONFIG_PREEMPT_RCU void rcu_all_qs(void); #endif diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 3a96d068915f..d17c5ea3d55d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1352,6 +1352,7 @@ bool regmap_can_raw_write(struct regmap *map); size_t regmap_get_raw_read_max(struct regmap *map); size_t regmap_get_raw_write_max(struct regmap *map); +void regcache_sort_defaults(struct reg_default *defaults, unsigned int ndefaults); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, unsigned int max); @@ -2043,6 +2044,12 @@ static inline bool regmap_might_sleep(struct regmap *map) return true; } +static inline void regcache_sort_defaults(struct reg_default *defaults, + unsigned int ndefaults) +{ + WARN_ONCE(1, "regmap API is disabled"); +} + static inline int regcache_sync(struct regmap *map) { WARN_ONCE(1, "regmap API is disabled"); diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index ffe912f345ae..56fe2693d9b2 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -677,6 +677,12 @@ regulator_is_equal(struct regulator *reg1, struct regulator *reg2) #endif #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_REGULATOR) +struct regulator *__must_check of_regulator_get(struct device *dev, + struct device_node *node, + const char *id); +struct regulator *__must_check devm_of_regulator_get(struct device *dev, + struct device_node *node, + const char *id); struct regulator *__must_check of_regulator_get_optional(struct device *dev, struct device_node *node, const char *id); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index d94abba1c716..880351ca3dfc 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/pid.h> +#include <linux/resctrl_types.h> /* CLOSID, RMID value used by the default control group */ #define RESCTRL_RESERVED_CLOSID 0 @@ -25,6 +26,24 @@ int proc_resctrl_show(struct seq_file *m, /* max value for struct rdt_domain's mbps_val */ #define MBA_MAX_MBPS U32_MAX +/* Walk all possible resources, with variants for only controls or monitors. */ +#define for_each_rdt_resource(_r) \ + for ((_r) = resctrl_arch_get_resource(0); \ + (_r) && (_r)->rid < RDT_NUM_RESOURCES; \ + (_r) = resctrl_arch_get_resource((_r)->rid + 1)) + +#define for_each_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->alloc_capable || (r)->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for_each_rdt_resource((r)) \ + if ((r)->mon_capable) + /** * enum resctrl_conf_type - The type of configuration. * @CDP_NONE: No prioritisation, both code and data are controlled or monitored. @@ -40,13 +59,42 @@ enum resctrl_conf_type { #define CDP_NUM_TYPES (CDP_DATA + 1) /* - * Event IDs, the values match those used to program IA32_QM_EVTSEL before - * reading IA32_QM_CTR on RDT systems. + * struct pseudo_lock_region - pseudo-lock region information + * @s: Resctrl schema for the resource to which this + * pseudo-locked region belongs + * @closid: The closid that this pseudo-locked region uses + * @d: RDT domain to which this pseudo-locked region + * belongs + * @cbm: bitmask of the pseudo-locked region + * @lock_thread_wq: waitqueue used to wait on the pseudo-locking thread + * completion + * @thread_done: variable used by waitqueue to test if pseudo-locking + * thread completed + * @cpu: core associated with the cache on which the setup code + * will be run + * @line_size: size of the cache lines + * @size: size of pseudo-locked region in bytes + * @kmem: the kernel memory associated with pseudo-locked region + * @minor: minor number of character device associated with this + * region + * @debugfs_dir: pointer to this region's directory in the debugfs + * filesystem + * @pm_reqs: Power management QoS requests related to this region */ -enum resctrl_event_id { - QOS_L3_OCCUP_EVENT_ID = 0x01, - QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, - QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, +struct pseudo_lock_region { + struct resctrl_schema *s; + u32 closid; + struct rdt_ctrl_domain *d; + u32 cbm; + wait_queue_head_t lock_thread_wq; + int thread_done; + int cpu; + unsigned int line_size; + unsigned int size; + void *kmem; + unsigned int minor; + struct dentry *debugfs_dir; + struct list_head pm_reqs; }; /** @@ -155,6 +203,7 @@ enum membw_throttle_mode { /** * struct resctrl_membw - Memory bandwidth allocation related data * @min_bw: Minimum memory bandwidth percentage user can request + * @max_bw: Maximum memory bandwidth value, used as the reset value * @bw_gran: Granularity at which the memory bandwidth is allocated * @delay_linear: True if memory B/W delay is in linear scale * @arch_needs_linear: True if we can't configure non-linear resources @@ -165,6 +214,7 @@ enum membw_throttle_mode { */ struct resctrl_membw { u32 min_bw; + u32 max_bw; u32 bw_gran; u32 delay_linear; bool arch_needs_linear; @@ -173,7 +223,6 @@ struct resctrl_membw { u32 *mb_map; }; -struct rdt_parse_data; struct resctrl_schema; enum resctrl_scope { @@ -183,6 +232,16 @@ enum resctrl_scope { }; /** + * enum resctrl_schema_fmt - The format user-space provides for a schema. + * @RESCTRL_SCHEMA_BITMAP: The schema is a bitmap in hex. + * @RESCTRL_SCHEMA_RANGE: The schema is a decimal number. + */ +enum resctrl_schema_fmt { + RESCTRL_SCHEMA_BITMAP, + RESCTRL_SCHEMA_RANGE, +}; + +/** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine @@ -195,12 +254,10 @@ enum resctrl_scope { * @ctrl_domains: RCU list of all control domains for this resource * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. - * @data_width: Character width of data when displaying - * @default_ctrl: Specifies default cache cbm or memory B/W percent. - * @format_str: Per resource format string to show domain value - * @parse_ctrlval: Per resource function pointer to parse control values + * @schema_fmt: Which format string and parser is used for this schema. * @evt_list: List of monitoring events - * @fflags: flags to choose base and info files + * @mbm_cfg_mask: Bandwidth sources that can be tracked when bandwidth + * monitoring events can be configured. * @cdp_capable: Is the CDP feature available on this resource */ struct rdt_resource { @@ -215,22 +272,25 @@ struct rdt_resource { struct list_head ctrl_domains; struct list_head mon_domains; char *name; - int data_width; - u32 default_ctrl; - const char *format_str; - int (*parse_ctrlval)(struct rdt_parse_data *data, - struct resctrl_schema *s, - struct rdt_ctrl_domain *d); + enum resctrl_schema_fmt schema_fmt; struct list_head evt_list; - unsigned long fflags; + unsigned int mbm_cfg_mask; bool cdp_capable; }; +/* + * Get the resource that exists at this level. If the level is not supported + * a dummy/not-capable resource can be returned. Levels >= RDT_NUM_RESOURCES + * will return NULL. + */ +struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l); + /** * struct resctrl_schema - configuration abilities of a resource presented to * user-space * @list: Member of resctrl_schema_all. * @name: The name to use in the "schemata" file. + * @fmt_str: Format string to show domain value. * @conf_type: Whether this schema is specific to code/data. * @res: The resource structure exported by the architecture to describe * the hardware that is configured by this schema. @@ -241,16 +301,104 @@ struct rdt_resource { struct resctrl_schema { struct list_head list; char name[8]; + const char *fmt_str; enum resctrl_conf_type conf_type; struct rdt_resource *res; u32 num_closid; }; +struct resctrl_cpu_defaults { + u32 closid; + u32 rmid; +}; + +struct resctrl_mon_config_info { + struct rdt_resource *r; + struct rdt_mon_domain *d; + u32 evtid; + u32 mon_config; +}; + +/** + * resctrl_arch_sync_cpu_closid_rmid() - Refresh this CPU's CLOSID and RMID. + * Call via IPI. + * @info: If non-NULL, a pointer to a struct resctrl_cpu_defaults + * specifying the new CLOSID and RMID for tasks in the default + * resctrl ctrl and mon group when running on this CPU. If NULL, + * this CPU is not re-assigned to a different default group. + * + * Propagates reassignment of CPUs and/or tasks to different resctrl groups + * when requested by the resctrl core code. + * + * This function records the per-cpu defaults specified by @info (if any), + * and then reconfigures the CPU's hardware CLOSID and RMID for subsequent + * execution based on @current, in the same way as during a task switch. + */ +void resctrl_arch_sync_cpu_closid_rmid(void *info); + +/** + * resctrl_get_default_ctrl() - Return the default control value for this + * resource. + * @r: The resource whose default control type is queried. + */ +static inline u32 resctrl_get_default_ctrl(struct rdt_resource *r) +{ + switch (r->schema_fmt) { + case RESCTRL_SCHEMA_BITMAP: + return BIT_MASK(r->cache.cbm_len) - 1; + case RESCTRL_SCHEMA_RANGE: + return r->membw.max_bw; + } + + return WARN_ON_ONCE(1); +} + /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); +__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt); + +/** + * resctrl_arch_mon_event_config_write() - Write the config for an event. + * @config_info: struct resctrl_mon_config_info describing the resource, domain + * and event. + * + * Reads resource, domain and eventid from @config_info and writes the + * event config_info->mon_config into hardware. + * + * Called via IPI to reach a CPU that is a member of the specified domain. + */ +void resctrl_arch_mon_event_config_write(void *config_info); + +/** + * resctrl_arch_mon_event_config_read() - Read the config for an event. + * @config_info: struct resctrl_mon_config_info describing the resource, domain + * and event. + * + * Reads resource, domain and eventid from @config_info and reads the + * hardware config value into config_info->mon_config. + * + * Called via IPI to reach a CPU that is a member of the specified domain. + */ +void resctrl_arch_mon_event_config_read(void *config_info); + +/* For use by arch code to remap resctrl's smaller CDP CLOSID range */ +static inline u32 resctrl_get_config_index(u32 closid, + enum resctrl_conf_type type) +{ + switch (type) { + default: + case CDP_NONE: + return closid; + case CDP_CODE: + return closid * 2 + 1; + case CDP_DATA: + return closid * 2; + } +} + /* * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. @@ -314,6 +462,20 @@ static inline void resctrl_arch_rmid_read_context_check(void) } /** + * resctrl_find_domain() - Search for a domain id in a resource domain list. + * @h: The domain list to search. + * @id: The domain id to search for. + * @pos: A pointer to position in the list id should be inserted. + * + * Search the domain list to find the domain id. If the domain id is + * found, return the domain. NULL otherwise. If the domain id is not + * found (and NULL returned) then the first domain with id bigger than + * the input id can be returned to the caller via @pos. + */ +struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id, + struct list_head **pos); + +/** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid * and eventid. * @r: The domain's resource. @@ -340,7 +502,19 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, */ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); +/** + * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to its + * default. + * @r: The resctrl resource to reset. + * + * This can be called from any CPU. + */ +void resctrl_arch_reset_all_ctrls(struct rdt_resource *r); + extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; +int __init resctrl_init(void); +void __exit resctrl_exit(void); + #endif /* _RESCTRL_H */ diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h new file mode 100644 index 000000000000..f26450b3326b --- /dev/null +++ b/include/linux/resctrl_types.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Arm Ltd. + * Based on arch/x86/kernel/cpu/resctrl/internal.h + */ + +#ifndef __LINUX_RESCTRL_TYPES_H +#define __LINUX_RESCTRL_TYPES_H + +/* Reads to Local DRAM Memory */ +#define READS_TO_LOCAL_MEM BIT(0) + +/* Reads to Remote DRAM Memory */ +#define READS_TO_REMOTE_MEM BIT(1) + +/* Non-Temporal Writes to Local Memory */ +#define NON_TEMP_WRITE_TO_LOCAL_MEM BIT(2) + +/* Non-Temporal Writes to Remote Memory */ +#define NON_TEMP_WRITE_TO_REMOTE_MEM BIT(3) + +/* Reads to Local Memory the system identifies as "Slow Memory" */ +#define READS_TO_LOCAL_S_MEM BIT(4) + +/* Reads to Remote Memory the system identifies as "Slow Memory" */ +#define READS_TO_REMOTE_S_MEM BIT(5) + +/* Dirty Victims to All Types of Memory */ +#define DIRTY_VICTIMS_TO_ALL_MEM BIT(6) + +/* Max event bits supported */ +#define MAX_EVT_CONFIG_BITS GENMASK(6, 0) + +enum resctrl_res_level { + RDT_RESOURCE_L3, + RDT_RESOURCE_L2, + RDT_RESOURCE_MBA, + RDT_RESOURCE_SMBA, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + +/* + * Event IDs, the values match those used to program IA32_QM_EVTSEL before + * reading IA32_QM_CTR on RDT systems. + */ +enum resctrl_event_id { + QOS_L3_OCCUP_EVENT_ID = 0x01, + QOS_L3_MBM_TOTAL_EVENT_ID = 0x02, + QOS_L3_MBM_LOCAL_EVENT_ID = 0x03, +}; + +#endif /* __LINUX_RESCTRL_TYPES_H */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 4bc2ee0b10b0..ccaaf4c7d5f6 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -43,6 +43,7 @@ extern void rtnl_lock(void); extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); +extern int rtnl_lock_interruptible(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c15365a30c0..6e5c38718ff5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,6 +65,7 @@ struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; +struct perf_ctx_data; struct pid_namespace; struct pipe_inode_info; struct rcu_node; @@ -382,6 +383,11 @@ enum uclamp_id { #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; +extern void sched_domains_mutex_lock(void); +extern void sched_domains_mutex_unlock(void); +#else +static inline void sched_domains_mutex_lock(void) { } +static inline void sched_domains_mutex_unlock(void) { } #endif struct sched_param { @@ -1311,6 +1317,7 @@ struct task_struct { struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; + struct perf_ctx_data __rcu *perf_ctx_data; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 3a912ab42bb5..f9aabbc9d22e 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -34,7 +34,11 @@ static inline bool dl_time_before(u64 a, u64 b) struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); +extern void dl_clear_root_domain_cpu(int cpu); #endif /* CONFIG_SMP */ +extern u64 dl_cookie; +extern bool dl_bw_visited(int cpu, u64 cookie); + #endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index b5035afa2396..35ed4577a6cc 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -35,12 +35,10 @@ extern void show_stack(struct task_struct *task, unsigned long *sp, extern void sched_show_task(struct task_struct *p); -#ifdef CONFIG_SCHED_DEBUG struct seq_file; extern void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -#endif /* Attach to any functions which should be ignored in wchan output. */ #define __sched __section(".sched.text") diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1d70a9867fb1..f7545430a548 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -146,6 +146,7 @@ struct sched_ext_entity { u32 weight; s32 sticky_cpu; s32 holding_cpu; + s32 selected_cpu; u32 kf_mask; /* see scx_kf_mask above */ struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ atomic_long_t ops_state; diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index e670ac282333..439f6029d3b9 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -79,6 +79,21 @@ static __always_inline bool __must_check current_clr_polling_and_test(void) return unlikely(tif_need_resched()); } +static __always_inline void current_clr_polling(void) +{ + __current_clr_polling(); + + /* + * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. + * Once the bit is cleared, we'll get IPIs with every new + * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also + * fold. + */ + smp_mb__after_atomic(); /* paired with resched_curr() */ + + preempt_fold_need_resched(); +} + #else static inline void __current_set_polling(void) { } static inline void __current_clr_polling(void) { } @@ -91,21 +106,15 @@ static inline bool __must_check current_clr_polling_and_test(void) { return unlikely(tif_need_resched()); } -#endif static __always_inline void current_clr_polling(void) { __current_clr_polling(); - /* - * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. - * Once the bit is cleared, we'll get IPIs with every new - * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also - * fold. - */ smp_mb(); /* paired with resched_curr() */ preempt_fold_need_resched(); } +#endif #endif /* _LINUX_SCHED_IDLE_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 928a626725e6..b13474825130 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -531,6 +531,13 @@ enum { static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { + /* + * The atomic_read() below prevents CSE. The following should + * help the compiler generate more efficient code on architectures + * where sync_core_before_usermode() is a no-op. + */ + if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE)) + return; if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d5d03d919df8..1ef1edbaaf79 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -136,7 +136,8 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - unsigned int next_posix_timer_id; + unsigned int timer_create_restore_ids:1; + atomic_t next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7f3dbafe1817..7b4301b7235f 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -25,16 +25,12 @@ enum { }; #undef SD_FLAG -#ifdef CONFIG_SCHED_DEBUG - struct sd_flag_debug { unsigned int meta_flags; char *name; }; extern const struct sd_flag_debug sd_flag_debug[]; -#endif - #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) { @@ -166,10 +162,6 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } -extern void partition_sched_domains_locked(int ndoms_new, - cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new); - extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); @@ -211,12 +203,6 @@ extern void __init set_sched_topology(struct sched_domain_topology_level *tl); struct sched_domain_attr; static inline void -partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ -} - -static inline void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 836a7e200f39..6719949135c9 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -222,7 +222,6 @@ struct sctp_datahdr { __be16 stream; __be16 ssn; __u32 ppid; - /* __u8 payload[]; */ }; struct sctp_data_chunk { @@ -239,7 +238,6 @@ struct sctp_idatahdr { __u32 ppid; __be32 fsn; }; - __u8 payload[0]; }; struct sctp_idata_chunk { diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index e45531455d3b..9b959972bf4a 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -22,21 +22,17 @@ #include <linux/atomic.h> #include <asm/seccomp.h> +extern int __secure_computing(void); + #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -extern int __secure_computing(const struct seccomp_data *sd); static inline int secure_computing(void) { if (unlikely(test_syscall_work(SECCOMP))) - return __secure_computing(NULL); + return __secure_computing(); return 0; } #else extern void secure_computing_strict(int this_syscall); -static inline int __secure_computing(const struct seccomp_data *sd) -{ - secure_computing_strict(sd->nr); - return 0; -} #endif extern long prctl_get_seccomp(void); @@ -58,7 +54,7 @@ static inline int secure_computing(void) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } +static inline int __secure_computing(void) { return 0; } static inline long prctl_get_seccomp(void) { diff --git a/include/linux/security.h b/include/linux/security.h index 980b6c207cad..1545d515a66b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2324,14 +2324,13 @@ struct perf_event_attr; struct perf_event; #ifdef CONFIG_SECURITY -extern int security_perf_event_open(struct perf_event_attr *attr, int type); +extern int security_perf_event_open(int type); extern int security_perf_event_alloc(struct perf_event *event); extern void security_perf_event_free(struct perf_event *event); extern int security_perf_event_read(struct perf_event *event); extern int security_perf_event_write(struct perf_event *event); #else -static inline int security_perf_event_open(struct perf_event_attr *attr, - int type) +static inline int security_perf_event_open(int type) { return 0; } @@ -2362,6 +2361,7 @@ static inline int security_perf_event_write(struct perf_event *event) extern int security_uring_override_creds(const struct cred *new); extern int security_uring_sqpoll(void); extern int security_uring_cmd(struct io_uring_cmd *ioucmd); +extern int security_uring_allowed(void); #else static inline int security_uring_override_creds(const struct cred *new) { @@ -2375,6 +2375,10 @@ static inline int security_uring_cmd(struct io_uring_cmd *ioucmd) { return 0; } +static inline int security_uring_allowed(void) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_IO_URING */ diff --git a/include/linux/sizes.h b/include/linux/sizes.h index c3a00b967d18..49039494076f 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -23,17 +23,25 @@ #define SZ_4K 0x00001000 #define SZ_8K 0x00002000 #define SZ_16K 0x00004000 +#define SZ_24K 0x00006000 #define SZ_32K 0x00008000 #define SZ_64K 0x00010000 #define SZ_128K 0x00020000 +#define SZ_192K 0x00030000 #define SZ_256K 0x00040000 +#define SZ_384K 0x00060000 #define SZ_512K 0x00080000 #define SZ_1M 0x00100000 #define SZ_2M 0x00200000 +#define SZ_3M 0x00300000 #define SZ_4M 0x00400000 +#define SZ_6M 0x00600000 #define SZ_8M 0x00800000 +#define SZ_12M 0x00c00000 #define SZ_16M 0x01000000 +#define SZ_18M 0x01200000 +#define SZ_24M 0x01800000 #define SZ_32M 0x02000000 #define SZ_64M 0x04000000 #define SZ_128M 0x08000000 diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bb2b751d274a..b974a277975a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -470,7 +470,7 @@ struct skb_shared_hwtstamps { /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ - SKBTX_HW_TSTAMP = 1 << 0, + SKBTX_HW_TSTAMP_NOBPF = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, @@ -478,8 +478,8 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, - /* generate hardware time stamp based on cycles if supported */ - SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, + /* generate software time stamp on packet tx completion */ + SKBTX_COMPLETION_TSTAMP = 1 << 3, /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, @@ -489,12 +489,18 @@ enum { /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, + + /* used for bpf extension when a bpf program is loaded */ + SKBTX_BPF = 1 << 7, }; +#define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) + #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ - SKBTX_SCHED_TSTAMP) + SKBTX_SCHED_TSTAMP | \ + SKBTX_BPF | \ + SKBTX_COMPLETION_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ - SKBTX_HW_TSTAMP_USE_CYCLES | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ @@ -703,6 +709,8 @@ enum { SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, + + SKB_GSO_TCP_ACCECN = 1 << 19, }; #if BITS_PER_LONG > 32 @@ -1315,6 +1323,7 @@ struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); +u32 napi_skb_cache_get_bulk(void **skbs, u32 n); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); @@ -1527,14 +1536,8 @@ void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); -__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, - const void *data, int hlen_proto); - -static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, - int thoff, u8 ip_proto) -{ - return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); -} +__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + const void *data, int hlen_proto); void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, @@ -3865,25 +3868,6 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; -static inline int skb_add_data(struct sk_buff *skb, - struct iov_iter *from, int copy) -{ - const int off = skb->len; - - if (skb->ip_summed == CHECKSUM_NONE) { - __wsum csum = 0; - if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy, - &csum, from)) { - skb->csum = csum_block_add(skb->csum, csum, off); - return 0; - } - } else if (copy_from_iter_full(skb_put(skb, copy), copy, from)) - return 0; - - __skb_trim(skb, off); - return -EFAULT; -} - static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { @@ -4564,7 +4548,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); - if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP) + if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF)) skb_tstamp_tx(skb, NULL); } diff --git a/include/linux/slab.h b/include/linux/slab.h index 09eedaecf120..98e07e9e9e58 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -16,6 +16,7 @@ #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> +#include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> @@ -941,8 +942,6 @@ static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t siz if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc_noprof(bytes, flags); return kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) @@ -1082,6 +1081,19 @@ extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); +#ifndef CONFIG_KVFREE_RCU_BATCHED +static inline void kvfree_rcu_barrier(void) +{ + rcu_barrier(); +} + +static inline void kfree_rcu_scheduler_running(void) { } +#else +void kvfree_rcu_barrier(void); + +void kfree_rcu_scheduler_running(void); +#endif + /** * kmalloc_size_roundup - Report allocation bucket size for the given size * diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index c06d17599ae7..736f53018017 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -56,7 +56,7 @@ struct apple_rtkit_shmem { * context. */ struct apple_rtkit_ops { - void (*crashed)(void *cookie); + void (*crashed)(void *cookie, const void *crashlog, size_t crashlog_size); void (*recv_message)(void *cookie, u8 endpoint, u64 message); bool (*recv_message_early)(void *cookie, u8 endpoint, u64 message); int (*shmem_setup)(void *cookie, struct apple_rtkit_shmem *bfr); diff --git a/include/linux/spi/offload/consumer.h b/include/linux/spi/offload/consumer.h new file mode 100644 index 000000000000..cd7d5daa21e6 --- /dev/null +++ b/include/linux/spi/offload/consumer.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Analog Devices Inc. + * Copyright (C) 2024 BayLibre, SAS + */ + +#ifndef __LINUX_SPI_OFFLOAD_CONSUMER_H +#define __LINUX_SPI_OFFLOAD_CONSUMER_H + +#include <linux/module.h> +#include <linux/spi/offload/types.h> +#include <linux/types.h> + +MODULE_IMPORT_NS("SPI_OFFLOAD"); + +struct device; +struct spi_device; + +struct spi_offload *devm_spi_offload_get(struct device *dev, struct spi_device *spi, + const struct spi_offload_config *config); + +struct spi_offload_trigger +*devm_spi_offload_trigger_get(struct device *dev, + struct spi_offload *offload, + enum spi_offload_trigger_type type); +int spi_offload_trigger_validate(struct spi_offload_trigger *trigger, + struct spi_offload_trigger_config *config); +int spi_offload_trigger_enable(struct spi_offload *offload, + struct spi_offload_trigger *trigger, + struct spi_offload_trigger_config *config); +void spi_offload_trigger_disable(struct spi_offload *offload, + struct spi_offload_trigger *trigger); + +struct dma_chan *devm_spi_offload_tx_stream_request_dma_chan(struct device *dev, + struct spi_offload *offload); +struct dma_chan *devm_spi_offload_rx_stream_request_dma_chan(struct device *dev, + struct spi_offload *offload); + +#endif /* __LINUX_SPI_OFFLOAD_CONSUMER_H */ diff --git a/include/linux/spi/offload/provider.h b/include/linux/spi/offload/provider.h new file mode 100644 index 000000000000..76c7cf651092 --- /dev/null +++ b/include/linux/spi/offload/provider.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Analog Devices Inc. + * Copyright (C) 2024 BayLibre, SAS + */ + +#ifndef __LINUX_SPI_OFFLOAD_PROVIDER_H +#define __LINUX_SPI_OFFLOAD_PROVIDER_H + +#include <linux/module.h> +#include <linux/spi/offload/types.h> +#include <linux/types.h> + +MODULE_IMPORT_NS("SPI_OFFLOAD"); + +struct device; +struct spi_offload_trigger; + +struct spi_offload *devm_spi_offload_alloc(struct device *dev, size_t priv_size); + +struct spi_offload_trigger_ops { + bool (*match)(struct spi_offload_trigger *trigger, + enum spi_offload_trigger_type type, u64 *args, u32 nargs); + int (*request)(struct spi_offload_trigger *trigger, + enum spi_offload_trigger_type type, u64 *args, u32 nargs); + void (*release)(struct spi_offload_trigger *trigger); + int (*validate)(struct spi_offload_trigger *trigger, + struct spi_offload_trigger_config *config); + int (*enable)(struct spi_offload_trigger *trigger, + struct spi_offload_trigger_config *config); + void (*disable)(struct spi_offload_trigger *trigger); +}; + +struct spi_offload_trigger_info { + /** @fwnode: Provider fwnode, used to match to consumer. */ + struct fwnode_handle *fwnode; + /** @ops: Provider-specific callbacks. */ + const struct spi_offload_trigger_ops *ops; + /** Provider-specific state to be used in callbacks. */ + void *priv; +}; + +int devm_spi_offload_trigger_register(struct device *dev, + struct spi_offload_trigger_info *info); +void *spi_offload_trigger_get_priv(struct spi_offload_trigger *trigger); + +#endif /* __LINUX_SPI_OFFLOAD_PROVIDER_H */ diff --git a/include/linux/spi/offload/types.h b/include/linux/spi/offload/types.h new file mode 100644 index 000000000000..6f7892347871 --- /dev/null +++ b/include/linux/spi/offload/types.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Analog Devices Inc. + * Copyright (C) 2024 BayLibre, SAS + */ + +#ifndef __LINUX_SPI_OFFLOAD_TYPES_H +#define __LINUX_SPI_OFFLOAD_TYPES_H + +#include <linux/bits.h> +#include <linux/types.h> + +struct device; + +/* This is write xfer but TX uses external data stream rather than tx_buf. */ +#define SPI_OFFLOAD_XFER_TX_STREAM BIT(0) +/* This is read xfer but RX uses external data stream rather than rx_buf. */ +#define SPI_OFFLOAD_XFER_RX_STREAM BIT(1) + +/* Offload can be triggered by external hardware event. */ +#define SPI_OFFLOAD_CAP_TRIGGER BIT(0) +/* Offload can record and then play back TX data when triggered. */ +#define SPI_OFFLOAD_CAP_TX_STATIC_DATA BIT(1) +/* Offload can get TX data from an external stream source. */ +#define SPI_OFFLOAD_CAP_TX_STREAM_DMA BIT(2) +/* Offload can send RX data to an external stream sink. */ +#define SPI_OFFLOAD_CAP_RX_STREAM_DMA BIT(3) + +/** + * struct spi_offload_config - offload configuration + * + * This is used to request an offload with specific configuration. + */ +struct spi_offload_config { + /** @capability_flags: required capabilities. See %SPI_OFFLOAD_CAP_* */ + u32 capability_flags; +}; + +/** + * struct spi_offload - offload instance + */ +struct spi_offload { + /** @provider_dev: for get/put reference counting */ + struct device *provider_dev; + /** @priv: provider driver private data */ + void *priv; + /** @ops: callbacks for offload support */ + const struct spi_offload_ops *ops; + /** @xfer_flags: %SPI_OFFLOAD_XFER_* flags supported by provider */ + u32 xfer_flags; +}; + +enum spi_offload_trigger_type { + /* Indication from SPI peripheral that data is read to read. */ + SPI_OFFLOAD_TRIGGER_DATA_READY, + /* Trigger comes from a periodic source such as a clock. */ + SPI_OFFLOAD_TRIGGER_PERIODIC, +}; + +struct spi_offload_trigger_periodic { + u64 frequency_hz; +}; + +struct spi_offload_trigger_config { + /** @type: type discriminator for union */ + enum spi_offload_trigger_type type; + union { + struct spi_offload_trigger_periodic periodic; + }; +}; + +/** + * struct spi_offload_ops - callbacks implemented by offload providers + */ +struct spi_offload_ops { + /** + * @trigger_enable: Optional callback to enable the trigger for the + * given offload instance. + */ + int (*trigger_enable)(struct spi_offload *offload); + /** + * @trigger_disable: Optional callback to disable the trigger for the + * given offload instance. + */ + void (*trigger_disable)(struct spi_offload *offload); + /** + * @tx_stream_request_dma_chan: Optional callback for controllers that + * have an offload where the TX data stream is connected directly to a + * DMA channel. + */ + struct dma_chan *(*tx_stream_request_dma_chan)(struct spi_offload *offload); + /** + * @rx_stream_request_dma_chan: Optional callback for controllers that + * have an offload where the RX data stream is connected directly to a + * DMA channel. + */ + struct dma_chan *(*rx_stream_request_dma_chan)(struct spi_offload *offload); +}; + +#endif /* __LINUX_SPI_OFFLOAD_TYPES_H */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8497f4747e24..0ba5e49bace4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -31,9 +31,11 @@ struct spi_transfer; struct spi_controller_mem_ops; struct spi_controller_mem_caps; struct spi_message; +struct spi_offload; +struct spi_offload_config; /* - * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, + * INTERFACES between SPI controller-side drivers and SPI target protocol handlers, * and SPI infrastructure. */ extern const struct bus_type spi_bus_type; @@ -128,7 +130,7 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, struct spi_transfer *xfer); /** - * struct spi_device - Controller side proxy for an SPI slave device + * struct spi_device - Controller side proxy for an SPI target device * @dev: Driver model representation of the device. * @controller: SPI controller used with the device. * @max_speed_hz: Maximum clock rate to be used with this chip @@ -172,7 +174,7 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * @pcpu_statistics: statistics for the spi_device * @cs_index_mask: Bit mask of the active chipselect(s) in the chipselect array * - * A @spi_device is used to interchange data between an SPI slave + * A @spi_device is used to interchange data between an SPI target device * (usually a discrete chip) and CPU memory. * * In @dev, the platform_data is used to hold information about this @@ -386,15 +388,15 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch spi_unregister_driver) /** - * struct spi_controller - interface to SPI master or slave controller + * struct spi_controller - interface to SPI host or target controller * @dev: device interface to this driver * @list: link with the global spi_controller list * @bus_num: board-specific (and often SOC-specific) identifier for a * given SPI controller. * @num_chipselect: chipselects are used to distinguish individual - * SPI slaves, and are numbered from zero to num_chipselects. - * each slave has a chipselect signal, but it's common that not - * every chipselect is connected to a slave. + * SPI targets, and are numbered from zero to num_chipselects. + * each target has a chipselect signal, but it's common that not + * every chipselect is connected to a target. * @dma_alignment: SPI controller constraint on DMA buffers alignment. * @mode_bits: flags understood by this controller driver * @buswidth_override_bits: flags to override for this controller driver @@ -423,9 +425,9 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * must fail if an unrecognized or unsupported mode is requested. * It's always safe to call this unless transfers are pending on * the device whose settings are being modified. - * @set_cs_timing: optional hook for SPI devices to request SPI master + * @set_cs_timing: optional hook for SPI devices to request SPI * controller for configuring specific CS setup time, hold time and inactive - * delay interms of clock counts + * delay in terms of clock counts * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA @@ -496,6 +498,10 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @mem_ops: optimized/dedicated operations for interactions with SPI memory. * This field is optional and should only be implemented if the * controller has native support for memory like operations. + * @get_offload: callback for controllers with offload support to get matching + * offload instance. Implementations should return -ENODEV if no match is + * found. + * @put_offload: release the offload instance acquired by @get_offload. * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). * @target_abort: abort the ongoing transfer request on an SPI target controller @@ -541,7 +547,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * * The driver for an SPI controller manages access to those devices through * a queue of spi_message transactions, copying data between CPU memory and - * an SPI slave device. For each such message it queues, it calls the + * an SPI target device. For each such message it queues, it calls the * message's completion function when the transaction completes. */ struct spi_controller { @@ -591,7 +597,7 @@ struct spi_controller { #define SPI_CONTROLLER_NO_TX BIT(2) /* Can't do buffer write */ #define SPI_CONTROLLER_MUST_RX BIT(3) /* Requires rx */ #define SPI_CONTROLLER_MUST_TX BIT(4) /* Requires tx */ -#define SPI_CONTROLLER_GPIO_SS BIT(5) /* GPIO CS must select slave */ +#define SPI_CONTROLLER_GPIO_SS BIT(5) /* GPIO CS must select target device */ #define SPI_CONTROLLER_SUSPENDED BIT(6) /* Currently suspended */ /* * The spi-controller has multi chip select capability and can @@ -658,7 +664,7 @@ struct spi_controller { * + To a given spi_device, message queueing is pure FIFO * * + The controller's main job is to process its message queue, - * selecting a chip (for masters), then transferring data + * selecting a chip (for controllers), then transferring data * + If there are multiple spi_device children, the i/o queue * arbitration algorithm is unspecified (round robin, FIFO, * priority, reservations, preemption, etc) @@ -740,6 +746,10 @@ struct spi_controller { const struct spi_controller_mem_ops *mem_ops; const struct spi_controller_mem_caps *mem_caps; + struct spi_offload *(*get_offload)(struct spi_device *spi, + const struct spi_offload_config *config); + void (*put_offload)(struct spi_offload *offload); + /* GPIO chip select */ struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; @@ -822,7 +832,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr, /* The SPI driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, - unsigned int size, bool slave); + unsigned int size, bool target); static inline struct spi_controller *spi_alloc_host(struct device *dev, unsigned int size) @@ -841,7 +851,7 @@ static inline struct spi_controller *spi_alloc_target(struct device *dev, struct spi_controller *__devm_spi_alloc_controller(struct device *dev, unsigned int size, - bool slave); + bool target); static inline struct spi_controller *devm_spi_alloc_host(struct device *dev, unsigned int size) @@ -963,6 +973,8 @@ struct spi_res { * @rx_sg_mapped: If true, the @rx_sg is mapped for DMA * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use + * @offload_flags: Flags that are only applicable to specialized SPI offload + * transfers. See %SPI_OFFLOAD_XFER_* in spi-offload.h. * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset * within @tx_buf for which the SPI device is requesting that the time * snapshot for this transfer begins. Upon completing the SPI transfer, @@ -977,12 +989,12 @@ struct spi_res { * purposefully (instead of setting to spi_transfer->len - 1) to denote * that a transfer-level snapshot taken from within the driver may still * be of higher quality. - * @ptp_sts: Pointer to a memory location held by the SPI slave device where a + * @ptp_sts: Pointer to a memory location held by the SPI target device where a * PTP system timestamp structure may lie. If drivers use PIO or their * hardware has some sort of assist for retrieving exact transfer timing, * they can (and should) assert @ptp_sts_supported and populate this * structure using the ptp_read_system_*ts helper functions. - * The timestamp must represent the time at which the SPI slave device has + * The timestamp must represent the time at which the SPI target device has * processed the word, i.e. the "pre" timestamp should be taken before * transmitting the "pre" word, and the "post" timestamp after receiving * transmit confirmation from the controller for the "post" word. @@ -1083,6 +1095,9 @@ struct spi_transfer { u32 effective_speed_hz; + /* Use %SPI_OFFLOAD_XFER_* from spi-offload.h */ + unsigned int offload_flags; + unsigned int ptp_sts_word_pre; unsigned int ptp_sts_word_post; @@ -1108,6 +1123,7 @@ struct spi_transfer { * @state: for use by whichever driver currently owns the message * @opt_state: for use by whichever driver currently owns the message * @resources: for resource management when the SPI message is processed + * @offload: (optional) offload instance used by this message * * A @spi_message is used to execute an atomic sequence of data transfers, * each represented by a struct spi_transfer. The sequence is "atomic" @@ -1168,6 +1184,12 @@ struct spi_message { */ void *opt_state; + /* + * Optional offload instance used by this message. This must be set + * by the peripheral driver before calling spi_optimize_message(). + */ + struct spi_offload *offload; + /* List of spi_res resources when the SPI message is processed */ struct list_head resources; }; @@ -1600,7 +1622,7 @@ struct spi_board_info { * bus_num is board specific and matches the bus_num of some * spi_controller that will probably be registered later. * - * chip_select reflects how this chip is wired to that master; + * chip_select reflects how this chip is wired to that controller; * it's less than num_chipselect. */ u16 bus_num; diff --git a/include/linux/srcu.h b/include/linux/srcu.h index d7ba46e74f58..900b0d5c05f5 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -47,7 +47,13 @@ int init_srcu_struct(struct srcu_struct *ssp); #define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). #define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). #define SRCU_READ_FLAVOR_LITE 0x4 // srcu_read_lock_lite(). -#define SRCU_READ_FLAVOR_ALL 0x7 // All of the above. +#define SRCU_READ_FLAVOR_FAST 0x8 // srcu_read_lock_fast(). +#define SRCU_READ_FLAVOR_ALL (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \ + SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST) // All of the above. +#define SRCU_READ_FLAVOR_SLOWGP (SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST) + // Flavors requiring synchronize_rcu() + // instead of smp_mb(). +void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> @@ -60,15 +66,6 @@ int init_srcu_struct(struct srcu_struct *ssp); void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); -int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); -void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); -#ifdef CONFIG_TINY_SRCU -#define __srcu_read_lock_lite __srcu_read_lock -#define __srcu_read_unlock_lite __srcu_read_unlock -#else // #ifdef CONFIG_TINY_SRCU -int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); -void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); -#endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 @@ -258,6 +255,51 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) } /** + * srcu_read_lock_fast - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section, but for a light-weight + * smp_mb()-free reader. See srcu_read_lock() for more information. + * + * If srcu_read_lock_fast() is ever used on an srcu_struct structure, + * then none of the other flavors may be used, whether before, during, + * or after. Note that grace-period auto-expediting is disabled for _fast + * srcu_struct structures because auto-expedited grace periods invoke + * synchronize_rcu_expedited(), IPIs and all. + * + * Note that srcu_read_lock_fast() can be invoked only from those contexts + * where RCU is watching, that is, from contexts where it would be legal + * to invoke rcu_read_lock(). Otherwise, lockdep will complain. + */ +static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *ssp) __acquires(ssp) +{ + struct srcu_ctr __percpu *retval; + + srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST); + retval = __srcu_read_lock_fast(ssp); + rcu_try_lock_acquire(&ssp->dep_map); + return retval; +} + +/** + * srcu_down_read_fast - register a new reader for an SRCU-protected structure. + * @ssp: srcu_struct in which to register the new reader. + * + * Enter a semaphore-like SRCU read-side critical section, but for + * a light-weight smp_mb()-free reader. See srcu_read_lock_fast() and + * srcu_down_read() for more information. + * + * The same srcu_struct may be used concurrently by srcu_down_read_fast() + * and srcu_read_lock_fast(). + */ +static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires(ssp) +{ + WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); + srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST); + return __srcu_read_lock_fast(ssp); +} + +/** * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * @@ -278,7 +320,7 @@ static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) { int retval; - srcu_check_read_flavor_lite(ssp); + srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_LITE); retval = __srcu_read_lock_lite(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; @@ -335,7 +377,8 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in - * which calls to down_read() may be nested. + * which calls to down_read() may be nested. The same srcu_struct may be + * used concurrently by srcu_down_read() and srcu_read_lock(). */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { @@ -361,9 +404,40 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) } /** + * srcu_read_unlock_fast - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @scp: return value from corresponding srcu_read_lock_fast(). + * + * Exit a light-weight SRCU read-side critical section. + */ +static inline void srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) + __releases(ssp) +{ + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); + srcu_lock_release(&ssp->dep_map); + __srcu_read_unlock_fast(ssp, scp); +} + +/** + * srcu_up_read_fast - unregister a old reader from an SRCU-protected structure. + * @ssp: srcu_struct in which to unregister the old reader. + * @scp: return value from corresponding srcu_read_lock_fast(). + * + * Exit an SRCU read-side critical section, but not necessarily from + * the same context as the maching srcu_down_read_fast(). + */ +static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) + __releases(ssp) +{ + WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); + srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); + __srcu_read_unlock_fast(ssp, scp); +} + +/** * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. - * @idx: return value from corresponding srcu_read_lock(). + * @idx: return value from corresponding srcu_read_lock_lite(). * * Exit a light-weight SRCU read-side critical section. */ @@ -379,7 +453,7 @@ static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. - * @idx: return value from corresponding srcu_read_lock(). + * @idx: return value from corresponding srcu_read_lock_nmisafe(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 1321da803274..380260317d98 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -64,13 +64,38 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; - preempt_disable(); // Needed for PREEMPT_AUTO + preempt_disable(); // Needed for PREEMPT_LAZY idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); preempt_enable(); return idx; } +struct srcu_ctr; + +static inline bool __srcu_ptr_to_ctr(struct srcu_struct *ssp, struct srcu_ctr __percpu *scpp) +{ + return (int)(intptr_t)(struct srcu_ctr __force __kernel *)scpp; +} + +static inline struct srcu_ctr __percpu *__srcu_ctr_to_ptr(struct srcu_struct *ssp, int idx) +{ + return (struct srcu_ctr __percpu *)(intptr_t)idx; +} + +static inline struct srcu_ctr __percpu *__srcu_read_lock_fast(struct srcu_struct *ssp) +{ + return __srcu_ctr_to_ptr(ssp, __srcu_read_lock(ssp)); +} + +static inline void __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) +{ + __srcu_read_unlock(ssp, __srcu_ptr_to_ctr(ssp, scp)); +} + +#define __srcu_read_lock_lite __srcu_read_lock +#define __srcu_read_unlock_lite __srcu_read_unlock + static inline void synchronize_srcu_expedited(struct srcu_struct *ssp) { synchronize_srcu(ssp); @@ -82,7 +107,7 @@ static inline void srcu_barrier(struct srcu_struct *ssp) } #define srcu_check_read_flavor(ssp, read_flavor) do { } while (0) -#define srcu_check_read_flavor_lite(ssp) do { } while (0) +#define srcu_check_read_flavor_force(ssp, read_flavor) do { } while (0) /* Defined here to avoid size increase for non-torture kernels. */ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index b17814c9d1c7..8bed7e6cc4c1 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -17,14 +17,19 @@ struct srcu_node; struct srcu_struct; +/* One element of the srcu_data srcu_ctrs array. */ +struct srcu_ctr { + atomic_long_t srcu_locks; /* Locks per CPU. */ + atomic_long_t srcu_unlocks; /* Unlocks per CPU. */ +}; + /* * Per-CPU structure feeding into leaf srcu_node, similar in function * to rcu_node. */ struct srcu_data { /* Read-side state. */ - atomic_long_t srcu_lock_count[2]; /* Locks per CPU. */ - atomic_long_t srcu_unlock_count[2]; /* Unlocks per CPU. */ + struct srcu_ctr srcu_ctrs[2]; /* Locks and unlocks per CPU. */ int srcu_reader_flavor; /* Reader flavor for srcu_struct structure? */ /* Values: SRCU_READ_FLAVOR_.* */ @@ -95,7 +100,7 @@ struct srcu_usage { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - unsigned int srcu_idx; /* Current rdr array element. */ + struct srcu_ctr __percpu *srcu_ctrp; struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ struct lockdep_map dep_map; struct srcu_usage *srcu_sup; /* Update-side data. */ @@ -162,6 +167,7 @@ struct srcu_struct { #define __SRCU_STRUCT_INIT(name, usage_name, pcpu_name) \ { \ .sda = &pcpu_name, \ + .srcu_ctrp = &pcpu_name.srcu_ctrs[0], \ __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ } @@ -201,10 +207,77 @@ struct srcu_struct { #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) +int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void synchronize_srcu_expedited(struct srcu_struct *ssp); void srcu_barrier(struct srcu_struct *ssp); void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf); +// Converts a per-CPU pointer to an ->srcu_ctrs[] array element to that +// element's index. +static inline bool __srcu_ptr_to_ctr(struct srcu_struct *ssp, struct srcu_ctr __percpu *scpp) +{ + return scpp - &ssp->sda->srcu_ctrs[0]; +} + +// Converts an integer to a per-CPU pointer to the corresponding +// ->srcu_ctrs[] array element. +static inline struct srcu_ctr __percpu *__srcu_ctr_to_ptr(struct srcu_struct *ssp, int idx) +{ + return &ssp->sda->srcu_ctrs[idx]; +} + +/* + * Counts the new reader in the appropriate per-CPU element of the + * srcu_struct. Returns a pointer that must be passed to the matching + * srcu_read_unlock_fast(). + * + * Note that both this_cpu_inc() and atomic_long_inc() are RCU read-side + * critical sections either because they disables interrupts, because they + * are a single instruction, or because they are a read-modify-write atomic + * operation, depending on the whims of the architecture. + * + * This means that __srcu_read_lock_fast() is not all that fast + * on architectures that support NMIs but do not supply NMI-safe + * implementations of this_cpu_inc(). + */ +static inline struct srcu_ctr __percpu *__srcu_read_lock_fast(struct srcu_struct *ssp) +{ + struct srcu_ctr __percpu *scp = READ_ONCE(ssp->srcu_ctrp); + + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_fast()."); + if (!IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) + this_cpu_inc(scp->srcu_locks.counter); /* Y */ + else + atomic_long_inc(raw_cpu_ptr(&scp->srcu_locks)); /* Z */ + barrier(); /* Avoid leaking the critical section. */ + return scp; +} + +/* + * Removes the count for the old reader from the appropriate + * per-CPU element of the srcu_struct. Note that this may well be a + * different CPU than that which was incremented by the corresponding + * srcu_read_lock_fast(), but it must be within the same task. + * + * Note that both this_cpu_inc() and atomic_long_inc() are RCU read-side + * critical sections either because they disables interrupts, because they + * are a single instruction, or because they are a read-modify-write atomic + * operation, depending on the whims of the architecture. + * + * This means that __srcu_read_unlock_fast() is not all that fast + * on architectures that support NMIs but do not supply NMI-safe + * implementations of this_cpu_inc(). + */ +static inline void __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) +{ + barrier(); /* Avoid leaking the critical section. */ + if (!IS_ENABLED(CONFIG_NEED_SRCU_NMI_SAFE)) + this_cpu_inc(scp->srcu_unlocks.counter); /* Z */ + else + atomic_long_inc(raw_cpu_ptr(&scp->srcu_unlocks)); /* Z */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast()."); +} + /* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. Returns an index that must be passed to the matching @@ -217,13 +290,12 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf); */ static inline int __srcu_read_lock_lite(struct srcu_struct *ssp) { - int idx; + struct srcu_ctr __percpu *scp = READ_ONCE(ssp->srcu_ctrp); RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite()."); - idx = READ_ONCE(ssp->srcu_idx) & 0x1; - this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); /* Y */ + this_cpu_inc(scp->srcu_locks.counter); /* Y */ barrier(); /* Avoid leaking the critical section. */ - return idx; + return __srcu_ptr_to_ctr(ssp, scp); } /* @@ -240,22 +312,24 @@ static inline int __srcu_read_lock_lite(struct srcu_struct *ssp) static inline void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) { barrier(); /* Avoid leaking the critical section. */ - this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter); /* Z */ + this_cpu_inc(__srcu_ctr_to_ptr(ssp, idx)->srcu_unlocks.counter); /* Z */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite()."); } void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor); -// Record _lite() usage even for CONFIG_PROVE_RCU=n kernels. -static inline void srcu_check_read_flavor_lite(struct srcu_struct *ssp) +// Record reader usage even for CONFIG_PROVE_RCU=n kernels. This is +// needed only for flavors that require grace-period smp_mb() calls to be +// promoted to synchronize_rcu(). +static inline void srcu_check_read_flavor_force(struct srcu_struct *ssp, int read_flavor) { struct srcu_data *sdp = raw_cpu_ptr(ssp->sda); - if (likely(READ_ONCE(sdp->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)) + if (likely(READ_ONCE(sdp->srcu_reader_flavor) & read_flavor)) return; // Note that the cmpxchg() in __srcu_check_read_flavor() is fully ordered. - __srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); + __srcu_check_read_flavor(ssp, read_flavor); } // Record non-_lite() usage only for CONFIG_PROVE_RCU=y kernels. diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c9878a612e53..c4ec8bb8144e 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -78,6 +78,7 @@ | DMA_AXI_BLEN_32 | DMA_AXI_BLEN_64 \ | DMA_AXI_BLEN_128 | DMA_AXI_BLEN_256) +struct clk; struct stmmac_priv; /* Platfrom data for platform device structure's platform_data field */ @@ -182,7 +183,8 @@ struct dwmac4_addrs { #define STMMAC_FLAG_INT_SNAPSHOT_EN BIT(9) #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI BIT(10) #define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING BIT(11) -#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(12) +#define STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP BIT(12) +#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(13) struct plat_stmmacenet_data { int bus_id; @@ -231,11 +233,17 @@ struct plat_stmmacenet_data { u8 tx_sched_algorithm; struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; - void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); + int (*set_clk_tx_rate)(void *priv, struct clk *clk_tx_i, + phy_interface_t interface, int speed); + void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); + int (*mac_finish)(struct net_device *ndev, + void *priv, + unsigned int mode, + phy_interface_t interface); void (*ptp_clk_freq_config)(struct stmmac_priv *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); @@ -252,8 +260,11 @@ struct plat_stmmacenet_data { struct clk *stmmac_clk; struct clk *pclk; struct clk *clk_ptp_ref; + struct clk *clk_tx_i; /* clk_tx_i to MAC core */ unsigned long clk_ptp_rate; unsigned long clk_ref_rate; + struct clk_bulk_data *clks; + int num_clks; unsigned int mult_fact_100ns; s32 ptp_max_adj; u32 cdc_error_adj; diff --git a/include/linux/string.h b/include/linux/string.h index f8e21e80942f..0403a4ca4c11 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -415,8 +415,10 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define strtomem_pad(dest, src, pad) do { \ const size_t _dest_len = __must_be_byte_array(dest) + \ + __must_be_noncstr(dest) + \ ARRAY_SIZE(dest); \ - const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_len = __must_be_cstr(src) + \ + __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ @@ -439,8 +441,10 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define strtomem(dest, src) do { \ const size_t _dest_len = __must_be_byte_array(dest) + \ + __must_be_noncstr(dest) + \ ARRAY_SIZE(dest); \ - const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_len = __must_be_cstr(src) + \ + __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ _dest_len == (size_t)-1); \ @@ -459,8 +463,10 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define memtostr(dest, src) do { \ const size_t _dest_len = __must_be_byte_array(dest) + \ + __must_be_cstr(dest) + \ ARRAY_SIZE(dest); \ - const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_len = __must_be_noncstr(src) + \ + __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ \ @@ -485,8 +491,10 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, */ #define memtostr_pad(dest, src) do { \ const size_t _dest_len = __must_be_byte_array(dest) + \ + __must_be_cstr(dest) + \ ARRAY_SIZE(dest); \ - const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_len = __must_be_noncstr(src) + \ + __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ \ diff --git a/include/linux/string_choices.h b/include/linux/string_choices.h index 120ca0f28e95..f3ba4f52ff26 100644 --- a/include/linux/string_choices.h +++ b/include/linux/string_choices.h @@ -41,23 +41,23 @@ static inline const char *str_high_low(bool v) } #define str_low_high(v) str_high_low(!(v)) -static inline const char *str_read_write(bool v) -{ - return v ? "read" : "write"; -} -#define str_write_read(v) str_read_write(!(v)) - static inline const char *str_on_off(bool v) { return v ? "on" : "off"; } #define str_off_on(v) str_on_off(!(v)) -static inline const char *str_yes_no(bool v) +static inline const char *str_read_write(bool v) { - return v ? "yes" : "no"; + return v ? "read" : "write"; } -#define str_no_yes(v) str_yes_no(!(v)) +#define str_write_read(v) str_read_write(!(v)) + +static inline const char *str_true_false(bool v) +{ + return v ? "true" : "false"; +} +#define str_false_true(v) str_true_false(!(v)) static inline const char *str_up_down(bool v) { @@ -65,11 +65,11 @@ static inline const char *str_up_down(bool v) } #define str_down_up(v) str_up_down(!(v)) -static inline const char *str_true_false(bool v) +static inline const char *str_yes_no(bool v) { - return v ? "true" : "false"; + return v ? "yes" : "no"; } -#define str_false_true(v) str_true_false(!(v)) +#define str_no_yes(v) str_yes_no(!(v)) /** * str_plural - Return the simple pluralization based on English counts diff --git a/include/linux/swap.h b/include/linux/swap.h index b13b72645db3..a98c757400fe 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -433,19 +433,10 @@ extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA -extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; -#else -#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); -} - void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c6333204d451..e5603cc91963 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -951,6 +951,10 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len, int flags, uint32_t sig); asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags); +asmlinkage long sys_open_tree_attr(int dfd, const char __user *path, + unsigned flags, + struct mount_attr __user *uattr, + size_t usize); asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path, int to_dfd, const char __user *to_path, unsigned int ms_flags); @@ -1266,14 +1270,14 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, AT_SYMLINK_NOFOLLOW); } -extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); +int do_sys_ftruncate(unsigned int fd, loff_t length, int small); static inline long ksys_ftruncate(unsigned int fd, loff_t length) { return do_sys_ftruncate(fd, length, 1); } -extern long do_sys_truncate(const char __user *pathname, loff_t length); +int do_sys_truncate(const char __user *pathname, loff_t length); static inline long ksys_truncate(const char __user *pathname, loff_t length) { diff --git a/include/linux/sysv_fs.h b/include/linux/sysv_fs.h deleted file mode 100644 index 5cf77dbb8d86..000000000000 --- a/include/linux/sysv_fs.h +++ /dev/null @@ -1,214 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_SYSV_FS_H -#define _LINUX_SYSV_FS_H - -#define __packed2__ __attribute__((packed, aligned(2))) - - -#ifndef __KERNEL__ -typedef u16 __fs16; -typedef u32 __fs16; -#endif - -/* inode numbers are 16 bit */ -typedef __fs16 sysv_ino_t; - -/* Block numbers are 24 bit, sometimes stored in 32 bit. - On Coherent FS, they are always stored in PDP-11 manner: the least - significant 16 bits come last. */ -typedef __fs32 sysv_zone_t; - -/* 0 is non-existent */ -#define SYSV_BADBL_INO 1 /* inode of bad blocks file */ -#define SYSV_ROOT_INO 2 /* inode of root directory */ - - -/* Xenix super-block data on disk */ -#define XENIX_NICINOD 100 /* number of inode cache entries */ -#define XENIX_NICFREE 100 /* number of free block list chunk entries */ -struct xenix_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= XENIX_NICFREE */ - sysv_zone_t s_free[XENIX_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= XENIX_NICINOD */ - sysv_ino_t s_inode[XENIX_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_dinfo[4]; /* device information ?? */ - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - char s_clean; /* set to 0x46 when filesystem is properly unmounted */ - char s_fill[371]; - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks - 3 for 2048 byte blocks */ - -}; - -/* - * SystemV FS comes in two variants: - * sysv2: System V Release 2 (e.g. Microport), structure elements aligned(2). - * sysv4: System V Release 4 (e.g. Consensys), structure elements aligned(4). - */ -#define SYSV_NICINOD 100 /* number of inode cache entries */ -#define SYSV_NICFREE 50 /* number of free block list chunk entries */ - -/* SystemV4 super-block data on disk */ -struct sysv4_super_block { - __fs16 s_isize; /* index of first data zone */ - u16 s_pad0; - __fs32 s_fsize; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= SYSV_NICFREE */ - u16 s_pad1; - sysv_zone_t s_free[SYSV_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= SYSV_NICINOD */ - u16 s_pad2; - sysv_ino_t s_inode[SYSV_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time; /* time of last super block update */ - __fs16 s_dinfo[4]; /* device information ?? */ - __fs32 s_tfree; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - u16 s_pad3; - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - s32 s_fill[12]; - __fs32 s_state; /* file system state: 0x7c269d38-s_time means clean */ - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks */ -}; - -/* SystemV2 super-block data on disk */ -struct sysv2_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= SYSV_NICFREE */ - sysv_zone_t s_free[SYSV_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= SYSV_NICINOD */ - sysv_ino_t s_inode[SYSV_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs16 s_dinfo[4]; /* device information ?? */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - s32 s_fill[14]; - __fs32 s_state; /* file system state: 0xcb096f43 means clean */ - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks */ -}; - -/* V7 super-block data on disk */ -#define V7_NICINOD 100 /* number of inode cache entries */ -#define V7_NICFREE 50 /* number of free block list chunk entries */ -struct v7_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= V7_NICFREE */ - sysv_zone_t s_free[V7_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= V7_NICINOD */ - sysv_ino_t s_inode[V7_NICINOD]; /* some free inodes */ - /* locks, not used by Linux or V7: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - /* the following fields are not maintained by V7: */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_m; /* interleave factor */ - __fs16 s_n; /* interleave factor */ - char s_fname[6]; /* file system name */ - char s_fpack[6]; /* file system pack name */ -}; -/* Constants to aid sanity checking */ -/* This is not a hard limit, nor enforced by v7 kernel. It's actually just - * the limit used by Seventh Edition's ls, though is high enough to assume - * that no reasonable file system would have that much entries in root - * directory. Thus, if we see anything higher, we just probably got the - * endiannes wrong. */ -#define V7_NFILES 1024 -/* The disk addresses are three-byte (despite direct block addresses being - * aligned word-wise in inode). If the most significant byte is non-zero, - * something is most likely wrong (not a filesystem, bad bytesex). */ -#define V7_MAXSIZE 0x00ffffff - -/* Coherent super-block data on disk */ -#define COH_NICINOD 100 /* number of inode cache entries */ -#define COH_NICFREE 64 /* number of free block list chunk entries */ -struct coh_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= COH_NICFREE */ - sysv_zone_t s_free[COH_NICFREE] __packed2__; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= COH_NICINOD */ - sysv_ino_t s_inode[COH_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_interleave_m; /* interleave factor */ - __fs16 s_interleave_n; - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - __fs32 s_unique; /* zero, not used */ -}; - -/* SystemV/Coherent inode data on disk */ -struct sysv_inode { - __fs16 i_mode; - __fs16 i_nlink; - __fs16 i_uid; - __fs16 i_gid; - __fs32 i_size; - u8 i_data[3*(10+1+1+1)]; - u8 i_gen; - __fs32 i_atime; /* time of last access */ - __fs32 i_mtime; /* time of last modification */ - __fs32 i_ctime; /* time of creation */ -}; - -/* SystemV/Coherent directory entry on disk */ -#define SYSV_NAMELEN 14 /* max size of name in struct sysv_dir_entry */ -struct sysv_dir_entry { - sysv_ino_t inode; - char name[SYSV_NAMELEN]; /* up to 14 characters, the rest are zeroes */ -}; - -#define SYSV_DIRSIZE sizeof(struct sysv_dir_entry) /* size of every directory entry */ - -#endif /* _LINUX_SYSV_FS_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f88daaa76d83..1669d95bb0f9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -160,6 +160,8 @@ struct tcp_request_sock { u32 rcv_isn; u32 snt_isn; u32 ts_off; + u32 snt_tsval_first; + u32 snt_tsval_last; u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# @@ -242,6 +244,9 @@ struct tcp_sock { struct minmax rtt_min; /* OOO segments go in this rbtree. Socket lock must be held. */ struct rb_root out_of_order_queue; +#if defined(CONFIG_TLS_DEVICE) + void (*tcp_clean_acked)(struct sock *sk, u32 acked_seq); +#endif u32 snd_ssthresh; /* Slow start size threshold */ u8 recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_rx); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cf2446c9c30d..dd925d84fa46 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -217,54 +217,6 @@ static inline int arch_within_stack_frames(const void * const stack, } #endif -#ifdef CONFIG_HARDENED_USERCOPY -extern void __check_object_size(const void *ptr, unsigned long n, - bool to_user); - -static __always_inline void check_object_size(const void *ptr, unsigned long n, - bool to_user) -{ - if (!__builtin_constant_p(n)) - __check_object_size(ptr, n, to_user); -} -#else -static inline void check_object_size(const void *ptr, unsigned long n, - bool to_user) -{ } -#endif /* CONFIG_HARDENED_USERCOPY */ - -extern void __compiletime_error("copy source size is too small") -__bad_copy_from(void); -extern void __compiletime_error("copy destination size is too small") -__bad_copy_to(void); - -void __copy_overflow(int size, unsigned long count); - -static inline void copy_overflow(int size, unsigned long count) -{ - if (IS_ENABLED(CONFIG_BUG)) - __copy_overflow(size, count); -} - -static __always_inline __must_check bool -check_copy_size(const void *addr, size_t bytes, bool is_source) -{ - int sz = __builtin_object_size(addr, 0); - if (unlikely(sz >= 0 && sz < bytes)) { - if (!__builtin_constant_p(bytes)) - copy_overflow(sz, bytes); - else if (is_source) - __bad_copy_from(); - else - __bad_copy_to(); - return false; - } - if (WARN_ON_ONCE(bytes > INT_MAX)) - return false; - check_object_size(addr, bytes, is_source); - return true; -} - #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 876e31b4461d..0b8b32bf0655 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -165,6 +165,4 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #endif -struct vdso_data *arch_get_vdso_data(void *vvar_page); - #endif /* _LINUX_TIMENS_H */ diff --git a/include/linux/topology.h b/include/linux/topology.h index 52f5850730b3..24e715f0f6d2 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,6 +240,29 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif +#ifndef topology_is_primary_thread + +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + /* + * When disabling SMT, the primary thread of the SMT will remain + * enabled/active. Architectures that have a special primary thread + * (e.g. x86) need to override this function. Otherwise the first + * thread in the SMT can be made the primary thread. + * + * The sibling cpumask of an offline CPU always contains the CPU + * itself on architectures using the implementation of + * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. + * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for + * building their topology have to check whether to use this default + * implementation or to override it. + */ + return cpu == cpumask_first(topology_sibling_cpumask(cpu)); +} +#define topology_is_primary_thread topology_is_primary_thread + +#endif + static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); @@ -262,6 +285,36 @@ sched_numa_hop_mask(unsigned int node, unsigned int hops) #endif /* CONFIG_NUMA */ /** + * for_each_node_numadist() - iterate over nodes in increasing distance + * order, starting from a given node + * @node: the iteration variable and the starting node. + * @unvisited: a nodemask to keep track of the unvisited nodes. + * + * This macro iterates over NUMA node IDs in increasing distance from the + * starting @node and yields MAX_NUMNODES when all the nodes have been + * visited. + * + * Note that by the time the loop completes, the @unvisited nodemask will + * be fully cleared, unless the loop exits early. + * + * The difference between for_each_node() and for_each_node_numadist() is + * that the former allows to iterate over nodes in numerical order, whereas + * the latter iterates over nodes in increasing order of distance. + * + * This complexity of this iterator is O(N^2), where N represents the + * number of nodes, as each iteration involves scanning all nodes to + * find the one with the shortest distance. + * + * Requires rcu_lock to be held. + */ +#define for_each_node_numadist(node, unvisited) \ + for (int __start = (node), \ + (node) = nearest_node_nodemask((__start), &(unvisited)); \ + (node) < MAX_NUMNODES; \ + node_clear((node), (unvisited)), \ + (node) = nearest_node_nodemask((__start), &(unvisited))) + +/** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. diff --git a/include/linux/torture.h b/include/linux/torture.h index 0134e7221cae..1b59056c3b18 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -104,6 +104,7 @@ int torture_stutter_init(int s, int sgap); /* Initialization and cleanup. */ bool torture_init_begin(char *ttype, int v); void torture_init_end(void); +unsigned long get_torture_init_jiffies(void); bool torture_cleanup_begin(void); void torture_cleanup_end(void); bool torture_must_stop(void); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index e9c702c1908d..7c06f4795670 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -7,7 +7,7 @@ #include <linux/minmax.h> #include <linux/nospec.h> #include <linux/sched.h> -#include <linux/thread_info.h> +#include <linux/ucopysize.h> #include <asm/uaccess.h> diff --git a/include/linux/ucopysize.h b/include/linux/ucopysize.h new file mode 100644 index 000000000000..41c2d9720466 --- /dev/null +++ b/include/linux/ucopysize.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Perform sanity checking for object sizes for uaccess.h and uio.h. */ +#ifndef __LINUX_UCOPYSIZE_H__ +#define __LINUX_UCOPYSIZE_H__ + +#include <linux/bug.h> + +#ifdef CONFIG_HARDENED_USERCOPY +#include <linux/jump_label.h> +extern void __check_object_size(const void *ptr, unsigned long n, + bool to_user); + +DECLARE_STATIC_KEY_MAYBE(CONFIG_HARDENED_USERCOPY_DEFAULT_ON, + validate_usercopy_range); + +static __always_inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ + if (!__builtin_constant_p(n) && + static_branch_maybe(CONFIG_HARDENED_USERCOPY_DEFAULT_ON, + &validate_usercopy_range)) { + __check_object_size(ptr, n, to_user); + } +} +#else +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ } +#endif /* CONFIG_HARDENED_USERCOPY */ + +extern void __compiletime_error("copy source size is too small") +__bad_copy_from(void); +extern void __compiletime_error("copy destination size is too small") +__bad_copy_to(void); + +void __copy_overflow(int size, unsigned long count); + +static inline void copy_overflow(int size, unsigned long count) +{ + if (IS_ENABLED(CONFIG_BUG)) + __copy_overflow(size, count); +} + +static __always_inline __must_check bool +check_copy_size(const void *addr, size_t bytes, bool is_source) +{ + int sz = __builtin_object_size(addr, 0); + if (unlikely(sz >= 0 && sz < bytes)) { + if (!__builtin_constant_p(bytes)) + copy_overflow(sz, bytes); + else if (is_source) + __bad_copy_from(); + else + __bad_copy_to(); + return false; + } + if (WARN_ON_ONCE(bytes > INT_MAX)) + return false; + check_object_size(addr, bytes, is_source); + return true; +} + +#endif /* __LINUX_UCOPYSIZE_H__ */ diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index f85ec5613721..2dc767e08f54 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -132,6 +132,7 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); +u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count); #else @@ -186,6 +187,11 @@ static inline u32 map_id_down(struct uid_gid_map *map, u32 id) return id; } +static inline u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) +{ + return id; +} + static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; diff --git a/include/linux/uio.h b/include/linux/uio.h index 8ada84e85447..49ece9e1888f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -6,8 +6,8 @@ #define __LINUX_UIO_H #include <linux/kernel.h> -#include <linux/thread_info.h> #include <linux/mm_types.h> +#include <linux/ucopysize.h> #include <uapi/linux/uio.h> struct page; diff --git a/include/linux/unroll.h b/include/linux/unroll.h index d42fd6366373..863fb69f6a7e 100644 --- a/include/linux/unroll.h +++ b/include/linux/unroll.h @@ -9,6 +9,50 @@ #include <linux/args.h> +#ifdef CONFIG_CC_IS_CLANG +#define __pick_unrolled(x, y) _Pragma(#x) +#elif CONFIG_GCC_VERSION >= 80000 +#define __pick_unrolled(x, y) _Pragma(#y) +#else +#define __pick_unrolled(x, y) /* not supported */ +#endif + +/** + * unrolled - loop attributes to ask the compiler to unroll it + * + * Usage: + * + * #define BATCH 8 + * + * unrolled_count(BATCH) + * for (u32 i = 0; i < BATCH; i++) + * // loop body without cross-iteration dependencies + * + * This is only a hint and the compiler is free to disable unrolling if it + * thinks the count is suboptimal and may hurt performance and/or hugely + * increase object code size. + * Not having any cross-iteration dependencies (i.e. when iter x + 1 depends + * on what iter x will do with variables) is not a strict requirement, but + * provides best performance and object code size. + * Available only on Clang and GCC 8.x onwards. + */ + +/* Ask the compiler to pick an optimal unroll count, Clang only */ +#define unrolled \ + __pick_unrolled(clang loop unroll(enable), /* nothing */) + +/* Unroll each @n iterations of the loop */ +#define unrolled_count(n) \ + __pick_unrolled(clang loop unroll_count(n), GCC unroll n) + +/* Unroll the whole loop */ +#define unrolled_full \ + __pick_unrolled(clang loop unroll(full), GCC unroll 65534) + +/* Never unroll the loop */ +#define unrolled_none \ + __pick_unrolled(clang loop unroll(disable), GCC unroll 1) + #define UNROLL(N, MACRO, args...) CONCATENATE(__UNROLL_, N)(MACRO, args) #define __UNROLL_0(MACRO, args...) diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b1df7d792fa1..2e46b69ff0a6 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -39,6 +39,8 @@ struct page; #define MAX_URETPROBE_DEPTH 64 +#define UPROBE_NO_TRAMPOLINE_VADDR (~0UL) + struct uprobe_consumer { /* * handler() can return UPROBE_HANDLER_REMOVE to signal the need to @@ -143,6 +145,7 @@ struct uprobe_task { struct uprobe *active_uprobe; unsigned long xol_vaddr; + bool signal_denied; struct arch_uprobe *auprobe; }; diff --git a/include/linux/usb/mctp-usb.h b/include/linux/usb/mctp-usb.h new file mode 100644 index 000000000000..a2f6f1e04efb --- /dev/null +++ b/include/linux/usb/mctp-usb.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * mctp-usb.h - MCTP USB transport binding: common definitions, + * based on DMTF0283 specification: + * https://www.dmtf.org/sites/default/files/standards/documents/DSP0283_1.0.1.pdf + * + * These are protocol-level definitions, that may be shared between host + * and gadget drivers. + * + * Copyright (C) 2024-2025 Code Construct Pty Ltd + */ + +#ifndef __LINUX_USB_MCTP_USB_H +#define __LINUX_USB_MCTP_USB_H + +#include <linux/types.h> + +struct mctp_usb_hdr { + __be16 id; + u8 rsvd; + u8 len; +} __packed; + +#define MCTP_USB_XFER_SIZE 512 +#define MCTP_USB_BTU 68 +#define MCTP_USB_MTU_MIN MCTP_USB_BTU +#define MCTP_USB_MTU_MAX (U8_MAX - sizeof(struct mctp_usb_hdr)) +#define MCTP_USB_DMTF_ID 0x1ab4 + +#endif /* __LINUX_USB_MCTP_USB_H */ diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 33a4c146dc19..2ca60828f28b 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -30,6 +30,7 @@ #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 #define VENDOR_ID_DLINK 0x2001 +#define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 #if IS_REACHABLE(CONFIG_USB_RTL8152) diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 825487fb66fa..3b570b765b75 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -5,6 +5,21 @@ #include <linux/math.h> /** + * for_each_if - helper for handling conditionals in various for_each macros + * @condition: The condition to check + * + * Typical use:: + * + * #define for_each_foo_bar(x, y) \' + * list_for_each_entry(x, y->list, head) \' + * for_each_if(x->something == SOMETHING) + * + * The for_each_if() macro makes the use of for_each_foo_bar() less error + * prone. + */ +#define for_each_if(condition) if (!(condition)) {} else + +/** * find_closest - locate the closest element in a sorted array * @x: The reference value. * @a: The array in which to look for the closest element. Must be sorted diff --git a/include/linux/vdso_datastore.h b/include/linux/vdso_datastore.h new file mode 100644 index 000000000000..a91fa24b06e0 --- /dev/null +++ b/include/linux/vdso_datastore.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VDSO_DATASTORE_H +#define _LINUX_VDSO_DATASTORE_H + +#include <linux/mm_types.h> + +extern const struct vm_special_mapping vdso_vvar_mapping; +struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr); + +#endif /* _LINUX_VDSO_DATASTORE_H */ diff --git a/include/linux/vfsdebug.h b/include/linux/vfsdebug.h new file mode 100644 index 000000000000..9cf22d3eb9dd --- /dev/null +++ b/include/linux/vfsdebug.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_VFS_DEBUG_H +#define LINUX_VFS_DEBUG_H 1 + +#include <linux/bug.h> + +struct inode; + +#ifdef CONFIG_DEBUG_VFS +void dump_inode(struct inode *inode, const char *reason); + +#define VFS_BUG_ON(cond) BUG_ON(cond) +#define VFS_WARN_ON(cond) (void)WARN_ON(cond) +#define VFS_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#define VFS_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format) +#define VFS_WARN(cond, format...) (void)WARN(cond, format) + +#define VFS_BUG_ON_INODE(cond, inode) ({ \ + if (unlikely(!!(cond))) { \ + dump_inode(inode, "VFS_BUG_ON_INODE(" #cond")");\ + BUG_ON(1); \ + } \ +}) + +#define VFS_WARN_ON_INODE(cond, inode) ({ \ + int __ret_warn = !!(cond); \ + \ + if (unlikely(__ret_warn)) { \ + dump_inode(inode, "VFS_WARN_ON_INODE(" #cond")");\ + WARN_ON(1); \ + } \ + unlikely(__ret_warn); \ +}) +#else +#define VFS_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) + +#define VFS_BUG_ON_INODE(cond, inode) VFS_BUG_ON(cond) +#define VFS_WARN_ON_INODE(cond, inode) BUILD_BUG_ON_INVALID(cond) +#endif /* CONFIG_DEBUG_VFS */ + +#endif diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index f70d0958095c..5a37cb2b6f93 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, + DIRECT_MAP_LEVEL2_COLLAPSE, + DIRECT_MAP_LEVEL3_COLLAPSE, #endif #ifdef CONFIG_PER_VMA_LOCK_STATS VMA_LOCK_SUCCESS, diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h index e1dec1a6a749..37e003ae5262 100644 --- a/include/linux/vmcore_info.h +++ b/include/linux/vmcore_info.h @@ -6,9 +6,8 @@ #include <linux/elfcore.h> #include <linux/elf.h> -#define CRASH_CORE_NOTE_NAME "CORE" #define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) -#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4) +#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(NN_PRSTATUS), 4) #define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4) /* diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9f3a04345b86..4751e3ecc467 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -10,15 +10,8 @@ #include <linux/static_key.h> #include <linux/mmdebug.h> -extern int sysctl_stat_interval; - #ifdef CONFIG_NUMA -#define ENABLE_NUMA_STAT 1 -#define DISABLE_NUMA_STAT 0 -extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); -int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { @@ -304,10 +297,6 @@ void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); -struct ctl_table; -int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, - loff_t *ppos); - void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); diff --git a/include/linux/wait.h b/include/linux/wait.h index 6d90ad974408..965a19809c7e 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -316,6 +316,9 @@ extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); } \ \ cmd; \ + \ + if (condition) \ + break; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ @@ -1207,14 +1210,16 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) -#define init_wait(wait) \ +#define init_wait_func(wait, function) \ do { \ (wait)->private = current; \ - (wait)->func = autoremove_wake_function; \ + (wait)->func = function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) +#define init_wait(wait) init_wait_func(wait, autoremove_wake_function) + typedef int (*task_call_f)(struct task_struct *p, void *arg); extern int task_call_func(struct task_struct *p, task_call_f func, void *arg); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d11b903c2edb..caf4f0b12235 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -327,12 +327,8 @@ extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; -extern unsigned int dirtytime_expire_interval; extern int laptop_mode; -int dirtytime_interval_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); - void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); diff --git a/include/linux/zstd.h b/include/linux/zstd.h index b2c7cf310c8f..2f2a3c8b8a33 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* - * Copyright (c) Yann Collet, Facebook, Inc. + * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the @@ -160,7 +160,6 @@ typedef ZSTD_parameters zstd_parameters; zstd_parameters zstd_get_params(int level, unsigned long long estimated_src_size); - /** * zstd_get_cparams() - returns zstd_compression_parameters for selected level * @level: The compression level @@ -173,9 +172,20 @@ zstd_parameters zstd_get_params(int level, zstd_compression_parameters zstd_get_cparams(int level, unsigned long long estimated_src_size, size_t dict_size); -/* ====== Single-pass Compression ====== */ - typedef ZSTD_CCtx zstd_cctx; +typedef ZSTD_cParameter zstd_cparameter; + +/** + * zstd_cctx_set_param() - sets a compression parameter + * @cctx: The context. Must have been initialized with zstd_init_cctx(). + * @param: The parameter to set. + * @value: The value to set the parameter to. + * + * Return: Zero or an error, which can be checked using zstd_is_error(). + */ +size_t zstd_cctx_set_param(zstd_cctx *cctx, zstd_cparameter param, int value); + +/* ====== Single-pass Compression ====== */ /** * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx @@ -191,6 +201,20 @@ typedef ZSTD_CCtx zstd_cctx; size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters); /** + * zstd_cctx_workspace_bound_with_ext_seq_prod() - max memory needed to + * initialize a zstd_cctx when using the block-level external sequence + * producer API. + * @parameters: The compression parameters to be used. + * + * If multiple compression parameters might be used, the caller must call + * this function for each set of parameters and use the maximum size. + * + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_cctx(). + */ +size_t zstd_cctx_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *parameters); + +/** * zstd_init_cctx() - initialize a zstd compression context * @workspace: The workspace to emplace the context into. It must outlive * the returned context. @@ -425,6 +449,16 @@ typedef ZSTD_CStream zstd_cstream; size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams); /** + * zstd_cstream_workspace_bound_with_ext_seq_prod() - memory needed to initialize + * a zstd_cstream when using the block-level external sequence producer API. + * @cparams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_cstream(). + */ +size_t zstd_cstream_workspace_bound_with_ext_seq_prod(const zstd_compression_parameters *cparams); + +/** * zstd_init_cstream() - initialize a zstd streaming compression context * @parameters The zstd parameters to use for compression. * @pledged_src_size: If params.fParams.contentSizeFlag == 1 then the caller @@ -584,6 +618,18 @@ size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); /** + * zstd_register_sequence_producer() - exposes the zstd library function + * ZSTD_registerSequenceProducer(). This is used for the block-level external + * sequence producer API. See upstream zstd.h for detailed documentation. + */ +typedef ZSTD_sequenceProducer_F zstd_sequence_producer_f; +void zstd_register_sequence_producer( + zstd_cctx *cctx, + void* sequence_producer_state, + zstd_sequence_producer_f sequence_producer +); + +/** * struct zstd_frame_params - zstd frame parameters stored in the frame header * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not * present. @@ -596,7 +642,7 @@ size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); * * See zstd_lib.h. */ -typedef ZSTD_frameHeader zstd_frame_header; +typedef ZSTD_FrameHeader zstd_frame_header; /** * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame @@ -611,4 +657,35 @@ typedef ZSTD_frameHeader zstd_frame_header; size_t zstd_get_frame_header(zstd_frame_header *params, const void *src, size_t src_size); +/** + * struct zstd_sequence - a sequence of literals or a match + * + * @offset: The offset of the match + * @litLength: The literal length of the sequence + * @matchLength: The match length of the sequence + * @rep: Represents which repeat offset is used + */ +typedef ZSTD_Sequence zstd_sequence; + +/** + * zstd_compress_sequences_and_literals() - compress an array of zstd_sequence and literals + * + * @cctx: The zstd compression context. + * @dst: The buffer to compress the data into. + * @dst_capacity: The size of the destination buffer. + * @in_seqs: The array of zstd_sequence to compress. + * @in_seqs_size: The number of sequences in in_seqs. + * @literals: The literals associated to the sequences to be compressed. + * @lit_size: The size of the literals in the literals buffer. + * @lit_capacity: The size of the literals buffer. + * @decompressed_size: The size of the input data + * + * Return: The compressed size or an error, which can be checked using + * zstd_is_error(). + */ +size_t zstd_compress_sequences_and_literals(zstd_cctx *cctx, void* dst, size_t dst_capacity, + const zstd_sequence *in_seqs, size_t in_seqs_size, + const void* literals, size_t lit_size, size_t lit_capacity, + size_t decompressed_size); + #endif /* LINUX_ZSTD_H */ diff --git a/include/linux/zstd_errors.h b/include/linux/zstd_errors.h index 58b6dd45a969..c307fb011132 100644 --- a/include/linux/zstd_errors.h +++ b/include/linux/zstd_errors.h @@ -1,5 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* - * Copyright (c) Yann Collet, Facebook, Inc. + * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the @@ -12,13 +13,18 @@ #define ZSTD_ERRORS_H_398273423 -/*===== dependency =====*/ -#include <linux/types.h> /* size_t */ +/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ +#define ZSTDERRORLIB_VISIBLE +#ifndef ZSTDERRORLIB_HIDDEN +# if (__GNUC__ >= 4) && !defined(__MINGW32__) +# define ZSTDERRORLIB_HIDDEN __attribute__ ((visibility ("hidden"))) +# else +# define ZSTDERRORLIB_HIDDEN +# endif +#endif -/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ -#define ZSTDERRORLIB_VISIBILITY -#define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY +#define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBLE /*-********************************************* * Error codes list @@ -43,14 +49,18 @@ typedef enum { ZSTD_error_frameParameter_windowTooLarge = 16, ZSTD_error_corruption_detected = 20, ZSTD_error_checksum_wrong = 22, + ZSTD_error_literals_headerWrong = 24, ZSTD_error_dictionary_corrupted = 30, ZSTD_error_dictionary_wrong = 32, ZSTD_error_dictionaryCreation_failed = 34, ZSTD_error_parameter_unsupported = 40, + ZSTD_error_parameter_combination_unsupported = 41, ZSTD_error_parameter_outOfBound = 42, ZSTD_error_tableLog_tooLarge = 44, ZSTD_error_maxSymbolValue_tooLarge = 46, ZSTD_error_maxSymbolValue_tooSmall = 48, + ZSTD_error_cannotProduce_uncompressedBlock = 49, + ZSTD_error_stabilityCondition_notRespected = 50, ZSTD_error_stage_wrong = 60, ZSTD_error_init_missing = 62, ZSTD_error_memory_allocation = 64, @@ -58,18 +68,18 @@ typedef enum { ZSTD_error_dstSize_tooSmall = 70, ZSTD_error_srcSize_wrong = 72, ZSTD_error_dstBuffer_null = 74, + ZSTD_error_noForwardProgress_destFull = 80, + ZSTD_error_noForwardProgress_inputEmpty = 82, /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */ ZSTD_error_frameIndex_tooLarge = 100, ZSTD_error_seekableIO = 102, ZSTD_error_dstBuffer_wrong = 104, ZSTD_error_srcBuffer_wrong = 105, + ZSTD_error_sequenceProducer_failed = 106, + ZSTD_error_externalSequences_invalid = 107, ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */ } ZSTD_ErrorCode; -/*! ZSTD_getErrorCode() : - convert a `size_t` function result into a `ZSTD_ErrorCode` enum type, - which can be used to compare with enum list published above */ -ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /*< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */ diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h index 79d55465d5c1..e295d4125dde 100644 --- a/include/linux/zstd_lib.h +++ b/include/linux/zstd_lib.h @@ -1,5 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* - * Copyright (c) Yann Collet, Facebook, Inc. + * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the @@ -11,23 +12,47 @@ #ifndef ZSTD_H_235446 #define ZSTD_H_235446 -/* ====== Dependency ======*/ -#include <linux/limits.h> /* INT_MAX */ + +/* ====== Dependencies ======*/ #include <linux/types.h> /* size_t */ +#include <linux/zstd_errors.h> /* list of errors */ +#if !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) +#include <linux/limits.h> /* INT_MAX */ +#endif /* ZSTD_STATIC_LINKING_ONLY */ + /* ===== ZSTDLIB_API : control library symbols visibility ===== */ -#ifndef ZSTDLIB_VISIBLE +#define ZSTDLIB_VISIBLE + +#ifndef ZSTDLIB_HIDDEN # if (__GNUC__ >= 4) && !defined(__MINGW32__) -# define ZSTDLIB_VISIBLE __attribute__ ((visibility ("default"))) # define ZSTDLIB_HIDDEN __attribute__ ((visibility ("hidden"))) # else -# define ZSTDLIB_VISIBLE # define ZSTDLIB_HIDDEN # endif #endif + #define ZSTDLIB_API ZSTDLIB_VISIBLE +/* Deprecation warnings : + * Should these warnings be a problem, it is generally possible to disable them, + * typically with -Wno-deprecated-declarations for gcc or _CRT_SECURE_NO_WARNINGS in Visual. + * Otherwise, it's also possible to define ZSTD_DISABLE_DEPRECATE_WARNINGS. + */ +#ifdef ZSTD_DISABLE_DEPRECATE_WARNINGS +# define ZSTD_DEPRECATED(message) /* disable deprecation warnings */ +#else +# if (defined(GNUC) && (GNUC > 4 || (GNUC == 4 && GNUC_MINOR >= 5))) || defined(__clang__) || defined(__IAR_SYSTEMS_ICC__) +# define ZSTD_DEPRECATED(message) __attribute__((deprecated(message))) +# elif (__GNUC__ >= 3) +# define ZSTD_DEPRECATED(message) __attribute__((deprecated)) +# else +# pragma message("WARNING: You need to implement ZSTD_DEPRECATED for this compiler") +# define ZSTD_DEPRECATED(message) +# endif +#endif /* ZSTD_DISABLE_DEPRECATE_WARNINGS */ + /* ***************************************************************************** Introduction @@ -65,7 +90,7 @@ /*------ Version ------*/ #define ZSTD_VERSION_MAJOR 1 #define ZSTD_VERSION_MINOR 5 -#define ZSTD_VERSION_RELEASE 2 +#define ZSTD_VERSION_RELEASE 7 #define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) /*! ZSTD_versionNumber() : @@ -103,11 +128,12 @@ ZSTDLIB_API const char* ZSTD_versionString(void); /* ************************************* -* Simple API +* Simple Core API ***************************************/ /*! ZSTD_compress() : * Compresses `src` content as a single zstd compressed frame into already allocated `dst`. - * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * NOTE: Providing `dstCapacity >= ZSTD_compressBound(srcSize)` guarantees that zstd will have + * enough space to successfully compress the data. * @return : compressed size written into `dst` (<= `dstCapacity), * or an error code if it fails (which can be tested using ZSTD_isError()). */ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, @@ -115,47 +141,55 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, int compressionLevel); /*! ZSTD_decompress() : - * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. - * `dstCapacity` is an upper bound of originalSize to regenerate. - * If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. - * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), - * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ + * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. + * Multiple compressed frames can be decompressed at once with this method. + * The result will be the concatenation of all decompressed frames, back to back. + * `dstCapacity` is an upper bound of originalSize to regenerate. + * First frame's decompressed size can be extracted using ZSTD_getFrameContentSize(). + * If maximum upper bound isn't known, prefer using streaming mode to decompress data. + * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), + * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); + +/*====== Decompression helper functions ======*/ + /*! ZSTD_getFrameContentSize() : requires v1.3.0+ - * `src` should point to the start of a ZSTD encoded frame. - * `srcSize` must be at least as large as the frame header. - * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. - * @return : - decompressed size of `src` frame content, if known - * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined - * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) - * note 1 : a 0 return value means the frame is valid but "empty". - * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode. - * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. - * In which case, it's necessary to use streaming mode to decompress data. - * Optionally, application can rely on some implicit limit, - * as ZSTD_decompress() only needs an upper bound of decompressed size. - * (For example, data could be necessarily cut into blocks <= 16 KB). - * note 3 : decompressed size is always present when compression is completed using single-pass functions, - * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). - * note 4 : decompressed size can be very large (64-bits value), - * potentially larger than what local system can handle as a single memory segment. - * In which case, it's necessary to use streaming mode to decompress data. - * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. - * Always ensure return value fits within application's authorized limits. - * Each application can set its own limits. - * note 6 : This function replaces ZSTD_getDecompressedSize() */ + * `src` should point to the start of a ZSTD encoded frame. + * `srcSize` must be at least as large as the frame header. + * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. + * @return : - decompressed size of `src` frame content, if known + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) + * note 1 : a 0 return value means the frame is valid but "empty". + * When invoking this method on a skippable frame, it will return 0. + * note 2 : decompressed size is an optional field, it may not be present (typically in streaming mode). + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * Optionally, application can rely on some implicit limit, + * as ZSTD_decompress() only needs an upper bound of decompressed size. + * (For example, data could be necessarily cut into blocks <= 16 KB). + * note 3 : decompressed size is always present when compression is completed using single-pass functions, + * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). + * note 4 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure return value fits within application's authorized limits. + * Each application can set its own limits. + * note 6 : This function replaces ZSTD_getDecompressedSize() */ #define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) #define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); -/*! ZSTD_getDecompressedSize() : - * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). +/*! ZSTD_getDecompressedSize() (obsolete): + * This function is now obsolete, in favor of ZSTD_getFrameContentSize(). * Both functions work the same way, but ZSTD_getDecompressedSize() blends * "empty", "unknown" and "error" results to the same return value (0), * while ZSTD_getFrameContentSize() gives them separate return values. * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */ +ZSTD_DEPRECATED("Replaced by ZSTD_getFrameContentSize") ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize); /*! ZSTD_findFrameCompressedSize() : Requires v1.4.0+ @@ -163,18 +197,50 @@ ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t * `srcSize` must be >= first frame size * @return : the compressed size of the first frame starting at `src`, * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, - * or an error code if input is invalid */ + * or an error code if input is invalid + * Note 1: this method is called _find*() because it's not enough to read the header, + * it may have to scan through the frame's content, to reach its end. + * Note 2: this method also works with Skippable Frames. In which case, + * it returns the size of the complete skippable frame, + * which is always equal to its content size + 8 bytes for headers. */ ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); -/*====== Helper functions ======*/ -#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ -ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ -ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ -ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ -ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed, requires v1.4.0+ */ -ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ -ZSTDLIB_API int ZSTD_defaultCLevel(void); /*!< default compression level, specified by ZSTD_CLEVEL_DEFAULT, requires v1.5.0+ */ +/*====== Compression helper functions ======*/ + +/*! ZSTD_compressBound() : + * maximum compressed size in worst case single-pass scenario. + * When invoking `ZSTD_compress()`, or any other one-pass compression function, + * it's recommended to provide @dstCapacity >= ZSTD_compressBound(srcSize) + * as it eliminates one potential failure scenario, + * aka not enough room in dst buffer to write the compressed frame. + * Note : ZSTD_compressBound() itself can fail, if @srcSize >= ZSTD_MAX_INPUT_SIZE . + * In which case, ZSTD_compressBound() will return an error code + * which can be tested using ZSTD_isError(). + * + * ZSTD_COMPRESSBOUND() : + * same as ZSTD_compressBound(), but as a macro. + * It can be used to produce constants, which can be useful for static allocation, + * for example to size a static array on stack. + * Will produce constant value 0 if srcSize is too large. + */ +#define ZSTD_MAX_INPUT_SIZE ((sizeof(size_t)==8) ? 0xFF00FF00FF00FF00ULL : 0xFF00FF00U) +#define ZSTD_COMPRESSBOUND(srcSize) (((size_t)(srcSize) >= ZSTD_MAX_INPUT_SIZE) ? 0 : (srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ +ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ + + +/*====== Error helper functions ======*/ +/* ZSTD_isError() : + * Most ZSTD_* functions returning a size_t value can be tested for error, + * using ZSTD_isError(). + * @return 1 if error, 0 otherwise + */ +ZSTDLIB_API unsigned ZSTD_isError(size_t result); /*!< tells if a `size_t` function result is an error code */ +ZSTDLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); /* convert a result into an error code, which can be compared to error enum list */ +ZSTDLIB_API const char* ZSTD_getErrorName(size_t result); /*!< provides readable string from a function result */ +ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed, requires v1.4.0+ */ +ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ +ZSTDLIB_API int ZSTD_defaultCLevel(void); /*!< default compression level, specified by ZSTD_CLEVEL_DEFAULT, requires v1.5.0+ */ /* ************************************* @@ -182,25 +248,25 @@ ZSTDLIB_API int ZSTD_defaultCLevel(void); /*!< default compres ***************************************/ /*= Compression context * When compressing many times, - * it is recommended to allocate a context just once, - * and re-use it for each successive compression operation. - * This will make workload friendlier for system's memory. + * it is recommended to allocate a compression context just once, + * and reuse it for each successive compression operation. + * This will make the workload easier for system's memory. * Note : re-using context is just a speed / resource optimization. * It doesn't change the compression ratio, which remains identical. - * Note 2 : In multi-threaded environments, - * use one different context per thread for parallel execution. + * Note 2: For parallel execution in multi-threaded environments, + * use one different context per thread . */ typedef struct ZSTD_CCtx_s ZSTD_CCtx; ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void); -ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /* accept NULL pointer */ +ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /* compatible with NULL pointer */ /*! ZSTD_compressCCtx() : * Same as ZSTD_compress(), using an explicit ZSTD_CCtx. - * Important : in order to behave similarly to `ZSTD_compress()`, - * this function compresses at requested compression level, - * __ignoring any other parameter__ . + * Important : in order to mirror `ZSTD_compress()` behavior, + * this function compresses at the requested compression level, + * __ignoring any other advanced parameter__ . * If any advanced parameter was set using the advanced API, - * they will all be reset. Only `compressionLevel` remains. + * they will all be reset. Only @compressionLevel remains. */ ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, @@ -210,7 +276,7 @@ ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, /*= Decompression context * When decompressing many times, * it is recommended to allocate a context only once, - * and re-use it for each successive compression operation. + * and reuse it for each successive compression operation. * This will make workload friendlier for system's memory. * Use one context per thread for parallel execution. */ typedef struct ZSTD_DCtx_s ZSTD_DCtx; @@ -220,7 +286,7 @@ ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /* accept NULL pointer * /*! ZSTD_decompressDCtx() : * Same as ZSTD_decompress(), * requires an allocated ZSTD_DCtx. - * Compatible with sticky parameters. + * Compatible with sticky parameters (see below). */ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, @@ -236,12 +302,12 @@ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, * using ZSTD_CCtx_set*() functions. * Pushed parameters are sticky : they are valid for next compressed frame, and any subsequent frame. * "sticky" parameters are applicable to `ZSTD_compress2()` and `ZSTD_compressStream*()` ! - * __They do not apply to "simple" one-shot variants such as ZSTD_compressCCtx()__ . + * __They do not apply to one-shot variants such as ZSTD_compressCCtx()__ . * * It's possible to reset all parameters to "default" using ZSTD_CCtx_reset(). * * This API supersedes all other "advanced" API entry points in the experimental section. - * In the future, we expect to remove from experimental API entry points which are redundant with this API. + * In the future, we expect to remove API entry points from experimental which are redundant with this API. */ @@ -324,6 +390,19 @@ typedef enum { * The higher the value of selected strategy, the more complex it is, * resulting in stronger and slower compression. * Special: value 0 means "use default strategy". */ + + ZSTD_c_targetCBlockSize=130, /* v1.5.6+ + * Attempts to fit compressed block size into approximately targetCBlockSize. + * Bound by ZSTD_TARGETCBLOCKSIZE_MIN and ZSTD_TARGETCBLOCKSIZE_MAX. + * Note that it's not a guarantee, just a convergence target (default:0). + * No target when targetCBlockSize == 0. + * This is helpful in low bandwidth streaming environments to improve end-to-end latency, + * when a client can make use of partial documents (a prominent example being Chrome). + * Note: this parameter is stable since v1.5.6. + * It was present as an experimental parameter in earlier versions, + * but it's not recommended using it with earlier library versions + * due to massive performance regressions. + */ /* LDM mode parameters */ ZSTD_c_enableLongDistanceMatching=160, /* Enable long distance matching. * This parameter is designed to improve compression ratio @@ -403,15 +482,18 @@ typedef enum { * ZSTD_c_forceMaxWindow * ZSTD_c_forceAttachDict * ZSTD_c_literalCompressionMode - * ZSTD_c_targetCBlockSize * ZSTD_c_srcSizeHint * ZSTD_c_enableDedicatedDictSearch * ZSTD_c_stableInBuffer * ZSTD_c_stableOutBuffer * ZSTD_c_blockDelimiters * ZSTD_c_validateSequences - * ZSTD_c_useBlockSplitter + * ZSTD_c_blockSplitterLevel + * ZSTD_c_splitAfterSequences * ZSTD_c_useRowMatchFinder + * ZSTD_c_prefetchCDictTables + * ZSTD_c_enableSeqProducerFallback + * ZSTD_c_maxBlockSize * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. * note : never ever use experimentalParam? names directly; * also, the enums values themselves are unstable and can still change. @@ -421,7 +503,7 @@ typedef enum { ZSTD_c_experimentalParam3=1000, ZSTD_c_experimentalParam4=1001, ZSTD_c_experimentalParam5=1002, - ZSTD_c_experimentalParam6=1003, + /* was ZSTD_c_experimentalParam6=1003; is now ZSTD_c_targetCBlockSize */ ZSTD_c_experimentalParam7=1004, ZSTD_c_experimentalParam8=1005, ZSTD_c_experimentalParam9=1006, @@ -430,7 +512,12 @@ typedef enum { ZSTD_c_experimentalParam12=1009, ZSTD_c_experimentalParam13=1010, ZSTD_c_experimentalParam14=1011, - ZSTD_c_experimentalParam15=1012 + ZSTD_c_experimentalParam15=1012, + ZSTD_c_experimentalParam16=1013, + ZSTD_c_experimentalParam17=1014, + ZSTD_c_experimentalParam18=1015, + ZSTD_c_experimentalParam19=1016, + ZSTD_c_experimentalParam20=1017 } ZSTD_cParameter; typedef struct { @@ -493,7 +580,7 @@ typedef enum { * They will be used to compress next frame. * Resetting session never fails. * - The parameters : changes all parameters back to "default". - * This removes any reference to any dictionary too. + * This also removes any reference to any dictionary or external sequence producer. * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) * - Both : similar to resetting the session, followed by resetting parameters. @@ -502,11 +589,13 @@ ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset); /*! ZSTD_compress2() : * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. + * (note that this entry point doesn't even expose a compression level parameter). * ZSTD_compress2() always starts a new frame. * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() * - The function is always blocking, returns when compression is completed. - * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * NOTE: Providing `dstCapacity >= ZSTD_compressBound(srcSize)` guarantees that zstd will have + * enough space to successfully compress the data, though it is possible it fails for other reasons. * @return : compressed size written into `dst` (<= `dstCapacity), * or an error code if it fails (which can be tested using ZSTD_isError()). */ @@ -543,13 +632,17 @@ typedef enum { * ZSTD_d_stableOutBuffer * ZSTD_d_forceIgnoreChecksum * ZSTD_d_refMultipleDDicts + * ZSTD_d_disableHuffmanAssembly + * ZSTD_d_maxBlockSize * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. * note : never ever use experimentalParam? names directly */ ZSTD_d_experimentalParam1=1000, ZSTD_d_experimentalParam2=1001, ZSTD_d_experimentalParam3=1002, - ZSTD_d_experimentalParam4=1003 + ZSTD_d_experimentalParam4=1003, + ZSTD_d_experimentalParam5=1004, + ZSTD_d_experimentalParam6=1005 } ZSTD_dParameter; @@ -604,14 +697,14 @@ typedef struct ZSTD_outBuffer_s { * A ZSTD_CStream object is required to track streaming operation. * Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. * ZSTD_CStream objects can be reused multiple times on consecutive compression operations. -* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. +* It is recommended to reuse ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. * * For parallel execution, use one separate ZSTD_CStream per thread. * * note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. * * Parameters are sticky : when starting a new compression on the same context, -* it will re-use the same sticky parameters as previous compression session. +* it will reuse the same sticky parameters as previous compression session. * When in doubt, it's recommended to fully initialize the context before usage. * Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), * ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to @@ -700,6 +793,11 @@ typedef enum { * only ZSTD_e_end or ZSTD_e_flush operations are allowed. * Before starting a new compression job, or changing compression parameters, * it is required to fully flush internal buffers. + * - note: if an operation ends with an error, it may leave @cctx in an undefined state. + * Therefore, it's UB to invoke ZSTD_compressStream2() of ZSTD_compressStream() on such a state. + * In order to be re-employed after an error, a state must be reset, + * which can be done explicitly (ZSTD_CCtx_reset()), + * or is sometimes implied by methods starting a new compression job (ZSTD_initCStream(), ZSTD_compressCCtx()) */ ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, ZSTD_outBuffer* output, @@ -728,8 +826,6 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /*< recommended size for output * This following is a legacy streaming API, available since v1.0+ . * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2(). * It is redundant, but remains fully supported. - * Streaming in combination with advanced parameters and dictionary compression - * can only be used through the new API. ******************************************************************************/ /*! @@ -738,6 +834,9 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /*< recommended size for output * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * + * Note that ZSTD_initCStream() clears any previously set dictionary. Use the new API + * to compress with a dictionary. */ ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); /*! @@ -758,7 +857,7 @@ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); * * A ZSTD_DStream object is required to track streaming operations. * Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. -* ZSTD_DStream objects can be re-used multiple times. +* ZSTD_DStream objects can be re-employed multiple times. * * Use ZSTD_initDStream() to start a new decompression operation. * @return : recommended first input size @@ -768,16 +867,21 @@ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); * The function will update both `pos` fields. * If `input.pos < input.size`, some input has not been consumed. * It's up to the caller to present again remaining data. +* * The function tries to flush all data decoded immediately, respecting output buffer size. * If `output.pos < output.size`, decoder has flushed everything it could. -* But if `output.pos == output.size`, there might be some data left within internal buffers., +* +* However, when `output.pos == output.size`, it's more difficult to know. +* If @return > 0, the frame is not complete, meaning +* either there is still some data left to flush within internal buffers, +* or there is more input to read to complete the frame (or both). * In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. * Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. * @return : 0 when a frame is completely decoded and fully flushed, * or an error code, which can be tested using ZSTD_isError(), * or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : * the return value is a suggested next input size (just a hint for better latency) -* that will never request more than the remaining frame size. +* that will never request more than the remaining content of the compressed frame. * *******************************************************************************/ typedef ZSTD_DCtx ZSTD_DStream; /*< DCtx and DStream are now effectively same object (>= v1.3.0) */ @@ -788,13 +892,38 @@ ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); /* accept NULL pointer /*===== Streaming decompression functions =====*/ -/* This function is redundant with the advanced API and equivalent to: +/*! ZSTD_initDStream() : + * Initialize/reset DStream state for new decompression operation. + * Call before new decompression operation using same DStream. * + * Note : This function is redundant with the advanced API and equivalent to: * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); * ZSTD_DCtx_refDDict(zds, NULL); */ ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); +/*! ZSTD_decompressStream() : + * Streaming decompression function. + * Call repetitively to consume full input updating it as necessary. + * Function will update both input and output `pos` fields exposing current state via these fields: + * - `input.pos < input.size`, some input remaining and caller should provide remaining input + * on the next call. + * - `output.pos < output.size`, decoder flushed internal output buffer. + * - `output.pos == output.size`, unflushed data potentially present in the internal buffers, + * check ZSTD_decompressStream() @return value, + * if > 0, invoke it again to flush remaining data to output. + * Note : with no additional input, amount of data flushed <= ZSTD_BLOCKSIZE_MAX. + * + * @return : 0 when a frame is completely decoded and fully flushed, + * or an error code, which can be tested using ZSTD_isError(), + * or any other value > 0, which means there is some decoding or flushing to do to complete current frame. + * + * Note: when an operation returns with an error code, the @zds state may be left in undefined state. + * It's UB to invoke `ZSTD_decompressStream()` on such a state. + * In order to re-use such a state, it must be first reset, + * which can be done explicitly (`ZSTD_DCtx_reset()`), + * or is implied for operations starting some new decompression job (`ZSTD_initDStream`, `ZSTD_decompressDCtx()`, `ZSTD_decompress_usingDict()`) + */ ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ @@ -913,7 +1042,7 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); * If @return == 0, the dictID could not be decoded. * This could for one of the following reasons : * - The frame does not require a dictionary to be decoded (most common case). - * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. + * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden piece of information. * Note : this use case also happens when using a non-conformant dictionary. * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). * - This is not a Zstandard frame. @@ -925,9 +1054,11 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); * Advanced dictionary and prefix API (Requires v1.4.0+) * * This API allows dictionaries to be used with ZSTD_compress2(), - * ZSTD_compressStream2(), and ZSTD_decompressDCtx(). Dictionaries are sticky, and - * only reset with the context is reset with ZSTD_reset_parameters or - * ZSTD_reset_session_and_parameters. Prefixes are single-use. + * ZSTD_compressStream2(), and ZSTD_decompressDCtx(). + * Dictionaries are sticky, they remain valid when same context is reused, + * they only reset when the context is reset + * with ZSTD_reset_parameters or ZSTD_reset_session_and_parameters. + * In contrast, Prefixes are single-use. ******************************************************************************/ @@ -937,8 +1068,9 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); * @result : 0, or an error code (which can be tested with ZSTD_isError()). * Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, * meaning "return to no-dictionary mode". - * Note 1 : Dictionary is sticky, it will be used for all future compressed frames. - * To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). + * Note 1 : Dictionary is sticky, it will be used for all future compressed frames, + * until parameters are reset, a new dictionary is loaded, or the dictionary + * is explicitly invalidated by loading a NULL dictionary. * Note 2 : Loading a dictionary involves building tables. * It's also a CPU consuming operation, with non-negligible impact on latency. * Tables are dependent on compression parameters, and for this reason, @@ -947,11 +1079,15 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); * Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead. * In such a case, dictionary buffer must outlive its users. * Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() - * to precisely select how dictionary content must be interpreted. */ + * to precisely select how dictionary content must be interpreted. + * Note 5 : This method does not benefit from LDM (long distance mode). + * If you want to employ LDM on some large dictionary content, + * prefer employing ZSTD_CCtx_refPrefix() described below. + */ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); /*! ZSTD_CCtx_refCDict() : Requires v1.4.0+ - * Reference a prepared dictionary, to be used for all next compressed frames. + * Reference a prepared dictionary, to be used for all future compressed frames. * Note that compression parameters are enforced from within CDict, * and supersede any compression parameter previously set within CCtx. * The parameters ignored are labelled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. @@ -970,6 +1106,7 @@ ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); * Decompression will need same prefix to properly regenerate data. * Compressing with a prefix is similar in outcome as performing a diff and compressing it, * but performs much faster, especially during decompression (compression speed is tunable with compression level). + * This method is compatible with LDM (long distance mode). * @result : 0, or an error code (which can be tested with ZSTD_isError()). * Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary * Note 1 : Prefix buffer is referenced. It **must** outlive compression. @@ -986,9 +1123,9 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize); /*! ZSTD_DCtx_loadDictionary() : Requires v1.4.0+ - * Create an internal DDict from dict buffer, - * to be used to decompress next frames. - * The dictionary remains valid for all future frames, until explicitly invalidated. + * Create an internal DDict from dict buffer, to be used to decompress all future frames. + * The dictionary remains valid for all future frames, until explicitly invalidated, or + * a new dictionary is loaded. * @result : 0, or an error code (which can be tested with ZSTD_isError()). * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, * meaning "return to no-dictionary mode". @@ -1012,9 +1149,10 @@ ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, s * The memory for the table is allocated on the first call to refDDict, and can be * freed with ZSTD_freeDCtx(). * + * If called with ZSTD_d_refMultipleDDicts disabled (the default), only one dictionary + * will be managed, and referencing a dictionary effectively "discards" any previous one. + * * @result : 0, or an error code (which can be tested with ZSTD_isError()). - * Note 1 : Currently, only one dictionary can be managed. - * Referencing a new dictionary effectively "discards" any previous one. * Special: referencing a NULL DDict means "return to no-dictionary mode". * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. */ @@ -1051,6 +1189,7 @@ ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); + #endif /* ZSTD_H_235446 */ @@ -1066,29 +1205,12 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); #if !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) #define ZSTD_H_ZSTD_STATIC_LINKING_ONLY + /* This can be overridden externally to hide static symbols. */ #ifndef ZSTDLIB_STATIC_API #define ZSTDLIB_STATIC_API ZSTDLIB_VISIBLE #endif -/* Deprecation warnings : - * Should these warnings be a problem, it is generally possible to disable them, - * typically with -Wno-deprecated-declarations for gcc or _CRT_SECURE_NO_WARNINGS in Visual. - * Otherwise, it's also possible to define ZSTD_DISABLE_DEPRECATE_WARNINGS. - */ -#ifdef ZSTD_DISABLE_DEPRECATE_WARNINGS -# define ZSTD_DEPRECATED(message) ZSTDLIB_STATIC_API /* disable deprecation warnings */ -#else -# if (defined(GNUC) && (GNUC > 4 || (GNUC == 4 && GNUC_MINOR >= 5))) || defined(__clang__) -# define ZSTD_DEPRECATED(message) ZSTDLIB_STATIC_API __attribute__((deprecated(message))) -# elif (__GNUC__ >= 3) -# define ZSTD_DEPRECATED(message) ZSTDLIB_STATIC_API __attribute__((deprecated)) -# else -# pragma message("WARNING: You need to implement ZSTD_DEPRECATED for this compiler") -# define ZSTD_DEPRECATED(message) ZSTDLIB_STATIC_API -# endif -#endif /* ZSTD_DISABLE_DEPRECATE_WARNINGS */ - /* ************************************************************************************** * experimental API (static linking only) **************************************************************************************** @@ -1123,6 +1245,7 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); #define ZSTD_TARGETLENGTH_MIN 0 /* note : comparing this constant to an unsigned results in a tautological test */ #define ZSTD_STRATEGY_MIN ZSTD_fast #define ZSTD_STRATEGY_MAX ZSTD_btultra2 +#define ZSTD_BLOCKSIZE_MAX_MIN (1 << 10) /* The minimum valid max blocksize. Maximum blocksizes smaller than this make compressBound() inaccurate. */ #define ZSTD_OVERLAPLOG_MIN 0 @@ -1146,7 +1269,7 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); #define ZSTD_LDM_HASHRATELOG_MAX (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN) /* Advanced parameter bounds */ -#define ZSTD_TARGETCBLOCKSIZE_MIN 64 +#define ZSTD_TARGETCBLOCKSIZE_MIN 1340 /* suitable to fit into an ethernet / wifi / 4G transport frame */ #define ZSTD_TARGETCBLOCKSIZE_MAX ZSTD_BLOCKSIZE_MAX #define ZSTD_SRCSIZEHINT_MIN 0 #define ZSTD_SRCSIZEHINT_MAX INT_MAX @@ -1188,7 +1311,7 @@ typedef struct { * * Note: This field is optional. ZSTD_generateSequences() will calculate the value of * 'rep', but repeat offsets do not necessarily need to be calculated from an external - * sequence provider's perspective. For example, ZSTD_compressSequences() does not + * sequence provider perspective. For example, ZSTD_compressSequences() does not * use this 'rep' field at all (as of now). */ } ZSTD_Sequence; @@ -1293,17 +1416,18 @@ typedef enum { } ZSTD_literalCompressionMode_e; typedef enum { - /* Note: This enum controls features which are conditionally beneficial. Zstd typically will make a final - * decision on whether or not to enable the feature (ZSTD_ps_auto), but setting the switch to ZSTD_ps_enable - * or ZSTD_ps_disable allow for a force enable/disable the feature. + /* Note: This enum controls features which are conditionally beneficial. + * Zstd can take a decision on whether or not to enable the feature (ZSTD_ps_auto), + * but setting the switch to ZSTD_ps_enable or ZSTD_ps_disable force enable/disable the feature. */ ZSTD_ps_auto = 0, /* Let the library automatically determine whether the feature shall be enabled */ ZSTD_ps_enable = 1, /* Force-enable the feature */ ZSTD_ps_disable = 2 /* Do not use the feature */ -} ZSTD_paramSwitch_e; +} ZSTD_ParamSwitch_e; +#define ZSTD_paramSwitch_e ZSTD_ParamSwitch_e /* old name */ /* ************************************* -* Frame size functions +* Frame header and size functions ***************************************/ /*! ZSTD_findDecompressedSize() : @@ -1345,34 +1469,130 @@ ZSTDLIB_STATIC_API unsigned long long ZSTD_findDecompressedSize(const void* src, ZSTDLIB_STATIC_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize); /*! ZSTD_frameHeaderSize() : - * srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. + * srcSize must be large enough, aka >= ZSTD_FRAMEHEADERSIZE_PREFIX. * @return : size of the Frame Header, * or an error code (if srcSize is too small) */ ZSTDLIB_STATIC_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); +typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_FrameType_e; +#define ZSTD_frameType_e ZSTD_FrameType_e /* old name */ +typedef struct { + unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ + unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ + unsigned blockSizeMax; + ZSTD_FrameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ + unsigned headerSize; + unsigned dictID; /* for ZSTD_skippableFrame, contains the skippable magic variant [0-15] */ + unsigned checksumFlag; + unsigned _reserved1; + unsigned _reserved2; +} ZSTD_FrameHeader; +#define ZSTD_frameHeader ZSTD_FrameHeader /* old name */ + +/*! ZSTD_getFrameHeader() : + * decode Frame Header into `zfhPtr`, or requires larger `srcSize`. + * @return : 0 => header is complete, `zfhPtr` is correctly filled, + * >0 => `srcSize` is too small, @return value is the wanted `srcSize` amount, `zfhPtr` is not filled, + * or an error code, which can be tested using ZSTD_isError() */ +ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader(ZSTD_FrameHeader* zfhPtr, const void* src, size_t srcSize); +/*! ZSTD_getFrameHeader_advanced() : + * same as ZSTD_getFrameHeader(), + * with added capability to select a format (like ZSTD_f_zstd1_magicless) */ +ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_FrameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format); + +/*! ZSTD_decompressionMargin() : + * Zstd supports in-place decompression, where the input and output buffers overlap. + * In this case, the output buffer must be at least (Margin + Output_Size) bytes large, + * and the input buffer must be at the end of the output buffer. + * + * _______________________ Output Buffer ________________________ + * | | + * | ____ Input Buffer ____| + * | | | + * v v v + * |---------------------------------------|-----------|----------| + * ^ ^ ^ + * |___________________ Output_Size ___________________|_ Margin _| + * + * NOTE: See also ZSTD_DECOMPRESSION_MARGIN(). + * NOTE: This applies only to single-pass decompression through ZSTD_decompress() or + * ZSTD_decompressDCtx(). + * NOTE: This function supports multi-frame input. + * + * @param src The compressed frame(s) + * @param srcSize The size of the compressed frame(s) + * @returns The decompression margin or an error that can be checked with ZSTD_isError(). + */ +ZSTDLIB_STATIC_API size_t ZSTD_decompressionMargin(const void* src, size_t srcSize); + +/*! ZSTD_DECOMPRESS_MARGIN() : + * Similar to ZSTD_decompressionMargin(), but instead of computing the margin from + * the compressed frame, compute it from the original size and the blockSizeLog. + * See ZSTD_decompressionMargin() for details. + * + * WARNING: This macro does not support multi-frame input, the input must be a single + * zstd frame. If you need that support use the function, or implement it yourself. + * + * @param originalSize The original uncompressed size of the data. + * @param blockSize The block size == MIN(windowSize, ZSTD_BLOCKSIZE_MAX). + * Unless you explicitly set the windowLog smaller than + * ZSTD_BLOCKSIZELOG_MAX you can just use ZSTD_BLOCKSIZE_MAX. + */ +#define ZSTD_DECOMPRESSION_MARGIN(originalSize, blockSize) ((size_t)( \ + ZSTD_FRAMEHEADERSIZE_MAX /* Frame header */ + \ + 4 /* checksum */ + \ + ((originalSize) == 0 ? 0 : 3 * (((originalSize) + (blockSize) - 1) / blockSize)) /* 3 bytes per block */ + \ + (blockSize) /* One block of margin */ \ + )) + typedef enum { - ZSTD_sf_noBlockDelimiters = 0, /* Representation of ZSTD_Sequence has no block delimiters, sequences only */ - ZSTD_sf_explicitBlockDelimiters = 1 /* Representation of ZSTD_Sequence contains explicit block delimiters */ -} ZSTD_sequenceFormat_e; + ZSTD_sf_noBlockDelimiters = 0, /* ZSTD_Sequence[] has no block delimiters, just sequences */ + ZSTD_sf_explicitBlockDelimiters = 1 /* ZSTD_Sequence[] contains explicit block delimiters */ +} ZSTD_SequenceFormat_e; +#define ZSTD_sequenceFormat_e ZSTD_SequenceFormat_e /* old name */ + +/*! ZSTD_sequenceBound() : + * `srcSize` : size of the input buffer + * @return : upper-bound for the number of sequences that can be generated + * from a buffer of srcSize bytes + * + * note : returns number of sequences - to get bytes, multiply by sizeof(ZSTD_Sequence). + */ +ZSTDLIB_STATIC_API size_t ZSTD_sequenceBound(size_t srcSize); /*! ZSTD_generateSequences() : - * Generate sequences using ZSTD_compress2, given a source buffer. + * WARNING: This function is meant for debugging and informational purposes ONLY! + * Its implementation is flawed, and it will be deleted in a future version. + * It is not guaranteed to succeed, as there are several cases where it will give + * up and fail. You should NOT use this function in production code. + * + * This function is deprecated, and will be removed in a future version. + * + * Generate sequences using ZSTD_compress2(), given a source buffer. + * + * @param zc The compression context to be used for ZSTD_compress2(). Set any + * compression parameters you need on this context. + * @param outSeqs The output sequences buffer of size @p outSeqsSize + * @param outSeqsCapacity The size of the output sequences buffer. + * ZSTD_sequenceBound(srcSize) is an upper bound on the number + * of sequences that can be generated. + * @param src The source buffer to generate sequences from of size @p srcSize. + * @param srcSize The size of the source buffer. * * Each block will end with a dummy sequence * with offset == 0, matchLength == 0, and litLength == length of last literals. * litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0) * simply acts as a block delimiter. * - * zc can be used to insert custom compression params. - * This function invokes ZSTD_compress2 - * - * The output of this function can be fed into ZSTD_compressSequences() with CCtx - * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters - * @return : number of sequences generated + * @returns The number of sequences generated, necessarily less than + * ZSTD_sequenceBound(srcSize), or an error code that can be checked + * with ZSTD_isError(). */ - -ZSTDLIB_STATIC_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, - size_t outSeqsSize, const void* src, size_t srcSize); +ZSTD_DEPRECATED("For debugging only, will be replaced by ZSTD_extractSequences()") +ZSTDLIB_STATIC_API size_t +ZSTD_generateSequences(ZSTD_CCtx* zc, + ZSTD_Sequence* outSeqs, size_t outSeqsCapacity, + const void* src, size_t srcSize); /*! ZSTD_mergeBlockDelimiters() : * Given an array of ZSTD_Sequence, remove all sequences that represent block delimiters/last literals @@ -1388,8 +1608,10 @@ ZSTDLIB_STATIC_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* o ZSTDLIB_STATIC_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize); /*! ZSTD_compressSequences() : - * Compress an array of ZSTD_Sequence, generated from the original source buffer, into dst. - * If a dictionary is included, then the cctx should reference the dict. (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.) + * Compress an array of ZSTD_Sequence, associated with @src buffer, into dst. + * @src contains the entire input (not just the literals). + * If @srcSize > sum(sequence.length), the remaining bytes are considered all literals + * If a dictionary is included, then the cctx should reference the dict (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.). * The entire source is compressed into a single frame. * * The compression behavior changes based on cctx params. In particular: @@ -1398,11 +1620,17 @@ ZSTDLIB_STATIC_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, si * the block size derived from the cctx, and sequences may be split. This is the default setting. * * If ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, the array of ZSTD_Sequence is expected to contain - * block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided. + * valid block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided. + * + * When ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, it's possible to decide generating repcodes + * using the advanced parameter ZSTD_c_repcodeResolution. Repcodes will improve compression ratio, though the benefit + * can vary greatly depending on Sequences. On the other hand, repcode resolution is an expensive operation. + * By default, it's disabled at low (<10) compression levels, and enabled above the threshold (>=10). + * ZSTD_c_repcodeResolution makes it possible to directly manage this processing in either direction. * - * If ZSTD_c_validateSequences == 0, this function will blindly accept the sequences provided. Invalid sequences cause undefined - * behavior. If ZSTD_c_validateSequences == 1, then if sequence is invalid (see doc/zstd_compression_format.md for - * specifics regarding offset/matchlength requirements) then the function will bail out and return an error. + * If ZSTD_c_validateSequences == 0, this function blindly accepts the Sequences provided. Invalid Sequences cause undefined + * behavior. If ZSTD_c_validateSequences == 1, then the function will detect invalid Sequences (see doc/zstd_compression_format.md for + * specifics regarding offset/matchlength requirements) and then bail out and return an error. * * In addition to the two adjustable experimental params, there are other important cctx params. * - ZSTD_c_minMatch MUST be set as less than or equal to the smallest match generated by the match finder. It has a minimum value of ZSTD_MINMATCH_MIN. @@ -1410,14 +1638,42 @@ ZSTDLIB_STATIC_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, si * - ZSTD_c_windowLog affects offset validation: this function will return an error at higher debug levels if a provided offset * is larger than what the spec allows for a given window log and dictionary (if present). See: doc/zstd_compression_format.md * - * Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused. - * Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly, - * and cannot emit an RLE block that disagrees with the repcode history - * @return : final compressed size or a ZSTD error. - */ -ZSTDLIB_STATIC_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstSize, - const ZSTD_Sequence* inSeqs, size_t inSeqsSize, - const void* src, size_t srcSize); + * Note: Repcodes are, as of now, always re-calculated within this function, ZSTD_Sequence.rep is effectively unused. + * Dev Note: Once ability to ingest repcodes become available, the explicit block delims mode must respect those repcodes exactly, + * and cannot emit an RLE block that disagrees with the repcode history. + * @return : final compressed size, or a ZSTD error code. + */ +ZSTDLIB_STATIC_API size_t +ZSTD_compressSequences(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const ZSTD_Sequence* inSeqs, size_t inSeqsSize, + const void* src, size_t srcSize); + + +/*! ZSTD_compressSequencesAndLiterals() : + * This is a variant of ZSTD_compressSequences() which, + * instead of receiving (src,srcSize) as input parameter, receives (literals,litSize), + * aka all the literals, already extracted and laid out into a single continuous buffer. + * This can be useful if the process generating the sequences also happens to generate the buffer of literals, + * thus skipping an extraction + caching stage. + * It's a speed optimization, useful when the right conditions are met, + * but it also features the following limitations: + * - Only supports explicit delimiter mode + * - Currently does not support Sequences validation (so input Sequences are trusted) + * - Not compatible with frame checksum, which must be disabled + * - If any block is incompressible, will fail and return an error + * - @litSize must be == sum of all @.litLength fields in @inSeqs. Any discrepancy will generate an error. + * - @litBufCapacity is the size of the underlying buffer into which literals are written, starting at address @literals. + * @litBufCapacity must be at least 8 bytes larger than @litSize. + * - @decompressedSize must be correct, and correspond to the sum of all Sequences. Any discrepancy will generate an error. + * @return : final compressed size, or a ZSTD error code. + */ +ZSTDLIB_STATIC_API size_t +ZSTD_compressSequencesAndLiterals(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const ZSTD_Sequence* inSeqs, size_t nbSequences, + const void* literals, size_t litSize, size_t litBufCapacity, + size_t decompressedSize); /*! ZSTD_writeSkippableFrame() : @@ -1425,8 +1681,8 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* ds * * Skippable frames begin with a 4-byte magic number. There are 16 possible choices of magic number, * ranging from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15. - * As such, the parameter magicVariant controls the exact skippable frame magic number variant used, so - * the magic number used will be ZSTD_MAGIC_SKIPPABLE_START + magicVariant. + * As such, the parameter magicVariant controls the exact skippable frame magic number variant used, + * so the magic number used will be ZSTD_MAGIC_SKIPPABLE_START + magicVariant. * * Returns an error if destination buffer is not large enough, if the source size is not representable * with a 4-byte unsigned int, or if the parameter magicVariant is greater than 15 (and therefore invalid). @@ -1434,26 +1690,28 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* ds * @return : number of bytes written or a ZSTD error. */ ZSTDLIB_STATIC_API size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity, - const void* src, size_t srcSize, unsigned magicVariant); + const void* src, size_t srcSize, + unsigned magicVariant); /*! ZSTD_readSkippableFrame() : - * Retrieves a zstd skippable frame containing data given by src, and writes it to dst buffer. + * Retrieves the content of a zstd skippable frame starting at @src, and writes it to @dst buffer. * - * The parameter magicVariant will receive the magicVariant that was supplied when the frame was written, - * i.e. magicNumber - ZSTD_MAGIC_SKIPPABLE_START. This can be NULL if the caller is not interested - * in the magicVariant. + * The parameter @magicVariant will receive the magicVariant that was supplied when the frame was written, + * i.e. magicNumber - ZSTD_MAGIC_SKIPPABLE_START. + * This can be NULL if the caller is not interested in the magicVariant. * * Returns an error if destination buffer is not large enough, or if the frame is not skippable. * * @return : number of bytes written or a ZSTD error. */ -ZSTDLIB_API size_t ZSTD_readSkippableFrame(void* dst, size_t dstCapacity, unsigned* magicVariant, - const void* src, size_t srcSize); +ZSTDLIB_STATIC_API size_t ZSTD_readSkippableFrame(void* dst, size_t dstCapacity, + unsigned* magicVariant, + const void* src, size_t srcSize); /*! ZSTD_isSkippableFrame() : * Tells if the content of `buffer` starts with a valid Frame Identifier for a skippable frame. */ -ZSTDLIB_API unsigned ZSTD_isSkippableFrame(const void* buffer, size_t size); +ZSTDLIB_STATIC_API unsigned ZSTD_isSkippableFrame(const void* buffer, size_t size); @@ -1464,48 +1722,59 @@ ZSTDLIB_API unsigned ZSTD_isSkippableFrame(const void* buffer, size_t size); /*! ZSTD_estimate*() : * These functions make it possible to estimate memory usage * of a future {D,C}Ctx, before its creation. + * This is useful in combination with ZSTD_initStatic(), + * which makes it possible to employ a static buffer for ZSTD_CCtx* state. * * ZSTD_estimateCCtxSize() will provide a memory budget large enough - * for any compression level up to selected one. - * Note : Unlike ZSTD_estimateCStreamSize*(), this estimate - * does not include space for a window buffer. - * Therefore, the estimation is only guaranteed for single-shot compressions, not streaming. + * to compress data of any size using one-shot compression ZSTD_compressCCtx() or ZSTD_compress2() + * associated with any compression level up to max specified one. * The estimate will assume the input may be arbitrarily large, * which is the worst case. * + * Note that the size estimation is specific for one-shot compression, + * it is not valid for streaming (see ZSTD_estimateCStreamSize*()) + * nor other potential ways of using a ZSTD_CCtx* state. + * * When srcSize can be bound by a known and rather "small" value, - * this fact can be used to provide a tighter estimation - * because the CCtx compression context will need less memory. - * This tighter estimation can be provided by more advanced functions + * this knowledge can be used to provide a tighter budget estimation + * because the ZSTD_CCtx* state will need less memory for small inputs. + * This tighter estimation can be provided by employing more advanced functions * ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(), * and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter(). * Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits. * - * Note 2 : only single-threaded compression is supported. + * Note : only single-threaded compression is supported. * ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1. */ -ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize(int compressionLevel); +ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize(int maxCompressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); ZSTDLIB_STATIC_API size_t ZSTD_estimateDCtxSize(void); /*! ZSTD_estimateCStreamSize() : - * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. - * It will also consider src size to be arbitrarily "large", which is worst case. + * ZSTD_estimateCStreamSize() will provide a memory budget large enough for streaming compression + * using any compression level up to the max specified one. + * It will also consider src size to be arbitrarily "large", which is a worst case scenario. * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. * Note : CStream size estimation is only correct for single-threaded compression. - * ZSTD_DStream memory budget depends on window Size. + * ZSTD_estimateCStreamSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1. + * Note 2 : ZSTD_estimateCStreamSize* functions are not compatible with the Block-Level Sequence Producer API at this time. + * Size estimates assume that no external sequence producer is registered. + * + * ZSTD_DStream memory budget depends on frame's window Size. * This information can be passed manually, using ZSTD_estimateDStreamSize, * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); + * Any frame requesting a window size larger than max specified one will be rejected. * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), * an internal ?Dict will be created, which additional size is not estimated here. - * In this case, get total size by adding ZSTD_estimate?DictSize */ -ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize(int compressionLevel); + * In this case, get total size by adding ZSTD_estimate?DictSize + */ +ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize(int maxCompressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams); ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params); -ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize(size_t windowSize); +ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize(size_t maxWindowSize); ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); /*! ZSTD_estimate?DictSize() : @@ -1568,7 +1837,15 @@ typedef void (*ZSTD_freeFunction) (void* opaque, void* address); typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; static __attribute__((__unused__)) + +#if defined(__clang__) && __clang_major__ >= 5 +#pragma clang diagnostic push +#pragma clang diagnostic ignored "-Wzero-as-null-pointer-constant" +#endif ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /*< this constant defers to stdlib's functions */ +#if defined(__clang__) && __clang_major__ >= 5 +#pragma clang diagnostic pop +#endif ZSTDLIB_STATIC_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); ZSTDLIB_STATIC_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); @@ -1649,22 +1926,45 @@ ZSTDLIB_STATIC_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); * This function never fails (wide contract) */ ZSTDLIB_STATIC_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); +/*! ZSTD_CCtx_setCParams() : + * Set all parameters provided within @p cparams into the working @p cctx. + * Note : if modifying parameters during compression (MT mode only), + * note that changes to the .windowLog parameter will be ignored. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()). + * On failure, no parameters are updated. + */ +ZSTDLIB_STATIC_API size_t ZSTD_CCtx_setCParams(ZSTD_CCtx* cctx, ZSTD_compressionParameters cparams); + +/*! ZSTD_CCtx_setFParams() : + * Set all parameters provided within @p fparams into the working @p cctx. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()). + */ +ZSTDLIB_STATIC_API size_t ZSTD_CCtx_setFParams(ZSTD_CCtx* cctx, ZSTD_frameParameters fparams); + +/*! ZSTD_CCtx_setParams() : + * Set all parameters provided within @p params into the working @p cctx. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()). + */ +ZSTDLIB_STATIC_API size_t ZSTD_CCtx_setParams(ZSTD_CCtx* cctx, ZSTD_parameters params); + /*! ZSTD_compress_advanced() : * Note : this function is now DEPRECATED. * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_setParameter() and other parameter setters. * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_compress2") +ZSTDLIB_STATIC_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, - ZSTD_parameters params); + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + ZSTD_parameters params); /*! ZSTD_compress_usingCDict_advanced() : * Note : this function is now DEPRECATED. * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters. * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_compress2 with ZSTD_CCtx_loadDictionary") +ZSTDLIB_STATIC_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, @@ -1725,7 +2025,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo * See the comments on that enum for an explanation of the feature. */ #define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4 -/* Controlled with ZSTD_paramSwitch_e enum. +/* Controlled with ZSTD_ParamSwitch_e enum. * Default is ZSTD_ps_auto. * Set to ZSTD_ps_disable to never compress literals. * Set to ZSTD_ps_enable to always compress literals. (Note: uncompressed literals @@ -1737,11 +2037,6 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo */ #define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5 -/* Tries to fit compressed block size to be around targetCBlockSize. - * No target when targetCBlockSize == 0. - * There is no guarantee on compressed block size (default:0) */ -#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6 - /* User's best guess of source size. * Hint is not valid when srcSizeHint == 0. * There is no guarantee that hint is close to actual source size, @@ -1808,13 +2103,16 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo * Experimental parameter. * Default is 0 == disabled. Set to 1 to enable. * - * Tells the compressor that the ZSTD_inBuffer will ALWAYS be the same - * between calls, except for the modifications that zstd makes to pos (the - * caller must not modify pos). This is checked by the compressor, and - * compression will fail if it ever changes. This means the only flush - * mode that makes sense is ZSTD_e_end, so zstd will error if ZSTD_e_end - * is not used. The data in the ZSTD_inBuffer in the range [src, src + pos) - * MUST not be modified during compression or you will get data corruption. + * Tells the compressor that input data presented with ZSTD_inBuffer + * will ALWAYS be the same between calls. + * Technically, the @src pointer must never be changed, + * and the @pos field can only be updated by zstd. + * However, it's possible to increase the @size field, + * allowing scenarios where more data can be appended after compressions starts. + * These conditions are checked by the compressor, + * and compression will fail if they are not respected. + * Also, data in the ZSTD_inBuffer within the range [src, src + pos) + * MUST not be modified during compression or it will result in data corruption. * * When this flag is enabled zstd won't allocate an input window buffer, * because the user guarantees it can reference the ZSTD_inBuffer until @@ -1822,18 +2120,15 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo * large enough to fit a block (see ZSTD_c_stableOutBuffer). This will also * avoid the memcpy() from the input buffer to the input window buffer. * - * NOTE: ZSTD_compressStream2() will error if ZSTD_e_end is not used. - * That means this flag cannot be used with ZSTD_compressStream(). - * * NOTE: So long as the ZSTD_inBuffer always points to valid memory, using * this flag is ALWAYS memory safe, and will never access out-of-bounds - * memory. However, compression WILL fail if you violate the preconditions. + * memory. However, compression WILL fail if conditions are not respected. * - * WARNING: The data in the ZSTD_inBuffer in the range [dst, dst + pos) MUST - * not be modified during compression or you will get data corruption. This - * is because zstd needs to reference data in the ZSTD_inBuffer to find + * WARNING: The data in the ZSTD_inBuffer in the range [src, src + pos) MUST + * not be modified during compression or it will result in data corruption. + * This is because zstd needs to reference data in the ZSTD_inBuffer to find * matches. Normally zstd maintains its own window buffer for this purpose, - * but passing this flag tells zstd to use the user provided buffer. + * but passing this flag tells zstd to rely on user provided buffer instead. */ #define ZSTD_c_stableInBuffer ZSTD_c_experimentalParam9 @@ -1871,22 +2166,46 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo /* ZSTD_c_validateSequences * Default is 0 == disabled. Set to 1 to enable sequence validation. * - * For use with sequence compression API: ZSTD_compressSequences(). - * Designates whether or not we validate sequences provided to ZSTD_compressSequences() + * For use with sequence compression API: ZSTD_compressSequences*(). + * Designates whether or not provided sequences are validated within ZSTD_compressSequences*() * during function execution. * - * Without validation, providing a sequence that does not conform to the zstd spec will cause - * undefined behavior, and may produce a corrupted block. + * When Sequence validation is disabled (default), Sequences are compressed as-is, + * so they must correct, otherwise it would result in a corruption error. * - * With validation enabled, a if sequence is invalid (see doc/zstd_compression_format.md for + * Sequence validation adds some protection, by ensuring that all values respect boundary conditions. + * If a Sequence is detected invalid (see doc/zstd_compression_format.md for * specifics regarding offset/matchlength requirements) then the function will bail out and * return an error. - * */ #define ZSTD_c_validateSequences ZSTD_c_experimentalParam12 -/* ZSTD_c_useBlockSplitter - * Controlled with ZSTD_paramSwitch_e enum. +/* ZSTD_c_blockSplitterLevel + * note: this parameter only influences the first splitter stage, + * which is active before producing the sequences. + * ZSTD_c_splitAfterSequences controls the next splitter stage, + * which is active after sequence production. + * Note that both can be combined. + * Allowed values are between 0 and ZSTD_BLOCKSPLITTER_LEVEL_MAX included. + * 0 means "auto", which will select a value depending on current ZSTD_c_strategy. + * 1 means no splitting. + * Then, values from 2 to 6 are sorted in increasing cpu load order. + * + * Note that currently the first block is never split, + * to ensure expansion guarantees in presence of incompressible data. + */ +#define ZSTD_BLOCKSPLITTER_LEVEL_MAX 6 +#define ZSTD_c_blockSplitterLevel ZSTD_c_experimentalParam20 + +/* ZSTD_c_splitAfterSequences + * This is a stronger splitter algorithm, + * based on actual sequences previously produced by the selected parser. + * It's also slower, and as a consequence, mostly used for high compression levels. + * While the post-splitter does overlap with the pre-splitter, + * both can nonetheless be combined, + * notably with ZSTD_c_blockSplitterLevel at ZSTD_BLOCKSPLITTER_LEVEL_MAX, + * resulting in higher compression ratio than just one of them. + * * Default is ZSTD_ps_auto. * Set to ZSTD_ps_disable to never use block splitter. * Set to ZSTD_ps_enable to always use block splitter. @@ -1894,10 +2213,10 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo * By default, in ZSTD_ps_auto, the library will decide at runtime whether to use * block splitting based on the compression parameters. */ -#define ZSTD_c_useBlockSplitter ZSTD_c_experimentalParam13 +#define ZSTD_c_splitAfterSequences ZSTD_c_experimentalParam13 /* ZSTD_c_useRowMatchFinder - * Controlled with ZSTD_paramSwitch_e enum. + * Controlled with ZSTD_ParamSwitch_e enum. * Default is ZSTD_ps_auto. * Set to ZSTD_ps_disable to never use row-based matchfinder. * Set to ZSTD_ps_enable to force usage of row-based matchfinder. @@ -1928,6 +2247,80 @@ ZSTDLIB_STATIC_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const vo */ #define ZSTD_c_deterministicRefPrefix ZSTD_c_experimentalParam15 +/* ZSTD_c_prefetchCDictTables + * Controlled with ZSTD_ParamSwitch_e enum. Default is ZSTD_ps_auto. + * + * In some situations, zstd uses CDict tables in-place rather than copying them + * into the working context. (See docs on ZSTD_dictAttachPref_e above for details). + * In such situations, compression speed is seriously impacted when CDict tables are + * "cold" (outside CPU cache). This parameter instructs zstd to prefetch CDict tables + * when they are used in-place. + * + * For sufficiently small inputs, the cost of the prefetch will outweigh the benefit. + * For sufficiently large inputs, zstd will by default memcpy() CDict tables + * into the working context, so there is no need to prefetch. This parameter is + * targeted at a middle range of input sizes, where a prefetch is cheap enough to be + * useful but memcpy() is too expensive. The exact range of input sizes where this + * makes sense is best determined by careful experimentation. + * + * Note: for this parameter, ZSTD_ps_auto is currently equivalent to ZSTD_ps_disable, + * but in the future zstd may conditionally enable this feature via an auto-detection + * heuristic for cold CDicts. + * Use ZSTD_ps_disable to opt out of prefetching under any circumstances. + */ +#define ZSTD_c_prefetchCDictTables ZSTD_c_experimentalParam16 + +/* ZSTD_c_enableSeqProducerFallback + * Allowed values are 0 (disable) and 1 (enable). The default setting is 0. + * + * Controls whether zstd will fall back to an internal sequence producer if an + * external sequence producer is registered and returns an error code. This fallback + * is block-by-block: the internal sequence producer will only be called for blocks + * where the external sequence producer returns an error code. Fallback parsing will + * follow any other cParam settings, such as compression level, the same as in a + * normal (fully-internal) compression operation. + * + * The user is strongly encouraged to read the full Block-Level Sequence Producer API + * documentation (below) before setting this parameter. */ +#define ZSTD_c_enableSeqProducerFallback ZSTD_c_experimentalParam17 + +/* ZSTD_c_maxBlockSize + * Allowed values are between 1KB and ZSTD_BLOCKSIZE_MAX (128KB). + * The default is ZSTD_BLOCKSIZE_MAX, and setting to 0 will set to the default. + * + * This parameter can be used to set an upper bound on the blocksize + * that overrides the default ZSTD_BLOCKSIZE_MAX. It cannot be used to set upper + * bounds greater than ZSTD_BLOCKSIZE_MAX or bounds lower than 1KB (will make + * compressBound() inaccurate). Only currently meant to be used for testing. + */ +#define ZSTD_c_maxBlockSize ZSTD_c_experimentalParam18 + +/* ZSTD_c_repcodeResolution + * This parameter only has an effect if ZSTD_c_blockDelimiters is + * set to ZSTD_sf_explicitBlockDelimiters (may change in the future). + * + * This parameter affects how zstd parses external sequences, + * provided via the ZSTD_compressSequences*() API + * or from an external block-level sequence producer. + * + * If set to ZSTD_ps_enable, the library will check for repeated offsets within + * external sequences, even if those repcodes are not explicitly indicated in + * the "rep" field. Note that this is the only way to exploit repcode matches + * while using compressSequences*() or an external sequence producer, since zstd + * currently ignores the "rep" field of external sequences. + * + * If set to ZSTD_ps_disable, the library will not exploit repeated offsets in + * external sequences, regardless of whether the "rep" field has been set. This + * reduces sequence compression overhead by about 25% while sacrificing some + * compression ratio. + * + * The default value is ZSTD_ps_auto, for which the library will enable/disable + * based on compression level (currently: level<10 disables, level>=10 enables). + */ +#define ZSTD_c_repcodeResolution ZSTD_c_experimentalParam19 +#define ZSTD_c_searchForExternalRepcodes ZSTD_c_experimentalParam19 /* older name */ + + /*! ZSTD_CCtx_getParameter() : * Get the requested compression parameter value, selected by enum ZSTD_cParameter, * and store it into int* value. @@ -2084,7 +2477,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParamete * in the range [dst, dst + pos) MUST not be modified during decompression * or you will get data corruption. * - * When this flags is enabled zstd won't allocate an output buffer, because + * When this flag is enabled zstd won't allocate an output buffer, because * it can write directly to the ZSTD_outBuffer, but it will still allocate * an input buffer large enough to fit any compressed block. This will also * avoid the memcpy() from the internal output buffer to the ZSTD_outBuffer. @@ -2137,6 +2530,33 @@ ZSTDLIB_STATIC_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParamete */ #define ZSTD_d_refMultipleDDicts ZSTD_d_experimentalParam4 +/* ZSTD_d_disableHuffmanAssembly + * Set to 1 to disable the Huffman assembly implementation. + * The default value is 0, which allows zstd to use the Huffman assembly + * implementation if available. + * + * This parameter can be used to disable Huffman assembly at runtime. + * If you want to disable it at compile time you can define the macro + * ZSTD_DISABLE_ASM. + */ +#define ZSTD_d_disableHuffmanAssembly ZSTD_d_experimentalParam5 + +/* ZSTD_d_maxBlockSize + * Allowed values are between 1KB and ZSTD_BLOCKSIZE_MAX (128KB). + * The default is ZSTD_BLOCKSIZE_MAX, and setting to 0 will set to the default. + * + * Forces the decompressor to reject blocks whose content size is + * larger than the configured maxBlockSize. When maxBlockSize is + * larger than the windowSize, the windowSize is used instead. + * This saves memory on the decoder when you know all blocks are small. + * + * This option is typically used in conjunction with ZSTD_c_maxBlockSize. + * + * WARNING: This causes the decoder to reject otherwise valid frames + * that have block sizes larger than the configured maxBlockSize. + */ +#define ZSTD_d_maxBlockSize ZSTD_d_experimentalParam6 + /*! ZSTD_DCtx_setFormat() : * This function is REDUNDANT. Prefer ZSTD_DCtx_setParameter(). @@ -2145,6 +2565,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParamete * such ZSTD_f_zstd1_magicless for example. * @return : 0, or an error code (which can be tested using ZSTD_isError()). */ ZSTD_DEPRECATED("use ZSTD_DCtx_setParameter() instead") +ZSTDLIB_STATIC_API size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format); /*! ZSTD_decompressStream_simpleArgs() : @@ -2181,6 +2602,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_decompressStream_simpleArgs ( * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); @@ -2198,17 +2620,15 @@ size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /*! ZSTD_initCStream_advanced() : - * This function is DEPRECATED, and is approximately equivalent to: + * This function is DEPRECATED, and is equivalent to: * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); - * // Pseudocode: Set each zstd parameter and leave the rest as-is. - * for ((param, value) : params) { - * ZSTD_CCtx_setParameter(zcs, param, value); - * } + * ZSTD_CCtx_setParams(zcs, params); * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); * @@ -2218,6 +2638,7 @@ size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, ZSTD_parameters params, @@ -2232,15 +2653,13 @@ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset and ZSTD_CCtx_refCDict, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /*! ZSTD_initCStream_usingCDict_advanced() : - * This function is DEPRECATED, and is approximately equivalent to: + * This function is DEPRECATED, and is equivalent to: * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); - * // Pseudocode: Set each zstd frame parameter and leave the rest as-is. - * for ((fParam, value) : fParams) { - * ZSTD_CCtx_setParameter(zcs, fParam, value); - * } + * ZSTD_CCtx_setFParams(zcs, fParams); * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); * ZSTD_CCtx_refCDict(zcs, cdict); * @@ -2250,6 +2669,7 @@ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset and ZSTD_CCtx_refCDict, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, @@ -2264,7 +2684,7 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, * explicitly specified. * * start a new frame, using same parameters from previous frame. - * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. + * This is typically useful to skip dictionary loading stage, since it will reuse it in-place. * Note that zcs must be init at least once before using ZSTD_resetCStream(). * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. @@ -2274,6 +2694,7 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions") +ZSTDLIB_STATIC_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); @@ -2319,8 +2740,8 @@ ZSTDLIB_STATIC_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); * ZSTD_DCtx_loadDictionary(zds, dict, dictSize); * * note: no dictionary will be used if dict == NULL or dictSize < 8 - * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ +ZSTD_DEPRECATED("use ZSTD_DCtx_reset + ZSTD_DCtx_loadDictionary, see zstd.h for detailed instructions") ZSTDLIB_STATIC_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /*! @@ -2330,8 +2751,8 @@ ZSTDLIB_STATIC_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const vo * ZSTD_DCtx_refDDict(zds, ddict); * * note : ddict is referenced, it must outlive decompression session - * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ +ZSTD_DEPRECATED("use ZSTD_DCtx_reset + ZSTD_DCtx_refDDict, see zstd.h for detailed instructions") ZSTDLIB_STATIC_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /*! @@ -2339,18 +2760,202 @@ ZSTDLIB_STATIC_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const Z * * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); * - * re-use decompression parameters from previous init; saves dictionary loading - * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + * reuse decompression parameters from previous init; saves dictionary loading */ +ZSTD_DEPRECATED("use ZSTD_DCtx_reset, see zstd.h for detailed instructions") ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); +/* ********************* BLOCK-LEVEL SEQUENCE PRODUCER API ********************* + * + * *** OVERVIEW *** + * The Block-Level Sequence Producer API allows users to provide their own custom + * sequence producer which libzstd invokes to process each block. The produced list + * of sequences (literals and matches) is then post-processed by libzstd to produce + * valid compressed blocks. + * + * This block-level offload API is a more granular complement of the existing + * frame-level offload API compressSequences() (introduced in v1.5.1). It offers + * an easier migration story for applications already integrated with libzstd: the + * user application continues to invoke the same compression functions + * ZSTD_compress2() or ZSTD_compressStream2() as usual, and transparently benefits + * from the specific advantages of the external sequence producer. For example, + * the sequence producer could be tuned to take advantage of known characteristics + * of the input, to offer better speed / ratio, or could leverage hardware + * acceleration not available within libzstd itself. + * + * See contrib/externalSequenceProducer for an example program employing the + * Block-Level Sequence Producer API. + * + * *** USAGE *** + * The user is responsible for implementing a function of type + * ZSTD_sequenceProducer_F. For each block, zstd will pass the following + * arguments to the user-provided function: + * + * - sequenceProducerState: a pointer to a user-managed state for the sequence + * producer. + * + * - outSeqs, outSeqsCapacity: an output buffer for the sequence producer. + * outSeqsCapacity is guaranteed >= ZSTD_sequenceBound(srcSize). The memory + * backing outSeqs is managed by the CCtx. + * + * - src, srcSize: an input buffer for the sequence producer to parse. + * srcSize is guaranteed to be <= ZSTD_BLOCKSIZE_MAX. + * + * - dict, dictSize: a history buffer, which may be empty, which the sequence + * producer may reference as it parses the src buffer. Currently, zstd will + * always pass dictSize == 0 into external sequence producers, but this will + * change in the future. + * + * - compressionLevel: a signed integer representing the zstd compression level + * set by the user for the current operation. The sequence producer may choose + * to use this information to change its compression strategy and speed/ratio + * tradeoff. Note: the compression level does not reflect zstd parameters set + * through the advanced API. + * + * - windowSize: a size_t representing the maximum allowed offset for external + * sequences. Note that sequence offsets are sometimes allowed to exceed the + * windowSize if a dictionary is present, see doc/zstd_compression_format.md + * for details. + * + * The user-provided function shall return a size_t representing the number of + * sequences written to outSeqs. This return value will be treated as an error + * code if it is greater than outSeqsCapacity. The return value must be non-zero + * if srcSize is non-zero. The ZSTD_SEQUENCE_PRODUCER_ERROR macro is provided + * for convenience, but any value greater than outSeqsCapacity will be treated as + * an error code. + * + * If the user-provided function does not return an error code, the sequences + * written to outSeqs must be a valid parse of the src buffer. Data corruption may + * occur if the parse is not valid. A parse is defined to be valid if the + * following conditions hold: + * - The sum of matchLengths and literalLengths must equal srcSize. + * - All sequences in the parse, except for the final sequence, must have + * matchLength >= ZSTD_MINMATCH_MIN. The final sequence must have + * matchLength >= ZSTD_MINMATCH_MIN or matchLength == 0. + * - All offsets must respect the windowSize parameter as specified in + * doc/zstd_compression_format.md. + * - If the final sequence has matchLength == 0, it must also have offset == 0. + * + * zstd will only validate these conditions (and fail compression if they do not + * hold) if the ZSTD_c_validateSequences cParam is enabled. Note that sequence + * validation has a performance cost. + * + * If the user-provided function returns an error, zstd will either fall back + * to an internal sequence producer or fail the compression operation. The user can + * choose between the two behaviors by setting the ZSTD_c_enableSeqProducerFallback + * cParam. Fallback compression will follow any other cParam settings, such as + * compression level, the same as in a normal compression operation. + * + * The user shall instruct zstd to use a particular ZSTD_sequenceProducer_F + * function by calling + * ZSTD_registerSequenceProducer(cctx, + * sequenceProducerState, + * sequenceProducer) + * This setting will persist until the next parameter reset of the CCtx. + * + * The sequenceProducerState must be initialized by the user before calling + * ZSTD_registerSequenceProducer(). The user is responsible for destroying the + * sequenceProducerState. + * + * *** LIMITATIONS *** + * This API is compatible with all zstd compression APIs which respect advanced parameters. + * However, there are three limitations: + * + * First, the ZSTD_c_enableLongDistanceMatching cParam is not currently supported. + * COMPRESSION WILL FAIL if it is enabled and the user tries to compress with a block-level + * external sequence producer. + * - Note that ZSTD_c_enableLongDistanceMatching is auto-enabled by default in some + * cases (see its documentation for details). Users must explicitly set + * ZSTD_c_enableLongDistanceMatching to ZSTD_ps_disable in such cases if an external + * sequence producer is registered. + * - As of this writing, ZSTD_c_enableLongDistanceMatching is disabled by default + * whenever ZSTD_c_windowLog < 128MB, but that's subject to change. Users should + * check the docs on ZSTD_c_enableLongDistanceMatching whenever the Block-Level Sequence + * Producer API is used in conjunction with advanced settings (like ZSTD_c_windowLog). + * + * Second, history buffers are not currently supported. Concretely, zstd will always pass + * dictSize == 0 to the external sequence producer (for now). This has two implications: + * - Dictionaries are not currently supported. Compression will *not* fail if the user + * references a dictionary, but the dictionary won't have any effect. + * - Stream history is not currently supported. All advanced compression APIs, including + * streaming APIs, work with external sequence producers, but each block is treated as + * an independent chunk without history from previous blocks. + * + * Third, multi-threading within a single compression is not currently supported. In other words, + * COMPRESSION WILL FAIL if ZSTD_c_nbWorkers > 0 and an external sequence producer is registered. + * Multi-threading across compressions is fine: simply create one CCtx per thread. + * + * Long-term, we plan to overcome all three limitations. There is no technical blocker to + * overcoming them. It is purely a question of engineering effort. + */ + +#define ZSTD_SEQUENCE_PRODUCER_ERROR ((size_t)(-1)) + +typedef size_t (*ZSTD_sequenceProducer_F) ( + void* sequenceProducerState, + ZSTD_Sequence* outSeqs, size_t outSeqsCapacity, + const void* src, size_t srcSize, + const void* dict, size_t dictSize, + int compressionLevel, + size_t windowSize +); + +/*! ZSTD_registerSequenceProducer() : + * Instruct zstd to use a block-level external sequence producer function. + * + * The sequenceProducerState must be initialized by the caller, and the caller is + * responsible for managing its lifetime. This parameter is sticky across + * compressions. It will remain set until the user explicitly resets compression + * parameters. + * + * Sequence producer registration is considered to be an "advanced parameter", + * part of the "advanced API". This means it will only have an effect on compression + * APIs which respect advanced parameters, such as compress2() and compressStream2(). + * Older compression APIs such as compressCCtx(), which predate the introduction of + * "advanced parameters", will ignore any external sequence producer setting. + * + * The sequence producer can be "cleared" by registering a NULL function pointer. This + * removes all limitations described above in the "LIMITATIONS" section of the API docs. + * + * The user is strongly encouraged to read the full API documentation (above) before + * calling this function. */ +ZSTDLIB_STATIC_API void +ZSTD_registerSequenceProducer( + ZSTD_CCtx* cctx, + void* sequenceProducerState, + ZSTD_sequenceProducer_F sequenceProducer +); + +/*! ZSTD_CCtxParams_registerSequenceProducer() : + * Same as ZSTD_registerSequenceProducer(), but operates on ZSTD_CCtx_params. + * This is used for accurate size estimation with ZSTD_estimateCCtxSize_usingCCtxParams(), + * which is needed when creating a ZSTD_CCtx with ZSTD_initStaticCCtx(). + * + * If you are using the external sequence producer API in a scenario where ZSTD_initStaticCCtx() + * is required, then this function is for you. Otherwise, you probably don't need it. + * + * See tests/zstreamtest.c for example usage. */ +ZSTDLIB_STATIC_API void +ZSTD_CCtxParams_registerSequenceProducer( + ZSTD_CCtx_params* params, + void* sequenceProducerState, + ZSTD_sequenceProducer_F sequenceProducer +); + + /* ******************************************************************* -* Buffer-less and synchronous inner streaming functions +* Buffer-less and synchronous inner streaming functions (DEPRECATED) +* +* This API is deprecated, and will be removed in a future version. +* It allows streaming (de)compression with user allocated buffers. +* However, it is hard to use, and not as well tested as the rest of +* our API. * -* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. -* But it's also a complex one, with several restrictions, documented below. -* Prefer normal streaming API for an easier experience. +* Please use the normal streaming API instead: ZSTD_compressStream2, +* and ZSTD_decompressStream. +* If there is functionality that you need, but it doesn't provide, +* please open an issue on our GitHub. ********************************************************************* */ /* @@ -2358,11 +2963,10 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); A ZSTD_CCtx object is required to track streaming operations. Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource. - ZSTD_CCtx object can be re-used multiple times within successive compression operations. + ZSTD_CCtx object can be reused multiple times within successive compression operations. Start by initializing a context. Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression. - It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx() Then, consume your input using ZSTD_compressContinue(). There are some important considerations to keep in mind when using this advanced function : @@ -2380,39 +2984,49 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. - `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. + `ZSTD_CCtx` object can be reused (ZSTD_compressBegin()) to compress again. */ /*===== Buffer-less streaming compression functions =====*/ +ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); +ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); +ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /*< note: fails if cdict==NULL */ -ZSTDLIB_STATIC_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /*< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */ +ZSTD_DEPRECATED("This function will likely be removed in a future release. It is misleading and has very limited utility.") +ZSTDLIB_STATIC_API +size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /*< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */ + +ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTD_DEPRECATED("The buffer-less API is deprecated in favor of the normal streaming API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); /* The ZSTD_compressBegin_advanced() and ZSTD_compressBegin_usingCDict_advanced() are now DEPRECATED and will generate a compiler warning */ ZSTD_DEPRECATED("use advanced API to access custom parameters") +ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /*< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */ ZSTD_DEPRECATED("use advanced API to access custom parameters") +ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */ /* Buffer-less streaming decompression (synchronous mode) A ZSTD_DCtx object is required to track streaming operations. Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it. - A ZSTD_DCtx object can be re-used multiple times. + A ZSTD_DCtx object can be reused multiple times. First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. Data fragment must be large enough to ensure successful decoding. `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. - @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. - >0 : `srcSize` is too small, please provide at least @result bytes on next attempt. + result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. + >0 : `srcSize` is too small, please provide at least result bytes on next attempt. errorCode, which can be tested using ZSTD_isError(). - It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, + It fills a ZSTD_FrameHeader structure with important information to correctly decode the frame, such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. As a consequence, check that values remain within valid application range. @@ -2428,7 +3042,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_ The most memory efficient way is to use a round buffer of sufficient size. Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), - which can @return an error code if required value is too large for current system (in 32-bits mode). + which can return an error code if required value is too large for current system (in 32-bits mode). In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, up to the moment there is not enough room left in the buffer to guarantee decoding another full block, which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. @@ -2448,7 +3062,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_ ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue(). ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail. - @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). + result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. It can also be an error code, which can be tested with ZSTD_isError(). @@ -2471,27 +3085,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_ */ /*===== Buffer-less streaming decompression functions =====*/ -typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; -typedef struct { - unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ - unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ - unsigned blockSizeMax; - ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ - unsigned headerSize; - unsigned dictID; - unsigned checksumFlag; -} ZSTD_frameHeader; -/*! ZSTD_getFrameHeader() : - * decode Frame Header, or requires larger `srcSize`. - * @return : 0, `zfhPtr` is correctly filled, - * >0, `srcSize` is too small, value is wanted `srcSize` amount, - * or an error code, which can be tested using ZSTD_isError() */ -ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); /*< doesn't consume input */ -/*! ZSTD_getFrameHeader_advanced() : - * same as ZSTD_getFrameHeader(), - * with added capability to select a format (like ZSTD_f_zstd1_magicless) */ -ZSTDLIB_STATIC_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format); ZSTDLIB_STATIC_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize); /*< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */ ZSTDLIB_STATIC_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); @@ -2502,6 +3096,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); ZSTDLIB_STATIC_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); /* misc */ +ZSTD_DEPRECATED("This function will likely be removed in the next minor release. It is misleading and has very limited utility.") ZSTDLIB_STATIC_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); @@ -2509,11 +3104,23 @@ ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); -/* ============================ */ -/* Block level API */ -/* ============================ */ +/* ========================================= */ +/* Block level API (DEPRECATED) */ +/* ========================================= */ /*! + + This API is deprecated in favor of the regular compression API. + You can get the frame header down to 2 bytes by setting: + - ZSTD_c_format = ZSTD_f_zstd1_magicless + - ZSTD_c_contentSizeFlag = 0 + - ZSTD_c_checksumFlag = 0 + - ZSTD_c_dictIDFlag = 0 + + This API is not as well tested as our normal API, so we recommend not using it. + We will be removing it in a future version. If the normal API doesn't provide + the functionality you need, please open a GitHub issue. + Block functions produce and decode raw zstd blocks, without frame metadata. Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes). But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes. @@ -2524,7 +3131,6 @@ ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); - It is necessary to init context before starting + compression : any ZSTD_compressBegin*() variant, including with dictionary + decompression : any ZSTD_decompressBegin*() variant, including with dictionary - + copyCCtx() and copyDCtx() can be used too - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB + If input is larger than a block size, it's necessary to split input data into multiple blocks + For inputs larger than a single block, consider using regular ZSTD_compress() instead. @@ -2541,11 +3147,14 @@ ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); */ /*===== Raw zstd block functions =====*/ +ZSTD_DEPRECATED("The block API is deprecated in favor of the normal compression API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx); +ZSTD_DEPRECATED("The block API is deprecated in favor of the normal compression API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTD_DEPRECATED("The block API is deprecated in favor of the normal compression API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTD_DEPRECATED("The block API is deprecated in favor of the normal compression API. See docs.") ZSTDLIB_STATIC_API size_t ZSTD_insertBlock (ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /*< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression. */ #endif /* ZSTD_H_ZSTD_STATIC_LINKING_ONLY */ - |